diff --git "a/vocab/gpt_neox_chinese_v1/to_v2/word_count.corpus.sort_by_count.jsonl" "b/vocab/gpt_neox_chinese_v1/to_v2/word_count.corpus.sort_by_count.jsonl" deleted file mode 100644--- "a/vocab/gpt_neox_chinese_v1/to_v2/word_count.corpus.sort_by_count.jsonl" +++ /dev/null @@ -1,54610 +0,0 @@ -{"id": 19979, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 44919, "token": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n "} -{"id": 7421, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 36393, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 20170, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 25835, "token": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n "} -{"id": 2763, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 27728, "token": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n "} -{"id": 8369, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 48303, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 49051, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 44652, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 47666, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 43833, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 41727, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 39454, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 37505, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 37242, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 31617, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 37992, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 40960, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 37129, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 36732, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 36321, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 11261, "token": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n "} -{"id": 1085, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 28272, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 26625, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 24245, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 25878, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 25511, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 24262, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 24546, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 5980, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 43068, "token": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n "} -{"id": 23913, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 24356, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 22686, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 22177, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 36411, "token": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n "} -{"id": 47464, "token": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n "} -{"id": 21336, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 19617, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 46500, "token": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n "} -{"id": 18411, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 39992, "token": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n "} -{"id": 29162, "token": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n "} -{"id": 17677, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 16727, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 48513, "token": "\u010a\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n\n "} -{"id": 41642, "token": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n "} -{"id": 17067, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 38531, "token": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n "} -{"id": 16085, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 39229, "token": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n "} -{"id": 22672, "token": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n "} -{"id": 15533, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 14921, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 37974, "token": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n "} -{"id": 48523, "token": "\u010a\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n\n "} -{"id": 33634, "token": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n "} -{"id": 14686, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 33640, "token": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n "} -{"id": 13075, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 17240, "token": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n "} -{"id": 13582, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 13475, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 29942, "token": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n "} -{"id": 13873, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 27323, "token": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n "} -{"id": 25927, "token": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n "} -{"id": 13113, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 14222, "token": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n "} -{"id": 13095, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 29424, "token": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n "} -{"id": 37570, "token": "\u01200000000000000000000000000000000000", "merges": "\u012000000000000000000000000000000000 00", "raw_count": 0, "count": 0, "decode_str": " 0000000000000000000000000000000000"} -{"id": 12375, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 8533, "token": "\u010a\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u010a \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n\n "} -{"id": 12703, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 26213, "token": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120", "raw_count": 0, "count": 0, "decode_str": "\n "} -{"id": 3263, "token": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n "} -{"id": 12849, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 47729, "token": "\u010a\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u010a \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n\n "} -{"id": 542, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 41606, "token": "\u00c3\u0125\u00c3\u0124\u00c3\u0125\u00c3\u0124\u00c3\u0125\u00c3\u0124\u00c3\u0125\u00c3\u0124\u00c3\u0125\u00c3\u0124\u00c3\u0125\u00c3\u0124\u00c3\u0125\u00c3\u0124\u00c3\u0125\u00c3\u0124", "merges": "\u00c3\u0125\u00c3\u0124\u00c3\u0125\u00c3\u0124\u00c3\u0125\u00c3\u0124\u00c3\u0125\u00c3\u0124 \u00c3\u0125\u00c3\u0124\u00c3\u0125\u00c3\u0124\u00c3\u0125\u00c3\u0124\u00c3\u0125\u00c3\u0124", "raw_count": 0, "count": 0, "decode_str": "\u00c3\u00c2\u00c3\u00c2\u00c3\u00c2\u00c3\u00c2\u00c3\u00c2\u00c3\u00c2\u00c3\u00c2\u00c3\u00c2"} -{"id": 9740, "token": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n "} -{"id": 10033, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 22597, "token": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n "} -{"id": 10204, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 18774, "token": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n "} -{"id": 42897, "token": "\u010a\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u010a \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n\n "} -{"id": 9531, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 20102, "token": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n "} -{"id": 6596, "token": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n "} -{"id": 9219, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 8044, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 20380, "token": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n "} -{"id": 16310, "token": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n "} -{"id": 7828, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 46336, "token": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n \n "} -{"id": 18118, "token": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n "} -{"id": 7643, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 33528, "token": "\u010d\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010d \u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\r\n "} -{"id": 30462, "token": "\u010a\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u010a \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n\n "} -{"id": 1636, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 4119, "token": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n "} -{"id": 5640, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 17482, "token": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n "} -{"id": 5808, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 12826, "token": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n "} -{"id": 48458, "token": "\u010a\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u010a \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n\n "} -{"id": 5144, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 19738, "token": "\u010a\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u010a \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n\n "} -{"id": 14243, "token": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n "} -{"id": 21981, "token": "\u010d\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010d \u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\r\n "} -{"id": 5121, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 2580, "token": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n "} -{"id": 4333, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 50133, "token": "\u010a\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u010a \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n\n "} -{"id": 15518, "token": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n "} -{"id": 4643, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 8940, "token": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120", "raw_count": 0, "count": 0, "decode_str": "\n "} -{"id": 42010, "token": "\u0120BytePtrFromString", "merges": "\u0120Byte PtrFromString", "raw_count": 0, "count": 0, "decode_str": " BytePtrFromString"} -{"id": 4356, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 1188, "token": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n "} -{"id": 13286, "token": "\u010d\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010d \u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\r\n "} -{"id": 24675, "token": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n \n "} -{"id": 11475, "token": "\u010a\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u010a \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n\n "} -{"id": 3990, "token": "\u0120\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120 \u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " \n "} -{"id": 349, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 26868, "token": "\u00c3\u0125\u00c3\u0124\u00c3\u0125\u00c3\u0124\u00c3\u0125\u00c3\u0124\u00c3\u0125\u00c3\u0124", "merges": "\u00c3\u0125\u00c3\u0124\u00c3\u0125\u00c3\u0124 \u00c3\u0125\u00c3\u0124\u00c3\u0125\u00c3\u0124", "raw_count": 0, "count": 0, "decode_str": "\u00c3\u00c2\u00c3\u00c2\u00c3\u00c2\u00c3\u00c2"} -{"id": 1015, "token": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n "} -{"id": 39922, "token": "1451450014514500", "merges": "14514500 14514500", "raw_count": 0, "count": 0, "decode_str": "1451450014514500"} -{"id": 25766, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u010a\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u010a\u0120", "raw_count": 0, "count": 0, "decode_str": " \n "} -{"id": 47034, "token": "\u010a\u0120\u010a\u0120\u010a\u0120\u010a\u0120\u010a\u0120\u010a\u0120\u010a\u0120\u010a\u0120", "merges": "\u010a\u0120\u010a\u0120\u010a\u0120\u010a\u0120 \u010a\u0120\u010a\u0120\u010a\u0120\u010a\u0120", "raw_count": 0, "count": 0, "decode_str": "\n \n \n \n \n \n \n \n "} -{"id": 30871, "token": "\u010a\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u010a \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n\n "} -{"id": 2857, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 9660, "token": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n "} -{"id": 31072, "token": "\u010a\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u010a \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n\n "} -{"id": 38827, "token": "\u010d\u010a\u010d\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010d\u010a\u010d \u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\r\n\r\n "} -{"id": 38411, "token": "\u010d\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010d \u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\r\n "} -{"id": 3380, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 4945, "token": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n "} -{"id": 44782, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u010a\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u010a\u0120", "raw_count": 0, "count": 0, "decode_str": " \n "} -{"id": 32972, "token": "\u010a\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u010a \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n\n "} -{"id": 3203, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 7833, "token": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n "} -{"id": 41557, "token": "PtrFromString", "merges": "Ptr FromString", "raw_count": 0, "count": 0, "decode_str": "PtrFromString"} -{"id": 21024, "token": "\u0120\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120 \u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " \n "} -{"id": 6066, "token": "\u010a\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u010a \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n\n "} -{"id": 8173, "token": "\u010d\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010d \u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\r\n "} -{"id": 23893, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u010a\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u010a\u0120", "raw_count": 0, "count": 0, "decode_str": " \n "} -{"id": 3059, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 935, "token": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n "} -{"id": 34229, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u010a\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u010a\u0120", "raw_count": 0, "count": 0, "decode_str": " \n "} -{"id": 36209, "token": "\u010a\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u010a \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n\n "} -{"id": 1932, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 37406, "token": "medscimonit", "merges": "medsc imonit", "raw_count": 0, "count": 0, "decode_str": "medscimonit"} -{"id": 30371, "token": "marinedrugs", "merges": "marined rugs", "raw_count": 0, "count": 0, "decode_str": "marinedrugs"} -{"id": 46209, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u010a\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u010a\u0120", "raw_count": 0, "count": 0, "decode_str": " \n "} -{"id": 17091, "token": "\u010a\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u010a \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n\n "} -{"id": 48581, "token": "\u0120\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120 \u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " \n "} -{"id": 45659, "token": "\u0120Spacewatch", "merges": "\u0120Space watch", "raw_count": 0, "count": 0, "decode_str": " Spacewatch"} -{"id": 41499, "token": "\u010d\u010d\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010d\u010d \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\r\r "} -{"id": 33463, "token": "\u0120Parlamento", "merges": "\u0120Parl amento", "raw_count": 0, "count": 0, "decode_str": " Parlamento"} -{"id": 7633, "token": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n "} -{"id": 23883, "token": "\u010d\u010a\u010d\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010d\u010a\u010d \u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\r\n\r\n "} -{"id": 18761, "token": "\u010d\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010d \u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\r\n "} -{"id": 2674, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 2463, "token": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120", "raw_count": 0, "count": 0, "decode_str": "\n "} -{"id": 49176, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u010a\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u010a\u0120", "raw_count": 0, "count": 0, "decode_str": " \n "} -{"id": 21120, "token": "\u010a\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u010a \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n\n "} -{"id": 38568, "token": "\u0120Appellees", "merges": "\u0120App ellees", "raw_count": 0, "count": 0, "decode_str": " Appellees"} -{"id": 47827, "token": "mathchoice", "merges": "math choice", "raw_count": 0, "count": 0, "decode_str": "mathchoice"} -{"id": 47147, "token": "\u010a\u010a\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u010a \u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n\n\n "} -{"id": 47231, "token": "\u0120\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120 \u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " \n "} -{"id": 33235, "token": "\u010d\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010d \u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\r\n "} -{"id": 2286, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 576, "token": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a \u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n "} -{"id": 45536, "token": "\u0120Euroopan", "merges": "\u0120Euro opan", "raw_count": 0, "count": 0, "decode_str": " Euroopan"} -{"id": 2707, "token": "\u010a\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u010a \u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n\n "} -{"id": 28912, "token": "^\u00e2\u012a\u0134/\u00e2\u012a\u0134^", "merges": "^\u00e2\u012a\u0134/\u00e2\u012a\u0134 ^", "raw_count": 0, "count": 0, "decode_str": "^\u2212/\u2212^"} -{"id": 45437, "token": "\u0120AFFIRMED", "merges": "\u0120A FFIRMED", "raw_count": 0, "count": 0, "decode_str": " AFFIRMED"} -{"id": 15398, "token": "\u010a\u0120\u0120\u0120\u0120\u010a\u0120\u0120\u0120", "merges": "\u010a\u0120\u0120\u0120\u0120 \u010a\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n \n "} -{"id": 43566, "token": "\u010a\u0120\u0120\u00c2\u0142\u00c2\u0142\u00c2\u0142", "merges": "\u010a\u0120\u0120 \u00c2\u0142\u00c2\u0142\u00c2\u0142", "raw_count": 0, "count": 0, "decode_str": "\n \u00a0\u00a0\u00a0"} -{"id": 13300, "token": "\u0120\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120 \u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " \n "} -{"id": 37293, "token": "\u010a\u010a\u010a\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u010a\u010a \u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n\n\n "} -{"id": 5452, "token": "\u010d\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010d \u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\r\n "} -{"id": 22702, "token": "\u0120errnoErr", "merges": "\u0120errno Err", "raw_count": 0, "count": 0, "decode_str": " errnoErr"} -{"id": 47245, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u010a\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120 \u010a\u0120", "raw_count": 0, "count": 0, "decode_str": " \n "} -{"id": 286, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120 \u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 648, "token": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a \u0120\u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n "} -{"id": 39743, "token": "14514500", "merges": "14514 500", "raw_count": 0, "count": 0, "decode_str": "14514500"} -{"id": 25395, "token": "\u010a\u0120\u010a\u0120\u010a\u0120\u010a\u0120", "merges": "\u010a\u0120\u010a\u0120 \u010a\u0120\u010a\u0120", "raw_count": 0, "count": 0, "decode_str": "\n \n \n \n "} -{"id": 17030, "token": "\u00c3\u0125\u00c3\u0124\u00c3\u0125\u00c3\u0124", "merges": "\u00c3\u0125\u00c3\u0124 \u00c3\u0125\u00c3\u0124", "raw_count": 0, "count": 0, "decode_str": "\u00c3\u00c2\u00c3\u00c2"} -{"id": 23286, "token": "^\u00e2\u012a\u0134/\u00e2\u012a\u0134", "merges": "^\u00e2\u012a\u0134 /\u00e2\u012a\u0134", "raw_count": 0, "count": 0, "decode_str": "^\u2212/\u2212"} -{"id": 48018, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u010a\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120\u0120 \u010a\u0120", "raw_count": 0, "count": 0, "decode_str": " \n "} -{"id": 25330, "token": "\u010a\u010a\u010a\u010a\u010a\u010a\u010a\u010a", "merges": "\u010a\u010a\u010a\u010a \u010a\u010a\u010a\u010a", "raw_count": 0, "count": 0, "decode_str": "\n\n\n\n\n\n\n\n"} -{"id": 45936, "token": "\u010a\u010a\u010a\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u010a \u010a\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n\n\n "} -{"id": 6530, "token": "\u010a\u010a\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u010a \u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n\n "} -{"id": 35088, "token": "...\\...\\", "merges": "...\\ ...\\", "raw_count": 0, "count": 0, "decode_str": "...\\...\\"} -{"id": 46045, "token": "brainsci", "merges": "brains ci", "raw_count": 0, "count": 0, "decode_str": "brainsci"} -{"id": 37682, "token": "\u010a\u010c\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u010c \u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n\f "} -{"id": 41689, "token": "\u010d\u010a\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010d\u010a \u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\r\n "} -{"id": 44863, "token": "\u0120\u010a\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u010a \u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " \n "} -{"id": 467, "token": "\u0120\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120 \u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 43226, "token": "\u00e2\u012a\u0134/\u00e2\u012a\u0134", "merges": "\u00e2\u012a\u0134 /\u00e2\u012a\u0134", "raw_count": 0, "count": 0, "decode_str": "\u2212/\u2212"} -{"id": 42820, "token": "\u010a\u0109\u0109\u0109\u0120\u0120\u0120", "merges": "\u010a\u0109\u0109\u0109 \u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n\t\t\t "} -{"id": 17293, "token": "\u010d\u010a\u010d\u010a\u0120\u0120\u0120", "merges": "\u010d\u010a \u010d\u010a\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\r\n\r\n "} -{"id": 39472, "token": "\u010a\u0109\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u0109 \u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n\t "} -{"id": 8431, "token": "\u010d\u010a\u0120\u0120\u0120\u0120\u0120", "merges": "\u010d \u010a\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\r\n "} -{"id": 3893, "token": "\u010a\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a \u0120\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n "} -{"id": 22937, "token": "\u0120\u010a\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120 \u010a\u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " \n "} -{"id": 35451, "token": "\u010a\u010a\u010a\u010a\u010a\u010a\u010a", "merges": "\u010a\u010a\u010a\u010a \u010a\u010a\u010a", "raw_count": 0, "count": 0, "decode_str": "\n\n\n\n\n\n\n"} -{"id": 43993, "token": "\u0120\u0120\u0120\u0120\u0120\u010a\u0120", "merges": "\u0120\u0120\u0120\u0120\u0120 \u010a\u0120", "raw_count": 0, "count": 0, "decode_str": " \n "} -{"id": 23734, "token": "\u0120[****,", "merges": "\u0120[ ****,", "raw_count": 0, "count": 0, "decode_str": " [****,"} -{"id": 42595, "token": "\u010d\u010a\u0109\u0109\u0109\u0109\u0109", "merges": "\u010d \u010a\u0109\u0109\u0109\u0109\u0109", "raw_count": 0, "count": 0, "decode_str": "\r\n\t\t\t\t\t"} -{"id": 33835, "token": "doibase", "merges": "do ibase", "raw_count": 0, "count": 0, "decode_str": "doibase"} -{"id": 5814, "token": "\u010a\u010a\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a\u010a \u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n\n "} -{"id": 979, "token": "\u0120\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120 \u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 1043, "token": "\u010a\u0120\u0120\u0120\u0120\u0120", "merges": "\u010a \u0120\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n "} -{"id": 48471, "token": ":**]{}", "merges": ":** ]{}", "raw_count": 0, "count": 0, "decode_str": ":**]{}"} -{"id": 43134, "token": "\u0120()]{}", "merges": "\u0120() ]{}", "raw_count": 0, "count": 0, "decode_str": " ()]{}"} -{"id": 25416, "token": "[\\*](#", "merges": "[ \\*](#", "raw_count": 0, "count": 0, "decode_str": "[\\*](#"} -{"id": 36487, "token": ".**]{}", "merges": ".** ]{}", "raw_count": 0, "count": 0, "decode_str": ".**]{}"} -{"id": 46924, "token": "obbsee", "merges": "obb see", "raw_count": 0, "count": 0, "decode_str": "obbsee"} -{"id": 39900, "token": "\u010a\u010a\u0109\u0109\u0109\u0109", "merges": "\u010a\u010a \u0109\u0109\u0109\u0109", "raw_count": 0, "count": 0, "decode_str": "\n\n\t\t\t\t"} -{"id": 41305, "token": "]{}\\_[", "merges": "]{}\\ _[", "raw_count": 0, "count": 0, "decode_str": "]{}\\_["} -{"id": 11763, "token": "ijerph", "merges": "ijer ph", "raw_count": 0, "count": 0, "decode_str": "ijerph"} -{"id": 26046, "token": "\u010a\u010a\u010a\u0120\u0120\u0120", "merges": "\u010a\u010a \u010a\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n\n\n "} -{"id": 46468, "token": "\\])]{}", "merges": "\\]) ]{}", "raw_count": 0, "count": 0, "decode_str": "\\])]{}"} -{"id": 34761, "token": "\u0120()](\\", "merges": "\u0120() ](\\", "raw_count": 0, "count": 0, "decode_str": " ()](\\"} -{"id": 28655, "token": "\u010a\u0109\u0109\u0120\u0120\u0120", "merges": "\u010a\u0109\u0109 \u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n\t\t "} -{"id": 6257, "token": "**]{},", "merges": "** ]{},", "raw_count": 0, "count": 0, "decode_str": "**]{},"} -{"id": 46597, "token": "\u0120${{{\\", "merges": "\u0120${ {{\\", "raw_count": 0, "count": 0, "decode_str": " ${{{\\"} -{"id": 10072, "token": "\u010a\u010a\u0120\u0120\u0120\u0120", "merges": "\u010a\u010a \u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n\n "} -{"id": 27401, "token": "\u0120\u010a\u0120\u0120\u0120\u0120", "merges": "\u0120 \u010a\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " \n "} -{"id": 29223, "token": "\u010a\u0120\u0120\u00e2\u0122\u0125", "merges": "\u010a\u0120\u0120 \u00e2\u0122\u0125", "raw_count": 0, "count": 0, "decode_str": "\n \u2003"} -{"id": 38710, "token": "\u0120\\*\\**", "merges": "\u0120\\* \\**", "raw_count": 0, "count": 0, "decode_str": " \\*\\**"} -{"id": 44162, "token": "]{}\\^[", "merges": "]{}\\ ^[", "raw_count": 0, "count": 0, "decode_str": "]{}\\^["} -{"id": 43782, "token": ".^\\[[@", "merges": ". ^\\[[@", "raw_count": 0, "count": 0, "decode_str": ".^\\[[@"} -{"id": 27720, "token": ".*]{},", "merges": ".* ]{},", "raw_count": 0, "count": 0, "decode_str": ".*]{},"} -{"id": 28778, "token": "\u010d\u010a\u0109\u0109\u0109\u0109", "merges": "\u010d \u010a\u0109\u0109\u0109\u0109", "raw_count": 0, "count": 0, "decode_str": "\r\n\t\t\t\t"} -{"id": 47056, "token": "}}}({\\", "merges": "}} }({\\", "raw_count": 0, "count": 0, "decode_str": "}}}({\\"} -{"id": 9899, "token": "]{}]{}", "merges": "]{} ]{}", "raw_count": 0, "count": 0, "decode_str": "]{}]{}"} -{"id": 31988, "token": "\u0120\u0120\u0120\u0120\u010a\u0120", "merges": "\u0120\u0120\u0120\u0120 \u010a\u0120", "raw_count": 0, "count": 0, "decode_str": " \n "} -{"id": 17723, "token": "\u010d\u010a\u0120\u0120\u0120\u0120", "merges": "\u010d \u010a\u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\r\n "} -{"id": 45099, "token": "}}({{\\", "merges": "}}( {{\\", "raw_count": 0, "count": 0, "decode_str": "}}({{\\"} -{"id": 35950, "token": "\u0120\u0120\u010a\u0120\u0120\u0120", "merges": "\u0120\u0120 \u010a\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " \n "} -{"id": 39310, "token": "\"}**).", "merges": "\"} **).", "raw_count": 0, "count": 0, "decode_str": "\"}**)."} -{"id": 674, "token": "\u0120\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120\u0120\u0120 \u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 1760, "token": "\u010a\u0120\u0120\u0120\u0120", "merges": "\u010a \u0120\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n "} -{"id": 3568, "token": "\u010d\u010a\u0120\u0120\u0120", "merges": "\u010d \u010a\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\r\n "} -{"id": 18022, "token": "\\*](#", "merges": "\\* ](#", "raw_count": 0, "count": 0, "decode_str": "\\*](#"} -{"id": 31096, "token": "^\\[[@", "merges": "^ \\[[@", "raw_count": 0, "count": 0, "decode_str": "^\\[[@"} -{"id": 29683, "token": "\u010a\u0120\u0120\u00c2\u0142", "merges": "\u010a\u0120\u0120 \u00c2\u0142", "raw_count": 0, "count": 0, "decode_str": "\n \u00a0"} -{"id": 22180, "token": "_{{{\\", "merges": "_{ {{\\", "raw_count": 0, "count": 0, "decode_str": "_{{{\\"} -{"id": 17158, "token": "\u010d\u010a\u0109\u0109\u0109", "merges": "\u010d \u010a\u0109\u0109\u0109", "raw_count": 0, "count": 0, "decode_str": "\r\n\t\t\t"} -{"id": 39083, "token": "\"}](#", "merges": "\"} ](#", "raw_count": 0, "count": 0, "decode_str": "\"}](#"} -{"id": 47312, "token": "iNdEx", "merges": "i NdEx", "raw_count": 0, "count": 0, "decode_str": "iNdEx"} -{"id": 20977, "token": "}$]{}", "merges": "}$ ]{}", "raw_count": 0, "count": 0, "decode_str": "}$]{}"} -{"id": 7444, "token": "**]{}", "merges": "** ]{}", "raw_count": 0, "count": 0, "decode_str": "**]{}"} -{"id": 1254, "token": "\u0120\\[[@", "merges": "\u0120\\[ [@", "raw_count": 0, "count": 0, "decode_str": " \\[[@"} -{"id": 35379, "token": ")}^{(", "merges": ") }^{(", "raw_count": 0, "count": 0, "decode_str": ")}^{("} -{"id": 26061, "token": "\u010d\u010a\u010d\u010a\u0120", "merges": "\u010d\u010a \u010d\u010a\u0120", "raw_count": 0, "count": 0, "decode_str": "\r\n\r\n "} -{"id": 8129, "token": "\u0120\u010a\u0120\u0120\u0120", "merges": "\u0120 \u010a\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " \n "} -{"id": 24994, "token": "^\u00e2\u012a\u0134^", "merges": "^\u00e2\u012a\u0134 ^", "raw_count": 0, "count": 0, "decode_str": "^\u2212^"} -{"id": 26119, "token": "*]{}.", "merges": "*]{} .", "raw_count": 0, "count": 0, "decode_str": "*]{}."} -{"id": 27655, "token": "\u0120$[]$", "merges": "\u0120$ []$", "raw_count": 0, "count": 0, "decode_str": " $[]$"} -{"id": 8863, "token": "\u010a\u010a\u010a\u010a\u010a", "merges": "\u010a\u010a \u010a\u010a\u010a", "raw_count": 0, "count": 0, "decode_str": "\n\n\n\n\n"} -{"id": 16207, "token": "\u0120$${\\", "merges": "\u0120$$ {\\", "raw_count": 0, "count": 0, "decode_str": " $${\\"} -{"id": 34833, "token": "\u0120xcex", "merges": "\u0120x cex", "raw_count": 0, "count": 0, "decode_str": " xcex"} -{"id": 38320, "token": "\u0120\u00c2\u00b6\u00c2\u00b6", "merges": "\u0120\u00c2\u00b6 \u00c2\u00b6", "raw_count": 0, "count": 0, "decode_str": " \u00b6\u00b6"} -{"id": 45488, "token": "\u0120([**", "merges": "\u0120([ **", "raw_count": 0, "count": 0, "decode_str": " ([**"} -{"id": 1496, "token": "\u010a\u010a\u0120\u0120\u0120", "merges": "\u010a \u010a\u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n\n "} -{"id": 49021, "token": "$.[]{", "merges": "$. []{", "raw_count": 0, "count": 0, "decode_str": "$.[]{"} -{"id": 33158, "token": "\u010a\u0109\u0109\u010a\u0109", "merges": "\u010a\u0109\u0109 \u010a\u0109", "raw_count": 0, "count": 0, "decode_str": "\n\t\t\n\t"} -{"id": 28122, "token": "\u010a\u010a\u0109\u0109\u0109", "merges": "\u010a\u010a\u0109\u0109 \u0109", "raw_count": 0, "count": 0, "decode_str": "\n\n\t\t\t"} -{"id": 29013, "token": "\\]]{}", "merges": "\\] ]{}", "raw_count": 0, "count": 0, "decode_str": "\\]]{}"} -{"id": 32964, "token": "}}.$$", "merges": "}} .$$", "raw_count": 0, "count": 0, "decode_str": "}}.$$"} -{"id": 7201, "token": "\u0120${{\\", "merges": "\u0120$ {{\\", "raw_count": 0, "count": 0, "decode_str": " ${{\\"} -{"id": 30324, "token": "\u010a\u0120\u0120\u010a\u0120", "merges": "\u010a\u0120\u0120 \u010a\u0120", "raw_count": 0, "count": 0, "decode_str": "\n \n "} -{"id": 13663, "token": ".*]{}", "merges": ". *]{}", "raw_count": 0, "count": 0, "decode_str": ".*]{}"} -{"id": 31350, "token": "$]{};", "merges": "$]{} ;", "raw_count": 0, "count": 0, "decode_str": "$]{};"} -{"id": 35745, "token": "\u010d\u010a\u010d\u010a\u010d", "merges": "\u010d\u010a \u010d\u010a\u010d", "raw_count": 0, "count": 0, "decode_str": "\r\n\r\n\r"} -{"id": 45382, "token": "]{}\\_", "merges": "]{}\\ _", "raw_count": 0, "count": 0, "decode_str": "]{}\\_"} -{"id": 15775, "token": ".\\[[@", "merges": ". \\[[@", "raw_count": 0, "count": 0, "decode_str": ".\\[[@"} -{"id": 7254, "token": "]--[@", "merges": "]-- [@", "raw_count": 0, "count": 0, "decode_str": "]--[@"} -{"id": 39049, "token": "}})$.", "merges": "}} )$.", "raw_count": 0, "count": 0, "decode_str": "}})$."} -{"id": 42041, "token": "\u0120\u00c2\u00a7\\[", "merges": "\u0120\u00c2\u00a7 \\[", "raw_count": 0, "count": 0, "decode_str": " \u00a7\\["} -{"id": 42348, "token": ")}.$$", "merges": ")} .$$", "raw_count": 0, "count": 0, "decode_str": ")}.$$"} -{"id": 14352, "token": "\u010a\u0109\u0120\u0120\u0120", "merges": "\u010a\u0109 \u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n\t "} -{"id": 49824, "token": "\u0120[(\\[", "merges": "\u0120[ (\\[", "raw_count": 0, "count": 0, "decode_str": " [(\\["} -{"id": 11661, "token": "*]{},", "merges": "* ]{},", "raw_count": 0, "count": 0, "decode_str": "*]{},"} -{"id": 20426, "token": "\u0120\u0120\u0120\u010a\u0120", "merges": "\u0120\u0120\u0120 \u010a\u0120", "raw_count": 0, "count": 0, "decode_str": " \n "} -{"id": 33805, "token": "]{}\\^", "merges": "]{}\\ ^", "raw_count": 0, "count": 0, "decode_str": "]{}\\^"} -{"id": 36134, "token": "[\\*\\*", "merges": "[ \\*\\*", "raw_count": 0, "count": 0, "decode_str": "[\\*\\*"} -{"id": 38475, "token": "\"}\\].", "merges": "\"} \\].", "raw_count": 0, "count": 0, "decode_str": "\"}\\]."} -{"id": 39015, "token": "\u010d\u010a\u010d\u010a\u0109", "merges": "\u010d\u010a\u010d \u010a\u0109", "raw_count": 0, "count": 0, "decode_str": "\r\n\r\n\t"} -{"id": 39077, "token": "\\}.$$", "merges": "\\ }.$$", "raw_count": 0, "count": 0, "decode_str": "\\}.$$"} -{"id": 252, "token": "\u0120\u0120\u0120\u0120", "merges": "\u0120\u0120 \u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 477, "token": "\u010a\u0120\u0120\u0120", "merges": "\u010a \u0120\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n "} -{"id": 5429, "token": "\u010a\u010a\u010a\u010a", "merges": "\u010a\u010a \u010a\u010a", "raw_count": 0, "count": 0, "decode_str": "\n\n\n\n"} -{"id": 12593, "token": "\u010a\u0120\u010a\u0120", "merges": "\u010a\u0120 \u010a\u0120", "raw_count": 0, "count": 0, "decode_str": "\n \n "} -{"id": 11866, "token": "\u010a\u010a\u0109\u0109", "merges": "\u010a\u010a \u0109\u0109", "raw_count": 0, "count": 0, "decode_str": "\n\n\t\t"} -{"id": 13488, "token": "$]{}", "merges": "$ ]{}", "raw_count": 0, "count": 0, "decode_str": "$]{}"} -{"id": 17981, "token": ").](", "merges": "). ](", "raw_count": 0, "count": 0, "decode_str": ").]("} -{"id": 44578, "token": "\u0120\u00e2\u0122\u012b", "merges": "\u0120\u00e2\u0122 \u012b", "raw_count": 0, "count": 0, "decode_str": " \u2009"} -{"id": 32776, "token": "\u0120\u0120\u010a\u0120", "merges": "\u0120\u0120 \u010a\u0120", "raw_count": 0, "count": 0, "decode_str": " \n "} -{"id": 34607, "token": "\u0120^[@", "merges": "\u0120 ^[@", "raw_count": 0, "count": 0, "decode_str": " ^[@"} -{"id": 49411, "token": "*\u00e2\u0122\u0132", "merges": "* \u00e2\u0122\u0132", "raw_count": 0, "count": 0, "decode_str": "*\u2010"} -{"id": 21898, "token": "\u0120\u010a\u0120\u0120", "merges": "\u0120 \u010a\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": " \n "} -{"id": 15971, "token": "\u010d\u010a\u010d\u010a", "merges": "\u010d\u010a \u010d\u010a", "raw_count": 0, "count": 0, "decode_str": "\r\n\r\n"} -{"id": 33653, "token": "^\\*^", "merges": "^\\ *^", "raw_count": 0, "count": 0, "decode_str": "^\\*^"} -{"id": 30996, "token": ",^[@", "merges": ", ^[@", "raw_count": 0, "count": 0, "decode_str": ",^[@"} -{"id": 17278, "token": "^](#", "merges": "^ ](#", "raw_count": 0, "count": 0, "decode_str": "^](#"} -{"id": 31522, "token": "\u0120\u00e2\u0123\u00a2", "merges": "\u0120\u00e2\u0123 \u00a2", "raw_count": 0, "count": 0, "decode_str": " \u2062"} -{"id": 30775, "token": "$\u00e2\u0122\u0135", "merges": "$ \u00e2\u0122\u0135", "raw_count": 0, "count": 0, "decode_str": "$\u2013"} -{"id": 45581, "token": "dAtA", "merges": "d AtA", "raw_count": 0, "count": 0, "decode_str": "dAtA"} -{"id": 16413, "token": "\u010d\u010a\u0120\u0120", "merges": "\u010d \u010a\u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\r\n "} -{"id": 28375, "token": "\u0120\u00ce\u00bcL", "merges": "\u0120\u00ce\u00bc L", "raw_count": 0, "count": 0, "decode_str": " \u03bcL"} -{"id": 10174, "token": ".^[@", "merges": ". ^[@", "raw_count": 0, "count": 0, "decode_str": ".^[@"} -{"id": 29547, "token": "]\\];", "merges": "]\\] ;", "raw_count": 0, "count": 0, "decode_str": "]\\];"} -{"id": 35768, "token": ",{{\\", "merges": ", {{\\", "raw_count": 0, "count": 0, "decode_str": ",{{\\"} -{"id": 46230, "token": "\u00c2\u012a\u00c2\u0133", "merges": "\u00c2\u012a \u00c2\u0133", "raw_count": 0, "count": 0, "decode_str": "\u0088\u0091"} -{"id": 47279, "token": ":$$\\", "merges": ": $$\\", "raw_count": 0, "count": 0, "decode_str": ":$$\\"} -{"id": 39945, "token": "~}{~", "merges": "~ }{~", "raw_count": 0, "count": 0, "decode_str": "~}{~"} -{"id": 18031, "token": ":\"){", "merges": ":\" ){", "raw_count": 0, "count": 0, "decode_str": ":\"){"} -{"id": 33525, "token": "\u010a\u010a\u010a\u0120", "merges": "\u010a\u010a \u010a\u0120", "raw_count": 0, "count": 0, "decode_str": "\n\n\n "} -{"id": 44898, "token": "\u010a\u0109\u0120\u0120", "merges": "\u010a\u0109 \u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n\t "} -{"id": 47686, "token": "\\^[-", "merges": "\\^ [-", "raw_count": 0, "count": 0, "decode_str": "\\^[-"} -{"id": 5413, "token": "]\\],", "merges": "]\\] ,", "raw_count": 0, "count": 0, "decode_str": "]\\],"} -{"id": 26362, "token": "\u0120{\u00c2\u00b6", "merges": "\u0120{ \u00c2\u00b6", "raw_count": 0, "count": 0, "decode_str": " {\u00b6"} -{"id": 46603, "token": "\u010a\u010a\u0120\u010a", "merges": "\u010a\u010a\u0120 \u010a", "raw_count": 0, "count": 0, "decode_str": "\n\n \n"} -{"id": 32214, "token": "]\\]^", "merges": "]\\] ^", "raw_count": 0, "count": 0, "decode_str": "]\\]^"} -{"id": 27468, "token": "\u0120\\_[", "merges": "\u0120\\ _[", "raw_count": 0, "count": 0, "decode_str": " \\_["} -{"id": 11459, "token": "\u010d\u010a\u0109\u0109", "merges": "\u010d \u010a\u0109\u0109", "raw_count": 0, "count": 0, "decode_str": "\r\n\t\t"} -{"id": 42804, "token": ")^[@", "merges": ") ^[@", "raw_count": 0, "count": 0, "decode_str": ")^[@"} -{"id": 8926, "token": "\u010a\u010a\u0120\u0120", "merges": "\u010a\u010a \u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n\n "} -{"id": 27114, "token": ".(\\[", "merges": ". (\\[", "raw_count": 0, "count": 0, "decode_str": ".(\\["} -{"id": 31743, "token": "^\u00c2\u00ae^", "merges": "^\u00c2\u00ae ^", "raw_count": 0, "count": 0, "decode_str": "^\u00ae^"} -{"id": 34985, "token": "\u00c2\u0142\u010a\u0120", "merges": "\u00c2\u0142 \u010a\u0120", "raw_count": 0, "count": 0, "decode_str": "\u00a0\n "} -{"id": 30119, "token": "\u0120(\\>", "merges": "\u0120(\\ >", "raw_count": 0, "count": 0, "decode_str": " (\\>"} -{"id": 42419, "token": "\u0120(\\~", "merges": "\u0120(\\ ~", "raw_count": 0, "count": 0, "decode_str": " (\\~"} -{"id": 38679, "token": "\u0120\u0120\u0120\u010a", "merges": "\u0120\u0120\u0120 \u010a", "raw_count": 0, "count": 0, "decode_str": " \n"} -{"id": 341, "token": "\u0120\u0120\u0120", "merges": "\u0120\u0120 \u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 4888, "token": "\u010d\u010a\u010d", "merges": "\u010d\u010a \u010d", "raw_count": 0, "count": 0, "decode_str": "\r\n\r"} -{"id": 1772, "token": "\u010a\u0120\u0120", "merges": "\u010a \u0120\u0120", "raw_count": 0, "count": 0, "decode_str": "\n "} -{"id": 4256, "token": "\u010d\u010a\u0120", "merges": "\u010d \u010a\u0120", "raw_count": 0, "count": 0, "decode_str": "\r\n "} -{"id": 1744, "token": "\u010a\u010a\u0120", "merges": "\u010a\u010a \u0120", "raw_count": 0, "count": 0, "decode_str": "\n\n "} -{"id": 6886, "token": "\u010a\u010a\u0109", "merges": "\u010a\u010a \u0109", "raw_count": 0, "count": 0, "decode_str": "\n\n\t"} -{"id": 53775, "token": "\u00e8\u00ab\u00a1", "merges": "\u00e8\u00ab \u00a1", "raw_count": 0, "count": 0, "decode_str": "\u8ae1"} -{"id": 7951, "token": "\u010d\u010a\u0109", "merges": "\u010d \u010a\u0109", "raw_count": 0, "count": 0, "decode_str": "\r\n\t"} -{"id": 13769, "token": "\u0120\u0120\u010a", "merges": "\u0120\u0120 \u010a", "raw_count": 0, "count": 0, "decode_str": " \n"} -{"id": 22417, "token": "\u010a\u0109\u010a", "merges": "\u010a\u0109 \u010a", "raw_count": 0, "count": 0, "decode_str": "\n\t\n"} -{"id": 245, "token": "\u0120\u0120", "merges": "\u0120 \u0120", "raw_count": 0, "count": 0, "decode_str": " "} -{"id": 16981, "token": "\u010d\u010d", "merges": "\u010d \u010d", "raw_count": 0, "count": 0, "decode_str": "\r\r"} -{"id": 8675, "token": "\u010a\u010c", "merges": "\u010a \u010c", "raw_count": 0, "count": 0, "decode_str": "\n\f"} -{"id": 2379, "token": "\u010d\u010a", "merges": "\u010d \u010a", "raw_count": 0, "count": 0, "decode_str": "\r\n"} -{"id": 38572, "token": "\\\u0103", "merges": "\\ \u0103", "raw_count": 0, "count": 0, "decode_str": "\\\u0003"} -{"id": 20434, "token": "\u0120\u010d", "merges": "\u0120 \u010d", "raw_count": 0, "count": 0, "decode_str": " \r"} -{"id": 33059, "token": "\u0111\u0103", "merges": "\u0111 \u0103", "raw_count": 0, "count": 0, "decode_str": "\u0011\u0003"} -{"id": 190, "token": "\u010d", "merges": "NULL", "raw_count": 0, "count": 0, "decode_str": "\r"} -{"id": 27886, "token": "scriptscriptstyle", "merges": "script scriptstyle", "raw_count": 1, "count": 1, "decode_str": "scriptscriptstyle"} -{"id": 43421, "token": "Sportspeople", "merges": "Sports people", "raw_count": 1, "count": 1, "decode_str": "Sportspeople"} -{"id": 27528, "token": "\u0120Appellants", "merges": "\u0120App ellants", "raw_count": 1, "count": 1, "decode_str": " Appellants"} -{"id": 18160, "token": "\u0120Petitioner", "merges": "\u0120Petition er", "raw_count": 1, "count": 1, "decode_str": " Petitioner"} -{"id": 46558, "token": "Appellees", "merges": "App ellees", "raw_count": 1, "count": 1, "decode_str": "Appellees"} -{"id": 39834, "token": "\u0120Europese", "merges": "\u0120Europ ese", "raw_count": 1, "count": 1, "decode_str": " Europese"} -{"id": 8860, "token": "wasysym", "merges": "was ysym", "raw_count": 1, "count": 1, "decode_str": "wasysym"} -{"id": 37276, "token": "}}}_{\\", "merges": "}} }_{\\", "raw_count": 1, "count": 1, "decode_str": "}}}_{\\"} -{"id": 47996, "token": "\\!\\!\\!", "merges": "\\!\\! \\!", "raw_count": 1, "count": 1, "decode_str": "\\!\\!\\!"} -{"id": 45251, "token": "}})$,", "merges": "}} )$,", "raw_count": 1, "count": 1, "decode_str": "}})$,"} -{"id": 19753, "token": "}}({\\", "merges": "}}( {\\", "raw_count": 1, "count": 1, "decode_str": "}}({\\"} -{"id": 43214, "token": "}).$$", "merges": "} ).$$", "raw_count": 1, "count": 1, "decode_str": "}).$$"} -{"id": 30780, "token": "\u0120$({\\", "merges": "\u0120$( {\\", "raw_count": 1, "count": 1, "decode_str": " $({\\"} -{"id": 35539, "token": "NdEx", "merges": "Nd Ex", "raw_count": 1, "count": 1, "decode_str": "NdEx"} -{"id": 16079, "token": ".[]{", "merges": ".[ ]{", "raw_count": 1, "count": 1, "decode_str": ".[]{"} -{"id": 28381, "token": "\u0120A\u00ce\u00b2", "merges": "\u0120A \u00ce\u00b2", "raw_count": 1, "count": 1, "decode_str": " A\u03b2"} -{"id": 10148, "token": "\"}](", "merges": "\"} ](", "raw_count": 1, "count": 1, "decode_str": "\"}]("} -{"id": 17548, "token": "]-[@", "merges": "]- [@", "raw_count": 1, "count": 1, "decode_str": "]-[@"} -{"id": 33939, "token": "\u00c2\u0122\u00c2\u0124", "merges": "\u00c2\u0122 \u00c2\u0124", "raw_count": 1, "count": 1, "decode_str": "\u0080\u0082"} -{"id": 38913, "token": "\u00c2\u013a\u00c2\u00af", "merges": "\u00c2\u013a \u00c2\u00af", "raw_count": 1, "count": 1, "decode_str": "\u0098\u00af"} -{"id": 24237, "token": ".]{}", "merges": ". ]{}", "raw_count": 1, "count": 1, "decode_str": ".]{}"} -{"id": 47446, "token": "*](#", "merges": "* ](#", "raw_count": 1, "count": 1, "decode_str": "*](#"} -{"id": 2756, "token": "\u010a\u010a\u010a", "merges": "\u010a\u010a \u010a", "raw_count": 1, "count": 1, "decode_str": "\n\n\n"} -{"id": 27596, "token": "^\u00c2\u00ae", "merges": "^ \u00c2\u00ae", "raw_count": 1, "count": 1, "decode_str": "^\u00ae"} -{"id": 19668, "token": "\u010a\u0120\u010a", "merges": "\u010a\u0120 \u010a", "raw_count": 1, "count": 1, "decode_str": "\n \n"} -{"id": 46224, "token": "\u0120immunoreactivity", "merges": "\u0120immunore activity", "raw_count": 2, "count": 2, "decode_str": " immunoreactivity"} -{"id": 41321, "token": "\u0120supernatants", "merges": "\u0120supernat ants", "raw_count": 2, "count": 2, "decode_str": " supernatants"} -{"id": 49597, "token": "\u0120Petitioners", "merges": "\u0120Petition ers", "raw_count": 2, "count": 2, "decode_str": " Petitioners"} -{"id": 12601, "token": "\u0120Plaintiffs", "merges": "\u0120Plaintiff s", "raw_count": 2, "count": 2, "decode_str": " Plaintiffs"} -{"id": 34443, "token": "\u0120appellees", "merges": "\u0120app ellees", "raw_count": 2, "count": 2, "decode_str": " appellees"} -{"id": 34319, "token": "\u0120CURIAM", "merges": "\u0120CURI AM", "raw_count": 2, "count": 2, "decode_str": " CURIAM"} -{"id": 32334, "token": "ubottu", "merges": "ub ottu", "raw_count": 2, "count": 2, "decode_str": "ubottu"} -{"id": 35799, "token": "}}}$,", "merges": "}} }$,", "raw_count": 2, "count": 2, "decode_str": "}}}$,"} -{"id": 38451, "token": "\u0120da\u00c3\u0141", "merges": "\u0120da \u00c3\u0141", "raw_count": 2, "count": 2, "decode_str": " da\u00df"} -{"id": 33438, "token": "biggl", "merges": "big gl", "raw_count": 2, "count": 2, "decode_str": "biggl"} -{"id": 47028, "token": ")\\|_{", "merges": ")\\ |_{", "raw_count": 2, "count": 2, "decode_str": ")\\|_{"} -{"id": 42465, "token": "}},$$", "merges": "}}, $$", "raw_count": 2, "count": 2, "decode_str": "}},$$"} -{"id": 37786, "token": "**](#", "merges": "** ](#", "raw_count": 2, "count": 2, "decode_str": "**](#"} -{"id": 34494, "token": "]\\]).", "merges": "]\\] ).", "raw_count": 2, "count": 2, "decode_str": "]\\])."} -{"id": 33471, "token": "}}}$.", "merges": "}} }$.", "raw_count": 2, "count": 2, "decode_str": "}}}$."} -{"id": 44524, "token": "].$$", "merges": "]. $$", "raw_count": 2, "count": 2, "decode_str": "].$$"} -{"id": 42213, "token": "\u0120\u00c2\u00b5l", "merges": "\u0120\u00c2\u00b5 l", "raw_count": 2, "count": 2, "decode_str": " \u00b5l"} -{"id": 21687, "token": ")]{}", "merges": ") ]{}", "raw_count": 2, "count": 2, "decode_str": ")]{}"} -{"id": 15267, "token": "\u0120\u010a\u010a", "merges": "\u0120 \u010a\u010a", "raw_count": 2, "count": 2, "decode_str": " \n\n"} -{"id": 40521, "token": "\u0120\u00c2\u0135", "merges": "\u0120\u00c2 \u0135", "raw_count": 2, "count": 2, "decode_str": " \u0093"} -{"id": 30843, "token": "\u010f\u0103", "merges": "\u010f \u0103", "raw_count": 2, "count": 2, "decode_str": "\u000f\u0003"} -{"id": 194, "token": "\u0111", "merges": "NULL", "raw_count": 2, "count": 2, "decode_str": "\u0011"} -{"id": 9517, "token": "\u0120Appellant", "merges": "\u0120App ellant", "raw_count": 3, "count": 3, "decode_str": " Appellant"} -{"id": 24730, "token": "\u0120APPEALS", "merges": "\u0120APPE ALS", "raw_count": 3, "count": 3, "decode_str": " APPEALS"} -{"id": 37857, "token": "\\!\\!\\!\\!", "merges": "\\!\\! \\!\\!", "raw_count": 3, "count": 3, "decode_str": "\\!\\!\\!\\!"} -{"id": 36847, "token": "mathbbm", "merges": "mathbb m", "raw_count": 3, "count": 3, "decode_str": "mathbbm"} -{"id": 8844, "token": "amsbsy", "merges": "ams bsy", "raw_count": 3, "count": 3, "decode_str": "amsbsy"} -{"id": 47183, "token": "\u0120$\\|\\", "merges": "\u0120$\\ |\\", "raw_count": 3, "count": 3, "decode_str": " $\\|\\"} -{"id": 35420, "token": "}({{\\", "merges": "}( {{\\", "raw_count": 3, "count": 3, "decode_str": "}({{\\"} -{"id": 15304, "token": "/\u00e2\u012a\u0134", "merges": "/ \u00e2\u012a\u0134", "raw_count": 3, "count": 3, "decode_str": "/\u2212"} -{"id": 8088, "token": "\\[[@", "merges": "\\[ [@", "raw_count": 3, "count": 3, "decode_str": "\\[[@"} -{"id": 28554, "token": "}}$-", "merges": "}} $-", "raw_count": 3, "count": 3, "decode_str": "}}$-"} -{"id": 30707, "token": "\u00c2\u013c\u00c2\u0126", "merges": "\u00c2\u013c \u00c2\u0126", "raw_count": 3, "count": 3, "decode_str": "\u009a\u0084"} -{"id": 18822, "token": "\u0120.$$", "merges": "\u0120. $$", "raw_count": 3, "count": 3, "decode_str": " .$$"} -{"id": 26786, "token": "\u0120(\\<", "merges": "\u0120( \\<", "raw_count": 3, "count": 3, "decode_str": " (\\<"} -{"id": 52864, "token": "\u00e7\u0136\u0137", "merges": "\u00e7\u0136 \u0137", "raw_count": 3, "count": 3, "decode_str": "\u7515"} -{"id": 44847, "token": "\u0120Commissie", "merges": "\u0120Commiss ie", "raw_count": 4, "count": 4, "decode_str": " Commissie"} -{"id": 22706, "token": "\u0120Appellee", "merges": "\u0120App ellee", "raw_count": 4, "count": 4, "decode_str": " Appellee"} -{"id": 40968, "token": "\u0120Israelis", "merges": "\u0120Israel is", "raw_count": 4, "count": 4, "decode_str": " Israelis"} -{"id": 20089, "token": "lesssim", "merges": "less sim", "raw_count": 4, "count": 4, "decode_str": "lesssim"} -{"id": 38443, "token": "\u00e2\u012a\u0139\u00e2\u012a\u0139", "merges": "\u00e2\u012a\u0139 \u00e2\u012a\u0139", "raw_count": 4, "count": 4, "decode_str": "\u2217\u2217"} -{"id": 41610, "token": "\u0120GAPDH", "merges": "\u0120G APDH", "raw_count": 4, "count": 4, "decode_str": " GAPDH"} -{"id": 41908, "token": "gtrsim", "merges": "gtr sim", "raw_count": 4, "count": 4, "decode_str": "gtrsim"} -{"id": 39111, "token": "}}}(\\", "merges": "}} }(\\", "raw_count": 4, "count": 4, "decode_str": "}}}(\\"} -{"id": 40743, "token": "ubotu", "merges": "ubot u", "raw_count": 4, "count": 4, "decode_str": "ubotu"} -{"id": 18781, "token": "\u0120\u00e2\u013b\u00aa\"", "merges": "\u0120\u00e2\u013b\u00aa \"", "raw_count": 4, "count": 4, "decode_str": " \u266a\""} -{"id": 45881, "token": "}=-\\", "merges": "}= -\\", "raw_count": 4, "count": 4, "decode_str": "}=-\\"} -{"id": 24759, "token": "}}}^", "merges": "}} }^", "raw_count": 4, "count": 4, "decode_str": "}}}^"} -{"id": 19219, "token": "\u0120$^{", "merges": "\u0120$ ^{", "raw_count": 4, "count": 4, "decode_str": " $^{"} -{"id": 52368, "token": "\u00e6\u00a8\u00ab", "merges": "\u00e6\u00a8 \u00ab", "raw_count": 4, "count": 4, "decode_str": "\u6a2b"} -{"id": 33307, "token": "\u00c2\u013d", "merges": "\u00c2 \u013d", "raw_count": 4, "count": 4, "decode_str": "\u009b"} -{"id": 202, "token": "\u0119", "merges": "NULL", "raw_count": 4, "count": 4, "decode_str": "\u0019"} -{"id": 199, "token": "\u0116", "merges": "NULL", "raw_count": 4, "count": 4, "decode_str": "\u0016"} -{"id": 200, "token": "\u0117", "merges": "NULL", "raw_count": 4, "count": 4, "decode_str": "\u0017"} -{"id": 42051, "token": "\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142", "merges": "\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142 \u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142", "raw_count": 5, "count": 5, "decode_str": "\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0"} -{"id": 28072, "token": "\u0120Palestinians", "merges": "\u0120Palestin ians", "raw_count": 5, "count": 5, "decode_str": " Palestinians"} -{"id": 43140, "token": "transfected", "merges": "trans fected", "raw_count": 5, "count": 5, "decode_str": "transfected"} -{"id": 41383, "token": "Appellants", "merges": "App ellants", "raw_count": 5, "count": 5, "decode_str": "Appellants"} -{"id": 32291, "token": "geqslant", "merges": "geq slant", "raw_count": 5, "count": 5, "decode_str": "geqslant"} -{"id": 8828, "token": "mathrsfs", "merges": "math rsfs", "raw_count": 5, "count": 5, "decode_str": "mathrsfs"} -{"id": 48367, "token": "}}^{{\\", "merges": "}}^{ {\\", "raw_count": 5, "count": 5, "decode_str": "}}^{{\\"} -{"id": 41897, "token": "\u00c3\u0132\u00c2\u00b5\u00c3\u0133", "merges": "\u00c3\u0132\u00c2\u00b5 \u00c3\u0133", "raw_count": 5, "count": 5, "decode_str": "\u00d0\u00b5\u00d1"} -{"id": 25352, "token": "\u0120$\\{\\", "merges": "\u0120$\\ {\\", "raw_count": 5, "count": 5, "decode_str": " $\\{\\"} -{"id": 10878, "token": "}.$$", "merges": "} .$$", "raw_count": 5, "count": 5, "decode_str": "}.$$"} -{"id": 47264, "token": "}-{\\", "merges": "}- {\\", "raw_count": 5, "count": 5, "decode_str": "}-{\\"} -{"id": 49372, "token": "_{\\{", "merges": "_{\\ {", "raw_count": 5, "count": 5, "decode_str": "_{\\{"} -{"id": 41625, "token": "\u00c2\u00b8\u00c2\u012f", "merges": "\u00c2\u00b8 \u00c2\u012f", "raw_count": 5, "count": 5, "decode_str": "\u00b8\u008d"} -{"id": 34908, "token": "\u0120qRT", "merges": "\u0120q RT", "raw_count": 5, "count": 5, "decode_str": " qRT"} -{"id": 38606, "token": "\u0120\\}$", "merges": "\u0120\\ }$", "raw_count": 5, "count": 5, "decode_str": " \\}$"} -{"id": 37982, "token": "![\\[", "merges": "![ \\[", "raw_count": 5, "count": 5, "decode_str": "![\\["} -{"id": 44957, "token": "\u0120\u00c2\u00b5L", "merges": "\u0120\u00c2\u00b5 L", "raw_count": 5, "count": 5, "decode_str": " \u00b5L"} -{"id": 47389, "token": "~\\]", "merges": "~ \\]", "raw_count": 5, "count": 5, "decode_str": "~\\]"} -{"id": 201, "token": "\u0118", "merges": "NULL", "raw_count": 5, "count": 5, "decode_str": "\u0018"} -{"id": 48128, "token": "\u0120CONSEQUENTIAL", "merges": "\u0120CON SEQUENTIAL", "raw_count": 6, "count": 6, "decode_str": " CONSEQUENTIAL"} -{"id": 49505, "token": "\u0120NEGLIGENCE", "merges": "\u0120NE GLIGENCE", "raw_count": 6, "count": 6, "decode_str": " NEGLIGENCE"} -{"id": 39604, "token": "\u0120Kommission", "merges": "\u0120Kom mission", "raw_count": 6, "count": 6, "decode_str": " Kommission"} -{"id": 38747, "token": "cjwatson", "merges": "cj watson", "raw_count": 6, "count": 6, "decode_str": "cjwatson"} -{"id": 42827, "token": "\u0120microM", "merges": "\u0120micro M", "raw_count": 6, "count": 6, "decode_str": " microM"} -{"id": 35937, "token": "}}}}$", "merges": "}} }}$", "raw_count": 6, "count": 6, "decode_str": "}}}}$"} -{"id": 48201, "token": "=\"'$(", "merges": "=\"' $(", "raw_count": 6, "count": 6, "decode_str": "=\"'$("} -{"id": 37944, "token": "\u0120/**<", "merges": "\u0120/** <", "raw_count": 6, "count": 6, "decode_str": " /**<"} -{"id": 16769, "token": "\u0120\u00ce\u00bcM", "merges": "\u0120\u00ce\u00bc M", "raw_count": 6, "count": 6, "decode_str": " \u03bcM"} -{"id": 16489, "token": "),$$", "merges": "), $$", "raw_count": 6, "count": 6, "decode_str": "),$$"} -{"id": 46201, "token": ")}/\\", "merges": ")} /\\", "raw_count": 6, "count": 6, "decode_str": ")}/\\"} -{"id": 43266, "token": "/\u00e2\u0122\u012d", "merges": "/ \u00e2\u0122\u012d", "raw_count": 6, "count": 6, "decode_str": "/\u200b"} -{"id": 22805, "token": "\\}$,", "merges": "\\ }$,", "raw_count": 6, "count": 6, "decode_str": "\\}$,"} -{"id": 45122, "token": "\u0120p\u00c3\u0125", "merges": "\u0120p \u00c3\u0125", "raw_count": 6, "count": 6, "decode_str": " p\u00c3"} -{"id": 26325, "token": "\u0120,$$", "merges": "\u0120, $$", "raw_count": 6, "count": 6, "decode_str": " ,$$"} -{"id": 17281, "token": ")](#", "merges": ") ](#", "raw_count": 6, "count": 6, "decode_str": ")](#"} -{"id": 18413, "token": "]^,", "merges": "]^ ,", "raw_count": 6, "count": 6, "decode_str": "]^,"} -{"id": 12004, "token": "]{.", "merges": "]{ .", "raw_count": 6, "count": 6, "decode_str": "]{."} -{"id": 6043, "token": "\u0120Plaintiff", "merges": "\u0120Pl aintiff", "raw_count": 5, "count": 7, "decode_str": " Plaintiff"} -{"id": 37368, "token": "\u0120Pursuant", "merges": "\u0120P ursuant", "raw_count": 7, "count": 7, "decode_str": " Pursuant"} -{"id": 45622, "token": "\u0120EEOC", "merges": "\u0120EE OC", "raw_count": 7, "count": 7, "decode_str": " EEOC"} -{"id": 35998, "token": "\u0120Rptr", "merges": "\u0120R ptr", "raw_count": 7, "count": 7, "decode_str": " Rptr"} -{"id": 32222, "token": "}},{\\", "merges": "}}, {\\", "raw_count": 7, "count": 7, "decode_str": "}},{\\"} -{"id": 44740, "token": "\u0120/*!<", "merges": "\u0120/*! <", "raw_count": 7, "count": 7, "decode_str": " /*!<"} -{"id": 13270, "token": "MOESM", "merges": "MO ESM", "raw_count": 7, "count": 7, "decode_str": "MOESM"} -{"id": 26271, "token": "\u0120\u00c2\u00b5M", "merges": "\u0120\u00c2\u00b5 M", "raw_count": 7, "count": 7, "decode_str": " \u00b5M"} -{"id": 35869, "token": "]{}(", "merges": "]{} (", "raw_count": 7, "count": 7, "decode_str": "]{}("} -{"id": 38400, "token": "}={\\", "merges": "}= {\\", "raw_count": 7, "count": 7, "decode_str": "}={\\"} -{"id": 49538, "token": "^*$,", "merges": "^* $,", "raw_count": 7, "count": 7, "decode_str": "^*$,"} -{"id": 39300, "token": "\u0120s\u00c3\u0125", "merges": "\u0120s \u00c3\u0125", "raw_count": 7, "count": 7, "decode_str": " s\u00c3"} -{"id": 47044, "token": "|$.", "merges": "| $.", "raw_count": 7, "count": 7, "decode_str": "|$."} -{"id": 53546, "token": "\u00e8\u0126\u00a3", "merges": "\u00e8\u0126 \u00a3", "raw_count": 7, "count": 7, "decode_str": "\u8123"} -{"id": 20587, "token": "\u00c2\u012d", "merges": "\u00c2 \u012d", "raw_count": 7, "count": 7, "decode_str": "\u008b"} -{"id": 174, "token": "\u00f2", "merges": "NULL", "raw_count": 7, "count": 7, "decode_str": "\ufffd"} -{"id": 197, "token": "\u0114", "merges": "NULL", "raw_count": 7, "count": 7, "decode_str": "\u0014"} -{"id": 48924, "token": "//----------------------------------------------------------------", "merges": "// ----------------------------------------------------------------", "raw_count": 8, "count": 8, "decode_str": "//----------------------------------------------------------------"} -{"id": 26939, "token": "\u0120\u00c2\u0142\u00c2\u0142\u0120\u00c2\u0142\u00c2\u0142\u0120\u00c2\u0142\u00c2\u0142\u0120\u00c2\u0142\u00c2\u0142", "merges": "\u0120\u00c2\u0142\u00c2\u0142\u0120\u00c2\u0142\u00c2\u0142 \u0120\u00c2\u0142\u00c2\u0142\u0120\u00c2\u0142\u00c2\u0142", "raw_count": 8, "count": 8, "decode_str": " \u00a0\u00a0 \u00a0\u00a0 \u00a0\u00a0 \u00a0\u00a0"} -{"id": 50048, "token": "\u0120Congressman", "merges": "\u0120Congress man", "raw_count": 8, "count": 8, "decode_str": " Congressman"} -{"id": 1, "token": "<|padding|>", "merges": "NULL", "raw_count": 8, "count": 8, "decode_str": ""} -{"id": 39193, "token": "\u0120Obamacare", "merges": "\u0120Ob amacare", "raw_count": 8, "count": 8, "decode_str": " Obamacare"} -{"id": 48346, "token": "\u0120Comiss\u00c3\u00a3o", "merges": "\u0120Comiss \u00c3\u00a3o", "raw_count": 8, "count": 8, "decode_str": " Comiss\u00e3o"} -{"id": 46900, "token": "\u0120Lebanese", "merges": "\u0120Leban ese", "raw_count": 8, "count": 8, "decode_str": " Lebanese"} -{"id": 47810, "token": "\u0120ocks\u00c3\u00a5", "merges": "\u0120ocks \u00c3\u00a5", "raw_count": 8, "count": 8, "decode_str": " ocks\u00e5"} -{"id": 37980, "token": "\u00c3\u0132\u00c2\u00b5\u00c3\u0132", "merges": "\u00c3\u0132\u00c2\u00b5 \u00c3\u0132", "raw_count": 8, "count": 8, "decode_str": "\u00d0\u00b5\u00d0"} -{"id": 45237, "token": "\u0120shRNA", "merges": "\u0120sh RNA", "raw_count": 8, "count": 8, "decode_str": " shRNA"} -{"id": 30145, "token": "}^{{\\", "merges": "}^{ {\\", "raw_count": 8, "count": 8, "decode_str": "}^{{\\"} -{"id": 28691, "token": ")\u00e2\u0122\u0135(", "merges": ")\u00e2\u0122\u0135 (", "raw_count": 8, "count": 8, "decode_str": ")\u2013("} -{"id": 1656, "token": "]\\].", "merges": "]\\] .", "raw_count": 8, "count": 8, "decode_str": "]\\]."} -{"id": 22367, "token": "![**", "merges": "![ **", "raw_count": 8, "count": 8, "decode_str": "![**"} -{"id": 31357, "token": "\u0120$\\|", "merges": "\u0120$\\ |", "raw_count": 8, "count": 8, "decode_str": " $\\|"} -{"id": 31782, "token": "\u00c3\u00a4\u00c2\u00ba", "merges": "\u00c3\u00a4 \u00c2\u00ba", "raw_count": 8, "count": 8, "decode_str": "\u00e4\u00ba"} -{"id": 27872, "token": "\u0120ALJ", "merges": "\u0120AL J", "raw_count": 8, "count": 8, "decode_str": " ALJ"} -{"id": 14640, "token": "},$$", "merges": "}, $$", "raw_count": 8, "count": 8, "decode_str": "},$$"} -{"id": 11971, "token": "}}$.", "merges": "}} $.", "raw_count": 8, "count": 8, "decode_str": "}}$."} -{"id": 37192, "token": "\\,{\\", "merges": "\\, {\\", "raw_count": 8, "count": 8, "decode_str": "\\,{\\"} -{"id": 35017, "token": "\u0120\u00c3\u013b", "merges": "\u0120\u00c3 \u013b", "raw_count": 8, "count": 8, "decode_str": " \u00d9"} -{"id": 51501, "token": "\u00e5\u00b7\u0138", "merges": "\u00e5\u00b7 \u0138", "raw_count": 8, "count": 8, "decode_str": "\u5dd6"} -{"id": 28372, "token": "\u00c2\u0130", "merges": "\u00c2 \u0130", "raw_count": 8, "count": 8, "decode_str": "\u008e"} -{"id": 191, "token": "\u010e", "merges": "NULL", "raw_count": 8, "count": 8, "decode_str": "\u000e"} -{"id": 182, "token": "\u0105", "merges": "NULL", "raw_count": 8, "count": 8, "decode_str": "\u0005"} -{"id": 195, "token": "\u0112", "merges": "NULL", "raw_count": 8, "count": 8, "decode_str": "\u0012"} -{"id": 38110, "token": "\u0120resuspended", "merges": "\u0120res uspended", "raw_count": 9, "count": 9, "decode_str": " resuspended"} -{"id": 28906, "token": "\u0120neutrophils", "merges": "\u0120neutroph ils", "raw_count": 9, "count": 9, "decode_str": " neutrophils"} -{"id": 12254, "token": "\u0120Defendants", "merges": "\u0120Def endants", "raw_count": 9, "count": 9, "decode_str": " Defendants"} -{"id": 46187, "token": "\u0120Comisi\u00c3\u00b3n", "merges": "\u0120Com isi\u00c3\u00b3n", "raw_count": 9, "count": 9, "decode_str": " Comisi\u00f3n"} -{"id": 46733, "token": "\u0120Islamist", "merges": "\u0120Islam ist", "raw_count": 9, "count": 9, "decode_str": " Islamist"} -{"id": 32777, "token": "\u0120lysates", "merges": "\u0120lys ates", "raw_count": 9, "count": 9, "decode_str": " lysates"} -{"id": 47596, "token": "vphantom", "merges": "v phantom", "raw_count": 9, "count": 9, "decode_str": "vphantom"} -{"id": 43215, "token": "\u0120curiam", "merges": "\u0120cur iam", "raw_count": 9, "count": 9, "decode_str": " curiam"} -{"id": 45409, "token": "\u0120Sunni", "merges": "\u0120Sun ni", "raw_count": 9, "count": 9, "decode_str": " Sunni"} -{"id": 39601, "token": "\u0120ERISA", "merges": "\u0120ER ISA", "raw_count": 9, "count": 9, "decode_str": " ERISA"} -{"id": 43654, "token": "\\|_{\\", "merges": "\\| _{\\", "raw_count": 9, "count": 9, "decode_str": "\\|_{\\"} -{"id": 48003, "token": "\u0120HepG", "merges": "\u0120Hep G", "raw_count": 9, "count": 9, "decode_str": " HepG"} -{"id": 28185, "token": ")}$.", "merges": ") }$.", "raw_count": 9, "count": 9, "decode_str": ")}$."} -{"id": 20940, "token": "\u0120_{\\", "merges": "\u0120_ {\\", "raw_count": 9, "count": 9, "decode_str": " _{\\"} -{"id": 40413, "token": "\u00c3\u0132\u00c2\u00ba", "merges": "\u00c3\u0132 \u00c2\u00ba", "raw_count": 9, "count": 9, "decode_str": "\u00d0\u00ba"} -{"id": 50334, "token": "\u00e2\u012d\u012a", "merges": "\u00e2\u012d \u012a", "raw_count": 9, "count": 9, "decode_str": "\u22c8"} -{"id": 18455, "token": "\u00c2\u0128", "merges": "\u00c2 \u0128", "raw_count": 9, "count": 9, "decode_str": "\u0086"} -{"id": 173, "token": "\u00f1", "merges": "NULL", "raw_count": 9, "count": 9, "decode_str": "\ufffd"} -{"id": 206, "token": "\u011d", "merges": "NULL", "raw_count": 9, "count": 9, "decode_str": "\u001d"} -{"id": 40055, "token": "\u0120Conservatives", "merges": "\u0120Conserv atives", "raw_count": 10, "count": 10, "decode_str": " Conservatives"} -{"id": 41163, "token": "micromachines", "merges": "microm achines", "raw_count": 10, "count": 10, "decode_str": "micromachines"} -{"id": 46066, "token": "\u0120Jacksonville", "merges": "\u0120Jackson ville", "raw_count": 10, "count": 10, "decode_str": " Jacksonville"} -{"id": 28107, "token": "Appellee", "merges": "App ellee", "raw_count": 10, "count": 10, "decode_str": "Appellee"} -{"id": 49065, "token": "\u0120Texans", "merges": "\u0120Tex ans", "raw_count": 10, "count": 10, "decode_str": " Texans"} -{"id": 37087, "token": "medsc", "merges": "med sc", "raw_count": 10, "count": 10, "decode_str": "medsc"} -{"id": 40608, "token": "}^{(\\", "merges": "}^{ (\\", "raw_count": 10, "count": 10, "decode_str": "}^{(\\"} -{"id": 45656, "token": "\u0120{{{\\", "merges": "\u0120{ {{\\", "raw_count": 10, "count": 10, "decode_str": " {{{\\"} -{"id": 24255, "token": "&=&\\", "merges": "&= &\\", "raw_count": 10, "count": 10, "decode_str": "&=&\\"} -{"id": 32477, "token": ".\u00e2\u0122\u012d", "merges": ". \u00e2\u0122\u012d", "raw_count": 10, "count": 10, "decode_str": ".\u200b"} -{"id": 28503, "token": "}}\\,", "merges": "}}\\ ,", "raw_count": 10, "count": 10, "decode_str": "}}\\,"} -{"id": 40130, "token": "\u0120f\u00c3\u0125", "merges": "\u0120f \u00c3\u0125", "raw_count": 10, "count": 10, "decode_str": " f\u00c3"} -{"id": 48817, "token": "}+{\\", "merges": "}+ {\\", "raw_count": 10, "count": 10, "decode_str": "}+{\\"} -{"id": 53776, "token": "\u00e8\u0143\u0123", "merges": "\u00e8\u0143 \u0123", "raw_count": 10, "count": 10, "decode_str": "\u8b41"} -{"id": 13854, "token": "\u00c2\u0126", "merges": "\u00c2 \u0126", "raw_count": 7, "count": 10, "decode_str": "\u0084"} -{"id": 31779, "token": "=\"../../../../../", "merges": "=\"../../../../ ../", "raw_count": 11, "count": 11, "decode_str": "=\"../../../../../"} -{"id": 38726, "token": "\u0120downregulation", "merges": "\u0120down regulation", "raw_count": 11, "count": 11, "decode_str": " downregulation"} -{"id": 43275, "token": "\u0120Numerous", "merges": "\u0120Numer ous", "raw_count": 11, "count": 11, "decode_str": " Numerous"} -{"id": 36805, "token": "\u0120oocytes", "merges": "\u0120o ocytes", "raw_count": 11, "count": 11, "decode_str": " oocytes"} -{"id": 8861, "token": "upgreek", "merges": "up greek", "raw_count": 11, "count": 11, "decode_str": "upgreek"} -{"id": 25349, "token": "))/((-", "merges": "))/( (-", "raw_count": 11, "count": 11, "decode_str": "))/((-"} -{"id": 11127, "token": ").$$", "merges": "). $$", "raw_count": 10, "count": 11, "decode_str": ").$$"} -{"id": 19562, "token": "\\}$.", "merges": "\\ }$.", "raw_count": 11, "count": 11, "decode_str": "\\}$."} -{"id": 26136, "token": "}}_\\", "merges": "}} _\\", "raw_count": 11, "count": 11, "decode_str": "}}_\\"} -{"id": 39096, "token": "\u0120mAb", "merges": "\u0120m Ab", "raw_count": 11, "count": 11, "decode_str": " mAb"} -{"id": 2947, "token": "],[@", "merges": "], [@", "raw_count": 11, "count": 11, "decode_str": "],[@"} -{"id": 2479, "token": "\u0120([@", "merges": "\u0120( [@", "raw_count": 11, "count": 11, "decode_str": " ([@"} -{"id": 47702, "token": "\u0120PCa", "merges": "\u0120PC a", "raw_count": 11, "count": 11, "decode_str": " PCa"} -{"id": 50319, "token": "\u00e2\u012a\u0141", "merges": "\u00e2\u012a \u0141", "raw_count": 11, "count": 11, "decode_str": "\u221f"} -{"id": 54272, "token": "\u00e9\u0139\u00a2", "merges": "\u00e9\u0139 \u00a2", "raw_count": 11, "count": 11, "decode_str": "\u95e2"} -{"id": 47571, "token": "\u0120immunostaining", "merges": "\u0120immunost aining", "raw_count": 12, "count": 12, "decode_str": " immunostaining"} -{"id": 8867, "token": "oddsidemargin", "merges": "odds idemargin", "raw_count": 12, "count": 12, "decode_str": "oddsidemargin"} -{"id": 38651, "token": "xymatrix", "merges": "xym atrix", "raw_count": 12, "count": 12, "decode_str": "xymatrix"} -{"id": 26712, "token": "\u0120Atty", "merges": "\u0120At ty", "raw_count": 12, "count": 12, "decode_str": " Atty"} -{"id": 14434, "token": "\u0120\"\u00e2\u013b\u00aa", "merges": "\u0120\" \u00e2\u013b\u00aa", "raw_count": 12, "count": 12, "decode_str": " \"\u266a"} -{"id": 33795, "token": "\u0120HeLa", "merges": "\u0120He La", "raw_count": 12, "count": 12, "decode_str": " HeLa"} -{"id": 48138, "token": ")}}{\\", "merges": ") }}{\\", "raw_count": 12, "count": 12, "decode_str": ")}}{\\"} -{"id": 16302, "token": "}}}_", "merges": "}} }_", "raw_count": 12, "count": 12, "decode_str": "}}}_"} -{"id": 43638, "token": "$.\\", "merges": "$. \\", "raw_count": 12, "count": 12, "decode_str": "$.\\"} -{"id": 14716, "token": "\u0120\u00c2\u0139", "merges": "\u0120\u00c2 \u0139", "raw_count": 12, "count": 12, "decode_str": " \u0097"} -{"id": 45509, "token": "\"}^", "merges": "\"} ^", "raw_count": 12, "count": 12, "decode_str": "\"}^"} -{"id": 43657, "token": ";{\\", "merges": "; {\\", "raw_count": 12, "count": 12, "decode_str": ";{\\"} -{"id": 19819, "token": "\u00c2\u0133", "merges": "\u00c2 \u0133", "raw_count": 12, "count": 12, "decode_str": "\u0091"} -{"id": 30477, "token": "\u0120upregulation", "merges": "\u0120up regulation", "raw_count": 13, "count": 13, "decode_str": " upregulation"} -{"id": 45707, "token": "}}})$", "merges": "}}} )$", "raw_count": 13, "count": 13, "decode_str": "}}})$"} -{"id": 28073, "token": "}}^\\", "merges": "}} ^\\", "raw_count": 13, "count": 13, "decode_str": "}}^\\"} -{"id": 37185, "token": "):=\\", "merges": "): =\\", "raw_count": 13, "count": 13, "decode_str": "):=\\"} -{"id": 42691, "token": "jcmm", "merges": "jc mm", "raw_count": 13, "count": 13, "decode_str": "jcmm"} -{"id": 35138, "token": "\u0120\\[*", "merges": "\u0120\\[ *", "raw_count": 13, "count": 13, "decode_str": " \\[*"} -{"id": 45472, "token": "]{})", "merges": "]{} )", "raw_count": 13, "count": 13, "decode_str": "]{})"} -{"id": 35729, "token": "}}+\\", "merges": "}} +\\", "raw_count": 13, "count": 13, "decode_str": "}}+\\"} -{"id": 49960, "token": "\u0120$(-", "merges": "\u0120$ (-", "raw_count": 13, "count": 13, "decode_str": " $(-"} -{"id": 37860, "token": "/{\\", "merges": "/ {\\", "raw_count": 13, "count": 13, "decode_str": "/{\\"} -{"id": 153, "token": "\u00dd", "merges": "NULL", "raw_count": 13, "count": 13, "decode_str": "\ufffd"} -{"id": 183, "token": "\u0106", "merges": "NULL", "raw_count": 13, "count": 13, "decode_str": "\u0006"} -{"id": 33763, "token": "=\"../../../../../../", "merges": "=\"../../../../ ../../", "raw_count": 14, "count": 14, "decode_str": "=\"../../../../../../"} -{"id": 34682, "token": "\u0120Redistributions", "merges": "\u0120Redist ributions", "raw_count": 14, "count": 14, "decode_str": " Redistributions"} -{"id": 34122, "token": "\u0120downregulated", "merges": "\u0120down regulated", "raw_count": 14, "count": 14, "decode_str": " downregulated"} -{"id": 45233, "token": "hookrightarrow", "merges": "hook rightarrow", "raw_count": 14, "count": 14, "decode_str": "hookrightarrow"} -{"id": 30960, "token": "\u0120luciferase", "merges": "\u0120luc iferase", "raw_count": 14, "count": 14, "decode_str": " luciferase"} -{"id": 8167, "token": "\u0120Defendant", "merges": "\u0120Def endant", "raw_count": 14, "count": 14, "decode_str": " Defendant"} -{"id": 46542, "token": "\u0120exosomes", "merges": "\u0120ex osomes", "raw_count": 14, "count": 14, "decode_str": " exosomes"} -{"id": 49169, "token": "GLIGENCE", "merges": "GL IGENCE", "raw_count": 8, "count": 14, "decode_str": "GLIGENCE"} -{"id": 32625, "token": "\u0120Taliban", "merges": "\u0120Tal iban", "raw_count": 14, "count": 14, "decode_str": " Taliban"} -{"id": 40557, "token": "\u0120\u00cf\u012e\u00cf\u0126\u00ce\u00b9", "merges": "\u0120\u00cf\u012e \u00cf\u0126\u00ce\u00b9", "raw_count": 14, "count": 14, "decode_str": " \u03cc\u03c4\u03b9"} -{"id": 37077, "token": ")\\].", "merges": ") \\].", "raw_count": 14, "count": 14, "decode_str": ")\\]."} -{"id": 17137, "token": "})$.", "merges": "} )$.", "raw_count": 14, "count": 14, "decode_str": "})$."} -{"id": 35655, "token": "\u0120BJP", "merges": "\u0120B JP", "raw_count": 14, "count": 14, "decode_str": " BJP"} -{"id": 50331, "token": "\u00e2\u012b\u00aa", "merges": "\u00e2\u012b \u00aa", "raw_count": 14, "count": 14, "decode_str": "\u226a"} -{"id": 50592, "token": "\u00e4\u00be\u00b7", "merges": "\u00e4\u00be \u00b7", "raw_count": 14, "count": 14, "decode_str": "\u4fb7"} -{"id": 14681, "token": "\u00c2\u012a", "merges": "\u00c2 \u012a", "raw_count": 14, "count": 14, "decode_str": "\u0088"} -{"id": 20006, "token": "\u00c2\u013a", "merges": "\u00c2 \u013a", "raw_count": 13, "count": 14, "decode_str": "\u0098"} -{"id": 196, "token": "\u0113", "merges": "NULL", "raw_count": 14, "count": 14, "decode_str": "\u0013"} -{"id": 48687, "token": "\u0120findViewById", "merges": "\u0120find ViewById", "raw_count": 15, "count": 15, "decode_str": " findViewById"} -{"id": 44694, "token": "\u0120lysed", "merges": "\u0120lys ed", "raw_count": 15, "count": 15, "decode_str": " lysed"} -{"id": 46880, "token": "\u0120///<", "merges": "\u0120/// <", "raw_count": 15, "count": 15, "decode_str": " ///<"} -{"id": 35487, "token": "\\]\\].", "merges": "\\] \\].", "raw_count": 15, "count": 15, "decode_str": "\\]\\]."} -{"id": 32399, "token": "\u0120----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------", "merges": "\u0120 ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------", "raw_count": 16, "count": 16, "decode_str": " ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------"} -{"id": 45373, "token": "\u0120Australians", "merges": "\u0120Austral ians", "raw_count": 16, "count": 16, "decode_str": " Australians"} -{"id": 43607, "token": "\u0120Respondents", "merges": "\u0120Respond ents", "raw_count": 16, "count": 16, "decode_str": " Respondents"} -{"id": 49950, "token": "\u0120CONCLUSION", "merges": "\u0120CON CLUSION", "raw_count": 16, "count": 16, "decode_str": " CONCLUSION"} -{"id": 37402, "token": "imonit", "merges": "imon it", "raw_count": 16, "count": 16, "decode_str": "imonit"} -{"id": 49819, "token": "hskip", "merges": "h skip", "raw_count": 16, "count": 16, "decode_str": "hskip"} -{"id": 41780, "token": ")}=\\", "merges": ")} =\\", "raw_count": 16, "count": 16, "decode_str": ")}=\\"} -{"id": 38229, "token": "\u0120n\u00c3\u0125", "merges": "\u0120n \u00c3\u0125", "raw_count": 16, "count": 16, "decode_str": " n\u00c3"} -{"id": 50327, "token": "\u00e2\u012b\u0134", "merges": "\u00e2\u012b \u0134", "raw_count": 16, "count": 16, "decode_str": "\u2252"} -{"id": 49806, "token": "]$$", "merges": "] $$", "raw_count": 16, "count": 16, "decode_str": "]$$"} -{"id": 51628, "token": "\u00e5\u00bd\u00ab", "merges": "\u00e5\u00bd \u00ab", "raw_count": 16, "count": 16, "decode_str": "\u5f6b"} -{"id": 18994, "token": "\u00c2\u0129", "merges": "\u00c2 \u0129", "raw_count": 16, "count": 16, "decode_str": "\u0087"} -{"id": 24372, "token": "\u00c2\u012b", "merges": "\u00c2 \u012b", "raw_count": 16, "count": 16, "decode_str": "\u0089"} -{"id": 26261, "token": "\u00c2\u012c", "merges": "\u00c2 \u012c", "raw_count": 16, "count": 16, "decode_str": "\u008a"} -{"id": 198, "token": "\u0115", "merges": "NULL", "raw_count": 16, "count": 16, "decode_str": "\u0015"} -{"id": 46338, "token": "\u0120Sentencing", "merges": "\u0120Sent encing", "raw_count": 17, "count": 17, "decode_str": " Sentencing"} -{"id": 43029, "token": "AFFIRMED", "merges": "A FFIRMED", "raw_count": 17, "count": 17, "decode_str": "AFFIRMED"} -{"id": 28696, "token": "FFIRMED", "merges": "FFIR MED", "raw_count": 0, "count": 17, "decode_str": "FFIRMED"} -{"id": 49659, "token": "\u0120j\u00c3\u00a4sen", "merges": "\u0120j\u00c3\u00a4 sen", "raw_count": 17, "count": 17, "decode_str": " j\u00e4sen"} -{"id": 27790, "token": "}}_{{\\", "merges": "}} _{{\\", "raw_count": 17, "count": 17, "decode_str": "}}_{{\\"} -{"id": 38225, "token": ")}_{\\", "merges": ")} _{\\", "raw_count": 17, "count": 17, "decode_str": ")}_{\\"} -{"id": 49406, "token": "\u0120\u00c3\u00aent", "merges": "\u0120\u00c3\u00ae nt", "raw_count": 17, "count": 17, "decode_str": " \u00eent"} -{"id": 10791, "token": "}({\\", "merges": "}( {\\", "raw_count": 17, "count": 17, "decode_str": "}({\\"} -{"id": 39294, "token": ")={\\", "merges": ")= {\\", "raw_count": 17, "count": 17, "decode_str": ")={\\"} -{"id": 40227, "token": ")}$$", "merges": ") }$$", "raw_count": 17, "count": 17, "decode_str": ")}$$"} -{"id": 23125, "token": "pntd", "merges": "pnt d", "raw_count": 17, "count": 17, "decode_str": "pntd"} -{"id": 43044, "token": "\u0120\u00c2\u0143", "merges": "\u0120\u00c2 \u0143", "raw_count": 17, "count": 17, "decode_str": " \u00ad"} -{"id": 207, "token": "\u011e", "merges": "NULL", "raw_count": 17, "count": 17, "decode_str": "\u001e"} -{"id": 44701, "token": "\u0120overexpressed", "merges": "\u0120overex pressed", "raw_count": 18, "count": 18, "decode_str": " overexpressed"} -{"id": 45359, "token": "\u0120Africans", "merges": "\u0120Afric ans", "raw_count": 18, "count": 18, "decode_str": " Africans"} -{"id": 10131, "token": "\u0120uintptr", "merges": "\u0120uint ptr", "raw_count": 18, "count": 18, "decode_str": " uintptr"} -{"id": 41538, "token": "\u0120Corbyn", "merges": "\u0120Corb yn", "raw_count": 18, "count": 18, "decode_str": " Corbyn"} -{"id": 45094, "token": "\u0120ocks", "merges": "\u0120o cks", "raw_count": 10, "count": 18, "decode_str": " ocks"} -{"id": 29230, "token": "\u0120Figs", "merges": "\u0120Fig s", "raw_count": 18, "count": 18, "decode_str": " Figs"} -{"id": 16990, "token": "\u00c3\u0125\u00c3\u0124", "merges": "\u00c3\u0125 \u00c3\u0124", "raw_count": 18, "count": 18, "decode_str": "\u00c3\u00c2"} -{"id": 18251, "token": "\u00c3\u0132\u00c2\u00b5", "merges": "\u00c3\u0132 \u00c2\u00b5", "raw_count": 5, "count": 18, "decode_str": "\u00d0\u00b5"} -{"id": 45662, "token": "\\]](", "merges": "\\] ](", "raw_count": 18, "count": 18, "decode_str": "\\]]("} -{"id": 21067, "token": "\u0120\u00c5\u0141i", "merges": "\u0120\u00c5\u0141 i", "raw_count": 18, "count": 18, "decode_str": " \u015fi"} -{"id": 43742, "token": "})$$", "merges": "})$ $", "raw_count": 18, "count": 18, "decode_str": "})$$"} -{"id": 34813, "token": "|_{\\", "merges": "| _{\\", "raw_count": 18, "count": 18, "decode_str": "|_{\\"} -{"id": 28903, "token": "\u0120\u00ce\u00bcl", "merges": "\u0120\u00ce\u00bc l", "raw_count": 18, "count": 18, "decode_str": " \u03bcl"} -{"id": 22001, "token": "-{\\", "merges": "- {\\", "raw_count": 18, "count": 18, "decode_str": "-{\\"} -{"id": 36576, "token": "$}}", "merges": "$ }}", "raw_count": 18, "count": 18, "decode_str": "$}}"} -{"id": 25371, "token": "\u00c2\u0138", "merges": "\u00c2 \u0138", "raw_count": 18, "count": 18, "decode_str": "\u0096"} -{"id": 17858, "token": "\u0120transfected", "merges": "\u0120trans fected", "raw_count": 19, "count": 19, "decode_str": " transfected"} -{"id": 15707, "token": "\u0120]{}", "merges": "\u0120 ]{}", "raw_count": 19, "count": 19, "decode_str": " ]{}"} -{"id": 16746, "token": "({{\\", "merges": "( {{\\", "raw_count": 19, "count": 19, "decode_str": "({{\\"} -{"id": 34801, "token": "))$.", "merges": ") )$.", "raw_count": 19, "count": 19, "decode_str": "))$."} -{"id": 7610, "token": "ijms", "merges": "ij ms", "raw_count": 19, "count": 19, "decode_str": "ijms"} -{"id": 20236, "token": "\u00c2\u013b", "merges": "\u00c2 \u013b", "raw_count": 19, "count": 19, "decode_str": "\u0099"} -{"id": 205, "token": "\u011c", "merges": "NULL", "raw_count": 19, "count": 19, "decode_str": "\u001c"} -{"id": 29881, "token": "\u0120centrifuged", "merges": "\u0120centrifug ed", "raw_count": 20, "count": 20, "decode_str": " centrifuged"} -{"id": 38421, "token": "Defendants", "merges": "Def endants", "raw_count": 20, "count": 20, "decode_str": "Defendants"} -{"id": 19747, "token": "boldmath", "merges": "bold math", "raw_count": 20, "count": 20, "decode_str": "boldmath"} -{"id": 42795, "token": "\u0120Saddam", "merges": "\u0120S addam", "raw_count": 20, "count": 20, "decode_str": " Saddam"} -{"id": 41136, "token": "\u0120Qaeda", "merges": "\u0120Q aeda", "raw_count": 20, "count": 20, "decode_str": " Qaeda"} -{"id": 45605, "token": "\u0120CXCR", "merges": "\u0120CX CR", "raw_count": 20, "count": 20, "decode_str": " CXCR"} -{"id": 38850, "token": "Bankr", "merges": "Bank r", "raw_count": 20, "count": 20, "decode_str": "Bankr"} -{"id": 27501, "token": "\u0120[]{", "merges": "\u0120[ ]{", "raw_count": 20, "count": 20, "decode_str": " []{"} -{"id": 40344, "token": "\u0120immunoblot", "merges": "\u0120immun oblot", "raw_count": 21, "count": 21, "decode_str": " immunoblot"} -{"id": 44987, "token": "\u0120Fran\u00c3\u00a7ois", "merges": "\u0120Fran \u00c3\u00a7ois", "raw_count": 21, "count": 21, "decode_str": " Fran\u00e7ois"} -{"id": 32846, "token": "\u0120Canadians", "merges": "\u0120Canad ians", "raw_count": 21, "count": 21, "decode_str": " Canadians"} -{"id": 47732, "token": "\u0120Steelers", "merges": "\u0120Steel ers", "raw_count": 21, "count": 21, "decode_str": " Steelers"} -{"id": 49080, "token": "\u0120PROFITS", "merges": "\u0120PROF ITS", "raw_count": 21, "count": 21, "decode_str": " PROFITS"} -{"id": 46795, "token": "\u0120Bosnia", "merges": "\u0120Bos nia", "raw_count": 21, "count": 21, "decode_str": " Bosnia"} -{"id": 26071, "token": "Errorf", "merges": "Error f", "raw_count": 21, "count": 21, "decode_str": "Errorf"} -{"id": 28171, "token": "bigcup", "merges": "big cup", "raw_count": 21, "count": 21, "decode_str": "bigcup"} -{"id": 42643, "token": "_{|", "merges": "_{ |", "raw_count": 21, "count": 21, "decode_str": "_{|"} -{"id": 19481, "token": "\u0120\\~", "merges": "\u0120\\ ~", "raw_count": 21, "count": 21, "decode_str": " \\~"} -{"id": 52422, "token": "\u00e6\u00ae\u0143", "merges": "\u00e6\u00ae \u0143", "raw_count": 21, "count": 21, "decode_str": "\u6bad"} -{"id": 35329, "token": "\u0120Conclusions", "merges": "\u0120Con clusions", "raw_count": 22, "count": 22, "decode_str": " Conclusions"} -{"id": 49059, "token": "\u0120Attorneys", "merges": "\u0120Att orneys", "raw_count": 22, "count": 22, "decode_str": " Attorneys"} -{"id": 34538, "token": "\u0120Pakistani", "merges": "\u0120Pak istani", "raw_count": 22, "count": 22, "decode_str": " Pakistani"} -{"id": 45002, "token": "\u0120\u00cf\u0122\u00ce\u00bf\u00ce\u00bb", "merges": "\u0120\u00cf\u0122 \u00ce\u00bf\u00ce\u00bb", "raw_count": 22, "count": 22, "decode_str": " \u03c0\u03bf\u03bb"} -{"id": 48443, "token": "\u0120eluted", "merges": "\u0120el uted", "raw_count": 22, "count": 22, "decode_str": " eluted"} -{"id": 12945, "token": "}$$\\", "merges": "}$ $\\", "raw_count": 22, "count": 22, "decode_str": "}$$\\"} -{"id": 24281, "token": "\u0120$-$", "merges": "\u0120$- $", "raw_count": 22, "count": 22, "decode_str": " $-$"} -{"id": 43736, "token": "\u0120$<$", "merges": "\u0120$< $", "raw_count": 22, "count": 22, "decode_str": " $<$"} -{"id": 34210, "token": "\u00c2\u0140", "merges": "\u00c2 \u0140", "raw_count": 22, "count": 22, "decode_str": "\u009e"} -{"id": 19326, "token": "scriptstyle", "merges": "script style", "raw_count": 22, "count": 23, "decode_str": "scriptstyle"} -{"id": 47536, "token": "\u0120adipocytes", "merges": "\u0120adip ocytes", "raw_count": 23, "count": 23, "decode_str": " adipocytes"} -{"id": 35335, "token": "\u0120Parlement", "merges": "\u0120Par lement", "raw_count": 23, "count": 23, "decode_str": " Parlement"} -{"id": 33097, "token": "\u0120Catholics", "merges": "\u0120Cath olics", "raw_count": 23, "count": 23, "decode_str": " Catholics"} -{"id": 22049, "token": "\u0120\u00e2\u0122\u0135,", "merges": "\u0120\u00e2\u0122\u0135 ,", "raw_count": 23, "count": 23, "decode_str": " \u2013,"} -{"id": 3951, "token": "^[@", "merges": "^ [@", "raw_count": 23, "count": 23, "decode_str": "^[@"} -{"id": 46986, "token": "\\,$", "merges": "\\, $", "raw_count": 23, "count": 23, "decode_str": "\\,$"} -{"id": 50376, "token": "\u00e2\u0139\u0142", "merges": "\u00e2\u0139 \u0142", "raw_count": 23, "count": 23, "decode_str": "\u25e0"} -{"id": 23002, "token": "+{\\", "merges": "+ {\\", "raw_count": 23, "count": 23, "decode_str": "+{\\"} -{"id": 17719, "token": "\u00c2\u0134", "merges": "\u00c2 \u0134", "raw_count": 23, "count": 23, "decode_str": "\u0092"} -{"id": 12555, "token": "\u00c2\u0139", "merges": "\u00c2 \u0139", "raw_count": 23, "count": 23, "decode_str": "\u0097"} -{"id": 37826, "token": "xrightarrow", "merges": "x rightarrow", "raw_count": 24, "count": 24, "decode_str": "xrightarrow"} -{"id": 50201, "token": "\u0120mycket", "merges": "\u0120my cket", "raw_count": 24, "count": 24, "decode_str": " mycket"} -{"id": 32885, "token": "\u0120Hamas", "merges": "\u0120Ham as", "raw_count": 24, "count": 24, "decode_str": " Hamas"} -{"id": 32673, "token": "}}^{(", "merges": "}} ^{(", "raw_count": 24, "count": 24, "decode_str": "}}^{("} -{"id": 47260, "token": "\u0120}^{", "merges": "\u0120} ^{", "raw_count": 24, "count": 24, "decode_str": " }^{"} -{"id": 37299, "token": "}\\}$", "merges": "}\\ }$", "raw_count": 24, "count": 24, "decode_str": "}\\}$"} -{"id": 44454, "token": "\u0120JNK", "merges": "\u0120J NK", "raw_count": 24, "count": 24, "decode_str": " JNK"} -{"id": 50807, "token": "\u00e5\u012b\u00b7", "merges": "\u00e5\u012b \u00b7", "raw_count": 24, "count": 24, "decode_str": "\u5277"} -{"id": 8562, "token": "]^.", "merges": "]^ .", "raw_count": 24, "count": 24, "decode_str": "]^."} -{"id": 43009, "token": "\u0120proinflammatory", "merges": "\u0120pro inflammatory", "raw_count": 25, "count": 25, "decode_str": " proinflammatory"} -{"id": 33053, "token": "biomolecules", "merges": "biom olecules", "raw_count": 25, "count": 25, "decode_str": "biomolecules"} -{"id": 41172, "token": "\u0120Liberals", "merges": "\u0120Liber als", "raw_count": 25, "count": 25, "decode_str": " Liberals"} -{"id": 49248, "token": "\u0120TEXAS", "merges": "\u0120TEX AS", "raw_count": 25, "count": 25, "decode_str": " TEXAS"} -{"id": 26398, "token": "_{(\\", "merges": "_{ (\\", "raw_count": 25, "count": 25, "decode_str": "_{(\\"} -{"id": 49793, "token": "-\u00e2\u0124\u00ac", "merges": "- \u00e2\u0124\u00ac", "raw_count": 25, "count": 25, "decode_str": "-\u20ac"} -{"id": 24680, "token": "\u0120upregulated", "merges": "\u0120up regulated", "raw_count": 26, "count": 26, "decode_str": " upregulated"} -{"id": 30079, "token": "})=\\", "merges": "}) =\\", "raw_count": 26, "count": 26, "decode_str": "})=\\"} -{"id": 19181, "token": "]{}.", "merges": "]{} .", "raw_count": 26, "count": 26, "decode_str": "]{}."} -{"id": 13704, "token": "\u0120\u00c2\u0142\u00c2\u0142\u0120\u00c2\u0142\u00c2\u0142", "merges": "\u0120\u00c2\u0142\u00c2\u0142 \u0120\u00c2\u0142\u00c2\u0142", "raw_count": 11, "count": 27, "decode_str": " \u00a0\u00a0 \u00a0\u00a0"} -{"id": 33682, "token": "\u0120Appellate", "merges": "\u0120App ellate", "raw_count": 27, "count": 27, "decode_str": " Appellate"} -{"id": 36645, "token": "Plaintiffs", "merges": "Plaintiff s", "raw_count": 27, "count": 27, "decode_str": "Plaintiffs"} -{"id": 47654, "token": "\u0120Statutes", "merges": "\u0120Stat utes", "raw_count": 27, "count": 27, "decode_str": " Statutes"} -{"id": 42685, "token": "\u0120europea", "merges": "\u0120europe a", "raw_count": 27, "count": 27, "decode_str": " europea"} -{"id": 18866, "token": ",\\,\\", "merges": ",\\ ,\\", "raw_count": 27, "count": 27, "decode_str": ",\\,\\"} -{"id": 6334, "token": ".[@", "merges": ". [@", "raw_count": 27, "count": 27, "decode_str": ".[@"} -{"id": 50295, "token": "\u00e2\u0122\u00a5", "merges": "\u00e2\u0122 \u00a5", "raw_count": 27, "count": 27, "decode_str": "\u2025"} -{"id": 16605, "token": "\u00c2\u013e", "merges": "\u00c2 \u013e", "raw_count": 27, "count": 27, "decode_str": "\u009c"} -{"id": 17237, "token": "\u00c2\u0137", "merges": "\u00c2 \u0137", "raw_count": 27, "count": 27, "decode_str": "\u0095"} -{"id": 46822, "token": "\u0120AMPK", "merges": "\u0120AMP K", "raw_count": 28, "count": 28, "decode_str": " AMPK"} -{"id": 42762, "token": "\u0120CXCL", "merges": "\u0120CX CL", "raw_count": 28, "count": 28, "decode_str": " CXCL"} -{"id": 46479, "token": "\u0120\\|_{", "merges": "\u0120\\| _{", "raw_count": 28, "count": 28, "decode_str": " \\|_{"} -{"id": 33570, "token": "\u0120Ariz", "merges": "\u0120Ari z", "raw_count": 28, "count": 28, "decode_str": " Ariz"} -{"id": 34942, "token": "}$).", "merges": "}$ ).", "raw_count": 28, "count": 28, "decode_str": "}$)."} -{"id": 42274, "token": "]{}[", "merges": "]{} [", "raw_count": 28, "count": 28, "decode_str": "]{}["} -{"id": 49760, "token": "IRQHandler", "merges": "IRQ Handler", "raw_count": 29, "count": 29, "decode_str": "IRQHandler"} -{"id": 38481, "token": "\u0120integrin", "merges": "\u0120integr in", "raw_count": 29, "count": 29, "decode_str": " integrin"} -{"id": 48738, "token": "\u00e2\u0122\u0125\u00e2\u0122\u0125\u00e2\u0122\u0125", "merges": "\u00e2\u0122\u0125\u00e2\u0122\u0125 \u00e2\u0122\u0125", "raw_count": 29, "count": 29, "decode_str": "\u2003\u2003\u2003"} -{"id": 31667, "token": "\\}_{", "merges": "\\ }_{", "raw_count": 29, "count": 29, "decode_str": "\\}_{"} -{"id": 50791, "token": "\u00e5\u012b\u012b", "merges": "\u00e5\u012b \u012b", "raw_count": 29, "count": 29, "decode_str": "\u5249"} -{"id": 193, "token": "\u0110", "merges": "NULL", "raw_count": 29, "count": 29, "decode_str": "\u0010"} -{"id": 41346, "token": "\u0120neurodegenerative", "merges": "\u0120neurode generative", "raw_count": 30, "count": 30, "decode_str": " neurodegenerative"} -{"id": 46527, "token": "\u0120Magistrate", "merges": "\u0120Mag istrate", "raw_count": 30, "count": 30, "decode_str": " Magistrate"} -{"id": 47351, "token": "\u0120chemokine", "merges": "\u0120chemok ine", "raw_count": 30, "count": 30, "decode_str": " chemokine"} -{"id": 47598, "token": "\u0120Kavanaugh", "merges": "\u0120K avanaugh", "raw_count": 30, "count": 30, "decode_str": " Kavanaugh"} -{"id": 20866, "token": "leqslant", "merges": "leq slant", "raw_count": 30, "count": 30, "decode_str": "leqslant"} -{"id": 47766, "token": "\u0120Kerala", "merges": "\u0120K erala", "raw_count": 30, "count": 30, "decode_str": " Kerala"} -{"id": 46034, "token": "\u0120RNase", "merges": "\u0120RN ase", "raw_count": 30, "count": 30, "decode_str": " RNase"} -{"id": 39939, "token": "\u0120h\u00c3\u00a4n", "merges": "\u0120h \u00c3\u00a4n", "raw_count": 30, "count": 30, "decode_str": " h\u00e4n"} -{"id": 17334, "token": "\u0120$|\\", "merges": "\u0120$ |\\", "raw_count": 30, "count": 30, "decode_str": " $|\\"} -{"id": 42637, "token": "}}-\\", "merges": "}} -\\", "raw_count": 30, "count": 30, "decode_str": "}}-\\"} -{"id": 39106, "token": "}^+", "merges": "}^ +", "raw_count": 30, "count": 30, "decode_str": "}^+"} -{"id": 21837, "token": "|{\\", "merges": "| {\\", "raw_count": 30, "count": 30, "decode_str": "|{\\"} -{"id": 43748, "token": "\u0120Caucasian", "merges": "\u0120Cauc asian", "raw_count": 31, "count": 31, "decode_str": " Caucasian"} -{"id": 42173, "token": "\u0120Amended", "merges": "\u0120Am ended", "raw_count": 31, "count": 31, "decode_str": " Amended"} -{"id": 46699, "token": "\u0120Somalia", "merges": "\u0120Somal ia", "raw_count": 31, "count": 31, "decode_str": " Somalia"} -{"id": 24923, "token": "\u0120Iraqi", "merges": "\u0120Iraq i", "raw_count": 31, "count": 31, "decode_str": " Iraqi"} -{"id": 32603, "token": "textup", "merges": "text up", "raw_count": 31, "count": 31, "decode_str": "textup"} -{"id": 39004, "token": "\u0120Arabs", "merges": "\u0120Ar abs", "raw_count": 31, "count": 31, "decode_str": " Arabs"} -{"id": 17738, "token": "}_{{\\", "merges": "}_{ {\\", "raw_count": 31, "count": 31, "decode_str": "}_{{\\"} -{"id": 47402, "token": "})^{\\", "merges": "}) ^{\\", "raw_count": 31, "count": 31, "decode_str": "})^{\\"} -{"id": 30634, "token": ")_{\\", "merges": ") _{\\", "raw_count": 31, "count": 31, "decode_str": ")_{\\"} -{"id": 2367, "token": "\u0120${\\", "merges": "\u0120$ {\\", "raw_count": 31, "count": 31, "decode_str": " ${\\"} -{"id": 25778, "token": "\u0120\u00c3\u0130", "merges": "\u0120\u00c3 \u0130", "raw_count": 31, "count": 31, "decode_str": " \u00ce"} -{"id": 13033, "token": "\u0120\u00c3\u0132", "merges": "\u0120\u00c3 \u0132", "raw_count": 31, "count": 31, "decode_str": " \u00d0"} -{"id": 11400, "token": ",{\\", "merges": ", {\\", "raw_count": 31, "count": 31, "decode_str": ",{\\"} -{"id": 40598, "token": "\u0120Schr\u00c3\u00b6dinger", "merges": "\u0120Schr \u00c3\u00b6dinger", "raw_count": 32, "count": 32, "decode_str": " Schr\u00f6dinger"} -{"id": 33041, "token": "\u0120Thereafter", "merges": "\u0120There after", "raw_count": 32, "count": 32, "decode_str": " Thereafter"} -{"id": 36325, "token": "\u0120immunost", "merges": "\u0120immun ost", "raw_count": 20, "count": 32, "decode_str": " immunost"} -{"id": 46142, "token": "\u0120luminal", "merges": "\u0120lum inal", "raw_count": 32, "count": 32, "decode_str": " luminal"} -{"id": 49405, "token": "\u00c3\u00a9sident", "merges": "\u00c3\u00a9s ident", "raw_count": 32, "count": 32, "decode_str": "\u00e9sident"} -{"id": 42680, "token": "\u0120Comiss", "merges": "\u0120Com iss", "raw_count": 24, "count": 32, "decode_str": " Comiss"} -{"id": 35496, "token": "**--**", "merges": "** --**", "raw_count": 32, "count": 32, "decode_str": "**--**"} -{"id": 29748, "token": "}}{{\\", "merges": "}} {{\\", "raw_count": 32, "count": 32, "decode_str": "}}{{\\"} -{"id": 49408, "token": "\u0120RPMI", "merges": "\u0120RP MI", "raw_count": 32, "count": 32, "decode_str": " RPMI"} -{"id": 39099, "token": "\u0120HDAC", "merges": "\u0120HD AC", "raw_count": 32, "count": 32, "decode_str": " HDAC"} -{"id": 40125, "token": "]^{\\", "merges": "] ^{\\", "raw_count": 32, "count": 32, "decode_str": "]^{\\"} -{"id": 45637, "token": "\u0120(\\#", "merges": "\u0120(\\ #", "raw_count": 32, "count": 32, "decode_str": " (\\#"} -{"id": 50332, "token": "\u00e2\u012b\u00ab", "merges": "\u00e2\u012b \u00ab", "raw_count": 32, "count": 32, "decode_str": "\u226b"} -{"id": 50339, "token": "\u00e2\u0136\u0128", "merges": "\u00e2\u0136 \u0128", "raw_count": 32, "count": 32, "decode_str": "\u2506"} -{"id": 36929, "token": "\u0120malignancies", "merges": "\u0120malign ancies", "raw_count": 33, "count": 33, "decode_str": " malignancies"} -{"id": 42624, "token": "\u0120Archbishop", "merges": "\u0120Arch bishop", "raw_count": 33, "count": 33, "decode_str": " Archbishop"} -{"id": 34045, "token": "\u0120skulle", "merges": "\u0120sk ulle", "raw_count": 33, "count": 33, "decode_str": " skulle"} -{"id": 38220, "token": "\u0120Assad", "merges": "\u0120Ass ad", "raw_count": 33, "count": 33, "decode_str": " Assad"} -{"id": 49869, "token": "\u0120----,", "merges": "\u0120---- ,", "raw_count": 33, "count": 33, "decode_str": " ----,"} -{"id": 48963, "token": ")|$(", "merges": ")| $(", "raw_count": 33, "count": 33, "decode_str": ")|$("} -{"id": 20744, "token": ";\\;\\", "merges": ";\\ ;\\", "raw_count": 33, "count": 33, "decode_str": ";\\;\\"} -{"id": 14082, "token": "\u0120&=&", "merges": "\u0120&= &", "raw_count": 33, "count": 33, "decode_str": " &=&"} -{"id": 28599, "token": "\u0120\u00c2\u00bb,", "merges": "\u0120\u00c2\u00bb ,", "raw_count": 33, "count": 33, "decode_str": " \u00bb,"} -{"id": 16550, "token": ")$-", "merges": ")$ -", "raw_count": 33, "count": 33, "decode_str": ")$-"} -{"id": 15728, "token": "}$-", "merges": "}$ -", "raw_count": 33, "count": 33, "decode_str": "}$-"} -{"id": 33671, "token": "\u0120Europeans", "merges": "\u0120Europe ans", "raw_count": 34, "count": 34, "decode_str": " Europeans"} -{"id": 39734, "token": "\u0120cytosolic", "merges": "\u0120cytos olic", "raw_count": 34, "count": 34, "decode_str": " cytosolic"} -{"id": 10809, "token": "\u0120$\\{", "merges": "\u0120$\\ {", "raw_count": 34, "count": 34, "decode_str": " $\\{"} -{"id": 35386, "token": "Rptr", "merges": "R ptr", "raw_count": 34, "count": 34, "decode_str": "Rptr"} -{"id": 50381, "token": "\u00e2\u013a\u00bc", "merges": "\u00e2\u013a \u00bc", "raw_count": 34, "count": 34, "decode_str": "\u263c"} -{"id": 54390, "token": "\u00e9\u013e\u0133", "merges": "\u00e9\u013e \u0133", "raw_count": 34, "count": 34, "decode_str": "\u9711"} -{"id": 36889, "token": "\u0120immunoprecip", "merges": "\u0120immun oprecip", "raw_count": 35, "count": 35, "decode_str": " immunoprecip"} -{"id": 16492, "token": "\u0120Muslims", "merges": "\u0120Muslim s", "raw_count": 35, "count": 35, "decode_str": " Muslims"} -{"id": 36985, "token": "bigoplus", "merges": "big oplus", "raw_count": 35, "count": 35, "decode_str": "bigoplus"} -{"id": 38414, "token": ")}}\\", "merges": ") }}\\", "raw_count": 35, "count": 35, "decode_str": ")}}\\"} -{"id": 52691, "token": "\u00e6\u00ba\u00bc", "merges": "\u00e6\u00ba \u00bc", "raw_count": 35, "count": 35, "decode_str": "\u6ebc"} -{"id": 20481, "token": "]$.", "merges": "] $.", "raw_count": 35, "count": 35, "decode_str": "]$."} -{"id": 52959, "token": "\u00e7\u013b\u00a1", "merges": "\u00e7\u013b \u00a1", "raw_count": 35, "count": 35, "decode_str": "\u7661"} -{"id": 37805, "token": "\u0120Charleston", "merges": "\u0120Charl eston", "raw_count": 36, "count": 36, "decode_str": " Charleston"} -{"id": 39094, "token": "\u0120Netanyahu", "merges": "\u0120Net anyahu", "raw_count": 36, "count": 36, "decode_str": " Netanyahu"} -{"id": 29762, "token": "fasterxml", "merges": "faster xml", "raw_count": 36, "count": 36, "decode_str": "fasterxml"} -{"id": 41340, "token": "\u0120Kurdish", "merges": "\u0120Kurd ish", "raw_count": 36, "count": 36, "decode_str": " Kurdish"} -{"id": 45962, "token": "\u0120belang", "merges": "\u0120bel ang", "raw_count": 36, "count": 36, "decode_str": " belang"} -{"id": 44918, "token": "\u0120my\u00c3\u00b6s", "merges": "\u0120my \u00c3\u00b6s", "raw_count": 36, "count": 36, "decode_str": " my\u00f6s"} -{"id": 13093, "token": "\\!\\!", "merges": "\\! \\!", "raw_count": 29, "count": 36, "decode_str": "\\!\\!"} -{"id": 49694, "token": "\u0120([*", "merges": "\u0120([ *", "raw_count": 36, "count": 36, "decode_str": " ([*"} -{"id": 47942, "token": "^*(\\", "merges": "^* (\\", "raw_count": 36, "count": 36, "decode_str": "^*(\\"} -{"id": 19022, "token": "^{{\\", "merges": "^{ {\\", "raw_count": 36, "count": 36, "decode_str": "^{{\\"} -{"id": 27618, "token": "[]$", "merges": "[] $", "raw_count": 36, "count": 36, "decode_str": "[]$"} -{"id": 33541, "token": "\u00c5\u00a3i", "merges": "\u00c5\u00a3 i", "raw_count": 36, "count": 36, "decode_str": "\u0163i"} -{"id": 4253, "token": "){#", "merges": "){ #", "raw_count": 36, "count": 36, "decode_str": "){#"} -{"id": 27399, "token": "\u00c2\u0135", "merges": "\u00c2 \u0135", "raw_count": 36, "count": 36, "decode_str": "\u0093"} -{"id": 181, "token": "\u0104", "merges": "NULL", "raw_count": 36, "count": 36, "decode_str": "\u0004"} -{"id": 49920, "token": "\u0120Personally", "merges": "\u0120Person ally", "raw_count": 37, "count": 37, "decode_str": " Personally"} -{"id": 39492, "token": "\u0120Louisville", "merges": "\u0120Louis ville", "raw_count": 37, "count": 37, "decode_str": " Louisville"} -{"id": 39267, "token": "omitempty", "merges": "omit empty", "raw_count": 37, "count": 37, "decode_str": "omitempty"} -{"id": 39537, "token": ".\u00e2\u0122\u013f).", "merges": ".\u00e2\u0122\u013f ).", "raw_count": 37, "count": 37, "decode_str": ".\u201d)."} -{"id": 22520, "token": "\u0120\u00c3\u0133", "merges": "\u0120\u00c3 \u0133", "raw_count": 37, "count": 37, "decode_str": " \u00d1"} -{"id": 53900, "token": "\u00e8\u00b1\u0136", "merges": "\u00e8\u00b1 \u0136", "raw_count": 37, "count": 37, "decode_str": "\u8c54"} -{"id": 27212, "token": "\\%$", "merges": "\\% $", "raw_count": 37, "count": 37, "decode_str": "\\%$"} -{"id": 13348, "token": "\u00c2\u012e", "merges": "\u00c2 \u012e", "raw_count": 37, "count": 37, "decode_str": "\u008c"} -{"id": 48642, "token": "\u0120Punjab", "merges": "\u0120Pun jab", "raw_count": 38, "count": 38, "decode_str": " Punjab"} -{"id": 38560, "token": "ORANDUM", "merges": "ORAND UM", "raw_count": 38, "count": 38, "decode_str": "ORANDUM"} -{"id": 46005, "token": "\u0120Rabbi", "merges": "\u0120Rab bi", "raw_count": 38, "count": 38, "decode_str": " Rabbi"} -{"id": 44766, "token": "}}}=", "merges": "}} }=", "raw_count": 38, "count": 38, "decode_str": "}}}="} -{"id": 41284, "token": "/((-", "merges": "/( (-", "raw_count": 38, "count": 38, "decode_str": "/((-"} -{"id": 19911, "token": "\u0120overexpression", "merges": "\u0120overex pression", "raw_count": 39, "count": 39, "decode_str": " overexpression"} -{"id": 39056, "token": "\u0120Fourteenth", "merges": "\u0120Four teenth", "raw_count": 39, "count": 39, "decode_str": " Fourteenth"} -{"id": 45207, "token": "\u0120Nigerian", "merges": "\u0120Niger ian", "raw_count": 39, "count": 39, "decode_str": " Nigerian"} -{"id": 48046, "token": "\u0120Winnipeg", "merges": "\u0120Winn ipeg", "raw_count": 39, "count": 39, "decode_str": " Winnipeg"} -{"id": 49971, "token": "\u0120Anglican", "merges": "\u0120Anglic an", "raw_count": 39, "count": 39, "decode_str": " Anglican"} -{"id": 50028, "token": "\u0120Eleventh", "merges": "\u0120Ele venth", "raw_count": 39, "count": 39, "decode_str": " Eleventh"} -{"id": 35775, "token": "\u0120Shortly", "merges": "\u0120Short ly", "raw_count": 39, "count": 39, "decode_str": " Shortly"} -{"id": 46555, "token": "\u0120Azerba", "merges": "\u0120A zerba", "raw_count": 39, "count": 39, "decode_str": " Azerba"} -{"id": 46099, "token": "\u0120JHEP", "merges": "\u0120J HEP", "raw_count": 39, "count": 39, "decode_str": " JHEP"} -{"id": 45868, "token": "\u0120DEGs", "merges": "\u0120DE Gs", "raw_count": 39, "count": 39, "decode_str": " DEGs"} -{"id": 37075, "token": "RSOS", "merges": "RS OS", "raw_count": 39, "count": 39, "decode_str": "RSOS"} -{"id": 46938, "token": "\u0120}_", "merges": "\u0120} _", "raw_count": 39, "count": 39, "decode_str": " }_"} -{"id": 24943, "token": "{$\\", "merges": "{ $\\", "raw_count": 39, "count": 39, "decode_str": "{$\\"} -{"id": 48776, "token": "\u0120doxorubicin", "merges": "\u0120doxor ubicin", "raw_count": 40, "count": 40, "decode_str": " doxorubicin"} -{"id": 40198, "token": "\u0120millilitres", "merges": "\u0120millilit res", "raw_count": 40, "count": 40, "decode_str": " millilitres"} -{"id": 48665, "token": "\u0120Arabidopsis", "merges": "\u0120Arab idopsis", "raw_count": 40, "count": 40, "decode_str": " Arabidopsis"} -{"id": 24794, "token": "\u0120Russians", "merges": "\u0120Russ ians", "raw_count": 40, "count": 40, "decode_str": " Russians"} -{"id": 33857, "token": "mathds", "merges": "math ds", "raw_count": 40, "count": 40, "decode_str": "mathds"} -{"id": 39851, "token": "textsf", "merges": "text sf", "raw_count": 40, "count": 40, "decode_str": "textsf"} -{"id": 47851, "token": "\u0120\u00ce\u00b5\u00ce\u00bd", "merges": "\u0120\u00ce\u00b5 \u00ce\u00bd", "raw_count": 40, "count": 40, "decode_str": " \u03b5\u03bd"} -{"id": 45176, "token": "\u0120\u00c3\u012bt", "merges": "\u0120\u00c3\u012b t", "raw_count": 40, "count": 40, "decode_str": " \u00c9t"} -{"id": 8001, "token": "\\]).", "merges": "\\] ).", "raw_count": 40, "count": 40, "decode_str": "\\])."} -{"id": 23377, "token": "\u0120\u00e2\u012a\u00bc", "merges": "\u0120\u00e2\u012a \u00bc", "raw_count": 40, "count": 40, "decode_str": " \u223c"} -{"id": 48074, "token": "\u0120<%=", "merges": "\u0120< %=", "raw_count": 40, "count": 40, "decode_str": " <%="} -{"id": 37596, "token": "\\]-", "merges": "\\] -", "raw_count": 40, "count": 40, "decode_str": "\\]-"} -{"id": 36444, "token": "\u0120\u00c2\u00bc", "merges": "\u0120\u00c2 \u00bc", "raw_count": 40, "count": 40, "decode_str": " \u00bc"} -{"id": 44698, "token": "\u0120Superintendent", "merges": "\u0120Super intendent", "raw_count": 41, "count": 41, "decode_str": " Superintendent"} -{"id": 11885, "token": "\u0120Republicans", "merges": "\u0120Republic ans", "raw_count": 41, "count": 41, "decode_str": " Republicans"} -{"id": 42053, "token": "\u0120Aboriginal", "merges": "\u0120Abor iginal", "raw_count": 41, "count": 41, "decode_str": " Aboriginal"} -{"id": 45613, "token": "\u0120bioactive", "merges": "\u0120bio active", "raw_count": 41, "count": 41, "decode_str": " bioactive"} -{"id": 47637, "token": "\u0120Argentine", "merges": "\u0120Argent ine", "raw_count": 41, "count": 41, "decode_str": " Argentine"} -{"id": 38581, "token": "\u0120Zimbabwe", "merges": "\u0120Z imbabwe", "raw_count": 41, "count": 41, "decode_str": " Zimbabwe"} -{"id": 23386, "token": "stackrel", "merges": "stack rel", "raw_count": 41, "count": 41, "decode_str": "stackrel"} -{"id": 49433, "token": "\u0120Auburn", "merges": "\u0120Aub urn", "raw_count": 41, "count": 41, "decode_str": " Auburn"} -{"id": 22845, "token": "\u0120Brexit", "merges": "\u0120Bre xit", "raw_count": 41, "count": 41, "decode_str": " Brexit"} -{"id": 45609, "token": "zitter", "merges": "z itter", "raw_count": 41, "count": 41, "decode_str": "zitter"} -{"id": 41101, "token": "\u0120Comey", "merges": "\u0120Come y", "raw_count": 41, "count": 41, "decode_str": " Comey"} -{"id": 20485, "token": "\u0120\u00c2\u00a7\u00c2\u00a7", "merges": "\u0120\u00c2\u00a7 \u00c2\u00a7", "raw_count": 41, "count": 41, "decode_str": " \u00a7\u00a7"} -{"id": 37329, "token": "\u0120$-\\", "merges": "\u0120$ -\\", "raw_count": 41, "count": 41, "decode_str": " $-\\"} -{"id": 22762, "token": "\u0120\u00c2\u00b5g", "merges": "\u0120\u00c2\u00b5 g", "raw_count": 41, "count": 41, "decode_str": " \u00b5g"} -{"id": 42409, "token": "\u0120Senators", "merges": "\u0120Sen ators", "raw_count": 42, "count": 42, "decode_str": " Senators"} -{"id": 27412, "token": "\u0120Yemen", "merges": "\u0120Y emen", "raw_count": 42, "count": 42, "decode_str": " Yemen"} -{"id": 34273, "token": "}}^{-", "merges": "}} ^{-", "raw_count": 42, "count": 42, "decode_str": "}}^{-"} -{"id": 17092, "token": "\\|_{", "merges": "\\| _{", "raw_count": 42, "count": 42, "decode_str": "\\|_{"} -{"id": 26637, "token": "\u0120^{\\", "merges": "\u0120 ^{\\", "raw_count": 42, "count": 42, "decode_str": " ^{\\"} -{"id": 41449, "token": ")[$", "merges": ")[ $", "raw_count": 42, "count": 42, "decode_str": ")[$"} -{"id": 42308, "token": "''$", "merges": "'' $", "raw_count": 42, "count": 42, "decode_str": "''$"} -{"id": 10778, "token": "\u00c2\u0125", "merges": "\u00c2 \u0125", "raw_count": 42, "count": 42, "decode_str": "\u0083"} -{"id": 16815, "token": "=\"../../../../", "merges": "=\"../../ ../../", "raw_count": 18, "count": 43, "decode_str": "=\"../../../../"} -{"id": 48251, "token": "\u0120monocyte", "merges": "\u0120mon ocyte", "raw_count": 43, "count": 43, "decode_str": " monocyte"} -{"id": 48644, "token": "\u0120lncRNAs", "merges": "\u0120lnc RNAs", "raw_count": 43, "count": 43, "decode_str": " lncRNAs"} -{"id": 46885, "token": "\u0120Kremlin", "merges": "\u0120Kre mlin", "raw_count": 43, "count": 43, "decode_str": " Kremlin"} -{"id": 8834, "token": "amsfonts", "merges": "ams fonts", "raw_count": 43, "count": 43, "decode_str": "amsfonts"} -{"id": 31205, "token": "\u0120Tampa", "merges": "\u0120T ampa", "raw_count": 43, "count": 43, "decode_str": " Tampa"} -{"id": 44674, "token": "\u0120hatte", "merges": "\u0120hat te", "raw_count": 43, "count": 43, "decode_str": " hatte"} -{"id": 40415, "token": "\u0120ogs\u00c3\u00a5", "merges": "\u0120o gs\u00c3\u00a5", "raw_count": 43, "count": 43, "decode_str": " ogs\u00e5"} -{"id": 39427, "token": "gs\u00c3\u00a5", "merges": "gs \u00c3\u00a5", "raw_count": 0, "count": 43, "decode_str": "gs\u00e5"} -{"id": 35762, "token": "\u0120\u00ef\u00bb\u00bf", "merges": "\u0120\u00ef \u00bb\u00bf", "raw_count": 43, "count": 43, "decode_str": " \ufeff"} -{"id": 28247, "token": "\u0120\\,\\", "merges": "\u0120\\ ,\\", "raw_count": 43, "count": 43, "decode_str": " \\,\\"} -{"id": 34398, "token": "\u0120$[\\", "merges": "\u0120$ [\\", "raw_count": 43, "count": 43, "decode_str": " $[\\"} -{"id": 35990, "token": "\u00e2\u0122\u0124", "merges": "\u00e2\u0122 \u0124", "raw_count": 43, "count": 43, "decode_str": "\u2002"} -{"id": 15802, "token": "\u00c2\u0136", "merges": "\u00c2 \u0136", "raw_count": 43, "count": 43, "decode_str": "\u0094"} -{"id": 45195, "token": "overrightarrow", "merges": "over rightarrow", "raw_count": 44, "count": 44, "decode_str": "overrightarrow"} -{"id": 44156, "token": "\u0120Surprisingly", "merges": "\u0120Sur prisingly", "raw_count": 44, "count": 44, "decode_str": " Surprisingly"} -{"id": 47840, "token": "\u0120Qu\u00c3\u00a9", "merges": "\u0120Qu \u00c3\u00a9", "raw_count": 44, "count": 44, "decode_str": " Qu\u00e9"} -{"id": 30848, "token": "}}$$", "merges": "}} $$", "raw_count": 44, "count": 44, "decode_str": "}}$$"} -{"id": 39829, "token": "})}\\", "merges": "}) }\\", "raw_count": 44, "count": 44, "decode_str": "})}\\"} -{"id": 31828, "token": "\u0120\u00e0\u00aa", "merges": "\u0120 \u00e0\u00aa", "raw_count": 44, "count": 44, "decode_str": " \ufffd"} -{"id": 46658, "token": "\"}*", "merges": "\"} *", "raw_count": 44, "count": 44, "decode_str": "\"}*"} -{"id": 37067, "token": "\u0120Honorable", "merges": "\u0120Hon orable", "raw_count": 45, "count": 45, "decode_str": " Honorable"} -{"id": 21113, "token": "\u0120appellee", "merges": "\u0120app ellee", "raw_count": 45, "count": 45, "decode_str": " appellee"} -{"id": 33512, "token": "\u0120NSCLC", "merges": "\u0120NS CLC", "raw_count": 45, "count": 45, "decode_str": " NSCLC"} -{"id": 14024, "token": "}}_{\\", "merges": "}} _{\\", "raw_count": 45, "count": 45, "decode_str": "}}_{\\"} -{"id": 50302, "token": "\u00e2\u0123\u00b1", "merges": "\u00e2\u0123 \u00b1", "raw_count": 45, "count": 45, "decode_str": "\u2071"} -{"id": 42929, "token": "-$\\", "merges": "- $\\", "raw_count": 45, "count": 45, "decode_str": "-$\\"} -{"id": 12836, "token": "\u00e2\u0122\u0127", "merges": "\u00e2\u0122 \u0127", "raw_count": 45, "count": 45, "decode_str": "\u2005"} -{"id": 46849, "token": "^+(", "merges": "^+ (", "raw_count": 45, "count": 45, "decode_str": "^+("} -{"id": 13380, "token": "\\_[", "merges": "\\_ [", "raw_count": 45, "count": 45, "decode_str": "\\_["} -{"id": 28786, "token": "\u0120Throughout", "merges": "\u0120Through out", "raw_count": 46, "count": 46, "decode_str": " Throughout"} -{"id": 42422, "token": "\u0120Panthers", "merges": "\u0120Pant hers", "raw_count": 46, "count": 46, "decode_str": " Panthers"} -{"id": 11861, "token": "subseteq", "merges": "subset eq", "raw_count": 46, "count": 46, "decode_str": "subseteq"} -{"id": 24297, "token": "\u0120Corollary", "merges": "\u0120Cor ollary", "raw_count": 47, "count": 47, "decode_str": " Corollary"} -{"id": 39769, "token": "\u0120Debtors", "merges": "\u0120Debt ors", "raw_count": 47, "count": 47, "decode_str": " Debtors"} -{"id": 29914, "token": "Bigr", "merges": "Big r", "raw_count": 47, "count": 47, "decode_str": "Bigr"} -{"id": 42613, "token": "\u0120Broncos", "merges": "\u0120Bron cos", "raw_count": 48, "count": 48, "decode_str": " Broncos"} -{"id": 39699, "token": "\u0120Browns", "merges": "\u0120Brow ns", "raw_count": 48, "count": 48, "decode_str": " Browns"} -{"id": 33406, "token": "\u0120Nazis", "merges": "\u0120Naz is", "raw_count": 48, "count": 48, "decode_str": " Nazis"} -{"id": 18239, "token": "\u0120(\u00e2\u012a\u0134", "merges": "\u0120( \u00e2\u012a\u0134", "raw_count": 48, "count": 48, "decode_str": " (\u2212"} -{"id": 32220, "token": "\u0120MSCs", "merges": "\u0120M SCs", "raw_count": 48, "count": 48, "decode_str": " MSCs"} -{"id": 44327, "token": "\u0120(\u00e2\u012b\u00a5", "merges": "\u0120( \u00e2\u012b\u00a5", "raw_count": 48, "count": 48, "decode_str": " (\u2265"} -{"id": 16986, "token": ")/((-", "merges": ")/( (-", "raw_count": 48, "count": 48, "decode_str": ")/((-"} -{"id": 35623, "token": "\u0120Indigenous", "merges": "\u0120Ind igenous", "raw_count": 49, "count": 49, "decode_str": " Indigenous"} -{"id": 39759, "token": "\u0120Baghdad", "merges": "\u0120Bag hdad", "raw_count": 49, "count": 49, "decode_str": " Baghdad"} -{"id": 30174, "token": "\u0120Libya", "merges": "\u0120Lib ya", "raw_count": 49, "count": 49, "decode_str": " Libya"} -{"id": 46855, "token": "\u0120Torah", "merges": "\u0120Tor ah", "raw_count": 49, "count": 49, "decode_str": " Torah"} -{"id": 41065, "token": "\u0120DMEM", "merges": "\u0120DM EM", "raw_count": 49, "count": 49, "decode_str": " DMEM"} -{"id": 49043, "token": "\u0120\u00d8\u00a3\u00d9\u0128", "merges": "\u0120\u00d8\u00a3 \u00d9\u0128", "raw_count": 49, "count": 49, "decode_str": " \u0623\u0646"} -{"id": 6006, "token": "^\u00e2\u012a\u0134", "merges": "^ \u00e2\u012a\u0134", "raw_count": 49, "count": 49, "decode_str": "^\u2212"} -{"id": 33701, "token": "\u0120*/,", "merges": "\u0120*/ ,", "raw_count": 49, "count": 49, "decode_str": " */,"} -{"id": 30984, "token": "\u0120}_{", "merges": "\u0120} _{", "raw_count": 49, "count": 49, "decode_str": " }_{"} -{"id": 46265, "token": "[$\\", "merges": "[ $\\", "raw_count": 49, "count": 49, "decode_str": "[$\\"} -{"id": 43227, "token": "\u0120HOLDERS", "merges": "\u0120HOLD ERS", "raw_count": 50, "count": 50, "decode_str": " HOLDERS"} -{"id": 35699, "token": "\u0120Newark", "merges": "\u0120New ark", "raw_count": 50, "count": 50, "decode_str": " Newark"} -{"id": 31855, "token": "\u0120qPCR", "merges": "\u0120q PCR", "raw_count": 50, "count": 50, "decode_str": " qPCR"} -{"id": 48457, "token": "\u0120FACS", "merges": "\u0120F ACS", "raw_count": 50, "count": 50, "decode_str": " FACS"} -{"id": 38113, "token": "}_{(", "merges": "}_{ (", "raw_count": 50, "count": 50, "decode_str": "}_{("} -{"id": 31550, "token": "\u00ce\u00bcl", "merges": "\u00ce\u00bc l", "raw_count": 50, "count": 50, "decode_str": "\u03bcl"} -{"id": 52395, "token": "\u00e6\u0143\u0130", "merges": "\u00e6\u0143 \u0130", "raw_count": 50, "count": 50, "decode_str": "\u6b4e"} -{"id": 38039, "token": ".\"_", "merges": ".\" _", "raw_count": 50, "count": 50, "decode_str": ".\"_"} -{"id": 20688, "token": "\u00ce\u00baB", "merges": "\u00ce\u00ba B", "raw_count": 50, "count": 50, "decode_str": "\u03baB"} -{"id": 152, "token": "\u00dc", "merges": "NULL", "raw_count": 50, "count": 50, "decode_str": "\ufffd"} -{"id": 19018, "token": "\u0120Palestinian", "merges": "\u0120Palestin ian", "raw_count": 51, "count": 51, "decode_str": " Palestinian"} -{"id": 34161, "token": "\u0120microglia", "merges": "\u0120microgl ia", "raw_count": 51, "count": 51, "decode_str": " microglia"} -{"id": 48191, "token": "\u0120Malaysian", "merges": "\u0120Malays ian", "raw_count": 51, "count": 51, "decode_str": " Malaysian"} -{"id": 43290, "token": "\u0120Packers", "merges": "\u0120Pack ers", "raw_count": 51, "count": 51, "decode_str": " Packers"} -{"id": 37677, "token": "\u0120\u00ce\u00b1\u00cf\u0127\u00cf\u0126", "merges": "\u0120\u00ce\u00b1 \u00cf\u0127\u00cf\u0126", "raw_count": 51, "count": 51, "decode_str": " \u03b1\u03c5\u03c4"} -{"id": 32233, "token": "\u0120mTOR", "merges": "\u0120m TOR", "raw_count": 51, "count": 51, "decode_str": " mTOR"} -{"id": 37578, "token": "^+\\", "merges": "^ +\\", "raw_count": 51, "count": 51, "decode_str": "^+\\"} -{"id": 31547, "token": "_->", "merges": "_ ->", "raw_count": 51, "count": 51, "decode_str": "_->"} -{"id": 33714, "token": "}\\!", "merges": "}\\ !", "raw_count": 51, "count": 51, "decode_str": "}\\!"} -{"id": 23560, "token": "\u0120Bankruptcy", "merges": "\u0120Bank ruptcy", "raw_count": 52, "count": 52, "decode_str": " Bankruptcy"} -{"id": 48652, "token": "\u0120mistrial", "merges": "\u0120mist rial", "raw_count": 52, "count": 52, "decode_str": " mistrial"} -{"id": 39030, "token": "\u0120Midwest", "merges": "\u0120Mid west", "raw_count": 52, "count": 52, "decode_str": " Midwest"} -{"id": 34984, "token": "\u0120ARISING", "merges": "\u0120AR ISING", "raw_count": 52, "count": 52, "decode_str": " ARISING"} -{"id": 34875, "token": "\u0120mammary", "merges": "\u0120mam mary", "raw_count": 52, "count": 52, "decode_str": " mammary"} -{"id": 27056, "token": "varrho", "merges": "var rho", "raw_count": 52, "count": 52, "decode_str": "varrho"} -{"id": 46865, "token": "),\\\\", "merges": "), \\\\", "raw_count": 52, "count": 52, "decode_str": "),\\\\"} -{"id": 14466, "token": "\u00e2\u0122\u00b2-", "merges": "\u00e2\u0122\u00b2 -", "raw_count": 52, "count": 52, "decode_str": "\u2032-"} -{"id": 22372, "token": ",[@", "merges": ", [@", "raw_count": 52, "count": 52, "decode_str": ",[@"} -{"id": 188, "token": "\u010b", "merges": "NULL", "raw_count": 52, "count": 52, "decode_str": "\u000b"} -{"id": 44369, "token": "ActivityThread", "merges": "Activity Thread", "raw_count": 53, "count": 53, "decode_str": "ActivityThread"} -{"id": 33867, "token": "\u0120Parlament", "merges": "\u0120Par lament", "raw_count": 53, "count": 53, "decode_str": " Parlament"} -{"id": 35363, "token": "\u0120Ethiopia", "merges": "\u0120Ethiop ia", "raw_count": 53, "count": 53, "decode_str": " Ethiopia"} -{"id": 40787, "token": "\u0120Yugoslav", "merges": "\u0120Yug oslav", "raw_count": 53, "count": 53, "decode_str": " Yugoslav"} -{"id": 40136, "token": "\u0120Cassie", "merges": "\u0120Cass ie", "raw_count": 53, "count": 53, "decode_str": " Cassie"} -{"id": 47234, "token": "taient", "merges": "ta ient", "raw_count": 53, "count": 53, "decode_str": "taient"} -{"id": 13960, "token": "simeq", "merges": "sime q", "raw_count": 53, "count": 53, "decode_str": "simeq"} -{"id": 49159, "token": "\u0120Qur", "merges": "\u0120Q ur", "raw_count": 53, "count": 53, "decode_str": " Qur"} -{"id": 34580, "token": "}.$", "merges": "}. $", "raw_count": 53, "count": 53, "decode_str": "}.$"} -{"id": 50838, "token": "\u00e5\u012d\u00b3", "merges": "\u00e5\u012d \u00b3", "raw_count": 53, "count": 53, "decode_str": "\u52f3"} -{"id": 49763, "token": "\u00e0\u00ab\u0129", "merges": "\u00e0\u00ab \u0129", "raw_count": 53, "count": 53, "decode_str": "\u0ac7"} -{"id": 46245, "token": "\u0120tumorigenesis", "merges": "\u0120tumorigen esis", "raw_count": 54, "count": 54, "decode_str": " tumorigenesis"} -{"id": 43939, "token": "\u0120perturbative", "merges": "\u0120perturb ative", "raw_count": 54, "count": 54, "decode_str": " perturbative"} -{"id": 45914, "token": "\u0120Tanzania", "merges": "\u0120Tanz ania", "raw_count": 54, "count": 54, "decode_str": " Tanzania"} -{"id": 32647, "token": "\u0120neurode", "merges": "\u0120neuro de", "raw_count": 24, "count": 54, "decode_str": " neurode"} -{"id": 44117, "token": "\u0120Veteran", "merges": "\u0120Veter an", "raw_count": 54, "count": 54, "decode_str": " Veteran"} -{"id": 39086, "token": "\u0120agarose", "merges": "\u0120agar ose", "raw_count": 54, "count": 54, "decode_str": " agarose"} -{"id": 42757, "token": "Sprintf", "merges": "S printf", "raw_count": 54, "count": 54, "decode_str": "Sprintf"} -{"id": 39566, "token": "\u0120Ebola", "merges": "\u0120Eb ola", "raw_count": 54, "count": 54, "decode_str": " Ebola"} -{"id": 24448, "token": "^{(\\", "merges": "^{ (\\", "raw_count": 54, "count": 54, "decode_str": "^{(\\"} -{"id": 31502, "token": "\u0120$^", "merges": "\u0120$ ^", "raw_count": 54, "count": 54, "decode_str": " $^"} -{"id": 46655, "token": "\\*,", "merges": "\\ *,", "raw_count": 54, "count": 54, "decode_str": "\\*,"} -{"id": 27863, "token": "\u0120cytotoxicity", "merges": "\u0120cytotox icity", "raw_count": 55, "count": 55, "decode_str": " cytotoxicity"} -{"id": 32038, "token": "\u0120chemok", "merges": "\u0120chem ok", "raw_count": 25, "count": 55, "decode_str": " chemok"} -{"id": 19592, "token": "\u0120Judges", "merges": "\u0120Jud ges", "raw_count": 55, "count": 55, "decode_str": " Judges"} -{"id": 40906, "token": "\u0120Haiti", "merges": "\u0120Hait i", "raw_count": 55, "count": 55, "decode_str": " Haiti"} -{"id": 26038, "token": "=\"@+", "merges": "=\"@ +", "raw_count": 55, "count": 55, "decode_str": "=\"@+"} -{"id": 47940, "token": "\u0120%>%", "merges": "\u0120%> %", "raw_count": 55, "count": 55, "decode_str": " %>%"} -{"id": 48662, "token": "\u0120HFD", "merges": "\u0120H FD", "raw_count": 55, "count": 55, "decode_str": " HFD"} -{"id": 49449, "token": "\u0120postoperatively", "merges": "\u0120post operatively", "raw_count": 56, "count": 56, "decode_str": " postoperatively"} -{"id": 45291, "token": "\u0120Opposition", "merges": "\u0120Opp osition", "raw_count": 56, "count": 56, "decode_str": " Opposition"} -{"id": 48070, "token": "smallmatrix", "merges": "small matrix", "raw_count": 56, "count": 56, "decode_str": "smallmatrix"} -{"id": 45351, "token": "\u0120Reverend", "merges": "\u0120Reve rend", "raw_count": 56, "count": 56, "decode_str": " Reverend"} -{"id": 38736, "token": "databind", "merges": "datab ind", "raw_count": 56, "count": 56, "decode_str": "databind"} -{"id": 25487, "token": "\u0120Briefly", "merges": "\u0120Brief ly", "raw_count": 56, "count": 56, "decode_str": " Briefly"} -{"id": 37243, "token": "\u00e2\u0122\u00b2,", "merges": "\u00e2\u0122\u00b2 ,", "raw_count": 56, "count": 56, "decode_str": "\u2032,"} -{"id": 38341, "token": "\u0120($(", "merges": "\u0120($ (", "raw_count": 56, "count": 56, "decode_str": " ($("} -{"id": 54328, "token": "\u00e9\u013b\u0140", "merges": "\u00e9\u013b \u0140", "raw_count": 56, "count": 56, "decode_str": "\u965e"} -{"id": 34846, "token": "\\}}", "merges": "\\ }}", "raw_count": 56, "count": 56, "decode_str": "\\}}"} -{"id": 14198, "token": "\u0120Palestin", "merges": "\u0120Palest in", "raw_count": 1, "count": 57, "decode_str": " Palestin"} -{"id": 34657, "token": "appellant", "merges": "app ellant", "raw_count": 57, "count": 57, "decode_str": "appellant"} -{"id": 34745, "token": "\u0120LIABLE", "merges": "\u0120LI ABLE", "raw_count": 57, "count": 57, "decode_str": " LIABLE"} -{"id": 53298, "token": "\u00e7\u00b5\u0125", "merges": "\u00e7\u00b5 \u0125", "raw_count": 57, "count": 57, "decode_str": "\u7d43"} -{"id": 24638, "token": "^*\\", "merges": "^* \\", "raw_count": 57, "count": 57, "decode_str": "^*\\"} -{"id": 16643, "token": "\u00c2\u0127", "merges": "\u00c2 \u0127", "raw_count": 57, "count": 57, "decode_str": "\u0085"} -{"id": 50155, "token": "\u0120Parenthood", "merges": "\u0120Pa renthood", "raw_count": 58, "count": 58, "decode_str": " Parenthood"} -{"id": 46777, "token": "\u0120falciparum", "merges": "\u0120fal ciparum", "raw_count": 58, "count": 58, "decode_str": " falciparum"} -{"id": 39447, "token": "\u0120Scripture", "merges": "\u0120Script ure", "raw_count": 58, "count": 58, "decode_str": " Scripture"} -{"id": 42591, "token": "\u0120Judiciary", "merges": "\u0120Jud iciary", "raw_count": 58, "count": 58, "decode_str": " Judiciary"} -{"id": 49560, "token": "\u00c3\u00a4sident", "merges": "\u00c3\u00a4s ident", "raw_count": 58, "count": 58, "decode_str": "\u00e4sident"} -{"id": 48114, "token": "\u0120myosin", "merges": "\u0120my osin", "raw_count": 58, "count": 58, "decode_str": " myosin"} -{"id": 30401, "token": "\u0120Canad", "merges": "\u0120Can ad", "raw_count": 37, "count": 58, "decode_str": " Canad"} -{"id": 44418, "token": "))$,", "merges": ") )$,", "raw_count": 58, "count": 58, "decode_str": "))$,"} -{"id": 29270, "token": "}}=\\", "merges": "}} =\\", "raw_count": 58, "count": 58, "decode_str": "}}=\\"} -{"id": 29119, "token": ")}$,", "merges": ") }$,", "raw_count": 58, "count": 58, "decode_str": ")}$,"} -{"id": 35911, "token": "\u0120\\^", "merges": "\u0120\\ ^", "raw_count": 58, "count": 58, "decode_str": " \\^"} -{"id": 37040, "token": "\u0120neutrophil", "merges": "\u0120neutroph il", "raw_count": 59, "count": 59, "decode_str": " neutrophil"} -{"id": 8865, "token": "idemargin", "merges": "idem argin", "raw_count": 47, "count": 59, "decode_str": "idemargin"} -{"id": 20003, "token": "\u0120Germans", "merges": "\u0120Germ ans", "raw_count": 59, "count": 59, "decode_str": " Germans"} -{"id": 48069, "token": "\u0120Serbian", "merges": "\u0120Ser bian", "raw_count": 59, "count": 59, "decode_str": " Serbian"} -{"id": 41974, "token": "\u0120f\u00c3\u00b6rs", "merges": "\u0120f\u00c3\u00b6 rs", "raw_count": 59, "count": 59, "decode_str": " f\u00f6rs"} -{"id": 46538, "token": ")}^{", "merges": ") }^{", "raw_count": 59, "count": 59, "decode_str": ")}^{"} -{"id": 39478, "token": "}$;", "merges": "}$ ;", "raw_count": 59, "count": 59, "decode_str": "}$;"} -{"id": 38540, "token": "\u0120Confederate", "merges": "\u0120Confed erate", "raw_count": 60, "count": 60, "decode_str": " Confederate"} -{"id": 43133, "token": "\u0120Researchers", "merges": "\u0120Res earchers", "raw_count": 60, "count": 60, "decode_str": " Researchers"} -{"id": 38513, "token": "\u0120polyclonal", "merges": "\u0120poly clonal", "raw_count": 60, "count": 60, "decode_str": " polyclonal"} -{"id": 40073, "token": "\u0120Biosystems", "merges": "\u0120Bios ystems", "raw_count": 60, "count": 60, "decode_str": " Biosystems"} -{"id": 32242, "token": "\u0120immunore", "merges": "\u0120immun ore", "raw_count": 58, "count": 60, "decode_str": " immunore"} -{"id": 25700, "token": "\u0120Medicaid", "merges": "\u0120Med icaid", "raw_count": 60, "count": 60, "decode_str": " Medicaid"} -{"id": 46544, "token": "\u0120Spani", "merges": "\u0120Sp ani", "raw_count": 60, "count": 60, "decode_str": " Spani"} -{"id": 49548, "token": "\u0120Judah", "merges": "\u0120Jud ah", "raw_count": 60, "count": 60, "decode_str": " Judah"} -{"id": 16052, "token": "}}^{\\", "merges": "}} ^{\\", "raw_count": 60, "count": 60, "decode_str": "}}^{\\"} -{"id": 39885, "token": "$^{\\", "merges": "$ ^{\\", "raw_count": 60, "count": 60, "decode_str": "$^{\\"} -{"id": 51600, "token": "\u00e5\u00bc\u0136", "merges": "\u00e5\u00bc \u0136", "raw_count": 60, "count": 60, "decode_str": "\u5f14"} -{"id": 53302, "token": "\u00e7\u00b6\u0133", "merges": "\u00e7\u00b6 \u0133", "raw_count": 60, "count": 60, "decode_str": "\u7d91"} -{"id": 26130, "token": "\u00ce\u00bcM", "merges": "\u00ce\u00bc M", "raw_count": 60, "count": 60, "decode_str": "\u03bcM"} -{"id": 29650, "token": "_{[", "merges": "_{ [", "raw_count": 60, "count": 60, "decode_str": "_{["} -{"id": 45053, "token": "\u0120Edmonton", "merges": "\u0120Ed monton", "raw_count": 61, "count": 61, "decode_str": " Edmonton"} -{"id": 40987, "token": "\u0120DAPI", "merges": "\u0120D API", "raw_count": 61, "count": 61, "decode_str": " DAPI"} -{"id": 54599, "token": "\u00ef\u00bd\u00af", "merges": "\u00ef\u00bd \u00af", "raw_count": 61, "count": 61, "decode_str": "\uff6f"} -{"id": 47106, "token": "^+_", "merges": "^+ _", "raw_count": 61, "count": 61, "decode_str": "^+_"} -{"id": 42979, "token": "\u0120Quantification", "merges": "\u0120Quant ification", "raw_count": 62, "count": 62, "decode_str": " Quantification"} -{"id": 49500, "token": "\u0120Saskatchewan", "merges": "\u0120Sask atchewan", "raw_count": 62, "count": 62, "decode_str": " Saskatchewan"} -{"id": 32635, "token": "\u0120Minneapolis", "merges": "\u0120Min neapolis", "raw_count": 62, "count": 62, "decode_str": " Minneapolis"} -{"id": 44686, "token": "\u0120neoplastic", "merges": "\u0120ne oplastic", "raw_count": 62, "count": 62, "decode_str": " neoplastic"} -{"id": 46406, "token": "\u0120Dominican", "merges": "\u0120Domin ican", "raw_count": 62, "count": 62, "decode_str": " Dominican"} -{"id": 25900, "token": "\u0120IMPLIED", "merges": "\u0120IM PLIED", "raw_count": 62, "count": 62, "decode_str": " IMPLIED"} -{"id": 40145, "token": "\u0120Ecuador", "merges": "\u0120E cuador", "raw_count": 62, "count": 62, "decode_str": " Ecuador"} -{"id": 20533, "token": "\u0120Iranian", "merges": "\u0120Iran ian", "raw_count": 62, "count": 62, "decode_str": " Iranian"} -{"id": 30356, "token": "marined", "merges": "mar ined", "raw_count": 62, "count": 62, "decode_str": "marined"} -{"id": 54596, "token": "\u00ef\u00bd\u00a3", "merges": "\u00ef\u00bd \u00a3", "raw_count": 62, "count": 62, "decode_str": "\uff63"} -{"id": 25942, "token": ":=\\", "merges": ": =\\", "raw_count": 62, "count": 62, "decode_str": ":=\\"} -{"id": 42566, "token": "\u0120osteoclast", "merges": "\u0120oste oclast", "raw_count": 63, "count": 63, "decode_str": " osteoclast"} -{"id": 30884, "token": "underset", "merges": "unders et", "raw_count": 63, "count": 63, "decode_str": "underset"} -{"id": 44188, "token": "supset", "merges": "sup set", "raw_count": 63, "count": 63, "decode_str": "supset"} -{"id": 34033, "token": "\u0120mRNAs", "merges": "\u0120mRNA s", "raw_count": 63, "count": 63, "decode_str": " mRNAs"} -{"id": 42666, "token": "\u0120d\u00c3\u00a4r", "merges": "\u0120d \u00c3\u00a4r", "raw_count": 63, "count": 63, "decode_str": " d\u00e4r"} -{"id": 16996, "token": "}})$", "merges": "}} )$", "raw_count": 63, "count": 63, "decode_str": "}})$"} -{"id": 35763, "token": "\u00ce\u00bcL", "merges": "\u00ce\u00bc L", "raw_count": 63, "count": 63, "decode_str": "\u03bcL"} -{"id": 53296, "token": "\u00e7\u00b4\u00ae", "merges": "\u00e7\u00b4 \u00ae", "raw_count": 63, "count": 63, "decode_str": "\u7d2e"} -{"id": 14522, "token": "\u0120Interestingly", "merges": "\u0120Interest ingly", "raw_count": 64, "count": 64, "decode_str": " Interestingly"} -{"id": 48376, "token": "\u0120transgene", "merges": "\u0120trans gene", "raw_count": 64, "count": 64, "decode_str": " transgene"} -{"id": 40269, "token": "\u0120Vikings", "merges": "\u0120Vik ings", "raw_count": 64, "count": 64, "decode_str": " Vikings"} -{"id": 34915, "token": "\u0120TORT", "merges": "\u0120T ORT", "raw_count": 64, "count": 64, "decode_str": " TORT"} -{"id": 44272, "token": "\u0120Cubs", "merges": "\u0120Cub s", "raw_count": 64, "count": 64, "decode_str": " Cubs"} -{"id": 46433, "token": ")$;", "merges": ")$ ;", "raw_count": 64, "count": 64, "decode_str": ")$;"} -{"id": 23794, "token": "\u00c2\u0132", "merges": "\u00c2 \u0132", "raw_count": 64, "count": 64, "decode_str": "\u0090"} -{"id": 37584, "token": "\u0120comorbidities", "merges": "\u0120comorbid ities", "raw_count": 65, "count": 65, "decode_str": " comorbidities"} -{"id": 48847, "token": "\u0120Socorro", "merges": "\u0120Soc orro", "raw_count": 65, "count": 65, "decode_str": " Socorro"} -{"id": 32024, "token": "\u0120DAMAGES", "merges": "\u0120DAM AGES", "raw_count": 65, "count": 65, "decode_str": " DAMAGES"} -{"id": 28711, "token": "}^{*", "merges": "}^{ *", "raw_count": 65, "count": 65, "decode_str": "}^{*"} -{"id": 44106, "token": "at\u00c4\u0125", "merges": "at \u00c4\u0125", "raw_count": 65, "count": 65, "decode_str": "at\u0103"} -{"id": 48653, "token": "\u0120Sgt", "merges": "\u0120S gt", "raw_count": 65, "count": 65, "decode_str": " Sgt"} -{"id": 42696, "token": ",\\[", "merges": ",\\ [", "raw_count": 65, "count": 65, "decode_str": ",\\["} -{"id": 44391, "token": "#{$", "merges": "# {$", "raw_count": 65, "count": 65, "decode_str": "#{$"} -{"id": 18637, "token": "longrightarrow", "merges": "long rightarrow", "raw_count": 66, "count": 66, "decode_str": "longrightarrow"} -{"id": 35032, "token": "\u0120xenograft", "merges": "\u0120xen ograft", "raw_count": 66, "count": 66, "decode_str": " xenograft"} -{"id": 40863, "token": "\u0120Cowboys", "merges": "\u0120Cow boys", "raw_count": 66, "count": 66, "decode_str": " Cowboys"} -{"id": 35522, "token": "\u0120Uganda", "merges": "\u0120Ug anda", "raw_count": 66, "count": 66, "decode_str": " Uganda"} -{"id": 32377, "token": "\u0120Enron", "merges": "\u0120En ron", "raw_count": 66, "count": 66, "decode_str": " Enron"} -{"id": 32453, "token": "}\\;", "merges": "}\\ ;", "raw_count": 66, "count": 66, "decode_str": "}\\;"} -{"id": 33189, "token": "'$,", "merges": "' $,", "raw_count": 66, "count": 66, "decode_str": "'$,"} -{"id": 34575, "token": "\u012000000000000000000000000000000000", "merges": "\u0120 00000000000000000000000000000000", "raw_count": 67, "count": 67, "decode_str": " 00000000000000000000000000000000"} -{"id": 30445, "token": "\u0120Certainly", "merges": "\u0120C ertainly", "raw_count": 67, "count": 67, "decode_str": " Certainly"} -{"id": 40767, "token": "\u0120Brisbane", "merges": "\u0120Bris bane", "raw_count": 67, "count": 67, "decode_str": " Brisbane"} -{"id": 33366, "token": "\u0120Commiss", "merges": "\u0120Com miss", "raw_count": 63, "count": 67, "decode_str": " Commiss"} -{"id": 44092, "token": "\u0120Denote", "merges": "\u0120Den ote", "raw_count": 67, "count": 67, "decode_str": " Denote"} -{"id": 43664, "token": "\u0120Lemmon", "merges": "\u0120Lem mon", "raw_count": 67, "count": 67, "decode_str": " Lemmon"} -{"id": 20886, "token": "\u0120({\\", "merges": "\u0120( {\\", "raw_count": 67, "count": 67, "decode_str": " ({\\"} -{"id": 48323, "token": "\u0120\u00c3\u0124", "merges": "\u0120\u00c3 \u0124", "raw_count": 67, "count": 67, "decode_str": " \u00c2"} -{"id": 24060, "token": "&=\\", "merges": "& =\\", "raw_count": 67, "count": 67, "decode_str": "&=\\"} -{"id": 34476, "token": "![(", "merges": "![ (", "raw_count": 67, "count": 67, "decode_str": "![("} -{"id": 52786, "token": "\u00e7\u012b\u00b4", "merges": "\u00e7\u012b \u00b4", "raw_count": 67, "count": 67, "decode_str": "\u7274"} -{"id": 45692, "token": "\u0120heterosexual", "merges": "\u0120heter osexual", "raw_count": 68, "count": 68, "decode_str": " heterosexual"} -{"id": 26951, "token": "\u0120supernatant", "merges": "\u0120supernat ant", "raw_count": 68, "count": 68, "decode_str": " supernatant"} -{"id": 27255, "token": "\u0120LIABILITY", "merges": "\u0120LI ABILITY", "raw_count": 68, "count": 68, "decode_str": " LIABILITY"} -{"id": 29649, "token": "\u0120monocytes", "merges": "\u0120mon ocytes", "raw_count": 68, "count": 68, "decode_str": " monocytes"} -{"id": 33668, "token": "\u0120Patriots", "merges": "\u0120Patri ots", "raw_count": 68, "count": 68, "decode_str": " Patriots"} -{"id": 40585, "token": "\u0120Pelosi", "merges": "\u0120Pel osi", "raw_count": 68, "count": 68, "decode_str": " Pelosi"} -{"id": 40327, "token": "\u0120Celtic", "merges": "\u0120Celt ic", "raw_count": 68, "count": 68, "decode_str": " Celtic"} -{"id": 34275, "token": "\u0120Mormon", "merges": "\u0120Morm on", "raw_count": 68, "count": 68, "decode_str": " Mormon"} -{"id": 47719, "token": "\u00e2\u0124\u00ac\u00e2\u0126\u00a2", "merges": "\u00e2\u0124\u00ac \u00e2\u0126\u00a2", "raw_count": 68, "count": 68, "decode_str": "\u20ac\u2122"} -{"id": 24076, "token": "\u0120Gaza", "merges": "\u0120G aza", "raw_count": 68, "count": 68, "decode_str": " Gaza"} -{"id": 38833, "token": "\u0120\u00ce\u00b8\u00ce\u00b1", "merges": "\u0120\u00ce\u00b8 \u00ce\u00b1", "raw_count": 68, "count": 68, "decode_str": " \u03b8\u03b1"} -{"id": 30485, "token": "\u0120}{\\", "merges": "\u0120} {\\", "raw_count": 68, "count": 68, "decode_str": " }{\\"} -{"id": 29432, "token": "*.,", "merges": "* .,", "raw_count": 68, "count": 68, "decode_str": "*.,"} -{"id": 21824, "token": "\u00c2\u0131", "merges": "\u00c2 \u0131", "raw_count": 68, "count": 68, "decode_str": "\u008f"} -{"id": 37486, "token": "\u0120tumorigen", "merges": "\u0120tumor igen", "raw_count": 15, "count": 69, "decode_str": " tumorigen"} -{"id": 47607, "token": "\u0120\u00cf\u0125\u00cf\u0126\u00ce\u00b7\u00ce\u00bd", "merges": "\u0120\u00cf\u0125\u00cf\u0126\u00ce\u00b7 \u00ce\u00bd", "raw_count": 69, "count": 69, "decode_str": " \u03c3\u03c4\u03b7\u03bd"} -{"id": 41560, "token": "\u0120n\u00c3\u00a4r", "merges": "\u0120n \u00c3\u00a4r", "raw_count": 69, "count": 69, "decode_str": " n\u00e4r"} -{"id": 33996, "token": "varpi", "merges": "var pi", "raw_count": 69, "count": 69, "decode_str": "varpi"} -{"id": 18381, "token": "pcbi", "merges": "pc bi", "raw_count": 69, "count": 69, "decode_str": "pcbi"} -{"id": 50292, "token": "\u00e1\u0125\u00a6", "merges": "\u00e1\u0125 \u00a6", "raw_count": 69, "count": 69, "decode_str": "\u10e6"} -{"id": 42625, "token": "Interestingly", "merges": "Interest ingly", "raw_count": 70, "count": 70, "decode_str": "Interestingly"} -{"id": 48093, "token": "\u0120phosphatidyl", "merges": "\u0120phosphat idyl", "raw_count": 70, "count": 70, "decode_str": " phosphatidyl"} -{"id": 40571, "token": "\u0120Biosciences", "merges": "\u0120Biosc iences", "raw_count": 70, "count": 70, "decode_str": " Biosciences"} -{"id": 24883, "token": "\u0120Nonetheless", "merges": "\u0120Non etheless", "raw_count": 70, "count": 70, "decode_str": " Nonetheless"} -{"id": 35416, "token": "\u0120Kashmir", "merges": "\u0120Kash mir", "raw_count": 70, "count": 70, "decode_str": " Kashmir"} -{"id": 10609, "token": "mathscr", "merges": "math scr", "raw_count": 70, "count": 70, "decode_str": "mathscr"} -{"id": 46562, "token": "\u0120Carls", "merges": "\u0120Car ls", "raw_count": 70, "count": 70, "decode_str": " Carls"} -{"id": 43189, "token": ")[@", "merges": ") [@", "raw_count": 70, "count": 70, "decode_str": ")[@"} -{"id": 42714, "token": "}$:", "merges": "}$ :", "raw_count": 70, "count": 70, "decode_str": "}$:"} -{"id": 47658, "token": "\u0120dopaminergic", "merges": "\u0120dop aminergic", "raw_count": 71, "count": 71, "decode_str": " dopaminergic"} -{"id": 21485, "token": "\u0120Respondent", "merges": "\u0120Respond ent", "raw_count": 71, "count": 71, "decode_str": " Respondent"} -{"id": 50013, "token": "\u0120Arlington", "merges": "\u0120Ar lington", "raw_count": 71, "count": 71, "decode_str": " Arlington"} -{"id": 20637, "token": "\u0120supernat", "merges": "\u0120supern at", "raw_count": 1, "count": 71, "decode_str": " supernat"} -{"id": 40261, "token": "\u0120Scandin", "merges": "\u0120Sc andin", "raw_count": 71, "count": 71, "decode_str": " Scandin"} -{"id": 20271, "token": "\u0120siRNA", "merges": "\u0120si RNA", "raw_count": 71, "count": 71, "decode_str": " siRNA"} -{"id": 43255, "token": "rceil", "merges": "r ceil", "raw_count": 71, "count": 71, "decode_str": "rceil"} -{"id": 49170, "token": "\u00e0\u00aa\u00be", "merges": "\u00e0\u00aa \u00be", "raw_count": 71, "count": 71, "decode_str": "\u0abe"} -{"id": 47624, "token": "\u0120Northwestern", "merges": "\u0120North western", "raw_count": 72, "count": 72, "decode_str": " Northwestern"} -{"id": 44174, "token": "\u0120DISCLAIM", "merges": "\u0120DIS CLAIM", "raw_count": 72, "count": 72, "decode_str": " DISCLAIM"} -{"id": 42862, "token": "\u0120Croatia", "merges": "\u0120Croat ia", "raw_count": 72, "count": 72, "decode_str": " Croatia"} -{"id": 47506, "token": "\u0120Dodgers", "merges": "\u0120Dod gers", "raw_count": 72, "count": 72, "decode_str": " Dodgers"} -{"id": 48863, "token": "\u0120Kosovo", "merges": "\u0120Kos ovo", "raw_count": 72, "count": 72, "decode_str": " Kosovo"} -{"id": 41164, "token": "\u0120detta", "merges": "\u0120det ta", "raw_count": 72, "count": 72, "decode_str": " detta"} -{"id": 42914, "token": "lceil", "merges": "l ceil", "raw_count": 72, "count": 72, "decode_str": "lceil"} -{"id": 49437, "token": "\u00e1\u00bf\u00b6\u00ce\u00bd", "merges": "\u00e1\u00bf\u00b6 \u00ce\u00bd", "raw_count": 72, "count": 72, "decode_str": "\u1ff6\u03bd"} -{"id": 4622, "token": "*]{}", "merges": "* ]{}", "raw_count": 72, "count": 72, "decode_str": "*]{}"} -{"id": 42875, "token": "\u0120AKT", "merges": "\u0120AK T", "raw_count": 72, "count": 72, "decode_str": " AKT"} -{"id": 50325, "token": "\u00e2\u012a\u00bd", "merges": "\u00e2\u012a \u00bd", "raw_count": 72, "count": 72, "decode_str": "\u223d"} -{"id": 22015, "token": "\u00c2\u012f", "merges": "\u00c2 \u012f", "raw_count": 67, "count": 72, "decode_str": "\u008d"} -{"id": 20054, "token": "\u00c2\u013c", "merges": "\u00c2 \u013c", "raw_count": 69, "count": 72, "decode_str": "\u009a"} -{"id": 46965, "token": "\u0120antifer", "merges": "\u0120ant ifer", "raw_count": 73, "count": 73, "decode_str": " antifer"} -{"id": 31874, "token": "\u0120Somal", "merges": "\u0120S omal", "raw_count": 42, "count": 73, "decode_str": " Somal"} -{"id": 22254, "token": "}}}_{", "merges": "}} }_{", "raw_count": 73, "count": 73, "decode_str": "}}}_{"} -{"id": 48727, "token": "\u0120USSR", "merges": "\u0120US SR", "raw_count": 73, "count": 73, "decode_str": " USSR"} -{"id": 40360, "token": "}$),", "merges": "}$ ),", "raw_count": 73, "count": 73, "decode_str": "}$),"} -{"id": 49938, "token": "\u0120$+", "merges": "\u0120$ +", "raw_count": 73, "count": 73, "decode_str": " $+"} -{"id": 41829, "token": "\u00c2\u00b5g", "merges": "\u00c2\u00b5 g", "raw_count": 73, "count": 73, "decode_str": "\u00b5g"} -{"id": 50009, "token": "\u0120Cherokee", "merges": "\u0120Che rokee", "raw_count": 74, "count": 74, "decode_str": " Cherokee"} -{"id": 13389, "token": "\u0120Israeli", "merges": "\u0120Israel i", "raw_count": 74, "count": 74, "decode_str": " Israeli"} -{"id": 49260, "token": "\u0120Andr\u00c3\u00a9", "merges": "\u0120And r\u00c3\u00a9", "raw_count": 74, "count": 74, "decode_str": " Andr\u00e9"} -{"id": 47563, "token": "\u0120Turks", "merges": "\u0120Tur ks", "raw_count": 74, "count": 74, "decode_str": " Turks"} -{"id": 46145, "token": "<>();", "merges": "< >();", "raw_count": 74, "count": 74, "decode_str": "<>();"} -{"id": 42569, "token": "\u0120Jeg", "merges": "\u0120J eg", "raw_count": 74, "count": 74, "decode_str": " Jeg"} -{"id": 31704, "token": "\u0120Wnt", "merges": "\u0120W nt", "raw_count": 74, "count": 74, "decode_str": " Wnt"} -{"id": 27860, "token": "_{+", "merges": "_{ +", "raw_count": 74, "count": 74, "decode_str": "_{+"} -{"id": 53547, "token": "\u00e8\u0126\u00a9", "merges": "\u00e8\u0126 \u00a9", "raw_count": 74, "count": 74, "decode_str": "\u8129"} -{"id": 19905, "token": "\u0120neutroph", "merges": "\u0120neut roph", "raw_count": 7, "count": 75, "decode_str": " neutroph"} -{"id": 48022, "token": "\u0120Plymouth", "merges": "\u0120Ply mouth", "raw_count": 75, "count": 75, "decode_str": " Plymouth"} -{"id": 44736, "token": "\u0120Anglic", "merges": "\u0120Ang lic", "raw_count": 36, "count": 75, "decode_str": " Anglic"} -{"id": 46614, "token": "\u0120Kuwait", "merges": "\u0120Ku wait", "raw_count": 75, "count": 75, "decode_str": " Kuwait"} -{"id": 35889, "token": "\u0120Tehran", "merges": "\u0120Teh ran", "raw_count": 75, "count": 75, "decode_str": " Tehran"} -{"id": 49308, "token": "\u0120Golgi", "merges": "\u0120Gol gi", "raw_count": 75, "count": 75, "decode_str": " Golgi"} -{"id": 34353, "token": "-\\-\\", "merges": "-\\ -\\", "raw_count": 75, "count": 75, "decode_str": "-\\-\\"} -{"id": 48885, "token": ")\u00e2\u012a\u0134", "merges": ") \u00e2\u012a\u0134", "raw_count": 75, "count": 75, "decode_str": ")\u2212"} -{"id": 27927, "token": "}})\\", "merges": "}} )\\", "raw_count": 75, "count": 75, "decode_str": "}})\\"} -{"id": 7433, "token": "^+^", "merges": "^+ ^", "raw_count": 75, "count": 75, "decode_str": "^+^"} -{"id": 54595, "token": "\u00ef\u00bd\u00a2", "merges": "\u00ef\u00bd \u00a2", "raw_count": 75, "count": 75, "decode_str": "\uff62"} -{"id": 43506, "token": "\u0120Judaism", "merges": "\u0120Juda ism", "raw_count": 76, "count": 76, "decode_str": " Judaism"} -{"id": 36582, "token": "\u0120Wyoming", "merges": "\u0120Wy oming", "raw_count": 76, "count": 76, "decode_str": " Wyoming"} -{"id": 43372, "token": "\u0120Sloven", "merges": "\u0120Sl oven", "raw_count": 76, "count": 76, "decode_str": " Sloven"} -{"id": 48875, "token": "\u0120chemot", "merges": "\u0120chem ot", "raw_count": 76, "count": 76, "decode_str": " chemot"} -{"id": 8822, "token": "amssymb", "merges": "amss ymb", "raw_count": 76, "count": 76, "decode_str": "amssymb"} -{"id": 42967, "token": "\u0120Borel", "merges": "\u0120B orel", "raw_count": 76, "count": 76, "decode_str": " Borel"} -{"id": 44600, "token": "\u0120Athen", "merges": "\u0120A then", "raw_count": 76, "count": 76, "decode_str": " Athen"} -{"id": 44763, "token": "\u0120mononuclear", "merges": "\u0120mon onuclear", "raw_count": 77, "count": 77, "decode_str": " mononuclear"} -{"id": 23135, "token": "Accordingly", "merges": "According ly", "raw_count": 77, "count": 77, "decode_str": "Accordingly"} -{"id": 28994, "token": "\u0120Presidente", "merges": "\u0120President e", "raw_count": 77, "count": 77, "decode_str": " Presidente"} -{"id": 46857, "token": "\u0120Poincar\u00c3\u00a9", "merges": "\u0120Poinc ar\u00c3\u00a9", "raw_count": 77, "count": 77, "decode_str": " Poincar\u00e9"} -{"id": 26832, "token": "\u0120microgl", "merges": "\u0120micro gl", "raw_count": 26, "count": 77, "decode_str": " microgl"} -{"id": 49212, "token": "\u0120THEORY", "merges": "\u0120THE ORY", "raw_count": 77, "count": 77, "decode_str": " THEORY"} -{"id": 22736, "token": "\u0120Debtor", "merges": "\u0120Debt or", "raw_count": 77, "count": 77, "decode_str": " Debtor"} -{"id": 49428, "token": "\u0120serop", "merges": "\u0120ser op", "raw_count": 77, "count": 77, "decode_str": " serop"} -{"id": 28543, "token": "\u0120$(\"#", "merges": "\u0120$ (\"#", "raw_count": 77, "count": 77, "decode_str": " $(\"#"} -{"id": 208, "token": "\u011f", "merges": "NULL", "raw_count": 77, "count": 77, "decode_str": "\u001f"} -{"id": 43839, "token": "\u0120Hartford", "merges": "\u0120Hart ford", "raw_count": 78, "count": 78, "decode_str": " Hartford"} -{"id": 47419, "token": "\u0120Damascus", "merges": "\u0120Dam ascus", "raw_count": 78, "count": 78, "decode_str": " Damascus"} -{"id": 47909, "token": "\u0120\u00cf\u0125\u00cf\u0127\u00ce\u00bd", "merges": "\u0120\u00cf\u0125\u00cf\u0127 \u00ce\u00bd", "raw_count": 78, "count": 78, "decode_str": " \u03c3\u03c5\u03bd"} -{"id": 37876, "token": "\u0120moeten", "merges": "\u0120mo eten", "raw_count": 78, "count": 78, "decode_str": " moeten"} -{"id": 37425, "token": "ENRON", "merges": "EN RON", "raw_count": 78, "count": 78, "decode_str": "ENRON"} -{"id": 48745, "token": "\u0120ATCC", "merges": "\u0120AT CC", "raw_count": 78, "count": 78, "decode_str": " ATCC"} -{"id": 19289, "token": "}_{-", "merges": "}_{ -", "raw_count": 78, "count": 78, "decode_str": "}_{-"} -{"id": 49286, "token": "\u0120Esq", "merges": "\u0120Es q", "raw_count": 78, "count": 78, "decode_str": " Esq"} -{"id": 41663, "token": "\u00d1\u012c\u00d1\u0122", "merges": "\u00d1\u012c \u00d1\u0122", "raw_count": 78, "count": 78, "decode_str": "\u044a\u0440"} -{"id": 33070, "token": "\u0120Indianapolis", "merges": "\u0120Indian apolis", "raw_count": 79, "count": 79, "decode_str": " Indianapolis"} -{"id": 24083, "token": "\u0120Subsequently", "merges": "\u0120Sub sequently", "raw_count": 79, "count": 79, "decode_str": " Subsequently"} -{"id": 46560, "token": "\u0120Guatemala", "merges": "\u0120Guatem ala", "raw_count": 79, "count": 79, "decode_str": " Guatemala"} -{"id": 36111, "token": "\u0120OPINION", "merges": "\u0120OP INION", "raw_count": 79, "count": 79, "decode_str": " OPINION"} -{"id": 46365, "token": "\u0120Whilst", "merges": "\u0120Wh ilst", "raw_count": 79, "count": 79, "decode_str": " Whilst"} -{"id": 42605, "token": "\u0120Banach", "merges": "\u0120Ban ach", "raw_count": 79, "count": 79, "decode_str": " Banach"} -{"id": 34280, "token": "\u0120Calif", "merges": "\u0120Cal if", "raw_count": 79, "count": 79, "decode_str": " Calif"} -{"id": 48812, "token": "\u0120NRA", "merges": "\u0120N RA", "raw_count": 79, "count": 79, "decode_str": " NRA"} -{"id": 48534, "token": "\u0120Syracuse", "merges": "\u0120Syrac use", "raw_count": 80, "count": 80, "decode_str": " Syracuse"} -{"id": 49290, "token": "\u0120M\u00c3\u00bcller", "merges": "\u0120M \u00c3\u00bcller", "raw_count": 80, "count": 80, "decode_str": " M\u00fcller"} -{"id": 40983, "token": "\u0120Morocco", "merges": "\u0120Mor occo", "raw_count": 80, "count": 80, "decode_str": " Morocco"} -{"id": 44937, "token": "\u0120Perth", "merges": "\u0120Per th", "raw_count": 80, "count": 80, "decode_str": " Perth"} -{"id": 43276, "token": "\u0120Clint", "merges": "\u0120Cl int", "raw_count": 80, "count": 80, "decode_str": " Clint"} -{"id": 37450, "token": "}}}^{", "merges": "}} }^{", "raw_count": 80, "count": 80, "decode_str": "}}}^{"} -{"id": 31530, "token": "\u0120hogy", "merges": "\u0120h ogy", "raw_count": 80, "count": 80, "decode_str": " hogy"} -{"id": 49370, "token": "\u0120Treg", "merges": "\u0120T reg", "raw_count": 80, "count": 80, "decode_str": " Treg"} -{"id": 3455, "token": "]{},", "merges": "]{} ,", "raw_count": 80, "count": 80, "decode_str": "]{},"} -{"id": 34027, "token": "\u0120$$(", "merges": "\u0120$$ (", "raw_count": 80, "count": 80, "decode_str": " $$("} -{"id": 26997, "token": "\\^[", "merges": "\\^ [", "raw_count": 80, "count": 80, "decode_str": "\\^["} -{"id": 34399, "token": "\u0120Suddenly", "merges": "\u0120Sud denly", "raw_count": 81, "count": 81, "decode_str": " Suddenly"} -{"id": 21618, "token": "\u0120Arkansas", "merges": "\u0120Ark ansas", "raw_count": 81, "count": 81, "decode_str": " Arkansas"} -{"id": 37252, "token": "\u0120Norfolk", "merges": "\u0120Nor folk", "raw_count": 81, "count": 81, "decode_str": " Norfolk"} -{"id": 45277, "token": "\u0120Trudeau", "merges": "\u0120Tr udeau", "raw_count": 81, "count": 81, "decode_str": " Trudeau"} -{"id": 33891, "token": "\u0120Yankees", "merges": "\u0120Yan kees", "raw_count": 81, "count": 81, "decode_str": " Yankees"} -{"id": 38372, "token": "\u0120Qatar", "merges": "\u0120Q atar", "raw_count": 81, "count": 81, "decode_str": " Qatar"} -{"id": 32330, "token": "\u0120NLR", "merges": "\u0120N LR", "raw_count": 81, "count": 81, "decode_str": " NLR"} -{"id": 53435, "token": "\u00e7\u00be\u00a8", "merges": "\u00e7\u00be \u00a8", "raw_count": 81, "count": 81, "decode_str": "\u7fa8"} -{"id": 35055, "token": "\u0120immunofluorescence", "merges": "\u0120immun ofluorescence", "raw_count": 82, "count": 82, "decode_str": " immunofluorescence"} -{"id": 47518, "token": "\u0120Affordable", "merges": "\u0120Aff ordable", "raw_count": 82, "count": 82, "decode_str": " Affordable"} -{"id": 31914, "token": "\u0120Milwaukee", "merges": "\u0120Mil waukee", "raw_count": 82, "count": 82, "decode_str": " Milwaukee"} -{"id": 16667, "token": "Appellant", "merges": "App ellant", "raw_count": 82, "count": 82, "decode_str": "Appellant"} -{"id": 45951, "token": "Inflater", "merges": "Infl ater", "raw_count": 82, "count": 82, "decode_str": "Inflater"} -{"id": 42973, "token": "\u0120Nate", "merges": "\u0120N ate", "raw_count": 82, "count": 82, "decode_str": " Nate"} -{"id": 28052, "token": "\u0120\\[[", "merges": "\u0120\\[ [", "raw_count": 82, "count": 82, "decode_str": " \\[["} -{"id": 39779, "token": "}=-", "merges": "}= -", "raw_count": 82, "count": 82, "decode_str": "}=-"} -{"id": 23930, "token": "\u0120autophagy", "merges": "\u0120aut ophagy", "raw_count": 83, "count": 83, "decode_str": " autophagy"} -{"id": 48401, "token": "\u0120Isaiah", "merges": "\u0120Isa iah", "raw_count": 83, "count": 83, "decode_str": " Isaiah"} -{"id": 46578, "token": "\u0120Syrac", "merges": "\u0120Sy rac", "raw_count": 3, "count": 83, "decode_str": " Syrac"} -{"id": 39379, "token": "\u0120Asst", "merges": "\u0120As st", "raw_count": 83, "count": 83, "decode_str": " Asst"} -{"id": 29591, "token": ")}(\\", "merges": ")} (\\", "raw_count": 83, "count": 83, "decode_str": ")}(\\"} -{"id": 8381, "token": "\u00c2\u0124", "merges": "\u00c2 \u0124", "raw_count": 82, "count": 83, "decode_str": "\u0082"} -{"id": 50290, "token": "\u00cb\u00a2", "merges": "\u00cb \u00a2", "raw_count": 83, "count": 83, "decode_str": "\u02e2"} -{"id": 15466, "token": "\u0120WARRANTIES", "merges": "\u0120WARRANT IES", "raw_count": 84, "count": 84, "decode_str": " WARRANTIES"} -{"id": 42521, "token": "\u0120leukocytes", "merges": "\u0120leuk ocytes", "raw_count": 84, "count": 84, "decode_str": " leukocytes"} -{"id": 37911, "token": "\u0120Cardinals", "merges": "\u0120Card inals", "raw_count": 84, "count": 84, "decode_str": " Cardinals"} -{"id": 41198, "token": "\u0120Jamaica", "merges": "\u0120Jama ica", "raw_count": 84, "count": 84, "decode_str": " Jamaica"} -{"id": 32558, "token": "nolimits", "merges": "nol imits", "raw_count": 84, "count": 84, "decode_str": "nolimits"} -{"id": 6274, "token": "nonumber", "merges": "non umber", "raw_count": 84, "count": 84, "decode_str": "nonumber"} -{"id": 17959, "token": "\u0120Syrian", "merges": "\u0120Sy rian", "raw_count": 84, "count": 84, "decode_str": " Syrian"} -{"id": 20999, "token": "mathop", "merges": "math op", "raw_count": 84, "count": 84, "decode_str": "mathop"} -{"id": 40288, "token": "\u0120$('.", "merges": "\u0120$(' .", "raw_count": 84, "count": 84, "decode_str": " $('."} -{"id": 33002, "token": "\u0120PPAR", "merges": "\u0120P PAR", "raw_count": 84, "count": 84, "decode_str": " PPAR"} -{"id": 9014, "token": "\\]),", "merges": "\\] ),", "raw_count": 84, "count": 84, "decode_str": "\\]),"} -{"id": 18955, "token": "{{{\\", "merges": "{ {{\\", "raw_count": 84, "count": 84, "decode_str": "{{{\\"} -{"id": 35235, "token": "\u0120Memorandum", "merges": "\u0120Mem orandum", "raw_count": 85, "count": 85, "decode_str": " Memorandum"} -{"id": 49106, "token": "\u0120Snowden", "merges": "\u0120Snow den", "raw_count": 85, "count": 85, "decode_str": " Snowden"} -{"id": 34917, "token": "\u0120\u00ce\u00ba\u00ce\u00b1\u00e1\u00bd\u00b6", "merges": "\u0120\u00ce\u00ba\u00ce\u00b1 \u00e1\u00bd\u00b6", "raw_count": 85, "count": 85, "decode_str": " \u03ba\u03b1\u1f76"} -{"id": 27751, "token": "\u0120Vermont", "merges": "\u0120Verm ont", "raw_count": 85, "count": 85, "decode_str": " Vermont"} -{"id": 36388, "token": "\u0120Nearly", "merges": "\u0120N early", "raw_count": 85, "count": 85, "decode_str": " Nearly"} -{"id": 48386, "token": "\u0120Venet", "merges": "\u0120Ven et", "raw_count": 85, "count": 85, "decode_str": " Venet"} -{"id": 43168, "token": "\u0120brane", "merges": "\u0120br ane", "raw_count": 85, "count": 85, "decode_str": " brane"} -{"id": 45079, "token": "\u0120ovat", "merges": "\u0120ov at", "raw_count": 85, "count": 85, "decode_str": " ovat"} -{"id": 27852, "token": "\u0120(\u00c2\u00b1", "merges": "\u0120( \u00c2\u00b1", "raw_count": 85, "count": 85, "decode_str": " (\u00b1"} -{"id": 27628, "token": "\u0120Importantly", "merges": "\u0120Import antly", "raw_count": 86, "count": 86, "decode_str": " Importantly"} -{"id": 36405, "token": "\u0120Sacramento", "merges": "\u0120Sac ramento", "raw_count": 86, "count": 86, "decode_str": " Sacramento"} -{"id": 38641, "token": "\u0120cyclin", "merges": "\u0120cycl in", "raw_count": 86, "count": 86, "decode_str": " cyclin"} -{"id": 49970, "token": "\u0120Quran", "merges": "\u0120Q uran", "raw_count": 86, "count": 86, "decode_str": " Quran"} -{"id": 50180, "token": "\u0120Omaha", "merges": "\u0120O maha", "raw_count": 86, "count": 86, "decode_str": " Omaha"} -{"id": 45657, "token": "underbrace", "merges": "under brace", "raw_count": 87, "count": 87, "decode_str": "underbrace"} -{"id": 17318, "token": "smallcaps", "merges": "small caps", "raw_count": 87, "count": 87, "decode_str": "smallcaps"} -{"id": 48610, "token": "\u0120Sanskrit", "merges": "\u0120Sans krit", "raw_count": 87, "count": 87, "decode_str": " Sanskrit"} -{"id": 27637, "token": "}}}{\\", "merges": "}} }{\\", "raw_count": 87, "count": 87, "decode_str": "}}}{\\"} -{"id": 49217, "token": "\u0120inducible", "merges": "\u0120indu cible", "raw_count": 88, "count": 88, "decode_str": " inducible"} -{"id": 48981, "token": "\u0120autosomal", "merges": "\u0120aut osomal", "raw_count": 88, "count": 88, "decode_str": " autosomal"} -{"id": 41984, "token": "\u0120Cambodia", "merges": "\u0120Camb odia", "raw_count": 88, "count": 88, "decode_str": " Cambodia"} -{"id": 40104, "token": "\u0120Connie", "merges": "\u0120Con nie", "raw_count": 88, "count": 88, "decode_str": " Connie"} -{"id": 34905, "token": "\u0120Ghana", "merges": "\u0120Gh ana", "raw_count": 88, "count": 88, "decode_str": " Ghana"} -{"id": 37664, "token": "\u0120Particularly", "merges": "\u0120Part icularly", "raw_count": 89, "count": 89, "decode_str": " Particularly"} -{"id": 43424, "token": "\u0120Socrates", "merges": "\u0120S ocrates", "raw_count": 89, "count": 89, "decode_str": " Socrates"} -{"id": 40346, "token": "\u0120Guatem", "merges": "\u0120Gu atem", "raw_count": 10, "count": 89, "decode_str": " Guatem"} -{"id": 19446, "token": "})$,", "merges": "} )$,", "raw_count": 89, "count": 89, "decode_str": "})$,"} -{"id": 43182, "token": "\u00e1\u00bd\u0132", "merges": "\u00e1\u00bd \u0132", "raw_count": 89, "count": 89, "decode_str": "\u1f50"} -{"id": 40188, "token": ")}^", "merges": ") }^", "raw_count": 89, "count": 89, "decode_str": ")}^"} -{"id": 44772, "token": "\u0120Strickland", "merges": "\u0120Strick land", "raw_count": 90, "count": 90, "decode_str": " Strickland"} -{"id": 38968, "token": "\u0120phospho", "merges": "\u0120phosph o", "raw_count": 90, "count": 90, "decode_str": " phospho"} -{"id": 38463, "token": "\u0120Abor", "merges": "\u0120A bor", "raw_count": 49, "count": 90, "decode_str": " Abor"} -{"id": 6263, "token": "_{{\\", "merges": "_{ {\\", "raw_count": 73, "count": 90, "decode_str": "_{{\\"} -{"id": 41883, "token": "'}(", "merges": "' }(", "raw_count": 90, "count": 90, "decode_str": "'}("} -{"id": 15638, "token": "&=&", "merges": "&= &", "raw_count": 90, "count": 90, "decode_str": "&=&"} -{"id": 39507, "token": "\u0120INTRODUCTION", "merges": "\u0120IN TRODUCTION", "raw_count": 91, "count": 91, "decode_str": " INTRODUCTION"} -{"id": 47129, "token": "\u0120Escherichia", "merges": "\u0120Esc herichia", "raw_count": 91, "count": 91, "decode_str": " Escherichia"} -{"id": 47778, "token": "\u0120proteases", "merges": "\u0120prote ases", "raw_count": 91, "count": 91, "decode_str": " proteases"} -{"id": 12750, "token": "setminus", "merges": "set minus", "raw_count": 91, "count": 91, "decode_str": "setminus"} -{"id": 44359, "token": "})^{-", "merges": "}) ^{-", "raw_count": 91, "count": 91, "decode_str": "})^{-"} -{"id": 29864, "token": "\u0120DMSO", "merges": "\u0120D MSO", "raw_count": 91, "count": 91, "decode_str": " DMSO"} -{"id": 39115, "token": "},\\\\", "merges": "},\\ \\", "raw_count": 91, "count": 91, "decode_str": "},\\\\"} -{"id": 40673, "token": "\u00e2\u012a\u00bc", "merges": "\u00e2\u012a \u00bc", "raw_count": 91, "count": 91, "decode_str": "\u223c"} -{"id": 34140, "token": "\u0120Holocaust", "merges": "\u0120Hol ocaust", "raw_count": 92, "count": 92, "decode_str": " Holocaust"} -{"id": 44466, "token": "lifeless", "merges": "lif eless", "raw_count": 92, "count": 92, "decode_str": "lifeless"} -{"id": 34921, "token": "\u0120Surely", "merges": "\u0120Sure ly", "raw_count": 92, "count": 92, "decode_str": " Surely"} -{"id": 29179, "token": "rbrack", "merges": "r brack", "raw_count": 92, "count": 92, "decode_str": "rbrack"} -{"id": 32738, "token": "\u0120Kurd", "merges": "\u0120K urd", "raw_count": 56, "count": 92, "decode_str": " Kurd"} -{"id": 26058, "token": "\u0120MPs", "merges": "\u0120M Ps", "raw_count": 92, "count": 92, "decode_str": " MPs"} -{"id": 48542, "token": ")_\\", "merges": ") _\\", "raw_count": 92, "count": 92, "decode_str": ")_\\"} -{"id": 31232, "token": "\u0120phosphorylated", "merges": "\u0120phosphory lated", "raw_count": 93, "count": 93, "decode_str": " phosphorylated"} -{"id": 28103, "token": "\u0120polymorphisms", "merges": "\u0120polymorph isms", "raw_count": 93, "count": 93, "decode_str": " polymorphisms"} -{"id": 46657, "token": "\u0120Armenian", "merges": "\u0120Armen ian", "raw_count": 93, "count": 93, "decode_str": " Armenian"} -{"id": 27373, "token": "\u0120Oakland", "merges": "\u0120Oak land", "raw_count": 93, "count": 93, "decode_str": " Oakland"} -{"id": 37959, "token": "\u0120Serbia", "merges": "\u0120Ser bia", "raw_count": 93, "count": 93, "decode_str": " Serbia"} -{"id": 8827, "token": "rsfs", "merges": "rs fs", "raw_count": 88, "count": 93, "decode_str": "rsfs"} -{"id": 33211, "token": "\u00ce\u00bf\u00ce\u00bb", "merges": "\u00ce\u00bf \u00ce\u00bb", "raw_count": 71, "count": 93, "decode_str": "\u03bf\u03bb"} -{"id": 5539, "token": "ensuremath", "merges": "ensure math", "raw_count": 94, "count": 94, "decode_str": "ensuremath"} -{"id": 28787, "token": "\u0120Hispanic", "merges": "\u0120His panic", "raw_count": 94, "count": 94, "decode_str": " Hispanic"} -{"id": 48986, "token": "\u0120cytosol", "merges": "\u0120cytos ol", "raw_count": 94, "count": 94, "decode_str": " cytosol"} -{"id": 27247, "token": "\u0120Ethiop", "merges": "\u0120Eth iop", "raw_count": 41, "count": 94, "decode_str": " Ethiop"} -{"id": 49119, "token": "\u0120Gideon", "merges": "\u0120G ideon", "raw_count": 94, "count": 94, "decode_str": " Gideon"} -{"id": 29477, "token": "\u0120hab\u00c3\u0143a", "merges": "\u0120hab \u00c3\u0143a", "raw_count": 94, "count": 94, "decode_str": " hab\u00eda"} -{"id": 29580, "token": "\u0120Bernie", "merges": "\u0120Bern ie", "raw_count": 94, "count": 94, "decode_str": " Bernie"} -{"id": 38845, "token": "\u0120Sask", "merges": "\u0120S ask", "raw_count": 32, "count": 94, "decode_str": " Sask"} -{"id": 48718, "token": "\u0120Nell", "merges": "\u0120N ell", "raw_count": 94, "count": 94, "decode_str": " Nell"} -{"id": 40161, "token": "}}{(", "merges": "}}{ (", "raw_count": 94, "count": 94, "decode_str": "}}{("} -{"id": 23505, "token": ".\\[", "merges": ". \\[", "raw_count": 94, "count": 94, "decode_str": ".\\["} -{"id": 21167, "token": "\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142", "merges": "\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142 \u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142\u00c2\u0142", "raw_count": 85, "count": 95, "decode_str": "\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0"} -{"id": 41782, "token": "\u0120contralateral", "merges": "\u0120contral ateral", "raw_count": 95, "count": 95, "decode_str": " contralateral"} -{"id": 45805, "token": "\u0120cytoskeleton", "merges": "\u0120cytos keleton", "raw_count": 95, "count": 95, "decode_str": " cytoskeleton"} -{"id": 46662, "token": "\u0120microg", "merges": "\u0120micro g", "raw_count": 95, "count": 95, "decode_str": " microg"} -{"id": 21411, "token": "overset", "merges": "overs et", "raw_count": 95, "count": 95, "decode_str": "overset"} -{"id": 49211, "token": "\u0120Tenth", "merges": "\u0120T enth", "raw_count": 95, "count": 95, "decode_str": " Tenth"} -{"id": 22891, "token": "\u0120Legislature", "merges": "\u0120Legisl ature", "raw_count": 96, "count": 96, "decode_str": " Legislature"} -{"id": 44943, "token": "\u0120Naturally", "merges": "\u0120N aturally", "raw_count": 96, "count": 96, "decode_str": " Naturally"} -{"id": 28776, "token": "\u0120Notably", "merges": "\u0120Not ably", "raw_count": 96, "count": 96, "decode_str": " Notably"} -{"id": 41330, "token": "fefefe", "merges": "fefe fe", "raw_count": 96, "count": 96, "decode_str": "fefefe"} -{"id": 44526, "token": "\u0120Mets", "merges": "\u0120M ets", "raw_count": 96, "count": 96, "decode_str": " Mets"} -{"id": 24768, "token": "},{\\", "merges": "}, {\\", "raw_count": 96, "count": 96, "decode_str": "},{\\"} -{"id": 45307, "token": "\u0120H\u00c3\u00b6", "merges": "\u0120H \u00c3\u00b6", "raw_count": 96, "count": 96, "decode_str": " H\u00f6"} -{"id": 52398, "token": "\u00e6\u0143\u013d", "merges": "\u00e6\u0143 \u013d", "raw_count": 96, "count": 96, "decode_str": "\u6b5b"} -{"id": 44259, "token": "Acknowledgments", "merges": "Acknowled gments", "raw_count": 97, "count": 97, "decode_str": "Acknowledgments"} -{"id": 49937, "token": "\u0120Chevrolet", "merges": "\u0120Chev rolet", "raw_count": 97, "count": 97, "decode_str": " Chevrolet"} -{"id": 49680, "token": "\u0120hadronic", "merges": "\u0120had ronic", "raw_count": 97, "count": 97, "decode_str": " hadronic"} -{"id": 49457, "token": "\u0120HOWEVER", "merges": "\u0120HOW EVER", "raw_count": 97, "count": 97, "decode_str": " HOWEVER"} -{"id": 37304, "token": "\u0120Calgary", "merges": "\u0120Cal gary", "raw_count": 97, "count": 97, "decode_str": " Calgary"} -{"id": 42499, "token": "\u0120m\u00c3\u00a5ste", "merges": "\u0120m\u00c3\u00a5 ste", "raw_count": 97, "count": 97, "decode_str": " m\u00e5ste"} -{"id": 17098, "token": "}{{\\", "merges": "}{ {\\", "raw_count": 97, "count": 97, "decode_str": "}{{\\"} -{"id": 46149, "token": "\u0120Hsp", "merges": "\u0120H sp", "raw_count": 97, "count": 97, "decode_str": " Hsp"} -{"id": 46075, "token": "\u0120idiopathic", "merges": "\u0120idi opathic", "raw_count": 98, "count": 98, "decode_str": " idiopathic"} -{"id": 45585, "token": "\u0120linebacker", "merges": "\u0120lineback er", "raw_count": 98, "count": 98, "decode_str": " linebacker"} -{"id": 49702, "token": "\u0120proteasome", "merges": "\u0120prote asome", "raw_count": 98, "count": 98, "decode_str": " proteasome"} -{"id": 49402, "token": "\u0120Athletics", "merges": "\u0120Athlet ics", "raw_count": 98, "count": 98, "decode_str": " Athletics"} -{"id": 45575, "token": "\u0120Romanian", "merges": "\u0120Roman ian", "raw_count": 98, "count": 98, "decode_str": " Romanian"} -{"id": 43828, "token": "\u0120Myanmar", "merges": "\u0120My anmar", "raw_count": 98, "count": 98, "decode_str": " Myanmar"} -{"id": 46019, "token": "Argued", "merges": "Arg ued", "raw_count": 98, "count": 98, "decode_str": "Argued"} -{"id": 36317, "token": "\u0120FIGS", "merges": "\u0120FIG S", "raw_count": 98, "count": 98, "decode_str": " FIGS"} -{"id": 45496, "token": "\u0120(!(", "merges": "\u0120(! (", "raw_count": 98, "count": 98, "decode_str": " (!("} -{"id": 38217, "token": "(@\"", "merges": "( @\"", "raw_count": 98, "count": 98, "decode_str": "(@\""} -{"id": 34488, "token": ").$", "merges": "). $", "raw_count": 98, "count": 98, "decode_str": ").$"} -{"id": 38409, "token": "leftrightarrow", "merges": "left rightarrow", "raw_count": 99, "count": 99, "decode_str": "leftrightarrow"} -{"id": 46409, "token": "\u0120histologic", "merges": "\u0120hist ologic", "raw_count": 99, "count": 99, "decode_str": " histologic"} -{"id": 38173, "token": "ClCompile", "merges": "Cl Compile", "raw_count": 99, "count": 99, "decode_str": "ClCompile"} -{"id": 46936, "token": "\u0120Kazakh", "merges": "\u0120Kaz akh", "raw_count": 99, "count": 99, "decode_str": " Kazakh"} -{"id": 44660, "token": "\u0120Ravens", "merges": "\u0120Rav ens", "raw_count": 99, "count": 99, "decode_str": " Ravens"} -{"id": 38327, "token": "))/(-", "merges": ")) /(-", "raw_count": 99, "count": 99, "decode_str": "))/(-"} -{"id": 43790, "token": ")\\,\\", "merges": ")\\ ,\\", "raw_count": 99, "count": 99, "decode_str": ")\\,\\"} -{"id": 50304, "token": "\u00e2\u0123\u00bf", "merges": "\u00e2\u0123 \u00bf", "raw_count": 99, "count": 99, "decode_str": "\u207f"} -{"id": 50322, "token": "\u00e2\u012a\u00a5", "merges": "\u00e2\u012a \u00a5", "raw_count": 99, "count": 99, "decode_str": "\u2225"} -{"id": 46608, "token": "*~(", "merges": "*~ (", "raw_count": 99, "count": 99, "decode_str": "*~("} -{"id": 50394, "token": "\u00e3\u0122\u0135", "merges": "\u00e3\u0122 \u0135", "raw_count": 99, "count": 99, "decode_str": "\u3013"} -{"id": 43077, "token": "\u00e1\u00bf\u0138", "merges": "\u00e1\u00bf \u0138", "raw_count": 99, "count": 99, "decode_str": "\u1fd6"} -{"id": 20475, "token": "\u00c2\u013f", "merges": "\u00c2 \u013f", "raw_count": 99, "count": 99, "decode_str": "\u009d"} -{"id": 23879, "token": "\u0120transfection", "merges": "\u0120trans fection", "raw_count": 100, "count": 100, "decode_str": " transfection"} -{"id": 39966, "token": "\u0120\u00c3\u00b6ver", "merges": "\u0120\u00c3\u00b6 ver", "raw_count": 100, "count": 100, "decode_str": " \u00f6ver"} -{"id": 48660, "token": "\u0120Reds", "merges": "\u0120Red s", "raw_count": 100, "count": 100, "decode_str": " Reds"} -{"id": 35969, "token": "\u0120L\u00c3\u00a9", "merges": "\u0120L \u00c3\u00a9", "raw_count": 100, "count": 100, "decode_str": " L\u00e9"} -{"id": 53171, "token": "\u00e7\u00a8\u013e", "merges": "\u00e7\u00a8 \u013e", "raw_count": 100, "count": 100, "decode_str": "\u7a1c"} -{"id": 49377, "token": "\u00c4\u0123m", "merges": "\u00c4\u0123 m", "raw_count": 100, "count": 100, "decode_str": "\u0101m"} -{"id": 36242, "token": "\u0120Approximately", "merges": "\u0120Appro ximately", "raw_count": 101, "count": 101, "decode_str": " Approximately"} -{"id": 38623, "token": "\u0120CONTRIBUTORS", "merges": "\u0120CONTRIBUT ORS", "raw_count": 101, "count": 101, "decode_str": " CONTRIBUTORS"} -{"id": 49238, "token": "\u0120anesthetized", "merges": "\u0120anest hetized", "raw_count": 101, "count": 101, "decode_str": " anesthetized"} -{"id": 48633, "token": "\u0120microtubule", "merges": "\u0120microtub ule", "raw_count": 101, "count": 101, "decode_str": " microtubule"} -{"id": 48844, "token": "\u0120photoresist", "merges": "\u0120phot oresist", "raw_count": 101, "count": 101, "decode_str": " photoresist"} -{"id": 43393, "token": "\u0120neuropath", "merges": "\u0120neurop ath", "raw_count": 101, "count": 101, "decode_str": " neuropath"} -{"id": 37384, "token": "\u0120\u00cf\u0125\u00cf\u0126\u00ce\u00b7", "merges": "\u0120\u00cf\u0125 \u00cf\u0126\u00ce\u00b7", "raw_count": 32, "count": 101, "decode_str": " \u03c3\u03c4\u03b7"} -{"id": 25135, "token": "}^{+", "merges": "}^{ +", "raw_count": 101, "count": 101, "decode_str": "}^{+"} -{"id": 12410, "token": "\u00c2\u0123", "merges": "\u00c2 \u0123", "raw_count": 101, "count": 101, "decode_str": "\u0081"} -{"id": 27608, "token": "\u0120Venezuela", "merges": "\u0120Venezuel a", "raw_count": 102, "count": 102, "decode_str": " Venezuela"} -{"id": 27794, "token": "\u0120Victorian", "merges": "\u0120Victor ian", "raw_count": 102, "count": 102, "decode_str": " Victorian"} -{"id": 39519, "token": "\u0120ubiquitin", "merges": "\u0120ubiquit in", "raw_count": 102, "count": 102, "decode_str": " ubiquitin"} -{"id": 22565, "token": "\u0120Sheriff", "merges": "\u0120Sher iff", "raw_count": 102, "count": 102, "decode_str": " Sheriff"} -{"id": 48907, "token": "\u0120Allies", "merges": "\u0120All ies", "raw_count": 102, "count": 102, "decode_str": " Allies"} -{"id": 44489, "token": "\u0120Naples", "merges": "\u0120Na ples", "raw_count": 102, "count": 102, "decode_str": " Naples"} -{"id": 45602, "token": "\u0120MRSA", "merges": "\u0120MR SA", "raw_count": 102, "count": 102, "decode_str": " MRSA"} -{"id": 27889, "token": "pbio", "merges": "pb io", "raw_count": 102, "count": 102, "decode_str": "pbio"} -{"id": 44177, "token": "\u00c3\u00bdm", "merges": "\u00c3\u00bd m", "raw_count": 102, "count": 102, "decode_str": "\u00fdm"} -{"id": 16525, "token": "----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------", "merges": "-------------------------------------------------------------------------------------------------------------------------------- --------------------------------------------------------------------------------------------------------------------------------", "raw_count": 87, "count": 103, "decode_str": "----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------"} -{"id": 41878, "token": "\u0120\u00ce\u00b4\u00ce\u00b9\u00ce\u00b1", "merges": "\u0120\u00ce\u00b4 \u00ce\u00b9\u00ce\u00b1", "raw_count": 103, "count": 103, "decode_str": " \u03b4\u03b9\u03b1"} -{"id": 41068, "token": "\u0120antitumor", "merges": "\u0120antit umor", "raw_count": 104, "count": 104, "decode_str": " antitumor"} -{"id": 50178, "token": "\u0120Lindsey", "merges": "\u0120Lind sey", "raw_count": 104, "count": 104, "decode_str": " Lindsey"} -{"id": 31351, "token": "\u0120Belgian", "merges": "\u0120Bel gian", "raw_count": 104, "count": 104, "decode_str": " Belgian"} -{"id": 40839, "token": "\u0120Chiefs", "merges": "\u0120Chief s", "raw_count": 104, "count": 104, "decode_str": " Chiefs"} -{"id": 48911, "token": "\u0120\u00ce\u00bc\u00ce\u0143", "merges": "\u0120\u00ce\u00bc \u00ce\u0143", "raw_count": 104, "count": 104, "decode_str": " \u03bc\u03ad"} -{"id": 16265, "token": "}}}(", "merges": "}} }(", "raw_count": 104, "count": 104, "decode_str": "}}}("} -{"id": 32998, "token": "})_{", "merges": "}) _{", "raw_count": 104, "count": 104, "decode_str": "})_{"} -{"id": 29313, "token": "\u0120Palestine", "merges": "\u0120Palest ine", "raw_count": 105, "count": 105, "decode_str": " Palestine"} -{"id": 48628, "token": "\u0120doxor", "merges": "\u0120do xor", "raw_count": 65, "count": 105, "decode_str": " doxor"} -{"id": 21627, "token": "}\\,\\", "merges": "}\\ ,\\", "raw_count": 105, "count": 105, "decode_str": "}\\,\\"} -{"id": 47898, "token": "\u0120h\u00c3\u00a5", "merges": "\u0120h \u00c3\u00a5", "raw_count": 105, "count": 105, "decode_str": " h\u00e5"} -{"id": 49740, "token": "\u0120Utt", "merges": "\u0120U tt", "raw_count": 105, "count": 105, "decode_str": " Utt"} -{"id": 46186, "token": ":{\\", "merges": ": {\\", "raw_count": 105, "count": 105, "decode_str": ":{\\"} -{"id": 35622, "token": "\u0120astrocytes", "merges": "\u0120ast rocytes", "raw_count": 106, "count": 106, "decode_str": " astrocytes"} -{"id": 10823, "token": "\u0120Democrats", "merges": "\u0120Democr ats", "raw_count": 106, "count": 106, "decode_str": " Democrats"} -{"id": 30142, "token": "\u0120comorbid", "merges": "\u0120comor bid", "raw_count": 41, "count": 106, "decode_str": " comorbid"} -{"id": 47823, "token": "\u0120INDIRECT", "merges": "\u0120IN DIRECT", "raw_count": 106, "count": 106, "decode_str": " INDIRECT"} -{"id": 38159, "token": "apoptotic", "merges": "apopt otic", "raw_count": 106, "count": 106, "decode_str": "apoptotic"} -{"id": 20176, "token": "\u0120Nebraska", "merges": "\u0120Ne braska", "raw_count": 106, "count": 106, "decode_str": " Nebraska"} -{"id": 39863, "token": "\u0120Eston", "merges": "\u0120E ston", "raw_count": 106, "count": 106, "decode_str": " Eston"} -{"id": 48744, "token": ")\\<", "merges": ")\\ <", "raw_count": 106, "count": 106, "decode_str": ")\\<"} -{"id": 48977, "token": "\u0120erythrocytes", "merges": "\u0120eryth rocytes", "raw_count": 107, "count": 107, "decode_str": " erythrocytes"} -{"id": 31737, "token": "\u0120transgender", "merges": "\u0120trans gender", "raw_count": 107, "count": 107, "decode_str": " transgender"} -{"id": 29089, "token": "\u0120Cincinnati", "merges": "\u0120Cinc innati", "raw_count": 107, "count": 107, "decode_str": " Cincinnati"} -{"id": 47804, "token": "\u0120quelques", "merges": "\u0120quel ques", "raw_count": 107, "count": 107, "decode_str": " quelques"} -{"id": 48104, "token": "\u0120Lisbon", "merges": "\u0120Lis bon", "raw_count": 107, "count": 107, "decode_str": " Lisbon"} -{"id": 24918, "token": "\u0120$('#", "merges": "\u0120$(' #", "raw_count": 107, "count": 107, "decode_str": " $('#"} -{"id": 41447, "token": "[\\#", "merges": "[\\ #", "raw_count": 107, "count": 107, "decode_str": "[\\#"} -{"id": 47625, "token": "\u0120subcellular", "merges": "\u0120sub cellular", "raw_count": 108, "count": 108, "decode_str": " subcellular"} -{"id": 43005, "token": "\u00ce\u00bf\u00cf\u0127\u00ce\u00bc\u00ce\u00b5", "merges": "\u00ce\u00bf\u00cf\u0127 \u00ce\u00bc\u00ce\u00b5", "raw_count": 108, "count": 108, "decode_str": "\u03bf\u03c5\u03bc\u03b5"} -{"id": 36763, "token": "\u0120Ottoman", "merges": "\u0120Ott oman", "raw_count": 108, "count": 108, "decode_str": " Ottoman"} -{"id": 49444, "token": "\u0120Lenin", "merges": "\u0120Len in", "raw_count": 108, "count": 108, "decode_str": " Lenin"} -{"id": 23882, "token": "|^{", "merges": "| ^{", "raw_count": 108, "count": 108, "decode_str": "|^{"} -{"id": 30522, "token": "]^{", "merges": "] ^{", "raw_count": 108, "count": 108, "decode_str": "]^{"} -{"id": 41254, "token": "\u0120\u00c3\u00ab", "merges": "\u0120\u00c3 \u00ab", "raw_count": 108, "count": 108, "decode_str": " \u00eb"} -{"id": 38843, "token": "\u0120surfactant", "merges": "\u0120surfact ant", "raw_count": 109, "count": 109, "decode_str": " surfactant"} -{"id": 49640, "token": "\u0120pretreated", "merges": "\u0120pret reated", "raw_count": 109, "count": 109, "decode_str": " pretreated"} -{"id": 25794, "token": "\u0120Delaware", "merges": "\u0120Del aware", "raw_count": 109, "count": 109, "decode_str": " Delaware"} -{"id": 42577, "token": "\u0120hypoxic", "merges": "\u0120hypox ic", "raw_count": 109, "count": 109, "decode_str": " hypoxic"} -{"id": 32681, "token": "\u0120\u00cf\u0126\u00cf\u012b\u00ce\u00bd", "merges": "\u0120\u00cf\u0126 \u00cf\u012b\u00ce\u00bd", "raw_count": 109, "count": 109, "decode_str": " \u03c4\u03c9\u03bd"} -{"id": 39272, "token": "}}}}\\", "merges": "}} }}\\", "raw_count": 109, "count": 109, "decode_str": "}}}}\\"} -{"id": 33697, "token": "\u0120DCs", "merges": "\u0120D Cs", "raw_count": 109, "count": 109, "decode_str": " DCs"} -{"id": 10952, "token": "\\}$", "merges": "\\ }$", "raw_count": 109, "count": 109, "decode_str": "\\}$"} -{"id": 184, "token": "\u0107", "merges": "NULL", "raw_count": 109, "count": 109, "decode_str": "\u0007"} -{"id": 45550, "token": "OnClickListener", "merges": "On ClickListener", "raw_count": 110, "count": 110, "decode_str": "OnClickListener"} -{"id": 9892, "token": "\u0120Appeals", "merges": "\u0120Appe als", "raw_count": 110, "count": 110, "decode_str": " Appeals"} -{"id": 38756, "token": "\u0120trypsin", "merges": "\u0120try psin", "raw_count": 110, "count": 110, "decode_str": " trypsin"} -{"id": 38752, "token": "\u0120Albany", "merges": "\u0120Alb any", "raw_count": 110, "count": 110, "decode_str": " Albany"} -{"id": 16158, "token": "\u0120Saudi", "merges": "\u0120S audi", "raw_count": 110, "count": 110, "decode_str": " Saudi"} -{"id": 46147, "token": "\u0120Kathy", "merges": "\u0120K athy", "raw_count": 110, "count": 110, "decode_str": " Kathy"} -{"id": 41277, "token": "\u0120Juda", "merges": "\u0120Jud a", "raw_count": 34, "count": 110, "decode_str": " Juda"} -{"id": 34145, "token": "biggr", "merges": "big gr", "raw_count": 110, "count": 110, "decode_str": "biggr"} -{"id": 16160, "token": "*\\<", "merges": "* \\<", "raw_count": 110, "count": 110, "decode_str": "*\\<"} -{"id": 28511, "token": ";\\;", "merges": ";\\ ;", "raw_count": 110, "count": 110, "decode_str": ";\\;"} -{"id": 37447, "token": "\u00db\u0137", "merges": "\u00db \u0137", "raw_count": 110, "count": 110, "decode_str": "\u06d5"} -{"id": 40099, "token": "\u0120proliferative", "merges": "\u0120prolifer ative", "raw_count": 111, "count": 111, "decode_str": " proliferative"} -{"id": 47486, "token": "\u0120Volkswagen", "merges": "\u0120Volks wagen", "raw_count": 111, "count": 111, "decode_str": " Volkswagen"} -{"id": 38717, "token": "\u0120mitotic", "merges": "\u0120mit otic", "raw_count": 111, "count": 111, "decode_str": " mitotic"} -{"id": 30841, "token": "\u0120Congressional", "merges": "\u0120Cong ressional", "raw_count": 112, "count": 112, "decode_str": " Congressional"} -{"id": 22283, "token": "\u0120Venezuel", "merges": "\u0120V enezuel", "raw_count": 10, "count": 112, "decode_str": " Venezuel"} -{"id": 48641, "token": "\u0120Marxist", "merges": "\u0120Marx ist", "raw_count": 112, "count": 112, "decode_str": " Marxist"} -{"id": 28746, "token": "\u0120Lebanon", "merges": "\u0120Leban on", "raw_count": 113, "count": 113, "decode_str": " Lebanon"} -{"id": 49456, "token": "\u0120\u00ce\u00b4\u00ce\u00b5\u00ce\u00bd", "merges": "\u0120\u00ce\u00b4 \u00ce\u00b5\u00ce\u00bd", "raw_count": 113, "count": 113, "decode_str": " \u03b4\u03b5\u03bd"} -{"id": 29539, "token": "\u0120Ottawa", "merges": "\u0120Ot tawa", "raw_count": 113, "count": 113, "decode_str": " Ottawa"} -{"id": 48002, "token": "\u0120\u00cf\u0126\u00ce\u00b9\u00cf\u0124", "merges": "\u0120\u00cf\u0126 \u00ce\u00b9\u00cf\u0124", "raw_count": 113, "count": 113, "decode_str": " \u03c4\u03b9\u03c2"} -{"id": 32345, "token": "\u0120Niger", "merges": "\u0120N iger", "raw_count": 74, "count": 113, "decode_str": " Niger"} -{"id": 38382, "token": "\u0120Bris", "merges": "\u0120Br is", "raw_count": 46, "count": 113, "decode_str": " Bris"} -{"id": 28280, "token": "\u0120Morm", "merges": "\u0120M orm", "raw_count": 45, "count": 113, "decode_str": " Morm"} -{"id": 27805, "token": "lVert", "merges": "l Vert", "raw_count": 113, "count": 113, "decode_str": "lVert"} -{"id": 42052, "token": "\u0120\u00c2\u00bb.", "merges": "\u0120\u00c2\u00bb .", "raw_count": 113, "count": 113, "decode_str": " \u00bb."} -{"id": 46673, "token": "\u00e1\u00bd\u00b0", "merges": "\u00e1\u00bd \u00b0", "raw_count": 113, "count": 113, "decode_str": "\u1f70"} -{"id": 54216, "token": "\u00e9\u0129\u00a6", "merges": "\u00e9\u0129 \u00a6", "raw_count": 113, "count": 113, "decode_str": "\u91e6"} -{"id": 46559, "token": "\u0120Brighton", "merges": "\u0120Bright on", "raw_count": 114, "count": 114, "decode_str": " Brighton"} -{"id": 22306, "token": "\u0120Barack", "merges": "\u0120Bar ack", "raw_count": 114, "count": 114, "decode_str": " Barack"} -{"id": 33074, "token": "\u0120Cuban", "merges": "\u0120Cub an", "raw_count": 114, "count": 114, "decode_str": " Cuban"} -{"id": 44558, "token": "\u0120Malay", "merges": "\u0120Mal ay", "raw_count": 114, "count": 114, "decode_str": " Malay"} -{"id": 46890, "token": ")}}{", "merges": ") }}{", "raw_count": 114, "count": 114, "decode_str": ")}}{"} -{"id": 43869, "token": "\u0120\u00c5\u0142", "merges": "\u0120\u00c5 \u0142", "raw_count": 114, "count": 114, "decode_str": " \u0160"} -{"id": 41491, "token": "\u0120Worcester", "merges": "\u0120Wor cester", "raw_count": 115, "count": 115, "decode_str": " Worcester"} -{"id": 47374, "token": "\u0120Lakers", "merges": "\u0120L akers", "raw_count": 115, "count": 115, "decode_str": " Lakers"} -{"id": 45248, "token": "\u0120Manit", "merges": "\u0120Man it", "raw_count": 115, "count": 115, "decode_str": " Manit"} -{"id": 47979, "token": "\u0120Abbas", "merges": "\u0120Ab bas", "raw_count": 115, "count": 115, "decode_str": " Abbas"} -{"id": 32710, "token": "\u0120Modi", "merges": "\u0120Mod i", "raw_count": 115, "count": 115, "decode_str": " Modi"} -{"id": 29310, "token": "\u0120Bangladesh", "merges": "\u0120Bangl adesh", "raw_count": 116, "count": 116, "decode_str": " Bangladesh"} -{"id": 30186, "token": "\u0120Pentagon", "merges": "\u0120Pent agon", "raw_count": 116, "count": 116, "decode_str": " Pentagon"} -{"id": 44867, "token": "\u0120Belfast", "merges": "\u0120Belf ast", "raw_count": 116, "count": 116, "decode_str": " Belfast"} -{"id": 32109, "token": "\u0120lactate", "merges": "\u0120lact ate", "raw_count": 116, "count": 116, "decode_str": " lactate"} -{"id": 32111, "token": "\u0120Mumbai", "merges": "\u0120M umbai", "raw_count": 116, "count": 116, "decode_str": " Mumbai"} -{"id": 24460, "token": "\u0120Romney", "merges": "\u0120Rom ney", "raw_count": 116, "count": 116, "decode_str": " Romney"} -{"id": 26874, "token": "lbrack", "merges": "l brack", "raw_count": 116, "count": 116, "decode_str": "lbrack"} -{"id": 40301, "token": "\u00ce\u00af\u00ce\u00b1\u00cf\u0124", "merges": "\u00ce\u00af\u00ce\u00b1 \u00cf\u0124", "raw_count": 116, "count": 116, "decode_str": "\u03af\u03b1\u03c2"} -{"id": 47478, "token": "\u0120TBI", "merges": "\u0120T BI", "raw_count": 116, "count": 116, "decode_str": " TBI"} -{"id": 37890, "token": "\u00c3\u00a2nd", "merges": "\u00c3\u00a2 nd", "raw_count": 116, "count": 116, "decode_str": "\u00e2nd"} -{"id": 50384, "token": "\u00e2\u013b\u00ac", "merges": "\u00e2\u013b \u00ac", "raw_count": 116, "count": 116, "decode_str": "\u266c"} -{"id": 203, "token": "\u011a", "merges": "NULL", "raw_count": 116, "count": 116, "decode_str": "\u001a"} -{"id": 26260, "token": "\u0120--------------------------------------------------------------------------------------------------------------------------------", "merges": "\u0120 --------------------------------------------------------------------------------------------------------------------------------", "raw_count": 117, "count": 117, "decode_str": " --------------------------------------------------------------------------------------------------------------------------------"} -{"id": 38521, "token": "\u0120lineback", "merges": "\u0120line back", "raw_count": 19, "count": 117, "decode_str": " lineback"} -{"id": 30489, "token": "lfloor", "merges": "l floor", "raw_count": 117, "count": 117, "decode_str": "lfloor"} -{"id": 47752, "token": "\u0120Bronx", "merges": "\u0120Bron x", "raw_count": 117, "count": 117, "decode_str": " Bronx"} -{"id": 45690, "token": "\u0120Scots", "merges": "\u0120Sc ots", "raw_count": 117, "count": 117, "decode_str": " Scots"} -{"id": 29135, "token": "\u0120\u00e1\u00bc\u0132", "merges": "\u0120\u00e1\u00bc \u0132", "raw_count": 117, "count": 117, "decode_str": " \u1f10"} -{"id": 43026, "token": "\u0120QTL", "merges": "\u0120Q TL", "raw_count": 117, "count": 117, "decode_str": " QTL"} -{"id": 48234, "token": "\u00e1\u00bf\u00a6", "merges": "\u00e1\u00bf \u00a6", "raw_count": 117, "count": 117, "decode_str": "\u1fe6"} -{"id": 26808, "token": "nanomaterials", "merges": "nan omaterials", "raw_count": 118, "count": 118, "decode_str": "nanomaterials"} -{"id": 27756, "token": "\u0120Idaho", "merges": "\u0120Id aho", "raw_count": 118, "count": 118, "decode_str": " Idaho"} -{"id": 42811, "token": "\u0120Pero", "merges": "\u0120P ero", "raw_count": 118, "count": 118, "decode_str": " Pero"} -{"id": 12460, "token": "}}$,", "merges": "}} $,", "raw_count": 118, "count": 118, "decode_str": "}}$,"} -{"id": 46363, "token": "\u0120HCT", "merges": "\u0120H CT", "raw_count": 118, "count": 118, "decode_str": " HCT"} -{"id": 46346, "token": "\u0120histopathological", "merges": "\u0120hist opathological", "raw_count": 119, "count": 119, "decode_str": " histopathological"} -{"id": 43326, "token": "\u0120Hawaiian", "merges": "\u0120Hawai ian", "raw_count": 119, "count": 119, "decode_str": " Hawaiian"} -{"id": 44637, "token": "\u0120Cyprus", "merges": "\u0120Cy prus", "raw_count": 119, "count": 119, "decode_str": " Cyprus"} -{"id": 40316, "token": "\u0120Devon", "merges": "\u0120Dev on", "raw_count": 119, "count": 119, "decode_str": " Devon"} -{"id": 33984, "token": "\u0120CURI", "merges": "\u0120C URI", "raw_count": 117, "count": 119, "decode_str": " CURI"} -{"id": 31878, "token": "\u0120Hait", "merges": "\u0120H ait", "raw_count": 64, "count": 119, "decode_str": " Hait"} -{"id": 44123, "token": "\u0120Liam", "merges": "\u0120Li am", "raw_count": 119, "count": 119, "decode_str": " Liam"} -{"id": 33509, "token": "INCLUDING", "merges": "IN CLUDING", "raw_count": 120, "count": 120, "decode_str": "INCLUDING"} -{"id": 29535, "token": "\u0120Austrian", "merges": "\u0120Aust rian", "raw_count": 120, "count": 120, "decode_str": " Austrian"} -{"id": 47627, "token": "\u0120Deborah", "merges": "\u0120Debor ah", "raw_count": 120, "count": 120, "decode_str": " Deborah"} -{"id": 36819, "token": "\u0120Tory", "merges": "\u0120T ory", "raw_count": 120, "count": 120, "decode_str": " Tory"} -{"id": 49220, "token": "\u0120MgCl", "merges": "\u0120Mg Cl", "raw_count": 120, "count": 120, "decode_str": " MgCl"} -{"id": 44797, "token": "\u0120ktor", "merges": "\u0120k tor", "raw_count": 120, "count": 120, "decode_str": " ktor"} -{"id": 14658, "token": "\u0120\u00e2\u013b\u00aa", "merges": "\u0120\u00e2 \u013b\u00aa", "raw_count": 116, "count": 120, "decode_str": " \u266a"} -{"id": 17849, "token": "\u0120s\u00c4\u0125", "merges": "\u0120s \u00c4\u0125", "raw_count": 120, "count": 120, "decode_str": " s\u0103"} -{"id": 20863, "token": "\u0120MERCHANTABILITY", "merges": "\u0120MER CHANTABILITY", "raw_count": 121, "count": 121, "decode_str": " MERCHANTABILITY"} -{"id": 43164, "token": "\u0120fprintf", "merges": "\u0120f printf", "raw_count": 121, "count": 121, "decode_str": " fprintf"} -{"id": 30266, "token": "rfloor", "merges": "r floor", "raw_count": 121, "count": 121, "decode_str": "rfloor"} -{"id": 47403, "token": "\u00cf\u0122\u00ce\u00b5\u00ce\u00b9", "merges": "\u00cf\u0122 \u00ce\u00b5\u00ce\u00b9", "raw_count": 121, "count": 121, "decode_str": "\u03c0\u03b5\u03b9"} -{"id": 45751, "token": "\u0120Photograph", "merges": "\u0120Phot ograph", "raw_count": 122, "count": 122, "decode_str": " Photograph"} -{"id": 27485, "token": "\u0120Ukrainian", "merges": "\u0120Uk rainian", "raw_count": 122, "count": 122, "decode_str": " Ukrainian"} -{"id": 30167, "token": "\u0120Brussels", "merges": "\u0120Br ussels", "raw_count": 122, "count": 122, "decode_str": " Brussels"} -{"id": 40115, "token": "\u0120Lithuan", "merges": "\u0120Lith uan", "raw_count": 122, "count": 122, "decode_str": " Lithuan"} -{"id": 49786, "token": "\u0120Minist", "merges": "\u0120Min ist", "raw_count": 122, "count": 122, "decode_str": " Minist"} -{"id": 30228, "token": "\u0120Croat", "merges": "\u0120Cro at", "raw_count": 50, "count": 122, "decode_str": " Croat"} -{"id": 35280, "token": "\u00ce\u00bf\u00cf\u0127\u00ce\u00bd", "merges": "\u00ce\u00bf\u00cf\u0127 \u00ce\u00bd", "raw_count": 122, "count": 122, "decode_str": "\u03bf\u03c5\u03bd"} -{"id": 36587, "token": "=\"../../../", "merges": "=\"../../ ../", "raw_count": 123, "count": 123, "decode_str": "=\"../../../"} -{"id": 48684, "token": "\u0120rehearing", "merges": "\u0120rehe aring", "raw_count": 123, "count": 123, "decode_str": " rehearing"} -{"id": 41414, "token": "\u0120Walmart", "merges": "\u0120Wal mart", "raw_count": 123, "count": 123, "decode_str": " Walmart"} -{"id": 27325, "token": "\u0120Sudan", "merges": "\u0120Sud an", "raw_count": 123, "count": 123, "decode_str": " Sudan"} -{"id": 36748, "token": "\u00c3\u00a9tait", "merges": "\u00c3\u00a9 tait", "raw_count": 123, "count": 123, "decode_str": "\u00e9tait"} -{"id": 50340, "token": "\u00e2\u0136\u012c", "merges": "\u00e2\u0136 \u012c", "raw_count": 123, "count": 123, "decode_str": "\u250a"} -{"id": 37207, "token": "}|^", "merges": "}| ^", "raw_count": 123, "count": 123, "decode_str": "}|^"} -{"id": 16111, "token": "\u0120Afghanistan", "merges": "\u0120Afghan istan", "raw_count": 124, "count": 124, "decode_str": " Afghanistan"} -{"id": 24646, "token": "\u0120Conversely", "merges": "\u0120Con versely", "raw_count": 124, "count": 124, "decode_str": " Conversely"} -{"id": 34402, "token": "\u0120cisplatin", "merges": "\u0120cis platin", "raw_count": 124, "count": 124, "decode_str": " cisplatin"} -{"id": 17753, "token": "\u0120Louisiana", "merges": "\u0120Louis iana", "raw_count": 124, "count": 124, "decode_str": " Louisiana"} -{"id": 22514, "token": "\u0120Leban", "merges": "\u0120Le ban", "raw_count": 3, "count": 124, "decode_str": " Leban"} -{"id": 43406, "token": "\u0120Jared", "merges": "\u0120J ared", "raw_count": 124, "count": 124, "decode_str": " Jared"} -{"id": 49076, "token": "ophils", "merges": "oph ils", "raw_count": 124, "count": 124, "decode_str": "ophils"} -{"id": 22295, "token": "\u0120c\u00c4\u0125", "merges": "\u0120c \u00c4\u0125", "raw_count": 124, "count": 124, "decode_str": " c\u0103"} -{"id": 30765, "token": "\u00c3\u00b1or", "merges": "\u00c3\u00b1 or", "raw_count": 124, "count": 124, "decode_str": "\u00f1or"} -{"id": 35311, "token": "\u0120immunohistochemistry", "merges": "\u0120immunohist ochemistry", "raw_count": 125, "count": 125, "decode_str": " immunohistochemistry"} -{"id": 47667, "token": "\u0120filos", "merges": "\u0120fil os", "raw_count": 125, "count": 125, "decode_str": " filos"} -{"id": 32080, "token": "\u0120\\{\\", "merges": "\u0120\\ {\\", "raw_count": 125, "count": 125, "decode_str": " \\{\\"} -{"id": 33011, "token": "\u00cf\u012b\u00cf\u0124", "merges": "\u00cf\u012b \u00cf\u0124", "raw_count": 125, "count": 125, "decode_str": "\u03c9\u03c2"} -{"id": 44973, "token": "\u00e0\u00b0\u00bf", "merges": "\u00e0\u00b0 \u00bf", "raw_count": 125, "count": 125, "decode_str": "\u0c3f"} -{"id": 45685, "token": "\u00c4\u0123r", "merges": "\u00c4\u0123 r", "raw_count": 125, "count": 125, "decode_str": "\u0101r"} -{"id": 49630, "token": "\u0120modulates", "merges": "\u0120modul ates", "raw_count": 126, "count": 126, "decode_str": " modulates"} -{"id": 28150, "token": "\u0120Sergeant", "merges": "\u0120Ser geant", "raw_count": 126, "count": 126, "decode_str": " Sergeant"} -{"id": 30109, "token": "\u0120Veterans", "merges": "\u0120Veter ans", "raw_count": 126, "count": 126, "decode_str": " Veterans"} -{"id": 45845, "token": "\u0120Tribunal", "merges": "\u0120Trib unal", "raw_count": 126, "count": 126, "decode_str": " Tribunal"} -{"id": 48486, "token": "\u0120Himself", "merges": "\u0120Him self", "raw_count": 126, "count": 126, "decode_str": " Himself"} -{"id": 47665, "token": "\u0120alanine", "merges": "\u0120al anine", "raw_count": 126, "count": 126, "decode_str": " alanine"} -{"id": 32553, "token": "\u0120aryl", "merges": "\u0120ar yl", "raw_count": 126, "count": 126, "decode_str": " aryl"} -{"id": 43391, "token": "})}{", "merges": "}) }{", "raw_count": 126, "count": 126, "decode_str": "})}{"} -{"id": 45339, "token": "\u0120Taq", "merges": "\u0120Ta q", "raw_count": 126, "count": 126, "decode_str": " Taq"} -{"id": 24254, "token": "\u0120]$", "merges": "\u0120] $", "raw_count": 126, "count": 126, "decode_str": " ]$"} -{"id": 8699, "token": "}{-", "merges": "}{ -", "raw_count": 126, "count": 126, "decode_str": "}{-"} -{"id": 42612, "token": "scriptsize", "merges": "script size", "raw_count": 127, "count": 127, "decode_str": "scriptsize"} -{"id": 23997, "token": "vartheta", "merges": "vart heta", "raw_count": 127, "count": 127, "decode_str": "vartheta"} -{"id": 45354, "token": "\u0120Salem", "merges": "\u0120Sal em", "raw_count": 127, "count": 127, "decode_str": " Salem"} -{"id": 48576, "token": "\u0120Marty", "merges": "\u0120Mart y", "raw_count": 127, "count": 127, "decode_str": " Marty"} -{"id": 44509, "token": "\u0120Hond", "merges": "\u0120H ond", "raw_count": 127, "count": 127, "decode_str": " Hond"} -{"id": 33045, "token": "\u0120kommer", "merges": "\u0120kom mer", "raw_count": 128, "count": 128, "decode_str": " kommer"} -{"id": 24599, "token": "\u0120murine", "merges": "\u0120mur ine", "raw_count": 128, "count": 128, "decode_str": " murine"} -{"id": 20830, "token": "\u0120miRNAs", "merges": "\u0120mi RNAs", "raw_count": 128, "count": 128, "decode_str": " miRNAs"} -{"id": 32333, "token": "\u0120efter", "merges": "\u0120e fter", "raw_count": 128, "count": 128, "decode_str": " efter"} -{"id": 44885, "token": "\u00c3\u00a4m\u00c3\u00a4", "merges": "\u00c3\u00a4m \u00c3\u00a4", "raw_count": 128, "count": 128, "decode_str": "\u00e4m\u00e4"} -{"id": 41862, "token": "\u00e1\u00bf\u00b6", "merges": "\u00e1\u00bf \u00b6", "raw_count": 56, "count": 128, "decode_str": "\u1ff6"} -{"id": 29152, "token": "${\\", "merges": "$ {\\", "raw_count": 128, "count": 128, "decode_str": "${\\"} -{"id": 43783, "token": "\u0120Philippine", "merges": "\u0120Philipp ine", "raw_count": 129, "count": 129, "decode_str": " Philippine"} -{"id": 45932, "token": "\u0120arginine", "merges": "\u0120arg inine", "raw_count": 129, "count": 129, "decode_str": " arginine"} -{"id": 38284, "token": "\u0120assayed", "merges": "\u0120assay ed", "raw_count": 129, "count": 129, "decode_str": " assayed"} -{"id": 48477, "token": "\u0120Baltic", "merges": "\u0120Balt ic", "raw_count": 129, "count": 129, "decode_str": " Baltic"} -{"id": 22404, "token": "\u0120Putin", "merges": "\u0120Put in", "raw_count": 129, "count": 129, "decode_str": " Putin"} -{"id": 29414, "token": "\u0120Jos\u00c3\u00a9", "merges": "\u0120Jos \u00c3\u00a9", "raw_count": 129, "count": 129, "decode_str": " Jos\u00e9"} -{"id": 47946, "token": "\u00cf\u0128\u00ce\u00bf", "merges": "\u00cf\u0128 \u00ce\u00bf", "raw_count": 129, "count": 129, "decode_str": "\u03c6\u03bf"} -{"id": 54597, "token": "\u00ef\u00bd\u00a4", "merges": "\u00ef\u00bd \u00a4", "raw_count": 129, "count": 129, "decode_str": "\uff64"} -{"id": 33975, "token": "\u0120Ultimately", "merges": "\u0120Ult imately", "raw_count": 130, "count": 130, "decode_str": " Ultimately"} -{"id": 23294, "token": "\u0120Alzheimer", "merges": "\u0120Al zheimer", "raw_count": 130, "count": 130, "decode_str": " Alzheimer"} -{"id": 41460, "token": "\u0120Istanbul", "merges": "\u0120I stanbul", "raw_count": 130, "count": 130, "decode_str": " Istanbul"} -{"id": 33072, "token": "\u0120Exhibit", "merges": "\u0120Ex hibit", "raw_count": 130, "count": 130, "decode_str": " Exhibit"} -{"id": 34913, "token": "\u0120Marines", "merges": "\u0120Mar ines", "raw_count": 130, "count": 130, "decode_str": " Marines"} -{"id": 37790, "token": "\u0120Rugby", "merges": "\u0120Rug by", "raw_count": 130, "count": 130, "decode_str": " Rugby"} -{"id": 48335, "token": "\u0120avons", "merges": "\u0120av ons", "raw_count": 130, "count": 130, "decode_str": " avons"} -{"id": 27650, "token": "\u0120\u00c5\u00bee", "merges": "\u0120\u00c5\u00be e", "raw_count": 130, "count": 130, "decode_str": " \u017ee"} -{"id": 43913, "token": "eqno", "merges": "eq no", "raw_count": 130, "count": 130, "decode_str": "eqno"} -{"id": 47200, "token": "\u0120oligonucleotides", "merges": "\u0120oligonucle otides", "raw_count": 131, "count": 131, "decode_str": " oligonucleotides"} -{"id": 41749, "token": "\u0120Supplemental", "merges": "\u0120Supp lemental", "raw_count": 131, "count": 131, "decode_str": " Supplemental"} -{"id": 42669, "token": "\u0120Springfield", "merges": "\u0120Spring field", "raw_count": 131, "count": 131, "decode_str": " Springfield"} -{"id": 37772, "token": "\u0120moiety", "merges": "\u0120moi ety", "raw_count": 131, "count": 131, "decode_str": " moiety"} -{"id": 29161, "token": "\u0120Stalin", "merges": "\u0120St alin", "raw_count": 131, "count": 131, "decode_str": " Stalin"} -{"id": 46625, "token": "\u0120Debor", "merges": "\u0120De bor", "raw_count": 11, "count": 131, "decode_str": " Debor"} -{"id": 12159, "token": "]{}\\", "merges": "]{ }\\", "raw_count": 131, "count": 131, "decode_str": "]{}\\"} -{"id": 28555, "token": "\u00e1\u00bd\u00b6", "merges": "\u00e1\u00bd \u00b6", "raw_count": 46, "count": 131, "decode_str": "\u1f76"} -{"id": 42916, "token": "\u00e0\u00b1\u012f", "merges": "\u00e0\u00b1 \u012f", "raw_count": 131, "count": 131, "decode_str": "\u0c4d"} -{"id": 24625, "token": "\u00c2\u0141", "merges": "\u00c2 \u0141", "raw_count": 131, "count": 131, "decode_str": "\u009f"} -{"id": 40867, "token": "\u0120ribosomal", "merges": "\u0120rib osomal", "raw_count": 132, "count": 132, "decode_str": " ribosomal"} -{"id": 50112, "token": "\u0120Gonzales", "merges": "\u0120Gonz ales", "raw_count": 132, "count": 132, "decode_str": " Gonzales"} -{"id": 49632, "token": "\u0120formalin", "merges": "\u0120formal in", "raw_count": 132, "count": 132, "decode_str": " formalin"} -{"id": 38027, "token": "\u0120Prosec", "merges": "\u0120Pro sec", "raw_count": 132, "count": 132, "decode_str": " Prosec"} -{"id": 45867, "token": "\u0120Megan", "merges": "\u0120Meg an", "raw_count": 132, "count": 132, "decode_str": " Megan"} -{"id": 39924, "token": "\u0120Tanz", "merges": "\u0120T anz", "raw_count": 78, "count": 132, "decode_str": " Tanz"} -{"id": 50203, "token": "\u0120Cys", "merges": "\u0120C ys", "raw_count": 132, "count": 132, "decode_str": " Cys"} -{"id": 4700, "token": ".$$", "merges": ". $$", "raw_count": 127, "count": 132, "decode_str": ".$$"} -{"id": 42479, "token": "\u00e1\u00bd\u00b8", "merges": "\u00e1\u00bd \u00b8", "raw_count": 132, "count": 132, "decode_str": "\u1f78"} -{"id": 32483, "token": "\u0120Increased", "merges": "\u0120Incre ased", "raw_count": 133, "count": 133, "decode_str": " Increased"} -{"id": 49048, "token": "\u0120Addiction", "merges": "\u0120Add iction", "raw_count": 133, "count": 133, "decode_str": " Addiction"} -{"id": 20736, "token": "\u0120Democrat", "merges": "\u0120Democr at", "raw_count": 133, "count": 133, "decode_str": " Democrat"} -{"id": 32533, "token": "\u0120Ninth", "merges": "\u0120N inth", "raw_count": 133, "count": 133, "decode_str": " Ninth"} -{"id": 41304, "token": "\u0120\u00c3\u00a5r", "merges": "\u0120\u00c3\u00a5 r", "raw_count": 133, "count": 133, "decode_str": " \u00e5r"} -{"id": 44687, "token": "\u00cf\u0122\u00ce\u00b5", "merges": "\u00cf\u0122 \u00ce\u00b5", "raw_count": 133, "count": 133, "decode_str": "\u03c0\u03b5"} -{"id": 14101, "token": ",\\,", "merges": ",\\ ,", "raw_count": 133, "count": 133, "decode_str": ",\\,"} -{"id": 192, "token": "\u010f", "merges": "NULL", "raw_count": 131, "count": 133, "decode_str": "\u000f"} -{"id": 34763, "token": "\u0120myeloid", "merges": "\u0120myel oid", "raw_count": 134, "count": 134, "decode_str": " myeloid"} -{"id": 26315, "token": "\u0120Bangl", "merges": "\u0120Bang l", "raw_count": 18, "count": 134, "decode_str": " Bangl"} -{"id": 42135, "token": "\u0120Vince", "merges": "\u0120V ince", "raw_count": 134, "count": 134, "decode_str": " Vince"} -{"id": 49008, "token": "\u0120Palin", "merges": "\u0120Pal in", "raw_count": 134, "count": 134, "decode_str": " Palin"} -{"id": 25614, "token": "\u0120avait", "merges": "\u0120av ait", "raw_count": 134, "count": 134, "decode_str": " avait"} -{"id": 40171, "token": "\u0120\u00e1\u00bc\u0122", "merges": "\u0120\u00e1\u00bc \u0122", "raw_count": 134, "count": 134, "decode_str": " \u1f00"} -{"id": 24142, "token": "\u0120\u00c2\u00bd", "merges": "\u0120\u00c2 \u00bd", "raw_count": 134, "count": 134, "decode_str": " \u00bd"} -{"id": 26723, "token": "^+$", "merges": "^+ $", "raw_count": 134, "count": 134, "decode_str": "^+$"} -{"id": 52472, "token": "\u00e6\u00b1\u0130", "merges": "\u00e6\u00b1 \u0130", "raw_count": 134, "count": 134, "decode_str": "\u6c4e"} -{"id": 50286, "token": "\u00cb\u012f", "merges": "\u00cb \u012f", "raw_count": 134, "count": 134, "decode_str": "\u02cd"} -{"id": 20973, "token": "\u0120Connecticut", "merges": "\u0120Conne cticut", "raw_count": 135, "count": 135, "decode_str": " Connecticut"} -{"id": 27330, "token": "\u0120cytotoxic", "merges": "\u0120cytotox ic", "raw_count": 135, "count": 135, "decode_str": " cytotoxic"} -{"id": 35843, "token": "\u0120Battalion", "merges": "\u0120Batt alion", "raw_count": 135, "count": 135, "decode_str": " Battalion"} -{"id": 32216, "token": "\u0120Secondly", "merges": "\u0120Second ly", "raw_count": 135, "count": 135, "decode_str": " Secondly"} -{"id": 47475, "token": "\u0120hydrogel", "merges": "\u0120hydro gel", "raw_count": 135, "count": 135, "decode_str": " hydrogel"} -{"id": 49185, "token": "\u0120Arabian", "merges": "\u0120Arab ian", "raw_count": 135, "count": 135, "decode_str": " Arabian"} -{"id": 41994, "token": "\u0120Raiders", "merges": "\u0120Ra iders", "raw_count": 135, "count": 135, "decode_str": " Raiders"} -{"id": 50226, "token": "\u0120andra", "merges": "\u0120and ra", "raw_count": 135, "count": 135, "decode_str": " andra"} -{"id": 48622, "token": "Kilos", "merges": "K ilos", "raw_count": 135, "count": 135, "decode_str": "Kilos"} -{"id": 43994, "token": "\u00ce\u00bb\u00ce\u00b1", "merges": "\u00ce\u00bb \u00ce\u00b1", "raw_count": 135, "count": 135, "decode_str": "\u03bb\u03b1"} -{"id": 26568, "token": "_{-\\", "merges": "_{ -\\", "raw_count": 135, "count": 135, "decode_str": "_{-\\"} -{"id": 48586, "token": "\u0120Nottingham", "merges": "\u0120Not tingham", "raw_count": 136, "count": 136, "decode_str": " Nottingham"} -{"id": 43113, "token": "\u0120Indonesian", "merges": "\u0120Indones ian", "raw_count": 136, "count": 136, "decode_str": " Indonesian"} -{"id": 32665, "token": "\u0120Judicial", "merges": "\u0120Jud icial", "raw_count": 136, "count": 136, "decode_str": " Judicial"} -{"id": 21461, "token": "\u0120Clearly", "merges": "\u0120Cle arly", "raw_count": 136, "count": 136, "decode_str": " Clearly"} -{"id": 38442, "token": "\u0120hade", "merges": "\u0120had e", "raw_count": 136, "count": 136, "decode_str": " hade"} -{"id": 46858, "token": "biamo", "merges": "bi amo", "raw_count": 136, "count": 136, "decode_str": "biamo"} -{"id": 35613, "token": "\u0120/*!", "merges": "\u0120/* !", "raw_count": 129, "count": 136, "decode_str": " /*!"} -{"id": 39586, "token": "}{~", "merges": "}{ ~", "raw_count": 136, "count": 136, "decode_str": "}{~"} -{"id": 34996, "token": "\u0120\u00e1\u00bd", "merges": "\u0120 \u00e1\u00bd", "raw_count": 136, "count": 136, "decode_str": " \ufffd"} -{"id": 52354, "token": "\u00e6\u00a7\u0135", "merges": "\u00e6\u00a7 \u0135", "raw_count": 136, "count": 136, "decode_str": "\u69d3"} -{"id": 9589, "token": "\u00c2\u0122", "merges": "\u00c2 \u0122", "raw_count": 135, "count": 136, "decode_str": "\u0080"} -{"id": 46383, "token": "\u0120oligonucleotide", "merges": "\u0120oligonucle otide", "raw_count": 137, "count": 137, "decode_str": " oligonucleotide"} -{"id": 40358, "token": "\u0120Bonferroni", "merges": "\u0120Bon ferroni", "raw_count": 137, "count": 137, "decode_str": " Bonferroni"} -{"id": 46058, "token": "\u0120econ\u00c3\u00b3", "merges": "\u0120econ \u00c3\u00b3", "raw_count": 137, "count": 137, "decode_str": " econ\u00f3"} -{"id": 31904, "token": "\u0120\\*\\*\\*", "merges": "\u0120\\* \\*\\*", "raw_count": 137, "count": 137, "decode_str": " \\*\\*\\*"} -{"id": 33649, "token": "\u0120PTSD", "merges": "\u0120PT SD", "raw_count": 137, "count": 137, "decode_str": " PTSD"} -{"id": 9722, "token": "\u0120$(\\", "merges": "\u0120$ (\\", "raw_count": 137, "count": 137, "decode_str": " $(\\"} -{"id": 50664, "token": "\u00e5\u0125\u012f", "merges": "\u00e5\u0125 \u012f", "raw_count": 137, "count": 137, "decode_str": "\u50cd"} -{"id": 50324, "token": "\u00e2\u012a\u00ae", "merges": "\u00e2\u012a \u00ae", "raw_count": 137, "count": 137, "decode_str": "\u222e"} -{"id": 189, "token": "\u010c", "merges": "NULL", "raw_count": 137, "count": 137, "decode_str": "\f"} -{"id": 47502, "token": "\u0120pharmacokinetic", "merges": "\u0120pharmac okinetic", "raw_count": 138, "count": 138, "decode_str": " pharmacokinetic"} -{"id": 49251, "token": "\u0120Rehabilitation", "merges": "\u0120Re habilitation", "raw_count": 138, "count": 138, "decode_str": " Rehabilitation"} -{"id": 35435, "token": "\u0120constexpr", "merges": "\u0120const expr", "raw_count": 138, "count": 138, "decode_str": " constexpr"} -{"id": 33154, "token": "\u0120pol\u00c3\u0143tica", "merges": "\u0120pol\u00c3\u0143 tica", "raw_count": 138, "count": 138, "decode_str": " pol\u00edtica"} -{"id": 25187, "token": "Defendant", "merges": "Def endant", "raw_count": 138, "count": 138, "decode_str": "Defendant"} -{"id": 17360, "token": "\u0120Oklahoma", "merges": "\u0120O klahoma", "raw_count": 138, "count": 138, "decode_str": " Oklahoma"} -{"id": 37976, "token": "\u0120Theresa", "merges": "\u0120The resa", "raw_count": 138, "count": 138, "decode_str": " Theresa"} -{"id": 33199, "token": "\u0120Memphis", "merges": "\u0120Mem phis", "raw_count": 138, "count": 138, "decode_str": " Memphis"} -{"id": 43265, "token": "jsfiddle", "merges": "js fiddle", "raw_count": 138, "count": 138, "decode_str": "jsfiddle"} -{"id": 34262, "token": "\u0120Romania", "merges": "\u0120Roman ia", "raw_count": 138, "count": 138, "decode_str": " Romania"} -{"id": 41876, "token": "\u0120titers", "merges": "\u0120tit ers", "raw_count": 138, "count": 138, "decode_str": " titers"} -{"id": 45428, "token": "\u0120Booker", "merges": "\u0120Book er", "raw_count": 138, "count": 138, "decode_str": " Booker"} -{"id": 30935, "token": "\u00cf\u0127\u00cf\u0126", "merges": "\u00cf\u0127 \u00cf\u0126", "raw_count": 87, "count": 138, "decode_str": "\u03c5\u03c4"} -{"id": 34957, "token": "\u0120COX", "merges": "\u0120CO X", "raw_count": 138, "count": 138, "decode_str": " COX"} -{"id": 33411, "token": "\u0120Vatican", "merges": "\u0120V atican", "raw_count": 139, "count": 139, "decode_str": " Vatican"} -{"id": 21219, "token": "\u0120Nazi", "merges": "\u0120Naz i", "raw_count": 139, "count": 139, "decode_str": " Nazi"} -{"id": 50377, "token": "\u00e2\u0139\u00a2", "merges": "\u00e2\u0139 \u00a2", "raw_count": 139, "count": 139, "decode_str": "\u25e2"} -{"id": 25465, "token": "\u0120apoptotic", "merges": "\u0120apopt otic", "raw_count": 140, "count": 140, "decode_str": " apoptotic"} -{"id": 45999, "token": "\u0120Sundays", "merges": "\u0120Sund ays", "raw_count": 140, "count": 140, "decode_str": " Sundays"} -{"id": 43137, "token": "\u0120Voor", "merges": "\u0120V oor", "raw_count": 140, "count": 140, "decode_str": " Voor"} -{"id": 43766, "token": "\u00e1\u00bd\u00b2", "merges": "\u00e1\u00bd \u00b2", "raw_count": 140, "count": 140, "decode_str": "\u1f72"} -{"id": 41426, "token": "\u0120Hampton", "merges": "\u0120Ham pton", "raw_count": 141, "count": 141, "decode_str": " Hampton"} -{"id": 46907, "token": "\u0120Kimber", "merges": "\u0120Kim ber", "raw_count": 141, "count": 141, "decode_str": " Kimber"} -{"id": 46390, "token": "\u0120Rubio", "merges": "\u0120Rub io", "raw_count": 141, "count": 141, "decode_str": " Rubio"} -{"id": 27078, "token": "\u0120Aunt", "merges": "\u0120A unt", "raw_count": 141, "count": 141, "decode_str": " Aunt"} -{"id": 29753, "token": "rvert", "merges": "r vert", "raw_count": 141, "count": 141, "decode_str": "rvert"} -{"id": 36589, "token": "\u0120Yug", "merges": "\u0120Y ug", "raw_count": 88, "count": 141, "decode_str": " Yug"} -{"id": 42257, "token": "\u00c4\u0123s", "merges": "\u00c4\u0123 s", "raw_count": 141, "count": 141, "decode_str": "\u0101s"} -{"id": 23471, "token": "\u0120knockdown", "merges": "\u0120knock down", "raw_count": 142, "count": 142, "decode_str": " knockdown"} -{"id": 46827, "token": "\u0120Downtown", "merges": "\u0120Down town", "raw_count": 142, "count": 142, "decode_str": " Downtown"} -{"id": 41521, "token": "\u0120kunnen", "merges": "\u0120kunn en", "raw_count": 142, "count": 142, "decode_str": " kunnen"} -{"id": 44465, "token": "\u0120Deaf", "merges": "\u0120De af", "raw_count": 142, "count": 142, "decode_str": " Deaf"} -{"id": 36880, "token": "\u0120RNAi", "merges": "\u0120RNA i", "raw_count": 142, "count": 142, "decode_str": " RNAi"} -{"id": 46424, "token": "\u0120Seah", "merges": "\u0120Se ah", "raw_count": 142, "count": 142, "decode_str": " Seah"} -{"id": 22479, "token": "\u0120LORD", "merges": "\u0120L ORD", "raw_count": 142, "count": 142, "decode_str": " LORD"} -{"id": 47715, "token": "|}\\", "merges": "| }\\", "raw_count": 142, "count": 142, "decode_str": "|}\\"} -{"id": 41137, "token": "*~,", "merges": "*~ ,", "raw_count": 142, "count": 142, "decode_str": "*~,"} -{"id": 6250, "token": "\u00e2\u0122\u012c", "merges": "\u00e2\u0122 \u012c", "raw_count": 142, "count": 142, "decode_str": "\u200a"} -{"id": 36472, "token": "\u0120hepatocytes", "merges": "\u0120hepat ocytes", "raw_count": 143, "count": 143, "decode_str": " hepatocytes"} -{"id": 31573, "token": "\u0120Protestant", "merges": "\u0120Protest ant", "raw_count": 143, "count": 143, "decode_str": " Protestant"} -{"id": 38394, "token": "\u0120Homeland", "merges": "\u0120Hom eland", "raw_count": 143, "count": 143, "decode_str": " Homeland"} -{"id": 35099, "token": "\u0120Eleanor", "merges": "\u0120Ele anor", "raw_count": 143, "count": 143, "decode_str": " Eleanor"} -{"id": 40158, "token": "\u0120\u00d1\u0123\u00d1\u012c", "merges": "\u0120\u00d1\u0123 \u00d1\u012c", "raw_count": 143, "count": 143, "decode_str": " \u0441\u044a"} -{"id": 38150, "token": "\u0120Stephanie", "merges": "\u0120Stephan ie", "raw_count": 144, "count": 144, "decode_str": " Stephanie"} -{"id": 49094, "token": "\u0120Breit", "merges": "\u0120Bre it", "raw_count": 144, "count": 144, "decode_str": " Breit"} -{"id": 33133, "token": "\u0120Mice", "merges": "\u0120M ice", "raw_count": 144, "count": 144, "decode_str": " Mice"} -{"id": 46604, "token": "\u0120Erin", "merges": "\u0120Er in", "raw_count": 144, "count": 144, "decode_str": " Erin"} -{"id": 48720, "token": "\u0120daar", "merges": "\u0120da ar", "raw_count": 144, "count": 144, "decode_str": " daar"} -{"id": 31016, "token": "\u0120\u00c3\u00ac", "merges": "\u0120\u00c3 \u00ac", "raw_count": 144, "count": 144, "decode_str": " \u00ec"} -{"id": 10022, "token": "\u0120Accordingly", "merges": "\u0120According ly", "raw_count": 145, "count": 145, "decode_str": " Accordingly"} -{"id": 48107, "token": "\u0120follicular", "merges": "\u0120follic ular", "raw_count": 145, "count": 145, "decode_str": " follicular"} -{"id": 44664, "token": "\u0120surjective", "merges": "\u0120sur jective", "raw_count": 145, "count": 145, "decode_str": " surjective"} -{"id": 21744, "token": "\u0120mammalian", "merges": "\u0120mamm alian", "raw_count": 145, "count": 145, "decode_str": " mammalian"} -{"id": 49542, "token": "\u0120Duchess", "merges": "\u0120Duc hess", "raw_count": 145, "count": 145, "decode_str": " Duchess"} -{"id": 41834, "token": "\u0120Hawks", "merges": "\u0120Haw ks", "raw_count": 145, "count": 145, "decode_str": " Hawks"} -{"id": 41654, "token": "\u0120Rosie", "merges": "\u0120Ros ie", "raw_count": 145, "count": 145, "decode_str": " Rosie"} -{"id": 43308, "token": "\u0120Aside", "merges": "\u0120As ide", "raw_count": 145, "count": 145, "decode_str": " Aside"} -{"id": 48058, "token": "\u00e0\u00b1\u0123", "merges": "\u00e0\u00b1 \u0123", "raw_count": 145, "count": 145, "decode_str": "\u0c41"} -{"id": 39880, "token": "\u0120homosexuality", "merges": "\u0120hom osexuality", "raw_count": 146, "count": 146, "decode_str": " homosexuality"} -{"id": 39689, "token": "\u0120Brotherhood", "merges": "\u0120Brother hood", "raw_count": 146, "count": 146, "decode_str": " Brotherhood"} -{"id": 40874, "token": "\u0120Interstate", "merges": "\u0120Inter state", "raw_count": 146, "count": 146, "decode_str": " Interstate"} -{"id": 30158, "token": "\u0120microbiota", "merges": "\u0120microbi ota", "raw_count": 146, "count": 146, "decode_str": " microbiota"} -{"id": 28681, "token": "\u0120Whereas", "merges": "\u0120Where as", "raw_count": 146, "count": 146, "decode_str": " Whereas"} -{"id": 40103, "token": "\u0120Dorothy", "merges": "\u0120Dor othy", "raw_count": 146, "count": 146, "decode_str": " Dorothy"} -{"id": 24073, "token": "\u0120\u00cf\u0126\u00ce\u00b7\u00cf\u0124", "merges": "\u0120\u00cf\u0126\u00ce\u00b7 \u00cf\u0124", "raw_count": 146, "count": 146, "decode_str": " \u03c4\u03b7\u03c2"} -{"id": 37801, "token": "\u0120Armen", "merges": "\u0120Arm en", "raw_count": 53, "count": 146, "decode_str": " Armen"} -{"id": 32546, "token": "\u0120interleukin", "merges": "\u0120interle ukin", "raw_count": 147, "count": 147, "decode_str": " interleukin"} -{"id": 43327, "token": "\u0120Methodist", "merges": "\u0120Method ist", "raw_count": 147, "count": 147, "decode_str": " Methodist"} -{"id": 54600, "token": "\u00ef\u00bd\u00b0", "merges": "\u00ef\u00bd \u00b0", "raw_count": 147, "count": 147, "decode_str": "\uff70"} -{"id": 41887, "token": "\u0120Embassy", "merges": "\u0120Emb assy", "raw_count": 148, "count": 148, "decode_str": " Embassy"} -{"id": 43320, "token": "\u0120porcine", "merges": "\u0120por cine", "raw_count": 148, "count": 148, "decode_str": " porcine"} -{"id": 40764, "token": "\u0120Conse", "merges": "\u0120Con se", "raw_count": 148, "count": 148, "decode_str": " Conse"} -{"id": 31719, "token": "\u0120RNAs", "merges": "\u0120RNA s", "raw_count": 148, "count": 148, "decode_str": " RNAs"} -{"id": 48990, "token": "\u0120Leah", "merges": "\u0120Le ah", "raw_count": 148, "count": 148, "decode_str": " Leah"} -{"id": 50303, "token": "\u00e2\u0123\u00ba", "merges": "\u00e2\u0123 \u00ba", "raw_count": 148, "count": 148, "decode_str": "\u207a"} -{"id": 40497, "token": "\u0120hydrophilic", "merges": "\u0120hydroph ilic", "raw_count": 149, "count": 149, "decode_str": " hydrophilic"} -{"id": 42573, "token": "\u0120leukocyte", "merges": "\u0120leuk ocyte", "raw_count": 149, "count": 149, "decode_str": " leukocyte"} -{"id": 48244, "token": "\u0120Somerset", "merges": "\u0120Somers et", "raw_count": 149, "count": 149, "decode_str": " Somerset"} -{"id": 45188, "token": "\u0120h\u00c3\u00a4r", "merges": "\u0120h \u00c3\u00a4r", "raw_count": 149, "count": 149, "decode_str": " h\u00e4r"} -{"id": 48291, "token": "\u0120PGE", "merges": "\u0120P GE", "raw_count": 149, "count": 149, "decode_str": " PGE"} -{"id": 21304, "token": "\u00c2\u0142\u010a", "merges": "\u00c2\u0142 \u010a", "raw_count": 149, "count": 149, "decode_str": "\u00a0\n"} -{"id": 49667, "token": "\u0120atherosclerotic", "merges": "\u0120atheros clerotic", "raw_count": 150, "count": 150, "decode_str": " atherosclerotic"} -{"id": 44377, "token": "\u0120glycoprotein", "merges": "\u0120glyc oprotein", "raw_count": 150, "count": 150, "decode_str": " glycoprotein"} -{"id": 46599, "token": "\u0120Chrysler", "merges": "\u0120Chrys ler", "raw_count": 150, "count": 150, "decode_str": " Chrysler"} -{"id": 33016, "token": "\u0120Corb", "merges": "\u0120Cor b", "raw_count": 132, "count": 150, "decode_str": " Corb"} -{"id": 43762, "token": "\u00d9\u0128\u00d8\u00a7", "merges": "\u00d9\u0128 \u00d8\u00a7", "raw_count": 150, "count": 150, "decode_str": "\u0646\u0627"} -{"id": 44586, "token": "\u00cf\u0125\u00ce\u00b9", "merges": "\u00cf\u0125 \u00ce\u00b9", "raw_count": 150, "count": 150, "decode_str": "\u03c3\u03b9"} -{"id": 44428, "token": "\u0120&$", "merges": "\u0120& $", "raw_count": 150, "count": 150, "decode_str": " &$"} -{"id": 47355, "token": "\u0120carcinogenesis", "merges": "\u0120carcin ogenesis", "raw_count": 151, "count": 151, "decode_str": " carcinogenesis"} -{"id": 47154, "token": "\u0120Byzantine", "merges": "\u0120Byz antine", "raw_count": 151, "count": 151, "decode_str": " Byzantine"} -{"id": 41726, "token": "\u0120liposomes", "merges": "\u0120lip osomes", "raw_count": 151, "count": 151, "decode_str": " liposomes"} -{"id": 46439, "token": "\u0120nucleon", "merges": "\u0120nucle on", "raw_count": 151, "count": 151, "decode_str": " nucleon"} -{"id": 40772, "token": "\u0120Strick", "merges": "\u0120St rick", "raw_count": 61, "count": 151, "decode_str": " Strick"} -{"id": 38916, "token": "\u0120Willie", "merges": "\u0120Will ie", "raw_count": 151, "count": 151, "decode_str": " Willie"} -{"id": 45907, "token": "\u0120Rapids", "merges": "\u0120Rap ids", "raw_count": 151, "count": 151, "decode_str": " Rapids"} -{"id": 40525, "token": "\u0120mtDNA", "merges": "\u0120mt DNA", "raw_count": 151, "count": 151, "decode_str": " mtDNA"} -{"id": 48545, "token": "\u0120Cody", "merges": "\u0120C ody", "raw_count": 151, "count": 151, "decode_str": " Cody"} -{"id": 41670, "token": "\u0120Jury", "merges": "\u0120J ury", "raw_count": 151, "count": 151, "decode_str": " Jury"} -{"id": 45489, "token": "\u0120GSK", "merges": "\u0120G SK", "raw_count": 151, "count": 151, "decode_str": " GSK"} -{"id": 37097, "token": "\u00cf\u0123\u00ce\u00b5", "merges": "\u00cf\u0123 \u00ce\u00b5", "raw_count": 151, "count": 151, "decode_str": "\u03c1\u03b5"} -{"id": 53115, "token": "\u00e7\u00a5\u0137", "merges": "\u00e7\u00a5 \u0137", "raw_count": 151, "count": 151, "decode_str": "\u7955"} -{"id": 44632, "token": "\u0120heterocy", "merges": "\u0120heter ocy", "raw_count": 152, "count": 152, "decode_str": " heterocy"} -{"id": 35743, "token": "\u0120Rhode", "merges": "\u0120Rh ode", "raw_count": 152, "count": 152, "decode_str": " Rhode"} -{"id": 42782, "token": "\u0120glial", "merges": "\u0120gl ial", "raw_count": 152, "count": 152, "decode_str": " glial"} -{"id": 50138, "token": "\u0120gonad", "merges": "\u0120gon ad", "raw_count": 152, "count": 152, "decode_str": " gonad"} -{"id": 34749, "token": "\u0120\u00e0\u00b0", "merges": "\u0120 \u00e0\u00b0", "raw_count": 152, "count": 152, "decode_str": " \ufffd"} -{"id": 22389, "token": "\u0120Lieutenant", "merges": "\u0120Lie utenant", "raw_count": 153, "count": 153, "decode_str": " Lieutenant"} -{"id": 33206, "token": "\u0120WHETHER", "merges": "\u0120WHE THER", "raw_count": 153, "count": 153, "decode_str": " WHETHER"} -{"id": 37083, "token": "\u0120Heather", "merges": "\u0120He ather", "raw_count": 153, "count": 153, "decode_str": " Heather"} -{"id": 47385, "token": "\u0120Elaine", "merges": "\u0120El aine", "raw_count": 153, "count": 153, "decode_str": " Elaine"} -{"id": 47329, "token": "\u0120Finals", "merges": "\u0120Fin als", "raw_count": 153, "count": 153, "decode_str": " Finals"} -{"id": 43427, "token": "\u0120endothelium", "merges": "\u0120end othelium", "raw_count": 154, "count": 154, "decode_str": " endothelium"} -{"id": 41661, "token": "\u0120hypothesize", "merges": "\u0120hypothes ize", "raw_count": 154, "count": 154, "decode_str": " hypothesize"} -{"id": 49224, "token": "\u0120Weinstein", "merges": "\u0120We instein", "raw_count": 154, "count": 154, "decode_str": " Weinstein"} -{"id": 35459, "token": "\u0120Newcastle", "merges": "\u0120New castle", "raw_count": 154, "count": 154, "decode_str": " Newcastle"} -{"id": 46787, "token": "\u0120striatum", "merges": "\u0120stri atum", "raw_count": 154, "count": 154, "decode_str": " striatum"} -{"id": 45711, "token": "\u0120Kathleen", "merges": "\u0120Kath leen", "raw_count": 154, "count": 154, "decode_str": " Kathleen"} -{"id": 48006, "token": "\u0120Trustees", "merges": "\u0120Trust ees", "raw_count": 154, "count": 154, "decode_str": " Trustees"} -{"id": 22538, "token": "\u0120Medicare", "merges": "\u0120Medic are", "raw_count": 154, "count": 154, "decode_str": " Medicare"} -{"id": 44669, "token": "\u0120Merkel", "merges": "\u0120Mer kel", "raw_count": 154, "count": 154, "decode_str": " Merkel"} -{"id": 30926, "token": "\u0120McCain", "merges": "\u0120McC ain", "raw_count": 154, "count": 154, "decode_str": " McCain"} -{"id": 12728, "token": "\u0120Syria", "merges": "\u0120Sy ria", "raw_count": 154, "count": 154, "decode_str": " Syria"} -{"id": 32194, "token": "\u0120assertEquals", "merges": "\u0120assert Equals", "raw_count": 155, "count": 155, "decode_str": " assertEquals"} -{"id": 40996, "token": "\u0120Northeast", "merges": "\u0120Nort heast", "raw_count": 155, "count": 155, "decode_str": " Northeast"} -{"id": 48531, "token": "\u0120\u00d8\u00a7\u00d9\u0126\u00d8\u00a3", "merges": "\u0120\u00d8\u00a7\u00d9\u0126\u00d8 \u00a3", "raw_count": 155, "count": 155, "decode_str": " \u0627\u0644\u0623"} -{"id": 46617, "token": "\u0120efflux", "merges": "\u0120eff lux", "raw_count": 155, "count": 155, "decode_str": " efflux"} -{"id": 36452, "token": "\u0120Greeks", "merges": "\u0120Gree ks", "raw_count": 155, "count": 155, "decode_str": " Greeks"} -{"id": 45274, "token": "\u0120Carrie", "merges": "\u0120Car rie", "raw_count": 155, "count": 155, "decode_str": " Carrie"} -{"id": 34861, "token": "\u0120Tamil", "merges": "\u0120Tam il", "raw_count": 155, "count": 155, "decode_str": " Tamil"} -{"id": 49878, "token": "\u0120Sears", "merges": "\u0120S ears", "raw_count": 155, "count": 155, "decode_str": " Sears"} -{"id": 26284, "token": "}}+", "merges": "}} +", "raw_count": 155, "count": 155, "decode_str": "}}+"} -{"id": 41600, "token": "\u0120angiotensin", "merges": "\u0120ang iotensin", "raw_count": 156, "count": 156, "decode_str": " angiotensin"} -{"id": 18370, "token": "\u0120Kentucky", "merges": "\u0120Kent ucky", "raw_count": 156, "count": 156, "decode_str": " Kentucky"} -{"id": 42748, "token": "\u0120Contrary", "merges": "\u0120Cont rary", "raw_count": 156, "count": 156, "decode_str": " Contrary"} -{"id": 46024, "token": "\u0120colonic", "merges": "\u0120col onic", "raw_count": 156, "count": 156, "decode_str": " colonic"} -{"id": 41118, "token": "\u0120Corinth", "merges": "\u0120Cor inth", "raw_count": 156, "count": 156, "decode_str": " Corinth"} -{"id": 47959, "token": "\u0120Thames", "merges": "\u0120Th ames", "raw_count": 156, "count": 156, "decode_str": " Thames"} -{"id": 52870, "token": "\u00e7\u0136\u00a6", "merges": "\u00e7\u0136 \u00a6", "raw_count": 156, "count": 156, "decode_str": "\u7526"} -{"id": 50086, "token": "\u0120Budapest", "merges": "\u0120Bud apest", "raw_count": 157, "count": 157, "decode_str": " Budapest"} -{"id": 41722, "token": "hetized", "merges": "het ized", "raw_count": 56, "count": 157, "decode_str": "hetized"} -{"id": 41577, "token": "\u0120Prague", "merges": "\u0120Pr ague", "raw_count": 157, "count": 157, "decode_str": " Prague"} -{"id": 49156, "token": "idenote", "merges": "iden ote", "raw_count": 157, "count": 157, "decode_str": "idenote"} -{"id": 21575, "token": "\u0120TLR", "merges": "\u0120T LR", "raw_count": 157, "count": 157, "decode_str": " TLR"} -{"id": 50308, "token": "\u00e2\u0124\u0126", "merges": "\u00e2\u0124 \u0126", "raw_count": 157, "count": 157, "decode_str": "\u2084"} -{"id": 1186, "token": "\u00e2\u0122\u012b", "merges": "\u00e2\u0122 \u012b", "raw_count": 157, "count": 157, "decode_str": "\u2009"} -{"id": 39130, "token": "\\},", "merges": "\\ },", "raw_count": 157, "count": 157, "decode_str": "\\},"} -{"id": 46400, "token": "\u0120prostagland", "merges": "\u0120prost agland", "raw_count": 158, "count": 158, "decode_str": " prostagland"} -{"id": 45172, "token": "\u0120Menschen", "merges": "\u0120Mens chen", "raw_count": 158, "count": 158, "decode_str": " Menschen"} -{"id": 29133, "token": "\u0120surfact", "merges": "\u0120sur fact", "raw_count": 49, "count": 158, "decode_str": " surfact"} -{"id": 20575, "token": "\u0120Colonel", "merges": "\u0120Col onel", "raw_count": 158, "count": 158, "decode_str": " Colonel"} -{"id": 33283, "token": "\u0120Gospel", "merges": "\u0120G ospel", "raw_count": 158, "count": 158, "decode_str": " Gospel"} -{"id": 49231, "token": "\u0120Shelby", "merges": "\u0120Shel by", "raw_count": 158, "count": 158, "decode_str": " Shelby"} -{"id": 44206, "token": "\u00cf\u0123\u00ce\u00b7", "merges": "\u00cf\u0123 \u00ce\u00b7", "raw_count": 158, "count": 158, "decode_str": "\u03c1\u03b7"} -{"id": 35962, "token": "\u0120microenvironment", "merges": "\u0120micro environment", "raw_count": 159, "count": 159, "decode_str": " microenvironment"} -{"id": 49105, "token": "\u0120antifungal", "merges": "\u0120antif ungal", "raw_count": 159, "count": 159, "decode_str": " antifungal"} -{"id": 40369, "token": "\u0120integrable", "merges": "\u0120integr able", "raw_count": 159, "count": 159, "decode_str": " integrable"} -{"id": 50033, "token": "\u0120Natalie", "merges": "\u0120Natal ie", "raw_count": 159, "count": 159, "decode_str": " Natalie"} -{"id": 44744, "token": "\u0120Indies", "merges": "\u0120Ind ies", "raw_count": 159, "count": 159, "decode_str": " Indies"} -{"id": 46634, "token": "\u0120Siber", "merges": "\u0120S iber", "raw_count": 159, "count": 159, "decode_str": " Siber"} -{"id": 42454, "token": "\u0120v\u00c3\u00a4l", "merges": "\u0120v \u00c3\u00a4l", "raw_count": 159, "count": 159, "decode_str": " v\u00e4l"} -{"id": 48739, "token": "\u0120Auss", "merges": "\u0120A uss", "raw_count": 159, "count": 159, "decode_str": " Auss"} -{"id": 29074, "token": "it\u00c3\u00a4", "merges": "it \u00c3\u00a4", "raw_count": 159, "count": 159, "decode_str": "it\u00e4"} -{"id": 42405, "token": "\u0120pathophysiology", "merges": "\u0120pathophys iology", "raw_count": 160, "count": 160, "decode_str": " pathophysiology"} -{"id": 30348, "token": "\u0120hippocampal", "merges": "\u0120hippocamp al", "raw_count": 160, "count": 160, "decode_str": " hippocampal"} -{"id": 34937, "token": "Throughout", "merges": "Through out", "raw_count": 160, "count": 160, "decode_str": "Throughout"} -{"id": 10158, "token": "\u0120Attorney", "merges": "\u0120Att orney", "raw_count": 160, "count": 160, "decode_str": " Attorney"} -{"id": 40003, "token": "\u0120Dayton", "merges": "\u0120Day ton", "raw_count": 160, "count": 160, "decode_str": " Dayton"} -{"id": 19897, "token": "\u0120Deputy", "merges": "\u0120Dep uty", "raw_count": 160, "count": 160, "decode_str": " Deputy"} -{"id": 48646, "token": "\u0120ADVIS", "merges": "\u0120AD VIS", "raw_count": 160, "count": 160, "decode_str": " ADVIS"} -{"id": 26820, "token": "\u0120eosin", "merges": "\u0120e osin", "raw_count": 160, "count": 160, "decode_str": " eosin"} -{"id": 37833, "token": "\u00ce\u00bf\u00cf\u0127\u00cf\u0124", "merges": "\u00ce\u00bf\u00cf\u0127 \u00cf\u0124", "raw_count": 160, "count": 160, "decode_str": "\u03bf\u03c5\u03c2"} -{"id": 24118, "token": "\u0120Eqs", "merges": "\u0120Eq s", "raw_count": 160, "count": 160, "decode_str": " Eqs"} -{"id": 45119, "token": "\u0120\u00c3\u00a9galement", "merges": "\u0120\u00c3\u00a9gal ement", "raw_count": 161, "count": 161, "decode_str": " \u00e9galement"} -{"id": 42457, "token": "\u0120Leicester", "merges": "\u0120Le icester", "raw_count": 161, "count": 161, "decode_str": " Leicester"} -{"id": 30154, "token": "\u0120Orthodox", "merges": "\u0120Orth odox", "raw_count": 161, "count": 161, "decode_str": " Orthodox"} -{"id": 18267, "token": "\u0120Atlanta", "merges": "\u0120Atl anta", "raw_count": 161, "count": 161, "decode_str": " Atlanta"} -{"id": 33279, "token": "\u0120hebben", "merges": "\u0120he bben", "raw_count": 161, "count": 161, "decode_str": " hebben"} -{"id": 26334, "token": "\u0120Hindu", "merges": "\u0120Hind u", "raw_count": 161, "count": 161, "decode_str": " Hindu"} -{"id": 43813, "token": "\u0120crore", "merges": "\u0120cro re", "raw_count": 161, "count": 161, "decode_str": " crore"} -{"id": 49266, "token": "\u0120EIGEN", "merges": "\u0120E IGEN", "raw_count": 161, "count": 161, "decode_str": " EIGEN"} -{"id": 40063, "token": "\u00ce\u00b9\u00cf\u0124", "merges": "\u00ce\u00b9 \u00cf\u0124", "raw_count": 48, "count": 161, "decode_str": "\u03b9\u03c2"} -{"id": 10493, "token": "\u0120$|", "merges": "\u0120$ |", "raw_count": 161, "count": 161, "decode_str": " $|"} -{"id": 12257, "token": "\u0120Nevertheless", "merges": "\u0120Never theless", "raw_count": 162, "count": 162, "decode_str": " Nevertheless"} -{"id": 35258, "token": "\u0120Providence", "merges": "\u0120Prov idence", "raw_count": 162, "count": 162, "decode_str": " Providence"} -{"id": 41123, "token": "aminergic", "merges": "amin ergic", "raw_count": 91, "count": 162, "decode_str": "aminergic"} -{"id": 25659, "token": "\u0120Cauc", "merges": "\u0120Ca uc", "raw_count": 131, "count": 162, "decode_str": " Cauc"} -{"id": 49711, "token": "\u0120Kush", "merges": "\u0120K ush", "raw_count": 162, "count": 162, "decode_str": " Kush"} -{"id": 31051, "token": "\u0120s\u00c3\u00a4", "merges": "\u0120s \u00c3\u00a4", "raw_count": 162, "count": 162, "decode_str": " s\u00e4"} -{"id": 36283, "token": "\u0120f\u00c3\u00a5", "merges": "\u0120f \u00c3\u00a5", "raw_count": 162, "count": 162, "decode_str": " f\u00e5"} -{"id": 39022, "token": "\u0120immunohistochemical", "merges": "\u0120immunohist ochemical", "raw_count": 163, "count": 163, "decode_str": " immunohistochemical"} -{"id": 25574, "token": "\u0120Representatives", "merges": "\u0120Represent atives", "raw_count": 163, "count": 163, "decode_str": " Representatives"} -{"id": 44154, "token": "\u0120glucocortic", "merges": "\u0120gluc ocortic", "raw_count": 163, "count": 163, "decode_str": " glucocortic"} -{"id": 16091, "token": "\u0120Tennessee", "merges": "\u0120Tenn essee", "raw_count": 163, "count": 163, "decode_str": " Tennessee"} -{"id": 42408, "token": "\u0120Beverly", "merges": "\u0120Bever ly", "raw_count": 163, "count": 163, "decode_str": " Beverly"} -{"id": 23506, "token": "\u0120caspase", "merges": "\u0120c aspase", "raw_count": 163, "count": 163, "decode_str": " caspase"} -{"id": 18718, "token": "\u0120Senator", "merges": "\u0120Sen ator", "raw_count": 163, "count": 163, "decode_str": " Senator"} -{"id": 29842, "token": "ottu", "merges": "ott u", "raw_count": 161, "count": 163, "decode_str": "ottu"} -{"id": 36535, "token": "r\u00c3\u00a5", "merges": "r \u00c3\u00a5", "raw_count": 163, "count": 163, "decode_str": "r\u00e5"} -{"id": 28118, "token": "\\][", "merges": "\\] [", "raw_count": 163, "count": 163, "decode_str": "\\]["} -{"id": 50383, "token": "\u00e2\u013b\u00ab", "merges": "\u00e2\u013b \u00ab", "raw_count": 163, "count": 163, "decode_str": "\u266b"} -{"id": 38851, "token": "\u00c8\u013di", "merges": "\u00c8\u013d i", "raw_count": 163, "count": 163, "decode_str": "\u021bi"} -{"id": 8994, "token": "\u0120\\>", "merges": "\u0120\\ >", "raw_count": 163, "count": 163, "decode_str": " \\>"} -{"id": 21828, "token": "]$,", "merges": "] $,", "raw_count": 163, "count": 163, "decode_str": "]$,"} -{"id": 32108, "token": "\u0120malignancy", "merges": "\u0120malign ancy", "raw_count": 164, "count": 164, "decode_str": " malignancy"} -{"id": 42923, "token": "\u0120Auckland", "merges": "\u0120A uckland", "raw_count": 164, "count": 164, "decode_str": " Auckland"} -{"id": 43614, "token": "\u0120Farmers", "merges": "\u0120Farm ers", "raw_count": 164, "count": 164, "decode_str": " Farmers"} -{"id": 32406, "token": "\u0120MAPK", "merges": "\u0120MAP K", "raw_count": 164, "count": 164, "decode_str": " MAPK"} -{"id": 43423, "token": "\u0120PKC", "merges": "\u0120PK C", "raw_count": 164, "count": 164, "decode_str": " PKC"} -{"id": 38118, "token": "\u0120FGF", "merges": "\u0120F GF", "raw_count": 164, "count": 164, "decode_str": " FGF"} -{"id": 38395, "token": "\u0120HbA", "merges": "\u0120Hb A", "raw_count": 164, "count": 164, "decode_str": " HbA"} -{"id": 28653, "token": "\\];", "merges": "\\] ;", "raw_count": 164, "count": 164, "decode_str": "\\];"} -{"id": 40892, "token": "\u0120Copenhagen", "merges": "\u0120C openhagen", "raw_count": 165, "count": 165, "decode_str": " Copenhagen"} -{"id": 6796, "token": "widetilde", "merges": "widet ilde", "raw_count": 165, "count": 165, "decode_str": "widetilde"} -{"id": 48922, "token": "\u0120Raleigh", "merges": "\u0120R aleigh", "raw_count": 165, "count": 165, "decode_str": " Raleigh"} -{"id": 45338, "token": "\u0120axonal", "merges": "\u0120ax onal", "raw_count": 165, "count": 165, "decode_str": " axonal"} -{"id": 39003, "token": "\u0120Mitch", "merges": "\u0120M itch", "raw_count": 165, "count": 165, "decode_str": " Mitch"} -{"id": 49177, "token": "\u0120Elvis", "merges": "\u0120El vis", "raw_count": 165, "count": 165, "decode_str": " Elvis"} -{"id": 40281, "token": "\u0120acyl", "merges": "\u0120ac yl", "raw_count": 165, "count": 165, "decode_str": " acyl"} -{"id": 42518, "token": "\u0120Rica", "merges": "\u0120R ica", "raw_count": 165, "count": 165, "decode_str": " Rica"} -{"id": 31807, "token": "')$", "merges": "' )$", "raw_count": 165, "count": 165, "decode_str": "')$"} -{"id": 30696, "token": "\u0120Regarding", "merges": "\u0120Reg arding", "raw_count": 166, "count": 166, "decode_str": " Regarding"} -{"id": 33028, "token": "leftarrow", "merges": "left arrow", "raw_count": 166, "count": 166, "decode_str": "leftarrow"} -{"id": 43905, "token": "\u0120Bulgaria", "merges": "\u0120Bulgar ia", "raw_count": 166, "count": 166, "decode_str": " Bulgaria"} -{"id": 31397, "token": "\u0120Trustee", "merges": "\u0120Trust ee", "raw_count": 166, "count": 166, "decode_str": " Trustee"} -{"id": 30449, "token": "\u0120Eagles", "merges": "\u0120E agles", "raw_count": 166, "count": 166, "decode_str": " Eagles"} -{"id": 40146, "token": "\u0120\u00cf\u0122\u00ce\u00b5", "merges": "\u0120\u00cf\u0122 \u00ce\u00b5", "raw_count": 166, "count": 166, "decode_str": " \u03c0\u03b5"} -{"id": 29007, "token": "\u0120NPs", "merges": "\u0120N Ps", "raw_count": 166, "count": 166, "decode_str": " NPs"} -{"id": 49095, "token": "\u0120EVs", "merges": "\u0120EV s", "raw_count": 166, "count": 166, "decode_str": " EVs"} -{"id": 50360, "token": "\u00e2\u0138\u012d", "merges": "\u00e2\u0138 \u012d", "raw_count": 166, "count": 166, "decode_str": "\u258b"} -{"id": 50321, "token": "\u00e2\u012a\u00a3", "merges": "\u00e2\u012a \u00a3", "raw_count": 166, "count": 166, "decode_str": "\u2223"} -{"id": 44688, "token": "findViewById", "merges": "find ViewById", "raw_count": 167, "count": 167, "decode_str": "findViewById"} -{"id": 29171, "token": "\u0120Hungary", "merges": "\u0120Hung ary", "raw_count": 167, "count": 167, "decode_str": " Hungary"} -{"id": 49929, "token": "\u0120\u00ce\u00b5\u00cf\u0122\u00ce\u00b9", "merges": "\u0120\u00ce\u00b5\u00cf\u0122 \u00ce\u00b9", "raw_count": 167, "count": 167, "decode_str": " \u03b5\u03c0\u03b9"} -{"id": 35020, "token": "\u0120Nepal", "merges": "\u0120Nep al", "raw_count": 167, "count": 167, "decode_str": " Nepal"} -{"id": 41180, "token": "\u0120superoxide", "merges": "\u0120super oxide", "raw_count": 168, "count": 168, "decode_str": " superoxide"} -{"id": 37497, "token": "\u0120Katherine", "merges": "\u0120K atherine", "raw_count": 168, "count": 168, "decode_str": " Katherine"} -{"id": 40282, "token": "\u0120Adelaide", "merges": "\u0120Ad elaide", "raw_count": 168, "count": 168, "decode_str": " Adelaide"} -{"id": 46543, "token": "\u0120blots", "merges": "\u0120bl ots", "raw_count": 168, "count": 168, "decode_str": " blots"} -{"id": 36935, "token": "\u0120Filip", "merges": "\u0120Fil ip", "raw_count": 168, "count": 168, "decode_str": " Filip"} -{"id": 49557, "token": "\u0120Ricky", "merges": "\u0120Rick y", "raw_count": 168, "count": 168, "decode_str": " Ricky"} -{"id": 49567, "token": "\u0120Peggy", "merges": "\u0120Peg gy", "raw_count": 168, "count": 168, "decode_str": " Peggy"} -{"id": 50167, "token": "\u0120Dors", "merges": "\u0120D ors", "raw_count": 168, "count": 168, "decode_str": " Dors"} -{"id": 33148, "token": "\u0120lysis", "merges": "\u0120l ysis", "raw_count": 169, "count": 169, "decode_str": " lysis"} -{"id": 49954, "token": "\u0120Sixty", "merges": "\u0120Six ty", "raw_count": 169, "count": 169, "decode_str": " Sixty"} -{"id": 39318, "token": "\u010a\u00c2\u0142\u00c2\u0142", "merges": "\u010a \u00c2\u0142\u00c2\u0142", "raw_count": 169, "count": 169, "decode_str": "\n\u00a0\u00a0"} -{"id": 49100, "token": "\u00cf\u0123\u00cf\u0130", "merges": "\u00cf\u0123 \u00cf\u0130", "raw_count": 169, "count": 169, "decode_str": "\u03c1\u03ce"} -{"id": 45728, "token": "\u0120DHS", "merges": "\u0120D HS", "raw_count": 169, "count": 169, "decode_str": " DHS"} -{"id": 43666, "token": "\u0120\u00ce\u013c", "merges": "\u0120\u00ce \u013c", "raw_count": 169, "count": 169, "decode_str": " \u039a"} -{"id": 31053, "token": "].)", "merges": "]. )", "raw_count": 169, "count": 169, "decode_str": "].)"} -{"id": 28866, "token": "\u0120Immigration", "merges": "\u0120Imm igration", "raw_count": 170, "count": 170, "decode_str": " Immigration"} -{"id": 10729, "token": "\u0120incubated", "merges": "\u0120incub ated", "raw_count": 170, "count": 170, "decode_str": " incubated"} -{"id": 44677, "token": "\u0120Cornwall", "merges": "\u0120Corn wall", "raw_count": 170, "count": 170, "decode_str": " Cornwall"} -{"id": 48882, "token": "\u0120Freddie", "merges": "\u0120Fred die", "raw_count": 170, "count": 170, "decode_str": " Freddie"} -{"id": 48838, "token": "\u0120Epidem", "merges": "\u0120Epid em", "raw_count": 170, "count": 170, "decode_str": " Epidem"} -{"id": 35251, "token": "\u0120Boeing", "merges": "\u0120Bo eing", "raw_count": 170, "count": 170, "decode_str": " Boeing"} -{"id": 31642, "token": "\u0120Lanka", "merges": "\u0120L anka", "raw_count": 170, "count": 170, "decode_str": " Lanka"} -{"id": 23199, "token": "\u0120VEGF", "merges": "\u0120VE GF", "raw_count": 170, "count": 170, "decode_str": " VEGF"} -{"id": 35493, "token": "aient", "merges": "a ient", "raw_count": 170, "count": 170, "decode_str": "aient"} -{"id": 44027, "token": "\u0120microbiome", "merges": "\u0120microbi ome", "raw_count": 171, "count": 171, "decode_str": " microbiome"} -{"id": 31402, "token": "\u0120virulence", "merges": "\u0120vir ulence", "raw_count": 171, "count": 171, "decode_str": " virulence"} -{"id": 46665, "token": "\u0120Ethical", "merges": "\u0120Eth ical", "raw_count": 171, "count": 171, "decode_str": " Ethical"} -{"id": 46249, "token": "\u0120v\u00c3\u00a6re", "merges": "\u0120v\u00c3\u00a6 re", "raw_count": 171, "count": 171, "decode_str": " v\u00e6re"} -{"id": 48038, "token": "\u0120Cory", "merges": "\u0120C ory", "raw_count": 171, "count": 171, "decode_str": " Cory"} -{"id": 47568, "token": "\u0120\u00e0\u00b2", "merges": "\u0120 \u00e0\u00b2", "raw_count": 171, "count": 171, "decode_str": " \ufffd"} -{"id": 30536, "token": "Rightarrow", "merges": "Right arrow", "raw_count": 172, "count": 172, "decode_str": "Rightarrow"} -{"id": 36480, "token": "\u0120Superman", "merges": "\u0120Super man", "raw_count": 172, "count": 172, "decode_str": " Superman"} -{"id": 45500, "token": "\u0120Acting", "merges": "\u0120Act ing", "raw_count": 172, "count": 172, "decode_str": " Acting"} -{"id": 50168, "token": "\u0120Slav", "merges": "\u0120Sl av", "raw_count": 172, "count": 172, "decode_str": " Slav"} -{"id": 40647, "token": "\u0120\u00cf\u0125\u00ce\u00b5", "merges": "\u0120\u00cf\u0125 \u00ce\u00b5", "raw_count": 172, "count": 172, "decode_str": " \u03c3\u03b5"} -{"id": 35830, "token": "]_{", "merges": "] _{", "raw_count": 172, "count": 172, "decode_str": "]_{"} -{"id": 40527, "token": "\u0120\\:", "merges": "\u0120\\ :", "raw_count": 172, "count": 172, "decode_str": " \\:"} -{"id": 18531, "token": "\u0120Mississippi", "merges": "\u0120Miss issippi", "raw_count": 173, "count": 173, "decode_str": " Mississippi"} -{"id": 48587, "token": "\u0120Seriously", "merges": "\u0120Ser iously", "raw_count": 173, "count": 173, "decode_str": " Seriously"} -{"id": 31003, "token": "\u0120Colombia", "merges": "\u0120Colomb ia", "raw_count": 173, "count": 173, "decode_str": " Colombia"} -{"id": 18175, "token": "\u0120Hillary", "merges": "\u0120Hill ary", "raw_count": 173, "count": 173, "decode_str": " Hillary"} -{"id": 46287, "token": "\u0120Buenos", "merges": "\u0120Bu enos", "raw_count": 173, "count": 173, "decode_str": " Buenos"} -{"id": 49389, "token": "\u0120Himal", "merges": "\u0120H imal", "raw_count": 173, "count": 173, "decode_str": " Himal"} -{"id": 40771, "token": "\u0120Shane", "merges": "\u0120Sh ane", "raw_count": 173, "count": 173, "decode_str": " Shane"} -{"id": 50378, "token": "\u00e2\u0139\u00a4", "merges": "\u00e2\u0139 \u00a4", "raw_count": 173, "count": 173, "decode_str": "\u25e4"} -{"id": 19135, "token": "}^*", "merges": "}^ *", "raw_count": 173, "count": 173, "decode_str": "}^*"} -{"id": 47206, "token": "_{*", "merges": "_{ *", "raw_count": 173, "count": 173, "decode_str": "_{*"} -{"id": 23022, "token": "\u0120\u00c3\u013a", "merges": "\u0120\u00c3 \u013a", "raw_count": 173, "count": 173, "decode_str": " \u00d8"} -{"id": 21070, "token": "\u00c4\u0122", "merges": "\u00c4 \u0122", "raw_count": 173, "count": 173, "decode_str": "\u0100"} -{"id": 28354, "token": "\u0120\u00cf\u0122\u00cf\u0123\u00ce\u00bf", "merges": "\u0120\u00cf\u0122 \u00cf\u0123\u00ce\u00bf", "raw_count": 174, "count": 174, "decode_str": " \u03c0\u03c1\u03bf"} -{"id": 41792, "token": "\u0120glioma", "merges": "\u0120gli oma", "raw_count": 174, "count": 174, "decode_str": " glioma"} -{"id": 47832, "token": "\u0120Malta", "merges": "\u0120Mal ta", "raw_count": 174, "count": 174, "decode_str": " Malta"} -{"id": 35943, "token": "\u0120cAMP", "merges": "\u0120c AMP", "raw_count": 174, "count": 174, "decode_str": " cAMP"} -{"id": 34500, "token": "\u00ce\u0143\u00cf\u0124", "merges": "\u00ce\u0143 \u00cf\u0124", "raw_count": 174, "count": 174, "decode_str": "\u03ad\u03c2"} -{"id": 41009, "token": "\u0120McConnell", "merges": "\u0120Mc Connell", "raw_count": 175, "count": 175, "decode_str": " McConnell"} -{"id": 34159, "token": "\u0120Helsinki", "merges": "\u0120Hels inki", "raw_count": 175, "count": 175, "decode_str": " Helsinki"} -{"id": 40607, "token": "\u0120Cochrane", "merges": "\u0120Co chrane", "raw_count": 175, "count": 175, "decode_str": " Cochrane"} -{"id": 47137, "token": "\u0120Valencia", "merges": "\u0120Val encia", "raw_count": 175, "count": 175, "decode_str": " Valencia"} -{"id": 34248, "token": "\u0120serine", "merges": "\u0120ser ine", "raw_count": 175, "count": 175, "decode_str": " serine"} -{"id": 39718, "token": "\u0120Acute", "merges": "\u0120Ac ute", "raw_count": 175, "count": 175, "decode_str": " Acute"} -{"id": 46620, "token": "\u0120sehr", "merges": "\u0120se hr", "raw_count": 175, "count": 175, "decode_str": " sehr"} -{"id": 42313, "token": "\u00ce\u00ac\u00ce\u00bd", "merges": "\u00ce\u00ac \u00ce\u00bd", "raw_count": 175, "count": 175, "decode_str": "\u03ac\u03bd"} -{"id": 36225, "token": "\u0120HEK", "merges": "\u0120HE K", "raw_count": 175, "count": 175, "decode_str": " HEK"} -{"id": 46194, "token": "\u0120Gus", "merges": "\u0120G us", "raw_count": 175, "count": 175, "decode_str": " Gus"} -{"id": 17372, "token": "\u0120Detroit", "merges": "\u0120Det roit", "raw_count": 176, "count": 176, "decode_str": " Detroit"} -{"id": 37063, "token": "\u0120Bengal", "merges": "\u0120Beng al", "raw_count": 176, "count": 176, "decode_str": " Bengal"} -{"id": 33147, "token": "oblot", "merges": "ob lot", "raw_count": 155, "count": 176, "decode_str": "oblot"} -{"id": 38093, "token": "\u00cf\u0123\u00cf\u012b", "merges": "\u00cf\u0123 \u00cf\u012b", "raw_count": 176, "count": 176, "decode_str": "\u03c1\u03c9"} -{"id": 47858, "token": "\u0120Taj", "merges": "\u0120T aj", "raw_count": 176, "count": 176, "decode_str": " Taj"} -{"id": 45299, "token": "\u00c3\u00b8re", "merges": "\u00c3\u00b8 re", "raw_count": 176, "count": 176, "decode_str": "\u00f8re"} -{"id": 33354, "token": "\\|^", "merges": "\\| ^", "raw_count": 176, "count": 176, "decode_str": "\\|^"} -{"id": 34038, "token": "Decided", "merges": "Dec ided", "raw_count": 177, "count": 177, "decode_str": "Decided"} -{"id": 26642, "token": "\u0120Martha", "merges": "\u0120Mar tha", "raw_count": 177, "count": 177, "decode_str": " Martha"} -{"id": 36180, "token": "\u0120Latino", "merges": "\u0120Lat ino", "raw_count": 177, "count": 177, "decode_str": " Latino"} -{"id": 25287, "token": "\u0120Quebec", "merges": "\u0120Que bec", "raw_count": 177, "count": 177, "decode_str": " Quebec"} -{"id": 36758, "token": "pdev", "merges": "p dev", "raw_count": 177, "count": 177, "decode_str": "pdev"} -{"id": 1764, "token": "\u0120$$\\", "merges": "\u0120$ $\\", "raw_count": 177, "count": 177, "decode_str": " $$\\"} -{"id": 39242, "token": "\u00ce\u00b1\u00cf\u0124", "merges": "\u00ce\u00b1 \u00cf\u0124", "raw_count": 177, "count": 177, "decode_str": "\u03b1\u03c2"} -{"id": 33809, "token": "\u0120transmembrane", "merges": "\u0120trans membrane", "raw_count": 178, "count": 178, "decode_str": " transmembrane"} -{"id": 34956, "token": "\u0120cytochrome", "merges": "\u0120cy tochrome", "raw_count": 178, "count": 178, "decode_str": " cytochrome"} -{"id": 38321, "token": "\u0120Monsieur", "merges": "\u0120Mons ieur", "raw_count": 178, "count": 178, "decode_str": " Monsieur"} -{"id": 21737, "token": "\u0120Licensed", "merges": "\u0120Lic ensed", "raw_count": 178, "count": 178, "decode_str": " Licensed"} -{"id": 47969, "token": "raisebox", "merges": "raise box", "raw_count": 178, "count": 178, "decode_str": "raisebox"} -{"id": 30979, "token": "\u0120Madame", "merges": "\u0120Mad ame", "raw_count": 178, "count": 178, "decode_str": " Madame"} -{"id": 34829, "token": "\u0120Biosc", "merges": "\u0120Bios c", "raw_count": 108, "count": 178, "decode_str": " Biosc"} -{"id": 26563, "token": "\u0120Cinc", "merges": "\u0120C inc", "raw_count": 71, "count": 178, "decode_str": " Cinc"} -{"id": 45169, "token": "\u0120immunosuppressive", "merges": "\u0120immunosupp ressive", "raw_count": 179, "count": 179, "decode_str": " immunosuppressive"} -{"id": 48766, "token": "\u0120thermoplastic", "merges": "\u0120therm oplastic", "raw_count": 179, "count": 179, "decode_str": " thermoplastic"} -{"id": 35563, "token": "\u0120carcinomas", "merges": "\u0120carcin omas", "raw_count": 179, "count": 179, "decode_str": " carcinomas"} -{"id": 42346, "token": "\u0120offseason", "merges": "\u0120off season", "raw_count": 179, "count": 179, "decode_str": " offseason"} -{"id": 42323, "token": "\u0120secretory", "merges": "\u0120secret ory", "raw_count": 179, "count": 179, "decode_str": " secretory"} -{"id": 48509, "token": "\u0120telomere", "merges": "\u0120telome re", "raw_count": 179, "count": 179, "decode_str": " telomere"} -{"id": 35732, "token": "\u0120Estados", "merges": "\u0120Est ados", "raw_count": 179, "count": 179, "decode_str": " Estados"} -{"id": 36718, "token": "textstyle", "merges": "text style", "raw_count": 180, "count": 180, "decode_str": "textstyle"} -{"id": 48432, "token": "\u0120Nissan", "merges": "\u0120Niss an", "raw_count": 180, "count": 180, "decode_str": " Nissan"} -{"id": 47203, "token": "\u0120\u00c3\u00a4n", "merges": "\u0120\u00c3\u00a4 n", "raw_count": 180, "count": 180, "decode_str": " \u00e4n"} -{"id": 45162, "token": "\u0120UAE", "merges": "\u0120U AE", "raw_count": 180, "count": 180, "decode_str": " UAE"} -{"id": 21846, "token": "\u0120\\!", "merges": "\u0120\\ !", "raw_count": 180, "count": 180, "decode_str": " \\!"} -{"id": 18304, "token": "\u0120transcriptional", "merges": "\u0120transcript ional", "raw_count": 181, "count": 181, "decode_str": " transcriptional"} -{"id": 42561, "token": "\u0120radiographic", "merges": "\u0120radi ographic", "raw_count": 181, "count": 181, "decode_str": " radiographic"} -{"id": 41418, "token": "\u0120glomerular", "merges": "\u0120glomer ular", "raw_count": 181, "count": 181, "decode_str": " glomerular"} -{"id": 41120, "token": "\u0120Esther", "merges": "\u0120Est her", "raw_count": 181, "count": 181, "decode_str": " Esther"} -{"id": 23401, "token": "\u00e2\u0122\u0125\u00e2\u0122\u0125", "merges": "\u00e2\u0122\u0125 \u00e2\u0122\u0125", "raw_count": 152, "count": 181, "decode_str": "\u2003\u2003"} -{"id": 29630, "token": "\u0120Welsh", "merges": "\u0120Wel sh", "raw_count": 181, "count": 181, "decode_str": " Welsh"} -{"id": 26855, "token": "\u0120\u00cf\u0125\u00cf\u0127", "merges": "\u0120\u00cf\u0125 \u00cf\u0127", "raw_count": 103, "count": 181, "decode_str": " \u03c3\u03c5"} -{"id": 40287, "token": "\u0120pr\u00c3\u00a1", "merges": "\u0120pr \u00c3\u00a1", "raw_count": 181, "count": 181, "decode_str": " pr\u00e1"} -{"id": 30096, "token": "f\u00c3\u00b6r", "merges": "f \u00c3\u00b6r", "raw_count": 181, "count": 181, "decode_str": "f\u00f6r"} -{"id": 50284, "token": "\u00cb\u012c", "merges": "\u00cb \u012c", "raw_count": 181, "count": 181, "decode_str": "\u02ca"} -{"id": 34421, "token": "\u0120Yorkshire", "merges": "\u0120Y orkshire", "raw_count": 182, "count": 182, "decode_str": " Yorkshire"} -{"id": 32683, "token": "\u0120Allied", "merges": "\u0120All ied", "raw_count": 182, "count": 182, "decode_str": " Allied"} -{"id": 21938, "token": "\u0120[\u00e2\u0122\u00a6]", "merges": "\u0120[ \u00e2\u0122\u00a6]", "raw_count": 182, "count": 182, "decode_str": " [\u2026]"} -{"id": 48295, "token": "Lastly", "merges": "Last ly", "raw_count": 182, "count": 182, "decode_str": "Lastly"} -{"id": 37919, "token": "\u0120gyrus", "merges": "\u0120g yrus", "raw_count": 182, "count": 182, "decode_str": " gyrus"} -{"id": 36684, "token": "\u0120\u00ce\u00b1\u00ce\u00bd", "merges": "\u0120\u00ce\u00b1 \u00ce\u00bd", "raw_count": 182, "count": 182, "decode_str": " \u03b1\u03bd"} -{"id": 43047, "token": "\u0120Tuc", "merges": "\u0120T uc", "raw_count": 182, "count": 182, "decode_str": " Tuc"} -{"id": 41302, "token": "},$", "merges": "}, $", "raw_count": 182, "count": 182, "decode_str": "},$"} -{"id": 30252, "token": "\u0120parlament", "merges": "\u0120par lament", "raw_count": 183, "count": 183, "decode_str": " parlament"} -{"id": 17960, "token": "\u0120Scottish", "merges": "\u0120Scott ish", "raw_count": 183, "count": 183, "decode_str": " Scottish"} -{"id": 35278, "token": "\u0120\u00ce\u00b1\u00cf\u0122\u00cf\u012e", "merges": "\u0120\u00ce\u00b1 \u00cf\u0122\u00cf\u012e", "raw_count": 183, "count": 183, "decode_str": " \u03b1\u03c0\u03cc"} -{"id": 26656, "token": "\u0120Biden", "merges": "\u0120B iden", "raw_count": 183, "count": 183, "decode_str": " Biden"} -{"id": 48835, "token": "\u0120arbe", "merges": "\u0120ar be", "raw_count": 183, "count": 183, "decode_str": " arbe"} -{"id": 44538, "token": "\u0120IHC", "merges": "\u0120I HC", "raw_count": 183, "count": 183, "decode_str": " IHC"} -{"id": 28748, "token": "\u0120Queensland", "merges": "\u0120Queens land", "raw_count": 184, "count": 184, "decode_str": " Queensland"} -{"id": 30907, "token": "\u0120Vietnamese", "merges": "\u0120Viet namese", "raw_count": 184, "count": 184, "decode_str": " Vietnamese"} -{"id": 37708, "token": "\u0120Americas", "merges": "\u0120Americ as", "raw_count": 184, "count": 184, "decode_str": " Americas"} -{"id": 48816, "token": "\u0120Hercules", "merges": "\u0120Her cules", "raw_count": 184, "count": 184, "decode_str": " Hercules"} -{"id": 31863, "token": "\u0120spermat", "merges": "\u0120sper mat", "raw_count": 184, "count": 184, "decode_str": " spermat"} -{"id": 47770, "token": "\u0120Severe", "merges": "\u0120Se vere", "raw_count": 184, "count": 184, "decode_str": " Severe"} -{"id": 32156, "token": "^*_", "merges": "^* _", "raw_count": 184, "count": 184, "decode_str": "^*_"} -{"id": 37055, "token": "'}$", "merges": "' }$", "raw_count": 184, "count": 184, "decode_str": "'}$"} -{"id": 18292, "token": "\u0120Supplementary", "merges": "\u0120Supp lementary", "raw_count": 185, "count": 185, "decode_str": " Supplementary"} -{"id": 41130, "token": "\u0120ferromagnetic", "merges": "\u0120fer romagnetic", "raw_count": 185, "count": 185, "decode_str": " ferromagnetic"} -{"id": 14723, "token": "\u0120Invention", "merges": "\u0120In vention", "raw_count": 185, "count": 185, "decode_str": " Invention"} -{"id": 44203, "token": "\u0120parietal", "merges": "\u0120par ietal", "raw_count": 185, "count": 185, "decode_str": " parietal"} -{"id": 28624, "token": "\u0120agonist", "merges": "\u0120agon ist", "raw_count": 185, "count": 185, "decode_str": " agonist"} -{"id": 47252, "token": "\u0120intrav", "merges": "\u0120int rav", "raw_count": 185, "count": 185, "decode_str": " intrav"} -{"id": 28364, "token": "\u0120Satan", "merges": "\u0120Sat an", "raw_count": 185, "count": 185, "decode_str": " Satan"} -{"id": 32874, "token": "\u0120Kerry", "merges": "\u0120K erry", "raw_count": 185, "count": 185, "decode_str": " Kerry"} -{"id": 44988, "token": "NFTA", "merges": "N FTA", "raw_count": 185, "count": 185, "decode_str": "NFTA"} -{"id": 38006, "token": "\\~", "merges": "\\ ~", "raw_count": 185, "count": 185, "decode_str": "\\~"} -{"id": 45273, "token": "\u0120Scientists", "merges": "\u0120Scient ists", "raw_count": 186, "count": 186, "decode_str": " Scientists"} -{"id": 37134, "token": "\u0120\u00ce\u00b5\u00ce\u00af\u00ce\u00bd\u00ce\u00b1\u00ce\u00b9", "merges": "\u0120\u00ce\u00b5 \u00ce\u00af\u00ce\u00bd\u00ce\u00b1\u00ce\u00b9", "raw_count": 186, "count": 186, "decode_str": " \u03b5\u03af\u03bd\u03b1\u03b9"} -{"id": 47857, "token": "\u0120Antarctic", "merges": "\u0120Antar ctic", "raw_count": 186, "count": 186, "decode_str": " Antarctic"} -{"id": 23856, "token": "\u0120Nigeria", "merges": "\u0120Nig eria", "raw_count": 186, "count": 186, "decode_str": " Nigeria"} -{"id": 46389, "token": "\u0120Judith", "merges": "\u0120Jud ith", "raw_count": 186, "count": 186, "decode_str": " Judith"} -{"id": 46600, "token": "\u0120Shawn", "merges": "\u0120Sh awn", "raw_count": 186, "count": 186, "decode_str": " Shawn"} -{"id": 35274, "token": "\u0120Aristotle", "merges": "\u0120Arist otle", "raw_count": 187, "count": 187, "decode_str": " Aristotle"} -{"id": 48067, "token": "\u00c3\u00bcssen", "merges": "\u00c3\u00bcss en", "raw_count": 187, "count": 187, "decode_str": "\u00fcssen"} -{"id": 27946, "token": "\u0120Kenya", "merges": "\u0120Ken ya", "raw_count": 187, "count": 187, "decode_str": " Kenya"} -{"id": 29691, "token": "\u0120centrifugation", "merges": "\u0120centrifug ation", "raw_count": 188, "count": 188, "decode_str": " centrifugation"} -{"id": 20386, "token": "CHANTABILITY", "merges": "CHANT ABILITY", "raw_count": 67, "count": 188, "decode_str": "CHANTABILITY"} -{"id": 45889, "token": "\u0120mutagenesis", "merges": "\u0120mutagen esis", "raw_count": 188, "count": 188, "decode_str": " mutagenesis"} -{"id": 43446, "token": "\u0120COUNTY", "merges": "\u0120COUNT Y", "raw_count": 188, "count": 188, "decode_str": " COUNTY"} -{"id": 25976, "token": "..\\..\\", "merges": "..\\ ..\\", "raw_count": 188, "count": 188, "decode_str": "..\\..\\"} -{"id": 12523, "token": "}}(\\", "merges": "}} (\\", "raw_count": 188, "count": 188, "decode_str": "}}(\\"} -{"id": 34465, "token": "}=(", "merges": "}= (", "raw_count": 188, "count": 188, "decode_str": "}=("} -{"id": 44347, "token": "\u0120Conventional", "merges": "\u0120Convention al", "raw_count": 189, "count": 189, "decode_str": " Conventional"} -{"id": 30577, "token": "\u0120phosphatase", "merges": "\u0120phosphat ase", "raw_count": 189, "count": 189, "decode_str": " phosphatase"} -{"id": 49466, "token": "\u0120INCIDENT", "merges": "\u0120INC IDENT", "raw_count": 189, "count": 189, "decode_str": " INCIDENT"} -{"id": 24213, "token": "propto", "merges": "pro pto", "raw_count": 189, "count": 189, "decode_str": "propto"} -{"id": 35593, "token": "\\*\\*\\*", "merges": "\\*\\* \\*", "raw_count": 189, "count": 189, "decode_str": "\\*\\*\\*"} -{"id": 35436, "token": "\u0120Donna", "merges": "\u0120Don na", "raw_count": 189, "count": 189, "decode_str": " Donna"} -{"id": 48076, "token": "\u0120Elsa", "merges": "\u0120El sa", "raw_count": 189, "count": 189, "decode_str": " Elsa"} -{"id": 47741, "token": "\u0120RPE", "merges": "\u0120R PE", "raw_count": 189, "count": 189, "decode_str": " RPE"} -{"id": 24036, "token": "\u0120\u00cf\u012e", "merges": "\u0120 \u00cf\u012e", "raw_count": 175, "count": 189, "decode_str": " \u03cc"} -{"id": 41146, "token": "\u0120senescence", "merges": "\u0120sen escence", "raw_count": 190, "count": 190, "decode_str": " senescence"} -{"id": 33537, "token": "\u0120biopsies", "merges": "\u0120bi opsies", "raw_count": 190, "count": 190, "decode_str": " biopsies"} -{"id": 37642, "token": "\u0120Congo", "merges": "\u0120Cong o", "raw_count": 190, "count": 190, "decode_str": " Congo"} -{"id": 49015, "token": "\u0120Sey", "merges": "\u0120Se y", "raw_count": 190, "count": 190, "decode_str": " Sey"} -{"id": 48155, "token": "ss\u00c3\u00a4", "merges": "ss \u00c3\u00a4", "raw_count": 190, "count": 190, "decode_str": "ss\u00e4"} -{"id": 33401, "token": "\u0120\\|\\", "merges": "\u0120\\ |\\", "raw_count": 190, "count": 190, "decode_str": " \\|\\"} -{"id": 34241, "token": "\u0120conformational", "merges": "\u0120conform ational", "raw_count": 191, "count": 191, "decode_str": " conformational"} -{"id": 43622, "token": "\u0120Differentiate", "merges": "\u0120Different iate", "raw_count": 191, "count": 191, "decode_str": " Differentiate"} -{"id": 42831, "token": "microorganisms", "merges": "micro organisms", "raw_count": 191, "count": 191, "decode_str": "microorganisms"} -{"id": 38702, "token": "\u0120micrograms", "merges": "\u0120micro grams", "raw_count": 191, "count": 191, "decode_str": " micrograms"} -{"id": 34596, "token": "\u0120peroxidase", "merges": "\u0120perox idase", "raw_count": 191, "count": 191, "decode_str": " peroxidase"} -{"id": 37121, "token": "\u0120adenosine", "merges": "\u0120aden osine", "raw_count": 191, "count": 191, "decode_str": " adenosine"} -{"id": 40431, "token": "\u0120Warsaw", "merges": "\u0120Wars aw", "raw_count": 191, "count": 191, "decode_str": " Warsaw"} -{"id": 41638, "token": "\u00c3\u00a4hler", "merges": "\u00c3\u00a4h ler", "raw_count": 191, "count": 191, "decode_str": "\u00e4hler"} -{"id": 44965, "token": "\u0120[[*", "merges": "\u0120[[ *", "raw_count": 191, "count": 191, "decode_str": " [[*"} -{"id": 32507, "token": "\u0120AGN", "merges": "\u0120AG N", "raw_count": 191, "count": 191, "decode_str": " AGN"} -{"id": 49233, "token": "\u00e0\u00bd", "merges": "\u00e0 \u00bd", "raw_count": 191, "count": 191, "decode_str": "\ufffd"} -{"id": 16257, "token": "\u0120Meanwhile", "merges": "\u0120Mean while", "raw_count": 192, "count": 192, "decode_str": " Meanwhile"} -{"id": 47922, "token": "\u0120Brewing", "merges": "\u0120Brew ing", "raw_count": 192, "count": 192, "decode_str": " Brewing"} -{"id": 41592, "token": "\u0120Tibetan", "merges": "\u0120Tibet an", "raw_count": 192, "count": 192, "decode_str": " Tibetan"} -{"id": 34454, "token": "\u0120)$", "merges": "\u0120 )$", "raw_count": 192, "count": 192, "decode_str": " )$"} -{"id": 34862, "token": "\u0120triplicate", "merges": "\u0120tri plicate", "raw_count": 193, "count": 193, "decode_str": " triplicate"} -{"id": 44542, "token": "\u0120Ethan", "merges": "\u0120Eth an", "raw_count": 193, "count": 193, "decode_str": " Ethan"} -{"id": 37073, "token": "\u0120Katie", "merges": "\u0120Kat ie", "raw_count": 193, "count": 193, "decode_str": " Katie"} -{"id": 41896, "token": "\u0120j\u00c3\u00a4", "merges": "\u0120j \u00c3\u00a4", "raw_count": 176, "count": 193, "decode_str": " j\u00e4"} -{"id": 30793, "token": "\u00ce\u00bf\u00ce\u00b9", "merges": "\u00ce\u00bf \u00ce\u00b9", "raw_count": 193, "count": 193, "decode_str": "\u03bf\u03b9"} -{"id": 19585, "token": "\u0120Baltimore", "merges": "\u0120Balt imore", "raw_count": 194, "count": 194, "decode_str": " Baltimore"} -{"id": 31877, "token": "\u0120INCLUDING", "merges": "\u0120IN CLUDING", "raw_count": 194, "count": 194, "decode_str": " INCLUDING"} -{"id": 44435, "token": "\u0120Colonial", "merges": "\u0120Col onial", "raw_count": 194, "count": 194, "decode_str": " Colonial"} -{"id": 35245, "token": "\u00ce\u00af\u00ce\u00bd\u00ce\u00b1\u00ce\u00b9", "merges": "\u00ce\u00af\u00ce\u00bd \u00ce\u00b1\u00ce\u00b9", "raw_count": 8, "count": 194, "decode_str": "\u03af\u03bd\u03b1\u03b9"} -{"id": 38994, "token": "\u0120Melissa", "merges": "\u0120Mel issa", "raw_count": 194, "count": 194, "decode_str": " Melissa"} -{"id": 33417, "token": "\u0120Courts", "merges": "\u0120Court s", "raw_count": 194, "count": 194, "decode_str": " Courts"} -{"id": 45526, "token": "\u0120Bulls", "merges": "\u0120Bull s", "raw_count": 194, "count": 194, "decode_str": " Bulls"} -{"id": 32221, "token": "\u0120SHALL", "merges": "\u0120SH ALL", "raw_count": 194, "count": 194, "decode_str": " SHALL"} -{"id": 49671, "token": "\u0120Mild", "merges": "\u0120M ild", "raw_count": 194, "count": 194, "decode_str": " Mild"} -{"id": 46292, "token": "\u0120v\u00c3\u00bd", "merges": "\u0120v \u00c3\u00bd", "raw_count": 194, "count": 194, "decode_str": " v\u00fd"} -{"id": 45530, "token": "\u0120Osw", "merges": "\u0120O sw", "raw_count": 194, "count": 194, "decode_str": " Osw"} -{"id": 32400, "token": "WKH", "merges": "W KH", "raw_count": 194, "count": 194, "decode_str": "WKH"} -{"id": 49020, "token": "\u0120triglyceride", "merges": "\u0120triglycer ide", "raw_count": 195, "count": 195, "decode_str": " triglyceride"} -{"id": 23273, "token": "\u0120fibroblasts", "merges": "\u0120fibrobl asts", "raw_count": 195, "count": 195, "decode_str": " fibroblasts"} -{"id": 35836, "token": "\u0120zebrafish", "merges": "\u0120zebra fish", "raw_count": 195, "count": 195, "decode_str": " zebrafish"} -{"id": 27687, "token": "\u0120Orlando", "merges": "\u0120Or lando", "raw_count": 195, "count": 195, "decode_str": " Orlando"} -{"id": 38012, "token": "\u0120MNRAS", "merges": "\u0120M NRAS", "raw_count": 195, "count": 195, "decode_str": " MNRAS"} -{"id": 23222, "token": "\u0120Conservative", "merges": "\u0120Conserv ative", "raw_count": 196, "count": 196, "decode_str": " Conservative"} -{"id": 39044, "token": "\u0120fibroblast", "merges": "\u0120fibrobl ast", "raw_count": 196, "count": 196, "decode_str": " fibroblast"} -{"id": 49846, "token": "\u0120heterozyg", "merges": "\u0120heter ozyg", "raw_count": 196, "count": 196, "decode_str": " heterozyg"} -{"id": 39528, "token": "\u0120Rochester", "merges": "\u0120Roche ster", "raw_count": 196, "count": 196, "decode_str": " Rochester"} -{"id": 46761, "token": "\u0120albicans", "merges": "\u0120alb icans", "raw_count": 196, "count": 196, "decode_str": " albicans"} -{"id": 18984, "token": "\u0120ovarian", "merges": "\u0120ovar ian", "raw_count": 196, "count": 196, "decode_str": " ovarian"} -{"id": 47144, "token": "\u0120GOODS", "merges": "\u0120GOOD S", "raw_count": 196, "count": 196, "decode_str": " GOODS"} -{"id": 37938, "token": "\u0120loro", "merges": "\u0120l oro", "raw_count": 196, "count": 196, "decode_str": " loro"} -{"id": 24110, "token": "\u0120Brazilian", "merges": "\u0120Brazil ian", "raw_count": 197, "count": 197, "decode_str": " Brazilian"} -{"id": 45208, "token": "\u0120plasmon", "merges": "\u0120plas mon", "raw_count": 197, "count": 197, "decode_str": " plasmon"} -{"id": 48507, "token": "\u0120splen", "merges": "\u0120spl en", "raw_count": 197, "count": 197, "decode_str": " splen"} -{"id": 30065, "token": "\u0120Celt", "merges": "\u0120C elt", "raw_count": 129, "count": 197, "decode_str": " Celt"} -{"id": 43145, "token": "hljs", "merges": "hl js", "raw_count": 197, "count": 197, "decode_str": "hljs"} -{"id": 40406, "token": "\u00c3\u00a5ng", "merges": "\u00c3\u00a5 ng", "raw_count": 197, "count": 197, "decode_str": "\u00e5ng"} -{"id": 39093, "token": "\u0120emulsion", "merges": "\u0120em ulsion", "raw_count": 198, "count": 198, "decode_str": " emulsion"} -{"id": 49512, "token": "\u0120Inhib", "merges": "\u0120In hib", "raw_count": 198, "count": 198, "decode_str": " Inhib"} -{"id": 46797, "token": "\u0120Chick", "merges": "\u0120Ch ick", "raw_count": 198, "count": 198, "decode_str": " Chick"} -{"id": 41951, "token": "\u0120Kyoto", "merges": "\u0120Ky oto", "raw_count": 198, "count": 198, "decode_str": " Kyoto"} -{"id": 46286, "token": "\u0120phenomenological", "merges": "\u0120phenomen ological", "raw_count": 199, "count": 199, "decode_str": " phenomenological"} -{"id": 21609, "token": "\u0120Mediterranean", "merges": "\u0120Med iterranean", "raw_count": 199, "count": 199, "decode_str": " Mediterranean"} -{"id": 24256, "token": "\u0120cytoplasmic", "merges": "\u0120cytoplasm ic", "raw_count": 199, "count": 199, "decode_str": " cytoplasmic"} -{"id": 37558, "token": "\u0120Legislative", "merges": "\u0120Legisl ative", "raw_count": 199, "count": 199, "decode_str": " Legislative"} -{"id": 47139, "token": "\u0120Wrestling", "merges": "\u0120Wrest ling", "raw_count": 199, "count": 199, "decode_str": " Wrestling"} -{"id": 39853, "token": "\u0120reductase", "merges": "\u0120reduct ase", "raw_count": 199, "count": 199, "decode_str": " reductase"} -{"id": 29530, "token": "\u0120plasmids", "merges": "\u0120plasm ids", "raw_count": 199, "count": 199, "decode_str": " plasmids"} -{"id": 26304, "token": "\u0120Danish", "merges": "\u0120Dan ish", "raw_count": 199, "count": 199, "decode_str": " Danish"} -{"id": 37603, "token": "\u0120Slov", "merges": "\u0120Sl ov", "raw_count": 199, "count": 199, "decode_str": " Slov"} -{"id": 31805, "token": "\u0120Peru", "merges": "\u0120Per u", "raw_count": 199, "count": 199, "decode_str": " Peru"} -{"id": 40051, "token": "\u00ce\u00b1\u00cf\u0125", "merges": "\u00ce\u00b1 \u00cf\u0125", "raw_count": 199, "count": 199, "decode_str": "\u03b1\u03c3"} -{"id": 45444, "token": "\u0120CDs", "merges": "\u0120CD s", "raw_count": 199, "count": 199, "decode_str": " CDs"} -{"id": 45944, "token": "\u0120glycine", "merges": "\u0120glyc ine", "raw_count": 200, "count": 200, "decode_str": " glycine"} -{"id": 46623, "token": "\u0120baryon", "merges": "\u0120bary on", "raw_count": 200, "count": 200, "decode_str": " baryon"} -{"id": 40914, "token": "textsc", "merges": "text sc", "raw_count": 200, "count": 200, "decode_str": "textsc"} -{"id": 29494, "token": "\u0120ERK", "merges": "\u0120ER K", "raw_count": 200, "count": 200, "decode_str": " ERK"} -{"id": 17180, "token": "|_{", "merges": "| _{", "raw_count": 198, "count": 200, "decode_str": "|_{"} -{"id": 29715, "token": "=-\\", "merges": "= -\\", "raw_count": 200, "count": 200, "decode_str": "=-\\"} -{"id": 25984, "token": "&&\\", "merges": "& &\\", "raw_count": 200, "count": 200, "decode_str": "&&\\"} -{"id": 42936, "token": "\u0120Stafford", "merges": "\u0120Staff ord", "raw_count": 201, "count": 201, "decode_str": " Stafford"} -{"id": 48824, "token": "\u0120Wilcoxon", "merges": "\u0120Wilcox on", "raw_count": 201, "count": 201, "decode_str": " Wilcoxon"} -{"id": 9315, "token": "qquad", "merges": "q quad", "raw_count": 201, "count": 201, "decode_str": "qquad"} -{"id": 39672, "token": "\u0120Nous", "merges": "\u0120N ous", "raw_count": 201, "count": 201, "decode_str": " Nous"} -{"id": 50354, "token": "\u00e2\u0137\u00b3", "merges": "\u00e2\u0137 \u00b3", "raw_count": 201, "count": 201, "decode_str": "\u2573"} -{"id": 43591, "token": "LRQ", "merges": "LR Q", "raw_count": 201, "count": 201, "decode_str": "LRQ"} -{"id": 47769, "token": "\u0120Inhibition", "merges": "\u0120In hibition", "raw_count": 202, "count": 202, "decode_str": " Inhibition"} -{"id": 47229, "token": "\u0120Emirates", "merges": "\u0120Emir ates", "raw_count": 202, "count": 202, "decode_str": " Emirates"} -{"id": 29026, "token": "\u0120Alberta", "merges": "\u0120Alber ta", "raw_count": 202, "count": 202, "decode_str": " Alberta"} -{"id": 13376, "token": "\u0120Afghan", "merges": "\u0120Af ghan", "raw_count": 78, "count": 202, "decode_str": " Afghan"} -{"id": 44870, "token": "\u0120Trevor", "merges": "\u0120Tre vor", "raw_count": 202, "count": 202, "decode_str": " Trevor"} -{"id": 30396, "token": "\u0120Romans", "merges": "\u0120Rom ans", "raw_count": 202, "count": 202, "decode_str": " Romans"} -{"id": 46275, "token": "/](", "merges": "/ ](", "raw_count": 202, "count": 202, "decode_str": "/]("} -{"id": 44045, "token": "\u0120prospectively", "merges": "\u0120prospect ively", "raw_count": 203, "count": 203, "decode_str": " prospectively"} -{"id": 15605, "token": "\u0120Commissioner", "merges": "\u0120Commission er", "raw_count": 203, "count": 203, "decode_str": " Commissioner"} -{"id": 40856, "token": "\u0120Bachelor", "merges": "\u0120B achelor", "raw_count": 203, "count": 203, "decode_str": " Bachelor"} -{"id": 37209, "token": "\u0120Officers", "merges": "\u0120Offic ers", "raw_count": 203, "count": 203, "decode_str": " Officers"} -{"id": 40828, "token": "\u0120Knowing", "merges": "\u0120Know ing", "raw_count": 203, "count": 203, "decode_str": " Knowing"} -{"id": 49771, "token": "\u0120Leone", "merges": "\u0120Le one", "raw_count": 203, "count": 203, "decode_str": " Leone"} -{"id": 45632, "token": "\u0120antisense", "merges": "\u0120antis ense", "raw_count": 204, "count": 204, "decode_str": " antisense"} -{"id": 48444, "token": "\u0120Ramirez", "merges": "\u0120Ram irez", "raw_count": 204, "count": 204, "decode_str": " Ramirez"} -{"id": 18143, "token": "\u0120Utah", "merges": "\u0120U tah", "raw_count": 204, "count": 204, "decode_str": " Utah"} -{"id": 38897, "token": "\u00e0\u00a9", "merges": "\u00e0 \u00a9", "raw_count": 204, "count": 204, "decode_str": "\ufffd"} -{"id": 49478, "token": "\u0120dexamethasone", "merges": "\u0120dex amethasone", "raw_count": 205, "count": 205, "decode_str": " dexamethasone"} -{"id": 28838, "token": "toxins", "merges": "tox ins", "raw_count": 205, "count": 205, "decode_str": "toxins"} -{"id": 28042, "token": "rVert", "merges": "r Vert", "raw_count": 205, "count": 205, "decode_str": "rVert"} -{"id": 20883, "token": "**).", "merges": "** ).", "raw_count": 205, "count": 205, "decode_str": "**)."} -{"id": 49773, "token": "\u00d9\u012d", "merges": "\u00d9 \u012d", "raw_count": 205, "count": 205, "decode_str": "\u064b"} -{"id": 46992, "token": "\u00ef\u00ac", "merges": "\u00ef \u00ac", "raw_count": 205, "count": 205, "decode_str": "\ufffd"} -{"id": 39722, "token": "\u0120Constitutional", "merges": "\u0120Constitution al", "raw_count": 206, "count": 206, "decode_str": " Constitutional"} -{"id": 47974, "token": "\u0120Augustine", "merges": "\u0120August ine", "raw_count": 206, "count": 206, "decode_str": " Augustine"} -{"id": 30647, "token": "\u0120Nashville", "merges": "\u0120Nash ville", "raw_count": 206, "count": 206, "decode_str": " Nashville"} -{"id": 44039, "token": "\u0120Pediatric", "merges": "\u0120Ped iatric", "raw_count": 206, "count": 206, "decode_str": " Pediatric"} -{"id": 39790, "token": "\u0120Verizon", "merges": "\u0120Ver izon", "raw_count": 206, "count": 206, "decode_str": " Verizon"} -{"id": 32309, "token": "\u0120\u00cf\u0122\u00ce\u00bf\u00cf\u0127", "merges": "\u0120\u00cf\u0122 \u00ce\u00bf\u00cf\u0127", "raw_count": 206, "count": 206, "decode_str": " \u03c0\u03bf\u03c5"} -{"id": 31208, "token": "\u0120Alban", "merges": "\u0120Al ban", "raw_count": 206, "count": 206, "decode_str": " Alban"} -{"id": 48511, "token": "\u0120Theo", "merges": "\u0120The o", "raw_count": 206, "count": 206, "decode_str": " Theo"} -{"id": 31217, "token": "\u0120n\u00c3\u00a5", "merges": "\u0120n \u00c3\u00a5", "raw_count": 206, "count": 206, "decode_str": " n\u00e5"} -{"id": 50380, "token": "\u00e2\u013a\u0140", "merges": "\u00e2\u013a \u0140", "raw_count": 206, "count": 206, "decode_str": "\u261e"} -{"id": 176, "token": "\u00f4", "merges": "NULL", "raw_count": 206, "count": 206, "decode_str": "\ufffd"} -{"id": 35916, "token": "AndroidRuntime", "merges": "Android Runtime", "raw_count": 207, "count": 207, "decode_str": "AndroidRuntime"} -{"id": 38143, "token": "\u0120aeruginosa", "merges": "\u0120aer uginosa", "raw_count": 207, "count": 207, "decode_str": " aeruginosa"} -{"id": 27314, "token": "\u0120Capitol", "merges": "\u0120Cap itol", "raw_count": 207, "count": 207, "decode_str": " Capitol"} -{"id": 24296, "token": "\u0120javax", "merges": "\u0120jav ax", "raw_count": 207, "count": 207, "decode_str": " javax"} -{"id": 43872, "token": "\u0120intraoperative", "merges": "\u0120intra operative", "raw_count": 208, "count": 208, "decode_str": " intraoperative"} -{"id": 43631, "token": "\u0120hemodynamic", "merges": "\u0120hem odynamic", "raw_count": 208, "count": 208, "decode_str": " hemodynamic"} -{"id": 48967, "token": "\u0120neoplasms", "merges": "\u0120neopl asms", "raw_count": 208, "count": 208, "decode_str": " neoplasms"} -{"id": 47677, "token": "\u0120Bedford", "merges": "\u0120Bed ford", "raw_count": 208, "count": 208, "decode_str": " Bedford"} -{"id": 50320, "token": "\u00e2\u012a\u0142", "merges": "\u00e2\u012a \u0142", "raw_count": 208, "count": 208, "decode_str": "\u2220"} -{"id": 13181, "token": "\u0120\\#", "merges": "\u0120\\ #", "raw_count": 208, "count": 208, "decode_str": " \\#"} -{"id": 38029, "token": "\u0120touchdowns", "merges": "\u0120touchdown s", "raw_count": 209, "count": 209, "decode_str": " touchdowns"} -{"id": 36541, "token": "\u0120agonists", "merges": "\u0120agon ists", "raw_count": 209, "count": 209, "decode_str": " agonists"} -{"id": 34992, "token": "\u0120Dubai", "merges": "\u0120Dub ai", "raw_count": 209, "count": 209, "decode_str": " Dubai"} -{"id": 49426, "token": "\u0120Dover", "merges": "\u0120D over", "raw_count": 209, "count": 209, "decode_str": " Dover"} -{"id": 44846, "token": "\u0120Elena", "merges": "\u0120El ena", "raw_count": 209, "count": 209, "decode_str": " Elena"} -{"id": 49000, "token": "\u0120Oste", "merges": "\u0120O ste", "raw_count": 209, "count": 209, "decode_str": " Oste"} -{"id": 29789, "token": "$\u00e2\u0122\u013b", "merges": "$ \u00e2\u0122\u013b", "raw_count": 209, "count": 209, "decode_str": "$\u2019"} -{"id": 15263, "token": "\u0120Alabama", "merges": "\u0120Al abama", "raw_count": 210, "count": 210, "decode_str": " Alabama"} -{"id": 37870, "token": "\u0120Durham", "merges": "\u0120Dur ham", "raw_count": 210, "count": 210, "decode_str": " Durham"} -{"id": 36779, "token": "\u0120Sharon", "merges": "\u0120Sh aron", "raw_count": 210, "count": 210, "decode_str": " Sharon"} -{"id": 25625, "token": "\u0120UNITED", "merges": "\u0120UN ITED", "raw_count": 210, "count": 210, "decode_str": " UNITED"} -{"id": 46516, "token": "\u0120Dios", "merges": "\u0120D ios", "raw_count": 210, "count": 210, "decode_str": " Dios"} -{"id": 41028, "token": "\u0120Balk", "merges": "\u0120B alk", "raw_count": 210, "count": 210, "decode_str": " Balk"} -{"id": 36397, "token": "\u0120(\u00c2\u00a3", "merges": "\u0120( \u00c2\u00a3", "raw_count": 210, "count": 210, "decode_str": " (\u00a3"} -{"id": 21370, "token": "$-$", "merges": "$- $", "raw_count": 210, "count": 210, "decode_str": "$-$"} -{"id": 47957, "token": "\u0120clonal", "merges": "\u0120cl onal", "raw_count": 211, "count": 211, "decode_str": " clonal"} -{"id": 47138, "token": "\u0120Scotia", "merges": "\u0120Scot ia", "raw_count": 211, "count": 211, "decode_str": " Scotia"} -{"id": 44065, "token": "\u0120Mickey", "merges": "\u0120Mic key", "raw_count": 211, "count": 211, "decode_str": " Mickey"} -{"id": 30175, "token": "\u0120\u00ce\u00b3\u00ce\u00b9\u00ce\u00b1", "merges": "\u0120\u00ce\u00b3 \u00ce\u00b9\u00ce\u00b1", "raw_count": 211, "count": 211, "decode_str": " \u03b3\u03b9\u03b1"} -{"id": 47873, "token": "\u0120Tyson", "merges": "\u0120T yson", "raw_count": 211, "count": 211, "decode_str": " Tyson"} -{"id": 37029, "token": "\u0120Presidential", "merges": "\u0120President ial", "raw_count": 212, "count": 212, "decode_str": " Presidential"} -{"id": 46718, "token": "\u0120massless", "merges": "\u0120mass less", "raw_count": 212, "count": 212, "decode_str": " massless"} -{"id": 42753, "token": "\u0120Dante", "merges": "\u0120D ante", "raw_count": 212, "count": 212, "decode_str": " Dante"} -{"id": 24605, "token": "\u0120Cuba", "merges": "\u0120Cub a", "raw_count": 212, "count": 212, "decode_str": " Cuba"} -{"id": 41234, "token": "\u0120genotyping", "merges": "\u0120gen otyping", "raw_count": 213, "count": 213, "decode_str": " genotyping"} -{"id": 29912, "token": "\u0120Bristol", "merges": "\u0120B ristol", "raw_count": 213, "count": 213, "decode_str": " Bristol"} -{"id": 32845, "token": ")}=", "merges": ")} =", "raw_count": 213, "count": 213, "decode_str": ")}="} -{"id": 33026, "token": "^-$", "merges": "^- $", "raw_count": 213, "count": 213, "decode_str": "^-$"} -{"id": 49054, "token": "\u0120copolymers", "merges": "\u0120cop olymers", "raw_count": 214, "count": 214, "decode_str": " copolymers"} -{"id": 17111, "token": "\u0120Ukraine", "merges": "\u0120Uk raine", "raw_count": 214, "count": 214, "decode_str": " Ukraine"} -{"id": 45576, "token": "carbonyl", "merges": "carbon yl", "raw_count": 214, "count": 214, "decode_str": "carbonyl"} -{"id": 46972, "token": "\u0120Gloria", "merges": "\u0120Glor ia", "raw_count": 214, "count": 214, "decode_str": " Gloria"} -{"id": 46440, "token": "\u0120\u00ce\u00b1\u00cf\u0122\u00ce\u00bf", "merges": "\u0120\u00ce\u00b1 \u00cf\u0122\u00ce\u00bf", "raw_count": 214, "count": 214, "decode_str": " \u03b1\u03c0\u03bf"} -{"id": 49531, "token": "\u0120Truman", "merges": "\u0120Tr uman", "raw_count": 214, "count": 214, "decode_str": " Truman"} -{"id": 38444, "token": "\u00cf\u0125\u00ce\u00b7\u00cf\u0124", "merges": "\u00cf\u0125\u00ce\u00b7 \u00cf\u0124", "raw_count": 214, "count": 214, "decode_str": "\u03c3\u03b7\u03c2"} -{"id": 10967, "token": "\u0120\u00c2\u0142\u00c2\u0142", "merges": "\u0120 \u00c2\u0142\u00c2\u0142", "raw_count": 160, "count": 214, "decode_str": " \u00a0\u00a0"} -{"id": 30148, "token": "$_{\\", "merges": "$ _{\\", "raw_count": 214, "count": 214, "decode_str": "$_{\\"} -{"id": 45490, "token": "\u0120Jed", "merges": "\u0120J ed", "raw_count": 214, "count": 214, "decode_str": " Jed"} -{"id": 47073, "token": "\u0120degenerative", "merges": "\u0120degener ative", "raw_count": 215, "count": 215, "decode_str": " degenerative"} -{"id": 32436, "token": "\u0120Napoleon", "merges": "\u0120Napole on", "raw_count": 215, "count": 215, "decode_str": " Napoleon"} -{"id": 30656, "token": "\u00cf\u0126\u00ce\u00b1\u00ce\u00b9", "merges": "\u00cf\u0126 \u00ce\u00b1\u00ce\u00b9", "raw_count": 215, "count": 215, "decode_str": "\u03c4\u03b1\u03b9"} -{"id": 48337, "token": "\u0120G\u00c3\u00b6", "merges": "\u0120G \u00c3\u00b6", "raw_count": 215, "count": 215, "decode_str": " G\u00f6"} -{"id": 22969, "token": "=\\{", "merges": "=\\ {", "raw_count": 215, "count": 215, "decode_str": "=\\{"} -{"id": 36500, "token": "\u0120pneumoniae", "merges": "\u0120pneumonia e", "raw_count": 216, "count": 216, "decode_str": " pneumoniae"} -{"id": 42894, "token": "\u0120Sheffield", "merges": "\u0120She ffield", "raw_count": 216, "count": 216, "decode_str": " Sheffield"} -{"id": 31109, "token": "\u0120motility", "merges": "\u0120mot ility", "raw_count": 216, "count": 216, "decode_str": " motility"} -{"id": 14553, "token": "$).", "merges": "$ ).", "raw_count": 216, "count": 216, "decode_str": "$)."} -{"id": 42264, "token": "nonatomic", "merges": "non atomic", "raw_count": 217, "count": 217, "decode_str": "nonatomic"} -{"id": 36532, "token": "\u0120Randy", "merges": "\u0120R andy", "raw_count": 217, "count": 217, "decode_str": " Randy"} -{"id": 36177, "token": "\u0120fr\u00c3\u00a5n", "merges": "\u0120fr\u00c3\u00a5 n", "raw_count": 217, "count": 217, "decode_str": " fr\u00e5n"} -{"id": 42735, "token": "\u0120Mick", "merges": "\u0120M ick", "raw_count": 217, "count": 217, "decode_str": " Mick"} -{"id": 46977, "token": "\u0120\u00d7\u0137", "merges": "\u0120\u00d7 \u0137", "raw_count": 217, "count": 217, "decode_str": " \u05d5"} -{"id": 29721, "token": "\u0120homosexual", "merges": "\u0120hom osexual", "raw_count": 218, "count": 218, "decode_str": " homosexual"} -{"id": 38476, "token": "\u0120Stockholm", "merges": "\u0120Stock holm", "raw_count": 218, "count": 218, "decode_str": " Stockholm"} -{"id": 42110, "token": "\u0120epitopes", "merges": "\u0120epit opes", "raw_count": 218, "count": 218, "decode_str": " epitopes"} -{"id": 43525, "token": "\u0120hypergly", "merges": "\u0120hyper gly", "raw_count": 218, "count": 218, "decode_str": " hypergly"} -{"id": 41678, "token": "\u0120Rodgers", "merges": "\u0120Rod gers", "raw_count": 218, "count": 218, "decode_str": " Rodgers"} -{"id": 41624, "token": "\u0120Luckily", "merges": "\u0120Luck ily", "raw_count": 218, "count": 218, "decode_str": " Luckily"} -{"id": 47572, "token": "\u0120Dix", "merges": "\u0120D ix", "raw_count": 218, "count": 218, "decode_str": " Dix"} -{"id": 50344, "token": "\u00e2\u0136\u00a3", "merges": "\u00e2\u0136 \u00a3", "raw_count": 218, "count": 218, "decode_str": "\u2523"} -{"id": 20868, "token": "%\"}", "merges": "% \"}", "raw_count": 218, "count": 218, "decode_str": "%\"}"} -{"id": 37689, "token": "\u0120breastfeeding", "merges": "\u0120breast feeding", "raw_count": 219, "count": 219, "decode_str": " breastfeeding"} -{"id": 46143, "token": "\u0120europ\u00c3\u00a9enne", "merges": "\u0120europ\u00c3\u00a9 enne", "raw_count": 219, "count": 219, "decode_str": " europ\u00e9enne"} -{"id": 36796, "token": "\u0120\u00cf\u0126\u00ce\u00b1", "merges": "\u0120\u00cf\u0126 \u00ce\u00b1", "raw_count": 219, "count": 219, "decode_str": " \u03c4\u03b1"} -{"id": 42860, "token": "\u0120AKI", "merges": "\u0120AK I", "raw_count": 219, "count": 219, "decode_str": " AKI"} -{"id": 18002, "token": "bigr", "merges": "big r", "raw_count": 219, "count": 219, "decode_str": "bigr"} -{"id": 54269, "token": "\u00e9\u0138\u0134", "merges": "\u00e9\u0138 \u0134", "raw_count": 219, "count": 219, "decode_str": "\u9592"} -{"id": 41915, "token": "}&\\", "merges": "} &\\", "raw_count": 219, "count": 219, "decode_str": "}&\\"} -{"id": 50670, "token": "\u00e5\u0125\u00b1", "merges": "\u00e5\u0125 \u00b1", "raw_count": 219, "count": 219, "decode_str": "\u50f1"} -{"id": 49419, "token": "\u0120Heidegger", "merges": "\u0120He idegger", "raw_count": 220, "count": 220, "decode_str": " Heidegger"} -{"id": 16301, "token": "\u0120Missouri", "merges": "\u0120Miss ouri", "raw_count": 220, "count": 220, "decode_str": " Missouri"} -{"id": 17297, "token": "\u0120cytotox", "merges": "\u0120cyt otox", "raw_count": 30, "count": 220, "decode_str": " cytotox"} -{"id": 36227, "token": "\u0120kunn", "merges": "\u0120k unn", "raw_count": 78, "count": 220, "decode_str": " kunn"} -{"id": 9256, "token": "\u0120Iraq", "merges": "\u0120Ira q", "raw_count": 189, "count": 220, "decode_str": " Iraq"} -{"id": 49179, "token": "\u0120methylated", "merges": "\u0120methyl ated", "raw_count": 221, "count": 221, "decode_str": " methylated"} -{"id": 43297, "token": "\u0120presidente", "merges": "\u0120president e", "raw_count": 221, "count": 221, "decode_str": " presidente"} -{"id": 29629, "token": "\u0120Rangers", "merges": "\u0120R angers", "raw_count": 221, "count": 221, "decode_str": " Rangers"} -{"id": 47060, "token": "\u0120hanno", "merges": "\u0120h anno", "raw_count": 221, "count": 221, "decode_str": " hanno"} -{"id": 42009, "token": "\u0120Saul", "merges": "\u0120Sa ul", "raw_count": 221, "count": 221, "decode_str": " Saul"} -{"id": 23591, "token": "\u0120IGF", "merges": "\u0120I GF", "raw_count": 221, "count": 221, "decode_str": " IGF"} -{"id": 49035, "token": "\u0120\u00c3\u013c", "merges": "\u0120\u00c3 \u013c", "raw_count": 221, "count": 221, "decode_str": " \u00da"} -{"id": 13941, "token": ")\\,", "merges": ")\\ ,", "raw_count": 221, "count": 221, "decode_str": ")\\,"} -{"id": 22119, "token": "\u0120Pittsburgh", "merges": "\u0120Pitts burgh", "raw_count": 222, "count": 222, "decode_str": " Pittsburgh"} -{"id": 35244, "token": "\u0120vascul", "merges": "\u0120vas cul", "raw_count": 222, "count": 222, "decode_str": " vascul"} -{"id": 36604, "token": "\u0120Brett", "merges": "\u0120B rett", "raw_count": 222, "count": 222, "decode_str": " Brett"} -{"id": 36364, "token": "\u0120Alger", "merges": "\u0120Al ger", "raw_count": 222, "count": 222, "decode_str": " Alger"} -{"id": 49648, "token": "\u0120Huh", "merges": "\u0120H uh", "raw_count": 222, "count": 222, "decode_str": " Huh"} -{"id": 38082, "token": "\u0120BMD", "merges": "\u0120B MD", "raw_count": 222, "count": 222, "decode_str": " BMD"} -{"id": 28832, "token": "\u00cf\u0123\u00cf\u012e", "merges": "\u00cf\u0123 \u00cf\u012e", "raw_count": 222, "count": 222, "decode_str": "\u03c1\u03cc"} -{"id": 48704, "token": "\u0120Proteins", "merges": "\u0120Prote ins", "raw_count": 223, "count": 223, "decode_str": " Proteins"} -{"id": 21249, "token": "\u0120Brooklyn", "merges": "\u0120Brook lyn", "raw_count": 223, "count": 223, "decode_str": " Brooklyn"} -{"id": 38196, "token": "\u0120pa\u00c3\u0143ses", "merges": "\u0120pa \u00c3\u0143ses", "raw_count": 223, "count": 223, "decode_str": " pa\u00edses"} -{"id": 41017, "token": "\u0120Quite", "merges": "\u0120Qu ite", "raw_count": 223, "count": 223, "decode_str": " Quite"} -{"id": 37138, "token": "\u0120Pruss", "merges": "\u0120Pr uss", "raw_count": 223, "count": 223, "decode_str": " Pruss"} -{"id": 20242, "token": "\u0120Christianity", "merges": "\u0120Christian ity", "raw_count": 224, "count": 224, "decode_str": " Christianity"} -{"id": 41073, "token": "\u0120Billboard", "merges": "\u0120Bill board", "raw_count": 224, "count": 224, "decode_str": " Billboard"} -{"id": 19918, "token": "\u0120cytokine", "merges": "\u0120cytok ine", "raw_count": 224, "count": 224, "decode_str": " cytokine"} -{"id": 47829, "token": "\u0120Adri", "merges": "\u0120Ad ri", "raw_count": 224, "count": 224, "decode_str": " Adri"} -{"id": 21284, "token": "FPar", "merges": "F Par", "raw_count": 224, "count": 224, "decode_str": "FPar"} -{"id": 49635, "token": "\u0120p\u00c3\u00a4", "merges": "\u0120p \u00c3\u00a4", "raw_count": 224, "count": 224, "decode_str": " p\u00e4"} -{"id": 45300, "token": "\u0120neonates", "merges": "\u0120neon ates", "raw_count": 225, "count": 225, "decode_str": " neonates"} -{"id": 34981, "token": "\u0120Forty", "merges": "\u0120Fort y", "raw_count": 225, "count": 225, "decode_str": " Forty"} -{"id": 34592, "token": "\u0120Petersburg", "merges": "\u0120Peters burg", "raw_count": 226, "count": 226, "decode_str": " Petersburg"} -{"id": 24713, "token": ")\u00e2\u0122\u0135", "merges": ") \u00e2\u0122\u0135", "raw_count": 218, "count": 226, "decode_str": ")\u2013"} -{"id": 38377, "token": "\u00ce\u00b8\u00ce\u00b5", "merges": "\u00ce\u00b8 \u00ce\u00b5", "raw_count": 226, "count": 226, "decode_str": "\u03b8\u03b5"} -{"id": 47546, "token": "**^", "merges": "** ^", "raw_count": 226, "count": 226, "decode_str": "**^"} -{"id": 35497, "token": "\u0120OTHERWISE", "merges": "\u0120OTHER WISE", "raw_count": 227, "count": 227, "decode_str": " OTHERWISE"} -{"id": 46667, "token": "\u0120preseason", "merges": "\u0120pre season", "raw_count": 227, "count": 227, "decode_str": " preseason"} -{"id": 48270, "token": "\u0120Doctors", "merges": "\u0120Do ctors", "raw_count": 227, "count": 227, "decode_str": " Doctors"} -{"id": 46063, "token": "\u0120AMERICA", "merges": "\u0120AMER ICA", "raw_count": 227, "count": 227, "decode_str": " AMERICA"} -{"id": 42835, "token": "\u0120Windsor", "merges": "\u0120Wind sor", "raw_count": 227, "count": 227, "decode_str": " Windsor"} -{"id": 37500, "token": "\u0120\u00e0\u00a4\u00ae", "merges": "\u0120\u00e0\u00a4 \u00ae", "raw_count": 227, "count": 227, "decode_str": " \u092e"} -{"id": 39613, "token": "\u0120monolayer", "merges": "\u0120monol ayer", "raw_count": 228, "count": 228, "decode_str": " monolayer"} -{"id": 43263, "token": "\u0120amygdala", "merges": "\u0120amyg dala", "raw_count": 228, "count": 228, "decode_str": " amygdala"} -{"id": 30031, "token": "ViewById", "merges": "View ById", "raw_count": 46, "count": 228, "decode_str": "ViewById"} -{"id": 38076, "token": "\u0120Belf", "merges": "\u0120B elf", "raw_count": 112, "count": 228, "decode_str": " Belf"} -{"id": 38033, "token": "\u00d9\u0126\u00d9\u012b", "merges": "\u00d9\u0126 \u00d9\u012b", "raw_count": 228, "count": 228, "decode_str": "\u0644\u0649"} -{"id": 48433, "token": "\u00e2\u0122\u0133", "merges": "\u00e2\u0122 \u0133", "raw_count": 228, "count": 228, "decode_str": "\u2011"} -{"id": 34473, "token": "\u0120Hurricane", "merges": "\u0120Hur ricane", "raw_count": 229, "count": 229, "decode_str": " Hurricane"} -{"id": 33386, "token": "\u0120Arsenal", "merges": "\u0120Ar senal", "raw_count": 229, "count": 229, "decode_str": " Arsenal"} -{"id": 44930, "token": "\u0120nanost", "merges": "\u0120nan ost", "raw_count": 229, "count": 229, "decode_str": " nanost"} -{"id": 47066, "token": "\u0120Sussex", "merges": "\u0120Sus sex", "raw_count": 229, "count": 229, "decode_str": " Sussex"} -{"id": 8752, "token": "widehat", "merges": "wide hat", "raw_count": 229, "count": 229, "decode_str": "widehat"} -{"id": 48547, "token": "\u0120zich", "merges": "\u0120z ich", "raw_count": 229, "count": 229, "decode_str": " zich"} -{"id": 43202, "token": "\u0120Myc", "merges": "\u0120My c", "raw_count": 229, "count": 229, "decode_str": " Myc"} -{"id": 34641, "token": "\u0120Chancellor", "merges": "\u0120Ch ancellor", "raw_count": 230, "count": 230, "decode_str": " Chancellor"} -{"id": 40169, "token": "\u0120ORDERED", "merges": "\u0120ORDER ED", "raw_count": 230, "count": 230, "decode_str": " ORDERED"} -{"id": 28299, "token": "\u0120Buffalo", "merges": "\u0120Buff alo", "raw_count": 230, "count": 230, "decode_str": " Buffalo"} -{"id": 27238, "token": "\u0120Eddie", "merges": "\u0120Edd ie", "raw_count": 230, "count": 230, "decode_str": " Eddie"} -{"id": 49690, "token": "\u0120ihn", "merges": "\u0120i hn", "raw_count": 230, "count": 230, "decode_str": " ihn"} -{"id": 41783, "token": "\u00cf\u0125\u00ce\u00b5", "merges": "\u00cf\u0125 \u00ce\u00b5", "raw_count": 230, "count": 230, "decode_str": "\u03c3\u03b5"} -{"id": 1184, "token": "]\\]", "merges": "] \\]", "raw_count": 220, "count": 230, "decode_str": "]\\]"} -{"id": 29471, "token": "\u0120Fortunately", "merges": "\u0120F ortunately", "raw_count": 231, "count": 231, "decode_str": " Fortunately"} -{"id": 48851, "token": "Fortunately", "merges": "F ortunately", "raw_count": 231, "count": 231, "decode_str": "Fortunately"} -{"id": 20383, "token": "\u0120PARTICULAR", "merges": "\u0120PARTIC ULAR", "raw_count": 231, "count": 231, "decode_str": " PARTICULAR"} -{"id": 49445, "token": "\u0120Abdullah", "merges": "\u0120Abd ullah", "raw_count": 231, "count": 231, "decode_str": " Abdullah"} -{"id": 49028, "token": "\u0120Donovan", "merges": "\u0120Don ovan", "raw_count": 231, "count": 231, "decode_str": " Donovan"} -{"id": 47281, "token": "\u0120Fasc", "merges": "\u0120F asc", "raw_count": 231, "count": 231, "decode_str": " Fasc"} -{"id": 49099, "token": "\u00c3\u0143v", "merges": "\u00c3\u0143 v", "raw_count": 231, "count": 231, "decode_str": "\u00edv"} -{"id": 47706, "token": "\u0120Kingston", "merges": "\u0120King ston", "raw_count": 232, "count": 232, "decode_str": " Kingston"} -{"id": 18231, "token": "ellees", "merges": "elle es", "raw_count": 229, "count": 232, "decode_str": "ellees"} -{"id": 44518, "token": "\u0120Amend", "merges": "\u0120Am end", "raw_count": 232, "count": 232, "decode_str": " Amend"} -{"id": 15600, "token": "\u0120Christians", "merges": "\u0120Christ ians", "raw_count": 233, "count": 233, "decode_str": " Christians"} -{"id": 36090, "token": "\u0120Finnish", "merges": "\u0120Finn ish", "raw_count": 233, "count": 233, "decode_str": " Finnish"} -{"id": 42191, "token": "\u0120\u00cf\u0125\u00cf\u0126\u00ce\u00bf", "merges": "\u0120\u00cf\u0125 \u00cf\u0126\u00ce\u00bf", "raw_count": 233, "count": 233, "decode_str": " \u03c3\u03c4\u03bf"} -{"id": 40868, "token": "\u0120Pompe", "merges": "\u0120Pom pe", "raw_count": 233, "count": 233, "decode_str": " Pompe"} -{"id": 3891, "token": "\u0120(\\[", "merges": "\u0120( \\[", "raw_count": 233, "count": 233, "decode_str": " (\\["} -{"id": 36204, "token": "\u00ce\u00b9\u00ce\u00bf", "merges": "\u00ce\u00b9 \u00ce\u00bf", "raw_count": 233, "count": 233, "decode_str": "\u03b9\u03bf"} -{"id": 44829, "token": "\u0120\\%", "merges": "\u0120\\ %", "raw_count": 233, "count": 233, "decode_str": " \\%"} -{"id": 42388, "token": "\u0120progenitors", "merges": "\u0120progen itors", "raw_count": 234, "count": 234, "decode_str": " progenitors"} -{"id": 47309, "token": "\u0120bilayer", "merges": "\u0120bil ayer", "raw_count": 234, "count": 234, "decode_str": " bilayer"} -{"id": 25579, "token": "\u0120Chelsea", "merges": "\u0120Chel sea", "raw_count": 234, "count": 234, "decode_str": " Chelsea"} -{"id": 47877, "token": "\u0120Stanton", "merges": "\u0120St anton", "raw_count": 234, "count": 234, "decode_str": " Stanton"} -{"id": 30008, "token": "\u0120tr\u00c3\u00a8s", "merges": "\u0120tr \u00c3\u00a8s", "raw_count": 234, "count": 234, "decode_str": " tr\u00e8s"} -{"id": 42580, "token": "\u00e2\u0122\u0141", "merges": "\u00e2\u0122 \u0141", "raw_count": 234, "count": 234, "decode_str": "\u201f"} -{"id": 24419, "token": "\u0120Protest", "merges": "\u0120Pro test", "raw_count": 92, "count": 235, "decode_str": " Protest"} -{"id": 39897, "token": "\u0120parench", "merges": "\u0120pa rench", "raw_count": 235, "count": 235, "decode_str": " parench"} -{"id": 8798, "token": "amsmath", "merges": "ams math", "raw_count": 235, "count": 235, "decode_str": "amsmath"} -{"id": 45393, "token": "\u0120Dillon", "merges": "\u0120D illon", "raw_count": 235, "count": 235, "decode_str": " Dillon"} -{"id": 42006, "token": "\u0120Paula", "merges": "\u0120Pa ula", "raw_count": 235, "count": 235, "decode_str": " Paula"} -{"id": 42319, "token": "\u0120Clare", "merges": "\u0120Cl are", "raw_count": 235, "count": 235, "decode_str": " Clare"} -{"id": 24501, "token": "\u00c3\u0143an", "merges": "\u00c3\u0143 an", "raw_count": 235, "count": 235, "decode_str": "\u00edan"} -{"id": 33627, "token": "\u00cf\u0126\u00ce\u00ac", "merges": "\u00cf\u0126 \u00ce\u00ac", "raw_count": 235, "count": 235, "decode_str": "\u03c4\u03ac"} -{"id": 53008, "token": "\u00e7\u013e\u0140", "merges": "\u00e7\u013e \u0140", "raw_count": 235, "count": 235, "decode_str": "\u771e"} -{"id": 38360, "token": "\u0120anticancer", "merges": "\u0120antican cer", "raw_count": 236, "count": 236, "decode_str": " anticancer"} -{"id": 26469, "token": "\u0120Township", "merges": "\u0120Town ship", "raw_count": 236, "count": 236, "decode_str": " Township"} -{"id": 49066, "token": "\u0120afferent", "merges": "\u0120af ferent", "raw_count": 236, "count": 236, "decode_str": " afferent"} -{"id": 37714, "token": "\u0120antican", "merges": "\u0120ant ican", "raw_count": 0, "count": 236, "decode_str": " antican"} -{"id": 30447, "token": "\u0120kinases", "merges": "\u0120kin ases", "raw_count": 236, "count": 236, "decode_str": " kinases"} -{"id": 46644, "token": "\u0120Flores", "merges": "\u0120Fl ores", "raw_count": 236, "count": 236, "decode_str": " Flores"} -{"id": 33811, "token": "\u0120Amanda", "merges": "\u0120Am anda", "raw_count": 236, "count": 236, "decode_str": " Amanda"} -{"id": 35307, "token": "\u0120Gavin", "merges": "\u0120G avin", "raw_count": 236, "count": 236, "decode_str": " Gavin"} -{"id": 31143, "token": "\u0120Lions", "merges": "\u0120L ions", "raw_count": 236, "count": 236, "decode_str": " Lions"} -{"id": 14890, "token": "\u0120Iowa", "merges": "\u0120I owa", "raw_count": 236, "count": 236, "decode_str": " Iowa"} -{"id": 41436, "token": "\u0120Wir", "merges": "\u0120W ir", "raw_count": 236, "count": 236, "decode_str": " Wir"} -{"id": 48564, "token": "\u0120GPs", "merges": "\u0120G Ps", "raw_count": 236, "count": 236, "decode_str": " GPs"} -{"id": 50375, "token": "\u00e2\u0139\u0137", "merges": "\u00e2\u0139 \u0137", "raw_count": 236, "count": 236, "decode_str": "\u25d5"} -{"id": 50281, "token": "\u00ca\u00b0", "merges": "\u00ca \u00b0", "raw_count": 236, "count": 236, "decode_str": "\u02b0"} -{"id": 27791, "token": "\u0120phenotypic", "merges": "\u0120phen otypic", "raw_count": 237, "count": 237, "decode_str": " phenotypic"} -{"id": 30249, "token": "\u0120pathophys", "merges": "\u0120path ophys", "raw_count": 77, "count": 237, "decode_str": " pathophys"} -{"id": 30556, "token": "\u0120Halloween", "merges": "\u0120Hallow een", "raw_count": 237, "count": 237, "decode_str": " Halloween"} -{"id": 43889, "token": "\u0120Lafayette", "merges": "\u0120Laf ayette", "raw_count": 237, "count": 237, "decode_str": " Lafayette"} -{"id": 19160, "token": "\u0120Appeal", "merges": "\u0120Appe al", "raw_count": 237, "count": 237, "decode_str": " Appeal"} -{"id": 44438, "token": "\u0120Refuge", "merges": "\u0120Ref uge", "raw_count": 237, "count": 237, "decode_str": " Refuge"} -{"id": 20734, "token": "\u0120Denver", "merges": "\u0120Den ver", "raw_count": 237, "count": 237, "decode_str": " Denver"} -{"id": 9501, "token": "mathsf", "merges": "math sf", "raw_count": 237, "count": 237, "decode_str": "mathsf"} -{"id": 44248, "token": "\u0120Owens", "merges": "\u0120Ow ens", "raw_count": 237, "count": 237, "decode_str": " Owens"} -{"id": 28526, "token": "lvert", "merges": "l vert", "raw_count": 237, "count": 237, "decode_str": "lvert"} -{"id": 38132, "token": "):=", "merges": "): =", "raw_count": 237, "count": 237, "decode_str": "):="} -{"id": 53253, "token": "\u00e7\u00b1\u0132", "merges": "\u00e7\u00b1 \u0132", "raw_count": 237, "count": 237, "decode_str": "\u7c50"} -{"id": 36152, "token": "\u0120homozygous", "merges": "\u0120hom ozygous", "raw_count": 238, "count": 238, "decode_str": " homozygous"} -{"id": 35287, "token": "\u0120Southwest", "merges": "\u0120South west", "raw_count": 238, "count": 238, "decode_str": " Southwest"} -{"id": 32984, "token": "\u0120CIRCUIT", "merges": "\u0120CIR CUIT", "raw_count": 238, "count": 238, "decode_str": " CIRCUIT"} -{"id": 27540, "token": "\u0120Montana", "merges": "\u0120Mont ana", "raw_count": 238, "count": 238, "decode_str": " Montana"} -{"id": 41874, "token": "\u0120Somers", "merges": "\u0120S omers", "raw_count": 89, "count": 238, "decode_str": " Somers"} -{"id": 18806, "token": "\u0120\u00ce\u00ba\u00ce\u00b1\u00ce\u00b9", "merges": "\u0120\u00ce\u00ba \u00ce\u00b1\u00ce\u00b9", "raw_count": 238, "count": 238, "decode_str": " \u03ba\u03b1\u03b9"} -{"id": 15427, "token": "\u0120Oregon", "merges": "\u0120O regon", "raw_count": 238, "count": 238, "decode_str": " Oregon"} -{"id": 36546, "token": "\u0120Seoul", "merges": "\u0120Se oul", "raw_count": 238, "count": 238, "decode_str": " Seoul"} -{"id": 49524, "token": "\u0120Zag", "merges": "\u0120Z ag", "raw_count": 238, "count": 238, "decode_str": " Zag"} -{"id": 41620, "token": "\u00cf\u0123\u00ce\u0143", "merges": "\u00cf\u0123 \u00ce\u0143", "raw_count": 238, "count": 238, "decode_str": "\u03c1\u03ad"} -{"id": 25657, "token": "\u00e0\u00ab", "merges": "\u00e0 \u00ab", "raw_count": 185, "count": 238, "decode_str": "\ufffd"} -{"id": 21240, "token": "\u0120Chairman", "merges": "\u0120Chair man", "raw_count": 239, "count": 239, "decode_str": " Chairman"} -{"id": 37273, "token": "mspace", "merges": "ms pace", "raw_count": 239, "count": 239, "decode_str": "mspace"} -{"id": 42044, "token": "\u00cf\u0122\u00ce\u00b1", "merges": "\u00cf\u0122 \u00ce\u00b1", "raw_count": 239, "count": 239, "decode_str": "\u03c0\u03b1"} -{"id": 50143, "token": "Unmarshal", "merges": "Un marshal", "raw_count": 240, "count": 240, "decode_str": "Unmarshal"} -{"id": 27411, "token": "\u0120Athens", "merges": "\u0120Athe ns", "raw_count": 240, "count": 240, "decode_str": " Athens"} -{"id": 36312, "token": "\u0120Derek", "merges": "\u0120De rek", "raw_count": 240, "count": 240, "decode_str": " Derek"} -{"id": 33629, "token": "\u00cf\u0125\u00ce\u00b5\u00ce\u00b9", "merges": "\u00cf\u0125 \u00ce\u00b5\u00ce\u00b9", "raw_count": 240, "count": 240, "decode_str": "\u03c3\u03b5\u03b9"} -{"id": 34215, "token": "\u0120S\u00c3\u00a3o", "merges": "\u0120S \u00c3\u00a3o", "raw_count": 240, "count": 240, "decode_str": " S\u00e3o"} -{"id": 45655, "token": "\u0120Tina", "merges": "\u0120T ina", "raw_count": 240, "count": 240, "decode_str": " Tina"} -{"id": 52955, "token": "\u00e7\u013b\u0134", "merges": "\u00e7\u013b \u0134", "raw_count": 240, "count": 240, "decode_str": "\u7652"} -{"id": 25564, "token": "\u0120Caribbean", "merges": "\u0120Carib bean", "raw_count": 241, "count": 241, "decode_str": " Caribbean"} -{"id": 39388, "token": "\u0120contral", "merges": "\u0120cont ral", "raw_count": 146, "count": 241, "decode_str": " contral"} -{"id": 38308, "token": "\u0120Hearing", "merges": "\u0120H earing", "raw_count": 241, "count": 241, "decode_str": " Hearing"} -{"id": 49684, "token": "\u0120Lymph", "merges": "\u0120L ymph", "raw_count": 241, "count": 241, "decode_str": " Lymph"} -{"id": 37204, "token": "\u0120Kris", "merges": "\u0120K ris", "raw_count": 241, "count": 241, "decode_str": " Kris"} -{"id": 14614, "token": "\u0120Indiana", "merges": "\u0120Indian a", "raw_count": 242, "count": 242, "decode_str": " Indiana"} -{"id": 33572, "token": "\u0120Tigers", "merges": "\u0120Tig ers", "raw_count": 242, "count": 242, "decode_str": " Tigers"} -{"id": 44379, "token": "\u0120mucho", "merges": "\u0120much o", "raw_count": 242, "count": 242, "decode_str": " mucho"} -{"id": 45090, "token": "\u0120Milky", "merges": "\u0120Mil ky", "raw_count": 242, "count": 242, "decode_str": " Milky"} -{"id": 49098, "token": "\u0120Huntington", "merges": "\u0120Hunting ton", "raw_count": 243, "count": 243, "decode_str": " Huntington"} -{"id": 17165, "token": "\u0120Olympics", "merges": "\u0120Olymp ics", "raw_count": 243, "count": 243, "decode_str": " Olympics"} -{"id": 45572, "token": "\u0120Brennan", "merges": "\u0120Bren nan", "raw_count": 243, "count": 243, "decode_str": " Brennan"} -{"id": 24175, "token": "uparrow", "merges": "up arrow", "raw_count": 244, "count": 244, "decode_str": "uparrow"} -{"id": 47918, "token": "\u0120Dental", "merges": "\u0120D ental", "raw_count": 244, "count": 244, "decode_str": " Dental"} -{"id": 38438, "token": "ORAND", "merges": "OR AND", "raw_count": 206, "count": 244, "decode_str": "ORAND"} -{"id": 29250, "token": "\u0120Laid", "merges": "\u0120La id", "raw_count": 244, "count": 244, "decode_str": " Laid"} -{"id": 19377, "token": "springframework", "merges": "spring framework", "raw_count": 245, "count": 245, "decode_str": "springframework"} -{"id": 44050, "token": "\u0120immunotherapy", "merges": "\u0120immun otherapy", "raw_count": 245, "count": 245, "decode_str": " immunotherapy"} -{"id": 28038, "token": "\u0120angiogenesis", "merges": "\u0120angi ogenesis", "raw_count": 245, "count": 245, "decode_str": " angiogenesis"} -{"id": 47831, "token": "\u0120Christina", "merges": "\u0120Christ ina", "raw_count": 245, "count": 245, "decode_str": " Christina"} -{"id": 48956, "token": "olinergic", "merges": "olin ergic", "raw_count": 245, "count": 245, "decode_str": "olinergic"} -{"id": 41429, "token": "\u0120Findings", "merges": "\u0120Find ings", "raw_count": 245, "count": 245, "decode_str": " Findings"} -{"id": 37241, "token": "\u0120k\u00c3\u00b6nnen", "merges": "\u0120k\u00c3\u00b6nn en", "raw_count": 245, "count": 245, "decode_str": " k\u00f6nnen"} -{"id": 16869, "token": "\u0120Indians", "merges": "\u0120Ind ians", "raw_count": 245, "count": 245, "decode_str": " Indians"} -{"id": 40592, "token": "\u0120Steele", "merges": "\u0120Ste ele", "raw_count": 245, "count": 245, "decode_str": " Steele"} -{"id": 49665, "token": "\u0120Abrams", "merges": "\u0120Abr ams", "raw_count": 245, "count": 245, "decode_str": " Abrams"} -{"id": 44057, "token": "\u0120Essex", "merges": "\u0120Es sex", "raw_count": 245, "count": 245, "decode_str": " Essex"} -{"id": 42898, "token": "\u0120ChIP", "merges": "\u0120Ch IP", "raw_count": 245, "count": 245, "decode_str": " ChIP"} -{"id": 52875, "token": "\u00e7\u0136\u00af", "merges": "\u00e7\u0136 \u00af", "raw_count": 245, "count": 245, "decode_str": "\u752f"} -{"id": 7294, "token": "}}^", "merges": "}} ^", "raw_count": 245, "count": 245, "decode_str": "}}^"} -{"id": 13162, "token": "\u0120Consequently", "merges": "\u0120Con sequently", "raw_count": 246, "count": 246, "decode_str": " Consequently"} -{"id": 49905, "token": "\u0120Nass", "merges": "\u0120N ass", "raw_count": 246, "count": 246, "decode_str": " Nass"} -{"id": 8633, "token": "}\\,", "merges": "}\\ ,", "raw_count": 246, "count": 246, "decode_str": "}\\,"} -{"id": 41813, "token": "\u0120Brunswick", "merges": "\u0120Brun swick", "raw_count": 247, "count": 247, "decode_str": " Brunswick"} -{"id": 28975, "token": "textnormal", "merges": "text normal", "raw_count": 247, "count": 247, "decode_str": "textnormal"} -{"id": 43978, "token": "ciparum", "merges": "cip arum", "raw_count": 189, "count": 247, "decode_str": "ciparum"} -{"id": 42948, "token": "\u0120Karn", "merges": "\u0120K arn", "raw_count": 247, "count": 247, "decode_str": " Karn"} -{"id": 21119, "token": "\u0120f\u00c3\u00b6", "merges": "\u0120f \u00c3\u00b6", "raw_count": 188, "count": 247, "decode_str": " f\u00f6"} -{"id": 48893, "token": "\u0120Determination", "merges": "\u0120Determ ination", "raw_count": 248, "count": 248, "decode_str": " Determination"} -{"id": 37495, "token": "\u0120Conclusion", "merges": "\u0120Con clusion", "raw_count": 248, "count": 248, "decode_str": " Conclusion"} -{"id": 23050, "token": "\u0120Nevada", "merges": "\u0120Nev ada", "raw_count": 248, "count": 248, "decode_str": " Nevada"} -{"id": 37839, "token": "\u0120Wrest", "merges": "\u0120W rest", "raw_count": 49, "count": 248, "decode_str": " Wrest"} -{"id": 47204, "token": "\u0120ellos", "merges": "\u0120ell os", "raw_count": 248, "count": 248, "decode_str": " ellos"} -{"id": 47086, "token": "\u0120heme", "merges": "\u0120he me", "raw_count": 248, "count": 248, "decode_str": " heme"} -{"id": 33599, "token": "\u0120inoculated", "merges": "\u0120inoc ulated", "raw_count": 249, "count": 249, "decode_str": " inoculated"} -{"id": 43107, "token": "\u0120Rivera", "merges": "\u0120River a", "raw_count": 249, "count": 249, "decode_str": " Rivera"} -{"id": 39605, "token": "\u0120Leeds", "merges": "\u0120Le eds", "raw_count": 249, "count": 249, "decode_str": " Leeds"} -{"id": 48555, "token": "\u0120Kirby", "merges": "\u0120Kir by", "raw_count": 249, "count": 249, "decode_str": " Kirby"} -{"id": 27006, "token": "\u0120Allah", "merges": "\u0120All ah", "raw_count": 249, "count": 249, "decode_str": " Allah"} -{"id": 44946, "token": "\u0120Pence", "merges": "\u0120P ence", "raw_count": 249, "count": 249, "decode_str": " Pence"} -{"id": 35069, "token": "\u0120RAF", "merges": "\u0120R AF", "raw_count": 249, "count": 249, "decode_str": " RAF"} -{"id": 42168, "token": "\u0120CMV", "merges": "\u0120CM V", "raw_count": 249, "count": 249, "decode_str": " CMV"} -{"id": 50385, "token": "\u00e3\u0122\u0125", "merges": "\u00e3\u0122 \u0125", "raw_count": 249, "count": 249, "decode_str": "\u3003"} -{"id": 51355, "token": "\u00e5\u00a7\u012b", "merges": "\u00e5\u00a7 \u012b", "raw_count": 249, "count": 249, "decode_str": "\u59c9"} -{"id": 26846, "token": "\u0120Birmingham", "merges": "\u0120B irmingham", "raw_count": 250, "count": 250, "decode_str": " Birmingham"} -{"id": 49034, "token": "\u0120testis", "merges": "\u0120test is", "raw_count": 250, "count": 250, "decode_str": " testis"} -{"id": 46801, "token": "\u0120McCoy", "merges": "\u0120McC oy", "raw_count": 250, "count": 250, "decode_str": " McCoy"} -{"id": 49318, "token": "\u0120Moody", "merges": "\u0120Mood y", "raw_count": 250, "count": 250, "decode_str": " Moody"} -{"id": 44499, "token": "\u0120Hegel", "merges": "\u0120He gel", "raw_count": 250, "count": 250, "decode_str": " Hegel"} -{"id": 33533, "token": "\u0120Negro", "merges": "\u0120Neg ro", "raw_count": 250, "count": 250, "decode_str": " Negro"} -{"id": 33164, "token": "\u0120Bcl", "merges": "\u0120B cl", "raw_count": 250, "count": 250, "decode_str": " Bcl"} -{"id": 48263, "token": "\u0120harboring", "merges": "\u0120harbor ing", "raw_count": 251, "count": 251, "decode_str": " harboring"} -{"id": 47944, "token": "\u0120Jorge", "merges": "\u0120J orge", "raw_count": 251, "count": 251, "decode_str": " Jorge"} -{"id": 38690, "token": "\u0120Emir", "merges": "\u0120Em ir", "raw_count": 49, "count": 251, "decode_str": " Emir"} -{"id": 42602, "token": "\u0120Neal", "merges": "\u0120Ne al", "raw_count": 251, "count": 251, "decode_str": " Neal"} -{"id": 48596, "token": "\u0120Wyn", "merges": "\u0120W yn", "raw_count": 251, "count": 251, "decode_str": " Wyn"} -{"id": 47841, "token": "\u0120Starbucks", "merges": "\u0120Star bucks", "raw_count": 252, "count": 252, "decode_str": " Starbucks"} -{"id": 32918, "token": "\u0120microtub", "merges": "\u0120micro tub", "raw_count": 151, "count": 252, "decode_str": " microtub"} -{"id": 39387, "token": "\u0120androgen", "merges": "\u0120and rogen", "raw_count": 252, "count": 252, "decode_str": " androgen"} -{"id": 37228, "token": "\u0120Chester", "merges": "\u0120Che ster", "raw_count": 252, "count": 252, "decode_str": " Chester"} -{"id": 31955, "token": "\u0120Geneva", "merges": "\u0120Gen eva", "raw_count": 252, "count": 252, "decode_str": " Geneva"} -{"id": 18785, "token": "\u0120TGF", "merges": "\u0120T GF", "raw_count": 252, "count": 252, "decode_str": " TGF"} -{"id": 43447, "token": "\u0120Bav", "merges": "\u0120B av", "raw_count": 252, "count": 252, "decode_str": " Bav"} -{"id": 46083, "token": "\u0120*);", "merges": "\u0120* );", "raw_count": 252, "count": 252, "decode_str": " *);"} -{"id": 52466, "token": "\u00e6\u00b0\u00be", "merges": "\u00e6\u00b0 \u00be", "raw_count": 252, "count": 252, "decode_str": "\u6c3e"} -{"id": 50285, "token": "\u00cb\u012d", "merges": "\u00cb \u012d", "raw_count": 252, "count": 252, "decode_str": "\u02cb"} -{"id": 47040, "token": "\u0120Lucia", "merges": "\u0120Luc ia", "raw_count": 253, "count": 253, "decode_str": " Lucia"} -{"id": 43623, "token": "\u0120Paso", "merges": "\u0120Pas o", "raw_count": 253, "count": 253, "decode_str": " Paso"} -{"id": 23641, "token": "\u0120LGBT", "merges": "\u0120L GBT", "raw_count": 253, "count": 253, "decode_str": " LGBT"} -{"id": 34299, "token": "\u00cf\u0123\u00ce\u00af", "merges": "\u00cf\u0123 \u00ce\u00af", "raw_count": 253, "count": 253, "decode_str": "\u03c1\u03af"} -{"id": 39117, "token": "\u0120Thy", "merges": "\u0120Th y", "raw_count": 253, "count": 253, "decode_str": " Thy"} -{"id": 50357, "token": "\u00e2\u0138\u0127", "merges": "\u00e2\u0138 \u0127", "raw_count": 253, "count": 253, "decode_str": "\u2585"} -{"id": 47622, "token": "\u0120reticulum", "merges": "\u0120reticul um", "raw_count": 254, "count": 254, "decode_str": " reticulum"} -{"id": 37783, "token": "\u0120Panama", "merges": "\u0120Pan ama", "raw_count": 254, "count": 254, "decode_str": " Panama"} -{"id": 47442, "token": "\u0120Gert", "merges": "\u0120G ert", "raw_count": 254, "count": 254, "decode_str": " Gert"} -{"id": 26794, "token": "\u0120Nucl", "merges": "\u0120N ucl", "raw_count": 254, "count": 254, "decode_str": " Nucl"} -{"id": 17840, "token": "^{*", "merges": "^{ *", "raw_count": 254, "count": 254, "decode_str": "^{*"} -{"id": 32668, "token": "\u0120Investig", "merges": "\u0120Invest ig", "raw_count": 255, "count": 255, "decode_str": " Investig"} -{"id": 41583, "token": "\u0120Seeing", "merges": "\u0120See ing", "raw_count": 255, "count": 255, "decode_str": " Seeing"} -{"id": 49134, "token": "\u0120Bronze", "merges": "\u0120Bron ze", "raw_count": 255, "count": 255, "decode_str": " Bronze"} -{"id": 49713, "token": "Saharan", "merges": "Sah aran", "raw_count": 255, "count": 255, "decode_str": "Saharan"} -{"id": 50061, "token": "\u0120Boeh", "merges": "\u0120Bo eh", "raw_count": 255, "count": 255, "decode_str": " Boeh"} -{"id": 44261, "token": "\u0120Cork", "merges": "\u0120C ork", "raw_count": 255, "count": 255, "decode_str": " Cork"} -{"id": 4299, "token": "\u0120[**", "merges": "\u0120[ **", "raw_count": 255, "count": 255, "decode_str": " [**"} -{"id": 29670, "token": "operatively", "merges": "oper atively", "raw_count": 200, "count": 256, "decode_str": "operatively"} -{"id": 43853, "token": "\u0120lymphoid", "merges": "\u0120lymph oid", "raw_count": 256, "count": 256, "decode_str": " lymphoid"} -{"id": 27741, "token": "\u0120Florence", "merges": "\u0120Fl orence", "raw_count": 256, "count": 256, "decode_str": " Florence"} -{"id": 31519, "token": "\u0120Bulgar", "merges": "\u0120Bul gar", "raw_count": 90, "count": 256, "decode_str": " Bulgar"} -{"id": 25628, "token": "\u0120\u00cf\u0126\u00ce\u00b7\u00ce\u00bd", "merges": "\u0120\u00cf\u0126\u00ce\u00b7 \u00ce\u00bd", "raw_count": 256, "count": 256, "decode_str": " \u03c4\u03b7\u03bd"} -{"id": 40076, "token": "\u0120larval", "merges": "\u0120lar val", "raw_count": 256, "count": 256, "decode_str": " larval"} -{"id": 26266, "token": "\u0120fr\u00c3\u00a5", "merges": "\u0120fr \u00c3\u00a5", "raw_count": 39, "count": 256, "decode_str": " fr\u00e5"} -{"id": 43702, "token": "\u0120Lack", "merges": "\u0120L ack", "raw_count": 256, "count": 256, "decode_str": " Lack"} -{"id": 22747, "token": "\u0120$<", "merges": "\u0120$ <", "raw_count": 234, "count": 256, "decode_str": " $<"} -{"id": 32821, "token": "\u00e2\u0122\u0135\u00e2\u0122\u0135\u00e2\u0122\u0135\u00e2\u0122\u0135\u00e2\u0122\u0135\u00e2\u0122\u0135\u00e2\u0122\u0135\u00e2\u0122\u0135", "merges": "\u00e2\u0122\u0135\u00e2\u0122\u0135\u00e2\u0122\u0135\u00e2\u0122\u0135 \u00e2\u0122\u0135\u00e2\u0122\u0135\u00e2\u0122\u0135\u00e2\u0122\u0135", "raw_count": 257, "count": 257, "decode_str": "\u2013\u2013\u2013\u2013\u2013\u2013\u2013\u2013"} -{"id": 29357, "token": "\u0120vesicles", "merges": "\u0120ves icles", "raw_count": 257, "count": 257, "decode_str": " vesicles"} -{"id": 27199, "token": "\u0120Broadway", "merges": "\u0120Broad way", "raw_count": 257, "count": 257, "decode_str": " Broadway"} -{"id": 39132, "token": "\u0120cleaved", "merges": "\u0120cle aved", "raw_count": 257, "count": 257, "decode_str": " cleaved"} -{"id": 49813, "token": "\u0120Kelley", "merges": "\u0120Kel ley", "raw_count": 257, "count": 257, "decode_str": " Kelley"} -{"id": 46985, "token": "\u0120Lans", "merges": "\u0120L ans", "raw_count": 257, "count": 257, "decode_str": " Lans"} -{"id": 30949, "token": "\u0120MCF", "merges": "\u0120M CF", "raw_count": 257, "count": 257, "decode_str": " MCF"} -{"id": 28827, "token": "\u0120COPYRIGHT", "merges": "\u0120COP YRIGHT", "raw_count": 258, "count": 258, "decode_str": " COPYRIGHT"} -{"id": 42928, "token": "\u0120Compton", "merges": "\u0120Com pton", "raw_count": 258, "count": 258, "decode_str": " Compton"} -{"id": 49226, "token": "\u0120Husband", "merges": "\u0120Hus band", "raw_count": 258, "count": 258, "decode_str": " Husband"} -{"id": 28518, "token": "\u0120Hannah", "merges": "\u0120H annah", "raw_count": 258, "count": 258, "decode_str": " Hannah"} -{"id": 18257, "token": ">();", "merges": "> ();", "raw_count": 184, "count": 258, "decode_str": ">();"} -{"id": 28876, "token": "\\|_", "merges": "\\| _", "raw_count": 258, "count": 258, "decode_str": "\\|_"} -{"id": 38311, "token": "\u0120asymptotically", "merges": "\u0120asympt otically", "raw_count": 259, "count": 259, "decode_str": " asymptotically"} -{"id": 22808, "token": "\u0120Liverpool", "merges": "\u0120Liver pool", "raw_count": 259, "count": 259, "decode_str": " Liverpool"} -{"id": 38007, "token": "\u0120Parish", "merges": "\u0120Par ish", "raw_count": 259, "count": 259, "decode_str": " Parish"} -{"id": 41713, "token": "oxylin", "merges": "oxyl in", "raw_count": 259, "count": 259, "decode_str": "oxylin"} -{"id": 40212, "token": "\u0120Salad", "merges": "\u0120Sal ad", "raw_count": 259, "count": 259, "decode_str": " Salad"} -{"id": 46130, "token": "rbrace", "merges": "r brace", "raw_count": 259, "count": 259, "decode_str": "rbrace"} -{"id": 35334, "token": "\u0120Chern", "merges": "\u0120C hern", "raw_count": 259, "count": 259, "decode_str": " Chern"} -{"id": 50145, "token": "\u0120circumferential", "merges": "\u0120circum ferential", "raw_count": 260, "count": 260, "decode_str": " circumferential"} -{"id": 50098, "token": "\u0120cardiomyopathy", "merges": "\u0120cardiomy opathy", "raw_count": 260, "count": 260, "decode_str": " cardiomyopathy"} -{"id": 41871, "token": "\u0120Regulations", "merges": "\u0120Reg ulations", "raw_count": 260, "count": 260, "decode_str": " Regulations"} -{"id": 22437, "token": "\u0120Egyptian", "merges": "\u0120Egypt ian", "raw_count": 260, "count": 260, "decode_str": " Egyptian"} -{"id": 28955, "token": "\u0120Napole", "merges": "\u0120Nap ole", "raw_count": 45, "count": 260, "decode_str": " Napole"} -{"id": 46612, "token": "\u0120Lilly", "merges": "\u0120L illy", "raw_count": 260, "count": 260, "decode_str": " Lilly"} -{"id": 29322, "token": "\u0120Filed", "merges": "\u0120F iled", "raw_count": 260, "count": 260, "decode_str": " Filed"} -{"id": 41833, "token": "\u0120Niss", "merges": "\u0120N iss", "raw_count": 80, "count": 260, "decode_str": " Niss"} -{"id": 48614, "token": "\u00ce\u00ba\u00ce\u00b1", "merges": "\u00ce\u00ba \u00ce\u00b1", "raw_count": 260, "count": 260, "decode_str": "\u03ba\u03b1"} -{"id": 30527, "token": "\u0120kDa", "merges": "\u0120k Da", "raw_count": 260, "count": 260, "decode_str": " kDa"} -{"id": 35098, "token": "\u0120BSA", "merges": "\u0120B SA", "raw_count": 260, "count": 260, "decode_str": " BSA"} -{"id": 23719, "token": "\u0120ApJ", "merges": "\u0120Ap J", "raw_count": 260, "count": 260, "decode_str": " ApJ"} -{"id": 12136, "token": "\u00c2\u00be", "merges": "\u00c2 \u00be", "raw_count": 260, "count": 260, "decode_str": "\u00be"} -{"id": 42427, "token": "\u0120Revolutionary", "merges": "\u0120Revolution ary", "raw_count": 261, "count": 261, "decode_str": " Revolutionary"} -{"id": 29490, "token": "\u0120Northwest", "merges": "\u0120North west", "raw_count": 261, "count": 261, "decode_str": " Northwest"} -{"id": 33278, "token": "\u0120PROVIDED", "merges": "\u0120PROVID ED", "raw_count": 261, "count": 261, "decode_str": " PROVIDED"} -{"id": 28351, "token": "\u0120Former", "merges": "\u0120Form er", "raw_count": 261, "count": 261, "decode_str": " Former"} -{"id": 44851, "token": "{|\\", "merges": "{ |\\", "raw_count": 261, "count": 261, "decode_str": "{|\\"} -{"id": 185, "token": "\u0108", "merges": "NULL", "raw_count": 261, "count": 261, "decode_str": "\b"} -{"id": 45330, "token": "ETHERTYPE", "merges": "ETH ERTYPE", "raw_count": 262, "count": 262, "decode_str": "ETHERTYPE"} -{"id": 38343, "token": "\u0120Hamburg", "merges": "\u0120Hamb urg", "raw_count": 262, "count": 262, "decode_str": " Hamburg"} -{"id": 48077, "token": "\u0120Watkins", "merges": "\u0120Wat kins", "raw_count": 262, "count": 262, "decode_str": " Watkins"} -{"id": 35112, "token": "\u0120Pradesh", "merges": "\u0120Pr adesh", "raw_count": 262, "count": 262, "decode_str": " Pradesh"} -{"id": 15391, "token": "\u0120Kansas", "merges": "\u0120K ansas", "raw_count": 262, "count": 262, "decode_str": " Kansas"} -{"id": 40208, "token": "\u0120Papa", "merges": "\u0120Pap a", "raw_count": 262, "count": 262, "decode_str": " Papa"} -{"id": 22623, "token": "\u0120cytometry", "merges": "\u0120cyt ometry", "raw_count": 263, "count": 263, "decode_str": " cytometry"} -{"id": 49566, "token": "\u0120Disorders", "merges": "\u0120Dis orders", "raw_count": 263, "count": 263, "decode_str": " Disorders"} -{"id": 5577, "token": "mathfrak", "merges": "math frak", "raw_count": 263, "count": 263, "decode_str": "mathfrak"} -{"id": 31328, "token": "\u0120Hockey", "merges": "\u0120H ockey", "raw_count": 263, "count": 263, "decode_str": " Hockey"} -{"id": 46283, "token": "\u0120Cardi", "merges": "\u0120Card i", "raw_count": 263, "count": 263, "decode_str": " Cardi"} -{"id": 41268, "token": "\u0120USC", "merges": "\u0120US C", "raw_count": 263, "count": 263, "decode_str": " USC"} -{"id": 33047, "token": "\u0120//!", "merges": "\u0120// !", "raw_count": 263, "count": 263, "decode_str": " //!"} -{"id": 28592, "token": "\u0120\u00c2\u00b5m", "merges": "\u0120\u00c2\u00b5 m", "raw_count": 263, "count": 263, "decode_str": " \u00b5m"} -{"id": 34867, "token": "\u0120(\u00c2\u00a7", "merges": "\u0120( \u00c2\u00a7", "raw_count": 263, "count": 263, "decode_str": " (\u00a7"} -{"id": 47022, "token": "\u00c5\u00a1\u00c3\u0143", "merges": "\u00c5\u00a1 \u00c3\u0143", "raw_count": 263, "count": 263, "decode_str": "\u0161\u00ed"} -{"id": 27324, "token": "\u0120}$", "merges": "\u0120 }$", "raw_count": 263, "count": 263, "decode_str": " }$"} -{"id": 33638, "token": "\u0120IOException", "merges": "\u0120IO Exception", "raw_count": 264, "count": 264, "decode_str": " IOException"} -{"id": 42819, "token": "\u0120Surgical", "merges": "\u0120S urgical", "raw_count": 264, "count": 264, "decode_str": " Surgical"} -{"id": 39351, "token": "\u0120Salvador", "merges": "\u0120Salv ador", "raw_count": 264, "count": 264, "decode_str": " Salvador"} -{"id": 49334, "token": "\u0120DAMAGE", "merges": "\u0120DAM AGE", "raw_count": 264, "count": 264, "decode_str": " DAMAGE"} -{"id": 44133, "token": "\u0120Luxem", "merges": "\u0120Lux em", "raw_count": 264, "count": 264, "decode_str": " Luxem"} -{"id": 41788, "token": "\u0120h\u00c3\u00a4", "merges": "\u0120h \u00c3\u00a4", "raw_count": 264, "count": 264, "decode_str": " h\u00e4"} -{"id": 50347, "token": "\u00e2\u0137\u0140", "merges": "\u00e2\u0137 \u0140", "raw_count": 264, "count": 264, "decode_str": "\u255e"} -{"id": 36250, "token": "\u0120Mohammed", "merges": "\u0120Moh ammed", "raw_count": 265, "count": 265, "decode_str": " Mohammed"} -{"id": 33112, "token": "\u0120biofilm", "merges": "\u0120bio film", "raw_count": 265, "count": 265, "decode_str": " biofilm"} -{"id": 47799, "token": "\u0120Titans", "merges": "\u0120Tit ans", "raw_count": 265, "count": 265, "decode_str": " Titans"} -{"id": 53780, "token": "\u00e8\u00ae\u013c", "merges": "\u00e8\u00ae \u013c", "raw_count": 265, "count": 265, "decode_str": "\u8b9a"} -{"id": 34328, "token": "\u0120Westminster", "merges": "\u0120West minster", "raw_count": 266, "count": 266, "decode_str": " Westminster"} -{"id": 33166, "token": "\u0120Infantry", "merges": "\u0120Inf antry", "raw_count": 266, "count": 266, "decode_str": " Infantry"} -{"id": 43648, "token": "\u0120Benefits", "merges": "\u0120Benef its", "raw_count": 266, "count": 266, "decode_str": " Benefits"} -{"id": 35750, "token": "\u0120cysteine", "merges": "\u0120cy steine", "raw_count": 266, "count": 266, "decode_str": " cysteine"} -{"id": 30140, "token": "\u0120Miranda", "merges": "\u0120Mir anda", "raw_count": 266, "count": 266, "decode_str": " Miranda"} -{"id": 47786, "token": "\u0120Tobacco", "merges": "\u0120Tob acco", "raw_count": 266, "count": 266, "decode_str": " Tobacco"} -{"id": 8797, "token": "\u0120Muslim", "merges": "\u0120Mus lim", "raw_count": 231, "count": 266, "decode_str": " Muslim"} -{"id": 25556, "token": "\u0120Reagan", "merges": "\u0120Re agan", "raw_count": 266, "count": 266, "decode_str": " Reagan"} -{"id": 36353, "token": "\u0120Plato", "merges": "\u0120Pl ato", "raw_count": 266, "count": 266, "decode_str": " Plato"} -{"id": 11563, "token": "\u0120Jews", "merges": "\u0120Jew s", "raw_count": 266, "count": 266, "decode_str": " Jews"} -{"id": 27435, "token": "\u00ce\u00bf\u00cf\u012f", "merges": "\u00ce\u00bf \u00cf\u012f", "raw_count": 266, "count": 266, "decode_str": "\u03bf\u03cd"} -{"id": 27487, "token": "\u0120\u00c8\u013bi", "merges": "\u0120 \u00c8\u013bi", "raw_count": 266, "count": 266, "decode_str": " \u0219i"} -{"id": 47149, "token": "\u0120patterning", "merges": "\u0120patter ning", "raw_count": 267, "count": 267, "decode_str": " patterning"} -{"id": 46765, "token": "\u0120guerra", "merges": "\u0120gu erra", "raw_count": 267, "count": 267, "decode_str": " guerra"} -{"id": 22366, "token": "\u0120Maine", "merges": "\u0120M aine", "raw_count": 267, "count": 267, "decode_str": " Maine"} -{"id": 29508, "token": "\u0120onder", "merges": "\u0120on der", "raw_count": 267, "count": 267, "decode_str": " onder"} -{"id": 39964, "token": "\u0120waar", "merges": "\u0120wa ar", "raw_count": 267, "count": 267, "decode_str": " waar"} -{"id": 25492, "token": "\u0120^\\", "merges": "\u0120 ^\\", "raw_count": 267, "count": 267, "decode_str": " ^\\"} -{"id": 40523, "token": "\u0120immunoglobulin", "merges": "\u0120immunoglob ulin", "raw_count": 268, "count": 268, "decode_str": " immunoglobulin"} -{"id": 34285, "token": "\u0120glutathione", "merges": "\u0120glut athione", "raw_count": 268, "count": 268, "decode_str": " glutathione"} -{"id": 30316, "token": "\u0120oligonucle", "merges": "\u0120olig onucle", "raw_count": 0, "count": 268, "decode_str": " oligonucle"} -{"id": 27457, "token": "\u0120vaginal", "merges": "\u0120vag inal", "raw_count": 268, "count": 268, "decode_str": " vaginal"} -{"id": 42223, "token": "\u0120CRISPR", "merges": "\u0120CR ISPR", "raw_count": 268, "count": 268, "decode_str": " CRISPR"} -{"id": 49942, "token": "\u0120nanoc", "merges": "\u0120nan oc", "raw_count": 268, "count": 268, "decode_str": " nanoc"} -{"id": 46394, "token": "\u0120myocardium", "merges": "\u0120myocard ium", "raw_count": 269, "count": 269, "decode_str": " myocardium"} -{"id": 47748, "token": "olymers", "merges": "ol ymers", "raw_count": 55, "count": 269, "decode_str": "olymers"} -{"id": 47945, "token": "\u0120Aviv", "merges": "\u0120Av iv", "raw_count": 269, "count": 269, "decode_str": " Aviv"} -{"id": 29924, "token": "Bigl", "merges": "Big l", "raw_count": 269, "count": 269, "decode_str": "Bigl"} -{"id": 35819, "token": "\u0120CONTRIBUT", "merges": "\u0120CONTR IBUT", "raw_count": 169, "count": 270, "decode_str": " CONTRIBUT"} -{"id": 25771, "token": "\u0120Norwegian", "merges": "\u0120Nor wegian", "raw_count": 270, "count": 270, "decode_str": " Norwegian"} -{"id": 37539, "token": "\u0120Gandhi", "merges": "\u0120Gand hi", "raw_count": 270, "count": 270, "decode_str": " Gandhi"} -{"id": 37294, "token": "\u00c3\u0143ses", "merges": "\u00c3\u0143 ses", "raw_count": 47, "count": 270, "decode_str": "\u00edses"} -{"id": 45109, "token": "ticos", "merges": "tic os", "raw_count": 270, "count": 270, "decode_str": "ticos"} -{"id": 47324, "token": "\u00c3\u00aetre", "merges": "\u00c3\u00ae tre", "raw_count": 270, "count": 270, "decode_str": "\u00eetre"} -{"id": 46552, "token": "pmed", "merges": "p med", "raw_count": 270, "count": 270, "decode_str": "pmed"} -{"id": 22899, "token": "\u0120HCV", "merges": "\u0120H CV", "raw_count": 271, "count": 271, "decode_str": " HCV"} -{"id": 47007, "token": "')->", "merges": "') ->", "raw_count": 271, "count": 271, "decode_str": "')->"} -{"id": 51978, "token": "\u00e6\u012f\u00b2", "merges": "\u00e6\u012f \u00b2", "raw_count": 271, "count": 271, "decode_str": "\u6372"} -{"id": 34665, "token": "\u0120Interests", "merges": "\u0120Interest s", "raw_count": 272, "count": 272, "decode_str": " Interests"} -{"id": 24604, "token": "\u0120Montreal", "merges": "\u0120Mont real", "raw_count": 272, "count": 272, "decode_str": " Montreal"} -{"id": 36072, "token": "\u0120Earlier", "merges": "\u0120E arlier", "raw_count": 272, "count": 272, "decode_str": " Earlier"} -{"id": 41253, "token": "\u0120dieser", "merges": "\u0120dies er", "raw_count": 272, "count": 272, "decode_str": " dieser"} -{"id": 38900, "token": "\u0120Omar", "merges": "\u0120O mar", "raw_count": 272, "count": 272, "decode_str": " Omar"} -{"id": 46847, "token": "\u0120Marl", "merges": "\u0120Mar l", "raw_count": 272, "count": 272, "decode_str": " Marl"} -{"id": 54423, "token": "\u00e9\u0142\u00bc", "merges": "\u00e9\u0142 \u00bc", "raw_count": 272, "count": 272, "decode_str": "\u983c"} -{"id": 48843, "token": "\u0120eigenstates", "merges": "\u0120eigen states", "raw_count": 273, "count": 273, "decode_str": " eigenstates"} -{"id": 49850, "token": "\u0120Provincial", "merges": "\u0120Prov incial", "raw_count": 273, "count": 273, "decode_str": " Provincial"} -{"id": 49267, "token": "\u0120parece", "merges": "\u0120pare ce", "raw_count": 273, "count": 273, "decode_str": " parece"} -{"id": 3363, "token": "}$.", "merges": "}$ .", "raw_count": 251, "count": 273, "decode_str": "}$."} -{"id": 15243, "token": "}}=", "merges": "}} =", "raw_count": 273, "count": 273, "decode_str": "}}="} -{"id": 33887, "token": "\u0120\u00cf\u0127", "merges": "\u0120 \u00cf\u0127", "raw_count": 273, "count": 273, "decode_str": " \u03c5"} -{"id": 40368, "token": "\u0120mechanistic", "merges": "\u0120mechan istic", "raw_count": 274, "count": 274, "decode_str": " mechanistic"} -{"id": 30719, "token": "\u0120macrophage", "merges": "\u0120macroph age", "raw_count": 274, "count": 274, "decode_str": " macrophage"} -{"id": 43318, "token": "\u0120metformin", "merges": "\u0120met formin", "raw_count": 274, "count": 274, "decode_str": " metformin"} -{"id": 27611, "token": "\u0120\u00c3\u00a9tait", "merges": "\u0120\u00c3\u00a9 tait", "raw_count": 274, "count": 274, "decode_str": " \u00e9tait"} -{"id": 30028, "token": "\u0120Serum", "merges": "\u0120Ser um", "raw_count": 274, "count": 274, "decode_str": " Serum"} -{"id": 21103, "token": "tfrac", "merges": "t frac", "raw_count": 274, "count": 274, "decode_str": "tfrac"} -{"id": 50227, "token": "\u0120Cary", "merges": "\u0120C ary", "raw_count": 274, "count": 274, "decode_str": " Cary"} -{"id": 26097, "token": "\u00ce\u00af\u00ce\u00bd", "merges": "\u00ce\u00af \u00ce\u00bd", "raw_count": 80, "count": 274, "decode_str": "\u03af\u03bd"} -{"id": 45275, "token": "\u0120ZnO", "merges": "\u0120Zn O", "raw_count": 274, "count": 274, "decode_str": " ZnO"} -{"id": 31234, "token": "\u0120t\u00c3\u00a4", "merges": "\u0120t \u00c3\u00a4", "raw_count": 274, "count": 274, "decode_str": " t\u00e4"} -{"id": 54422, "token": "\u00e9\u0142\u00ab", "merges": "\u00e9\u0142 \u00ab", "raw_count": 274, "count": 274, "decode_str": "\u982b"} -{"id": 31379, "token": "}}[", "merges": "}} [", "raw_count": 274, "count": 274, "decode_str": "}}["} -{"id": 50289, "token": "\u00cb\u013c", "merges": "\u00cb \u013c", "raw_count": 274, "count": 274, "decode_str": "\u02da"} -{"id": 20760, "token": "emptyset", "merges": "empt yset", "raw_count": 275, "count": 275, "decode_str": "emptyset"} -{"id": 42376, "token": "\u0120Hussein", "merges": "\u0120Hus sein", "raw_count": 275, "count": 275, "decode_str": " Hussein"} -{"id": 47293, "token": "\u0120haemat", "merges": "\u0120ha emat", "raw_count": 275, "count": 275, "decode_str": " haemat"} -{"id": 41382, "token": "\u0120axons", "merges": "\u0120ax ons", "raw_count": 275, "count": 275, "decode_str": " axons"} -{"id": 40794, "token": "\u0120Joey", "merges": "\u0120Jo ey", "raw_count": 275, "count": 275, "decode_str": " Joey"} -{"id": 50249, "token": "\u0120Tus", "merges": "\u0120T us", "raw_count": 275, "count": 275, "decode_str": " Tus"} -{"id": 28530, "token": "\u0120NHS", "merges": "\u0120N HS", "raw_count": 275, "count": 275, "decode_str": " NHS"} -{"id": 22075, "token": "\u0120Philippines", "merges": "\u0120Philipp ines", "raw_count": 276, "count": 276, "decode_str": " Philippines"} -{"id": 42887, "token": "\u0120placental", "merges": "\u0120plac ental", "raw_count": 276, "count": 276, "decode_str": " placental"} -{"id": 40854, "token": "\u0120colitis", "merges": "\u0120col itis", "raw_count": 276, "count": 276, "decode_str": " colitis"} -{"id": 42431, "token": "\u0120Epstein", "merges": "\u0120Ep stein", "raw_count": 276, "count": 276, "decode_str": " Epstein"} -{"id": 15222, "token": "\u0120Besides", "merges": "\u0120B esides", "raw_count": 276, "count": 276, "decode_str": " Besides"} -{"id": 44567, "token": "\u0120Viking", "merges": "\u0120V iking", "raw_count": 276, "count": 276, "decode_str": " Viking"} -{"id": 20829, "token": "\u0120Alaska", "merges": "\u0120Al aska", "raw_count": 276, "count": 276, "decode_str": " Alaska"} -{"id": 50400, "token": "\u00e3\u0122\u013f", "merges": "\u00e3\u0122 \u013f", "raw_count": 276, "count": 276, "decode_str": "\u301d"} -{"id": 45876, "token": "\u0120nanoparticle", "merges": "\u0120nanop article", "raw_count": 277, "count": 277, "decode_str": " nanoparticle"} -{"id": 36835, "token": "\u0120Hernandez", "merges": "\u0120Hern andez", "raw_count": 277, "count": 277, "decode_str": " Hernandez"} -{"id": 28410, "token": "\u0120histone", "merges": "\u0120hist one", "raw_count": 277, "count": 277, "decode_str": " histone"} -{"id": 43785, "token": "\u0120Sandra", "merges": "\u0120Sand ra", "raw_count": 277, "count": 277, "decode_str": " Sandra"} -{"id": 26411, "token": "\u0120Pete", "merges": "\u0120Pet e", "raw_count": 277, "count": 277, "decode_str": " Pete"} -{"id": 43037, "token": "n\u00c4\u013d", "merges": "n \u00c4\u013d", "raw_count": 277, "count": 277, "decode_str": "n\u011b"} -{"id": 50282, "token": "\u00cb\u0129", "merges": "\u00cb \u0129", "raw_count": 277, "count": 277, "decode_str": "\u02c7"} -{"id": 21673, "token": "\u0120differentially", "merges": "\u0120different ially", "raw_count": 278, "count": 278, "decode_str": " differentially"} -{"id": 41144, "token": "\u0120Signaling", "merges": "\u0120Sign aling", "raw_count": 278, "count": 278, "decode_str": " Signaling"} -{"id": 45034, "token": "\u0120cationic", "merges": "\u0120cation ic", "raw_count": 278, "count": 278, "decode_str": " cationic"} -{"id": 43949, "token": "\u0120Manila", "merges": "\u0120Man ila", "raw_count": 278, "count": 278, "decode_str": " Manila"} -{"id": 49668, "token": "\u0120Plains", "merges": "\u0120Pl ains", "raw_count": 278, "count": 278, "decode_str": " Plains"} -{"id": 27718, "token": "\u00cf\u0122\u00cf\u012e", "merges": "\u00cf\u0122 \u00cf\u012e", "raw_count": 95, "count": 278, "decode_str": "\u03c0\u03cc"} -{"id": 37471, "token": ">';", "merges": "> ';", "raw_count": 278, "count": 278, "decode_str": ">';"} -{"id": 37641, "token": "\u0120Jackie", "merges": "\u0120Jack ie", "raw_count": 279, "count": 279, "decode_str": " Jackie"} -{"id": 46831, "token": "\u0120Nolan", "merges": "\u0120N olan", "raw_count": 279, "count": 279, "decode_str": " Nolan"} -{"id": 37140, "token": "\u0120Assay", "merges": "\u0120Ass ay", "raw_count": 279, "count": 279, "decode_str": " Assay"} -{"id": 40060, "token": "\u0120Acad", "merges": "\u0120Ac ad", "raw_count": 279, "count": 279, "decode_str": " Acad"} -{"id": 26867, "token": "\u00cf\u0130\u00ce\u00bd", "merges": "\u00cf\u0130 \u00ce\u00bd", "raw_count": 279, "count": 279, "decode_str": "\u03ce\u03bd"} -{"id": 31858, "token": "\u0120\\}", "merges": "\u0120\\ }", "raw_count": 279, "count": 279, "decode_str": " \\}"} -{"id": 17913, "token": "\u0120Jerusalem", "merges": "\u0120Jer usalem", "raw_count": 280, "count": 280, "decode_str": " Jerusalem"} -{"id": 46182, "token": "\u0120menstrual", "merges": "\u0120menstru al", "raw_count": 280, "count": 280, "decode_str": " menstrual"} -{"id": 34928, "token": "\u0120DISTRICT", "merges": "\u0120DIST RICT", "raw_count": 280, "count": 280, "decode_str": " DISTRICT"} -{"id": 36890, "token": "\u0120Bradford", "merges": "\u0120Brad ford", "raw_count": 280, "count": 280, "decode_str": " Bradford"} -{"id": 29040, "token": "\u0120Brandon", "merges": "\u0120Br andon", "raw_count": 280, "count": 280, "decode_str": " Brandon"} -{"id": 42442, "token": "\u0120Bundes", "merges": "\u0120Bund es", "raw_count": 280, "count": 280, "decode_str": " Bundes"} -{"id": 40434, "token": "\u0120Lords", "merges": "\u0120Lord s", "raw_count": 280, "count": 280, "decode_str": " Lords"} -{"id": 41451, "token": "\u00ce\u00bd\u00ce\u00b7", "merges": "\u00ce\u00bd \u00ce\u00b7", "raw_count": 280, "count": 280, "decode_str": "\u03bd\u03b7"} -{"id": 33923, "token": ")|^", "merges": ")| ^", "raw_count": 280, "count": 280, "decode_str": ")|^"} -{"id": 35229, "token": "\u0120interferon", "merges": "\u0120interfer on", "raw_count": 281, "count": 281, "decode_str": " interferon"} -{"id": 34409, "token": "\u0120Malcolm", "merges": "\u0120Mal colm", "raw_count": 281, "count": 281, "decode_str": " Malcolm"} -{"id": 44056, "token": "\u0120Lindsay", "merges": "\u0120Lind say", "raw_count": 281, "count": 281, "decode_str": " Lindsay"} -{"id": 46571, "token": "\u0120entend", "merges": "\u0120ent end", "raw_count": 281, "count": 281, "decode_str": " entend"} -{"id": 47660, "token": "\u0120Calder", "merges": "\u0120Cal der", "raw_count": 281, "count": 281, "decode_str": " Calder"} -{"id": 37921, "token": "\u0120Molly", "merges": "\u0120M olly", "raw_count": 281, "count": 281, "decode_str": " Molly"} -{"id": 48304, "token": "\u0120parce", "merges": "\u0120par ce", "raw_count": 281, "count": 281, "decode_str": " parce"} -{"id": 44553, "token": "\u0120electrophys", "merges": "\u0120electroph ys", "raw_count": 282, "count": 282, "decode_str": " electrophys"} -{"id": 36449, "token": "\u0120Christine", "merges": "\u0120Christ ine", "raw_count": 282, "count": 282, "decode_str": " Christine"} -{"id": 38535, "token": "DISCUSSION", "merges": "DIS CUSSION", "raw_count": 282, "count": 282, "decode_str": "DISCUSSION"} -{"id": 24084, "token": "\u0120Portugal", "merges": "\u0120Portug al", "raw_count": 282, "count": 282, "decode_str": " Portugal"} -{"id": 20901, "token": "\u0120Compared", "merges": "\u0120Comp ared", "raw_count": 282, "count": 282, "decode_str": " Compared"} -{"id": 26013, "token": "\u0120Anyone", "merges": "\u0120Any one", "raw_count": 282, "count": 282, "decode_str": " Anyone"} -{"id": 47914, "token": "\u0120Sout", "merges": "\u0120S out", "raw_count": 282, "count": 282, "decode_str": " Sout"} -{"id": 9496, "token": "}}^{", "merges": "}} ^{", "raw_count": 277, "count": 282, "decode_str": "}}^{"} -{"id": 28817, "token": "\u0120\u00e0\u00a4\u00b9", "merges": "\u0120\u00e0\u00a4 \u00b9", "raw_count": 282, "count": 282, "decode_str": " \u0939"} -{"id": 40237, "token": "\u00ce\u00bc\u00ce\u00bf", "merges": "\u00ce\u00bc \u00ce\u00bf", "raw_count": 282, "count": 282, "decode_str": "\u03bc\u03bf"} -{"id": 24449, "token": "\u0120\u00c3\u0125", "merges": "\u0120\u00c3 \u0125", "raw_count": 282, "count": 282, "decode_str": " \u00c3"} -{"id": 35006, "token": "\u0120stromal", "merges": "\u0120strom al", "raw_count": 283, "count": 283, "decode_str": " stromal"} -{"id": 50218, "token": "\u0120Ramos", "merges": "\u0120Ram os", "raw_count": 283, "count": 283, "decode_str": " Ramos"} -{"id": 22361, "token": "\u0120Higgs", "merges": "\u0120Hig gs", "raw_count": 283, "count": 283, "decode_str": " Higgs"} -{"id": 45714, "token": "\u0120Hogan", "merges": "\u0120H ogan", "raw_count": 283, "count": 283, "decode_str": " Hogan"} -{"id": 41692, "token": "\u0120Jude", "merges": "\u0120J ude", "raw_count": 283, "count": 283, "decode_str": " Jude"} -{"id": 25703, "token": "})^{", "merges": "}) ^{", "raw_count": 283, "count": 283, "decode_str": "})^{"} -{"id": 31040, "token": "}\\|", "merges": "}\\ |", "raw_count": 283, "count": 283, "decode_str": "}\\|"} -{"id": 49279, "token": "\u0120hypothalamus", "merges": "\u0120hypothal amus", "raw_count": 284, "count": 284, "decode_str": " hypothalamus"} -{"id": 36670, "token": "\u0120millilit", "merges": "\u0120mill ilit", "raw_count": 244, "count": 284, "decode_str": " millilit"} -{"id": 24992, "token": "\u0120Judgment", "merges": "\u0120Jud gment", "raw_count": 284, "count": 284, "decode_str": " Judgment"} -{"id": 39206, "token": "\u0120Patricia", "merges": "\u0120Pat ricia", "raw_count": 284, "count": 284, "decode_str": " Patricia"} -{"id": 42167, "token": "\u0120Wendy", "merges": "\u0120Wend y", "raw_count": 284, "count": 284, "decode_str": " Wendy"} -{"id": 41456, "token": "))*-", "merges": ")) *-", "raw_count": 284, "count": 284, "decode_str": "))*-"} -{"id": 23743, "token": "}$\\", "merges": "}$ \\", "raw_count": 284, "count": 284, "decode_str": "}$\\"} -{"id": 50280, "token": "\u00c9\u00a1", "merges": "\u00c9 \u00a1", "raw_count": 284, "count": 284, "decode_str": "\u0261"} -{"id": 30256, "token": "\u0120Parkinson", "merges": "\u0120Park inson", "raw_count": 285, "count": 285, "decode_str": " Parkinson"} -{"id": 32762, "token": "\u0120Chev", "merges": "\u0120Che v", "raw_count": 188, "count": 285, "decode_str": " Chev"} -{"id": 41742, "token": "\u0120UCLA", "merges": "\u0120U CLA", "raw_count": 285, "count": 285, "decode_str": " UCLA"} -{"id": 40934, "token": "\u0120Rash", "merges": "\u0120R ash", "raw_count": 285, "count": 285, "decode_str": " Rash"} -{"id": 52025, "token": "\u00e6\u0131\u00b9", "merges": "\u00e6\u0131 \u00b9", "raw_count": 285, "count": 285, "decode_str": "\u63f9"} -{"id": 34187, "token": "ClickListener", "merges": "Click Listener", "raw_count": 176, "count": 286, "decode_str": "ClickListener"} -{"id": 30614, "token": "\u0120inactivation", "merges": "\u0120in activation", "raw_count": 286, "count": 286, "decode_str": " inactivation"} -{"id": 35702, "token": "\u0120Buddhism", "merges": "\u0120Buddh ism", "raw_count": 286, "count": 286, "decode_str": " Buddhism"} -{"id": 45664, "token": "\u0120Allison", "merges": "\u0120All ison", "raw_count": 286, "count": 286, "decode_str": " Allison"} -{"id": 43649, "token": "\u0120Guards", "merges": "\u0120Gu ards", "raw_count": 286, "count": 286, "decode_str": " Guards"} -{"id": 40549, "token": "\u0120Maced", "merges": "\u0120M aced", "raw_count": 286, "count": 286, "decode_str": " Maced"} -{"id": 43294, "token": "\u0120Revel", "merges": "\u0120Re vel", "raw_count": 286, "count": 286, "decode_str": " Revel"} -{"id": 36825, "token": "ist\u00c3\u00a4", "merges": "ist \u00c3\u00a4", "raw_count": 286, "count": 286, "decode_str": "ist\u00e4"} -{"id": 27977, "token": "\u0120QCD", "merges": "\u0120Q CD", "raw_count": 286, "count": 286, "decode_str": " QCD"} -{"id": 45612, "token": "\u0120echocardiography", "merges": "\u0120echocardi ography", "raw_count": 287, "count": 287, "decode_str": " echocardiography"} -{"id": 49339, "token": "\u0120Procedures", "merges": "\u0120Proced ures", "raw_count": 287, "count": 287, "decode_str": " Procedures"} -{"id": 34040, "token": "\u0120fermions", "merges": "\u0120ferm ions", "raw_count": 287, "count": 287, "decode_str": " fermions"} -{"id": 48025, "token": "\u0120vesicle", "merges": "\u0120ves icle", "raw_count": 287, "count": 287, "decode_str": " vesicle"} -{"id": 49983, "token": "\u0120Manor", "merges": "\u0120Man or", "raw_count": 287, "count": 287, "decode_str": " Manor"} -{"id": 33252, "token": "\u0120Anglo", "merges": "\u0120Angl o", "raw_count": 287, "count": 287, "decode_str": " Anglo"} -{"id": 37669, "token": "\u0120Rocky", "merges": "\u0120Rock y", "raw_count": 287, "count": 287, "decode_str": " Rocky"} -{"id": 32807, "token": "\u0120Teh", "merges": "\u0120Te h", "raw_count": 212, "count": 287, "decode_str": " Teh"} -{"id": 24815, "token": "->_", "merges": "-> _", "raw_count": 287, "count": 287, "decode_str": "->_"} -{"id": 17990, "token": ")-\\", "merges": ") -\\", "raw_count": 287, "count": 287, "decode_str": ")-\\"} -{"id": 31939, "token": "\u0120phospholip", "merges": "\u0120phosph olip", "raw_count": 288, "count": 288, "decode_str": " phospholip"} -{"id": 22126, "token": "\u0120Vancouver", "merges": "\u0120V ancouver", "raw_count": 288, "count": 288, "decode_str": " Vancouver"} -{"id": 29797, "token": "\u0120Southeast", "merges": "\u0120S outheast", "raw_count": 288, "count": 288, "decode_str": " Southeast"} -{"id": 43627, "token": "\u0120Violence", "merges": "\u0120Viol ence", "raw_count": 288, "count": 288, "decode_str": " Violence"} -{"id": 32866, "token": "\u0120homotopy", "merges": "\u0120homot opy", "raw_count": 288, "count": 288, "decode_str": " homotopy"} -{"id": 47569, "token": "\u0120Geoffrey", "merges": "\u0120Geoff rey", "raw_count": 288, "count": 288, "decode_str": " Geoffrey"} -{"id": 34567, "token": "\u0120Antib", "merges": "\u0120Ant ib", "raw_count": 288, "count": 288, "decode_str": " Antib"} -{"id": 30422, "token": "\u0120v\u00c3\u00a6", "merges": "\u0120v \u00c3\u00a6", "raw_count": 117, "count": 288, "decode_str": " v\u00e6"} -{"id": 46257, "token": "}),\\", "merges": "} ),\\", "raw_count": 288, "count": 288, "decode_str": "}),\\"} -{"id": 40589, "token": "\u0120FAA", "merges": "\u0120F AA", "raw_count": 288, "count": 288, "decode_str": " FAA"} -{"id": 15892, "token": "\u0120^{", "merges": "\u0120 ^{", "raw_count": 288, "count": 288, "decode_str": " ^{"} -{"id": 14748, "token": "\u0120Minnesota", "merges": "\u0120Minn esota", "raw_count": 289, "count": 289, "decode_str": " Minnesota"} -{"id": 40548, "token": "\u0120epitope", "merges": "\u0120epit ope", "raw_count": 289, "count": 289, "decode_str": " epitope"} -{"id": 46055, "token": "\u0120trypt", "merges": "\u0120try pt", "raw_count": 289, "count": 289, "decode_str": " trypt"} -{"id": 31078, "token": "\u0120Hels", "merges": "\u0120H els", "raw_count": 114, "count": 289, "decode_str": " Hels"} -{"id": 22537, "token": "\u0120immunohist", "merges": "\u0120immun ohist", "raw_count": 2, "count": 290, "decode_str": " immunohist"} -{"id": 16011, "token": "\u0120cytokines", "merges": "\u0120cytok ines", "raw_count": 290, "count": 290, "decode_str": " cytokines"} -{"id": 28260, "token": "\u0120Giants", "merges": "\u0120Gi ants", "raw_count": 290, "count": 290, "decode_str": " Giants"} -{"id": 43738, "token": "iorari", "merges": "ior ari", "raw_count": 290, "count": 290, "decode_str": "iorari"} -{"id": 40858, "token": "\u0120Laden", "merges": "\u0120L aden", "raw_count": 290, "count": 290, "decode_str": " Laden"} -{"id": 32393, "token": "\u0120Seth", "merges": "\u0120S eth", "raw_count": 290, "count": 290, "decode_str": " Seth"} -{"id": 50209, "token": "\u0120habl", "merges": "\u0120h abl", "raw_count": 290, "count": 290, "decode_str": " habl"} -{"id": 46664, "token": "\u0120KCl", "merges": "\u0120K Cl", "raw_count": 290, "count": 290, "decode_str": " KCl"} -{"id": 48992, "token": "\u0120FEV", "merges": "\u0120F EV", "raw_count": 290, "count": 290, "decode_str": " FEV"} -{"id": 13338, "token": "\u0120Colorado", "merges": "\u0120Color ado", "raw_count": 291, "count": 291, "decode_str": " Colorado"} -{"id": 49350, "token": "\u0120Alic", "merges": "\u0120A lic", "raw_count": 291, "count": 291, "decode_str": " Alic"} -{"id": 49633, "token": ")}+", "merges": ")} +", "raw_count": 291, "count": 291, "decode_str": ")}+"} -{"id": 37815, "token": "Drosophila", "merges": "D rosophila", "raw_count": 292, "count": 292, "decode_str": "Drosophila"} -{"id": 6767, "token": "widet", "merges": "wid et", "raw_count": 127, "count": 292, "decode_str": "widet"} -{"id": 47408, "token": "\u0120Coy", "merges": "\u0120C oy", "raw_count": 292, "count": 292, "decode_str": " Coy"} -{"id": 36030, "token": "\u00ce\u00bb\u00ce\u00b5", "merges": "\u00ce\u00bb \u00ce\u00b5", "raw_count": 292, "count": 292, "decode_str": "\u03bb\u03b5"} -{"id": 50355, "token": "\u00e2\u0138\u0124", "merges": "\u00e2\u0138 \u0124", "raw_count": 292, "count": 292, "decode_str": "\u2582"} -{"id": 41866, "token": "\u0120cerevisiae", "merges": "\u0120cere visiae", "raw_count": 293, "count": 293, "decode_str": " cerevisiae"} -{"id": 34674, "token": "Upsilon", "merges": "U psilon", "raw_count": 293, "count": 293, "decode_str": "Upsilon"} -{"id": 48935, "token": "\u0120felon", "merges": "\u0120fel on", "raw_count": 293, "count": 293, "decode_str": " felon"} -{"id": 46737, "token": "\u0120Cain", "merges": "\u0120C ain", "raw_count": 293, "count": 293, "decode_str": " Cain"} -{"id": 13090, "token": "\u0120\u00c3\u00aen", "merges": "\u0120\u00c3\u00ae n", "raw_count": 293, "count": 293, "decode_str": " \u00een"} -{"id": 41158, "token": "\u0120Cly", "merges": "\u0120C ly", "raw_count": 293, "count": 293, "decode_str": " Cly"} -{"id": 37957, "token": "\u0120NPR", "merges": "\u0120N PR", "raw_count": 293, "count": 293, "decode_str": " NPR"} -{"id": 33221, "token": "\u00ce\u00ae\u00cf\u0124", "merges": "\u00ce\u00ae \u00cf\u0124", "raw_count": 293, "count": 293, "decode_str": "\u03ae\u03c2"} -{"id": 36003, "token": "\u00cf\u0123\u00ce\u00b3", "merges": "\u00cf\u0123 \u00ce\u00b3", "raw_count": 293, "count": 293, "decode_str": "\u03c1\u03b3"} -{"id": 48329, "token": ")$)", "merges": ")$ )", "raw_count": 293, "count": 293, "decode_str": ")$)"} -{"id": 9213, "token": "}+\\", "merges": "} +\\", "raw_count": 293, "count": 293, "decode_str": "}+\\"} -{"id": 40823, "token": "\u00c5\u00bee", "merges": "\u00c5\u00be e", "raw_count": 293, "count": 293, "decode_str": "\u017ee"} -{"id": 30041, "token": "\u00c3\u013d", "merges": "\u00c3 \u013d", "raw_count": 293, "count": 293, "decode_str": "\u00db"} -{"id": 42557, "token": "\u0120politique", "merges": "\u0120polit ique", "raw_count": 294, "count": 294, "decode_str": " politique"} -{"id": 13115, "token": "\u0120Pakistan", "merges": "\u0120Pak istan", "raw_count": 294, "count": 294, "decode_str": " Pakistan"} -{"id": 44810, "token": "\u0120estaba", "merges": "\u0120est aba", "raw_count": 294, "count": 294, "decode_str": " estaba"} -{"id": 34410, "token": "\u0120Guinea", "merges": "\u0120Gu inea", "raw_count": 294, "count": 294, "decode_str": " Guinea"} -{"id": 46109, "token": "\u0120jamais", "merges": "\u0120j amais", "raw_count": 294, "count": 294, "decode_str": " jamais"} -{"id": 43242, "token": "\u00cf\u0126\u00ce\u00ae", "merges": "\u00cf\u0126 \u00ce\u00ae", "raw_count": 294, "count": 294, "decode_str": "\u03c4\u03ae"} -{"id": 28270, "token": "\u0120Thirty", "merges": "\u0120Th irty", "raw_count": 295, "count": 295, "decode_str": " Thirty"} -{"id": 48055, "token": "\u0120Violet", "merges": "\u0120V iolet", "raw_count": 295, "count": 295, "decode_str": " Violet"} -{"id": 30290, "token": "\u0120k\u00c3\u00b6nn", "merges": "\u0120k\u00c3\u00b6 nn", "raw_count": 50, "count": 295, "decode_str": " k\u00f6nn"} -{"id": 48239, "token": "\u0120nanow", "merges": "\u0120nan ow", "raw_count": 295, "count": 295, "decode_str": " nanow"} -{"id": 44537, "token": "lbrace", "merges": "l brace", "raw_count": 295, "count": 295, "decode_str": "lbrace"} -{"id": 35288, "token": "\u0120Tumor", "merges": "\u0120T umor", "raw_count": 295, "count": 295, "decode_str": " Tumor"} -{"id": 16724, "token": "\u0120\u00e2\u0122\u0140", "merges": "\u0120\u00e2\u0122 \u0140", "raw_count": 295, "count": 295, "decode_str": " \u201e"} -{"id": 42579, "token": "\u0120Cricket", "merges": "\u0120Crick et", "raw_count": 296, "count": 296, "decode_str": " Cricket"} -{"id": 36788, "token": "\u0120Notch", "merges": "\u0120Not ch", "raw_count": 296, "count": 296, "decode_str": " Notch"} -{"id": 40971, "token": "\u0120Nietzsche", "merges": "\u0120N ietzsche", "raw_count": 297, "count": 297, "decode_str": " Nietzsche"} -{"id": 44620, "token": "\u0120lysine", "merges": "\u0120lys ine", "raw_count": 297, "count": 297, "decode_str": " lysine"} -{"id": 18636, "token": "^*$", "merges": "^* $", "raw_count": 297, "count": 297, "decode_str": "^*$"} -{"id": 43727, "token": "\u0120hepatocellular", "merges": "\u0120hepat ocellular", "raw_count": 298, "count": 298, "decode_str": " hepatocellular"} -{"id": 49982, "token": "\u0120postseason", "merges": "\u0120post season", "raw_count": 298, "count": 298, "decode_str": " postseason"} -{"id": 43854, "token": "\u0120ligation", "merges": "\u0120l igation", "raw_count": 298, "count": 298, "decode_str": " ligation"} -{"id": 44786, "token": "\u0120Newport", "merges": "\u0120New port", "raw_count": 298, "count": 298, "decode_str": " Newport"} -{"id": 47896, "token": "\u0120Cecil", "merges": "\u0120Cec il", "raw_count": 298, "count": 298, "decode_str": " Cecil"} -{"id": 41097, "token": "\u0120Hicks", "merges": "\u0120H icks", "raw_count": 298, "count": 298, "decode_str": " Hicks"} -{"id": 38557, "token": "\u0120Byz", "merges": "\u0120By z", "raw_count": 147, "count": 298, "decode_str": " Byz"} -{"id": 50328, "token": "\u00e2\u012b\u00a1", "merges": "\u00e2\u012b \u00a1", "raw_count": 298, "count": 298, "decode_str": "\u2261"} -{"id": 47876, "token": "\u00c5\u0128", "merges": "\u00c5 \u0128", "raw_count": 298, "count": 298, "decode_str": "\u0146"} -{"id": 47640, "token": "otransferase", "merges": "otransfer ase", "raw_count": 299, "count": 299, "decode_str": "otransferase"} -{"id": 49734, "token": "\u0120testicular", "merges": "\u0120test icular", "raw_count": 299, "count": 299, "decode_str": " testicular"} -{"id": 42985, "token": "\u0120Nursing", "merges": "\u0120Nurs ing", "raw_count": 299, "count": 299, "decode_str": " Nursing"} -{"id": 48448, "token": "\u0120excised", "merges": "\u0120exc ised", "raw_count": 299, "count": 299, "decode_str": " excised"} -{"id": 29183, "token": "\u0120Batman", "merges": "\u0120Bat man", "raw_count": 299, "count": 299, "decode_str": " Batman"} -{"id": 26089, "token": "\u0120Nixon", "merges": "\u0120N ixon", "raw_count": 299, "count": 299, "decode_str": " Nixon"} -{"id": 23440, "token": "\u0120BASIS", "merges": "\u0120BAS IS", "raw_count": 299, "count": 299, "decode_str": " BASIS"} -{"id": 44950, "token": "\u0120Cumm", "merges": "\u0120C umm", "raw_count": 299, "count": 299, "decode_str": " Cumm"} -{"id": 39202, "token": "\u0120endometrial", "merges": "\u0120endomet rial", "raw_count": 300, "count": 300, "decode_str": " endometrial"} -{"id": 8731, "token": "setlength", "merges": "set length", "raw_count": 300, "count": 300, "decode_str": "setlength"} -{"id": 46773, "token": "\u0120Roberto", "merges": "\u0120Rober to", "raw_count": 300, "count": 300, "decode_str": " Roberto"} -{"id": 16234, "token": "\u0120Mexican", "merges": "\u0120Mex ican", "raw_count": 300, "count": 300, "decode_str": " Mexican"} -{"id": 40448, "token": "\u0120Sexual", "merges": "\u0120Sex ual", "raw_count": 300, "count": 300, "decode_str": " Sexual"} -{"id": 46637, "token": "\u0120Sidney", "merges": "\u0120Sid ney", "raw_count": 300, "count": 300, "decode_str": " Sidney"} -{"id": 25731, "token": ":@\"", "merges": ": @\"", "raw_count": 300, "count": 300, "decode_str": ":@\""} -{"id": 11466, "token": "\u00c2\u00b8", "merges": "\u00c2 \u00b8", "raw_count": 295, "count": 300, "decode_str": "\u00b8"} -{"id": 24898, "token": "\u0120embodiments", "merges": "\u0120embod iments", "raw_count": 301, "count": 301, "decode_str": " embodiments"} -{"id": 41112, "token": "\u0120Sterling", "merges": "\u0120Ster ling", "raw_count": 301, "count": 301, "decode_str": " Sterling"} -{"id": 48162, "token": "onitrile", "merges": "on itrile", "raw_count": 301, "count": 301, "decode_str": "onitrile"} -{"id": 45746, "token": "\u0120Hodge", "merges": "\u0120H odge", "raw_count": 301, "count": 301, "decode_str": " Hodge"} -{"id": 43802, "token": "\u0120McKin", "merges": "\u0120McK in", "raw_count": 301, "count": 301, "decode_str": " McKin"} -{"id": 49596, "token": "\u0120Nicol", "merges": "\u0120Nic ol", "raw_count": 301, "count": 301, "decode_str": " Nicol"} -{"id": 29164, "token": "\u0120Mais", "merges": "\u0120M ais", "raw_count": 301, "count": 301, "decode_str": " Mais"} -{"id": 51977, "token": "\u00e6\u012f\u00b1", "merges": "\u00e6\u012f \u00b1", "raw_count": 301, "count": 301, "decode_str": "\u6371"} -{"id": 50307, "token": "\u00e2\u0124\u0125", "merges": "\u00e2\u0124 \u0125", "raw_count": 301, "count": 301, "decode_str": "\u2083"} -{"id": 49765, "token": "\u0120Emmanuel", "merges": "\u0120Em manuel", "raw_count": 302, "count": 302, "decode_str": " Emmanuel"} -{"id": 30638, "token": "\u0120Confed", "merges": "\u0120Conf ed", "raw_count": 242, "count": 302, "decode_str": " Confed"} -{"id": 24607, "token": "\u0120Colomb", "merges": "\u0120Col omb", "raw_count": 129, "count": 302, "decode_str": " Colomb"} -{"id": 45014, "token": "\u0120Chloe", "merges": "\u0120Ch loe", "raw_count": 302, "count": 302, "decode_str": " Chloe"} -{"id": 27989, "token": "\u0120Tris", "merges": "\u0120Tr is", "raw_count": 302, "count": 302, "decode_str": " Tris"} -{"id": 36669, "token": "\u0120Dana", "merges": "\u0120D ana", "raw_count": 302, "count": 302, "decode_str": " Dana"} -{"id": 14808, "token": "\u00e2\u0122\u00af", "merges": "\u00e2\u0122 \u00af", "raw_count": 302, "count": 302, "decode_str": "\u202f"} -{"id": 25856, "token": "\u0120Kyle", "merges": "\u0120K yle", "raw_count": 303, "count": 303, "decode_str": " Kyle"} -{"id": 37710, "token": "\u0120\u00d9\u0123\u00d9\u012c", "merges": "\u0120\u00d9\u0123 \u00d9\u012c", "raw_count": 303, "count": 303, "decode_str": " \u0641\u064a"} -{"id": 32678, "token": "\u0120Thanksgiving", "merges": "\u0120Thanks giving", "raw_count": 304, "count": 304, "decode_str": " Thanksgiving"} -{"id": 46048, "token": "\u0120autologous", "merges": "\u0120aut ologous", "raw_count": 304, "count": 304, "decode_str": " autologous"} -{"id": 44340, "token": "\u0120Parties", "merges": "\u0120Part ies", "raw_count": 304, "count": 304, "decode_str": " Parties"} -{"id": 49239, "token": "\u0120Newsp", "merges": "\u0120New sp", "raw_count": 304, "count": 304, "decode_str": " Newsp"} -{"id": 49871, "token": "\u0120Tours", "merges": "\u0120T ours", "raw_count": 304, "count": 304, "decode_str": " Tours"} -{"id": 39345, "token": "\u0120Thir", "merges": "\u0120Th ir", "raw_count": 304, "count": 304, "decode_str": " Thir"} -{"id": 48780, "token": "\u0120APA", "merges": "\u0120AP A", "raw_count": 304, "count": 304, "decode_str": " APA"} -{"id": 36737, "token": "\u0120Astrophys", "merges": "\u0120Ast rophys", "raw_count": 305, "count": 305, "decode_str": " Astrophys"} -{"id": 25367, "token": "\u0120tyrosine", "merges": "\u0120ty rosine", "raw_count": 305, "count": 305, "decode_str": " tyrosine"} -{"id": 19930, "token": "\u0120Europa", "merges": "\u0120Europ a", "raw_count": 305, "count": 305, "decode_str": " Europa"} -{"id": 35666, "token": "\u0120decedent", "merges": "\u0120de cedent", "raw_count": 306, "count": 306, "decode_str": " decedent"} -{"id": 41046, "token": "\u0120Breast", "merges": "\u0120Bre ast", "raw_count": 306, "count": 306, "decode_str": " Breast"} -{"id": 48770, "token": "\u0120Territ", "merges": "\u0120Ter rit", "raw_count": 306, "count": 306, "decode_str": " Territ"} -{"id": 48282, "token": "\u0120$$|", "merges": "\u0120$$ |", "raw_count": 306, "count": 306, "decode_str": " $$|"} -{"id": 34441, "token": "\u0120\u00c3\u0126", "merges": "\u0120\u00c3 \u0126", "raw_count": 306, "count": 306, "decode_str": " \u00c4"} -{"id": 36692, "token": "^{[", "merges": "^{ [", "raw_count": 306, "count": 306, "decode_str": "^{["} -{"id": 28976, "token": "\u0120biomarker", "merges": "\u0120biomark er", "raw_count": 307, "count": 307, "decode_str": " biomarker"} -{"id": 36195, "token": "Regarding", "merges": "Reg arding", "raw_count": 307, "count": 307, "decode_str": "Regarding"} -{"id": 23181, "token": "\u0120WARRANTY", "merges": "\u0120WARRANT Y", "raw_count": 307, "count": 307, "decode_str": " WARRANTY"} -{"id": 43735, "token": "\u0120ovary", "merges": "\u0120ov ary", "raw_count": 307, "count": 307, "decode_str": " ovary"} -{"id": 47613, "token": "\u0120Irene", "merges": "\u0120I rene", "raw_count": 307, "count": 307, "decode_str": " Irene"} -{"id": 48119, "token": "\u0120Fraz", "merges": "\u0120F raz", "raw_count": 307, "count": 307, "decode_str": " Fraz"} -{"id": 31959, "token": "\u0120Rebecca", "merges": "\u0120Re becca", "raw_count": 308, "count": 308, "decode_str": " Rebecca"} -{"id": 36139, "token": "\u0120Isabel", "merges": "\u0120Is abel", "raw_count": 308, "count": 308, "decode_str": " Isabel"} -{"id": 49319, "token": "\u0120dette", "merges": "\u0120det te", "raw_count": 308, "count": 308, "decode_str": " dette"} -{"id": 43306, "token": "=\"$(", "merges": "=\" $(", "raw_count": 308, "count": 308, "decode_str": "=\"$("} -{"id": 46304, "token": "\u0120bioavailability", "merges": "\u0120bio availability", "raw_count": 309, "count": 309, "decode_str": " bioavailability"} -{"id": 45187, "token": "\u0120Deutsche", "merges": "\u0120Deut sche", "raw_count": 309, "count": 309, "decode_str": " Deutsche"} -{"id": 11481, "token": "\u0120Palest", "merges": "\u0120Pal est", "raw_count": 147, "count": 309, "decode_str": " Palest"} -{"id": 32252, "token": "\u0120Casey", "merges": "\u0120Case y", "raw_count": 309, "count": 309, "decode_str": " Casey"} -{"id": 41504, "token": "\u0120Eph", "merges": "\u0120E ph", "raw_count": 309, "count": 309, "decode_str": " Eph"} -{"id": 8786, "token": "\u0120Republican", "merges": "\u0120Republic an", "raw_count": 310, "count": 310, "decode_str": " Republican"} -{"id": 37446, "token": "////////////////////////////////////////////////////////////////", "merges": "//////////////////////////////// ////////////////////////////////", "raw_count": 311, "count": 311, "decode_str": "////////////////////////////////////////////////////////////////"} -{"id": 22356, "token": "\u0120Communist", "merges": "\u0120Commun ist", "raw_count": 311, "count": 311, "decode_str": " Communist"} -{"id": 39431, "token": "\u0120Namely", "merges": "\u0120Nam ely", "raw_count": 311, "count": 311, "decode_str": " Namely"} -{"id": 45481, "token": "\u0120erythe", "merges": "\u0120ery the", "raw_count": 311, "count": 311, "decode_str": " erythe"} -{"id": 43634, "token": "\u0120Byron", "merges": "\u0120By ron", "raw_count": 311, "count": 311, "decode_str": " Byron"} -{"id": 45431, "token": "\u0120\u00c3\u00a9p", "merges": "\u0120\u00c3\u00a9 p", "raw_count": 311, "count": 311, "decode_str": " \u00e9p"} -{"id": 33358, "token": "\u00e0\u00a5\u012a", "merges": "\u00e0\u00a5 \u012a", "raw_count": 311, "count": 311, "decode_str": "\u0948"} -{"id": 39889, "token": "\u0120misdemeanor", "merges": "\u0120misdem eanor", "raw_count": 312, "count": 312, "decode_str": " misdemeanor"} -{"id": 23498, "token": "\u0120Especially", "merges": "\u0120Es pecially", "raw_count": 312, "count": 312, "decode_str": " Especially"} -{"id": 18383, "token": "\u0120\u00ce\u00ba\u00ce\u00b1", "merges": "\u0120\u00ce\u00ba \u00ce\u00b1", "raw_count": 227, "count": 312, "decode_str": " \u03ba\u03b1"} -{"id": 34738, "token": "\u0120Kitt", "merges": "\u0120K itt", "raw_count": 312, "count": 312, "decode_str": " Kitt"} -{"id": 41124, "token": "Differentiate", "merges": "Different iate", "raw_count": 313, "count": 313, "decode_str": "Differentiate"} -{"id": 13786, "token": "\u0120Petition", "merges": "\u0120P etition", "raw_count": 310, "count": 313, "decode_str": " Petition"} -{"id": 22699, "token": "\u0120Puerto", "merges": "\u0120Pu erto", "raw_count": 313, "count": 313, "decode_str": " Puerto"} -{"id": 48126, "token": "\u0120Lawson", "merges": "\u0120Law son", "raw_count": 313, "count": 313, "decode_str": " Lawson"} -{"id": 44384, "token": "\u0120Tukey", "merges": "\u0120Tu key", "raw_count": 313, "count": 313, "decode_str": " Tukey"} -{"id": 31472, "token": "\u0120Jesse", "merges": "\u0120Jes se", "raw_count": 313, "count": 313, "decode_str": " Jesse"} -{"id": 29452, "token": "\u0120Zion", "merges": "\u0120Z ion", "raw_count": 313, "count": 313, "decode_str": " Zion"} -{"id": 44535, "token": "\u0120follicles", "merges": "\u0120follic les", "raw_count": 314, "count": 314, "decode_str": " follicles"} -{"id": 38929, "token": "\u00ce\u00bb\u00ce\u00b7", "merges": "\u00ce\u00bb \u00ce\u00b7", "raw_count": 314, "count": 314, "decode_str": "\u03bb\u03b7"} -{"id": 34556, "token": "\u00e0\u00ba", "merges": "\u00e0 \u00ba", "raw_count": 314, "count": 314, "decode_str": "\ufffd"} -{"id": 46646, "token": "\u0120Lipschitz", "merges": "\u0120Lips chitz", "raw_count": 315, "count": 315, "decode_str": " Lipschitz"} -{"id": 25223, "token": "\u0120protease", "merges": "\u0120prote ase", "raw_count": 315, "count": 315, "decode_str": " protease"} -{"id": 45729, "token": "\u0120Hammond", "merges": "\u0120Hamm ond", "raw_count": 315, "count": 315, "decode_str": " Hammond"} -{"id": 42005, "token": "\u0120Landau", "merges": "\u0120Land au", "raw_count": 315, "count": 315, "decode_str": " Landau"} -{"id": 19987, "token": "\u0120Pitts", "merges": "\u0120Pitt s", "raw_count": 93, "count": 315, "decode_str": " Pitts"} -{"id": 39979, "token": "\u0120Wheat", "merges": "\u0120Whe at", "raw_count": 315, "count": 315, "decode_str": " Wheat"} -{"id": 49626, "token": "\u00ce\u00b8\u00ce\u00b7", "merges": "\u00ce\u00b8 \u00ce\u00b7", "raw_count": 315, "count": 315, "decode_str": "\u03b8\u03b7"} -{"id": 25990, "token": "\u0120Edinburgh", "merges": "\u0120Ed inburgh", "raw_count": 316, "count": 316, "decode_str": " Edinburgh"} -{"id": 35512, "token": "\u0120Mercedes", "merges": "\u0120Mer cedes", "raw_count": 316, "count": 316, "decode_str": " Mercedes"} -{"id": 38436, "token": "\u0120Santiago", "merges": "\u0120S antiago", "raw_count": 316, "count": 316, "decode_str": " Santiago"} -{"id": 16700, "token": "\u0120Dallas", "merges": "\u0120D allas", "raw_count": 316, "count": 316, "decode_str": " Dallas"} -{"id": 41106, "token": "\u0120hecho", "merges": "\u0120he cho", "raw_count": 316, "count": 316, "decode_str": " hecho"} -{"id": 41825, "token": "^).", "merges": "^ ).", "raw_count": 316, "count": 316, "decode_str": "^)."} -{"id": 47630, "token": "\u00c3\u00aet", "merges": "\u00c3\u00ae t", "raw_count": 316, "count": 316, "decode_str": "\u00eet"} -{"id": 15667, "token": "$^{", "merges": "$ ^{", "raw_count": 316, "count": 316, "decode_str": "$^{"} -{"id": 49429, "token": "\u0120hypersensitivity", "merges": "\u0120hypers ensitivity", "raw_count": 317, "count": 317, "decode_str": " hypersensitivity"} -{"id": 41396, "token": "\u0120Contributions", "merges": "\u0120Cont ributions", "raw_count": 317, "count": 317, "decode_str": " Contributions"} -{"id": 28342, "token": "opathological", "merges": "opath ological", "raw_count": 198, "count": 317, "decode_str": "opathological"} -{"id": 31935, "token": "\u0120Institutes", "merges": "\u0120Instit utes", "raw_count": 317, "count": 317, "decode_str": " Institutes"} -{"id": 40801, "token": "Arabidopsis", "merges": "Arab idopsis", "raw_count": 317, "count": 317, "decode_str": "Arabidopsis"} -{"id": 37930, "token": "\u0120Nicole", "merges": "\u0120Nic ole", "raw_count": 317, "count": 317, "decode_str": " Nicole"} -{"id": 26865, "token": "\u0120NCAA", "merges": "\u0120NC AA", "raw_count": 317, "count": 317, "decode_str": " NCAA"} -{"id": 45357, "token": "\u0120cerebellar", "merges": "\u0120cereb ellar", "raw_count": 318, "count": 318, "decode_str": " cerebellar"} -{"id": 38901, "token": "menopausal", "merges": "men opausal", "raw_count": 318, "count": 318, "decode_str": "menopausal"} -{"id": 39591, "token": "\u0120aberrant", "merges": "\u0120aberr ant", "raw_count": 318, "count": 318, "decode_str": " aberrant"} -{"id": 45041, "token": "\u0120Bolton", "merges": "\u0120Bol ton", "raw_count": 318, "count": 318, "decode_str": " Bolton"} -{"id": 35262, "token": "\u0120Sophie", "merges": "\u0120Soph ie", "raw_count": 318, "count": 318, "decode_str": " Sophie"} -{"id": 38297, "token": "\u0120Sevent", "merges": "\u0120Se vent", "raw_count": 318, "count": 318, "decode_str": " Sevent"} -{"id": 49958, "token": "\u0120surgically", "merges": "\u0120surg ically", "raw_count": 319, "count": 319, "decode_str": " surgically"} -{"id": 43954, "token": "Certainly", "merges": "C ertainly", "raw_count": 319, "count": 319, "decode_str": "Certainly"} -{"id": 32000, "token": "\u0120Munich", "merges": "\u0120Mun ich", "raw_count": 319, "count": 319, "decode_str": " Munich"} -{"id": 25862, "token": "FFIR", "merges": "FF IR", "raw_count": 302, "count": 319, "decode_str": "FFIR"} -{"id": 45114, "token": "]}$", "merges": "] }$", "raw_count": 319, "count": 319, "decode_str": "]}$"} -{"id": 48914, "token": "\u0120\u00d8\u00a5", "merges": "\u0120\u00d8 \u00a5", "raw_count": 319, "count": 319, "decode_str": " \u0625"} -{"id": 37754, "token": "\u0120heterozygous", "merges": "\u0120heter ozygous", "raw_count": 320, "count": 320, "decode_str": " heterozygous"} -{"id": 36365, "token": "\u0120Squadron", "merges": "\u0120Squad ron", "raw_count": 320, "count": 320, "decode_str": " Squadron"} -{"id": 45124, "token": "\u0120Drugs", "merges": "\u0120Drug s", "raw_count": 320, "count": 320, "decode_str": " Drugs"} -{"id": 25748, "token": "ofluorescence", "merges": "oflu orescence", "raw_count": 239, "count": 321, "decode_str": "ofluorescence"} -{"id": 38873, "token": "\u0120preclinical", "merges": "\u0120pre clinical", "raw_count": 321, "count": 321, "decode_str": " preclinical"} -{"id": 41079, "token": "\u0120Religious", "merges": "\u0120Rel igious", "raw_count": 321, "count": 321, "decode_str": " Religious"} -{"id": 47356, "token": "\u0120proffered", "merges": "\u0120prof fered", "raw_count": 321, "count": 321, "decode_str": " proffered"} -{"id": 34655, "token": "\u0120Caroline", "merges": "\u0120Carol ine", "raw_count": 321, "count": 321, "decode_str": " Caroline"} -{"id": 46074, "token": "\u0120papill", "merges": "\u0120pap ill", "raw_count": 321, "count": 321, "decode_str": " papill"} -{"id": 46151, "token": "\u0120Injury", "merges": "\u0120In jury", "raw_count": 321, "count": 321, "decode_str": " Injury"} -{"id": 16146, "token": "\u0120Miami", "merges": "\u0120Mi ami", "raw_count": 321, "count": 321, "decode_str": " Miami"} -{"id": 17870, "token": "\u0120APPE", "merges": "\u0120AP PE", "raw_count": 318, "count": 321, "decode_str": " APPE"} -{"id": 50301, "token": "\u00e2\u0122\u00bf", "merges": "\u00e2\u0122 \u00bf", "raw_count": 321, "count": 321, "decode_str": "\u203f"} -{"id": 41604, "token": "}]$", "merges": "} ]$", "raw_count": 321, "count": 321, "decode_str": "}]$"} -{"id": 39358, "token": "\u0120renormalization", "merges": "\u0120renormal ization", "raw_count": 322, "count": 322, "decode_str": " renormalization"} -{"id": 43787, "token": "\u0120photosensitive", "merges": "\u0120photos ensitive", "raw_count": 322, "count": 322, "decode_str": " photosensitive"} -{"id": 44085, "token": "\u0120Connor", "merges": "\u0120Con nor", "raw_count": 322, "count": 322, "decode_str": " Connor"} -{"id": 49536, "token": "\u0120Sutton", "merges": "\u0120S utton", "raw_count": 322, "count": 322, "decode_str": " Sutton"} -{"id": 31913, "token": "\u0120Antar", "merges": "\u0120Ant ar", "raw_count": 136, "count": 322, "decode_str": " Antar"} -{"id": 49150, "token": "\u0120Leigh", "merges": "\u0120Le igh", "raw_count": 322, "count": 322, "decode_str": " Leigh"} -{"id": 49798, "token": "\u00cf\u0123\u00cf\u0129", "merges": "\u00cf\u0123 \u00cf\u0129", "raw_count": 322, "count": 322, "decode_str": "\u03c1\u03c7"} -{"id": 29830, "token": "\u0120\u00ce\u0137", "merges": "\u0120\u00ce \u0137", "raw_count": 322, "count": 322, "decode_str": " \u0395"} -{"id": 39588, "token": "\u0120progesterone", "merges": "\u0120pro gesterone", "raw_count": 323, "count": 323, "decode_str": " progesterone"} -{"id": 30545, "token": "\u0120sexuality", "merges": "\u0120sexual ity", "raw_count": 323, "count": 323, "decode_str": " sexuality"} -{"id": 25380, "token": "\u0120Richmond", "merges": "\u0120Rich mond", "raw_count": 323, "count": 323, "decode_str": " Richmond"} -{"id": 39102, "token": "\u0120Volks", "merges": "\u0120Vol ks", "raw_count": 212, "count": 323, "decode_str": " Volks"} -{"id": 34539, "token": "\u0120Armed", "merges": "\u0120Arm ed", "raw_count": 323, "count": 323, "decode_str": " Armed"} -{"id": 46888, "token": "\u0120Schematic", "merges": "\u0120Sc hematic", "raw_count": 324, "count": 324, "decode_str": " Schematic"} -{"id": 48408, "token": "\u0120Jennings", "merges": "\u0120Jenn ings", "raw_count": 324, "count": 324, "decode_str": " Jennings"} -{"id": 30036, "token": "mathtt", "merges": "mat htt", "raw_count": 324, "count": 324, "decode_str": "mathtt"} -{"id": 38366, "token": "\u0120\u00d1\u0123\u00d0\u00b5", "merges": "\u0120\u00d1\u0123 \u00d0\u00b5", "raw_count": 324, "count": 324, "decode_str": " \u0441\u0435"} -{"id": 39535, "token": "\u0120Buc", "merges": "\u0120B uc", "raw_count": 324, "count": 324, "decode_str": " Buc"} -{"id": 31741, "token": "\u0120RCT", "merges": "\u0120R CT", "raw_count": 324, "count": 324, "decode_str": " RCT"} -{"id": 33604, "token": "\u0120\u00c5\u00bce", "merges": "\u0120\u00c5\u00bc e", "raw_count": 324, "count": 324, "decode_str": " \u017ce"} -{"id": 50386, "token": "\u00e3\u0122\u0127", "merges": "\u00e3\u0122 \u0127", "raw_count": 324, "count": 324, "decode_str": "\u3005"} -{"id": 48438, "token": "\u0120Excellent", "merges": "\u0120Ex cellent", "raw_count": 325, "count": 325, "decode_str": " Excellent"} -{"id": 27447, "token": "oprecip", "merges": "op recip", "raw_count": 290, "count": 325, "decode_str": "oprecip"} -{"id": 28979, "token": "\u0120Hallow", "merges": "\u0120Hall ow", "raw_count": 88, "count": 325, "decode_str": " Hallow"} -{"id": 32509, "token": "\u0120Gerald", "merges": "\u0120G erald", "raw_count": 325, "count": 325, "decode_str": " Gerald"} -{"id": 35460, "token": "\u0120THEY", "merges": "\u0120THE Y", "raw_count": 325, "count": 325, "decode_str": " THEY"} -{"id": 43342, "token": "\u0120Cobb", "merges": "\u0120C obb", "raw_count": 325, "count": 325, "decode_str": " Cobb"} -{"id": 45098, "token": "printStackTrace", "merges": "print StackTrace", "raw_count": 326, "count": 326, "decode_str": "printStackTrace"} -{"id": 44924, "token": "\u0120reperfusion", "merges": "\u0120reper fusion", "raw_count": 326, "count": 326, "decode_str": " reperfusion"} -{"id": 35120, "token": "\u0120immunoglob", "merges": "\u0120immun oglob", "raw_count": 58, "count": 326, "decode_str": " immunoglob"} -{"id": 42991, "token": "\u0120Pinterest", "merges": "\u0120P interest", "raw_count": 326, "count": 326, "decode_str": " Pinterest"} -{"id": 38881, "token": "\u0120Phillip", "merges": "\u0120Phill ip", "raw_count": 326, "count": 326, "decode_str": " Phillip"} -{"id": 45358, "token": "\u0120Prayer", "merges": "\u0120Pray er", "raw_count": 326, "count": 326, "decode_str": " Prayer"} -{"id": 30016, "token": "\u0120Jama", "merges": "\u0120J ama", "raw_count": 242, "count": 326, "decode_str": " Jama"} -{"id": 44415, "token": "\u0120Heck", "merges": "\u0120He ck", "raw_count": 326, "count": 326, "decode_str": " Heck"} -{"id": 43399, "token": "\u0120SUCH", "merges": "\u0120SU CH", "raw_count": 326, "count": 326, "decode_str": " SUCH"} -{"id": 35691, "token": "\u0120\u00cf\u0122\u00ce\u00b1", "merges": "\u0120\u00cf\u0122 \u00ce\u00b1", "raw_count": 326, "count": 326, "decode_str": " \u03c0\u03b1"} -{"id": 50005, "token": "\u0120Tud", "merges": "\u0120T ud", "raw_count": 326, "count": 326, "decode_str": " Tud"} -{"id": 33750, "token": "\u0120.=", "merges": "\u0120. =", "raw_count": 326, "count": 326, "decode_str": " .="} -{"id": 31127, "token": "\u0120Glasgow", "merges": "\u0120Gl asgow", "raw_count": 327, "count": 327, "decode_str": " Glasgow"} -{"id": 34412, "token": "\u0120Brigade", "merges": "\u0120Brig ade", "raw_count": 327, "count": 327, "decode_str": " Brigade"} -{"id": 38809, "token": "\u0120Twelve", "merges": "\u0120Tw elve", "raw_count": 327, "count": 327, "decode_str": " Twelve"} -{"id": 49126, "token": "\u0120Docket", "merges": "\u0120D ocket", "raw_count": 327, "count": 327, "decode_str": " Docket"} -{"id": 27850, "token": "\u0120Milan", "merges": "\u0120Mil an", "raw_count": 327, "count": 327, "decode_str": " Milan"} -{"id": 37800, "token": "opically", "merges": "op ically", "raw_count": 328, "count": 328, "decode_str": "opically"} -{"id": 42171, "token": "\u0120Vernon", "merges": "\u0120Vern on", "raw_count": 328, "count": 328, "decode_str": " Vernon"} -{"id": 44070, "token": "\u0120___,", "merges": "\u0120___ ,", "raw_count": 328, "count": 328, "decode_str": " ___,"} -{"id": 31038, "token": "\u0120\u00e2\u0122\u0142", "merges": "\u0120\u00e2\u0122 \u0142", "raw_count": 328, "count": 328, "decode_str": " \u2020"} -{"id": 48872, "token": "\u0120OCD", "merges": "\u0120O CD", "raw_count": 328, "count": 328, "decode_str": " OCD"} -{"id": 36781, "token": "\u0120Socialist", "merges": "\u0120Social ist", "raw_count": 329, "count": 329, "decode_str": " Socialist"} -{"id": 26323, "token": "\u0120tambi\u00c3\u00a9n", "merges": "\u0120tamb i\u00c3\u00a9n", "raw_count": 329, "count": 329, "decode_str": " tambi\u00e9n"} -{"id": 42305, "token": "\u0120Derby", "merges": "\u0120Der by", "raw_count": 329, "count": 329, "decode_str": " Derby"} -{"id": 42944, "token": "]{};", "merges": "]{} ;", "raw_count": 329, "count": 329, "decode_str": "]{};"} -{"id": 36686, "token": "\u0120Quantitative", "merges": "\u0120Quant itative", "raw_count": 330, "count": 330, "decode_str": " Quantitative"} -{"id": 30617, "token": "\u0120mucosal", "merges": "\u0120muc osal", "raw_count": 330, "count": 330, "decode_str": " mucosal"} -{"id": 44495, "token": "\u0120Jerome", "merges": "\u0120Jer ome", "raw_count": 330, "count": 330, "decode_str": " Jerome"} -{"id": 36912, "token": "\u0120M\u00c3\u00a9", "merges": "\u0120M \u00c3\u00a9", "raw_count": 330, "count": 330, "decode_str": " M\u00e9"} -{"id": 33465, "token": "\u0120\u00e0\u00a4\u00b8", "merges": "\u0120\u00e0\u00a4 \u00b8", "raw_count": 330, "count": 330, "decode_str": " \u0938"} -{"id": 40307, "token": "\u0120EBV", "merges": "\u0120E BV", "raw_count": 330, "count": 330, "decode_str": " EBV"} -{"id": 46802, "token": "*>(", "merges": "* >(", "raw_count": 330, "count": 330, "decode_str": "*>("} -{"id": 49796, "token": "\u0120corticosteroids", "merges": "\u0120corticoster oids", "raw_count": 331, "count": 331, "decode_str": " corticosteroids"} -{"id": 19802, "token": "\u0120Cleveland", "merges": "\u0120C leveland", "raw_count": 331, "count": 331, "decode_str": " Cleveland"} -{"id": 10737, "token": "\u0120Amendment", "merges": "\u0120Am endment", "raw_count": 331, "count": 331, "decode_str": " Amendment"} -{"id": 39191, "token": "\u0120yogurt", "merges": "\u0120yog urt", "raw_count": 331, "count": 331, "decode_str": " yogurt"} -{"id": 38625, "token": "\u0120Fifty", "merges": "\u0120Fif ty", "raw_count": 331, "count": 331, "decode_str": " Fifty"} -{"id": 40537, "token": "\u0120Erik", "merges": "\u0120E rik", "raw_count": 331, "count": 331, "decode_str": " Erik"} -{"id": 18679, "token": "\u0120s\u00c3\u00a5", "merges": "\u0120s \u00c3\u00a5", "raw_count": 331, "count": 331, "decode_str": " s\u00e5"} -{"id": 46817, "token": "\u0120Ramsey", "merges": "\u0120Ram sey", "raw_count": 332, "count": 332, "decode_str": " Ramsey"} -{"id": 25164, "token": "\u0120Sixth", "merges": "\u0120Six th", "raw_count": 332, "count": 332, "decode_str": " Sixth"} -{"id": 43516, "token": "\u0120Oslo", "merges": "\u0120O slo", "raw_count": 332, "count": 332, "decode_str": " Oslo"} -{"id": 41489, "token": "otherapeutic", "merges": "othe rapeutic", "raw_count": 333, "count": 333, "decode_str": "otherapeutic"} -{"id": 35948, "token": "\u0120peritoneal", "merges": "\u0120per itoneal", "raw_count": 333, "count": 333, "decode_str": " peritoneal"} -{"id": 26529, "token": "\u0120Testament", "merges": "\u0120Test ament", "raw_count": 333, "count": 333, "decode_str": " Testament"} -{"id": 50087, "token": "\u0120Thornton", "merges": "\u0120Thorn ton", "raw_count": 333, "count": 333, "decode_str": " Thornton"} -{"id": 34071, "token": "\u0120glycerol", "merges": "\u0120glycer ol", "raw_count": 333, "count": 333, "decode_str": " glycerol"} -{"id": 47651, "token": "\u0120Managing", "merges": "\u0120Man aging", "raw_count": 333, "count": 333, "decode_str": " Managing"} -{"id": 47589, "token": "\u0120genom", "merges": "\u0120gen om", "raw_count": 333, "count": 333, "decode_str": " genom"} -{"id": 22974, "token": "\\!\\", "merges": "\\! \\", "raw_count": 333, "count": 333, "decode_str": "\\!\\"} -{"id": 40102, "token": "\u0120histology", "merges": "\u0120hist ology", "raw_count": 334, "count": 334, "decode_str": " histology"} -{"id": 7108, "token": "\u0120Americans", "merges": "\u0120Americ ans", "raw_count": 334, "count": 334, "decode_str": " Americans"} -{"id": 46388, "token": "\u0120pleural", "merges": "\u0120ple ural", "raw_count": 334, "count": 334, "decode_str": " pleural"} -{"id": 37601, "token": "\u0120Britt", "merges": "\u0120Br itt", "raw_count": 334, "count": 334, "decode_str": " Britt"} -{"id": 47784, "token": "\u0120Nurse", "merges": "\u0120N urse", "raw_count": 334, "count": 334, "decode_str": " Nurse"} -{"id": 14986, "token": "\u0120\u00ce\u00bcg", "merges": "\u0120\u00ce\u00bc g", "raw_count": 334, "count": 334, "decode_str": " \u03bcg"} -{"id": 13061, "token": "_{(", "merges": "_{ (", "raw_count": 334, "count": 334, "decode_str": "_{("} -{"id": 15097, "token": "\u00c3\u013b", "merges": "\u00c3 \u013b", "raw_count": 334, "count": 334, "decode_str": "\u00d9"} -{"id": 24163, "token": "Competing", "merges": "Comp eting", "raw_count": 335, "count": 335, "decode_str": "Competing"} -{"id": 15812, "token": "\u0120Maryland", "merges": "\u0120Mary land", "raw_count": 335, "count": 335, "decode_str": " Maryland"} -{"id": 43522, "token": "\u0120Randall", "merges": "\u0120Rand all", "raw_count": 335, "count": 335, "decode_str": " Randall"} -{"id": 44311, "token": "\u0120quien", "merges": "\u0120qu ien", "raw_count": 335, "count": 335, "decode_str": " quien"} -{"id": 49614, "token": "Docket", "merges": "D ocket", "raw_count": 335, "count": 335, "decode_str": "Docket"} -{"id": 46533, "token": "\u0120CLAIM", "merges": "\u0120CLA IM", "raw_count": 335, "count": 335, "decode_str": " CLAIM"} -{"id": 44484, "token": "\u0120Sart", "merges": "\u0120S art", "raw_count": 335, "count": 335, "decode_str": " Sart"} -{"id": 9929, "token": "\u0120$-", "merges": "\u0120$ -", "raw_count": 313, "count": 335, "decode_str": " $-"} -{"id": 40469, "token": "\u0120immunological", "merges": "\u0120immun ological", "raw_count": 336, "count": 336, "decode_str": " immunological"} -{"id": 42793, "token": "\u0120prefrontal", "merges": "\u0120pre frontal", "raw_count": 336, "count": 336, "decode_str": " prefrontal"} -{"id": 34427, "token": "osexuality", "merges": "osex uality", "raw_count": 190, "count": 336, "decode_str": "osexuality"} -{"id": 46596, "token": "\u0120particul", "merges": "\u0120partic ul", "raw_count": 336, "count": 336, "decode_str": " particul"} -{"id": 41547, "token": "\u0120Speaking", "merges": "\u0120Spe aking", "raw_count": 336, "count": 336, "decode_str": " Speaking"} -{"id": 47420, "token": "\u0120Hassan", "merges": "\u0120Hass an", "raw_count": 336, "count": 336, "decode_str": " Hassan"} -{"id": 32519, "token": "\u0120juror", "merges": "\u0120jur or", "raw_count": 336, "count": 336, "decode_str": " juror"} -{"id": 47662, "token": "\u0120Lah", "merges": "\u0120L ah", "raw_count": 336, "count": 336, "decode_str": " Lah"} -{"id": 13566, "token": "^{+", "merges": "^{ +", "raw_count": 336, "count": 336, "decode_str": "^{+"} -{"id": 35838, "token": "Acknowledgements", "merges": "Acknowled gements", "raw_count": 337, "count": 337, "decode_str": "Acknowledgements"} -{"id": 24129, "token": "\u0120Hampshire", "merges": "\u0120Ham pshire", "raw_count": 337, "count": 337, "decode_str": " Hampshire"} -{"id": 44423, "token": "\u0120radially", "merges": "\u0120rad ially", "raw_count": 337, "count": 337, "decode_str": " radially"} -{"id": 31113, "token": "\u0120fibrin", "merges": "\u0120fibr in", "raw_count": 337, "count": 337, "decode_str": " fibrin"} -{"id": 39864, "token": "\u0120amyg", "merges": "\u0120am yg", "raw_count": 109, "count": 337, "decode_str": " amyg"} -{"id": 29092, "token": "\u0120Joshua", "merges": "\u0120Josh ua", "raw_count": 338, "count": 338, "decode_str": " Joshua"} -{"id": 32425, "token": "\u0120Lesser", "merges": "\u0120Less er", "raw_count": 338, "count": 338, "decode_str": " Lesser"} -{"id": 39370, "token": "\u0120Kenny", "merges": "\u0120K enny", "raw_count": 338, "count": 338, "decode_str": " Kenny"} -{"id": 44193, "token": "\u00c3\u00a1nd", "merges": "\u00c3\u00a1 nd", "raw_count": 338, "count": 338, "decode_str": "\u00e1nd"} -{"id": 33948, "token": "\u0120RBC", "merges": "\u0120R BC", "raw_count": 338, "count": 338, "decode_str": " RBC"} -{"id": 30299, "token": "\u0120Citizens", "merges": "\u0120Cit izens", "raw_count": 339, "count": 339, "decode_str": " Citizens"} -{"id": 28244, "token": "\u0120Admiral", "merges": "\u0120Adm iral", "raw_count": 339, "count": 339, "decode_str": " Admiral"} -{"id": 38922, "token": "\u0120tachy", "merges": "\u0120t achy", "raw_count": 339, "count": 339, "decode_str": " tachy"} -{"id": 23894, "token": "\u0120Uncle", "merges": "\u0120Un cle", "raw_count": 339, "count": 339, "decode_str": " Uncle"} -{"id": 22206, "token": "\u00cf\u0126\u00ce\u00b9\u00ce\u00ba", "merges": "\u00cf\u0126 \u00ce\u00b9\u00ce\u00ba", "raw_count": 339, "count": 339, "decode_str": "\u03c4\u03b9\u03ba"} -{"id": 45921, "token": "\u0120USDA", "merges": "\u0120US DA", "raw_count": 339, "count": 339, "decode_str": " USDA"} -{"id": 44836, "token": "\u0120habe", "merges": "\u0120hab e", "raw_count": 339, "count": 339, "decode_str": " habe"} -{"id": 18391, "token": "\u00e2\u012a\u0139", "merges": "\u00e2\u012a \u0139", "raw_count": 331, "count": 339, "decode_str": "\u2217"} -{"id": 41259, "token": "othelium", "merges": "othe lium", "raw_count": 186, "count": 340, "decode_str": "othelium"} -{"id": 31534, "token": "\u0120Persian", "merges": "\u0120Pers ian", "raw_count": 340, "count": 340, "decode_str": " Persian"} -{"id": 45777, "token": "\u0120tibial", "merges": "\u0120tib ial", "raw_count": 340, "count": 340, "decode_str": " tibial"} -{"id": 45790, "token": "\u0120Olivia", "merges": "\u0120Ol ivia", "raw_count": 340, "count": 340, "decode_str": " Olivia"} -{"id": 23920, "token": "\u0120Carib", "merges": "\u0120Car ib", "raw_count": 99, "count": 340, "decode_str": " Carib"} -{"id": 15207, "token": ")^{\\", "merges": ") ^{\\", "raw_count": 340, "count": 340, "decode_str": ")^{\\"} -{"id": 43378, "token": "\u0120MTT", "merges": "\u0120M TT", "raw_count": 340, "count": 340, "decode_str": " MTT"} -{"id": 41216, "token": "\u0120Abe", "merges": "\u0120A be", "raw_count": 340, "count": 340, "decode_str": " Abe"} -{"id": 50656, "token": "\u00e5\u0124\u013c", "merges": "\u00e5\u0124 \u013c", "raw_count": 340, "count": 340, "decode_str": "\u509a"} -{"id": 49234, "token": "\u0120Hastings", "merges": "\u0120H astings", "raw_count": 341, "count": 341, "decode_str": " Hastings"} -{"id": 27899, "token": "\u0120Columbus", "merges": "\u0120Columb us", "raw_count": 341, "count": 341, "decode_str": " Columbus"} -{"id": 33808, "token": "\u0120Seventh", "merges": "\u0120Se venth", "raw_count": 341, "count": 341, "decode_str": " Seventh"} -{"id": 46262, "token": "\u0120Dalton", "merges": "\u0120Dal ton", "raw_count": 341, "count": 341, "decode_str": " Dalton"} -{"id": 29545, "token": "ligt", "merges": "lig t", "raw_count": 341, "count": 341, "decode_str": "ligt"} -{"id": 51125, "token": "\u00e5\u0138\u00ab", "merges": "\u00e5\u0138 \u00ab", "raw_count": 341, "count": 341, "decode_str": "\u55ab"} -{"id": 50356, "token": "\u00e2\u0138\u0125", "merges": "\u00e2\u0138 \u0125", "raw_count": 341, "count": 341, "decode_str": "\u2583"} -{"id": 49192, "token": "\u0120inactivated", "merges": "\u0120in activated", "raw_count": 342, "count": 342, "decode_str": " inactivated"} -{"id": 22592, "token": "\u0120monoclonal", "merges": "\u0120mon oclonal", "raw_count": 342, "count": 342, "decode_str": " monoclonal"} -{"id": 40052, "token": "\u0120judicata", "merges": "\u0120judic ata", "raw_count": 342, "count": 342, "decode_str": " judicata"} -{"id": 13169, "token": "\u0120Arizona", "merges": "\u0120Ari zona", "raw_count": 342, "count": 342, "decode_str": " Arizona"} -{"id": 39944, "token": "\u0120Vitamin", "merges": "\u0120Vit amin", "raw_count": 342, "count": 342, "decode_str": " Vitamin"} -{"id": 47429, "token": "\u0120Fargo", "merges": "\u0120F argo", "raw_count": 342, "count": 342, "decode_str": " Fargo"} -{"id": 31071, "token": "\u0120Winn", "merges": "\u0120W inn", "raw_count": 303, "count": 342, "decode_str": " Winn"} -{"id": 16595, "token": "\u0120\u00e2\u0122\u013e[", "merges": "\u0120\u00e2\u0122\u013e [", "raw_count": 342, "count": 342, "decode_str": " \u201c["} -{"id": 21433, "token": "\u0120\u00e0\u00a4\u0137", "merges": "\u0120\u00e0\u00a4 \u0137", "raw_count": 342, "count": 342, "decode_str": " \u0915"} -{"id": 38083, "token": "\u00c3\u00a4s", "merges": "\u00c3\u00a4 s", "raw_count": 284, "count": 342, "decode_str": "\u00e4s"} -{"id": 19002, "token": "})=", "merges": "}) =", "raw_count": 342, "count": 342, "decode_str": "})="} -{"id": 30068, "token": "\u0120Regiment", "merges": "\u0120Reg iment", "raw_count": 343, "count": 343, "decode_str": " Regiment"} -{"id": 36327, "token": "\u0120heparin", "merges": "\u0120hepar in", "raw_count": 343, "count": 343, "decode_str": " heparin"} -{"id": 25936, "token": "\u0120Redist", "merges": "\u0120Red ist", "raw_count": 329, "count": 343, "decode_str": " Redist"} -{"id": 19141, "token": "cancers", "merges": "c ancers", "raw_count": 343, "count": 343, "decode_str": "cancers"} -{"id": 37762, "token": "\u0120leurs", "merges": "\u0120le urs", "raw_count": 343, "count": 343, "decode_str": " leurs"} -{"id": 23102, "token": "}},\\", "merges": "}} ,\\", "raw_count": 343, "count": 343, "decode_str": "}},\\"} -{"id": 48723, "token": "\u0120dysplasia", "merges": "\u0120dys plasia", "raw_count": 344, "count": 344, "decode_str": " dysplasia"} -{"id": 48771, "token": "\u0120Bangkok", "merges": "\u0120Bang kok", "raw_count": 344, "count": 344, "decode_str": " Bangkok"} -{"id": 33654, "token": "\u0120keratin", "merges": "\u0120ker atin", "raw_count": 344, "count": 344, "decode_str": " keratin"} -{"id": 48982, "token": "\u0120Humans", "merges": "\u0120Hum ans", "raw_count": 344, "count": 344, "decode_str": " Humans"} -{"id": 43795, "token": "\u0120Ordin", "merges": "\u0120Or din", "raw_count": 344, "count": 344, "decode_str": " Ordin"} -{"id": 46863, "token": "rogens", "merges": "rog ens", "raw_count": 344, "count": 344, "decode_str": "rogens"} -{"id": 45641, "token": "\u0120toim", "merges": "\u0120to im", "raw_count": 344, "count": 344, "decode_str": " toim"} -{"id": 45557, "token": "\u0120Cous", "merges": "\u0120C ous", "raw_count": 344, "count": 344, "decode_str": " Cous"} -{"id": 29398, "token": "\u0120adjuvant", "merges": "\u0120adj uvant", "raw_count": 345, "count": 345, "decode_str": " adjuvant"} -{"id": 39498, "token": "\u0120salivary", "merges": "\u0120saliv ary", "raw_count": 345, "count": 345, "decode_str": " salivary"} -{"id": 48465, "token": "\u0120Biomed", "merges": "\u0120Bi omed", "raw_count": 345, "count": 345, "decode_str": " Biomed"} -{"id": 32577, "token": "\u0120Sally", "merges": "\u0120S ally", "raw_count": 345, "count": 345, "decode_str": " Sally"} -{"id": 24056, "token": "\u0120jeg", "merges": "\u0120j eg", "raw_count": 345, "count": 345, "decode_str": " jeg"} -{"id": 39042, "token": "\u0120apparatuses", "merges": "\u0120apparatus es", "raw_count": 346, "count": 346, "decode_str": " apparatuses"} -{"id": 45706, "token": "\u0120Analyses", "merges": "\u0120Anal yses", "raw_count": 346, "count": 346, "decode_str": " Analyses"} -{"id": 42707, "token": "\u0120Evangel", "merges": "\u0120Ev angel", "raw_count": 346, "count": 346, "decode_str": " Evangel"} -{"id": 35502, "token": "\u0120Divine", "merges": "\u0120Div ine", "raw_count": 346, "count": 346, "decode_str": " Divine"} -{"id": 32164, "token": "\u0120Schr", "merges": "\u0120Sch r", "raw_count": 314, "count": 346, "decode_str": " Schr"} -{"id": 32726, "token": "\u0120Mitt", "merges": "\u0120M itt", "raw_count": 346, "count": 346, "decode_str": " Mitt"} -{"id": 42767, "token": "]{\\", "merges": "] {\\", "raw_count": 346, "count": 346, "decode_str": "]{\\"} -{"id": 48357, "token": "\u0120Casual", "merges": "\u0120Cas ual", "raw_count": 347, "count": 347, "decode_str": " Casual"} -{"id": 40476, "token": "\u0120fecal", "merges": "\u0120fe cal", "raw_count": 347, "count": 347, "decode_str": " fecal"} -{"id": 37144, "token": "\u0120Evan", "merges": "\u0120Ev an", "raw_count": 347, "count": 347, "decode_str": " Evan"} -{"id": 42586, "token": "\u0120Dans", "merges": "\u0120D ans", "raw_count": 347, "count": 347, "decode_str": " Dans"} -{"id": 27079, "token": "\u0120COPD", "merges": "\u0120COP D", "raw_count": 347, "count": 347, "decode_str": " COPD"} -{"id": 30630, "token": "\u0120Stephan", "merges": "\u0120Ste phan", "raw_count": 204, "count": 348, "decode_str": " Stephan"} -{"id": 29495, "token": "\u0120\u00ce\u00b5\u00cf\u0122", "merges": "\u0120\u00ce\u00b5 \u00cf\u0122", "raw_count": 181, "count": 348, "decode_str": " \u03b5\u03c0"} -{"id": 33519, "token": "\u0120Suff", "merges": "\u0120S uff", "raw_count": 348, "count": 348, "decode_str": " Suff"} -{"id": 31479, "token": "\u0120Liz", "merges": "\u0120L iz", "raw_count": 348, "count": 348, "decode_str": " Liz"} -{"id": 42512, "token": "\u0120GSH", "merges": "\u0120G SH", "raw_count": 348, "count": 348, "decode_str": " GSH"} -{"id": 50338, "token": "\u00e2\u0136\u0127", "merges": "\u00e2\u0136 \u0127", "raw_count": 348, "count": 348, "decode_str": "\u2505"} -{"id": 24394, "token": "\u0120histological", "merges": "\u0120hist ological", "raw_count": 349, "count": 349, "decode_str": " histological"} -{"id": 19798, "token": "\u0120metastatic", "merges": "\u0120metast atic", "raw_count": 349, "count": 349, "decode_str": " metastatic"} -{"id": 31681, "token": "\u0120NSString", "merges": "\u0120NS String", "raw_count": 349, "count": 349, "decode_str": " NSString"} -{"id": 35767, "token": "otoxicity", "merges": "otox icity", "raw_count": 349, "count": 349, "decode_str": "otoxicity"} -{"id": 50240, "token": "\u0120Revised", "merges": "\u0120Rev ised", "raw_count": 349, "count": 349, "decode_str": " Revised"} -{"id": 40002, "token": "ticas", "merges": "tic as", "raw_count": 349, "count": 349, "decode_str": "ticas"} -{"id": 48403, "token": "\u0120Rousseau", "merges": "\u0120R ousseau", "raw_count": 350, "count": 350, "decode_str": " Rousseau"} -{"id": 36965, "token": "\u0120Diane", "merges": "\u0120D iane", "raw_count": 350, "count": 350, "decode_str": " Diane"} -{"id": 48488, "token": "\u0120JOHN", "merges": "\u0120J OHN", "raw_count": 350, "count": 350, "decode_str": " JOHN"} -{"id": 28675, "token": "\u0120Fla", "merges": "\u0120Fl a", "raw_count": 350, "count": 350, "decode_str": " Fla"} -{"id": 20896, "token": "\u0120biomarkers", "merges": "\u0120biomark ers", "raw_count": 351, "count": 351, "decode_str": " biomarkers"} -{"id": 43018, "token": "\u0120clinician", "merges": "\u0120clin ician", "raw_count": 351, "count": 351, "decode_str": " clinician"} -{"id": 15636, "token": "\u0120Governor", "merges": "\u0120Govern or", "raw_count": 351, "count": 351, "decode_str": " Governor"} -{"id": 20159, "token": "\u0120Orleans", "merges": "\u0120Or leans", "raw_count": 351, "count": 351, "decode_str": " Orleans"} -{"id": 32714, "token": "\u0120Toyota", "merges": "\u0120Toy ota", "raw_count": 351, "count": 351, "decode_str": " Toyota"} -{"id": 29654, "token": "\u0120Kash", "merges": "\u0120K ash", "raw_count": 281, "count": 351, "decode_str": " Kash"} -{"id": 27913, "token": "\u0120microarray", "merges": "\u0120micro array", "raw_count": 352, "count": 352, "decode_str": " microarray"} -{"id": 49237, "token": "\u0120ganglia", "merges": "\u0120gang lia", "raw_count": 352, "count": 352, "decode_str": " ganglia"} -{"id": 47716, "token": "\u0120hemod", "merges": "\u0120he mod", "raw_count": 352, "count": 352, "decode_str": " hemod"} -{"id": 24292, "token": "\u0120\u00ce\u0143", "merges": "\u0120\u00ce \u0143", "raw_count": 352, "count": 352, "decode_str": " \u03ad"} -{"id": 13655, "token": "\u0120phosphorylation", "merges": "\u0120phosphory lation", "raw_count": 353, "count": 353, "decode_str": " phosphorylation"} -{"id": 19056, "token": "Plaintiff", "merges": "Pl aintiff", "raw_count": 326, "count": 353, "decode_str": "Plaintiff"} -{"id": 39570, "token": "\u0120grafts", "merges": "\u0120graft s", "raw_count": 353, "count": 353, "decode_str": " grafts"} -{"id": 30168, "token": "\u0120Buddh", "merges": "\u0120Budd h", "raw_count": 67, "count": 353, "decode_str": " Buddh"} -{"id": 49057, "token": "\u0120Trin", "merges": "\u0120Tr in", "raw_count": 353, "count": 353, "decode_str": " Trin"} -{"id": 28649, "token": "\u00ce\u00bf\u00ce\u00bd", "merges": "\u00ce\u00bf \u00ce\u00bd", "raw_count": 353, "count": 353, "decode_str": "\u03bf\u03bd"} -{"id": 24029, "token": "\u00c3\u0131", "merges": "\u00c3 \u0131", "raw_count": 353, "count": 353, "decode_str": "\u00cf"} -{"id": 43121, "token": "\u0120analogs", "merges": "\u0120analog s", "raw_count": 354, "count": 354, "decode_str": " analogs"} -{"id": 43711, "token": "olateral", "merges": "ol ateral", "raw_count": 354, "count": 354, "decode_str": "olateral"} -{"id": 27999, "token": "\u0120homot", "merges": "\u0120hom ot", "raw_count": 66, "count": 354, "decode_str": " homot"} -{"id": 43093, "token": "\u0120Nile", "merges": "\u0120N ile", "raw_count": 354, "count": 354, "decode_str": " Nile"} -{"id": 34758, "token": "[{\\", "merges": "[ {\\", "raw_count": 354, "count": 354, "decode_str": "[{\\"} -{"id": 46380, "token": "\u0120despu\u00c3\u00a9s", "merges": "\u0120des pu\u00c3\u00a9s", "raw_count": 355, "count": 355, "decode_str": " despu\u00e9s"} -{"id": 42953, "token": "\u0120Edmund", "merges": "\u0120Ed mund", "raw_count": 355, "count": 355, "decode_str": " Edmund"} -{"id": 23239, "token": "\u0120Jake", "merges": "\u0120J ake", "raw_count": 355, "count": 355, "decode_str": " Jake"} -{"id": 39402, "token": "k\u00c3\u00a4", "merges": "k \u00c3\u00a4", "raw_count": 355, "count": 355, "decode_str": "k\u00e4"} -{"id": 45521, "token": "\u0120grandes", "merges": "\u0120grand es", "raw_count": 356, "count": 356, "decode_str": " grandes"} -{"id": 20498, "token": "\u0120Arabia", "merges": "\u0120Arab ia", "raw_count": 356, "count": 356, "decode_str": " Arabia"} -{"id": 45561, "token": "\u0120Aires", "merges": "\u0120A ires", "raw_count": 356, "count": 356, "decode_str": " Aires"} -{"id": 52560, "token": "\u00e6\u00b4\u00a9", "merges": "\u00e6\u00b4 \u00a9", "raw_count": 356, "count": 356, "decode_str": "\u6d29"} -{"id": 32576, "token": "\u0120Institutional", "merges": "\u0120In stitutional", "raw_count": 357, "count": 357, "decode_str": " Institutional"} -{"id": 41155, "token": "\u0120eukaryotic", "merges": "\u0120eukary otic", "raw_count": 357, "count": 357, "decode_str": " eukaryotic"} -{"id": 43870, "token": "\u0120neuropsych", "merges": "\u0120neuro psych", "raw_count": 357, "count": 357, "decode_str": " neuropsych"} -{"id": 39776, "token": "\u0120Triton", "merges": "\u0120T riton", "raw_count": 357, "count": 357, "decode_str": " Triton"} -{"id": 35665, "token": "\u0120Boris", "merges": "\u0120Bor is", "raw_count": 357, "count": 357, "decode_str": " Boris"} -{"id": 46174, "token": "\u0120Jagu", "merges": "\u0120J agu", "raw_count": 357, "count": 357, "decode_str": " Jagu"} -{"id": 44534, "token": "\u0120Mug", "merges": "\u0120M ug", "raw_count": 357, "count": 357, "decode_str": " Mug"} -{"id": 6922, "token": "}}_{", "merges": "}} _{", "raw_count": 357, "count": 357, "decode_str": "}}_{"} -{"id": 22457, "token": "downarrow", "merges": "down arrow", "raw_count": 358, "count": 358, "decode_str": "downarrow"} -{"id": 27045, "token": "\u0120Syscall", "merges": "\u0120S yscall", "raw_count": 358, "count": 358, "decode_str": " Syscall"} -{"id": 30593, "token": "\u0120amyloid", "merges": "\u0120amyl oid", "raw_count": 358, "count": 358, "decode_str": " amyloid"} -{"id": 22200, "token": "\u0120Charl", "merges": "\u0120Char l", "raw_count": 322, "count": 358, "decode_str": " Charl"} -{"id": 22635, "token": "\\**", "merges": "\\ **", "raw_count": 358, "count": 358, "decode_str": "\\**"} -{"id": 17732, "token": "\u0120\u00c3\u0127", "merges": "\u0120\u00c3 \u0127", "raw_count": 358, "count": 358, "decode_str": " \u00c5"} -{"id": 29605, "token": "\u0120reactivity", "merges": "\u0120react ivity", "raw_count": 359, "count": 359, "decode_str": " reactivity"} -{"id": 25270, "token": "\u0120Finland", "merges": "\u0120Fin land", "raw_count": 359, "count": 359, "decode_str": " Finland"} -{"id": 37225, "token": "\u0120Wilcox", "merges": "\u0120Wil cox", "raw_count": 158, "count": 359, "decode_str": " Wilcox"} -{"id": 44807, "token": "\u0120questa", "merges": "\u0120quest a", "raw_count": 359, "count": 359, "decode_str": " questa"} -{"id": 42421, "token": "\u0120Tribe", "merges": "\u0120Trib e", "raw_count": 359, "count": 359, "decode_str": " Tribe"} -{"id": 46980, "token": "\u0120Rita", "merges": "\u0120R ita", "raw_count": 359, "count": 359, "decode_str": " Rita"} -{"id": 48801, "token": "\u0120Nina", "merges": "\u0120N ina", "raw_count": 359, "count": 359, "decode_str": " Nina"} -{"id": 29704, "token": "\u00ce\u00bb\u00ce\u00bb", "merges": "\u00ce\u00bb \u00ce\u00bb", "raw_count": 359, "count": 359, "decode_str": "\u03bb\u03bb"} -{"id": 28651, "token": "\u0120Iceland", "merges": "\u0120I celand", "raw_count": 360, "count": 360, "decode_str": " Iceland"} -{"id": 49892, "token": "\u0120Coca", "merges": "\u0120C oca", "raw_count": 360, "count": 360, "decode_str": " Coca"} -{"id": 35113, "token": "\u00c4\u00be", "merges": "\u00c4 \u00be", "raw_count": 360, "count": 360, "decode_str": "\u013e"} -{"id": 14289, "token": "\u0120Philadelphia", "merges": "\u0120Phil adelphia", "raw_count": 361, "count": 361, "decode_str": " Philadelphia"} -{"id": 42392, "token": "\u0120flexion", "merges": "\u0120flex ion", "raw_count": 361, "count": 361, "decode_str": " flexion"} -{"id": 32903, "token": "\u0120heeft", "merges": "\u0120he eft", "raw_count": 361, "count": 361, "decode_str": " heeft"} -{"id": 34012, "token": "\u0120Midd", "merges": "\u0120M idd", "raw_count": 361, "count": 361, "decode_str": " Midd"} -{"id": 46271, "token": "\u0120antipsych", "merges": "\u0120ant ipsych", "raw_count": 362, "count": 362, "decode_str": " antipsych"} -{"id": 22300, "token": "\u0120Likewise", "merges": "\u0120Like wise", "raw_count": 362, "count": 362, "decode_str": " Likewise"} -{"id": 46242, "token": "\u0120Sisters", "merges": "\u0120S isters", "raw_count": 362, "count": 362, "decode_str": " Sisters"} -{"id": 34327, "token": "\u0120Maggie", "merges": "\u0120Mag gie", "raw_count": 362, "count": 362, "decode_str": " Maggie"} -{"id": 21665, "token": "\u0120Chel", "merges": "\u0120C hel", "raw_count": 128, "count": 362, "decode_str": " Chel"} -{"id": 42601, "token": "\u0120Riemannian", "merges": "\u0120Riemann ian", "raw_count": 363, "count": 363, "decode_str": " Riemannian"} -{"id": 14732, "token": "\u0120COURT", "merges": "\u0120COU RT", "raw_count": 363, "count": 363, "decode_str": " COURT"} -{"id": 47039, "token": "\u0120bara", "merges": "\u0120bar a", "raw_count": 363, "count": 363, "decode_str": " bara"} -{"id": 40980, "token": "r\u00c3\u0143a", "merges": "r \u00c3\u0143a", "raw_count": 363, "count": 363, "decode_str": "r\u00eda"} -{"id": 15431, "token": "\u0120macrophages", "merges": "\u0120macroph ages", "raw_count": 364, "count": 364, "decode_str": " macrophages"} -{"id": 18908, "token": "\u0120Switzerland", "merges": "\u0120Sw itzerland", "raw_count": 364, "count": 364, "decode_str": " Switzerland"} -{"id": 31585, "token": "\u0120creatinine", "merges": "\u0120creat inine", "raw_count": 364, "count": 364, "decode_str": " creatinine"} -{"id": 34050, "token": "\u0120Diabetes", "merges": "\u0120Di abetes", "raw_count": 364, "count": 364, "decode_str": " Diabetes"} -{"id": 46285, "token": "\u0120Eating", "merges": "\u0120E ating", "raw_count": 364, "count": 364, "decode_str": " Eating"} -{"id": 38783, "token": "\u0120Alexandria", "merges": "\u0120Alexand ria", "raw_count": 365, "count": 365, "decode_str": " Alexandria"} -{"id": 48860, "token": "\u0120mandibular", "merges": "\u0120mand ibular", "raw_count": 365, "count": 365, "decode_str": " mandibular"} -{"id": 32593, "token": "\u0120absorbance", "merges": "\u0120absorb ance", "raw_count": 365, "count": 365, "decode_str": " absorbance"} -{"id": 48785, "token": "\u0120glycogen", "merges": "\u0120glyc ogen", "raw_count": 365, "count": 365, "decode_str": " glycogen"} -{"id": 19688, "token": "\u0120Swedish", "merges": "\u0120Swed ish", "raw_count": 365, "count": 365, "decode_str": " Swedish"} -{"id": 49769, "token": "oblastic", "merges": "obl astic", "raw_count": 365, "count": 365, "decode_str": "oblastic"} -{"id": 38376, "token": "\u0120Alcohol", "merges": "\u0120Al cohol", "raw_count": 365, "count": 365, "decode_str": " Alcohol"} -{"id": 45004, "token": "\u0120Benson", "merges": "\u0120B enson", "raw_count": 365, "count": 365, "decode_str": " Benson"} -{"id": 34884, "token": "\u0120Chad", "merges": "\u0120Ch ad", "raw_count": 365, "count": 365, "decode_str": " Chad"} -{"id": 53268, "token": "\u00e7\u00b2\u00a7", "merges": "\u00e7\u00b2 \u00a7", "raw_count": 365, "count": 365, "decode_str": "\u7ca7"} -{"id": 50020, "token": "\u00cf\u0137", "merges": "\u00cf \u0137", "raw_count": 365, "count": 365, "decode_str": "\u03d5"} -{"id": 32241, "token": "\u0120Coalition", "merges": "\u0120Coal ition", "raw_count": 366, "count": 366, "decode_str": " Coalition"} -{"id": 46573, "token": "lipidemia", "merges": "lip idemia", "raw_count": 366, "count": 366, "decode_str": "lipidemia"} -{"id": 41913, "token": "\u0120bosons", "merges": "\u0120bos ons", "raw_count": 366, "count": 366, "decode_str": " bosons"} -{"id": 48215, "token": "\u0120Yorker", "merges": "\u0120York er", "raw_count": 366, "count": 366, "decode_str": " Yorker"} -{"id": 40152, "token": "\u0120Tracy", "merges": "\u0120Tr acy", "raw_count": 366, "count": 366, "decode_str": " Tracy"} -{"id": 30248, "token": "\u0120adenocarcinoma", "merges": "\u0120aden ocarcinoma", "raw_count": 367, "count": 367, "decode_str": " adenocarcinoma"} -{"id": 43230, "token": "\u0120Hawkins", "merges": "\u0120Haw kins", "raw_count": 367, "count": 367, "decode_str": " Hawkins"} -{"id": 21647, "token": "\u0120Czech", "merges": "\u0120C zech", "raw_count": 367, "count": 367, "decode_str": " Czech"} -{"id": 24427, "token": "\u00c8\u013bi", "merges": "\u00c8\u013b i", "raw_count": 101, "count": 367, "decode_str": "\u0219i"} -{"id": 54606, "token": "\u00ef\u00bc\u0129", "merges": "\u00ef\u00bc \u0129", "raw_count": 367, "count": 367, "decode_str": "\uff07"} -{"id": 35371, "token": "\u0120epidermal", "merges": "\u0120epid ermal", "raw_count": 368, "count": 368, "decode_str": " epidermal"} -{"id": 45762, "token": "\u0120Writers", "merges": "\u0120Writ ers", "raw_count": 368, "count": 368, "decode_str": " Writers"} -{"id": 44928, "token": "\u0120aspart", "merges": "\u0120as part", "raw_count": 368, "count": 368, "decode_str": " aspart"} -{"id": 49849, "token": "\u0120Olson", "merges": "\u0120Ol son", "raw_count": 368, "count": 368, "decode_str": " Olson"} -{"id": 28434, "token": "\u00ce\u00b5\u00cf\u0124", "merges": "\u00ce\u00b5 \u00cf\u0124", "raw_count": 368, "count": 368, "decode_str": "\u03b5\u03c2"} -{"id": 27983, "token": "\u0120Detective", "merges": "\u0120Detect ive", "raw_count": 369, "count": 369, "decode_str": " Detective"} -{"id": 40424, "token": "\u0120Theodore", "merges": "\u0120Theod ore", "raw_count": 369, "count": 369, "decode_str": " Theodore"} -{"id": 47802, "token": "aucoup", "merges": "auc oup", "raw_count": 369, "count": 369, "decode_str": "aucoup"} -{"id": 38633, "token": "\u0120Enforcement", "merges": "\u0120En forcement", "raw_count": 370, "count": 370, "decode_str": " Enforcement"} -{"id": 44124, "token": "\u0120Preston", "merges": "\u0120Prest on", "raw_count": 370, "count": 370, "decode_str": " Preston"} -{"id": 16166, "token": "\u0120$('", "merges": "\u0120$ ('", "raw_count": 179, "count": 370, "decode_str": " $('"} -{"id": 34628, "token": "\u0120Biotechnology", "merges": "\u0120Bi otechnology", "raw_count": 371, "count": 371, "decode_str": " Biotechnology"} -{"id": 24258, "token": "\u0120Considering", "merges": "\u0120Consider ing", "raw_count": 371, "count": 371, "decode_str": " Considering"} -{"id": 47271, "token": "Regardless", "merges": "Reg ardless", "raw_count": 371, "count": 371, "decode_str": "Regardless"} -{"id": 48467, "token": "\u0120Sinclair", "merges": "\u0120Sin clair", "raw_count": 371, "count": 371, "decode_str": " Sinclair"} -{"id": 32905, "token": "\u0120Timothy", "merges": "\u0120Tim othy", "raw_count": 371, "count": 371, "decode_str": " Timothy"} -{"id": 29045, "token": "st\u00c3\u00a4", "merges": "st \u00c3\u00a4", "raw_count": 371, "count": 371, "decode_str": "st\u00e4"} -{"id": 30818, "token": "\u0120epigenetic", "merges": "\u0120epigen etic", "raw_count": 372, "count": 372, "decode_str": " epigenetic"} -{"id": 43426, "token": "\u0120Nichols", "merges": "\u0120Nich ols", "raw_count": 372, "count": 372, "decode_str": " Nichols"} -{"id": 41940, "token": "\u0120Unter", "merges": "\u0120Un ter", "raw_count": 372, "count": 372, "decode_str": " Unter"} -{"id": 16119, "token": "\u0120ovar", "merges": "\u0120o var", "raw_count": 176, "count": 372, "decode_str": " ovar"} -{"id": 49142, "token": "\u0120Fuck", "merges": "\u0120F uck", "raw_count": 372, "count": 372, "decode_str": " Fuck"} -{"id": 42908, "token": "\u0120\u00f0\u0141\u013b\u0124", "merges": "\u0120\u00f0\u0141 \u013b\u0124", "raw_count": 372, "count": 372, "decode_str": " \ud83d\ude42"} -{"id": 22783, "token": "\u0120Denmark", "merges": "\u0120Den mark", "raw_count": 373, "count": 373, "decode_str": " Denmark"} -{"id": 35944, "token": "\u0120Andrea", "merges": "\u0120And rea", "raw_count": 373, "count": 373, "decode_str": " Andrea"} -{"id": 42266, "token": "\u0120Edwin", "merges": "\u0120Ed win", "raw_count": 373, "count": 373, "decode_str": " Edwin"} -{"id": 44533, "token": "\u0120Ces", "merges": "\u0120C es", "raw_count": 373, "count": 373, "decode_str": " Ces"} -{"id": 54603, "token": "\u00ef\u00bc\u0126", "merges": "\u00ef\u00bc \u0126", "raw_count": 373, "count": 373, "decode_str": "\uff04"} -{"id": 35984, "token": "\u0120mesenchymal", "merges": "\u0120mes enchymal", "raw_count": 374, "count": 374, "decode_str": " mesenchymal"} -{"id": 49834, "token": "\u0120stressors", "merges": "\u0120stress ors", "raw_count": 374, "count": 374, "decode_str": " stressors"} -{"id": 21335, "token": "\u0120phosphat", "merges": "\u0120phosph at", "raw_count": 115, "count": 374, "decode_str": " phosphat"} -{"id": 34777, "token": "\u0120Warriors", "merges": "\u0120War riors", "raw_count": 374, "count": 374, "decode_str": " Warriors"} -{"id": 46901, "token": "\u0120Rafael", "merges": "\u0120Raf ael", "raw_count": 374, "count": 374, "decode_str": " Rafael"} -{"id": 34564, "token": "oblasts", "merges": "oblast s", "raw_count": 374, "count": 374, "decode_str": "oblasts"} -{"id": 33149, "token": "\u0120Flynn", "merges": "\u0120Fly nn", "raw_count": 374, "count": 374, "decode_str": " Flynn"} -{"id": 27705, "token": "\u0120Sox", "merges": "\u0120S ox", "raw_count": 374, "count": 374, "decode_str": " Sox"} -{"id": 37795, "token": "\u0120CKD", "merges": "\u0120CK D", "raw_count": 374, "count": 374, "decode_str": " CKD"} -{"id": 3822, "token": ")$.", "merges": ")$ .", "raw_count": 341, "count": 374, "decode_str": ")$."} -{"id": 48648, "token": "\u0120Janeiro", "merges": "\u0120Jane iro", "raw_count": 375, "count": 375, "decode_str": " Janeiro"} -{"id": 38254, "token": "\u0120Apost", "merges": "\u0120Ap ost", "raw_count": 375, "count": 375, "decode_str": " Apost"} -{"id": 49550, "token": "\u0120\\\\[", "merges": "\u0120\\ \\[", "raw_count": 375, "count": 375, "decode_str": " \\\\["} -{"id": 40998, "token": "\u0120Clayton", "merges": "\u0120Clay ton", "raw_count": 376, "count": 376, "decode_str": " Clayton"} -{"id": 46937, "token": "\u0120Teresa", "merges": "\u0120Te resa", "raw_count": 376, "count": 376, "decode_str": " Teresa"} -{"id": 27016, "token": "\u0120Buddha", "merges": "\u0120Budd ha", "raw_count": 376, "count": 376, "decode_str": " Buddha"} -{"id": 47298, "token": "\u0120Hoover", "merges": "\u0120Ho over", "raw_count": 376, "count": 376, "decode_str": " Hoover"} -{"id": 25242, "token": "\u00c3\u00bdch", "merges": "\u00c3\u00bd ch", "raw_count": 376, "count": 376, "decode_str": "\u00fdch"} -{"id": 49404, "token": "\u0120pathologies", "merges": "\u0120path ologies", "raw_count": 377, "count": 377, "decode_str": " pathologies"} -{"id": 17746, "token": "\u0120Recently", "merges": "\u0120Rec ently", "raw_count": 377, "count": 377, "decode_str": " Recently"} -{"id": 31026, "token": "\u0120Glenn", "merges": "\u0120Gl enn", "raw_count": 377, "count": 377, "decode_str": " Glenn"} -{"id": 10128, "token": "\u0120Ohio", "merges": "\u0120Oh io", "raw_count": 377, "count": 377, "decode_str": " Ohio"} -{"id": 29778, "token": "\u0120Joan", "merges": "\u0120Jo an", "raw_count": 377, "count": 377, "decode_str": " Joan"} -{"id": 31463, "token": "\u0120Ala", "merges": "\u0120Al a", "raw_count": 377, "count": 377, "decode_str": " Ala"} -{"id": 24868, "token": "\u0120\u00c3\u00a9s", "merges": "\u0120\u00c3\u00a9 s", "raw_count": 377, "count": 377, "decode_str": " \u00e9s"} -{"id": 29636, "token": "\u0120Ug", "merges": "\u0120U g", "raw_count": 311, "count": 377, "decode_str": " Ug"} -{"id": 42511, "token": "_.\"", "merges": "_ .\"", "raw_count": 377, "count": 377, "decode_str": "_.\""} -{"id": 26308, "token": "\u0120preoperative", "merges": "\u0120pre operative", "raw_count": 378, "count": 378, "decode_str": " preoperative"} -{"id": 35566, "token": "\u0120viel", "merges": "\u0120v iel", "raw_count": 378, "count": 378, "decode_str": " viel"} -{"id": 38777, "token": "\u0120Fas", "merges": "\u0120F as", "raw_count": 378, "count": 378, "decode_str": " Fas"} -{"id": 48324, "token": "\u0120AdS", "merges": "\u0120Ad S", "raw_count": 378, "count": 378, "decode_str": " AdS"} -{"id": 47153, "token": "\u0120triglycerides", "merges": "\u0120triglycer ides", "raw_count": 379, "count": 379, "decode_str": " triglycerides"} -{"id": 23004, "token": "\u0120Championships", "merges": "\u0120Championship s", "raw_count": 379, "count": 379, "decode_str": " Championships"} -{"id": 30268, "token": "\u0120finitely", "merges": "\u0120fin itely", "raw_count": 379, "count": 379, "decode_str": " finitely"} -{"id": 42890, "token": "\u0120Dawson", "merges": "\u0120Daw son", "raw_count": 379, "count": 379, "decode_str": " Dawson"} -{"id": 32073, "token": "\u0120hepar", "merges": "\u0120he par", "raw_count": 36, "count": 379, "decode_str": " hepar"} -{"id": 27283, "token": "\u0120Jamie", "merges": "\u0120Jam ie", "raw_count": 379, "count": 379, "decode_str": " Jamie"} -{"id": 38923, "token": "\u0120Vaugh", "merges": "\u0120V augh", "raw_count": 379, "count": 379, "decode_str": " Vaugh"} -{"id": 29073, "token": "\u0120phag", "merges": "\u0120ph ag", "raw_count": 379, "count": 379, "decode_str": " phag"} -{"id": 16943, "token": "[]{", "merges": "[ ]{", "raw_count": 379, "count": 379, "decode_str": "[]{"} -{"id": 27988, "token": ">\";", "merges": "> \";", "raw_count": 379, "count": 379, "decode_str": ">\";"} -{"id": 28450, "token": "\u0120translocation", "merges": "\u0120transl ocation", "raw_count": 380, "count": 380, "decode_str": " translocation"} -{"id": 34358, "token": "\u0120Ambassador", "merges": "\u0120Amb assador", "raw_count": 380, "count": 380, "decode_str": " Ambassador"} -{"id": 47185, "token": "\u0120Dickinson", "merges": "\u0120Dick inson", "raw_count": 380, "count": 380, "decode_str": " Dickinson"} -{"id": 32042, "token": "\u0120Pierce", "merges": "\u0120Pier ce", "raw_count": 380, "count": 380, "decode_str": " Pierce"} -{"id": 46114, "token": "\u0120Examin", "merges": "\u0120Ex amin", "raw_count": 380, "count": 380, "decode_str": " Examin"} -{"id": 41527, "token": "\u0120Giul", "merges": "\u0120Gi ul", "raw_count": 380, "count": 380, "decode_str": " Giul"} -{"id": 36263, "token": "\u0120declaratory", "merges": "\u0120declar atory", "raw_count": 381, "count": 381, "decode_str": " declaratory"} -{"id": 45663, "token": "\u0120Borough", "merges": "\u0120Bor ough", "raw_count": 381, "count": 381, "decode_str": " Borough"} -{"id": 49249, "token": "\u0120BGCOLOR", "merges": "\u0120BGC OLOR", "raw_count": 381, "count": 381, "decode_str": " BGCOLOR"} -{"id": 33208, "token": "\u0120Zach", "merges": "\u0120Z ach", "raw_count": 381, "count": 381, "decode_str": " Zach"} -{"id": 33370, "token": "\u0120BIA", "merges": "\u0120B IA", "raw_count": 381, "count": 381, "decode_str": " BIA"} -{"id": 33911, "token": "\u0120Continental", "merges": "\u0120Contin ental", "raw_count": 382, "count": 382, "decode_str": " Continental"} -{"id": 30535, "token": "\u0120plasticity", "merges": "\u0120plastic ity", "raw_count": 382, "count": 382, "decode_str": " plasticity"} -{"id": 48395, "token": "\u0120arthro", "merges": "\u0120arth ro", "raw_count": 382, "count": 382, "decode_str": " arthro"} -{"id": 41942, "token": "\u0120Marin", "merges": "\u0120Mar in", "raw_count": 382, "count": 382, "decode_str": " Marin"} -{"id": 34105, "token": "\u0120Bears", "merges": "\u0120B ears", "raw_count": 382, "count": 382, "decode_str": " Bears"} -{"id": 32794, "token": "\u0120Noah", "merges": "\u0120No ah", "raw_count": 382, "count": 382, "decode_str": " Noah"} -{"id": 32698, "token": "\u0120Troy", "merges": "\u0120T roy", "raw_count": 382, "count": 382, "decode_str": " Troy"} -{"id": 31635, "token": "\u0120Tyr", "merges": "\u0120T yr", "raw_count": 382, "count": 382, "decode_str": " Tyr"} -{"id": 15558, "token": "\u0120Wisconsin", "merges": "\u0120Wis consin", "raw_count": 383, "count": 383, "decode_str": " Wisconsin"} -{"id": 42470, "token": "\u0120citrate", "merges": "\u0120cit rate", "raw_count": 383, "count": 383, "decode_str": " citrate"} -{"id": 42627, "token": "\u00e3\u0123\u0137\u00e3\u0124\u0135", "merges": "\u00e3\u0123\u0137 \u00e3\u0124\u0135", "raw_count": 383, "count": 383, "decode_str": "\u3055\u3093"} -{"id": 44288, "token": "\u0120CDK", "merges": "\u0120CD K", "raw_count": 383, "count": 383, "decode_str": " CDK"} -{"id": 47113, "token": "\u0120causative", "merges": "\u0120caus ative", "raw_count": 384, "count": 384, "decode_str": " causative"} -{"id": 49075, "token": "\u0120Eleven", "merges": "\u0120Ele ven", "raw_count": 384, "count": 384, "decode_str": " Eleven"} -{"id": 31316, "token": "\u0120Ellen", "merges": "\u0120Ell en", "raw_count": 384, "count": 384, "decode_str": " Ellen"} -{"id": 34701, "token": "\u0120Mum", "merges": "\u0120M um", "raw_count": 384, "count": 384, "decode_str": " Mum"} -{"id": 42812, "token": "\u0120Und", "merges": "\u0120Un d", "raw_count": 384, "count": 384, "decode_str": " Und"} -{"id": 26147, "token": "\u00c2\u00bb,", "merges": "\u00c2\u00bb ,", "raw_count": 384, "count": 384, "decode_str": "\u00bb,"} -{"id": 18978, "token": "Meanwhile", "merges": "Mean while", "raw_count": 385, "count": 385, "decode_str": "Meanwhile"} -{"id": 33602, "token": "\u0120Tribune", "merges": "\u0120Trib une", "raw_count": 385, "count": 385, "decode_str": " Tribune"} -{"id": 13281, "token": "\u0120Islamic", "merges": "\u0120Islam ic", "raw_count": 385, "count": 385, "decode_str": " Islamic"} -{"id": 49826, "token": "\u0120fuckin", "merges": "\u0120fuck in", "raw_count": 385, "count": 385, "decode_str": " fuckin"} -{"id": 38295, "token": "\u0120Torres", "merges": "\u0120Tor res", "raw_count": 385, "count": 385, "decode_str": " Torres"} -{"id": 37779, "token": "\u0120Libert", "merges": "\u0120Lib ert", "raw_count": 385, "count": 385, "decode_str": " Libert"} -{"id": 44035, "token": "\u0120Huss", "merges": "\u0120H uss", "raw_count": 385, "count": 385, "decode_str": " Huss"} -{"id": 30243, "token": "\u0120CVD", "merges": "\u0120C VD", "raw_count": 385, "count": 385, "decode_str": " CVD"} -{"id": 12886, "token": "^{-\\", "merges": "^{ -\\", "raw_count": 385, "count": 385, "decode_str": "^{-\\"} -{"id": 47341, "token": "a\u00c3\u00b1a", "merges": "a \u00c3\u00b1a", "raw_count": 385, "count": 385, "decode_str": "a\u00f1a"} -{"id": 42252, "token": "\u00d7\u013f", "merges": "\u00d7 \u013f", "raw_count": 385, "count": 385, "decode_str": "\u05dd"} -{"id": 36600, "token": "\u0120Directors", "merges": "\u0120Direct ors", "raw_count": 386, "count": 386, "decode_str": " Directors"} -{"id": 45226, "token": "\u0120Weaver", "merges": "\u0120We aver", "raw_count": 386, "count": 386, "decode_str": " Weaver"} -{"id": 27145, "token": "\u0120Tommy", "merges": "\u0120Tom my", "raw_count": 386, "count": 386, "decode_str": " Tommy"} -{"id": 43644, "token": "srep", "merges": "s rep", "raw_count": 386, "count": 386, "decode_str": "srep"} -{"id": 40942, "token": "Apparently", "merges": "App arently", "raw_count": 387, "count": 387, "decode_str": "Apparently"} -{"id": 40067, "token": "\u0120toujours", "merges": "\u0120tou jours", "raw_count": 387, "count": 387, "decode_str": " toujours"} -{"id": 9937, "token": "\u0120Despite", "merges": "\u0120Des pite", "raw_count": 387, "count": 387, "decode_str": " Despite"} -{"id": 36126, "token": "\u0120Sanchez", "merges": "\u0120S anchez", "raw_count": 387, "count": 387, "decode_str": " Sanchez"} -{"id": 43519, "token": "\u0120Marina", "merges": "\u0120Mar ina", "raw_count": 387, "count": 387, "decode_str": " Marina"} -{"id": 38502, "token": "\u0120Marion", "merges": "\u0120Mar ion", "raw_count": 387, "count": 387, "decode_str": " Marion"} -{"id": 49441, "token": "\u0120diced", "merges": "\u0120d iced", "raw_count": 387, "count": 387, "decode_str": " diced"} -{"id": 42808, "token": "\u0120Millenn", "merges": "\u0120Mill enn", "raw_count": 388, "count": 388, "decode_str": " Millenn"} -{"id": 19694, "token": "\u0120Veter", "merges": "\u0120V eter", "raw_count": 208, "count": 388, "decode_str": " Veter"} -{"id": 41910, "token": "\u0120Isle", "merges": "\u0120Is le", "raw_count": 388, "count": 388, "decode_str": " Isle"} -{"id": 19073, "token": "\u0120\u00ce\u00bd\u00ce\u00b1", "merges": "\u0120\u00ce\u00bd \u00ce\u00b1", "raw_count": 388, "count": 388, "decode_str": " \u03bd\u03b1"} -{"id": 46882, "token": "\u0120Kamp", "merges": "\u0120K amp", "raw_count": 388, "count": 388, "decode_str": " Kamp"} -{"id": 14070, "token": "\u0120Massachusetts", "merges": "\u0120Mass achusetts", "raw_count": 389, "count": 389, "decode_str": " Massachusetts"} -{"id": 33077, "token": "\u0120hypothal", "merges": "\u0120hyp othal", "raw_count": 105, "count": 389, "decode_str": " hypothal"} -{"id": 47870, "token": "\u0120Sadly", "merges": "\u0120Sad ly", "raw_count": 389, "count": 389, "decode_str": " Sadly"} -{"id": 32230, "token": "\u0120HPLC", "merges": "\u0120H PLC", "raw_count": 389, "count": 389, "decode_str": " HPLC"} -{"id": 33873, "token": "}(-", "merges": "} (-", "raw_count": 389, "count": 389, "decode_str": "}(-"} -{"id": 38261, "token": "\u0120circadian", "merges": "\u0120circ adian", "raw_count": 390, "count": 390, "decode_str": " circadian"} -{"id": 46696, "token": "\u0120Hospit", "merges": "\u0120H ospit", "raw_count": 390, "count": 390, "decode_str": " Hospit"} -{"id": 41502, "token": "\u0120rinsed", "merges": "\u0120rins ed", "raw_count": 390, "count": 390, "decode_str": " rinsed"} -{"id": 46484, "token": "\u0120Prol", "merges": "\u0120P rol", "raw_count": 390, "count": 390, "decode_str": " Prol"} -{"id": 49528, "token": "\u0120prophylactic", "merges": "\u0120prophyl actic", "raw_count": 391, "count": 391, "decode_str": " prophylactic"} -{"id": 36329, "token": "\u0120lymphocyte", "merges": "\u0120lymph ocyte", "raw_count": 391, "count": 391, "decode_str": " lymphocyte"} -{"id": 50190, "token": "\u0120Lorenzo", "merges": "\u0120Loren zo", "raw_count": 391, "count": 391, "decode_str": " Lorenzo"} -{"id": 26888, "token": "\u0120Brady", "merges": "\u0120Br ady", "raw_count": 391, "count": 391, "decode_str": " Brady"} -{"id": 45401, "token": "texttt", "merges": "text tt", "raw_count": 391, "count": 391, "decode_str": "texttt"} -{"id": 35607, "token": "\u0120Ranch", "merges": "\u0120R anch", "raw_count": 391, "count": 391, "decode_str": " Ranch"} -{"id": 41918, "token": "\u0120Krish", "merges": "\u0120Kr ish", "raw_count": 391, "count": 391, "decode_str": " Krish"} -{"id": 34213, "token": "\u0120Ned", "merges": "\u0120N ed", "raw_count": 391, "count": 391, "decode_str": " Ned"} -{"id": 49503, "token": "\u0120psychotic", "merges": "\u0120psych otic", "raw_count": 392, "count": 392, "decode_str": " psychotic"} -{"id": 47164, "token": "\u0120handgun", "merges": "\u0120hand gun", "raw_count": 392, "count": 392, "decode_str": " handgun"} -{"id": 44152, "token": "\u0120Ferrari", "merges": "\u0120Ferr ari", "raw_count": 392, "count": 392, "decode_str": " Ferrari"} -{"id": 22785, "token": "\u0120Belgium", "merges": "\u0120Bel gium", "raw_count": 392, "count": 392, "decode_str": " Belgium"} -{"id": 16496, "token": "\u0120Moscow", "merges": "\u0120M oscow", "raw_count": 392, "count": 392, "decode_str": " Moscow"} -{"id": 41167, "token": "\u0120elucidated", "merges": "\u0120elucid ated", "raw_count": 393, "count": 393, "decode_str": " elucidated"} -{"id": 22998, "token": "\u0120CONDITIONS", "merges": "\u0120CONDITION S", "raw_count": 393, "count": 393, "decode_str": " CONDITIONS"} -{"id": 38005, "token": "\u0120Marian", "merges": "\u0120Mar ian", "raw_count": 393, "count": 393, "decode_str": " Marian"} -{"id": 31340, "token": "\u0120Julie", "merges": "\u0120Jul ie", "raw_count": 393, "count": 393, "decode_str": " Julie"} -{"id": 38713, "token": "\u0120Laur", "merges": "\u0120La ur", "raw_count": 393, "count": 393, "decode_str": " Laur"} -{"id": 20629, "token": "\u0120[$\\", "merges": "\u0120[ $\\", "raw_count": 393, "count": 393, "decode_str": " [$\\"} -{"id": 37416, "token": "\u0120hypertrophy", "merges": "\u0120hypert rophy", "raw_count": 394, "count": 394, "decode_str": " hypertrophy"} -{"id": 47632, "token": "---|---|---", "merges": "---| ---|---", "raw_count": 394, "count": 394, "decode_str": "---|---|---"} -{"id": 22807, "token": "Conclusions", "merges": "Con clusions", "raw_count": 394, "count": 394, "decode_str": "Conclusions"} -{"id": 45269, "token": "\u0120ectopic", "merges": "\u0120ect opic", "raw_count": 394, "count": 394, "decode_str": " ectopic"} -{"id": 32398, "token": "\u0120Daddy", "merges": "\u0120D addy", "raw_count": 394, "count": 394, "decode_str": " Daddy"} -{"id": 45778, "token": "\u0120Brom", "merges": "\u0120B rom", "raw_count": 394, "count": 394, "decode_str": " Brom"} -{"id": 50609, "token": "\u00e4\u00bf\u00ac", "merges": "\u00e4\u00bf \u00ac", "raw_count": 394, "count": 394, "decode_str": "\u4fec"} -{"id": 47552, "token": "++]", "merges": "++ ]", "raw_count": 394, "count": 394, "decode_str": "++]"} -{"id": 33592, "token": "\u0120holomorphic", "merges": "\u0120hol omorphic", "raw_count": 395, "count": 395, "decode_str": " holomorphic"} -{"id": 48612, "token": "\u0120Photography", "merges": "\u0120Phot ography", "raw_count": 395, "count": 395, "decode_str": " Photography"} -{"id": 37534, "token": "\u0120obstructive", "merges": "\u0120obstruct ive", "raw_count": 395, "count": 395, "decode_str": " obstructive"} -{"id": 44811, "token": "\u0120cerebellum", "merges": "\u0120cere bellum", "raw_count": 395, "count": 395, "decode_str": " cerebellum"} -{"id": 27235, "token": "\u0120Buddhist", "merges": "\u0120Budd hist", "raw_count": 395, "count": 395, "decode_str": " Buddhist"} -{"id": 16795, "token": "\u0120Poland", "merges": "\u0120Pol and", "raw_count": 395, "count": 395, "decode_str": " Poland"} -{"id": 41518, "token": "\u0120quanto", "merges": "\u0120quant o", "raw_count": 395, "count": 395, "decode_str": " quanto"} -{"id": 46751, "token": "\u0120\u00d8\u00a7\u00d9\u0126\u00d8\u00aa", "merges": "\u0120\u00d8\u00a7\u00d9\u0126 \u00d8\u00aa", "raw_count": 395, "count": 395, "decode_str": " \u0627\u0644\u062a"} -{"id": 20272, "token": "\u0120HCC", "merges": "\u0120H CC", "raw_count": 395, "count": 395, "decode_str": " HCC"} -{"id": 45713, "token": "\u0120SBP", "merges": "\u0120S BP", "raw_count": 395, "count": 395, "decode_str": " SBP"} -{"id": 45979, "token": "\u0120Astronomy", "merges": "\u0120Astr onomy", "raw_count": 396, "count": 396, "decode_str": " Astronomy"} -{"id": 47262, "token": "\u0120Haskell", "merges": "\u0120H askell", "raw_count": 396, "count": 396, "decode_str": " Haskell"} -{"id": 43344, "token": "\u0120s\u00c3\u00b3lo", "merges": "\u0120s\u00c3\u00b3 lo", "raw_count": 396, "count": 396, "decode_str": " s\u00f3lo"} -{"id": 25681, "token": "\u0120Rico", "merges": "\u0120R ico", "raw_count": 396, "count": 396, "decode_str": " Rico"} -{"id": 46152, "token": "\u0120AFM", "merges": "\u0120AF M", "raw_count": 396, "count": 396, "decode_str": " AFM"} -{"id": 14548, "token": ")_{", "merges": ") _{", "raw_count": 396, "count": 396, "decode_str": ")_{"} -{"id": 36800, "token": "\u0120Gonzalez", "merges": "\u0120Gonz alez", "raw_count": 397, "count": 397, "decode_str": " Gonzalez"} -{"id": 48080, "token": "\u0120versch", "merges": "\u0120vers ch", "raw_count": 397, "count": 397, "decode_str": " versch"} -{"id": 36026, "token": "\u0120Isn", "merges": "\u0120Is n", "raw_count": 397, "count": 397, "decode_str": " Isn"} -{"id": 49572, "token": "\u00c5\u00b1", "merges": "\u00c5 \u00b1", "raw_count": 397, "count": 397, "decode_str": "\u0171"} -{"id": 40788, "token": "\u0120Individuals", "merges": "\u0120Individual s", "raw_count": 398, "count": 398, "decode_str": " Individuals"} -{"id": 45560, "token": "\u0120dissected", "merges": "\u0120disse cted", "raw_count": 398, "count": 398, "decode_str": " dissected"} -{"id": 28566, "token": "\u0120cardiomy", "merges": "\u0120cardi omy", "raw_count": 138, "count": 398, "decode_str": " cardiomy"} -{"id": 18003, "token": "\u0120fibrobl", "merges": "\u0120fib robl", "raw_count": 7, "count": 398, "decode_str": " fibrobl"} -{"id": 37117, "token": "\u0120Chrys", "merges": "\u0120Ch rys", "raw_count": 248, "count": 398, "decode_str": " Chrys"} -{"id": 28568, "token": "\u0120Clerk", "merges": "\u0120Cl erk", "raw_count": 398, "count": 398, "decode_str": " Clerk"} -{"id": 19950, "token": "\u0120Delhi", "merges": "\u0120Del hi", "raw_count": 398, "count": 398, "decode_str": " Delhi"} -{"id": 49730, "token": "\u0120XIII", "merges": "\u0120X III", "raw_count": 398, "count": 398, "decode_str": " XIII"} -{"id": 27580, "token": "\u00ce\u00b1\u00ce\u00bd", "merges": "\u00ce\u00b1 \u00ce\u00bd", "raw_count": 398, "count": 398, "decode_str": "\u03b1\u03bd"} -{"id": 47286, "token": "\u0120PFS", "merges": "\u0120P FS", "raw_count": 398, "count": 398, "decode_str": " PFS"} -{"id": 36519, "token": "\u0120oxidase", "merges": "\u0120oxid ase", "raw_count": 399, "count": 399, "decode_str": " oxidase"} -{"id": 38946, "token": "\u0120Forbes", "merges": "\u0120For bes", "raw_count": 399, "count": 399, "decode_str": " Forbes"} -{"id": 37509, "token": "it\u00c3\u00a4t", "merges": "it \u00c3\u00a4t", "raw_count": 399, "count": 399, "decode_str": "it\u00e4t"} -{"id": 36860, "token": "ADVERTISEMENT", "merges": "AD VERTISEMENT", "raw_count": 400, "count": 400, "decode_str": "ADVERTISEMENT"} -{"id": 47821, "token": "\u0120disulfide", "merges": "\u0120dis ulfide", "raw_count": 400, "count": 400, "decode_str": " disulfide"} -{"id": 36845, "token": "\u0120Simmons", "merges": "\u0120Sim mons", "raw_count": 401, "count": 401, "decode_str": " Simmons"} -{"id": 42650, "token": "\u0120Willis", "merges": "\u0120Will is", "raw_count": 401, "count": 401, "decode_str": " Willis"} -{"id": 36060, "token": "\u0120na\u00c3\u00afve", "merges": "\u0120na \u00c3\u00afve", "raw_count": 401, "count": 401, "decode_str": " na\u00efve"} -{"id": 49453, "token": "yzed", "merges": "y zed", "raw_count": 401, "count": 401, "decode_str": "yzed"} -{"id": 48185, "token": "\u0120\u00ce\u0133", "merges": "\u0120\u00ce \u0133", "raw_count": 401, "count": 401, "decode_str": " \u0391"} -{"id": 44093, "token": "r\u00c3\u00a4", "merges": "r \u00c3\u00a4", "raw_count": 401, "count": 401, "decode_str": "r\u00e4"} -{"id": 22322, "token": "unnumbered", "merges": "unn umbered", "raw_count": 402, "count": 402, "decode_str": "unnumbered"} -{"id": 34516, "token": "\u0120teaspoons", "merges": "\u0120teasp oons", "raw_count": 402, "count": 402, "decode_str": " teaspoons"} -{"id": 29804, "token": "\u0120Angela", "merges": "\u0120Ang ela", "raw_count": 402, "count": 402, "decode_str": " Angela"} -{"id": 33747, "token": "\u0120Ashley", "merges": "\u0120Ash ley", "raw_count": 402, "count": 402, "decode_str": " Ashley"} -{"id": 42635, "token": "\u0120cereb", "merges": "\u0120cere b", "raw_count": 84, "count": 402, "decode_str": " cereb"} -{"id": 43051, "token": "\u0120Homer", "merges": "\u0120H omer", "raw_count": 402, "count": 402, "decode_str": " Homer"} -{"id": 47797, "token": "\u0120Hopf", "merges": "\u0120Hop f", "raw_count": 402, "count": 402, "decode_str": " Hopf"} -{"id": 45411, "token": "\u0120Carb", "merges": "\u0120Car b", "raw_count": 402, "count": 402, "decode_str": " Carb"} -{"id": 31300, "token": "\u0120Lys", "merges": "\u0120L ys", "raw_count": 402, "count": 402, "decode_str": " Lys"} -{"id": 39795, "token": "\u0120Fernando", "merges": "\u0120Fern ando", "raw_count": 403, "count": 403, "decode_str": " Fernando"} -{"id": 48113, "token": "\u0120consegu", "merges": "\u0120conse gu", "raw_count": 403, "count": 403, "decode_str": " consegu"} -{"id": 22880, "token": "\u0120\u00cf\u0126\u00ce\u00bf\u00cf\u0127", "merges": "\u0120\u00cf\u0126 \u00ce\u00bf\u00cf\u0127", "raw_count": 403, "count": 403, "decode_str": " \u03c4\u03bf\u03c5"} -{"id": 14307, "token": "\u0120Turkey", "merges": "\u0120Tur key", "raw_count": 403, "count": 403, "decode_str": " Turkey"} -{"id": 48711, "token": "\u00e3\u0123\u013f\u00e3\u0123\u0128", "merges": "\u00e3\u0123\u013f \u00e3\u0123\u0128", "raw_count": 403, "count": 403, "decode_str": "\u305d\u3046"} -{"id": 36054, "token": "\u0120diese", "merges": "\u0120dies e", "raw_count": 403, "count": 403, "decode_str": " diese"} -{"id": 41716, "token": "clerotic", "merges": "cler otic", "raw_count": 254, "count": 404, "decode_str": "clerotic"} -{"id": 21740, "token": "\u0120Patri", "merges": "\u0120Pat ri", "raw_count": 336, "count": 404, "decode_str": " Patri"} -{"id": 28439, "token": "vdots", "merges": "v dots", "raw_count": 404, "count": 404, "decode_str": "vdots"} -{"id": 40437, "token": "}}\\\\", "merges": "}}\\ \\", "raw_count": 404, "count": 404, "decode_str": "}}\\\\"} -{"id": 39583, "token": "\u00c3\u0141en", "merges": "\u00c3\u0141 en", "raw_count": 404, "count": 404, "decode_str": "\u00dfen"} -{"id": 50034, "token": "\u00e2\u012d\u00af", "merges": "\u00e2\u012d \u00af", "raw_count": 404, "count": 404, "decode_str": "\u22ef"} -{"id": 41474, "token": "\u0120Johannes", "merges": "\u0120Johann es", "raw_count": 405, "count": 405, "decode_str": " Johannes"} -{"id": 34334, "token": "\u0120Monroe", "merges": "\u0120Mon roe", "raw_count": 405, "count": 405, "decode_str": " Monroe"} -{"id": 36538, "token": "\u0120Zel", "merges": "\u0120Z el", "raw_count": 405, "count": 405, "decode_str": " Zel"} -{"id": 37537, "token": "\u0120hematopoietic", "merges": "\u0120hemat opoietic", "raw_count": 406, "count": 406, "decode_str": " hematopoietic"} -{"id": 38552, "token": "\u0120transcriptome", "merges": "\u0120transcript ome", "raw_count": 406, "count": 406, "decode_str": " transcriptome"} -{"id": 16342, "token": "\u0120Commonwealth", "merges": "\u0120Common wealth", "raw_count": 406, "count": 406, "decode_str": " Commonwealth"} -{"id": 17367, "token": "\u0120Ontario", "merges": "\u0120Ont ario", "raw_count": 406, "count": 406, "decode_str": " Ontario"} -{"id": 38103, "token": "\u0120telome", "merges": "\u0120tel ome", "raw_count": 227, "count": 406, "decode_str": " telome"} -{"id": 26494, "token": "\u0120aureus", "merges": "\u0120a ureus", "raw_count": 406, "count": 406, "decode_str": " aureus"} -{"id": 38048, "token": "\u0120Judy", "merges": "\u0120Jud y", "raw_count": 406, "count": 406, "decode_str": " Judy"} -{"id": 47094, "token": "\u0120Hume", "merges": "\u0120H ume", "raw_count": 406, "count": 406, "decode_str": " Hume"} -{"id": 45201, "token": ")\\*", "merges": ")\\ *", "raw_count": 406, "count": 406, "decode_str": ")\\*"} -{"id": 22978, "token": "={\\", "merges": "= {\\", "raw_count": 406, "count": 406, "decode_str": "={\\"} -{"id": 31020, "token": "\u0120europ\u00c3\u00a9", "merges": "\u0120europ \u00c3\u00a9", "raw_count": 188, "count": 407, "decode_str": " europ\u00e9"} -{"id": 34084, "token": "\u0120Abbott", "merges": "\u0120Abb ott", "raw_count": 407, "count": 407, "decode_str": " Abbott"} -{"id": 30681, "token": "\u00ce\u00b5\u00ce\u00bd", "merges": "\u00ce\u00b5 \u00ce\u00bd", "raw_count": 294, "count": 407, "decode_str": "\u03b5\u03bd"} -{"id": 43199, "token": "Suddenly", "merges": "Sud denly", "raw_count": 408, "count": 408, "decode_str": "Suddenly"} -{"id": 35839, "token": "\u0120preterm", "merges": "\u0120pre term", "raw_count": 408, "count": 408, "decode_str": " preterm"} -{"id": 40703, "token": "\u0120Dismiss", "merges": "\u0120D ismiss", "raw_count": 408, "count": 408, "decode_str": " Dismiss"} -{"id": 3854, "token": "\u0120Suppose", "merges": "\u0120S uppose", "raw_count": 408, "count": 408, "decode_str": " Suppose"} -{"id": 41701, "token": "\u0120Priest", "merges": "\u0120Pri est", "raw_count": 408, "count": 408, "decode_str": " Priest"} -{"id": 48629, "token": "iphatic", "merges": "ip hatic", "raw_count": 408, "count": 408, "decode_str": "iphatic"} -{"id": 37383, "token": "\u0120toute", "merges": "\u0120tou te", "raw_count": 408, "count": 408, "decode_str": " toute"} -{"id": 47990, "token": "\u0120XII", "merges": "\u0120X II", "raw_count": 408, "count": 408, "decode_str": " XII"} -{"id": 21237, "token": "*^*", "merges": "* ^*", "raw_count": 408, "count": 408, "decode_str": "*^*"} -{"id": 19974, "token": "\u0120Representative", "merges": "\u0120Represent ative", "raw_count": 409, "count": 409, "decode_str": " Representative"} -{"id": 25787, "token": "\u0120autoimmune", "merges": "\u0120auto immune", "raw_count": 409, "count": 409, "decode_str": " autoimmune"} -{"id": 24014, "token": "\u0120chromatin", "merges": "\u0120chrom atin", "raw_count": 409, "count": 409, "decode_str": " chromatin"} -{"id": 33357, "token": "\u0120Adrian", "merges": "\u0120Ad rian", "raw_count": 409, "count": 409, "decode_str": " Adrian"} -{"id": 39177, "token": "\u0120minced", "merges": "\u0120min ced", "raw_count": 409, "count": 409, "decode_str": " minced"} -{"id": 33893, "token": "\u0120maar", "merges": "\u0120ma ar", "raw_count": 409, "count": 409, "decode_str": " maar"} -{"id": 17896, "token": "bigl", "merges": "big l", "raw_count": 409, "count": 409, "decode_str": "bigl"} -{"id": 21420, "token": "\u0120lymphocytes", "merges": "\u0120lymph ocytes", "raw_count": 410, "count": 410, "decode_str": " lymphocytes"} -{"id": 43225, "token": "\u0120pathologic", "merges": "\u0120path ologic", "raw_count": 410, "count": 410, "decode_str": " pathologic"} -{"id": 45950, "token": "\u00e3\u0123\u00a6\u00e3\u0123\u0126\u00e3\u0123\u0141", "merges": "\u00e3\u0123\u00a6\u00e3\u0123\u0126 \u00e3\u0123\u0141", "raw_count": 410, "count": 410, "decode_str": "\u3066\u3044\u305f"} -{"id": 27210, "token": "\u0120blotting", "merges": "\u0120blot ting", "raw_count": 410, "count": 410, "decode_str": " blotting"} -{"id": 19330, "token": "\u0120Counsel", "merges": "\u0120Coun sel", "raw_count": 410, "count": 410, "decode_str": " Counsel"} -{"id": 41494, "token": "\u0120GBM", "merges": "\u0120G BM", "raw_count": 410, "count": 410, "decode_str": " GBM"} -{"id": 30916, "token": "'$.", "merges": "' $.", "raw_count": 410, "count": 410, "decode_str": "'$."} -{"id": 37569, "token": "\u0120Knox", "merges": "\u0120Kn ox", "raw_count": 411, "count": 411, "decode_str": " Knox"} -{"id": 11567, "token": "\u0120WARRANT", "merges": "\u0120W ARRANT", "raw_count": 21, "count": 412, "decode_str": " WARRANT"} -{"id": 30913, "token": "\u0120Majesty", "merges": "\u0120Maj esty", "raw_count": 412, "count": 412, "decode_str": " Majesty"} -{"id": 45174, "token": "\u0120sentido", "merges": "\u0120sent ido", "raw_count": 412, "count": 412, "decode_str": " sentido"} -{"id": 28464, "token": "\u0120sepsis", "merges": "\u0120se psis", "raw_count": 412, "count": 412, "decode_str": " sepsis"} -{"id": 43921, "token": "\u0120Wesley", "merges": "\u0120Wes ley", "raw_count": 412, "count": 412, "decode_str": " Wesley"} -{"id": 49918, "token": "\u0120Says", "merges": "\u0120S ays", "raw_count": 412, "count": 412, "decode_str": " Says"} -{"id": 36614, "token": "\u0120Elle", "merges": "\u0120El le", "raw_count": 412, "count": 412, "decode_str": " Elle"} -{"id": 11367, "token": "\u0120\u00c2\u00b6", "merges": "\u0120\u00c2 \u00b6", "raw_count": 412, "count": 412, "decode_str": " \u00b6"} -{"id": 36741, "token": "\u0120Christie", "merges": "\u0120Christ ie", "raw_count": 413, "count": 413, "decode_str": " Christie"} -{"id": 42430, "token": "\u0120Marcel", "merges": "\u0120Mar cel", "raw_count": 413, "count": 413, "decode_str": " Marcel"} -{"id": 37869, "token": "\u0120Perez", "merges": "\u0120Pe rez", "raw_count": 413, "count": 413, "decode_str": " Perez"} -{"id": 46586, "token": "\u0120Gomez", "merges": "\u0120G omez", "raw_count": 413, "count": 413, "decode_str": " Gomez"} -{"id": 44446, "token": "\u0120jej", "merges": "\u0120je j", "raw_count": 413, "count": 413, "decode_str": " jej"} -{"id": 45133, "token": "\u00ce\u00ba\u00ce\u00b5", "merges": "\u00ce\u00ba \u00ce\u00b5", "raw_count": 413, "count": 413, "decode_str": "\u03ba\u03b5"} -{"id": 43855, "token": "\u0120Carpenter", "merges": "\u0120Carp enter", "raw_count": 414, "count": 414, "decode_str": " Carpenter"} -{"id": 37006, "token": "\u0120optically", "merges": "\u0120opt ically", "raw_count": 414, "count": 414, "decode_str": " optically"} -{"id": 42471, "token": "\u0120Frankfurt", "merges": "\u0120Frank furt", "raw_count": 414, "count": 414, "decode_str": " Frankfurt"} -{"id": 48088, "token": "\u0120Augustus", "merges": "\u0120August us", "raw_count": 414, "count": 414, "decode_str": " Augustus"} -{"id": 22085, "token": "\u0120Hawaii", "merges": "\u0120Hawai i", "raw_count": 414, "count": 414, "decode_str": " Hawaii"} -{"id": 41835, "token": "\u0120Snyder", "merges": "\u0120S nyder", "raw_count": 414, "count": 414, "decode_str": " Snyder"} -{"id": 40824, "token": "\u0120Humph", "merges": "\u0120Hum ph", "raw_count": 414, "count": 414, "decode_str": " Humph"} -{"id": 18308, "token": "\u0120Mayor", "merges": "\u0120May or", "raw_count": 414, "count": 414, "decode_str": " Mayor"} -{"id": 38804, "token": "\u0120\u00d9\u0125", "merges": "\u0120 \u00d9\u0125", "raw_count": 414, "count": 414, "decode_str": " \u0643"} -{"id": 36059, "token": "VERTISEMENT", "merges": "VERTIS EMENT", "raw_count": 15, "count": 415, "decode_str": "VERTISEMENT"} -{"id": 36595, "token": "plaintiff", "merges": "pl aintiff", "raw_count": 415, "count": 415, "decode_str": "plaintiff"} -{"id": 45752, "token": "\u0120cranial", "merges": "\u0120cran ial", "raw_count": 415, "count": 415, "decode_str": " cranial"} -{"id": 39505, "token": "\u0120Ahmad", "merges": "\u0120A hmad", "raw_count": 415, "count": 415, "decode_str": " Ahmad"} -{"id": 36527, "token": "\u0120Coron", "merges": "\u0120Cor on", "raw_count": 415, "count": 415, "decode_str": " Coron"} -{"id": 47296, "token": "NavBar", "merges": "Nav Bar", "raw_count": 415, "count": 415, "decode_str": "NavBar"} -{"id": 45101, "token": "\u0120Bess", "merges": "\u0120B ess", "raw_count": 415, "count": 415, "decode_str": " Bess"} -{"id": 41379, "token": "\u0120Zar", "merges": "\u0120Z ar", "raw_count": 415, "count": 415, "decode_str": " Zar"} -{"id": 39756, "token": "\u0120CCL", "merges": "\u0120C CL", "raw_count": 415, "count": 415, "decode_str": " CCL"} -{"id": 37061, "token": "\u0120RCC", "merges": "\u0120R CC", "raw_count": 415, "count": 415, "decode_str": " RCC"} -{"id": 25853, "token": "\u0120Princeton", "merges": "\u0120Princ eton", "raw_count": 416, "count": 416, "decode_str": " Princeton"} -{"id": 45280, "token": "\u0120Hilton", "merges": "\u0120H ilton", "raw_count": 416, "count": 416, "decode_str": " Hilton"} -{"id": 41333, "token": "\u0120Casino", "merges": "\u0120Cas ino", "raw_count": 416, "count": 416, "decode_str": " Casino"} -{"id": 33686, "token": "\u0120Betty", "merges": "\u0120Bet ty", "raw_count": 416, "count": 416, "decode_str": " Betty"} -{"id": 35864, "token": "\u0120LHC", "merges": "\u0120L HC", "raw_count": 416, "count": 416, "decode_str": " LHC"} -{"id": 36498, "token": "\u0120preferentially", "merges": "\u0120pre ferentially", "raw_count": 417, "count": 417, "decode_str": " preferentially"} -{"id": 35719, "token": "\u0120antico", "merges": "\u0120ant ico", "raw_count": 417, "count": 417, "decode_str": " antico"} -{"id": 40047, "token": ")},\\", "merges": ")} ,\\", "raw_count": 417, "count": 417, "decode_str": ")},\\"} -{"id": 47090, "token": "\u0120Afterwards", "merges": "\u0120After wards", "raw_count": 418, "count": 418, "decode_str": " Afterwards"} -{"id": 47246, "token": "\u0120Marvin", "merges": "\u0120Mar vin", "raw_count": 418, "count": 418, "decode_str": " Marvin"} -{"id": 46482, "token": "\u0120Pablo", "merges": "\u0120P ablo", "raw_count": 418, "count": 418, "decode_str": " Pablo"} -{"id": 7751, "token": "\u0120Iran", "merges": "\u0120I ran", "raw_count": 356, "count": 418, "decode_str": " Iran"} -{"id": 36638, "token": "\u0120Ches", "merges": "\u0120C hes", "raw_count": 418, "count": 418, "decode_str": " Ches"} -{"id": 48550, "token": "\u0120Howe", "merges": "\u0120How e", "raw_count": 418, "count": 418, "decode_str": " Howe"} -{"id": 38890, "token": "\u0120rheumatoid", "merges": "\u0120rheumat oid", "raw_count": 419, "count": 419, "decode_str": " rheumatoid"} -{"id": 32902, "token": "\u0120echocardi", "merges": "\u0120ech ocardi", "raw_count": 132, "count": 419, "decode_str": " echocardi"} -{"id": 40381, "token": "\u0120Lots", "merges": "\u0120L ots", "raw_count": 419, "count": 419, "decode_str": " Lots"} -{"id": 48171, "token": "\u0120Yas", "merges": "\u0120Y as", "raw_count": 419, "count": 419, "decode_str": " Yas"} -{"id": 40035, "token": "\u0120NSW", "merges": "\u0120NS W", "raw_count": 419, "count": 419, "decode_str": " NSW"} -{"id": 39481, "token": "//!", "merges": "// !", "raw_count": 419, "count": 419, "decode_str": "//!"} -{"id": 28888, "token": "\u00e0\u00b3", "merges": "\u00e0 \u00b3", "raw_count": 419, "count": 419, "decode_str": "\ufffd"} -{"id": 20145, "token": "\u0120Margaret", "merges": "\u0120Marg aret", "raw_count": 420, "count": 420, "decode_str": " Margaret"} -{"id": 49398, "token": "\u0120toasted", "merges": "\u0120to asted", "raw_count": 420, "count": 420, "decode_str": " toasted"} -{"id": 17785, "token": "\u0120Greece", "merges": "\u0120Gree ce", "raw_count": 420, "count": 420, "decode_str": " Greece"} -{"id": 18314, "token": "\u0120cytos", "merges": "\u0120cyt os", "raw_count": 197, "count": 420, "decode_str": " cytos"} -{"id": 45887, "token": "\u0120Diaz", "merges": "\u0120D iaz", "raw_count": 420, "count": 420, "decode_str": " Diaz"} -{"id": 26189, "token": "\u0120Vik", "merges": "\u0120V ik", "raw_count": 356, "count": 420, "decode_str": " Vik"} -{"id": 30322, "token": "\u0120Rug", "merges": "\u0120R ug", "raw_count": 290, "count": 420, "decode_str": " Rug"} -{"id": 34224, "token": "\u0120suppressor", "merges": "\u0120suppress or", "raw_count": 421, "count": 421, "decode_str": " suppressor"} -{"id": 22739, "token": "\u0120Rachel", "merges": "\u0120R achel", "raw_count": 421, "count": 421, "decode_str": " Rachel"} -{"id": 40012, "token": "\u0120Archae", "merges": "\u0120Arch ae", "raw_count": 421, "count": 421, "decode_str": " Archae"} -{"id": 32396, "token": "\u0120Lakes", "merges": "\u0120L akes", "raw_count": 421, "count": 421, "decode_str": " Lakes"} -{"id": 26467, "token": "\u0120Portuguese", "merges": "\u0120Portug uese", "raw_count": 422, "count": 422, "decode_str": " Portuguese"} -{"id": 46770, "token": "\u00e3\u0123\u0135\u00e3\u0123\u00a8\u00e3\u0123\u012e", "merges": "\u00e3\u0123\u0135\u00e3\u0123\u00a8 \u00e3\u0123\u012e", "raw_count": 422, "count": 422, "decode_str": "\u3053\u3068\u304c"} -{"id": 44787, "token": "\u0120phenolic", "merges": "\u0120phen olic", "raw_count": 422, "count": 422, "decode_str": " phenolic"} -{"id": 51637, "token": "\u00e5\u00bd\u00bf", "merges": "\u00e5\u00bd \u00bf", "raw_count": 422, "count": 422, "decode_str": "\u5f7f"} -{"id": 46296, "token": "\u0120Preliminary", "merges": "\u0120P reliminary", "raw_count": 423, "count": 423, "decode_str": " Preliminary"} -{"id": 31565, "token": "\u0120Regardless", "merges": "\u0120Reg ardless", "raw_count": 423, "count": 423, "decode_str": " Regardless"} -{"id": 22469, "token": "\u0120Obviously", "merges": "\u0120Ob viously", "raw_count": 423, "count": 423, "decode_str": " Obviously"} -{"id": 29479, "token": "\u0120systolic", "merges": "\u0120syst olic", "raw_count": 423, "count": 423, "decode_str": " systolic"} -{"id": 49424, "token": "\u0120cations", "merges": "\u0120c ations", "raw_count": 423, "count": 423, "decode_str": " cations"} -{"id": 50179, "token": "\u0120Sacred", "merges": "\u0120Sac red", "raw_count": 423, "count": 423, "decode_str": " Sacred"} -{"id": 37496, "token": "\u0120Standing", "merges": "\u0120Stand ing", "raw_count": 424, "count": 424, "decode_str": " Standing"} -{"id": 48415, "token": "Notable", "merges": "Not able", "raw_count": 424, "count": 424, "decode_str": "Notable"} -{"id": 24707, "token": "\u0120Bobby", "merges": "\u0120Bob by", "raw_count": 424, "count": 424, "decode_str": " Bobby"} -{"id": 24639, "token": "\u0120Barcelona", "merges": "\u0120B arcelona", "raw_count": 425, "count": 425, "decode_str": " Barcelona"} -{"id": 40284, "token": "\u0120hypogly", "merges": "\u0120hyp ogly", "raw_count": 425, "count": 425, "decode_str": " hypogly"} -{"id": 34192, "token": "\u0120Castro", "merges": "\u0120Cast ro", "raw_count": 425, "count": 425, "decode_str": " Castro"} -{"id": 31008, "token": "\u00ce\u00bc\u00ce\u0143", "merges": "\u00ce\u00bc \u00ce\u0143", "raw_count": 425, "count": 425, "decode_str": "\u03bc\u03ad"} -{"id": 30279, "token": "\u0120dendritic", "merges": "\u0120dend ritic", "raw_count": 426, "count": 426, "decode_str": " dendritic"} -{"id": 34819, "token": "\u0120Brent", "merges": "\u0120B rent", "raw_count": 426, "count": 426, "decode_str": " Brent"} -{"id": 47449, "token": "npmjs", "merges": "npm js", "raw_count": 426, "count": 426, "decode_str": "npmjs"} -{"id": 49841, "token": "\u0120BCG", "merges": "\u0120B CG", "raw_count": 426, "count": 426, "decode_str": " BCG"} -{"id": 28999, "token": "\u0120immunosupp", "merges": "\u0120immunos upp", "raw_count": 248, "count": 427, "decode_str": " immunosupp"} -{"id": 40738, "token": "\u0120Roland", "merges": "\u0120Rol and", "raw_count": 427, "count": 427, "decode_str": " Roland"} -{"id": 39652, "token": "\u0120Patrol", "merges": "\u0120Pat rol", "raw_count": 427, "count": 427, "decode_str": " Patrol"} -{"id": 17427, "token": "\u0120Manchester", "merges": "\u0120M anchester", "raw_count": 428, "count": 428, "decode_str": " Manchester"} -{"id": 21818, "token": "\u0120Melbourne", "merges": "\u0120Mel bourne", "raw_count": 428, "count": 428, "decode_str": " Melbourne"} -{"id": 45278, "token": "\u0120morphisms", "merges": "\u0120morph isms", "raw_count": 428, "count": 428, "decode_str": " morphisms"} -{"id": 35445, "token": "\u0120Goldman", "merges": "\u0120Gold man", "raw_count": 428, "count": 428, "decode_str": " Goldman"} -{"id": 45323, "token": "\u0120Dodge", "merges": "\u0120D odge", "raw_count": 428, "count": 428, "decode_str": " Dodge"} -{"id": 42796, "token": "\u0120Flint", "merges": "\u0120Fl int", "raw_count": 428, "count": 428, "decode_str": " Flint"} -{"id": 49143, "token": "\u0120Consc", "merges": "\u0120Cons c", "raw_count": 428, "count": 428, "decode_str": " Consc"} -{"id": 36476, "token": "\u0120cutaneous", "merges": "\u0120cut aneous", "raw_count": 429, "count": 429, "decode_str": " cutaneous"} -{"id": 36729, "token": "\u0120Charter", "merges": "\u0120Char ter", "raw_count": 429, "count": 429, "decode_str": " Charter"} -{"id": 46205, "token": "\u0120mitral", "merges": "\u0120mit ral", "raw_count": 429, "count": 429, "decode_str": " mitral"} -{"id": 48659, "token": "\u0120Barker", "merges": "\u0120B arker", "raw_count": 429, "count": 429, "decode_str": " Barker"} -{"id": 37013, "token": "\u0120immuno", "merges": "\u0120immun o", "raw_count": 429, "count": 429, "decode_str": " immuno"} -{"id": 42486, "token": "\u0120Tate", "merges": "\u0120T ate", "raw_count": 429, "count": 429, "decode_str": " Tate"} -{"id": 33622, "token": "\u0120Nobel", "merges": "\u0120Nob el", "raw_count": 430, "count": 430, "decode_str": " Nobel"} -{"id": 34970, "token": "\u0120Sic", "merges": "\u0120S ic", "raw_count": 430, "count": 430, "decode_str": " Sic"} -{"id": 29890, "token": "{(\\", "merges": "{ (\\", "raw_count": 430, "count": 430, "decode_str": "{(\\"} -{"id": 48015, "token": "\u0120Stephens", "merges": "\u0120Stephen s", "raw_count": 431, "count": 431, "decode_str": " Stephens"} -{"id": 32106, "token": "\u0120Sherman", "merges": "\u0120Sher man", "raw_count": 431, "count": 431, "decode_str": " Sherman"} -{"id": 22755, "token": "\u0120Chile", "merges": "\u0120Ch ile", "raw_count": 431, "count": 431, "decode_str": " Chile"} -{"id": 50189, "token": "\u0120Hitch", "merges": "\u0120H itch", "raw_count": 431, "count": 431, "decode_str": " Hitch"} -{"id": 31513, "token": "\u0120Joel", "merges": "\u0120Jo el", "raw_count": 431, "count": 431, "decode_str": " Joel"} -{"id": 48921, "token": "en\u00c3\u0143", "merges": "en \u00c3\u0143", "raw_count": 431, "count": 431, "decode_str": "en\u00ed"} -{"id": 42824, "token": "l\u00c3\u00a4", "merges": "l \u00c3\u00a4", "raw_count": 431, "count": 431, "decode_str": "l\u00e4"} -{"id": 28634, "token": "\u0120Metropolitan", "merges": "\u0120Met ropolitan", "raw_count": 432, "count": 432, "decode_str": " Metropolitan"} -{"id": 29166, "token": "Invitrogen", "merges": "Inv itrogen", "raw_count": 432, "count": 432, "decode_str": "Invitrogen"} -{"id": 20882, "token": "\u0120Danny", "merges": "\u0120D anny", "raw_count": 432, "count": 432, "decode_str": " Danny"} -{"id": 41596, "token": "\u0120otros", "merges": "\u0120ot ros", "raw_count": 432, "count": 432, "decode_str": " otros"} -{"id": 40399, "token": "\u0120\u00ce\u0142", "merges": "\u0120\u00ce \u0142", "raw_count": 432, "count": 432, "decode_str": " \u03a0"} -{"id": 53030, "token": "\u00e7\u013f\u00aa", "merges": "\u00e7\u013f \u00aa", "raw_count": 432, "count": 432, "decode_str": "\u776a"} -{"id": 22379, "token": "\u00e0\u00b1", "merges": "\u00e0 \u00b1", "raw_count": 156, "count": 432, "decode_str": "\ufffd"} -{"id": 37314, "token": "\u0120pornography", "merges": "\u0120porn ography", "raw_count": 433, "count": 433, "decode_str": " pornography"} -{"id": 32952, "token": "\u0120Bloomberg", "merges": "\u0120Bloom berg", "raw_count": 433, "count": 433, "decode_str": " Bloomberg"} -{"id": 28175, "token": "CUSSION", "merges": "CUSS ION", "raw_count": 151, "count": 433, "decode_str": "CUSSION"} -{"id": 34530, "token": "\u0120Natal", "merges": "\u0120N atal", "raw_count": 274, "count": 433, "decode_str": " Natal"} -{"id": 38899, "token": "\u0120Lund", "merges": "\u0120L und", "raw_count": 433, "count": 433, "decode_str": " Lund"} -{"id": 6401, "token": "\u0120/**", "merges": "\u0120/ **", "raw_count": 427, "count": 433, "decode_str": " /**"} -{"id": 48451, "token": "\u00d5\u00a5", "merges": "\u00d5 \u00a5", "raw_count": 433, "count": 433, "decode_str": "\u0565"} -{"id": 41283, "token": "\u0120Tradition", "merges": "\u0120Tr adition", "raw_count": 434, "count": 434, "decode_str": " Tradition"} -{"id": 33341, "token": "\u0120Behind", "merges": "\u0120Be hind", "raw_count": 434, "count": 434, "decode_str": " Behind"} -{"id": 26635, "token": "...](", "merges": "... ](", "raw_count": 434, "count": 434, "decode_str": "...]("} -{"id": 27709, "token": "\u0120Yale", "merges": "\u0120Y ale", "raw_count": 434, "count": 434, "decode_str": " Yale"} -{"id": 41995, "token": "Whoa", "merges": "Who a", "raw_count": 434, "count": 434, "decode_str": "Whoa"} -{"id": 30192, "token": "\u0120asymptomatic", "merges": "\u0120asympt omatic", "raw_count": 435, "count": 435, "decode_str": " asymptomatic"} -{"id": 20956, "token": "\u0120Portland", "merges": "\u0120Port land", "raw_count": 435, "count": 435, "decode_str": " Portland"} -{"id": 12194, "token": "\u0120Soviet", "merges": "\u0120Sov iet", "raw_count": 435, "count": 435, "decode_str": " Soviet"} -{"id": 34722, "token": "\u0120Trent", "merges": "\u0120T rent", "raw_count": 435, "count": 435, "decode_str": " Trent"} -{"id": 40081, "token": "\u0120Quin", "merges": "\u0120Qu in", "raw_count": 435, "count": 435, "decode_str": " Quin"} -{"id": 46766, "token": "\u00c3\u00bcnd", "merges": "\u00c3\u00bc nd", "raw_count": 435, "count": 435, "decode_str": "\u00fcnd"} -{"id": 6319, "token": "\u00c2\u0143", "merges": "\u00c2 \u0143", "raw_count": 435, "count": 435, "decode_str": "\u00ad"} -{"id": 36841, "token": "\u0120Benedict", "merges": "\u0120Bened ict", "raw_count": 436, "count": 436, "decode_str": " Benedict"} -{"id": 25260, "token": "\u0120Hebrew", "merges": "\u0120He brew", "raw_count": 436, "count": 436, "decode_str": " Hebrew"} -{"id": 40200, "token": "\u0120andere", "merges": "\u0120and ere", "raw_count": 436, "count": 436, "decode_str": " andere"} -{"id": 17979, "token": "\u0120Vice", "merges": "\u0120V ice", "raw_count": 436, "count": 436, "decode_str": " Vice"} -{"id": 9793, "token": "\u0120$[", "merges": "\u0120$ [", "raw_count": 436, "count": 436, "decode_str": " $["} -{"id": 25641, "token": "\u0120homeostasis", "merges": "\u0120homeost asis", "raw_count": 437, "count": 437, "decode_str": " homeostasis"} -{"id": 29986, "token": "\u0120Significant", "merges": "\u0120Sign ificant", "raw_count": 437, "count": 437, "decode_str": " Significant"} -{"id": 31920, "token": "\u0120squamous", "merges": "\u0120squ amous", "raw_count": 437, "count": 437, "decode_str": " squamous"} -{"id": 35530, "token": "\u0120fermion", "merges": "\u0120ferm ion", "raw_count": 437, "count": 437, "decode_str": " fermion"} -{"id": 20758, "token": "CLUDING", "merges": "CLUD ING", "raw_count": 123, "count": 437, "decode_str": "CLUDING"} -{"id": 39107, "token": "\u0120Claude", "merges": "\u0120Cla ude", "raw_count": 437, "count": 437, "decode_str": " Claude"} -{"id": 19669, "token": "\u0120Billy", "merges": "\u0120B illy", "raw_count": 437, "count": 437, "decode_str": " Billy"} -{"id": 45448, "token": "\u0120r\u00c3\u00a9p", "merges": "\u0120r\u00c3\u00a9 p", "raw_count": 437, "count": 437, "decode_str": " r\u00e9p"} -{"id": 39037, "token": "\u0120Sew", "merges": "\u0120S ew", "raw_count": 437, "count": 437, "decode_str": " Sew"} -{"id": 47111, "token": "\u0120Byr", "merges": "\u0120By r", "raw_count": 437, "count": 437, "decode_str": " Byr"} -{"id": 42192, "token": "\u0120probative", "merges": "\u0120prob ative", "raw_count": 438, "count": 438, "decode_str": " probative"} -{"id": 43914, "token": "\u0120Families", "merges": "\u0120F amilies", "raw_count": 438, "count": 438, "decode_str": " Families"} -{"id": 41057, "token": "\u0120ainsi", "merges": "\u0120a insi", "raw_count": 438, "count": 438, "decode_str": " ainsi"} -{"id": 36253, "token": "\u0120Jill", "merges": "\u0120J ill", "raw_count": 438, "count": 438, "decode_str": " Jill"} -{"id": 18537, "token": "\u00e0\u00a8", "merges": "\u00e0 \u00a8", "raw_count": 438, "count": 438, "decode_str": "\ufffd"} -{"id": 48775, "token": "\u0120capricious", "merges": "\u0120capric ious", "raw_count": 439, "count": 439, "decode_str": " capricious"} -{"id": 24641, "token": "\u0120albumin", "merges": "\u0120album in", "raw_count": 439, "count": 439, "decode_str": " albumin"} -{"id": 18816, "token": "\u0120Hitler", "merges": "\u0120Hit ler", "raw_count": 439, "count": 439, "decode_str": " Hitler"} -{"id": 44948, "token": "\u0120Comedy", "merges": "\u0120Com edy", "raw_count": 439, "count": 439, "decode_str": " Comedy"} -{"id": 15924, "token": "\u0120Balt", "merges": "\u0120B alt", "raw_count": 116, "count": 439, "decode_str": " Balt"} -{"id": 42870, "token": "\u0120Mayo", "merges": "\u0120May o", "raw_count": 439, "count": 439, "decode_str": " Mayo"} -{"id": 32443, "token": "\u0120\u00d9\u012c", "merges": "\u0120 \u00d9\u012c", "raw_count": 439, "count": 439, "decode_str": " \u064a"} -{"id": 50062, "token": "\u00d5\u00b8", "merges": "\u00d5 \u00b8", "raw_count": 439, "count": 439, "decode_str": "\u0578"} -{"id": 29474, "token": "\u00e3\u0123\u00a8\u00e3\u0123\u0126\u00e3\u0123\u0128", "merges": "\u00e3\u0123\u00a8\u00e3\u0123\u0126 \u00e3\u0123\u0128", "raw_count": 440, "count": 440, "decode_str": "\u3068\u3044\u3046"} -{"id": 48585, "token": "\u0120Fleming", "merges": "\u0120Fle ming", "raw_count": 440, "count": 440, "decode_str": " Fleming"} -{"id": 28307, "token": "\u0120acidic", "merges": "\u0120acid ic", "raw_count": 440, "count": 440, "decode_str": " acidic"} -{"id": 46550, "token": "j\u00c3\u00a4", "merges": "j \u00c3\u00a4", "raw_count": 440, "count": 440, "decode_str": "j\u00e4"} -{"id": 48261, "token": "\u0120Goldberg", "merges": "\u0120Gold berg", "raw_count": 441, "count": 441, "decode_str": " Goldberg"} -{"id": 28180, "token": "\u0120synthase", "merges": "\u0120synth ase", "raw_count": 441, "count": 441, "decode_str": " synthase"} -{"id": 36562, "token": "\u0120Lastly", "merges": "\u0120Last ly", "raw_count": 441, "count": 441, "decode_str": " Lastly"} -{"id": 48125, "token": "\u0120Denis", "merges": "\u0120Den is", "raw_count": 441, "count": 441, "decode_str": " Denis"} -{"id": 25635, "token": "\u0120Ruth", "merges": "\u0120R uth", "raw_count": 441, "count": 441, "decode_str": " Ruth"} -{"id": 44422, "token": "\u0120CURL", "merges": "\u0120C URL", "raw_count": 441, "count": 441, "decode_str": " CURL"} -{"id": 29354, "token": "\u00cf\u0123\u00ce\u00ac", "merges": "\u00cf\u0123 \u00ce\u00ac", "raw_count": 441, "count": 441, "decode_str": "\u03c1\u03ac"} -{"id": 15734, "token": ")}{\\", "merges": ") }{\\", "raw_count": 441, "count": 441, "decode_str": ")}{\\"} -{"id": 46666, "token": "\u00c5\u00bce", "merges": "\u00c5\u00bc e", "raw_count": 441, "count": 441, "decode_str": "\u017ce"} -{"id": 49205, "token": "\u0120Psychological", "merges": "\u0120Psych ological", "raw_count": 442, "count": 442, "decode_str": " Psychological"} -{"id": 47824, "token": "\u0120Barton", "merges": "\u0120Bart on", "raw_count": 442, "count": 442, "decode_str": " Barton"} -{"id": 37751, "token": "\u0120leptin", "merges": "\u0120lept in", "raw_count": 442, "count": 442, "decode_str": " leptin"} -{"id": 31755, "token": "\u0120Logan", "merges": "\u0120Log an", "raw_count": 442, "count": 442, "decode_str": " Logan"} -{"id": 42073, "token": "\u0120Payne", "merges": "\u0120Pay ne", "raw_count": 442, "count": 442, "decode_str": " Payne"} -{"id": 44146, "token": "\u0120chemo", "merges": "\u0120chem o", "raw_count": 442, "count": 442, "decode_str": " chemo"} -{"id": 24125, "token": "\u0120~*", "merges": "\u0120~ *", "raw_count": 442, "count": 442, "decode_str": " ~*"} -{"id": 17765, "token": "){\\", "merges": ") {\\", "raw_count": 442, "count": 442, "decode_str": "){\\"} -{"id": 33767, "token": "\u0120diastolic", "merges": "\u0120di astolic", "raw_count": 443, "count": 443, "decode_str": " diastolic"} -{"id": 32863, "token": "\u0120Hungarian", "merges": "\u0120Hung arian", "raw_count": 443, "count": 443, "decode_str": " Hungarian"} -{"id": 36839, "token": "\u0120Cemetery", "merges": "\u0120C emetery", "raw_count": 443, "count": 443, "decode_str": " Cemetery"} -{"id": 8308, "token": "\u0120Minister", "merges": "\u0120Min ister", "raw_count": 443, "count": 443, "decode_str": " Minister"} -{"id": 38437, "token": "\u0120Johnston", "merges": "\u0120John ston", "raw_count": 443, "count": 443, "decode_str": " Johnston"} -{"id": 36097, "token": "\u0120Jenny", "merges": "\u0120J enny", "raw_count": 443, "count": 443, "decode_str": " Jenny"} -{"id": 25433, "token": "\u0120haben", "merges": "\u0120hab en", "raw_count": 443, "count": 443, "decode_str": " haben"} -{"id": 47800, "token": "\u0120USS", "merges": "\u0120US S", "raw_count": 443, "count": 443, "decode_str": " USS"} -{"id": 36048, "token": "Nevertheless", "merges": "Never theless", "raw_count": 444, "count": 444, "decode_str": "Nevertheless"} -{"id": 39035, "token": "\u0120Franco", "merges": "\u0120Franc o", "raw_count": 444, "count": 444, "decode_str": " Franco"} -{"id": 37194, "token": "\u0120cystic", "merges": "\u0120cy stic", "raw_count": 444, "count": 444, "decode_str": " cystic"} -{"id": 22646, "token": "\u0120MMP", "merges": "\u0120M MP", "raw_count": 444, "count": 444, "decode_str": " MMP"} -{"id": 32209, "token": "\u0120MHC", "merges": "\u0120M HC", "raw_count": 444, "count": 444, "decode_str": " MHC"} -{"id": 46276, "token": "h\u00c3\u00a4", "merges": "h \u00c3\u00a4", "raw_count": 444, "count": 444, "decode_str": "h\u00e4"} -{"id": 30021, "token": "\u0120Baptist", "merges": "\u0120Bapt ist", "raw_count": 445, "count": 445, "decode_str": " Baptist"} -{"id": 46681, "token": "\u0120Murder", "merges": "\u0120Mur der", "raw_count": 445, "count": 445, "decode_str": " Murder"} -{"id": 35213, "token": "\u0120Sister", "merges": "\u0120S ister", "raw_count": 445, "count": 445, "decode_str": " Sister"} -{"id": 33609, "token": "\u0120Dul", "merges": "\u0120D ul", "raw_count": 445, "count": 445, "decode_str": " Dul"} -{"id": 43881, "token": "\u0120prostitution", "merges": "\u0120pro stitution", "raw_count": 446, "count": 446, "decode_str": " prostitution"} -{"id": 26132, "token": "\u0120biosynthesis", "merges": "\u0120bios ynthesis", "raw_count": 446, "count": 446, "decode_str": " biosynthesis"} -{"id": 41926, "token": "\u0120Fitzgerald", "merges": "\u0120Fitz gerald", "raw_count": 446, "count": 446, "decode_str": " Fitzgerald"} -{"id": 26653, "token": "\u0120Amsterdam", "merges": "\u0120Am sterdam", "raw_count": 446, "count": 446, "decode_str": " Amsterdam"} -{"id": 35346, "token": "\u0120Firstly", "merges": "\u0120First ly", "raw_count": 446, "count": 446, "decode_str": " Firstly"} -{"id": 43457, "token": "\u0120acuity", "merges": "\u0120ac uity", "raw_count": 446, "count": 446, "decode_str": " acuity"} -{"id": 37760, "token": "\u00d9\u0129\u00d8\u00a7", "merges": "\u00d9\u0129 \u00d8\u00a7", "raw_count": 446, "count": 446, "decode_str": "\u0647\u0627"} -{"id": 45691, "token": "\u0120Cunningham", "merges": "\u0120C unningham", "raw_count": 447, "count": 447, "decode_str": " Cunningham"} -{"id": 39369, "token": "\u0120Combining", "merges": "\u0120Comb ining", "raw_count": 447, "count": 447, "decode_str": " Combining"} -{"id": 31563, "token": "\u0120Vladimir", "merges": "\u0120Vlad imir", "raw_count": 447, "count": 447, "decode_str": " Vladimir"} -{"id": 33315, "token": "\u0120Greens", "merges": "\u0120G reens", "raw_count": 447, "count": 447, "decode_str": " Greens"} -{"id": 45374, "token": "\u0120Cran", "merges": "\u0120C ran", "raw_count": 447, "count": 447, "decode_str": " Cran"} -{"id": 34278, "token": "\u0120affidavits", "merges": "\u0120affidav its", "raw_count": 448, "count": 448, "decode_str": " affidavits"} -{"id": 40879, "token": "\u0120Ernest", "merges": "\u0120Ern est", "raw_count": 448, "count": 448, "decode_str": " Ernest"} -{"id": 33825, "token": "\u0120redox", "merges": "\u0120red ox", "raw_count": 448, "count": 448, "decode_str": " redox"} -{"id": 42385, "token": "\u0120Basil", "merges": "\u0120Bas il", "raw_count": 448, "count": 448, "decode_str": " Basil"} -{"id": 32920, "token": "\u0120Riley", "merges": "\u0120R iley", "raw_count": 448, "count": 448, "decode_str": " Riley"} -{"id": 28177, "token": "\u0120Amer", "merges": "\u0120A mer", "raw_count": 448, "count": 448, "decode_str": " Amer"} -{"id": 21227, "token": "\u00cf\u0126\u00ce\u00b9", "merges": "\u00cf\u0126 \u00ce\u00b9", "raw_count": 434, "count": 448, "decode_str": "\u03c4\u03b9"} -{"id": 47226, "token": "\u0120laterally", "merges": "\u0120later ally", "raw_count": 449, "count": 449, "decode_str": " laterally"} -{"id": 29204, "token": "\u0120glutamate", "merges": "\u0120glut amate", "raw_count": 449, "count": 449, "decode_str": " glutamate"} -{"id": 45776, "token": "\u00e3\u0123\u00a7\u00e3\u0124\u0124", "merges": "\u00e3\u0123\u00a7 \u00e3\u0124\u0124", "raw_count": 449, "count": 449, "decode_str": "\u3067\u3082"} -{"id": 50089, "token": "ostomy", "merges": "ost omy", "raw_count": 449, "count": 449, "decode_str": "ostomy"} -{"id": 33240, "token": "\u0120Diana", "merges": "\u0120D iana", "raw_count": 449, "count": 449, "decode_str": " Diana"} -{"id": 30864, "token": "\u0120Drew", "merges": "\u0120D rew", "raw_count": 449, "count": 449, "decode_str": " Drew"} -{"id": 37888, "token": "\u0120WWE", "merges": "\u0120W WE", "raw_count": 449, "count": 449, "decode_str": " WWE"} -{"id": 51376, "token": "\u00e5\u0143\u0125", "merges": "\u00e5\u0143 \u0125", "raw_count": 449, "count": 449, "decode_str": "\u5b43"} -{"id": 41222, "token": "\u0120analogues", "merges": "\u0120analog ues", "raw_count": 450, "count": 450, "decode_str": " analogues"} -{"id": 38607, "token": "\u0120inoculation", "merges": "\u0120inoc ulation", "raw_count": 451, "count": 451, "decode_str": " inoculation"} -{"id": 30778, "token": "\u0120Imagine", "merges": "\u0120Im agine", "raw_count": 451, "count": 451, "decode_str": " Imagine"} -{"id": 21753, "token": "\u0120Austria", "merges": "\u0120Aust ria", "raw_count": 451, "count": 451, "decode_str": " Austria"} -{"id": 48929, "token": "\u0120futuro", "merges": "\u0120fut uro", "raw_count": 451, "count": 451, "decode_str": " futuro"} -{"id": 37109, "token": "omethyl", "merges": "om ethyl", "raw_count": 451, "count": 451, "decode_str": "omethyl"} -{"id": 49693, "token": "\u0120Surviv", "merges": "\u0120Surv iv", "raw_count": 451, "count": 451, "decode_str": " Surviv"} -{"id": 11596, "token": "\u0120Irish", "merges": "\u0120Ir ish", "raw_count": 451, "count": 451, "decode_str": " Irish"} -{"id": 38815, "token": "ASHINGTON", "merges": "ASH INGTON", "raw_count": 452, "count": 452, "decode_str": "ASHINGTON"} -{"id": 27141, "token": "\u0120Baseball", "merges": "\u0120Base ball", "raw_count": 452, "count": 452, "decode_str": " Baseball"} -{"id": 41087, "token": "\u0120Herman", "merges": "\u0120H erman", "raw_count": 452, "count": 452, "decode_str": " Herman"} -{"id": 30155, "token": "Figs", "merges": "Fig s", "raw_count": 452, "count": 452, "decode_str": "Figs"} -{"id": 43935, "token": "\u0120Tonight", "merges": "\u0120Ton ight", "raw_count": 453, "count": 453, "decode_str": " Tonight"} -{"id": 34177, "token": "\u0120neopl", "merges": "\u0120ne opl", "raw_count": 245, "count": 453, "decode_str": " neopl"} -{"id": 53750, "token": "\u00e8\u00a6\u0129", "merges": "\u00e8\u00a6 \u0129", "raw_count": 453, "count": 453, "decode_str": "\u8987"} -{"id": 33157, "token": "\u0120Renaissance", "merges": "\u0120Rena issance", "raw_count": 454, "count": 454, "decode_str": " Renaissance"} -{"id": 41865, "token": "\u0120\u00c3\u00a9gal", "merges": "\u0120\u00c3\u00a9 gal", "raw_count": 293, "count": 454, "decode_str": " \u00e9gal"} -{"id": 43695, "token": "\u0120chez", "merges": "\u0120che z", "raw_count": 454, "count": 454, "decode_str": " chez"} -{"id": 44009, "token": "k\u00c3\u00a9", "merges": "k \u00c3\u00a9", "raw_count": 454, "count": 454, "decode_str": "k\u00e9"} -{"id": 35266, "token": "\u0120Municipal", "merges": "\u0120Municip al", "raw_count": 455, "count": 455, "decode_str": " Municipal"} -{"id": 34313, "token": "\u0120Matthews", "merges": "\u0120Matthe ws", "raw_count": 455, "count": 455, "decode_str": " Matthews"} -{"id": 45648, "token": "\u0120nmol", "merges": "\u0120nm ol", "raw_count": 455, "count": 455, "decode_str": " nmol"} -{"id": 23207, "token": "\u0120\u00d8\u00a3", "merges": "\u0120\u00d8 \u00a3", "raw_count": 406, "count": 455, "decode_str": " \u0623"} -{"id": 48671, "token": "\u0120nucleation", "merges": "\u0120nucle ation", "raw_count": 456, "count": 456, "decode_str": " nucleation"} -{"id": 49413, "token": "\u0120adsorbed", "merges": "\u0120adsor bed", "raw_count": 456, "count": 456, "decode_str": " adsorbed"} -{"id": 23618, "token": "\u0120hypoxia", "merges": "\u0120hypox ia", "raw_count": 456, "count": 456, "decode_str": " hypoxia"} -{"id": 38071, "token": "\u0120Irving", "merges": "\u0120Ir ving", "raw_count": 456, "count": 456, "decode_str": " Irving"} -{"id": 32772, "token": "\u0120ADHD", "merges": "\u0120AD HD", "raw_count": 456, "count": 456, "decode_str": " ADHD"} -{"id": 38856, "token": "\u0120Pale", "merges": "\u0120P ale", "raw_count": 456, "count": 456, "decode_str": " Pale"} -{"id": 49039, "token": "\u0120Ways", "merges": "\u0120W ays", "raw_count": 456, "count": 456, "decode_str": " Ways"} -{"id": 36893, "token": "__>", "merges": "__ >", "raw_count": 456, "count": 456, "decode_str": "__>"} -{"id": 41919, "token": "\u0120cultivars", "merges": "\u0120cultiv ars", "raw_count": 457, "count": 457, "decode_str": " cultivars"} -{"id": 35852, "token": "\u0120Diseases", "merges": "\u0120Dise ases", "raw_count": 457, "count": 457, "decode_str": " Diseases"} -{"id": 44452, "token": "\u0120Shepherd", "merges": "\u0120She pherd", "raw_count": 457, "count": 457, "decode_str": " Shepherd"} -{"id": 28982, "token": "\u0120Martinez", "merges": "\u0120Mart inez", "raw_count": 457, "count": 457, "decode_str": " Martinez"} -{"id": 21739, "token": "\u0120Liberal", "merges": "\u0120Lib eral", "raw_count": 457, "count": 457, "decode_str": " Liberal"} -{"id": 36262, "token": "\u0120Customs", "merges": "\u0120Custom s", "raw_count": 457, "count": 457, "decode_str": " Customs"} -{"id": 14857, "token": "\u0120TNF", "merges": "\u0120T NF", "raw_count": 457, "count": 457, "decode_str": " TNF"} -{"id": 27825, "token": "}}-", "merges": "}} -", "raw_count": 457, "count": 457, "decode_str": "}}-"} -{"id": 27476, "token": "\u0120Figures", "merges": "\u0120Fig ures", "raw_count": 458, "count": 458, "decode_str": " Figures"} -{"id": 36362, "token": "\u0120Eugene", "merges": "\u0120Eug ene", "raw_count": 458, "count": 458, "decode_str": " Eugene"} -{"id": 40466, "token": "\u0120cloves", "merges": "\u0120cl oves", "raw_count": 458, "count": 458, "decode_str": " cloves"} -{"id": 9658, "token": "\u0120Among", "merges": "\u0120Am ong", "raw_count": 458, "count": 458, "decode_str": " Among"} -{"id": 46892, "token": "\u0120prong", "merges": "\u0120pr ong", "raw_count": 458, "count": 458, "decode_str": " prong"} -{"id": 50080, "token": "\u0120foraging", "merges": "\u0120for aging", "raw_count": 459, "count": 459, "decode_str": " foraging"} -{"id": 29677, "token": "\u0120Aber", "merges": "\u0120A ber", "raw_count": 459, "count": 459, "decode_str": " Aber"} -{"id": 41397, "token": "\u0120Zur", "merges": "\u0120Z ur", "raw_count": 459, "count": 459, "decode_str": " Zur"} -{"id": 41848, "token": "\u0120Hag", "merges": "\u0120H ag", "raw_count": 459, "count": 459, "decode_str": " Hag"} -{"id": 24738, "token": "\u0120metastases", "merges": "\u0120metast ases", "raw_count": 460, "count": 460, "decode_str": " metastases"} -{"id": 42042, "token": "\u0120\u00e0\u00a4\u00aa", "merges": "\u0120\u00e0\u00a4 \u00aa", "raw_count": 460, "count": 460, "decode_str": " \u092a"} -{"id": 32760, "token": "\u0120Wildlife", "merges": "\u0120Wild life", "raw_count": 461, "count": 461, "decode_str": " Wildlife"} -{"id": 42526, "token": "\u0120stably", "merges": "\u0120st ably", "raw_count": 461, "count": 461, "decode_str": " stably"} -{"id": 37702, "token": "\u0120Notre", "merges": "\u0120Not re", "raw_count": 461, "count": 461, "decode_str": " Notre"} -{"id": 48855, "token": "\u0120Garn", "merges": "\u0120G arn", "raw_count": 461, "count": 461, "decode_str": " Garn"} -{"id": 42964, "token": "\u0120meer", "merges": "\u0120me er", "raw_count": 461, "count": 461, "decode_str": " meer"} -{"id": 24891, "token": "\u0120coronavirus", "merges": "\u0120coron avirus", "raw_count": 462, "count": 462, "decode_str": " coronavirus"} -{"id": 33226, "token": "\u0120antagonists", "merges": "\u0120antagon ists", "raw_count": 462, "count": 462, "decode_str": " antagonists"} -{"id": 18242, "token": "\u0120plasmid", "merges": "\u0120plasm id", "raw_count": 462, "count": 462, "decode_str": " plasmid"} -{"id": 36200, "token": "\u0120Legion", "merges": "\u0120Leg ion", "raw_count": 462, "count": 462, "decode_str": " Legion"} -{"id": 15869, "token": "mapsto", "merges": "map sto", "raw_count": 462, "count": 462, "decode_str": "mapsto"} -{"id": 36297, "token": "\u0120Boyd", "merges": "\u0120Boy d", "raw_count": 462, "count": 462, "decode_str": " Boyd"} -{"id": 45213, "token": "\u0120IgA", "merges": "\u0120Ig A", "raw_count": 462, "count": 462, "decode_str": " IgA"} -{"id": 46329, "token": "\u0120Constantin", "merges": "\u0120Constant in", "raw_count": 463, "count": 463, "decode_str": " Constantin"} -{"id": 23425, "token": "\u0120Catherine", "merges": "\u0120C atherine", "raw_count": 463, "count": 463, "decode_str": " Catherine"} -{"id": 35798, "token": "\u0120Brock", "merges": "\u0120Bro ck", "raw_count": 463, "count": 463, "decode_str": " Brock"} -{"id": 29051, "token": "\u0120Quinn", "merges": "\u0120Qu inn", "raw_count": 463, "count": 463, "decode_str": " Quinn"} -{"id": 20429, "token": "mathit", "merges": "math it", "raw_count": 463, "count": 463, "decode_str": "mathit"} -{"id": 34471, "token": "\u0120Mama", "merges": "\u0120M ama", "raw_count": 463, "count": 463, "decode_str": " Mama"} -{"id": 21142, "token": "\u0120appellants", "merges": "\u0120appell ants", "raw_count": 464, "count": 464, "decode_str": " appellants"} -{"id": 49731, "token": "\u0120DEAL", "merges": "\u0120DE AL", "raw_count": 464, "count": 464, "decode_str": " DEAL"} -{"id": 45722, "token": "\u0120Miz", "merges": "\u0120M iz", "raw_count": 464, "count": 464, "decode_str": " Miz"} -{"id": 35776, "token": "\u0120Ful", "merges": "\u0120F ul", "raw_count": 464, "count": 464, "decode_str": " Ful"} -{"id": 40380, "token": "\u00c3\u00b6k", "merges": "\u00c3\u00b6 k", "raw_count": 464, "count": 464, "decode_str": "\u00f6k"} -{"id": 46933, "token": "\u0120Planned", "merges": "\u0120Pl anned", "raw_count": 465, "count": 465, "decode_str": " Planned"} -{"id": 36041, "token": "\u0120AMER", "merges": "\u0120AM ER", "raw_count": 238, "count": 465, "decode_str": " AMER"} -{"id": 40019, "token": "\u0120Hale", "merges": "\u0120H ale", "raw_count": 465, "count": 465, "decode_str": " Hale"} -{"id": 30823, "token": "\u0120lipoprotein", "merges": "\u0120lip oprotein", "raw_count": 466, "count": 466, "decode_str": " lipoprotein"} -{"id": 48322, "token": "\u0120Theoretical", "merges": "\u0120The oretical", "raw_count": 466, "count": 466, "decode_str": " Theoretical"} -{"id": 36105, "token": "\u0120Patterson", "merges": "\u0120Pat terson", "raw_count": 466, "count": 466, "decode_str": " Patterson"} -{"id": 37103, "token": "\u0120Baldwin", "merges": "\u0120Bald win", "raw_count": 466, "count": 466, "decode_str": " Baldwin"} -{"id": 22926, "token": "\u0120chiral", "merges": "\u0120ch iral", "raw_count": 466, "count": 466, "decode_str": " chiral"} -{"id": 27061, "token": "\u0120Tibet", "merges": "\u0120Tib et", "raw_count": 274, "count": 466, "decode_str": " Tibet"} -{"id": 43484, "token": "\u0120Gul", "merges": "\u0120G ul", "raw_count": 466, "count": 466, "decode_str": " Gul"} -{"id": 27349, "token": "\u0120MDA", "merges": "\u0120M DA", "raw_count": 466, "count": 466, "decode_str": " MDA"} -{"id": 14457, "token": "bibr", "merges": "bib r", "raw_count": 466, "count": 466, "decode_str": "bibr"} -{"id": 49502, "token": "\u0120Hoe", "merges": "\u0120H oe", "raw_count": 466, "count": 466, "decode_str": " Hoe"} -{"id": 20524, "token": "\u0120FITNESS", "merges": "\u0120FIT NESS", "raw_count": 467, "count": 467, "decode_str": " FITNESS"} -{"id": 20767, "token": "\u0120!==", "merges": "\u0120! ==", "raw_count": 467, "count": 467, "decode_str": " !=="} -{"id": 36399, "token": ")\\[", "merges": ") \\[", "raw_count": 467, "count": 467, "decode_str": ")\\["} -{"id": 35558, "token": "Abbreviations", "merges": "Ab breviations", "raw_count": 468, "count": 468, "decode_str": "Abbreviations"} -{"id": 33968, "token": "\u0120Differences", "merges": "\u0120D ifferences", "raw_count": 468, "count": 468, "decode_str": " Differences"} -{"id": 39366, "token": "ivariable", "merges": "iv ariable", "raw_count": 468, "count": 468, "decode_str": "ivariable"} -{"id": 48021, "token": "\u0120Norris", "merges": "\u0120Nor ris", "raw_count": 468, "count": 468, "decode_str": " Norris"} -{"id": 41171, "token": "\u0120gente", "merges": "\u0120gent e", "raw_count": 469, "count": 469, "decode_str": " gente"} -{"id": 45075, "token": "glich", "merges": "gl ich", "raw_count": 469, "count": 469, "decode_str": "glich"} -{"id": 17578, "token": "\u0120GFP", "merges": "\u0120G FP", "raw_count": 469, "count": 469, "decode_str": " GFP"} -{"id": 41559, "token": "\u0120immobilized", "merges": "\u0120immob ilized", "raw_count": 470, "count": 470, "decode_str": " immobilized"} -{"id": 37125, "token": "\u0120Babylon", "merges": "\u0120Bab ylon", "raw_count": 470, "count": 470, "decode_str": " Babylon"} -{"id": 20463, "token": "\u0120ett\u00c3\u00a4", "merges": "\u0120ett \u00c3\u00a4", "raw_count": 470, "count": 470, "decode_str": " ett\u00e4"} -{"id": 49019, "token": "\u0120Locke", "merges": "\u0120Loc ke", "raw_count": 470, "count": 470, "decode_str": " Locke"} -{"id": 44302, "token": "\u0120Zimm", "merges": "\u0120Z imm", "raw_count": 470, "count": 470, "decode_str": " Zimm"} -{"id": 46511, "token": "\u0120Gunn", "merges": "\u0120G unn", "raw_count": 470, "count": 470, "decode_str": " Gunn"} -{"id": 21159, "token": "\u0120}{", "merges": "\u0120} {", "raw_count": 470, "count": 470, "decode_str": " }{"} -{"id": 44945, "token": "\u0120Lancaster", "merges": "\u0120Lanc aster", "raw_count": 471, "count": 471, "decode_str": " Lancaster"} -{"id": 29841, "token": "\u0120apical", "merges": "\u0120ap ical", "raw_count": 471, "count": 471, "decode_str": " apical"} -{"id": 48954, "token": "\u0120Oval", "merges": "\u0120O val", "raw_count": 471, "count": 471, "decode_str": " Oval"} -{"id": 46410, "token": "()", "merges": "() \">", "raw_count": 608, "count": 608, "decode_str": "()\">"} -{"id": 49922, "token": "\u0120mindfulness", "merges": "\u0120mind fulness", "raw_count": 609, "count": 609, "decode_str": " mindfulness"} -{"id": 39602, "token": "\u0120Hoffman", "merges": "\u0120Hoff man", "raw_count": 609, "count": 609, "decode_str": " Hoffman"} -{"id": 50082, "token": "\u0120snar", "merges": "\u0120sn ar", "raw_count": 609, "count": 609, "decode_str": " snar"} -{"id": 46689, "token": "\u0120Hed", "merges": "\u0120H ed", "raw_count": 609, "count": 609, "decode_str": " Hed"} -{"id": 39283, "token": "AtA", "merges": "At A", "raw_count": 609, "count": 609, "decode_str": "AtA"} -{"id": 50363, "token": "\u00e2\u0138\u0130", "merges": "\u00e2\u0138 \u0130", "raw_count": 609, "count": 609, "decode_str": "\u258e"} -{"id": 24848, "token": "\u0120polymorphism", "merges": "\u0120polymorph ism", "raw_count": 610, "count": 610, "decode_str": " polymorphism"} -{"id": 28852, "token": "\u0120Barnes", "merges": "\u0120Barn es", "raw_count": 610, "count": 610, "decode_str": " Barnes"} -{"id": 40278, "token": "\u0120Toast", "merges": "\u0120To ast", "raw_count": 610, "count": 610, "decode_str": " Toast"} -{"id": 48405, "token": "\u0120Shall", "merges": "\u0120Sh all", "raw_count": 610, "count": 610, "decode_str": " Shall"} -{"id": 46315, "token": "\u0120Gesch", "merges": "\u0120G esch", "raw_count": 610, "count": 610, "decode_str": " Gesch"} -{"id": 144, "token": "\u00d4", "merges": "NULL", "raw_count": 610, "count": 610, "decode_str": "\ufffd"} -{"id": 33489, "token": "\u0120Peninsula", "merges": "\u0120Pen insula", "raw_count": 611, "count": 611, "decode_str": " Peninsula"} -{"id": 4689, "token": "}_{\\", "merges": "} _{\\", "raw_count": 610, "count": 611, "decode_str": "}_{\\"} -{"id": 45588, "token": "\u0120suo", "merges": "\u0120su o", "raw_count": 611, "count": 611, "decode_str": " suo"} -{"id": 18485, "token": "\u0120GOP", "merges": "\u0120G OP", "raw_count": 611, "count": 611, "decode_str": " GOP"} -{"id": 26150, "token": "\u0120Lagrangian", "merges": "\u0120Lag rangian", "raw_count": 612, "count": 612, "decode_str": " Lagrangian"} -{"id": 19011, "token": "ellants", "merges": "ell ants", "raw_count": 606, "count": 612, "decode_str": "ellants"} -{"id": 33003, "token": "\u0120Dame", "merges": "\u0120D ame", "raw_count": 612, "count": 612, "decode_str": " Dame"} -{"id": 41069, "token": "\u0120HBO", "merges": "\u0120H BO", "raw_count": 612, "count": 612, "decode_str": " HBO"} -{"id": 29611, "token": "\u0120silencing", "merges": "\u0120sil encing", "raw_count": 613, "count": 613, "decode_str": " silencing"} -{"id": 48505, "token": "\u0120Giovanni", "merges": "\u0120Gi ovanni", "raw_count": 613, "count": 613, "decode_str": " Giovanni"} -{"id": 39836, "token": "\u0120Intra", "merges": "\u0120Int ra", "raw_count": 613, "count": 613, "decode_str": " Intra"} -{"id": 43767, "token": "\u0120Yard", "merges": "\u0120Y ard", "raw_count": 613, "count": 613, "decode_str": " Yard"} -{"id": 50233, "token": "\u0120StringBuilder", "merges": "\u0120String Builder", "raw_count": 614, "count": 614, "decode_str": " StringBuilder"} -{"id": 32833, "token": "\u0120CONTRACT", "merges": "\u0120CONTR ACT", "raw_count": 614, "count": 614, "decode_str": " CONTRACT"} -{"id": 49253, "token": "\u0120scler", "merges": "\u0120s cler", "raw_count": 614, "count": 614, "decode_str": " scler"} -{"id": 41660, "token": "\u0120Herz", "merges": "\u0120Her z", "raw_count": 614, "count": 614, "decode_str": " Herz"} -{"id": 24520, "token": "\u0120Eur", "merges": "\u0120E ur", "raw_count": 614, "count": 614, "decode_str": " Eur"} -{"id": 32101, "token": "\u0120McCarthy", "merges": "\u0120McC arthy", "raw_count": 615, "count": 615, "decode_str": " McCarthy"} -{"id": 34626, "token": "\u0120intram", "merges": "\u0120int ram", "raw_count": 615, "count": 615, "decode_str": " intram"} -{"id": 36292, "token": "\u0120Edgar", "merges": "\u0120Ed gar", "raw_count": 615, "count": 615, "decode_str": " Edgar"} -{"id": 26062, "token": "\u0120Dennis", "merges": "\u0120D ennis", "raw_count": 616, "count": 616, "decode_str": " Dennis"} -{"id": 35608, "token": "\u0120quarks", "merges": "\u0120qu arks", "raw_count": 616, "count": 616, "decode_str": " quarks"} -{"id": 11474, "token": "\u0120Though", "merges": "\u0120Th ough", "raw_count": 616, "count": 616, "decode_str": " Though"} -{"id": 45773, "token": "\u0120Eliot", "merges": "\u0120Eli ot", "raw_count": 616, "count": 616, "decode_str": " Eliot"} -{"id": 20164, "token": "\u0120Jimmy", "merges": "\u0120Jim my", "raw_count": 616, "count": 616, "decode_str": " Jimmy"} -{"id": 35194, "token": "\u0120Said", "merges": "\u0120Sa id", "raw_count": 616, "count": 616, "decode_str": " Said"} -{"id": 40000, "token": "/>.", "merges": "/> .", "raw_count": 616, "count": 616, "decode_str": "/>."} -{"id": 47063, "token": "\u0120primates", "merges": "\u0120prim ates", "raw_count": 617, "count": 617, "decode_str": " primates"} -{"id": 35595, "token": "\u0120p\u00c3\u00bablic", "merges": "\u0120p \u00c3\u00bablic", "raw_count": 617, "count": 617, "decode_str": " p\u00fablic"} -{"id": 34400, "token": "kubuntu", "merges": "k ubuntu", "raw_count": 617, "count": 617, "decode_str": "kubuntu"} -{"id": 23662, "token": "\u0120Nathan", "merges": "\u0120N athan", "raw_count": 617, "count": 617, "decode_str": " Nathan"} -{"id": 34534, "token": "\u0120Witt", "merges": "\u0120W itt", "raw_count": 617, "count": 617, "decode_str": " Witt"} -{"id": 45851, "token": "\u0120Mage", "merges": "\u0120M age", "raw_count": 617, "count": 617, "decode_str": " Mage"} -{"id": 43789, "token": "\u0120Tay", "merges": "\u0120T ay", "raw_count": 617, "count": 617, "decode_str": " Tay"} -{"id": 29897, "token": "\u0120Peterson", "merges": "\u0120Peters on", "raw_count": 618, "count": 618, "decode_str": " Peterson"} -{"id": 45246, "token": "\u0120Nielsen", "merges": "\u0120N ielsen", "raw_count": 618, "count": 618, "decode_str": " Nielsen"} -{"id": 37611, "token": "\u0120Proced", "merges": "\u0120Pro ced", "raw_count": 331, "count": 618, "decode_str": " Proced"} -{"id": 43082, "token": "\u0120Fluor", "merges": "\u0120Flu or", "raw_count": 618, "count": 618, "decode_str": " Fluor"} -{"id": 41888, "token": "\u0120Ernst", "merges": "\u0120Ern st", "raw_count": 618, "count": 618, "decode_str": " Ernst"} -{"id": 45744, "token": "\u0120Odys", "merges": "\u0120Od ys", "raw_count": 618, "count": 618, "decode_str": " Odys"} -{"id": 45817, "token": "\u0120Oriental", "merges": "\u0120Ori ental", "raw_count": 619, "count": 619, "decode_str": " Oriental"} -{"id": 32791, "token": "\u0120ocular", "merges": "\u0120o cular", "raw_count": 619, "count": 619, "decode_str": " ocular"} -{"id": 35203, "token": "\u0120Tas", "merges": "\u0120T as", "raw_count": 619, "count": 619, "decode_str": " Tas"} -{"id": 40751, "token": "\u0120Basketball", "merges": "\u0120B asketball", "raw_count": 620, "count": 620, "decode_str": " Basketball"} -{"id": 31897, "token": "\u0120Lopez", "merges": "\u0120L opez", "raw_count": 620, "count": 620, "decode_str": " Lopez"} -{"id": 25326, "token": "\u00ce\u00bb\u00ce\u00bf", "merges": "\u00ce\u00bb \u00ce\u00bf", "raw_count": 620, "count": 620, "decode_str": "\u03bb\u03bf"} -{"id": 30246, "token": "\u0120isoforms", "merges": "\u0120iso forms", "raw_count": 621, "count": 621, "decode_str": " isoforms"} -{"id": 40177, "token": "\u0120Witness", "merges": "\u0120W itness", "raw_count": 621, "count": 621, "decode_str": " Witness"} -{"id": 31049, "token": "\u0120Solomon", "merges": "\u0120Sol omon", "raw_count": 621, "count": 621, "decode_str": " Solomon"} -{"id": 26516, "token": "\u0120epigen", "merges": "\u0120ep igen", "raw_count": 249, "count": 621, "decode_str": " epigen"} -{"id": 49315, "token": "\u0120dalla", "merges": "\u0120d alla", "raw_count": 621, "count": 621, "decode_str": " dalla"} -{"id": 49893, "token": "\u0120Indy", "merges": "\u0120Ind y", "raw_count": 621, "count": 621, "decode_str": " Indy"} -{"id": 31375, "token": "\u0120dissociation", "merges": "\u0120diss ociation", "raw_count": 622, "count": 622, "decode_str": " dissociation"} -{"id": 41531, "token": "\u0120rebounds", "merges": "\u0120reb ounds", "raw_count": 622, "count": 622, "decode_str": " rebounds"} -{"id": 6824, "token": "\u0120});", "merges": "\u0120} );", "raw_count": 622, "count": 622, "decode_str": " });"} -{"id": 24045, "token": "\u0120hypothesized", "merges": "\u0120hypothes ized", "raw_count": 623, "count": 623, "decode_str": " hypothesized"} -{"id": 22810, "token": "\u0120Johnny", "merges": "\u0120John ny", "raw_count": 623, "count": 623, "decode_str": " Johnny"} -{"id": 50011, "token": "\u00d8\u00ba", "merges": "\u00d8 \u00ba", "raw_count": 623, "count": 623, "decode_str": "\u063a"} -{"id": 40149, "token": "\u0120reasonableness", "merges": "\u0120reason ableness", "raw_count": 624, "count": 624, "decode_str": " reasonableness"} -{"id": 42002, "token": "\u0120proximate", "merges": "\u0120pro ximate", "raw_count": 624, "count": 624, "decode_str": " proximate"} -{"id": 36051, "token": "\u0120Knights", "merges": "\u0120Kn ights", "raw_count": 624, "count": 624, "decode_str": " Knights"} -{"id": 43602, "token": "\u0120Berger", "merges": "\u0120Ber ger", "raw_count": 624, "count": 624, "decode_str": " Berger"} -{"id": 42265, "token": "\u0120Curry", "merges": "\u0120Cur ry", "raw_count": 624, "count": 624, "decode_str": " Curry"} -{"id": 44477, "token": "\u0120Pione", "merges": "\u0120P ione", "raw_count": 624, "count": 624, "decode_str": " Pione"} -{"id": 45861, "token": "\u0120bony", "merges": "\u0120b ony", "raw_count": 624, "count": 624, "decode_str": " bony"} -{"id": 48057, "token": "ouden", "merges": "oud en", "raw_count": 624, "count": 624, "decode_str": "ouden"} -{"id": 48493, "token": "\u0120Cres", "merges": "\u0120C res", "raw_count": 624, "count": 624, "decode_str": " Cres"} -{"id": 50191, "token": "\u0120Pep", "merges": "\u0120P ep", "raw_count": 625, "count": 625, "decode_str": " Pep"} -{"id": 47528, "token": "\u0120STRICT", "merges": "\u0120STR ICT", "raw_count": 626, "count": 626, "decode_str": " STRICT"} -{"id": 31508, "token": "\u0120Bever", "merges": "\u0120B ever", "raw_count": 463, "count": 626, "decode_str": " Bever"} -{"id": 18184, "token": "\u00ce\u00af\u00ce\u00b1", "merges": "\u00ce\u00af \u00ce\u00b1", "raw_count": 510, "count": 626, "decode_str": "\u03af\u03b1"} -{"id": 45147, "token": "\u0120SFR", "merges": "\u0120S FR", "raw_count": 626, "count": 626, "decode_str": " SFR"} -{"id": 48735, "token": "\u0120Wedding", "merges": "\u0120Wed ding", "raw_count": 627, "count": 627, "decode_str": " Wedding"} -{"id": 41675, "token": "\u0120Shim", "merges": "\u0120Sh im", "raw_count": 627, "count": 627, "decode_str": " Shim"} -{"id": 27438, "token": "\u0120Montgomery", "merges": "\u0120Mont gomery", "raw_count": 628, "count": 628, "decode_str": " Montgomery"} -{"id": 42113, "token": "\u0120BUSINESS", "merges": "\u0120BUS INESS", "raw_count": 628, "count": 628, "decode_str": " BUSINESS"} -{"id": 26250, "token": "\u0120Springs", "merges": "\u0120Spr ings", "raw_count": 628, "count": 628, "decode_str": " Springs"} -{"id": 52070, "token": "\u00e6\u0137\u0130", "merges": "\u00e6\u0137 \u0130", "raw_count": 628, "count": 628, "decode_str": "\u654e"} -{"id": 23340, "token": "\u0120Indonesia", "merges": "\u0120Indones ia", "raw_count": 629, "count": 629, "decode_str": " Indonesia"} -{"id": 47907, "token": "\u0120Braun", "merges": "\u0120Bra un", "raw_count": 629, "count": 629, "decode_str": " Braun"} -{"id": 45626, "token": "\u0120Exped", "merges": "\u0120Ex ped", "raw_count": 629, "count": 629, "decode_str": " Exped"} -{"id": 10857, "token": "\u0120phosphory", "merges": "\u0120phosph ory", "raw_count": 184, "count": 630, "decode_str": " phosphory"} -{"id": 43998, "token": "\u0120countable", "merges": "\u0120count able", "raw_count": 630, "count": 630, "decode_str": " countable"} -{"id": 40215, "token": "\u0120affective", "merges": "\u0120affect ive", "raw_count": 630, "count": 630, "decode_str": " affective"} -{"id": 39708, "token": "\u0120reflux", "merges": "\u0120re flux", "raw_count": 630, "count": 630, "decode_str": " reflux"} -{"id": 36055, "token": "\u0120Alleg", "merges": "\u0120Al leg", "raw_count": 630, "count": 630, "decode_str": " Alleg"} -{"id": 26121, "token": "\u0120Nep", "merges": "\u0120N ep", "raw_count": 463, "count": 630, "decode_str": " Nep"} -{"id": 39935, "token": "\u0120Progressive", "merges": "\u0120Pro gressive", "raw_count": 631, "count": 631, "decode_str": " Progressive"} -{"id": 24620, "token": "\u0120Guidelines", "merges": "\u0120Gu idelines", "raw_count": 631, "count": 631, "decode_str": " Guidelines"} -{"id": 36218, "token": "\u0120penicillin", "merges": "\u0120pen icillin", "raw_count": 631, "count": 631, "decode_str": " penicillin"} -{"id": 50158, "token": "\u0120desarroll", "merges": "\u0120des arroll", "raw_count": 631, "count": 631, "decode_str": " desarroll"} -{"id": 37874, "token": "\u0120paraffin", "merges": "\u0120par affin", "raw_count": 631, "count": 631, "decode_str": " paraffin"} -{"id": 34855, "token": "\u0120Andrews", "merges": "\u0120Andrew s", "raw_count": 631, "count": 631, "decode_str": " Andrews"} -{"id": 31083, "token": "\u0120Prison", "merges": "\u0120Pr ison", "raw_count": 631, "count": 631, "decode_str": " Prison"} -{"id": 26419, "token": "\u0120Chuck", "merges": "\u0120Ch uck", "raw_count": 631, "count": 631, "decode_str": " Chuck"} -{"id": 29336, "token": "\u0120Cann", "merges": "\u0120C ann", "raw_count": 631, "count": 631, "decode_str": " Cann"} -{"id": 39205, "token": "\u0120Gut", "merges": "\u0120G ut", "raw_count": 631, "count": 631, "decode_str": " Gut"} -{"id": 48627, "token": "\u0120Essentially", "merges": "\u0120Ess entially", "raw_count": 632, "count": 632, "decode_str": " Essentially"} -{"id": 46994, "token": "\u0120thickening", "merges": "\u0120thick ening", "raw_count": 632, "count": 632, "decode_str": " thickening"} -{"id": 34841, "token": "\u0120Heights", "merges": "\u0120He ights", "raw_count": 632, "count": 632, "decode_str": " Heights"} -{"id": 19917, "token": "\u0120Barbara", "merges": "\u0120Bar bara", "raw_count": 632, "count": 632, "decode_str": " Barbara"} -{"id": 50016, "token": "\u0120Tut", "merges": "\u0120T ut", "raw_count": 632, "count": 632, "decode_str": " Tut"} -{"id": 28562, "token": "\u0120ook", "merges": "\u0120o ok", "raw_count": 632, "count": 632, "decode_str": " ook"} -{"id": 36023, "token": "\u0120foreclosure", "merges": "\u0120fore closure", "raw_count": 633, "count": 633, "decode_str": " foreclosure"} -{"id": 46355, "token": "\u0120postpartum", "merges": "\u0120post partum", "raw_count": 633, "count": 633, "decode_str": " postpartum"} -{"id": 41348, "token": "oresist", "merges": "ores ist", "raw_count": 532, "count": 633, "decode_str": "oresist"} -{"id": 48226, "token": "\u0120caries", "merges": "\u0120car ies", "raw_count": 633, "count": 633, "decode_str": " caries"} -{"id": 37792, "token": "\u0120Lung", "merges": "\u0120L ung", "raw_count": 633, "count": 633, "decode_str": " Lung"} -{"id": 38867, "token": "\u0120TiO", "merges": "\u0120Ti O", "raw_count": 633, "count": 633, "decode_str": " TiO"} -{"id": 48807, "token": "\u0120\u00e0\u00b4", "merges": "\u0120 \u00e0\u00b4", "raw_count": 633, "count": 633, "decode_str": " \ufffd"} -{"id": 40721, "token": "\u0120Hubble", "merges": "\u0120Hub ble", "raw_count": 634, "count": 634, "decode_str": " Hubble"} -{"id": 39339, "token": "\u0120Cotton", "merges": "\u0120Cot ton", "raw_count": 634, "count": 634, "decode_str": " Cotton"} -{"id": 23204, "token": "\u0120\u00d0\u00b4\u00d0\u00b0", "merges": "\u0120\u00d0\u00b4 \u00d0\u00b0", "raw_count": 634, "count": 634, "decode_str": " \u0434\u0430"} -{"id": 25975, "token": "\u0120Emma", "merges": "\u0120Em ma", "raw_count": 634, "count": 634, "decode_str": " Emma"} -{"id": 23011, "token": "\u0120PhD", "merges": "\u0120Ph D", "raw_count": 634, "count": 634, "decode_str": " PhD"} -{"id": 38164, "token": "\u0120HIS", "merges": "\u0120H IS", "raw_count": 634, "count": 634, "decode_str": " HIS"} -{"id": 50305, "token": "\u00e2\u0124\u0123", "merges": "\u00e2\u0124 \u0123", "raw_count": 634, "count": 634, "decode_str": "\u2081"} -{"id": 50314, "token": "\u00e2\u012a\u0122", "merges": "\u00e2\u012a \u0122", "raw_count": 634, "count": 634, "decode_str": "\u2200"} -{"id": 21235, "token": "\u0120Jerem", "merges": "\u0120Je rem", "raw_count": 117, "count": 635, "decode_str": " Jerem"} -{"id": 46897, "token": "juvant", "merges": "ju vant", "raw_count": 635, "count": 635, "decode_str": "juvant"} -{"id": 21638, "token": "\u0120Terry", "merges": "\u0120T erry", "raw_count": 635, "count": 635, "decode_str": " Terry"} -{"id": 46884, "token": "\u0120gibt", "merges": "\u0120gib t", "raw_count": 635, "count": 635, "decode_str": " gibt"} -{"id": 50031, "token": "\u00c3\u00a1d", "merges": "\u00c3\u00a1 d", "raw_count": 635, "count": 635, "decode_str": "\u00e1d"} -{"id": 49113, "token": "\u00e1\u00be", "merges": "\u00e1 \u00be", "raw_count": 635, "count": 635, "decode_str": "\ufffd"} -{"id": 35257, "token": "\u0120\u00d5", "merges": "\u0120 \u00d5", "raw_count": 635, "count": 635, "decode_str": " \ufffd"} -{"id": 18856, "token": "\\;", "merges": "\\ ;", "raw_count": 635, "count": 635, "decode_str": "\\;"} -{"id": 43674, "token": "\u0120sophomore", "merges": "\u0120soph omore", "raw_count": 636, "count": 636, "decode_str": " sophomore"} -{"id": 42797, "token": "\u0120vagina", "merges": "\u0120vag ina", "raw_count": 636, "count": 636, "decode_str": " vagina"} -{"id": 45810, "token": "\u0120erotic", "merges": "\u0120er otic", "raw_count": 636, "count": 636, "decode_str": " erotic"} -{"id": 39523, "token": "\u0120Pride", "merges": "\u0120Pr ide", "raw_count": 636, "count": 636, "decode_str": " Pride"} -{"id": 48784, "token": "\u00e3\u0123\u00aa\u00e3\u0123\u0131", "merges": "\u00e3\u0123\u00aa \u00e3\u0123\u0131", "raw_count": 636, "count": 636, "decode_str": "\u306a\u304f"} -{"id": 45931, "token": "\u0120Vera", "merges": "\u0120V era", "raw_count": 636, "count": 636, "decode_str": " Vera"} -{"id": 46632, "token": "\u0120THEM", "merges": "\u0120THE M", "raw_count": 636, "count": 636, "decode_str": " THEM"} -{"id": 21380, "token": "v\u00c3\u00a4", "merges": "v \u00c3\u00a4", "raw_count": 636, "count": 636, "decode_str": "v\u00e4"} -{"id": 37349, "token": "\u0120Engineers", "merges": "\u0120Engine ers", "raw_count": 637, "count": 637, "decode_str": " Engineers"} -{"id": 39031, "token": "\u0120vertebral", "merges": "\u0120verte bral", "raw_count": 637, "count": 637, "decode_str": " vertebral"} -{"id": 45356, "token": "\u0120Observe", "merges": "\u0120Obs erve", "raw_count": 637, "count": 637, "decode_str": " Observe"} -{"id": 44990, "token": "\u0120Hew", "merges": "\u0120He w", "raw_count": 637, "count": 637, "decode_str": " Hew"} -{"id": 40109, "token": "\u0120h\u00c3\u00b6", "merges": "\u0120h \u00c3\u00b6", "raw_count": 637, "count": 637, "decode_str": " h\u00f6"} -{"id": 33005, "token": "\u0120Rac", "merges": "\u0120R ac", "raw_count": 637, "count": 637, "decode_str": " Rac"} -{"id": 35146, "token": "\u0120CRP", "merges": "\u0120CR P", "raw_count": 637, "count": 637, "decode_str": " CRP"} -{"id": 35290, "token": "\u0120Rum", "merges": "\u0120R um", "raw_count": 637, "count": 637, "decode_str": " Rum"} -{"id": 42931, "token": "\u00c2\u00b5m", "merges": "\u00c2\u00b5 m", "raw_count": 637, "count": 637, "decode_str": "\u00b5m"} -{"id": 23041, "token": "\u0120Historic", "merges": "\u0120Histor ic", "raw_count": 638, "count": 638, "decode_str": " Historic"} -{"id": 25188, "token": "\u0120worden", "merges": "\u0120word en", "raw_count": 638, "count": 638, "decode_str": " worden"} -{"id": 38020, "token": "\u0120Bend", "merges": "\u0120B end", "raw_count": 638, "count": 638, "decode_str": " Bend"} -{"id": 42610, "token": "\u0120STEM", "merges": "\u0120ST EM", "raw_count": 638, "count": 638, "decode_str": " STEM"} -{"id": 50359, "token": "\u00e2\u0138\u012b", "merges": "\u00e2\u0138 \u012b", "raw_count": 638, "count": 638, "decode_str": "\u2589"} -{"id": 41366, "token": "\u0120statewide", "merges": "\u0120state wide", "raw_count": 639, "count": 639, "decode_str": " statewide"} -{"id": 34070, "token": "\u0120Tucker", "merges": "\u0120T ucker", "raw_count": 639, "count": 639, "decode_str": " Tucker"} -{"id": 45966, "token": "\u0120monop", "merges": "\u0120mon op", "raw_count": 639, "count": 639, "decode_str": " monop"} -{"id": 26243, "token": "\u0120n\u00c3\u00a4", "merges": "\u0120n \u00c3\u00a4", "raw_count": 639, "count": 639, "decode_str": " n\u00e4"} -{"id": 34310, "token": "\u0120overruled", "merges": "\u0120overr uled", "raw_count": 640, "count": 640, "decode_str": " overruled"} -{"id": 45349, "token": "\u0120Fighting", "merges": "\u0120F ighting", "raw_count": 640, "count": 640, "decode_str": " Fighting"} -{"id": 42900, "token": "\u0120Trophy", "merges": "\u0120T rophy", "raw_count": 640, "count": 640, "decode_str": " Trophy"} -{"id": 28128, "token": "))**(-", "merges": ")) **(-", "raw_count": 640, "count": 640, "decode_str": "))**(-"} -{"id": 32543, "token": "\u0120Pray", "merges": "\u0120P ray", "raw_count": 314, "count": 640, "decode_str": " Pray"} -{"id": 43624, "token": "\u0120Bret", "merges": "\u0120B ret", "raw_count": 640, "count": 640, "decode_str": " Bret"} -{"id": 10968, "token": "\u0120Sov", "merges": "\u0120S ov", "raw_count": 205, "count": 640, "decode_str": " Sov"} -{"id": 50293, "token": "\u00e2\u0122\u0138", "merges": "\u00e2\u0122 \u0138", "raw_count": 640, "count": 640, "decode_str": "\u2016"} -{"id": 19331, "token": "\u0120heterogeneity", "merges": "\u0120heter ogeneity", "raw_count": 641, "count": 641, "decode_str": " heterogeneity"} -{"id": 40755, "token": "\u0120automorphism", "merges": "\u0120autom orphism", "raw_count": 641, "count": 641, "decode_str": " automorphism"} -{"id": 43556, "token": "\u0120columnist", "merges": "\u0120column ist", "raw_count": 641, "count": 641, "decode_str": " columnist"} -{"id": 36580, "token": "\u0120Angels", "merges": "\u0120Ang els", "raw_count": 641, "count": 641, "decode_str": " Angels"} -{"id": 45165, "token": "\u0120Witch", "merges": "\u0120W itch", "raw_count": 641, "count": 641, "decode_str": " Witch"} -{"id": 8755, "token": "\u0120Lemma", "merges": "\u0120Lem ma", "raw_count": 641, "count": 641, "decode_str": " Lemma"} -{"id": 45977, "token": "\u0120Fors", "merges": "\u0120F ors", "raw_count": 641, "count": 641, "decode_str": " Fors"} -{"id": 49324, "token": "\u0120Vamp", "merges": "\u0120V amp", "raw_count": 641, "count": 641, "decode_str": " Vamp"} -{"id": 27830, "token": "\u0120p\u00c5\u013b", "merges": "\u0120p \u00c5\u013b", "raw_count": 641, "count": 641, "decode_str": " p\u0159"} -{"id": 52939, "token": "\u00e7\u0139\u0142", "merges": "\u00e7\u0139 \u0142", "raw_count": 641, "count": 641, "decode_str": "\u75e0"} -{"id": 33736, "token": "\u0120spectroscopic", "merges": "\u0120spectrosc opic", "raw_count": 642, "count": 642, "decode_str": " spectroscopic"} -{"id": 31046, "token": "\u0120eukary", "merges": "\u0120e ukary", "raw_count": 285, "count": 642, "decode_str": " eukary"} -{"id": 28516, "token": "\u0120glomer", "merges": "\u0120gl omer", "raw_count": 461, "count": 642, "decode_str": " glomer"} -{"id": 49121, "token": "\u0120Essays", "merges": "\u0120Ess ays", "raw_count": 642, "count": 642, "decode_str": " Essays"} -{"id": 37089, "token": "\u0120Lips", "merges": "\u0120L ips", "raw_count": 327, "count": 642, "decode_str": " Lips"} -{"id": 18573, "token": "alkyl", "merges": "alk yl", "raw_count": 642, "count": 642, "decode_str": "alkyl"} -{"id": 45631, "token": "\u0120\u00c3\u00a9v", "merges": "\u0120\u00c3\u00a9 v", "raw_count": 642, "count": 642, "decode_str": " \u00e9v"} -{"id": 21039, "token": "\u0120platelet", "merges": "\u0120plate let", "raw_count": 643, "count": 643, "decode_str": " platelet"} -{"id": 40180, "token": "\u0120creamy", "merges": "\u0120cream y", "raw_count": 643, "count": 643, "decode_str": " creamy"} -{"id": 39736, "token": "\u0120Dixon", "merges": "\u0120D ixon", "raw_count": 643, "count": 643, "decode_str": " Dixon"} -{"id": 21965, "token": "\u0120Soon", "merges": "\u0120So on", "raw_count": 643, "count": 643, "decode_str": " Soon"} -{"id": 32585, "token": "TRODUCTION", "merges": "TR ODUCTION", "raw_count": 553, "count": 644, "decode_str": "TRODUCTION"} -{"id": 49540, "token": "\u0120Prospect", "merges": "\u0120Pro spect", "raw_count": 644, "count": 644, "decode_str": " Prospect"} -{"id": 22671, "token": "\u0120Cameron", "merges": "\u0120Cam eron", "raw_count": 644, "count": 644, "decode_str": " Cameron"} -{"id": 29944, "token": "\u0120Hardy", "merges": "\u0120Hard y", "raw_count": 644, "count": 644, "decode_str": " Hardy"} -{"id": 47976, "token": "\u0120Gru", "merges": "\u0120G ru", "raw_count": 644, "count": 644, "decode_str": " Gru"} -{"id": 25378, "token": "\u00d9\u012b", "merges": "\u00d9 \u012b", "raw_count": 416, "count": 644, "decode_str": "\u0649"} -{"id": 50283, "token": "\u00cb\u012a", "merges": "\u00cb \u012a", "raw_count": 644, "count": 644, "decode_str": "\u02c8"} -{"id": 42849, "token": "\u0120Consortium", "merges": "\u0120Cons ortium", "raw_count": 645, "count": 645, "decode_str": " Consortium"} -{"id": 38618, "token": "newcommand", "merges": "new command", "raw_count": 645, "count": 645, "decode_str": "newcommand"} -{"id": 13533, "token": "\u0120Toronto", "merges": "\u0120Tor onto", "raw_count": 645, "count": 645, "decode_str": " Toronto"} -{"id": 22663, "token": "\u0120Harper", "merges": "\u0120Har per", "raw_count": 645, "count": 645, "decode_str": " Harper"} -{"id": 29926, "token": "\u0120Griffin", "merges": "\u0120Griff in", "raw_count": 646, "count": 646, "decode_str": " Griffin"} -{"id": 47663, "token": "\u0120millig", "merges": "\u0120mill ig", "raw_count": 646, "count": 646, "decode_str": " millig"} -{"id": 50279, "token": "\u00c9\u0136", "merges": "\u00c9 \u0136", "raw_count": 646, "count": 646, "decode_str": "\u0254"} -{"id": 31199, "token": "\u0120Terror", "merges": "\u0120T error", "raw_count": 647, "count": 647, "decode_str": " Terror"} -{"id": 23442, "token": "\u0120Helen", "merges": "\u0120Hel en", "raw_count": 647, "count": 647, "decode_str": " Helen"} -{"id": 36044, "token": "\u0120Hunting", "merges": "\u0120Hun ting", "raw_count": 405, "count": 648, "decode_str": " Hunting"} -{"id": 36061, "token": "oplasmic", "merges": "oplasm ic", "raw_count": 648, "count": 648, "decode_str": "oplasmic"} -{"id": 17793, "token": "\u0120hypox", "merges": "\u0120hyp ox", "raw_count": 83, "count": 648, "decode_str": " hypox"} -{"id": 45858, "token": "\u0120Yosh", "merges": "\u0120Y osh", "raw_count": 648, "count": 648, "decode_str": " Yosh"} -{"id": 30598, "token": "\u00e0\u00a4\u00b9", "merges": "\u00e0\u00a4 \u00b9", "raw_count": 648, "count": 648, "decode_str": "\u0939"} -{"id": 27331, "token": "\u0120pharmacological", "merges": "\u0120pharmac ological", "raw_count": 649, "count": 649, "decode_str": " pharmacological"} -{"id": 31639, "token": "\u0120Interior", "merges": "\u0120Inter ior", "raw_count": 649, "count": 649, "decode_str": " Interior"} -{"id": 35463, "token": "\u0120Lance", "merges": "\u0120L ance", "raw_count": 649, "count": 649, "decode_str": " Lance"} -{"id": 48366, "token": "\u0120Jail", "merges": "\u0120J ail", "raw_count": 649, "count": 649, "decode_str": " Jail"} -{"id": 38943, "token": "}}|", "merges": "}} |", "raw_count": 649, "count": 649, "decode_str": "}}|"} -{"id": 31298, "token": "\u0120Proceedings", "merges": "\u0120Pro ceedings", "raw_count": 650, "count": 650, "decode_str": " Proceedings"} -{"id": 44339, "token": "\u0120Shirley", "merges": "\u0120Shir ley", "raw_count": 650, "count": 650, "decode_str": " Shirley"} -{"id": 45705, "token": "\u0120phenol", "merges": "\u0120phen ol", "raw_count": 650, "count": 650, "decode_str": " phenol"} -{"id": 32826, "token": "\u0120Tall", "merges": "\u0120T all", "raw_count": 650, "count": 650, "decode_str": " Tall"} -{"id": 47900, "token": "\u0120Oliv", "merges": "\u0120Ol iv", "raw_count": 650, "count": 650, "decode_str": " Oliv"} -{"id": 48905, "token": "\u0120Mush", "merges": "\u0120M ush", "raw_count": 650, "count": 650, "decode_str": " Mush"} -{"id": 17152, "token": "\u0120Legisl", "merges": "\u0120Leg isl", "raw_count": 356, "count": 651, "decode_str": " Legisl"} -{"id": 43354, "token": "\u0120Bates", "merges": "\u0120B ates", "raw_count": 651, "count": 651, "decode_str": " Bates"} -{"id": 17686, "token": "\u0120\u00cf\u0126\u00ce\u00bf", "merges": "\u0120\u00cf\u0126 \u00ce\u00bf", "raw_count": 651, "count": 651, "decode_str": " \u03c4\u03bf"} -{"id": 40938, "token": "\u0120Dogs", "merges": "\u0120D ogs", "raw_count": 651, "count": 651, "decode_str": " Dogs"} -{"id": 50310, "token": "\u00e2\u0126\u0138", "merges": "\u00e2\u0126 \u0138", "raw_count": 651, "count": 651, "decode_str": "\u2116"} -{"id": 50130, "token": "\u0120neutralizing", "merges": "\u0120neutral izing", "raw_count": 652, "count": 652, "decode_str": " neutralizing"} -{"id": 33477, "token": "\u0120corneal", "merges": "\u0120corne al", "raw_count": 652, "count": 652, "decode_str": " corneal"} -{"id": 49658, "token": "\u0120epistem", "merges": "\u0120epist em", "raw_count": 652, "count": 652, "decode_str": " epistem"} -{"id": 24962, "token": "\u0120Oscar", "merges": "\u0120O scar", "raw_count": 652, "count": 652, "decode_str": " Oscar"} -{"id": 41425, "token": "\u0120Gamb", "merges": "\u0120G amb", "raw_count": 652, "count": 652, "decode_str": " Gamb"} -{"id": 39921, "token": "\u0120Contemporary", "merges": "\u0120Cont emporary", "raw_count": 653, "count": 653, "decode_str": " Contemporary"} -{"id": 24324, "token": "\u0120Warner", "merges": "\u0120War ner", "raw_count": 653, "count": 653, "decode_str": " Warner"} -{"id": 44101, "token": "stating", "merges": "st ating", "raw_count": 653, "count": 653, "decode_str": "stating"} -{"id": 38056, "token": "\u0120Surve", "merges": "\u0120Sur ve", "raw_count": 653, "count": 653, "decode_str": " Surve"} -{"id": 27779, "token": "\u0120Herr", "merges": "\u0120H err", "raw_count": 653, "count": 653, "decode_str": " Herr"} -{"id": 44367, "token": "\u0120EGF", "merges": "\u0120E GF", "raw_count": 653, "count": 653, "decode_str": " EGF"} -{"id": 32432, "token": "ferentially", "merges": "ferent ially", "raw_count": 237, "count": 654, "decode_str": "ferentially"} -{"id": 35971, "token": "\u0120Chronicle", "merges": "\u0120Chron icle", "raw_count": 654, "count": 654, "decode_str": " Chronicle"} -{"id": 40289, "token": "\u0120Doyle", "merges": "\u0120D oyle", "raw_count": 654, "count": 654, "decode_str": " Doyle"} -{"id": 29053, "token": "\u0120Burke", "merges": "\u0120Bur ke", "raw_count": 654, "count": 654, "decode_str": " Burke"} -{"id": 35188, "token": "\u0120excitations", "merges": "\u0120excit ations", "raw_count": 655, "count": 655, "decode_str": " excitations"} -{"id": 20904, "token": "\u0120Cape", "merges": "\u0120C ape", "raw_count": 655, "count": 655, "decode_str": " Cape"} -{"id": 42789, "token": "})+", "merges": "}) +", "raw_count": 655, "count": 655, "decode_str": "})+"} -{"id": 34405, "token": "\u0120Robertson", "merges": "\u0120Roberts on", "raw_count": 656, "count": 656, "decode_str": " Robertson"} -{"id": 34929, "token": "\u0120lesbian", "merges": "\u0120les bian", "raw_count": 656, "count": 656, "decode_str": " lesbian"} -{"id": 48537, "token": "\u0120amplic", "merges": "\u0120am plic", "raw_count": 656, "count": 656, "decode_str": " amplic"} -{"id": 44575, "token": "\u0120Maple", "merges": "\u0120Map le", "raw_count": 656, "count": 656, "decode_str": " Maple"} -{"id": 47472, "token": "\u0120Fans", "merges": "\u0120F ans", "raw_count": 656, "count": 656, "decode_str": " Fans"} -{"id": 48669, "token": "\u0120Tir", "merges": "\u0120T ir", "raw_count": 656, "count": 656, "decode_str": " Tir"} -{"id": 29243, "token": "\u0120McL", "merges": "\u0120Mc L", "raw_count": 656, "count": 656, "decode_str": " McL"} -{"id": 12577, "token": "\\,\\", "merges": "\\ ,\\", "raw_count": 656, "count": 656, "decode_str": "\\,\\"} -{"id": 40623, "token": "\u0120hydrodynamic", "merges": "\u0120hydro dynamic", "raw_count": 657, "count": 657, "decode_str": " hydrodynamic"} -{"id": 47169, "token": "\u00e3\u0123\u00a6\u00e3\u0123\u0126\u00e3\u0123\u00be\u00e3\u0123\u013b", "merges": "\u00e3\u0123\u00a6\u00e3\u0123\u0126 \u00e3\u0123\u00be\u00e3\u0123\u013b", "raw_count": 657, "count": 657, "decode_str": "\u3066\u3044\u307e\u3059"} -{"id": 21519, "token": "\u0120Roosevelt", "merges": "\u0120Ro osevelt", "raw_count": 657, "count": 657, "decode_str": " Roosevelt"} -{"id": 31580, "token": "\u0120Walt", "merges": "\u0120W alt", "raw_count": 657, "count": 657, "decode_str": " Walt"} -{"id": 7182, "token": ")=\\", "merges": ") =\\", "raw_count": 657, "count": 657, "decode_str": ")=\\"} -{"id": 47050, "token": "\u0120Werner", "merges": "\u0120Wer ner", "raw_count": 658, "count": 658, "decode_str": " Werner"} -{"id": 36338, "token": "\u0120Drake", "merges": "\u0120Dra ke", "raw_count": 658, "count": 658, "decode_str": " Drake"} -{"id": 31293, "token": "\u0120Understanding", "merges": "\u0120Under standing", "raw_count": 659, "count": 659, "decode_str": " Understanding"} -{"id": 48845, "token": "\u0120libertarian", "merges": "\u0120libert arian", "raw_count": 659, "count": 659, "decode_str": " libertarian"} -{"id": 43359, "token": "\u0120covariant", "merges": "\u0120cov ariant", "raw_count": 659, "count": 659, "decode_str": " covariant"} -{"id": 20518, "token": "\u0120miRNA", "merges": "\u0120mi RNA", "raw_count": 659, "count": 659, "decode_str": " miRNA"} -{"id": 40905, "token": "\u0120Booth", "merges": "\u0120Bo oth", "raw_count": 659, "count": 659, "decode_str": " Booth"} -{"id": 36146, "token": "\u0120muito", "merges": "\u0120muit o", "raw_count": 659, "count": 659, "decode_str": " muito"} -{"id": 45843, "token": "\u0120$@", "merges": "\u0120$ @", "raw_count": 659, "count": 659, "decode_str": " $@"} -{"id": 32907, "token": "\u0120Investigation", "merges": "\u0120Invest igation", "raw_count": 660, "count": 660, "decode_str": " Investigation"} -{"id": 37804, "token": "\u0120pituitary", "merges": "\u0120pit uitary", "raw_count": 660, "count": 660, "decode_str": " pituitary"} -{"id": 32958, "token": "\u0120Carroll", "merges": "\u0120Car roll", "raw_count": 660, "count": 660, "decode_str": " Carroll"} -{"id": 39285, "token": "\u0120Thr", "merges": "\u0120Th r", "raw_count": 660, "count": 660, "decode_str": " Thr"} -{"id": 47187, "token": "\u0120willful", "merges": "\u0120will ful", "raw_count": 661, "count": 661, "decode_str": " willful"} -{"id": 15236, "token": "\u0120biomark", "merges": "\u0120biom ark", "raw_count": 4, "count": 662, "decode_str": " biomark"} -{"id": 41119, "token": "\u0120nitride", "merges": "\u0120nit ride", "raw_count": 662, "count": 662, "decode_str": " nitride"} -{"id": 22723, "token": "\u0120Sean", "merges": "\u0120Se an", "raw_count": 662, "count": 662, "decode_str": " Sean"} -{"id": 39133, "token": "_);", "merges": "_ );", "raw_count": 662, "count": 662, "decode_str": "_);"} -{"id": 35299, "token": "\u0120laparoscopic", "merges": "\u0120lapar oscopic", "raw_count": 663, "count": 663, "decode_str": " laparoscopic"} -{"id": 46068, "token": "SEQUENTIAL", "merges": "SEQU ENTIAL", "raw_count": 657, "count": 663, "decode_str": "SEQUENTIAL"} -{"id": 38202, "token": "\u0120reticul", "merges": "\u0120ret icul", "raw_count": 409, "count": 663, "decode_str": " reticul"} -{"id": 15732, "token": "\u0120Vietnam", "merges": "\u0120Viet nam", "raw_count": 663, "count": 663, "decode_str": " Vietnam"} -{"id": 48092, "token": "\u0120siempre", "merges": "\u0120si empre", "raw_count": 663, "count": 663, "decode_str": " siempre"} -{"id": 34597, "token": "\u0120raped", "merges": "\u0120ra ped", "raw_count": 663, "count": 663, "decode_str": " raped"} -{"id": 18654, "token": "\u0120auch", "merges": "\u0120a uch", "raw_count": 663, "count": 663, "decode_str": " auch"} -{"id": 21027, "token": "\u00ce\u00bd\u00ce\u00bf", "merges": "\u00ce\u00bd \u00ce\u00bf", "raw_count": 663, "count": 663, "decode_str": "\u03bd\u03bf"} -{"id": 48756, "token": "\u00e3\u0123\u0134", "merges": "\u00e3\u0123 \u0134", "raw_count": 663, "count": 663, "decode_str": "\u3052"} -{"id": 48603, "token": "culoskeletal", "merges": "culos keletal", "raw_count": 664, "count": 664, "decode_str": "culoskeletal"} -{"id": 11545, "token": "\u0120Illinois", "merges": "\u0120Ill inois", "raw_count": 664, "count": 664, "decode_str": " Illinois"} -{"id": 18618, "token": "\u0120Malays", "merges": "\u0120Mal ays", "raw_count": 13, "count": 664, "decode_str": " Malays"} -{"id": 44150, "token": "\u0120Rescue", "merges": "\u0120Res cue", "raw_count": 664, "count": 664, "decode_str": " Rescue"} -{"id": 41508, "token": "rogenic", "merges": "rogen ic", "raw_count": 664, "count": 664, "decode_str": "rogenic"} -{"id": 46574, "token": "\u0120Postal", "merges": "\u0120Post al", "raw_count": 664, "count": 664, "decode_str": " Postal"} -{"id": 43504, "token": "\u0120Ideas", "merges": "\u0120Ide as", "raw_count": 664, "count": 664, "decode_str": " Ideas"} -{"id": 45309, "token": "\u0120Ricci", "merges": "\u0120Ric ci", "raw_count": 664, "count": 664, "decode_str": " Ricci"} -{"id": 49368, "token": "\u0120Audi", "merges": "\u0120Aud i", "raw_count": 664, "count": 664, "decode_str": " Audi"} -{"id": 48535, "token": "\u0120Vall", "merges": "\u0120V all", "raw_count": 664, "count": 664, "decode_str": " Vall"} -{"id": 45432, "token": "\u0120goddamn", "merges": "\u0120god damn", "raw_count": 665, "count": 665, "decode_str": " goddamn"} -{"id": 48248, "token": "\u0120Edison", "merges": "\u0120Ed ison", "raw_count": 665, "count": 665, "decode_str": " Edison"} -{"id": 34599, "token": "\u0120Univ", "merges": "\u0120Un iv", "raw_count": 666, "count": 666, "decode_str": " Univ"} -{"id": 40098, "token": "\u0120Auf", "merges": "\u0120A uf", "raw_count": 666, "count": 666, "decode_str": " Auf"} -{"id": 46815, "token": "\u0120Sug", "merges": "\u0120S ug", "raw_count": 666, "count": 666, "decode_str": " Sug"} -{"id": 18945, "token": "\u0120LPS", "merges": "\u0120L PS", "raw_count": 666, "count": 666, "decode_str": " LPS"} -{"id": 17361, "token": "\u0120Sydney", "merges": "\u0120Syd ney", "raw_count": 667, "count": 667, "decode_str": " Sydney"} -{"id": 41004, "token": "\u0120PEOPLE", "merges": "\u0120PE OPLE", "raw_count": 667, "count": 667, "decode_str": " PEOPLE"} -{"id": 36496, "token": "\u0120IRA", "merges": "\u0120I RA", "raw_count": 667, "count": 667, "decode_str": " IRA"} -{"id": 34764, "token": "\\@", "merges": "\\ @", "raw_count": 667, "count": 667, "decode_str": "\\@"} -{"id": 26953, "token": "\u0120Tyler", "merges": "\u0120T yler", "raw_count": 668, "count": 668, "decode_str": " Tyler"} -{"id": 32354, "token": "\u0120Worth", "merges": "\u0120W orth", "raw_count": 668, "count": 668, "decode_str": " Worth"} -{"id": 41186, "token": "\u0120Eva", "merges": "\u0120Ev a", "raw_count": 668, "count": 668, "decode_str": " Eva"} -{"id": 16333, "token": "\u0120Netherlands", "merges": "\u0120Nether lands", "raw_count": 669, "count": 669, "decode_str": " Netherlands"} -{"id": 42661, "token": "\u0120detectives", "merges": "\u0120detect ives", "raw_count": 669, "count": 669, "decode_str": " detectives"} -{"id": 27051, "token": "\u0120Rodriguez", "merges": "\u0120Rodrig uez", "raw_count": 669, "count": 669, "decode_str": " Rodriguez"} -{"id": 34013, "token": "\u0120Acts", "merges": "\u0120Act s", "raw_count": 669, "count": 669, "decode_str": " Acts"} -{"id": 36894, "token": "\u00d7\u0137\u00d7\u00aa", "merges": "\u00d7\u0137\u00d7 \u00aa", "raw_count": 669, "count": 669, "decode_str": "\u05d5\u05ea"} -{"id": 33389, "token": "\u0120\u00d7\u0140", "merges": "\u0120\u00d7 \u0140", "raw_count": 669, "count": 669, "decode_str": " \u05de"} -{"id": 22385, "token": "\u0120quarterback", "merges": "\u0120quarter back", "raw_count": 670, "count": 670, "decode_str": " quarterback"} -{"id": 19425, "token": "\u0120Premier", "merges": "\u0120Prem ier", "raw_count": 670, "count": 670, "decode_str": " Premier"} -{"id": 48649, "token": "\u0120spiked", "merges": "\u0120sp iked", "raw_count": 670, "count": 670, "decode_str": " spiked"} -{"id": 41264, "token": "\u0120Hers", "merges": "\u0120H ers", "raw_count": 670, "count": 670, "decode_str": " Hers"} -{"id": 45377, "token": "\u0120Carey", "merges": "\u0120Care y", "raw_count": 671, "count": 671, "decode_str": " Carey"} -{"id": 33087, "token": "\u0120Conservation", "merges": "\u0120Conserv ation", "raw_count": 672, "count": 672, "decode_str": " Conservation"} -{"id": 23236, "token": "\u0120footballers", "merges": "\u0120football ers", "raw_count": 672, "count": 672, "decode_str": " footballers"} -{"id": 34324, "token": "\u0120positivity", "merges": "\u0120pos itivity", "raw_count": 672, "count": 672, "decode_str": " positivity"} -{"id": 44402, "token": "\u0120Julius", "merges": "\u0120Jul ius", "raw_count": 672, "count": 672, "decode_str": " Julius"} -{"id": 38725, "token": "\u0120ABA", "merges": "\u0120A BA", "raw_count": 672, "count": 672, "decode_str": " ABA"} -{"id": 46799, "token": "\u0120Hut", "merges": "\u0120H ut", "raw_count": 672, "count": 672, "decode_str": " Hut"} -{"id": 16732, "token": "\u0120Sanders", "merges": "\u0120Sand ers", "raw_count": 673, "count": 673, "decode_str": " Sanders"} -{"id": 44353, "token": "\u00d9\u012c\u00d8\u00b1", "merges": "\u00d9\u012c \u00d8\u00b1", "raw_count": 673, "count": 673, "decode_str": "\u064a\u0631"} -{"id": 42510, "token": "\u0120haplotypes", "merges": "\u0120hapl otypes", "raw_count": 674, "count": 674, "decode_str": " haplotypes"} -{"id": 32717, "token": "\u0120suggestive", "merges": "\u0120suggest ive", "raw_count": 674, "count": 674, "decode_str": " suggestive"} -{"id": 25391, "token": "iferase", "merges": "ifer ase", "raw_count": 660, "count": 674, "decode_str": "iferase"} -{"id": 36172, "token": "\u0120Felix", "merges": "\u0120Fel ix", "raw_count": 674, "count": 674, "decode_str": " Felix"} -{"id": 49552, "token": "\u0120Schwe", "merges": "\u0120Sch we", "raw_count": 674, "count": 674, "decode_str": " Schwe"} -{"id": 24010, "token": "\u0120Todd", "merges": "\u0120T odd", "raw_count": 674, "count": 674, "decode_str": " Todd"} -{"id": 40915, "token": "\u0120Tue", "merges": "\u0120T ue", "raw_count": 674, "count": 674, "decode_str": " Tue"} -{"id": 45173, "token": "\u0120Eck", "merges": "\u0120E ck", "raw_count": 674, "count": 674, "decode_str": " Eck"} -{"id": 48381, "token": "\u0120dermal", "merges": "\u0120d ermal", "raw_count": 675, "count": 675, "decode_str": " dermal"} -{"id": 41979, "token": "\u0120Pok\u00c3\u00a9mon", "merges": "\u0120Pok \u00c3\u00a9mon", "raw_count": 676, "count": 676, "decode_str": " Pok\u00e9mon"} -{"id": 38036, "token": "\u0120Fuj", "merges": "\u0120F uj", "raw_count": 676, "count": 676, "decode_str": " Fuj"} -{"id": 14620, "token": "\u0120\u00ce\u00bcm", "merges": "\u0120\u00ce\u00bc m", "raw_count": 676, "count": 676, "decode_str": " \u03bcm"} -{"id": 37167, "token": "\u0120\u00d7\u0133", "merges": "\u0120\u00d7 \u0133", "raw_count": 676, "count": 676, "decode_str": " \u05d1"} -{"id": 35972, "token": "\u0120Sebastian", "merges": "\u0120Sebast ian", "raw_count": 677, "count": 677, "decode_str": " Sebastian"} -{"id": 36943, "token": "\u0120Territory", "merges": "\u0120Ter ritory", "raw_count": 677, "count": 677, "decode_str": " Territory"} -{"id": 11314, "token": "\u0120Michigan", "merges": "\u0120Mich igan", "raw_count": 677, "count": 677, "decode_str": " Michigan"} -{"id": 39261, "token": "\u0120epiderm", "merges": "\u0120epid erm", "raw_count": 144, "count": 677, "decode_str": " epiderm"} -{"id": 14067, "token": "Despite", "merges": "Des pite", "raw_count": 677, "count": 677, "decode_str": "Despite"} -{"id": 45326, "token": "\u0120Annex", "merges": "\u0120An nex", "raw_count": 677, "count": 677, "decode_str": " Annex"} -{"id": 32369, "token": "\u0120lumen", "merges": "\u0120lum en", "raw_count": 677, "count": 677, "decode_str": " lumen"} -{"id": 47249, "token": "\u0120Feld", "merges": "\u0120F eld", "raw_count": 677, "count": 677, "decode_str": " Feld"} -{"id": 36212, "token": "\u00c3\u00a4ng", "merges": "\u00c3\u00a4 ng", "raw_count": 677, "count": 677, "decode_str": "\u00e4ng"} -{"id": 54607, "token": "\u00ef\u00bc\u012c", "merges": "\u00ef\u00bc \u012c", "raw_count": 677, "count": 677, "decode_str": "\uff0a"} -{"id": 34004, "token": "^**", "merges": "^ **", "raw_count": 677, "count": 677, "decode_str": "^**"} -{"id": 15458, "token": "\u0120Sarah", "merges": "\u0120Sar ah", "raw_count": 678, "count": 678, "decode_str": " Sarah"} -{"id": 48360, "token": "\u0120eines", "merges": "\u0120e ines", "raw_count": 678, "count": 678, "decode_str": " eines"} -{"id": 33117, "token": "\u0120deze", "merges": "\u0120de ze", "raw_count": 678, "count": 678, "decode_str": " deze"} -{"id": 37404, "token": "\u0120GTP", "merges": "\u0120G TP", "raw_count": 678, "count": 678, "decode_str": " GTP"} -{"id": 43379, "token": "\u0120autres", "merges": "\u0120aut res", "raw_count": 679, "count": 679, "decode_str": " autres"} -{"id": 35675, "token": "\u0120peric", "merges": "\u0120per ic", "raw_count": 679, "count": 679, "decode_str": " peric"} -{"id": 38921, "token": "\u0120cref", "merges": "\u0120c ref", "raw_count": 679, "count": 679, "decode_str": " cref"} -{"id": 20469, "token": "\u0120Dak", "merges": "\u0120D ak", "raw_count": 153, "count": 679, "decode_str": " Dak"} -{"id": 15848, "token": "\u0120cytoplasm", "merges": "\u0120cyt oplasm", "raw_count": 481, "count": 680, "decode_str": " cytoplasm"} -{"id": 24336, "token": "\u0120Marcus", "merges": "\u0120Mar cus", "raw_count": 680, "count": 680, "decode_str": " Marcus"} -{"id": 20572, "token": "\u00c5\u00a5", "merges": "\u00c5 \u00a5", "raw_count": 680, "count": 680, "decode_str": "\u0165"} -{"id": 41867, "token": "\u0120Kaiser", "merges": "\u0120K aiser", "raw_count": 681, "count": 681, "decode_str": " Kaiser"} -{"id": 21924, "token": "\u0120Madrid", "merges": "\u0120Mad rid", "raw_count": 681, "count": 681, "decode_str": " Madrid"} -{"id": 48065, "token": "\u0120favoring", "merges": "\u0120favor ing", "raw_count": 682, "count": 682, "decode_str": " favoring"} -{"id": 27504, "token": "\u0120Sandy", "merges": "\u0120Sand y", "raw_count": 682, "count": 682, "decode_str": " Sandy"} -{"id": 39659, "token": "\u0120endl", "merges": "\u0120end l", "raw_count": 682, "count": 682, "decode_str": " endl"} -{"id": 8809, "token": "amss", "merges": "am ss", "raw_count": 606, "count": 682, "decode_str": "amss"} -{"id": 43404, "token": "\u0120Assistance", "merges": "\u0120Ass istance", "raw_count": 683, "count": 683, "decode_str": " Assistance"} -{"id": 44583, "token": "\u0120depuis", "merges": "\u0120dep uis", "raw_count": 683, "count": 683, "decode_str": " depuis"} -{"id": 33414, "token": "\u0120Pedro", "merges": "\u0120Ped ro", "raw_count": 683, "count": 683, "decode_str": " Pedro"} -{"id": 43061, "token": "\"});", "merges": "\"} );", "raw_count": 683, "count": 683, "decode_str": "\"});"} -{"id": 39457, "token": "\u0120Barrett", "merges": "\u0120Bar rett", "raw_count": 684, "count": 684, "decode_str": " Barrett"} -{"id": 48802, "token": "\u0120Archer", "merges": "\u0120Ar cher", "raw_count": 684, "count": 684, "decode_str": " Archer"} -{"id": 43700, "token": "\u0120etched", "merges": "\u0120et ched", "raw_count": 684, "count": 684, "decode_str": " etched"} -{"id": 38293, "token": "oclast", "merges": "oc last", "raw_count": 621, "count": 684, "decode_str": "oclast"} -{"id": 45926, "token": "\u00c3\u00aam", "merges": "\u00c3\u00aa m", "raw_count": 684, "count": 684, "decode_str": "\u00eam"} -{"id": 40797, "token": "\u0120apr\u00c3\u00a8s", "merges": "\u0120ap r\u00c3\u00a8s", "raw_count": 685, "count": 685, "decode_str": " apr\u00e8s"} -{"id": 32574, "token": "\u0120Burns", "merges": "\u0120B urns", "raw_count": 685, "count": 685, "decode_str": " Burns"} -{"id": 44390, "token": "\u0120Hawk", "merges": "\u0120Haw k", "raw_count": 685, "count": 685, "decode_str": " Hawk"} -{"id": 40300, "token": "\u0120Ital", "merges": "\u0120It al", "raw_count": 685, "count": 685, "decode_str": " Ital"} -{"id": 44816, "token": "\u0120Pon", "merges": "\u0120P on", "raw_count": 685, "count": 685, "decode_str": " Pon"} -{"id": 43920, "token": "\u0120Chr", "merges": "\u0120Ch r", "raw_count": 685, "count": 685, "decode_str": " Chr"} -{"id": 11637, "token": "\u0120Pennsylvania", "merges": "\u0120Pen nsylvania", "raw_count": 686, "count": 686, "decode_str": " Pennsylvania"} -{"id": 33502, "token": "\u0120conjugated", "merges": "\u0120conjug ated", "raw_count": 686, "count": 686, "decode_str": " conjugated"} -{"id": 37108, "token": "\u0120Chapman", "merges": "\u0120Chap man", "raw_count": 687, "count": 687, "decode_str": " Chapman"} -{"id": 40445, "token": "\u0120Typical", "merges": "\u0120Typ ical", "raw_count": 687, "count": 687, "decode_str": " Typical"} -{"id": 39223, "token": "\u0120tackles", "merges": "\u0120tack les", "raw_count": 687, "count": 687, "decode_str": " tackles"} -{"id": 33903, "token": "\u0120adrenal", "merges": "\u0120adren al", "raw_count": 687, "count": 687, "decode_str": " adrenal"} -{"id": 32648, "token": "\u0120Treaty", "merges": "\u0120Treat y", "raw_count": 687, "count": 687, "decode_str": " Treaty"} -{"id": 33407, "token": "\u0120Dylan", "merges": "\u0120D ylan", "raw_count": 687, "count": 687, "decode_str": " Dylan"} -{"id": 48398, "token": "\u0120Kad", "merges": "\u0120K ad", "raw_count": 687, "count": 687, "decode_str": " Kad"} -{"id": 27743, "token": "\u0120polype", "merges": "\u0120pol ype", "raw_count": 187, "count": 688, "decode_str": " polype"} -{"id": 44363, "token": "\u0120Wings", "merges": "\u0120W ings", "raw_count": 688, "count": 688, "decode_str": " Wings"} -{"id": 15234, "token": "\u00cf\u012b\u00ce\u00bd", "merges": "\u00cf\u012b \u00ce\u00bd", "raw_count": 579, "count": 688, "decode_str": "\u03c9\u03bd"} -{"id": 28544, "token": "\u00c3\u00b6s", "merges": "\u00c3\u00b6 s", "raw_count": 652, "count": 688, "decode_str": "\u00f6s"} -{"id": 50382, "token": "\u00e2\u013b\u00a1", "merges": "\u00e2\u013b \u00a1", "raw_count": 688, "count": 688, "decode_str": "\u2661"} -{"id": 36949, "token": "\u0120_\"", "merges": "\u0120_ \"", "raw_count": 688, "count": 688, "decode_str": " _\""} -{"id": 42597, "token": "\u0120Fraser", "merges": "\u0120Fr aser", "raw_count": 689, "count": 689, "decode_str": " Fraser"} -{"id": 44289, "token": "opolys", "merges": "opol ys", "raw_count": 689, "count": 689, "decode_str": "opolys"} -{"id": 45693, "token": "\u00d8\u00b8", "merges": "\u00d8 \u00b8", "raw_count": 689, "count": 689, "decode_str": "\u0638"} -{"id": 27975, "token": "\u0120remodeling", "merges": "\u0120remod eling", "raw_count": 690, "count": 690, "decode_str": " remodeling"} -{"id": 34818, "token": "\u0120serotonin", "merges": "\u0120seroton in", "raw_count": 690, "count": 690, "decode_str": " serotonin"} -{"id": 20782, "token": "---|---", "merges": "---| ---", "raw_count": 296, "count": 690, "decode_str": "---|---"} -{"id": 5143, "token": "\u0120Israel", "merges": "\u0120Is rael", "raw_count": 612, "count": 690, "decode_str": " Israel"} -{"id": 33301, "token": "--**", "merges": "-- **", "raw_count": 658, "count": 690, "decode_str": "--**"} -{"id": 45812, "token": "\u0120Cic", "merges": "\u0120C ic", "raw_count": 690, "count": 690, "decode_str": " Cic"} -{"id": 33514, "token": "\u0120Gur", "merges": "\u0120G ur", "raw_count": 690, "count": 690, "decode_str": " Gur"} -{"id": 49272, "token": "\u0120Cellular", "merges": "\u0120C ellular", "raw_count": 691, "count": 691, "decode_str": " Cellular"} -{"id": 26876, "token": "\u0120Nicholas", "merges": "\u0120Nich olas", "raw_count": 691, "count": 691, "decode_str": " Nicholas"} -{"id": 38918, "token": "\u0120Wheeler", "merges": "\u0120Whe eler", "raw_count": 691, "count": 691, "decode_str": " Wheeler"} -{"id": 40912, "token": "\u00e0\u00a7\u0129", "merges": "\u00e0\u00a7 \u0129", "raw_count": 691, "count": 691, "decode_str": "\u09c7"} -{"id": 44342, "token": "\u0120", "merges": "=\"# \">", "raw_count": 752, "count": 752, "decode_str": "=\"#\">"} -{"id": 41853, "token": "\u0120Immediately", "merges": "\u0120Im mediately", "raw_count": 753, "count": 753, "decode_str": " Immediately"} -{"id": 46312, "token": "\u0120Nicolas", "merges": "\u0120Nic olas", "raw_count": 753, "count": 753, "decode_str": " Nicolas"} -{"id": 13227, "token": "\u0120mitochondrial", "merges": "\u0120mitochond rial", "raw_count": 754, "count": 754, "decode_str": " mitochondrial"} -{"id": 48341, "token": "\u0120immunized", "merges": "\u0120immun ized", "raw_count": 754, "count": 754, "decode_str": " immunized"} -{"id": 32211, "token": "\u0120Kurt", "merges": "\u0120K urt", "raw_count": 754, "count": 754, "decode_str": " Kurt"} -{"id": 39407, "token": "\u0120Wid", "merges": "\u0120W id", "raw_count": 754, "count": 754, "decode_str": " Wid"} -{"id": 39319, "token": "\u0120Ara", "merges": "\u0120A ra", "raw_count": 754, "count": 754, "decode_str": " Ara"} -{"id": 27439, "token": "\u0120granul", "merges": "\u0120gran ul", "raw_count": 755, "count": 755, "decode_str": " granul"} -{"id": 35129, "token": "\u0120essere", "merges": "\u0120esse re", "raw_count": 755, "count": 755, "decode_str": " essere"} -{"id": 26378, "token": "\u0120Ralph", "merges": "\u0120R alph", "raw_count": 755, "count": 755, "decode_str": " Ralph"} -{"id": 45498, "token": "\u0120dext", "merges": "\u0120de xt", "raw_count": 755, "count": 755, "decode_str": " dext"} -{"id": 43963, "token": "Disclaimer", "merges": "Dis claimer", "raw_count": 756, "count": 756, "decode_str": "Disclaimer"} -{"id": 49994, "token": "\u0120growled", "merges": "\u0120grow led", "raw_count": 756, "count": 756, "decode_str": " growled"} -{"id": 47363, "token": "\u0120keine", "merges": "\u0120ke ine", "raw_count": 756, "count": 756, "decode_str": " keine"} -{"id": 19466, "token": "\u0120Bowl", "merges": "\u0120Bow l", "raw_count": 756, "count": 756, "decode_str": " Bowl"} -{"id": 34997, "token": "\u0120skal", "merges": "\u0120sk al", "raw_count": 756, "count": 756, "decode_str": " skal"} -{"id": 17415, "token": "\u0120recombinant", "merges": "\u0120recom binant", "raw_count": 757, "count": 757, "decode_str": " recombinant"} -{"id": 20009, "token": "\u0120putative", "merges": "\u0120put ative", "raw_count": 757, "count": 757, "decode_str": " putative"} -{"id": 11918, "token": "\u0120Captain", "merges": "\u0120Capt ain", "raw_count": 757, "count": 757, "decode_str": " Captain"} -{"id": 26686, "token": "\u0120Kant", "merges": "\u0120K ant", "raw_count": 757, "count": 757, "decode_str": " Kant"} -{"id": 43918, "token": "\u0120fMRI", "merges": "\u0120f MRI", "raw_count": 757, "count": 757, "decode_str": " fMRI"} -{"id": 39174, "token": "\u0120suspensions", "merges": "\u0120susp ensions", "raw_count": 758, "count": 758, "decode_str": " suspensions"} -{"id": 37629, "token": "\u0120Traditional", "merges": "\u0120Tr aditional", "raw_count": 758, "count": 758, "decode_str": " Traditional"} -{"id": 34136, "token": "\u0120Advisory", "merges": "\u0120Ad visory", "raw_count": 758, "count": 758, "decode_str": " Advisory"} -{"id": 38315, "token": "\u0120Aviation", "merges": "\u0120Av iation", "raw_count": 758, "count": 758, "decode_str": " Aviation"} -{"id": 29947, "token": "tochrome", "merges": "to chrome", "raw_count": 580, "count": 758, "decode_str": "tochrome"} -{"id": 34909, "token": "\u0120Norton", "merges": "\u0120Nort on", "raw_count": 758, "count": 758, "decode_str": " Norton"} -{"id": 45998, "token": "\u0120Hog", "merges": "\u0120H og", "raw_count": 758, "count": 758, "decode_str": " Hog"} -{"id": 32524, "token": "\u0120Roh", "merges": "\u0120R oh", "raw_count": 758, "count": 758, "decode_str": " Roh"} -{"id": 50137, "token": "\u0120linearity", "merges": "\u0120linear ity", "raw_count": 759, "count": 759, "decode_str": " linearity"} -{"id": 12090, "token": "\u0120Several", "merges": "\u0120S everal", "raw_count": 759, "count": 759, "decode_str": " Several"} -{"id": 20703, "token": "osexual", "merges": "osex ual", "raw_count": 473, "count": 759, "decode_str": "osexual"} -{"id": 48732, "token": "\u0120galact", "merges": "\u0120gal act", "raw_count": 759, "count": 759, "decode_str": " galact"} -{"id": 47785, "token": "ophores", "merges": "op hores", "raw_count": 759, "count": 759, "decode_str": "ophores"} -{"id": 32005, "token": "\u0120Fear", "merges": "\u0120F ear", "raw_count": 759, "count": 759, "decode_str": " Fear"} -{"id": 36244, "token": "\u0120Prix", "merges": "\u0120P rix", "raw_count": 759, "count": 759, "decode_str": " Prix"} -{"id": 28252, "token": "\u0120\u00c5\u00bc", "merges": "\u0120\u00c5 \u00bc", "raw_count": 435, "count": 759, "decode_str": " \u017c"} -{"id": 36740, "token": "\u0120Democracy", "merges": "\u0120Democr acy", "raw_count": 760, "count": 760, "decode_str": " Democracy"} -{"id": 45149, "token": "\u0120resonator", "merges": "\u0120reson ator", "raw_count": 760, "count": 760, "decode_str": " resonator"} -{"id": 34147, "token": "\u0120Dies", "merges": "\u0120D ies", "raw_count": 760, "count": 760, "decode_str": " Dies"} -{"id": 35110, "token": "\u0120Certain", "merges": "\u0120C ertain", "raw_count": 761, "count": 761, "decode_str": " Certain"} -{"id": 46474, "token": "\u0120NAC", "merges": "\u0120N AC", "raw_count": 761, "count": 761, "decode_str": " NAC"} -{"id": 34254, "token": "\u0120neurotrans", "merges": "\u0120neuro trans", "raw_count": 762, "count": 762, "decode_str": " neurotrans"} -{"id": 32831, "token": "\u0120Defence", "merges": "\u0120Def ence", "raw_count": 762, "count": 762, "decode_str": " Defence"} -{"id": 21482, "token": "\u0120Ethics", "merges": "\u0120Eth ics", "raw_count": 762, "count": 762, "decode_str": " Ethics"} -{"id": 43253, "token": "\u0120lobes", "merges": "\u0120lob es", "raw_count": 762, "count": 762, "decode_str": " lobes"} -{"id": 42224, "token": "\u0120Beau", "merges": "\u0120Be au", "raw_count": 762, "count": 762, "decode_str": " Beau"} -{"id": 50398, "token": "\u00e3\u0122\u0139", "merges": "\u00e3\u0122 \u0139", "raw_count": 762, "count": 762, "decode_str": "\u3017"} -{"id": 45436, "token": "\u0120filmmaker", "merges": "\u0120filmm aker", "raw_count": 763, "count": 763, "decode_str": " filmmaker"} -{"id": 37047, "token": "\u0120Scholars", "merges": "\u0120Sch olars", "raw_count": 763, "count": 763, "decode_str": " Scholars"} -{"id": 47313, "token": "\u0120Conway", "merges": "\u0120Con way", "raw_count": 763, "count": 763, "decode_str": " Conway"} -{"id": 41446, "token": "Syscall", "merges": "S yscall", "raw_count": 763, "count": 763, "decode_str": "Syscall"} -{"id": 44345, "token": "\u0120ahora", "merges": "\u0120a hora", "raw_count": 763, "count": 763, "decode_str": " ahora"} -{"id": 39749, "token": "\u0120Athletic", "merges": "\u0120Athlet ic", "raw_count": 764, "count": 764, "decode_str": " Athletic"} -{"id": 41370, "token": "Footnote", "merges": "Foot note", "raw_count": 764, "count": 764, "decode_str": "Footnote"} -{"id": 36063, "token": "\u0120Jacques", "merges": "\u0120Jac ques", "raw_count": 764, "count": 764, "decode_str": " Jacques"} -{"id": 35503, "token": "\u0120Rosa", "merges": "\u0120R osa", "raw_count": 764, "count": 764, "decode_str": " Rosa"} -{"id": 50397, "token": "\u00e3\u0122\u0138", "merges": "\u00e3\u0122 \u0138", "raw_count": 764, "count": 764, "decode_str": "\u3016"} -{"id": 41338, "token": "z\u00c4\u0127", "merges": "z \u00c4\u0127", "raw_count": 765, "count": 765, "decode_str": "z\u0105"} -{"id": 39406, "token": "\u0120equivalently", "merges": "\u0120equival ently", "raw_count": 766, "count": 766, "decode_str": " equivalently"} -{"id": 49589, "token": "\u0120Turning", "merges": "\u0120Turn ing", "raw_count": 766, "count": 766, "decode_str": " Turning"} -{"id": 47492, "token": "\u0120Innov", "merges": "\u0120Inn ov", "raw_count": 766, "count": 766, "decode_str": " Innov"} -{"id": 15902, "token": "\u0120\u00ce\u00bd", "merges": "\u0120\u00ce \u00bd", "raw_count": 378, "count": 766, "decode_str": " \u03bd"} -{"id": 24389, "token": "\u0120hybridization", "merges": "\u0120hybrid ization", "raw_count": 767, "count": 767, "decode_str": " hybridization"} -{"id": 18850, "token": "\u0120tablespoons", "merges": "\u0120tables poons", "raw_count": 767, "count": 767, "decode_str": " tablespoons"} -{"id": 47273, "token": "\u0120propriety", "merges": "\u0120propri ety", "raw_count": 767, "count": 767, "decode_str": " propriety"} -{"id": 26853, "token": "\u0120Bennett", "merges": "\u0120Benn ett", "raw_count": 767, "count": 767, "decode_str": " Bennett"} -{"id": 34167, "token": "\u0120Weiss", "merges": "\u0120We iss", "raw_count": 767, "count": 767, "decode_str": " Weiss"} -{"id": 9831, "token": "\u0120mM", "merges": "\u0120m M", "raw_count": 767, "count": 767, "decode_str": " mM"} -{"id": 48837, "token": "\u0120Spearman", "merges": "\u0120Spe arman", "raw_count": 768, "count": 768, "decode_str": " Spearman"} -{"id": 18457, "token": "\u0120Indones", "merges": "\u0120Ind ones", "raw_count": 3, "count": 768, "decode_str": " Indones"} -{"id": 41327, "token": "\u0120Poinc", "merges": "\u0120Po inc", "raw_count": 691, "count": 768, "decode_str": " Poinc"} -{"id": 47445, "token": "\u0120Welch", "merges": "\u0120Wel ch", "raw_count": 768, "count": 768, "decode_str": " Welch"} -{"id": 15473, "token": "\u0120IgG", "merges": "\u0120Ig G", "raw_count": 768, "count": 768, "decode_str": " IgG"} -{"id": 49577, "token": "\u0120Hmm", "merges": "\u0120H mm", "raw_count": 768, "count": 768, "decode_str": " Hmm"} -{"id": 48214, "token": "\u00c3\u00a9v", "merges": "\u00c3\u00a9 v", "raw_count": 768, "count": 768, "decode_str": "\u00e9v"} -{"id": 28421, "token": "\u0120dehydrogenase", "merges": "\u0120dehydrogen ase", "raw_count": 769, "count": 769, "decode_str": " dehydrogenase"} -{"id": 46266, "token": "Salmonella", "merges": "Sal monella", "raw_count": 769, "count": 769, "decode_str": "Salmonella"} -{"id": 42778, "token": "\u0120Penny", "merges": "\u0120P enny", "raw_count": 769, "count": 769, "decode_str": " Penny"} -{"id": 30835, "token": "\u0120Appl", "merges": "\u0120App l", "raw_count": 769, "count": 769, "decode_str": " Appl"} -{"id": 43006, "token": "\u0120Excellence", "merges": "\u0120Excell ence", "raw_count": 770, "count": 770, "decode_str": " Excellence"} -{"id": 38813, "token": "\u0120aneurysm", "merges": "\u0120aneurys m", "raw_count": 770, "count": 770, "decode_str": " aneurysm"} -{"id": 7670, "token": "\u0120Jesus", "merges": "\u0120Jes us", "raw_count": 770, "count": 770, "decode_str": " Jesus"} -{"id": 34806, "token": "\u0120Elder", "merges": "\u0120Eld er", "raw_count": 772, "count": 772, "decode_str": " Elder"} -{"id": 47489, "token": "\u0120mucus", "merges": "\u0120muc us", "raw_count": 772, "count": 772, "decode_str": " mucus"} -{"id": 38397, "token": "\u0120Schwarz", "merges": "\u0120Sch warz", "raw_count": 773, "count": 773, "decode_str": " Schwarz"} -{"id": 37476, "token": "butyl", "merges": "but yl", "raw_count": 773, "count": 773, "decode_str": "butyl"} -{"id": 31461, "token": "\u0120\u00d9\u0127\u00d9\u0128", "merges": "\u0120\u00d9\u0127 \u00d9\u0128", "raw_count": 773, "count": 773, "decode_str": " \u0645\u0646"} -{"id": 27614, "token": "\u0120Rah", "merges": "\u0120R ah", "raw_count": 773, "count": 773, "decode_str": " Rah"} -{"id": 21161, "token": "})^", "merges": "}) ^", "raw_count": 773, "count": 773, "decode_str": "})^"} -{"id": 29271, "token": "\u0120Harold", "merges": "\u0120Har old", "raw_count": 774, "count": 774, "decode_str": " Harold"} -{"id": 28712, "token": "\u0120Marco", "merges": "\u0120Mar co", "raw_count": 774, "count": 774, "decode_str": " Marco"} -{"id": 40266, "token": "\u0120Infl", "merges": "\u0120In fl", "raw_count": 774, "count": 774, "decode_str": " Infl"} -{"id": 29241, "token": "\u0120Duc", "merges": "\u0120D uc", "raw_count": 629, "count": 774, "decode_str": " Duc"} -{"id": 35605, "token": "\u0120biologically", "merges": "\u0120bi ologically", "raw_count": 775, "count": 775, "decode_str": " biologically"} -{"id": 32271, "token": "\u0120Whenever", "merges": "\u0120Whe never", "raw_count": 775, "count": 775, "decode_str": " Whenever"} -{"id": 36071, "token": "emente", "merges": "ement e", "raw_count": 775, "count": 775, "decode_str": "emente"} -{"id": 41467, "token": "\u0120Basin", "merges": "\u0120Bas in", "raw_count": 775, "count": 775, "decode_str": " Basin"} -{"id": 22143, "token": "\u00e0\u00a4\u0124", "merges": "\u00e0\u00a4 \u0124", "raw_count": 775, "count": 775, "decode_str": "\u0902"} -{"id": 26002, "token": "\u0120Costa", "merges": "\u0120Cost a", "raw_count": 776, "count": 776, "decode_str": " Costa"} -{"id": 47353, "token": "\u0120grafting", "merges": "\u0120graft ing", "raw_count": 777, "count": 777, "decode_str": " grafting"} -{"id": 40566, "token": "\u0120Kab", "merges": "\u0120K ab", "raw_count": 777, "count": 777, "decode_str": " Kab"} -{"id": 43845, "token": "\u00d7\u00a4", "merges": "\u00d7 \u00a4", "raw_count": 777, "count": 777, "decode_str": "\u05e4"} -{"id": 46687, "token": "insects", "merges": "in sects", "raw_count": 778, "count": 778, "decode_str": "insects"} -{"id": 25158, "token": "\u0120fungal", "merges": "\u0120fun gal", "raw_count": 778, "count": 778, "decode_str": " fungal"} -{"id": 24940, "token": "\u0120Roche", "merges": "\u0120R oche", "raw_count": 582, "count": 778, "decode_str": " Roche"} -{"id": 30904, "token": "\u0120Thorn", "merges": "\u0120Th orn", "raw_count": 445, "count": 778, "decode_str": " Thorn"} -{"id": 29884, "token": "\u0120Theod", "merges": "\u0120The od", "raw_count": 409, "count": 778, "decode_str": " Theod"} -{"id": 40765, "token": "\u0120anion", "merges": "\u0120an ion", "raw_count": 778, "count": 778, "decode_str": " anion"} -{"id": 16739, "token": "\u0120Syd", "merges": "\u0120Sy d", "raw_count": 111, "count": 778, "decode_str": " Syd"} -{"id": 18453, "token": "\u00c3\u00a4m", "merges": "\u00c3\u00a4 m", "raw_count": 650, "count": 778, "decode_str": "\u00e4m"} -{"id": 43480, "token": "\u00c5\u012a", "merges": "\u00c5 \u012a", "raw_count": 778, "count": 778, "decode_str": "\u0148"} -{"id": 19990, "token": "\u0120fibrosis", "merges": "\u0120fib rosis", "raw_count": 779, "count": 779, "decode_str": " fibrosis"} -{"id": 43048, "token": "\u0120Teachers", "merges": "\u0120Te achers", "raw_count": 779, "count": 779, "decode_str": " Teachers"} -{"id": 44608, "token": "\u0120ortholog", "merges": "\u0120orth olog", "raw_count": 779, "count": 779, "decode_str": " ortholog"} -{"id": 33589, "token": "\u0120Centers", "merges": "\u0120Cent ers", "raw_count": 779, "count": 779, "decode_str": " Centers"} -{"id": 31692, "token": "\u0120Summit", "merges": "\u0120Sum mit", "raw_count": 779, "count": 779, "decode_str": " Summit"} -{"id": 40059, "token": "\u0120Santos", "merges": "\u0120Sant os", "raw_count": 779, "count": 779, "decode_str": " Santos"} -{"id": 23259, "token": "\u0120Ian", "merges": "\u0120I an", "raw_count": 779, "count": 779, "decode_str": " Ian"} -{"id": 22443, "token": "\u0120touchdown", "merges": "\u0120touch down", "raw_count": 571, "count": 780, "decode_str": " touchdown"} -{"id": 37770, "token": "\u0120Graduate", "merges": "\u0120Grad uate", "raw_count": 780, "count": 780, "decode_str": " Graduate"} -{"id": 48678, "token": "\u0120Believe", "merges": "\u0120Bel ieve", "raw_count": 780, "count": 780, "decode_str": " Believe"} -{"id": 21265, "token": "\u0120Alber", "merges": "\u0120Al ber", "raw_count": 578, "count": 780, "decode_str": " Alber"} -{"id": 40456, "token": "\u0120Strategic", "merges": "\u0120Strateg ic", "raw_count": 781, "count": 781, "decode_str": " Strategic"} -{"id": 31368, "token": "\u0120filaments", "merges": "\u0120fil aments", "raw_count": 781, "count": 781, "decode_str": " filaments"} -{"id": 39219, "token": "\u0120Healthy", "merges": "\u0120Health y", "raw_count": 781, "count": 781, "decode_str": " Healthy"} -{"id": 49890, "token": "\u0120Lange", "merges": "\u0120L ange", "raw_count": 781, "count": 781, "decode_str": " Lange"} -{"id": 32706, "token": "\u0120Sah", "merges": "\u0120S ah", "raw_count": 781, "count": 781, "decode_str": " Sah"} -{"id": 29936, "token": "\u0120Raymond", "merges": "\u0120Ray mond", "raw_count": 782, "count": 782, "decode_str": " Raymond"} -{"id": 47087, "token": "\u0120guitars", "merges": "\u0120gu itars", "raw_count": 782, "count": 782, "decode_str": " guitars"} -{"id": 18949, "token": "\u0120zijn", "merges": "\u0120z ijn", "raw_count": 782, "count": 782, "decode_str": " zijn"} -{"id": 26153, "token": "\u0120Abb", "merges": "\u0120Ab b", "raw_count": 375, "count": 782, "decode_str": " Abb"} -{"id": 16482, "token": "\u00e1\u00bf", "merges": "\u00e1 \u00bf", "raw_count": 438, "count": 782, "decode_str": "\ufffd"} -{"id": 23451, "token": "\u0120tablespoon", "merges": "\u0120tables poon", "raw_count": 783, "count": 783, "decode_str": " tablespoon"} -{"id": 22618, "token": "\u0120Phillips", "merges": "\u0120Phill ips", "raw_count": 783, "count": 783, "decode_str": " Phillips"} -{"id": 28373, "token": "\u0120Bald", "merges": "\u0120B ald", "raw_count": 317, "count": 783, "decode_str": " Bald"} -{"id": 33050, "token": "\u0120Till", "merges": "\u0120T ill", "raw_count": 783, "count": 783, "decode_str": " Till"} -{"id": 37057, "token": "\u0120foci", "merges": "\u0120f oci", "raw_count": 783, "count": 783, "decode_str": " foci"} -{"id": 5789, "token": ")/(-", "merges": ")/ (-", "raw_count": 783, "count": 783, "decode_str": ")/(-"} -{"id": 38567, "token": "\u0120Publications", "merges": "\u0120Public ations", "raw_count": 784, "count": 784, "decode_str": " Publications"} -{"id": 27147, "token": "\u0120Healthcare", "merges": "\u0120Health care", "raw_count": 784, "count": 784, "decode_str": " Healthcare"} -{"id": 46303, "token": "\u0120lymphatic", "merges": "\u0120lymph atic", "raw_count": 784, "count": 784, "decode_str": " lymphatic"} -{"id": 38799, "token": "\u0120Relief", "merges": "\u0120Rel ief", "raw_count": 784, "count": 784, "decode_str": " Relief"} -{"id": 17729, "token": "\u0120Corps", "merges": "\u0120Cor ps", "raw_count": 784, "count": 784, "decode_str": " Corps"} -{"id": 5095, "token": "\u0120\\,", "merges": "\u0120\\ ,", "raw_count": 784, "count": 784, "decode_str": " \\,"} -{"id": 46437, "token": "\u0120Opportunity", "merges": "\u0120Opp ortunity", "raw_count": 785, "count": 785, "decode_str": " Opportunity"} -{"id": 16200, "token": "\u0120metastasis", "merges": "\u0120metast asis", "raw_count": 785, "count": 785, "decode_str": " metastasis"} -{"id": 41755, "token": "\u0120migraine", "merges": "\u0120mig raine", "raw_count": 785, "count": 785, "decode_str": " migraine"} -{"id": 36656, "token": "\u0120MVC", "merges": "\u0120M VC", "raw_count": 785, "count": 785, "decode_str": " MVC"} -{"id": 43105, "token": "\u0120Wet", "merges": "\u0120W et", "raw_count": 785, "count": 785, "decode_str": " Wet"} -{"id": 41855, "token": "\u00d7\u00a7", "merges": "\u00d7 \u00a7", "raw_count": 785, "count": 785, "decode_str": "\u05e7"} -{"id": 40183, "token": "\u0120abscess", "merges": "\u0120abs cess", "raw_count": 786, "count": 786, "decode_str": " abscess"} -{"id": 34517, "token": "\u0120durante", "merges": "\u0120dur ante", "raw_count": 786, "count": 786, "decode_str": " durante"} -{"id": 33718, "token": "\u0120Burton", "merges": "\u0120Bur ton", "raw_count": 786, "count": 786, "decode_str": " Burton"} -{"id": 6729, "token": "\u0120Obama", "merges": "\u0120Ob ama", "raw_count": 786, "count": 786, "decode_str": " Obama"} -{"id": 46530, "token": "\u0120Zhao", "merges": "\u0120Z hao", "raw_count": 786, "count": 786, "decode_str": " Zhao"} -{"id": 38410, "token": "\u0120ALS", "merges": "\u0120AL S", "raw_count": 786, "count": 786, "decode_str": " ALS"} -{"id": 35942, "token": "\u0120Hundred", "merges": "\u0120H undred", "raw_count": 787, "count": 787, "decode_str": " Hundred"} -{"id": 29927, "token": "\u0120Owen", "merges": "\u0120O wen", "raw_count": 787, "count": 787, "decode_str": " Owen"} -{"id": 48420, "token": "\u0120Waste", "merges": "\u0120W aste", "raw_count": 788, "count": 788, "decode_str": " Waste"} -{"id": 17566, "token": "\u0120malignant", "merges": "\u0120malign ant", "raw_count": 789, "count": 789, "decode_str": " malignant"} -{"id": 32185, "token": "\u0120Ich", "merges": "\u0120I ch", "raw_count": 789, "count": 789, "decode_str": " Ich"} -{"id": 22092, "token": "\\}\\", "merges": "\\ }\\", "raw_count": 789, "count": 789, "decode_str": "\\}\\"} -{"id": 33662, "token": "\u0120homomorphism", "merges": "\u0120hom omorphism", "raw_count": 790, "count": 790, "decode_str": " homomorphism"} -{"id": 42832, "token": "\u0120lumines", "merges": "\u0120lum ines", "raw_count": 790, "count": 790, "decode_str": " lumines"} -{"id": 44433, "token": "\u0120d\u00c3\u0143a", "merges": "\u0120d \u00c3\u0143a", "raw_count": 790, "count": 790, "decode_str": " d\u00eda"} -{"id": 17879, "token": "\u0120CIA", "merges": "\u0120C IA", "raw_count": 790, "count": 790, "decode_str": " CIA"} -{"id": 46592, "token": "\u0120Adventures", "merges": "\u0120Advent ures", "raw_count": 791, "count": 791, "decode_str": " Adventures"} -{"id": 43779, "token": "\u0120Killing", "merges": "\u0120K illing", "raw_count": 791, "count": 791, "decode_str": " Killing"} -{"id": 24496, "token": "\u0120Luther", "merges": "\u0120L uther", "raw_count": 791, "count": 791, "decode_str": " Luther"} -{"id": 31890, "token": "\u0120Wals", "merges": "\u0120W als", "raw_count": 260, "count": 791, "decode_str": " Wals"} -{"id": 40558, "token": "\u0120Riv", "merges": "\u0120R iv", "raw_count": 791, "count": 791, "decode_str": " Riv"} -{"id": 35612, "token": "ocortic", "merges": "oc ortic", "raw_count": 629, "count": 792, "decode_str": "ocortic"} -{"id": 49154, "token": "odontic", "merges": "odont ic", "raw_count": 792, "count": 792, "decode_str": "odontic"} -{"id": 36373, "token": "\u0120Franz", "merges": "\u0120Fr anz", "raw_count": 792, "count": 792, "decode_str": " Franz"} -{"id": 25651, "token": "\u00ce\u00b6", "merges": "\u00ce \u00b6", "raw_count": 792, "count": 792, "decode_str": "\u03b6"} -{"id": 29136, "token": "\u0120VIII", "merges": "\u0120V III", "raw_count": 793, "count": 793, "decode_str": " VIII"} -{"id": 4398, "token": "\u0120\\<", "merges": "\u0120\\ <", "raw_count": 793, "count": 793, "decode_str": " \\<"} -{"id": 54141, "token": "\u00e9\u0123\u00b6", "merges": "\u00e9\u0123 \u00b6", "raw_count": 793, "count": 793, "decode_str": "\u9076"} -{"id": 32709, "token": "\u0120endoscopic", "merges": "\u0120end oscopic", "raw_count": 794, "count": 794, "decode_str": " endoscopic"} -{"id": 16069, "token": "\u0120neuronal", "merges": "\u0120neur onal", "raw_count": 794, "count": 794, "decode_str": " neuronal"} -{"id": 47255, "token": "\u0120Anto", "merges": "\u0120An to", "raw_count": 794, "count": 794, "decode_str": " Anto"} -{"id": 35810, "token": "ocellular", "merges": "oc ellular", "raw_count": 497, "count": 795, "decode_str": "ocellular"} -{"id": 34962, "token": "\u0120duality", "merges": "\u0120dual ity", "raw_count": 795, "count": 795, "decode_str": " duality"} -{"id": 35542, "token": "\u0120Ish", "merges": "\u0120I sh", "raw_count": 795, "count": 795, "decode_str": " Ish"} -{"id": 41808, "token": "\u00c3\u00a9p", "merges": "\u00c3\u00a9 p", "raw_count": 795, "count": 795, "decode_str": "\u00e9p"} -{"id": 47687, "token": "\u0120individualized", "merges": "\u0120individual ized", "raw_count": 796, "count": 796, "decode_str": " individualized"} -{"id": 49504, "token": "Affirmed", "merges": "Aff irmed", "raw_count": 796, "count": 796, "decode_str": "Affirmed"} -{"id": 40435, "token": "\u0120Noble", "merges": "\u0120Nob le", "raw_count": 796, "count": 796, "decode_str": " Noble"} -{"id": 50163, "token": "\u0120trich", "merges": "\u0120tr ich", "raw_count": 796, "count": 796, "decode_str": " trich"} -{"id": 27708, "token": "\u0120Leonard", "merges": "\u0120Leon ard", "raw_count": 797, "count": 797, "decode_str": " Leonard"} -{"id": 46252, "token": "\u0120spores", "merges": "\u0120sp ores", "raw_count": 797, "count": 797, "decode_str": " spores"} -{"id": 47556, "token": "\u0120delir", "merges": "\u0120del ir", "raw_count": 797, "count": 797, "decode_str": " delir"} -{"id": 30354, "token": "\u0120Dod", "merges": "\u0120D od", "raw_count": 725, "count": 797, "decode_str": " Dod"} -{"id": 11110, "token": "}_\\", "merges": "}_ \\", "raw_count": 797, "count": 797, "decode_str": "}_\\"} -{"id": 45221, "token": "\u0120Preparation", "merges": "\u0120Pre paration", "raw_count": 798, "count": 798, "decode_str": " Preparation"} -{"id": 16294, "token": "\u0120inhibitory", "merges": "\u0120inhib itory", "raw_count": 798, "count": 798, "decode_str": " inhibitory"} -{"id": 47261, "token": "\u0120insoluble", "merges": "\u0120insol uble", "raw_count": 798, "count": 798, "decode_str": " insoluble"} -{"id": 25645, "token": "defendant", "merges": "def endant", "raw_count": 798, "count": 798, "decode_str": "defendant"} -{"id": 41361, "token": "\u0120**[", "merges": "\u0120** [", "raw_count": 798, "count": 798, "decode_str": " **["} -{"id": 29100, "token": "\u0120relativistic", "merges": "\u0120rel ativistic", "raw_count": 799, "count": 799, "decode_str": " relativistic"} -{"id": 32237, "token": "\u0120Independence", "merges": "\u0120Ind ependence", "raw_count": 799, "count": 799, "decode_str": " Independence"} -{"id": 41116, "token": "\u0120seminal", "merges": "\u0120sem inal", "raw_count": 799, "count": 799, "decode_str": " seminal"} -{"id": 39119, "token": "\u0120Schwartz", "merges": "\u0120Sch wartz", "raw_count": 800, "count": 800, "decode_str": " Schwartz"} -{"id": 47803, "token": "\u0120LSD", "merges": "\u0120L SD", "raw_count": 800, "count": 800, "decode_str": " LSD"} -{"id": 26957, "token": "\u0120Abu", "merges": "\u0120Ab u", "raw_count": 800, "count": 800, "decode_str": " Abu"} -{"id": 26690, "token": "\u0120clinicians", "merges": "\u0120clin icians", "raw_count": 801, "count": 801, "decode_str": " clinicians"} -{"id": 30975, "token": "\u0120questo", "merges": "\u0120quest o", "raw_count": 801, "count": 801, "decode_str": " questo"} -{"id": 25062, "token": "\u0120Karen", "merges": "\u0120K aren", "raw_count": 801, "count": 801, "decode_str": " Karen"} -{"id": 25030, "token": "\u0120****,", "merges": "\u0120 ****,", "raw_count": 801, "count": 801, "decode_str": " ****,"} -{"id": 34042, "token": "aughs", "merges": "augh s", "raw_count": 282, "count": 801, "decode_str": "aughs"} -{"id": 32766, "token": "\u0120Hann", "merges": "\u0120H ann", "raw_count": 801, "count": 801, "decode_str": " Hann"} -{"id": 35637, "token": "\u0120symplectic", "merges": "\u0120sym plectic", "raw_count": 802, "count": 802, "decode_str": " symplectic"} -{"id": 50116, "token": "\u0120hetero", "merges": "\u0120heter o", "raw_count": 802, "count": 802, "decode_str": " hetero"} -{"id": 40696, "token": "\u0120dann", "merges": "\u0120d ann", "raw_count": 802, "count": 802, "decode_str": " dann"} -{"id": 48609, "token": "\u0120evaporated", "merges": "\u0120evapor ated", "raw_count": 803, "count": 803, "decode_str": " evaporated"} -{"id": 49301, "token": "\u0120budding", "merges": "\u0120bud ding", "raw_count": 803, "count": 803, "decode_str": " budding"} -{"id": 45625, "token": "\u0120lepton", "merges": "\u0120le pton", "raw_count": 803, "count": 803, "decode_str": " lepton"} -{"id": 37932, "token": "\u0120Raven", "merges": "\u0120R aven", "raw_count": 803, "count": 803, "decode_str": " Raven"} -{"id": 38233, "token": "\u0120ERA", "merges": "\u0120E RA", "raw_count": 803, "count": 803, "decode_str": " ERA"} -{"id": 42237, "token": "\u0120fibrillation", "merges": "\u0120fibr illation", "raw_count": 804, "count": 804, "decode_str": " fibrillation"} -{"id": 17592, "token": "\u0120hippocamp", "merges": "\u0120hipp ocamp", "raw_count": 39, "count": 804, "decode_str": " hippocamp"} -{"id": 27013, "token": "\u0120remanded", "merges": "\u0120rem anded", "raw_count": 804, "count": 804, "decode_str": " remanded"} -{"id": 29906, "token": "\u0120Bros", "merges": "\u0120B ros", "raw_count": 804, "count": 804, "decode_str": " Bros"} -{"id": 14858, "token": "\u00ce\u00b9\u00ce\u00b1", "merges": "\u00ce\u00b9 \u00ce\u00b1", "raw_count": 490, "count": 804, "decode_str": "\u03b9\u03b1"} -{"id": 43108, "token": "\u0120abnormality", "merges": "\u0120abnorm ality", "raw_count": 805, "count": 805, "decode_str": " abnormality"} -{"id": 24203, "token": "artifactId", "merges": "artifact Id", "raw_count": 805, "count": 805, "decode_str": "artifactId"} -{"id": 38122, "token": "\u0120antibacterial", "merges": "\u0120antib acterial", "raw_count": 806, "count": 806, "decode_str": " antibacterial"} -{"id": 29443, "token": "\u0120Wend", "merges": "\u0120W end", "raw_count": 522, "count": 806, "decode_str": " Wend"} -{"id": 45082, "token": "\u0120Levy", "merges": "\u0120Lev y", "raw_count": 806, "count": 806, "decode_str": " Levy"} -{"id": 36771, "token": "\u00d5\u00a1\u00d5", "merges": "\u00d5\u00a1 \u00d5", "raw_count": 806, "count": 806, "decode_str": "\u0561\ufffd"} -{"id": 29127, "token": "\u0120testosterone", "merges": "\u0120test osterone", "raw_count": 807, "count": 807, "decode_str": " testosterone"} -{"id": 36848, "token": "\u0120ventricle", "merges": "\u0120ventric le", "raw_count": 807, "count": 807, "decode_str": " ventricle"} -{"id": 36858, "token": "\u0120Calvin", "merges": "\u0120Cal vin", "raw_count": 807, "count": 807, "decode_str": " Calvin"} -{"id": 49774, "token": "\u0120hacia", "merges": "\u0120h acia", "raw_count": 807, "count": 807, "decode_str": " hacia"} -{"id": 25555, "token": "\u0120accretion", "merges": "\u0120accret ion", "raw_count": 808, "count": 808, "decode_str": " accretion"} -{"id": 44741, "token": "\u0120thriller", "merges": "\u0120thr iller", "raw_count": 808, "count": 808, "decode_str": " thriller"} -{"id": 38903, "token": "\u0120alors", "merges": "\u0120al ors", "raw_count": 808, "count": 808, "decode_str": " alors"} -{"id": 33219, "token": "\u0120KNOW", "merges": "\u0120K NOW", "raw_count": 808, "count": 808, "decode_str": " KNOW"} -{"id": 38312, "token": "\u0120Survival", "merges": "\u0120Surv ival", "raw_count": 809, "count": 809, "decode_str": " Survival"} -{"id": 39751, "token": "\u0120fibrous", "merges": "\u0120fibr ous", "raw_count": 809, "count": 809, "decode_str": " fibrous"} -{"id": 45968, "token": "\u0120Rag", "merges": "\u0120R ag", "raw_count": 809, "count": 809, "decode_str": " Rag"} -{"id": 46502, "token": "\u0120PDT", "merges": "\u0120PD T", "raw_count": 809, "count": 809, "decode_str": " PDT"} -{"id": 27273, "token": "\u0120electrophoresis", "merges": "\u0120electroph oresis", "raw_count": 810, "count": 810, "decode_str": " electrophoresis"} -{"id": 31270, "token": "\u0120Kenneth", "merges": "\u0120Kenn eth", "raw_count": 810, "count": 810, "decode_str": " Kenneth"} -{"id": 46345, "token": "antibodies", "merges": "antib odies", "raw_count": 811, "count": 811, "decode_str": "antibodies"} -{"id": 41932, "token": "\u0120Uh", "merges": "\u0120U h", "raw_count": 811, "count": 811, "decode_str": " Uh"} -{"id": 48374, "token": "\u0120illuminating", "merges": "\u0120illumin ating", "raw_count": 812, "count": 812, "decode_str": " illuminating"} -{"id": 38277, "token": "\u0120neutrinos", "merges": "\u0120neut rinos", "raw_count": 812, "count": 812, "decode_str": " neutrinos"} -{"id": 42761, "token": "\u00c3\u00b4le", "merges": "\u00c3\u00b4 le", "raw_count": 812, "count": 812, "decode_str": "\u00f4le"} -{"id": 31651, "token": "\u0120Ach", "merges": "\u0120A ch", "raw_count": 812, "count": 812, "decode_str": " Ach"} -{"id": 35661, "token": "\u0120Eighth", "merges": "\u0120Eight h", "raw_count": 813, "count": 813, "decode_str": " Eighth"} -{"id": 46755, "token": "\u0120Influ", "merges": "\u0120In flu", "raw_count": 813, "count": 813, "decode_str": " Influ"} -{"id": 41147, "token": "\u00d9\u012a\u00d9\u0126", "merges": "\u00d9\u012a \u00d9\u0126", "raw_count": 813, "count": 813, "decode_str": "\u0648\u0644"} -{"id": 41731, "token": "\u0120outper", "merges": "\u0120out per", "raw_count": 814, "count": 814, "decode_str": " outper"} -{"id": 28856, "token": "\u0120Laws", "merges": "\u0120Law s", "raw_count": 814, "count": 814, "decode_str": " Laws"} -{"id": 41353, "token": "Bibliography", "merges": "Bib liography", "raw_count": 815, "count": 815, "decode_str": "Bibliography"} -{"id": 42415, "token": "\u0120insulator", "merges": "\u0120ins ulator", "raw_count": 815, "count": 815, "decode_str": " insulator"} -{"id": 48827, "token": "\u0120Costs", "merges": "\u0120Cost s", "raw_count": 815, "count": 815, "decode_str": " Costs"} -{"id": 47674, "token": "\u0120Mayer", "merges": "\u0120May er", "raw_count": 815, "count": 815, "decode_str": " Mayer"} -{"id": 26511, "token": "\u0120Hern", "merges": "\u0120H ern", "raw_count": 538, "count": 815, "decode_str": " Hern"} -{"id": 44986, "token": "\u0120MSM", "merges": "\u0120M SM", "raw_count": 815, "count": 815, "decode_str": " MSM"} -{"id": 46158, "token": "\u0120travail", "merges": "\u0120trav ail", "raw_count": 816, "count": 816, "decode_str": " travail"} -{"id": 45899, "token": "\u0120macrom", "merges": "\u0120mac rom", "raw_count": 816, "count": 816, "decode_str": " macrom"} -{"id": 34197, "token": "\u0120Apollo", "merges": "\u0120Ap ollo", "raw_count": 816, "count": 816, "decode_str": " Apollo"} -{"id": 37386, "token": "\u0120probl", "merges": "\u0120pro bl", "raw_count": 816, "count": 816, "decode_str": " probl"} -{"id": 43475, "token": "\u0120Tomorrow", "merges": "\u0120Tom orrow", "raw_count": 817, "count": 817, "decode_str": " Tomorrow"} -{"id": 27991, "token": "\u0120Bradley", "merges": "\u0120Brad ley", "raw_count": 817, "count": 817, "decode_str": " Bradley"} -{"id": 41990, "token": "\u0120priming", "merges": "\u0120prim ing", "raw_count": 817, "count": 817, "decode_str": " priming"} -{"id": 16955, "token": "\u0120Charlie", "merges": "\u0120Char lie", "raw_count": 817, "count": 817, "decode_str": " Charlie"} -{"id": 42307, "token": "\u0120Scout", "merges": "\u0120Sc out", "raw_count": 817, "count": 817, "decode_str": " Scout"} -{"id": 41964, "token": "\u0120Sham", "merges": "\u0120Sh am", "raw_count": 817, "count": 817, "decode_str": " Sham"} -{"id": 48097, "token": "\u0120Stro", "merges": "\u0120St ro", "raw_count": 817, "count": 817, "decode_str": " Stro"} -{"id": 45236, "token": "\u0120HAD", "merges": "\u0120H AD", "raw_count": 817, "count": 817, "decode_str": " HAD"} -{"id": 18178, "token": "\u0120nanoparticles", "merges": "\u0120nanop articles", "raw_count": 818, "count": 818, "decode_str": " nanoparticles"} -{"id": 43152, "token": "\u0120creepy", "merges": "\u0120creep y", "raw_count": 818, "count": 818, "decode_str": " creepy"} -{"id": 10647, "token": "\u0120f\u00c3\u00b6r", "merges": "\u0120f \u00c3\u00b6r", "raw_count": 818, "count": 818, "decode_str": " f\u00f6r"} -{"id": 46166, "token": "\u0120Vale", "merges": "\u0120V ale", "raw_count": 818, "count": 818, "decode_str": " Vale"} -{"id": 30956, "token": "\u0120Cay", "merges": "\u0120C ay", "raw_count": 818, "count": 818, "decode_str": " Cay"} -{"id": 47410, "token": "\u0120rearrangement", "merges": "\u0120rearrang ement", "raw_count": 819, "count": 819, "decode_str": " rearrangement"} -{"id": 26144, "token": "\u0120dopamine", "merges": "\u0120dop amine", "raw_count": 819, "count": 819, "decode_str": " dopamine"} -{"id": 45420, "token": "\u0120caramel", "merges": "\u0120car amel", "raw_count": 819, "count": 819, "decode_str": " caramel"} -{"id": 27974, "token": "\u0120atrial", "merges": "\u0120at rial", "raw_count": 819, "count": 819, "decode_str": " atrial"} -{"id": 8033, "token": "\u0120Islam", "merges": "\u0120Is lam", "raw_count": 425, "count": 819, "decode_str": " Islam"} -{"id": 13124, "token": "\u0120Europ", "merges": "\u0120E urop", "raw_count": 513, "count": 819, "decode_str": " Europ"} -{"id": 19556, "token": "\u0120pathogenesis", "merges": "\u0120path ogenesis", "raw_count": 820, "count": 820, "decode_str": " pathogenesis"} -{"id": 48327, "token": "\u0120Enterprises", "merges": "\u0120Enter prises", "raw_count": 820, "count": 820, "decode_str": " Enterprises"} -{"id": 33613, "token": "\u0120uterine", "merges": "\u0120uter ine", "raw_count": 820, "count": 820, "decode_str": " uterine"} -{"id": 26134, "token": "\u0120Around", "merges": "\u0120Ar ound", "raw_count": 820, "count": 820, "decode_str": " Around"} -{"id": 36468, "token": "\u0120Carp", "merges": "\u0120Car p", "raw_count": 406, "count": 820, "decode_str": " Carp"} -{"id": 38050, "token": "\u0120d\u00c3\u00a9s", "merges": "\u0120d \u00c3\u00a9s", "raw_count": 821, "count": 821, "decode_str": " d\u00e9s"} -{"id": 43016, "token": "\u0120Hof", "merges": "\u0120H of", "raw_count": 821, "count": 821, "decode_str": " Hof"} -{"id": 43861, "token": "\u0120infused", "merges": "\u0120inf used", "raw_count": 822, "count": 822, "decode_str": " infused"} -{"id": 49369, "token": "\u0120Mystery", "merges": "\u0120My stery", "raw_count": 822, "count": 822, "decode_str": " Mystery"} -{"id": 40524, "token": "\u0120Blu", "merges": "\u0120Bl u", "raw_count": 822, "count": 822, "decode_str": " Blu"} -{"id": 12277, "token": "\u0120assays", "merges": "\u0120ass ays", "raw_count": 823, "count": 823, "decode_str": " assays"} -{"id": 48503, "token": "\u00e3\u0122\u0122\u00e3\u0122\u0122", "merges": "\u00e3\u0122\u0122 \u00e3\u0122\u0122", "raw_count": 823, "count": 823, "decode_str": "\u3000\u3000"} -{"id": 28257, "token": "\u0120Gand", "merges": "\u0120G and", "raw_count": 554, "count": 824, "decode_str": " Gand"} -{"id": 35929, "token": "\u0120Crus", "merges": "\u0120Cr us", "raw_count": 824, "count": 824, "decode_str": " Crus"} -{"id": 22303, "token": "\u0120NBC", "merges": "\u0120N BC", "raw_count": 824, "count": 824, "decode_str": " NBC"} -{"id": 48068, "token": "\u0120FISH", "merges": "\u0120F ISH", "raw_count": 825, "count": 825, "decode_str": " FISH"} -{"id": 36401, "token": "\u0120monomers", "merges": "\u0120mon omers", "raw_count": 826, "count": 826, "decode_str": " monomers"} -{"id": 33085, "token": "\u0120vacate", "merges": "\u0120vac ate", "raw_count": 826, "count": 826, "decode_str": " vacate"} -{"id": 23602, "token": "\u0120Hudson", "merges": "\u0120H udson", "raw_count": 826, "count": 826, "decode_str": " Hudson"} -{"id": 11268, "token": "\u0120Spain", "merges": "\u0120Sp ain", "raw_count": 826, "count": 826, "decode_str": " Spain"} -{"id": 36883, "token": "\u0120Hugo", "merges": "\u0120Hug o", "raw_count": 826, "count": 826, "decode_str": " Hugo"} -{"id": 38553, "token": "\u0120Fry", "merges": "\u0120F ry", "raw_count": 826, "count": 826, "decode_str": " Fry"} -{"id": 19049, "token": "\u0120,\\", "merges": "\u0120, \\", "raw_count": 826, "count": 826, "decode_str": " ,\\"} -{"id": 38838, "token": "omerase", "merges": "omer ase", "raw_count": 827, "count": 827, "decode_str": "omerase"} -{"id": 12885, "token": "\u0120Holly", "merges": "\u0120Hol ly", "raw_count": 243, "count": 827, "decode_str": " Holly"} -{"id": 49506, "token": "\u0120Essay", "merges": "\u0120Ess ay", "raw_count": 827, "count": 827, "decode_str": " Essay"} -{"id": 49839, "token": "\u0120Tale", "merges": "\u0120T ale", "raw_count": 828, "count": 828, "decode_str": " Tale"} -{"id": 13946, "token": "\u0120NFL", "merges": "\u0120N FL", "raw_count": 828, "count": 828, "decode_str": " NFL"} -{"id": 17902, "token": "\u0120cortical", "merges": "\u0120cort ical", "raw_count": 829, "count": 829, "decode_str": " cortical"} -{"id": 50105, "token": "\u0120Ket", "merges": "\u0120K et", "raw_count": 829, "count": 829, "decode_str": " Ket"} -{"id": 34029, "token": "\u0120thrombosis", "merges": "\u0120thromb osis", "raw_count": 830, "count": 830, "decode_str": " thrombosis"} -{"id": 32234, "token": "Originally", "merges": "Or iginally", "raw_count": 830, "count": 830, "decode_str": "Originally"} -{"id": 44207, "token": "\u0120Thermo", "merges": "\u0120Ther mo", "raw_count": 830, "count": 830, "decode_str": " Thermo"} -{"id": 34606, "token": "\u00d9\u012a\u00d9\u0128", "merges": "\u00d9\u012a \u00d9\u0128", "raw_count": 830, "count": 830, "decode_str": "\u0648\u0646"} -{"id": 25873, "token": "\u00c3\u00b6d", "merges": "\u00c3\u00b6 d", "raw_count": 337, "count": 830, "decode_str": "\u00f6d"} -{"id": 30837, "token": "transferase", "merges": "transfer ase", "raw_count": 831, "count": 831, "decode_str": "transferase"} -{"id": 40720, "token": "\u0120guitarist", "merges": "\u0120guitar ist", "raw_count": 831, "count": 831, "decode_str": " guitarist"} -{"id": 44198, "token": "\u0120Randolph", "merges": "\u0120Rand olph", "raw_count": 831, "count": 831, "decode_str": " Randolph"} -{"id": 39516, "token": "\u0120depolar", "merges": "\u0120dep olar", "raw_count": 831, "count": 831, "decode_str": " depolar"} -{"id": 9060, "token": "\u0120Chief", "merges": "\u0120Ch ief", "raw_count": 727, "count": 831, "decode_str": " Chief"} -{"id": 50026, "token": "\u0120Went", "merges": "\u0120W ent", "raw_count": 831, "count": 831, "decode_str": " Went"} -{"id": 38025, "token": "\u0120Hipp", "merges": "\u0120H ipp", "raw_count": 831, "count": 831, "decode_str": " Hipp"} -{"id": 8330, "token": "\u0120Wednesday", "merges": "\u0120Wed nesday", "raw_count": 832, "count": 832, "decode_str": " Wednesday"} -{"id": 39704, "token": "\u0120ureth", "merges": "\u0120ure th", "raw_count": 832, "count": 832, "decode_str": " ureth"} -{"id": 22212, "token": "\u0120Emperor", "merges": "\u0120Em peror", "raw_count": 833, "count": 833, "decode_str": " Emperor"} -{"id": 38826, "token": "\u0120Phosph", "merges": "\u0120Ph osph", "raw_count": 833, "count": 833, "decode_str": " Phosph"} -{"id": 38894, "token": "\u0120UIT", "merges": "\u0120U IT", "raw_count": 833, "count": 833, "decode_str": " UIT"} -{"id": 8313, "token": "\u00c2\u00bd", "merges": "\u00c2 \u00bd", "raw_count": 833, "count": 833, "decode_str": "\u00bd"} -{"id": 28079, "token": "\u0120Agriculture", "merges": "\u0120Agric ulture", "raw_count": 834, "count": 834, "decode_str": " Agriculture"} -{"id": 47673, "token": "okinetics", "merges": "ok inetics", "raw_count": 834, "count": 834, "decode_str": "okinetics"} -{"id": 41809, "token": "\u0120placenta", "merges": "\u0120placent a", "raw_count": 834, "count": 834, "decode_str": " placenta"} -{"id": 34162, "token": "\u0120atypical", "merges": "\u0120atyp ical", "raw_count": 834, "count": 834, "decode_str": " atypical"} -{"id": 48702, "token": "\u0120Tickets", "merges": "\u0120T ickets", "raw_count": 834, "count": 834, "decode_str": " Tickets"} -{"id": 31999, "token": "\u0120Mats", "merges": "\u0120M ats", "raw_count": 834, "count": 834, "decode_str": " Mats"} -{"id": 44141, "token": "\u0120}).", "merges": "\u0120} ).", "raw_count": 834, "count": 834, "decode_str": " })."} -{"id": 27526, "token": "\u0120Prevention", "merges": "\u0120Pre vention", "raw_count": 835, "count": 835, "decode_str": " Prevention"} -{"id": 180, "token": "\u0103", "merges": "NULL", "raw_count": 833, "count": 835, "decode_str": "\u0003"} -{"id": 48112, "token": "\u0120retardation", "merges": "\u0120retard ation", "raw_count": 836, "count": 836, "decode_str": " retardation"} -{"id": 38008, "token": "\u0120Orchestra", "merges": "\u0120Orche stra", "raw_count": 836, "count": 836, "decode_str": " Orchestra"} -{"id": 34877, "token": "\u0120Kerr", "merges": "\u0120K err", "raw_count": 836, "count": 836, "decode_str": " Kerr"} -{"id": 18759, "token": "\u0120Nig", "merges": "\u0120N ig", "raw_count": 650, "count": 836, "decode_str": " Nig"} -{"id": 39847, "token": "osyl", "merges": "os yl", "raw_count": 836, "count": 836, "decode_str": "osyl"} -{"id": 11444, "token": "}^{-", "merges": "}^{ -", "raw_count": 836, "count": 836, "decode_str": "}^{-"} -{"id": 48751, "token": "\u0120cochle", "merges": "\u0120co chle", "raw_count": 837, "count": 837, "decode_str": " cochle"} -{"id": 41720, "token": "\u0120Nokia", "merges": "\u0120N okia", "raw_count": 837, "count": 837, "decode_str": " Nokia"} -{"id": 30982, "token": "\u0120Bax", "merges": "\u0120B ax", "raw_count": 295, "count": 837, "decode_str": " Bax"} -{"id": 45941, "token": "\u0120Bis", "merges": "\u0120B is", "raw_count": 837, "count": 837, "decode_str": " Bis"} -{"id": 47983, "token": "\u0120metaphysical", "merges": "\u0120metaphys ical", "raw_count": 838, "count": 838, "decode_str": " metaphysical"} -{"id": 47450, "token": "\u0120coworkers", "merges": "\u0120cowork ers", "raw_count": 838, "count": 838, "decode_str": " coworkers"} -{"id": 21467, "token": "\u0120necrosis", "merges": "\u0120nec rosis", "raw_count": 838, "count": 838, "decode_str": " necrosis"} -{"id": 29301, "token": "\u0120Animals", "merges": "\u0120An imals", "raw_count": 838, "count": 838, "decode_str": " Animals"} -{"id": 38370, "token": "\u0120Bruno", "merges": "\u0120Brun o", "raw_count": 838, "count": 838, "decode_str": " Bruno"} -{"id": 35735, "token": "\u0120Laf", "merges": "\u0120L af", "raw_count": 601, "count": 838, "decode_str": " Laf"} -{"id": 45479, "token": "\u0120PLL", "merges": "\u0120P LL", "raw_count": 838, "count": 838, "decode_str": " PLL"} -{"id": 11227, "token": ",$$", "merges": ", $$", "raw_count": 838, "count": 838, "decode_str": ",$$"} -{"id": 50329, "token": "\u00e2\u012b\u00a6", "merges": "\u00e2\u012b \u00a6", "raw_count": 838, "count": 838, "decode_str": "\u2266"} -{"id": 43967, "token": "\u0120homogeneity", "merges": "\u0120hom ogeneity", "raw_count": 839, "count": 839, "decode_str": " homogeneity"} -{"id": 25084, "token": "\u0120Moses", "merges": "\u0120M oses", "raw_count": 839, "count": 839, "decode_str": " Moses"} -{"id": 42833, "token": "irubin", "merges": "ir ubin", "raw_count": 839, "count": 839, "decode_str": "irubin"} -{"id": 40285, "token": "\u0120Ost", "merges": "\u0120O st", "raw_count": 839, "count": 839, "decode_str": " Ost"} -{"id": 39291, "token": "\u00ef\u00bd\u00a1", "merges": "\u00ef\u00bd \u00a1", "raw_count": 839, "count": 839, "decode_str": "\uff61"} -{"id": 19964, "token": "\u00c2\u00aa", "merges": "\u00c2 \u00aa", "raw_count": 839, "count": 839, "decode_str": "\u00aa"} -{"id": 26267, "token": "\u0120ArrayList", "merges": "\u0120Array List", "raw_count": 840, "count": 840, "decode_str": " ArrayList"} -{"id": 37454, "token": "\u0120Fischer", "merges": "\u0120F ischer", "raw_count": 840, "count": 840, "decode_str": " Fischer"} -{"id": 28833, "token": "\u0120somatic", "merges": "\u0120som atic", "raw_count": 840, "count": 840, "decode_str": " somatic"} -{"id": 31603, "token": "\u0120Crist", "merges": "\u0120C rist", "raw_count": 840, "count": 840, "decode_str": " Crist"} -{"id": 17538, "token": "\u0120Fifth", "merges": "\u0120Fif th", "raw_count": 840, "count": 840, "decode_str": " Fifth"} -{"id": 43299, "token": "\u0120Fem", "merges": "\u0120F em", "raw_count": 840, "count": 840, "decode_str": " Fem"} -{"id": 35429, "token": "\u00d8\u00b6", "merges": "\u00d8 \u00b6", "raw_count": 840, "count": 840, "decode_str": "\u0636"} -{"id": 29940, "token": "\u0120stenosis", "merges": "\u0120sten osis", "raw_count": 841, "count": 841, "decode_str": " stenosis"} -{"id": 5664, "token": "boldsymbol", "merges": "bolds ymbol", "raw_count": 842, "count": 842, "decode_str": "boldsymbol"} -{"id": 36091, "token": "\u0120Mercury", "merges": "\u0120Merc ury", "raw_count": 842, "count": 842, "decode_str": " Mercury"} -{"id": 44071, "token": "\u0120Victory", "merges": "\u0120Vict ory", "raw_count": 842, "count": 842, "decode_str": " Victory"} -{"id": 15696, "token": "\u0120Nether", "merges": "\u0120Net her", "raw_count": 173, "count": 842, "decode_str": " Nether"} -{"id": 40552, "token": "\u00c3\u00a9qu", "merges": "\u00c3\u00a9 qu", "raw_count": 842, "count": 842, "decode_str": "\u00e9qu"} -{"id": 45835, "token": "\u0120-------------------------------", "merges": "\u0120---------------- ---------------", "raw_count": 843, "count": 843, "decode_str": " -------------------------------"} -{"id": 28773, "token": "\u0120femoral", "merges": "\u0120fem oral", "raw_count": 843, "count": 843, "decode_str": " femoral"} -{"id": 29169, "token": "\u0120Pearl", "merges": "\u0120Pear l", "raw_count": 843, "count": 843, "decode_str": " Pearl"} -{"id": 46568, "token": "\u0120Fres", "merges": "\u0120F res", "raw_count": 843, "count": 843, "decode_str": " Fres"} -{"id": 20669, "token": ")}_{", "merges": ") }_{", "raw_count": 843, "count": 843, "decode_str": ")}_{"} -{"id": 45301, "token": "]\\\\", "merges": "] \\\\", "raw_count": 843, "count": 843, "decode_str": "]\\\\"} -{"id": 43375, "token": "\u0120Rough", "merges": "\u0120R ough", "raw_count": 844, "count": 844, "decode_str": " Rough"} -{"id": 42538, "token": "\u0120Mond", "merges": "\u0120M ond", "raw_count": 844, "count": 844, "decode_str": " Mond"} -{"id": 36489, "token": "\u0120voir", "merges": "\u0120vo ir", "raw_count": 844, "count": 844, "decode_str": " voir"} -{"id": 48582, "token": "\u0120Rim", "merges": "\u0120R im", "raw_count": 844, "count": 844, "decode_str": " Rim"} -{"id": 37602, "token": "\u0120Erd", "merges": "\u0120E rd", "raw_count": 844, "count": 844, "decode_str": " Erd"} -{"id": 11549, "token": "\u0120\\;", "merges": "\u0120\\ ;", "raw_count": 844, "count": 844, "decode_str": " \\;"} -{"id": 30442, "token": "\u0120Clinic", "merges": "\u0120Cl inic", "raw_count": 845, "count": 845, "decode_str": " Clinic"} -{"id": 28750, "token": "\u0120Mills", "merges": "\u0120M ills", "raw_count": 845, "count": 845, "decode_str": " Mills"} -{"id": 25498, "token": "\u0120Gay", "merges": "\u0120G ay", "raw_count": 845, "count": 845, "decode_str": " Gay"} -{"id": 43734, "token": "\u0120phosphor", "merges": "\u0120phosph or", "raw_count": 846, "count": 846, "decode_str": " phosphor"} -{"id": 41963, "token": "\u0120Thomson", "merges": "\u0120Thom son", "raw_count": 846, "count": 846, "decode_str": " Thomson"} -{"id": 48621, "token": "\u0120atheist", "merges": "\u0120athe ist", "raw_count": 846, "count": 846, "decode_str": " atheist"} -{"id": 30674, "token": "\u0120Reich", "merges": "\u0120Re ich", "raw_count": 846, "count": 846, "decode_str": " Reich"} -{"id": 35300, "token": "\u00e3\u0123\u00ab\u00e3\u0123\u00af", "merges": "\u00e3\u0123\u00ab \u00e3\u0123\u00af", "raw_count": 846, "count": 846, "decode_str": "\u306b\u306f"} -{"id": 21217, "token": "\u0120Verm", "merges": "\u0120V erm", "raw_count": 761, "count": 846, "decode_str": " Verm"} -{"id": 32632, "token": "\u0120Wool", "merges": "\u0120W ool", "raw_count": 846, "count": 846, "decode_str": " Wool"} -{"id": 25198, "token": "\u0120Jag", "merges": "\u0120J ag", "raw_count": 846, "count": 846, "decode_str": " Jag"} -{"id": 47236, "token": "formaldehyde", "merges": "formal dehyde", "raw_count": 847, "count": 847, "decode_str": "formaldehyde"} -{"id": 18985, "token": "\u0120Jonathan", "merges": "\u0120Jon athan", "raw_count": 847, "count": 847, "decode_str": " Jonathan"} -{"id": 41925, "token": "\u0120Subsequent", "merges": "\u0120Sub sequent", "raw_count": 848, "count": 848, "decode_str": " Subsequent"} -{"id": 33017, "token": "\u0120Cathedral", "merges": "\u0120Cat hedral", "raw_count": 848, "count": 848, "decode_str": " Cathedral"} -{"id": 37549, "token": "\u0120Genes", "merges": "\u0120Gen es", "raw_count": 848, "count": 848, "decode_str": " Genes"} -{"id": 32508, "token": "\u0120dissection", "merges": "\u0120dis section", "raw_count": 849, "count": 849, "decode_str": " dissection"} -{"id": 47041, "token": "\u0120infinites", "merges": "\u0120infin ites", "raw_count": 849, "count": 849, "decode_str": " infinites"} -{"id": 45712, "token": "itars", "merges": "it ars", "raw_count": 67, "count": 849, "decode_str": "itars"} -{"id": 28962, "token": "\u0120Raf", "merges": "\u0120R af", "raw_count": 475, "count": 849, "decode_str": " Raf"} -{"id": 38707, "token": "\u0120Gothic", "merges": "\u0120Goth ic", "raw_count": 850, "count": 850, "decode_str": " Gothic"} -{"id": 52951, "token": "\u00e7\u0139\u00ba", "merges": "\u00e7\u0139 \u00ba", "raw_count": 850, "count": 850, "decode_str": "\u75fa"} -{"id": 43245, "token": "\u0120computationally", "merges": "\u0120computation ally", "raw_count": 851, "count": 851, "decode_str": " computationally"} -{"id": 34728, "token": "\u0120esophageal", "merges": "\u0120es ophageal", "raw_count": 851, "count": 851, "decode_str": " esophageal"} -{"id": 48066, "token": "\u0120counterclaim", "merges": "\u0120counter claim", "raw_count": 852, "count": 852, "decode_str": " counterclaim"} -{"id": 23878, "token": "\u0120colorectal", "merges": "\u0120col orectal", "raw_count": 852, "count": 852, "decode_str": " colorectal"} -{"id": 46384, "token": "\u0120Savings", "merges": "\u0120Sav ings", "raw_count": 852, "count": 852, "decode_str": " Savings"} -{"id": 45571, "token": "\u0120equilib", "merges": "\u0120equ ilib", "raw_count": 852, "count": 852, "decode_str": " equilib"} -{"id": 44442, "token": "\u0120Tian", "merges": "\u0120T ian", "raw_count": 852, "count": 852, "decode_str": " Tian"} -{"id": 10350, "token": "\u0120Constitution", "merges": "\u0120Con stitution", "raw_count": 647, "count": 853, "decode_str": " Constitution"} -{"id": 23001, "token": "\u0120Springer", "merges": "\u0120Spring er", "raw_count": 853, "count": 853, "decode_str": " Springer"} -{"id": 44278, "token": "\u0120Organic", "merges": "\u0120Organ ic", "raw_count": 853, "count": 853, "decode_str": " Organic"} -{"id": 33843, "token": "\u0120Canyon", "merges": "\u0120C anyon", "raw_count": 853, "count": 853, "decode_str": " Canyon"} -{"id": 30097, "token": "\u0120ethyl", "merges": "\u0120 ethyl", "raw_count": 853, "count": 853, "decode_str": " ethyl"} -{"id": 47730, "token": "autres", "merges": "aut res", "raw_count": 853, "count": 853, "decode_str": "autres"} -{"id": 21160, "token": "\u0120Bios", "merges": "\u0120B ios", "raw_count": 615, "count": 853, "decode_str": " Bios"} -{"id": 16411, "token": "\u00cf\u0126\u00ce\u00b5", "merges": "\u00cf\u0126 \u00ce\u00b5", "raw_count": 853, "count": 853, "decode_str": "\u03c4\u03b5"} -{"id": 48274, "token": "\u0120Boltzmann", "merges": "\u0120B oltzmann", "raw_count": 854, "count": 854, "decode_str": " Boltzmann"} -{"id": 31658, "token": "\u0120estoppel", "merges": "\u0120est oppel", "raw_count": 854, "count": 854, "decode_str": " estoppel"} -{"id": 39946, "token": "\u0120viscous", "merges": "\u0120vis cous", "raw_count": 854, "count": 854, "decode_str": " viscous"} -{"id": 39634, "token": "\u0120Stokes", "merges": "\u0120St okes", "raw_count": 854, "count": 854, "decode_str": " Stokes"} -{"id": 14180, "token": "\u0120Gree", "merges": "\u0120G ree", "raw_count": 279, "count": 854, "decode_str": " Gree"} -{"id": 38776, "token": "\u0120Rho", "merges": "\u0120R ho", "raw_count": 854, "count": 854, "decode_str": " Rho"} -{"id": 42360, "token": "r\u00c3\u0143", "merges": "r \u00c3\u0143", "raw_count": 854, "count": 854, "decode_str": "r\u00ed"} -{"id": 28854, "token": "\u0120Palmer", "merges": "\u0120Pal mer", "raw_count": 855, "count": 855, "decode_str": " Palmer"} -{"id": 34533, "token": "\u0120Hank", "merges": "\u0120H ank", "raw_count": 855, "count": 855, "decode_str": " Hank"} -{"id": 47910, "token": "epithelial", "merges": "epit helial", "raw_count": 856, "count": 856, "decode_str": "epithelial"} -{"id": 26768, "token": "\u0120neurop", "merges": "\u0120ne urop", "raw_count": 258, "count": 856, "decode_str": " neurop"} -{"id": 39058, "token": "fiddle", "merges": "f iddle", "raw_count": 718, "count": 856, "decode_str": "fiddle"} -{"id": 30193, "token": "\u0120Palm", "merges": "\u0120Pal m", "raw_count": 856, "count": 856, "decode_str": " Palm"} -{"id": 47269, "token": "}}<", "merges": "; \"><", "raw_count": 941, "count": 941, "decode_str": ";\"><"} -{"id": 42197, "token": "\u0120sedentary", "merges": "\u0120sed entary", "raw_count": 942, "count": 942, "decode_str": " sedentary"} -{"id": 8216, "token": "\u0120Thursday", "merges": "\u0120Th ursday", "raw_count": 943, "count": 943, "decode_str": " Thursday"} -{"id": 28447, "token": "\u0120opioid", "merges": "\u0120opio id", "raw_count": 943, "count": 943, "decode_str": " opioid"} -{"id": 22556, "token": "\u0120Tib", "merges": "\u0120T ib", "raw_count": 477, "count": 943, "decode_str": " Tib"} -{"id": 41922, "token": "\u0120mediates", "merges": "\u0120medi ates", "raw_count": 944, "count": 944, "decode_str": " mediates"} -{"id": 24008, "token": "\u0120Hughes", "merges": "\u0120Hug hes", "raw_count": 944, "count": 944, "decode_str": " Hughes"} -{"id": 31627, "token": "\u0120n\u00c3\u00a9", "merges": "\u0120n \u00c3\u00a9", "raw_count": 944, "count": 944, "decode_str": " n\u00e9"} -{"id": 11881, "token": "*~*", "merges": "*~ *", "raw_count": 944, "count": 944, "decode_str": "*~*"} -{"id": 45320, "token": "\u0120bipartisan", "merges": "\u0120bipart isan", "raw_count": 945, "count": 945, "decode_str": " bipartisan"} -{"id": 35499, "token": "\u0120Employment", "merges": "\u0120Employ ment", "raw_count": 945, "count": 945, "decode_str": " Employment"} -{"id": 27233, "token": "\u0120o\u00c3\u00b9", "merges": "\u0120o \u00c3\u00b9", "raw_count": 945, "count": 945, "decode_str": " o\u00f9"} -{"id": 44300, "token": "rugu", "merges": "rug u", "raw_count": 945, "count": 945, "decode_str": "rugu"} -{"id": 23630, "token": "\u0120\u00d9\u0126", "merges": "\u0120 \u00d9\u0126", "raw_count": 945, "count": 945, "decode_str": " \u0644"} -{"id": 38487, "token": "IOException", "merges": "IO Exception", "raw_count": 946, "count": 946, "decode_str": "IOException"} -{"id": 23728, "token": "\u0120Archives", "merges": "\u0120Arch ives", "raw_count": 946, "count": 946, "decode_str": " Archives"} -{"id": 44610, "token": "\u0120Mai", "merges": "\u0120M ai", "raw_count": 946, "count": 946, "decode_str": " Mai"} -{"id": 22155, "token": "\u0120superconduct", "merges": "\u0120super conduct", "raw_count": 444, "count": 947, "decode_str": " superconduct"} -{"id": 48790, "token": "\u0120Chaos", "merges": "\u0120Cha os", "raw_count": 947, "count": 947, "decode_str": " Chaos"} -{"id": 38117, "token": "\u0120wordt", "merges": "\u0120word t", "raw_count": 947, "count": 947, "decode_str": " wordt"} -{"id": 26226, "token": "\u0120Wes", "merges": "\u0120W es", "raw_count": 535, "count": 947, "decode_str": " Wes"} -{"id": 36953, "token": "\u0120t\u00c3\u00a9", "merges": "\u0120t \u00c3\u00a9", "raw_count": 947, "count": 947, "decode_str": " t\u00e9"} -{"id": 13602, "token": "\u0120Crim", "merges": "\u0120C rim", "raw_count": 408, "count": 948, "decode_str": " Crim"} -{"id": 15478, "token": "\u00c8\u013d", "merges": "\u00c8 \u013d", "raw_count": 785, "count": 948, "decode_str": "\u021b"} -{"id": 46743, "token": "\u0120superimposed", "merges": "\u0120super imposed", "raw_count": 949, "count": 949, "decode_str": " superimposed"} -{"id": 35873, "token": "\u0120radiative", "merges": "\u0120radi ative", "raw_count": 949, "count": 949, "decode_str": " radiative"} -{"id": 17106, "token": "\u0120Neither", "merges": "\u0120Ne ither", "raw_count": 949, "count": 949, "decode_str": " Neither"} -{"id": 39875, "token": "\u0120euthan", "merges": "\u0120e uthan", "raw_count": 949, "count": 949, "decode_str": " euthan"} -{"id": 23216, "token": "n\u00c3\u0143", "merges": "n \u00c3\u0143", "raw_count": 949, "count": 949, "decode_str": "n\u00ed"} -{"id": 39342, "token": "\u0120inversely", "merges": "\u0120in versely", "raw_count": 950, "count": 950, "decode_str": " inversely"} -{"id": 10392, "token": ")}$", "merges": ") }$", "raw_count": 950, "count": 950, "decode_str": ")}$"} -{"id": 40184, "token": "\u0120indistinguishable", "merges": "\u0120indist inguishable", "raw_count": 951, "count": 951, "decode_str": " indistinguishable"} -{"id": 41818, "token": "\u0120notations", "merges": "\u0120not ations", "raw_count": 951, "count": 951, "decode_str": " notations"} -{"id": 31286, "token": "\u0120WHE", "merges": "\u0120W HE", "raw_count": 798, "count": 951, "decode_str": " WHE"} -{"id": 32966, "token": "($_", "merges": "($ _", "raw_count": 951, "count": 951, "decode_str": "($_"} -{"id": 29029, "token": "\u0120selectivity", "merges": "\u0120select ivity", "raw_count": 952, "count": 952, "decode_str": " selectivity"} -{"id": 31961, "token": "=\"${", "merges": "=\" ${", "raw_count": 952, "count": 952, "decode_str": "=\"${"} -{"id": 44424, "token": "\u0120bek", "merges": "\u0120be k", "raw_count": 952, "count": 952, "decode_str": " bek"} -{"id": 26427, "token": "\u0120dehydrogen", "merges": "\u0120de hydrogen", "raw_count": 184, "count": 953, "decode_str": " dehydrogen"} -{"id": 26663, "token": "\u0120homolog", "merges": "\u0120hom olog", "raw_count": 953, "count": 953, "decode_str": " homolog"} -{"id": 49759, "token": "\u0120wafers", "merges": "\u0120w afers", "raw_count": 953, "count": 953, "decode_str": " wafers"} -{"id": 43267, "token": "\u0120Chest", "merges": "\u0120C hest", "raw_count": 953, "count": 953, "decode_str": " Chest"} -{"id": 47562, "token": ")$\\", "merges": ")$ \\", "raw_count": 953, "count": 953, "decode_str": ")$\\"} -{"id": 24031, "token": "\u0120ischemia", "merges": "\u0120is chemia", "raw_count": 954, "count": 954, "decode_str": " ischemia"} -{"id": 50194, "token": "\u0120ejemplo", "merges": "\u0120ej emplo", "raw_count": 954, "count": 954, "decode_str": " ejemplo"} -{"id": 22218, "token": "\u0120Freder", "merges": "\u0120Fred er", "raw_count": 229, "count": 954, "decode_str": " Freder"} -{"id": 21551, "token": "arlier", "merges": "ar lier", "raw_count": 177, "count": 954, "decode_str": "arlier"} -{"id": 40118, "token": "\u0120lute", "merges": "\u0120l ute", "raw_count": 954, "count": 954, "decode_str": " lute"} -{"id": 48307, "token": "~).", "merges": "~ ).", "raw_count": 954, "count": 954, "decode_str": "~)."} -{"id": 26166, "token": "\u0120cosmological", "merges": "\u0120cosm ological", "raw_count": 955, "count": 955, "decode_str": " cosmological"} -{"id": 34184, "token": "\u0120Waters", "merges": "\u0120Wat ers", "raw_count": 955, "count": 955, "decode_str": " Waters"} -{"id": 20554, "token": "\u0120Oliver", "merges": "\u0120O liver", "raw_count": 955, "count": 955, "decode_str": " Oliver"} -{"id": 9972, "token": "\u0120Italy", "merges": "\u0120It aly", "raw_count": 955, "count": 955, "decode_str": " Italy"} -{"id": 41558, "token": "\u0120Zhou", "merges": "\u0120Z hou", "raw_count": 955, "count": 955, "decode_str": " Zhou"} -{"id": 33135, "token": "\u0120Koch", "merges": "\u0120K och", "raw_count": 955, "count": 955, "decode_str": " Koch"} -{"id": 44149, "token": "\u0120MMA", "merges": "\u0120M MA", "raw_count": 955, "count": 955, "decode_str": " MMA"} -{"id": 43558, "token": "^*,", "merges": "^ *,", "raw_count": 955, "count": 955, "decode_str": "^*,"} -{"id": 45232, "token": "\u0120\u00d8\u00ae", "merges": "\u0120\u00d8 \u00ae", "raw_count": 955, "count": 955, "decode_str": " \u062e"} -{"id": 16783, "token": "\u0120methylation", "merges": "\u0120methyl ation", "raw_count": 956, "count": 956, "decode_str": " methylation"} -{"id": 35051, "token": "\u0120solubility", "merges": "\u0120solub ility", "raw_count": 956, "count": 956, "decode_str": " solubility"} -{"id": 46587, "token": "Eventually", "merges": "Event ually", "raw_count": 956, "count": 956, "decode_str": "Eventually"} -{"id": 24425, "token": "\u0120Bapt", "merges": "\u0120B apt", "raw_count": 511, "count": 956, "decode_str": " Bapt"} -{"id": 23312, "token": "\u0120HPV", "merges": "\u0120H PV", "raw_count": 956, "count": 956, "decode_str": " HPV"} -{"id": 39715, "token": "phosphory", "merges": "phosph ory", "raw_count": 957, "count": 957, "decode_str": "phosphory"} -{"id": 39357, "token": "Biography", "merges": "Bi ography", "raw_count": 957, "count": 957, "decode_str": "Biography"} -{"id": 33294, "token": "\u0120Henri", "merges": "\u0120Hen ri", "raw_count": 957, "count": 957, "decode_str": " Henri"} -{"id": 46155, "token": "\u0120Tales", "merges": "\u0120T ales", "raw_count": 957, "count": 957, "decode_str": " Tales"} -{"id": 30012, "token": "\u0120Kas", "merges": "\u0120K as", "raw_count": 957, "count": 957, "decode_str": " Kas"} -{"id": 42332, "token": "\u0120-----------------------------", "merges": "\u0120---------------- -------------", "raw_count": 958, "count": 958, "decode_str": " -----------------------------"} -{"id": 38587, "token": "\u0120nanot", "merges": "\u0120nan ot", "raw_count": 958, "count": 958, "decode_str": " nanot"} -{"id": 35359, "token": "\u0120Swan", "merges": "\u0120Sw an", "raw_count": 958, "count": 958, "decode_str": " Swan"} -{"id": 36482, "token": "\u0120Lil", "merges": "\u0120L il", "raw_count": 958, "count": 958, "decode_str": " Lil"} -{"id": 40083, "token": "\u0120inpatient", "merges": "\u0120in patient", "raw_count": 959, "count": 959, "decode_str": " inpatient"} -{"id": 23463, "token": "\u0120neutrino", "merges": "\u0120neutr ino", "raw_count": 959, "count": 959, "decode_str": " neutrino"} -{"id": 35845, "token": "\u0120excision", "merges": "\u0120exc ision", "raw_count": 959, "count": 959, "decode_str": " excision"} -{"id": 39872, "token": "\u0120glaucoma", "merges": "\u0120gl aucoma", "raw_count": 959, "count": 959, "decode_str": " glaucoma"} -{"id": 36566, "token": "\u0120isoform", "merges": "\u0120iso form", "raw_count": 959, "count": 959, "decode_str": " isoform"} -{"id": 16203, "token": "\u0120myel", "merges": "\u0120my el", "raw_count": 825, "count": 959, "decode_str": " myel"} -{"id": 35790, "token": "\u00d7\u0135", "merges": "\u00d7 \u0135", "raw_count": 959, "count": 959, "decode_str": "\u05d3"} -{"id": 38257, "token": "Populated", "merges": "Pop ulated", "raw_count": 960, "count": 960, "decode_str": "Populated"} -{"id": 50109, "token": "\u0120punches", "merges": "\u0120pun ches", "raw_count": 960, "count": 960, "decode_str": " punches"} -{"id": 24611, "token": "\u0120Harvey", "merges": "\u0120Har vey", "raw_count": 960, "count": 960, "decode_str": " Harvey"} -{"id": 36380, "token": "\u0120Meth", "merges": "\u0120M eth", "raw_count": 960, "count": 960, "decode_str": " Meth"} -{"id": 41903, "token": "\u0120Kai", "merges": "\u0120K ai", "raw_count": 960, "count": 960, "decode_str": " Kai"} -{"id": 25269, "token": "\u0120\u00d7\u0136", "merges": "\u0120\u00d7 \u0136", "raw_count": 960, "count": 960, "decode_str": " \u05d4"} -{"id": 45135, "token": "\"){", "merges": "\" ){", "raw_count": 960, "count": 960, "decode_str": "\"){"} -{"id": 44925, "token": "\u0120Heroes", "merges": "\u0120Hero es", "raw_count": 961, "count": 961, "decode_str": " Heroes"} -{"id": 39330, "token": "\u0120characterizing", "merges": "\u0120character izing", "raw_count": 962, "count": 962, "decode_str": " characterizing"} -{"id": 45797, "token": "\u0120Dew", "merges": "\u0120D ew", "raw_count": 962, "count": 962, "decode_str": " Dew"} -{"id": 47992, "token": "\u0120Trials", "merges": "\u0120Tri als", "raw_count": 963, "count": 963, "decode_str": " Trials"} -{"id": 28093, "token": "\u0120Haven", "merges": "\u0120H aven", "raw_count": 963, "count": 963, "decode_str": " Haven"} -{"id": 47808, "token": "\u0120HCl", "merges": "\u0120H Cl", "raw_count": 963, "count": 963, "decode_str": " HCl"} -{"id": 22224, "token": "\u00e0\u00a5\u0122", "merges": "\u00e0\u00a5 \u0122", "raw_count": 963, "count": 963, "decode_str": "\u0940"} -{"id": 42254, "token": "\u0120misrepresentation", "merges": "\u0120misrepresent ation", "raw_count": 964, "count": 964, "decode_str": " misrepresentation"} -{"id": 12533, "token": "\u0120macroph", "merges": "\u0120mac roph", "raw_count": 326, "count": 964, "decode_str": " macroph"} -{"id": 42885, "token": "\u0120diff\u00c3\u00a9", "merges": "\u0120diff \u00c3\u00a9", "raw_count": 964, "count": 964, "decode_str": " diff\u00e9"} -{"id": 42722, "token": "\u0120sempre", "merges": "\u0120sem pre", "raw_count": 964, "count": 964, "decode_str": " sempre"} -{"id": 13247, "token": "\u0120Korean", "merges": "\u0120Kore an", "raw_count": 964, "count": 964, "decode_str": " Korean"} -{"id": 26066, "token": "\u0120Brooks", "merges": "\u0120Brook s", "raw_count": 964, "count": 964, "decode_str": " Brooks"} -{"id": 17946, "token": "\u00cf\u0123\u00ce\u00b1", "merges": "\u00cf\u0123 \u00ce\u00b1", "raw_count": 964, "count": 964, "decode_str": "\u03c1\u03b1"} -{"id": 41373, "token": "\u0120malpractice", "merges": "\u0120mal practice", "raw_count": 965, "count": 965, "decode_str": " malpractice"} -{"id": 49488, "token": "\u0120tossing", "merges": "\u0120toss ing", "raw_count": 965, "count": 965, "decode_str": " tossing"} -{"id": 43181, "token": "\u0120patter", "merges": "\u0120pat ter", "raw_count": 698, "count": 965, "decode_str": " patter"} -{"id": 11042, "token": "\u0120Swed", "merges": "\u0120Sw ed", "raw_count": 74, "count": 965, "decode_str": " Swed"} -{"id": 42139, "token": "\u0120anter", "merges": "\u0120an ter", "raw_count": 966, "count": 966, "decode_str": " anter"} -{"id": 47433, "token": "\u0120Dee", "merges": "\u0120De e", "raw_count": 966, "count": 966, "decode_str": " Dee"} -{"id": 24303, "token": ",\\\\", "merges": ",\\ \\", "raw_count": 966, "count": 966, "decode_str": ",\\\\"} -{"id": 31860, "token": "\u0120Ik", "merges": "\u0120I k", "raw_count": 966, "count": 966, "decode_str": " Ik"} -{"id": 53535, "token": "\u00e8\u0126\u0129", "merges": "\u00e8\u0126 \u0129", "raw_count": 966, "count": 966, "decode_str": "\u8107"} -{"id": 17957, "token": "\u0120hydroph", "merges": "\u0120hydro ph", "raw_count": 306, "count": 967, "decode_str": " hydroph"} -{"id": 45681, "token": "\u0120Ludwig", "merges": "\u0120Lud wig", "raw_count": 967, "count": 967, "decode_str": " Ludwig"} -{"id": 23599, "token": "\u0120vocals", "merges": "\u0120voc als", "raw_count": 967, "count": 967, "decode_str": " vocals"} -{"id": 31948, "token": "rocyte", "merges": "rocy te", "raw_count": 967, "count": 967, "decode_str": "rocyte"} -{"id": 31976, "token": "\u0120Lith", "merges": "\u0120L ith", "raw_count": 845, "count": 967, "decode_str": " Lith"} -{"id": 33320, "token": "\u00c3\u00b3g", "merges": "\u00c3\u00b3 g", "raw_count": 967, "count": 967, "decode_str": "\u00f3g"} -{"id": 37651, "token": "\u0120distinguishable", "merges": "\u0120distinguish able", "raw_count": 968, "count": 968, "decode_str": " distinguishable"} -{"id": 42249, "token": "\u0120imagining", "merges": "\u0120imag ining", "raw_count": 968, "count": 968, "decode_str": " imagining"} -{"id": 42141, "token": "\u0120Deutsch", "merges": "\u0120Deut sch", "raw_count": 968, "count": 968, "decode_str": " Deutsch"} -{"id": 29589, "token": "blockList", "merges": "block List", "raw_count": 969, "count": 969, "decode_str": "blockList"} -{"id": 40392, "token": "\u0120Bec", "merges": "\u0120B ec", "raw_count": 969, "count": 969, "decode_str": " Bec"} -{"id": 21725, "token": "\u0120cleavage", "merges": "\u0120cle avage", "raw_count": 970, "count": 970, "decode_str": " cleavage"} -{"id": 33004, "token": "\u0120Freeman", "merges": "\u0120Fre eman", "raw_count": 970, "count": 970, "decode_str": " Freeman"} -{"id": 39146, "token": "\u00e1\u0125\u0136\u00e1\u0125", "merges": "\u00e1\u0125\u0136 \u00e1\u0125", "raw_count": 970, "count": 970, "decode_str": "\u10d4\ufffd"} -{"id": 39149, "token": "\u0120conventionally", "merges": "\u0120convention ally", "raw_count": 971, "count": 971, "decode_str": " conventionally"} -{"id": 41651, "token": "\u0120storytelling", "merges": "\u0120story telling", "raw_count": 971, "count": 971, "decode_str": " storytelling"} -{"id": 35228, "token": "\u0120PlayStation", "merges": "\u0120Play Station", "raw_count": 971, "count": 971, "decode_str": " PlayStation"} -{"id": 31680, "token": "\u0120progenitor", "merges": "\u0120progen itor", "raw_count": 971, "count": 971, "decode_str": " progenitor"} -{"id": 34199, "token": "\u0120burglary", "merges": "\u0120burgl ary", "raw_count": 971, "count": 971, "decode_str": " burglary"} -{"id": 50162, "token": "\u0120Fang", "merges": "\u0120F ang", "raw_count": 971, "count": 971, "decode_str": " Fang"} -{"id": 46656, "token": "\u0120DRAM", "merges": "\u0120DR AM", "raw_count": 971, "count": 971, "decode_str": " DRAM"} -{"id": 36403, "token": "\u00d7\u0139", "merges": "\u00d7 \u0139", "raw_count": 971, "count": 971, "decode_str": "\u05d7"} -{"id": 47933, "token": "\u0120homestead", "merges": "\u0120hom estead", "raw_count": 972, "count": 972, "decode_str": " homestead"} -{"id": 30331, "token": "\u0120\u00d8\u00a7\u00d9\u0126\u00d9\u0127", "merges": "\u0120\u00d8\u00a7\u00d9\u0126 \u00d9\u0127", "raw_count": 972, "count": 972, "decode_str": " \u0627\u0644\u0645"} -{"id": 15940, "token": "\u0120Rick", "merges": "\u0120R ick", "raw_count": 804, "count": 972, "decode_str": " Rick"} -{"id": 18481, "token": "\u00c3\u00a5r", "merges": "\u00c3\u00a5 r", "raw_count": 972, "count": 972, "decode_str": "\u00e5r"} -{"id": 31468, "token": "\u00d7\u00a2", "merges": "\u00d7 \u00a2", "raw_count": 972, "count": 972, "decode_str": "\u05e2"} -{"id": 38744, "token": "\u0120mediating", "merges": "\u0120medi ating", "raw_count": 973, "count": 973, "decode_str": " mediating"} -{"id": 27581, "token": "\u0120Gabriel", "merges": "\u0120Gab riel", "raw_count": 973, "count": 973, "decode_str": " Gabriel"} -{"id": 47806, "token": "\u0120juxt", "merges": "\u0120ju xt", "raw_count": 973, "count": 973, "decode_str": " juxt"} -{"id": 24800, "token": "|}", "merges": "| }", "raw_count": 973, "count": 973, "decode_str": "|}"} -{"id": 30772, "token": "\u0120splicing", "merges": "\u0120splic ing", "raw_count": 974, "count": 974, "decode_str": " splicing"} -{"id": 27080, "token": "\u0120Daw", "merges": "\u0120D aw", "raw_count": 595, "count": 974, "decode_str": " Daw"} -{"id": 47714, "token": "\u0120CTL", "merges": "\u0120CT L", "raw_count": 974, "count": 974, "decode_str": " CTL"} -{"id": 11011, "token": "\u0120Ireland", "merges": "\u0120I reland", "raw_count": 975, "count": 975, "decode_str": " Ireland"} -{"id": 28178, "token": "\u0120Salv", "merges": "\u0120Sal v", "raw_count": 711, "count": 975, "decode_str": " Salv"} -{"id": 31803, "token": "bben", "merges": "bb en", "raw_count": 814, "count": 975, "decode_str": "bben"} -{"id": 48916, "token": "\u0120Tao", "merges": "\u0120T ao", "raw_count": 975, "count": 975, "decode_str": " Tao"} -{"id": 45838, "token": "\u0120Xin", "merges": "\u0120X in", "raw_count": 975, "count": 975, "decode_str": " Xin"} -{"id": 9121, "token": "\u0120\\{", "merges": "\u0120\\ {", "raw_count": 975, "count": 975, "decode_str": " \\{"} -{"id": 40717, "token": "\u0120Agricultural", "merges": "\u0120Agric ultural", "raw_count": 976, "count": 976, "decode_str": " Agricultural"} -{"id": 48647, "token": "\u0120Bernstein", "merges": "\u0120Bern stein", "raw_count": 976, "count": 976, "decode_str": " Bernstein"} -{"id": 29544, "token": "\u0120Emm", "merges": "\u0120E mm", "raw_count": 976, "count": 976, "decode_str": " Emm"} -{"id": 35291, "token": "\u0120Aim", "merges": "\u0120A im", "raw_count": 977, "count": 977, "decode_str": " Aim"} -{"id": 50351, "token": "\u00e2\u0137\u00af", "merges": "\u00e2\u0137 \u00af", "raw_count": 977, "count": 977, "decode_str": "\u256f"} -{"id": 19717, "token": "\u0120Christopher", "merges": "\u0120Christ opher", "raw_count": 978, "count": 978, "decode_str": " Christopher"} -{"id": 44871, "token": "\u0120palliative", "merges": "\u0120pall iative", "raw_count": 978, "count": 978, "decode_str": " palliative"} -{"id": 42884, "token": "\u0120decid", "merges": "\u0120dec id", "raw_count": 978, "count": 978, "decode_str": " decid"} -{"id": 33216, "token": "\u0120Jazz", "merges": "\u0120J azz", "raw_count": 978, "count": 978, "decode_str": " Jazz"} -{"id": 51151, "token": "\u00e5\u013d\u012b", "merges": "\u00e5\u013d \u012b", "raw_count": 978, "count": 978, "decode_str": "\u56c9"} -{"id": 36657, "token": "\u0120Coming", "merges": "\u0120Com ing", "raw_count": 979, "count": 979, "decode_str": " Coming"} -{"id": 30312, "token": "\u0120corne", "merges": "\u0120cor ne", "raw_count": 327, "count": 979, "decode_str": " corne"} -{"id": 21178, "token": "\u0120Gonz", "merges": "\u0120G onz", "raw_count": 450, "count": 979, "decode_str": " Gonz"} -{"id": 21130, "token": "\u0120Andy", "merges": "\u0120And y", "raw_count": 979, "count": 979, "decode_str": " Andy"} -{"id": 40350, "token": "\u0120rigidity", "merges": "\u0120rig idity", "raw_count": 980, "count": 980, "decode_str": " rigidity"} -{"id": 45956, "token": "\u0120exerts", "merges": "\u0120exert s", "raw_count": 980, "count": 980, "decode_str": " exerts"} -{"id": 18088, "token": "\u0120Vegas", "merges": "\u0120Veg as", "raw_count": 980, "count": 980, "decode_str": " Vegas"} -{"id": 18975, "token": "\u0120Gary", "merges": "\u0120G ary", "raw_count": 980, "count": 980, "decode_str": " Gary"} -{"id": 34986, "token": "\u0120waveguide", "merges": "\u0120wave guide", "raw_count": 981, "count": 981, "decode_str": " waveguide"} -{"id": 31084, "token": "\u0120pelvic", "merges": "\u0120pel vic", "raw_count": 981, "count": 981, "decode_str": " pelvic"} -{"id": 19172, "token": "\u0120Dean", "merges": "\u0120De an", "raw_count": 981, "count": 981, "decode_str": " Dean"} -{"id": 26192, "token": "\u0120Baron", "merges": "\u0120Bar on", "raw_count": 982, "count": 982, "decode_str": " Baron"} -{"id": 36112, "token": "\u0120caud", "merges": "\u0120c aud", "raw_count": 982, "count": 982, "decode_str": " caud"} -{"id": 35569, "token": "\u0120wenn", "merges": "\u0120w enn", "raw_count": 982, "count": 982, "decode_str": " wenn"} -{"id": 36954, "token": "\u0120leuc", "merges": "\u0120le uc", "raw_count": 982, "count": 982, "decode_str": " leuc"} -{"id": 33691, "token": "\u0120elongation", "merges": "\u0120elong ation", "raw_count": 983, "count": 983, "decode_str": " elongation"} -{"id": 18360, "token": "\u0120affidavit", "merges": "\u0120affidav it", "raw_count": 983, "count": 983, "decode_str": " affidavit"} -{"id": 48048, "token": "\u0120rapper", "merges": "\u0120ra pper", "raw_count": 983, "count": 983, "decode_str": " rapper"} -{"id": 36876, "token": "\u0120eso", "merges": "\u0120es o", "raw_count": 983, "count": 983, "decode_str": " eso"} -{"id": 33201, "token": "\u0120metallicity", "merges": "\u0120metall icity", "raw_count": 984, "count": 984, "decode_str": " metallicity"} -{"id": 17974, "token": "\u0120felony", "merges": "\u0120fel ony", "raw_count": 984, "count": 984, "decode_str": " felony"} -{"id": 49876, "token": "\u0120roared", "merges": "\u0120ro ared", "raw_count": 984, "count": 984, "decode_str": " roared"} -{"id": 20577, "token": "\u0120Craig", "merges": "\u0120Cra ig", "raw_count": 984, "count": 984, "decode_str": " Craig"} -{"id": 39124, "token": "\u0120prejudiced", "merges": "\u0120prejud iced", "raw_count": 985, "count": 985, "decode_str": " prejudiced"} -{"id": 22497, "token": "\u0120Norman", "merges": "\u0120Norm an", "raw_count": 985, "count": 985, "decode_str": " Norman"} -{"id": 26907, "token": "\u00c3\u00bablic", "merges": "\u00c3\u00ba blic", "raw_count": 368, "count": 985, "decode_str": "\u00fablic"} -{"id": 31138, "token": "\u0120Paulo", "merges": "\u0120Paul o", "raw_count": 985, "count": 985, "decode_str": " Paulo"} -{"id": 24919, "token": "\u0120Shah", "merges": "\u0120Sh ah", "raw_count": 985, "count": 985, "decode_str": " Shah"} -{"id": 38078, "token": "\u0120Increasing", "merges": "\u0120Incre asing", "raw_count": 986, "count": 986, "decode_str": " Increasing"} -{"id": 25458, "token": "\u0120Wallace", "merges": "\u0120Wall ace", "raw_count": 986, "count": 986, "decode_str": " Wallace"} -{"id": 21946, "token": "\u0120CBS", "merges": "\u0120C BS", "raw_count": 986, "count": 986, "decode_str": " CBS"} -{"id": 34847, "token": "gesterone", "merges": "gester one", "raw_count": 664, "count": 987, "decode_str": "gesterone"} -{"id": 47362, "token": "\u0120jerked", "merges": "\u0120jerk ed", "raw_count": 987, "count": 987, "decode_str": " jerked"} -{"id": 37165, "token": "\u0120embol", "merges": "\u0120emb ol", "raw_count": 987, "count": 987, "decode_str": " embol"} -{"id": 22579, "token": "\u0120Kirk", "merges": "\u0120K irk", "raw_count": 987, "count": 987, "decode_str": " Kirk"} -{"id": 49216, "token": "\u0120\u00c3\u00b3", "merges": "\u0120\u00c3 \u00b3", "raw_count": 987, "count": 987, "decode_str": " \u00f3"} -{"id": 50132, "token": "\u0120Sensitivity", "merges": "\u0120S ensitivity", "raw_count": 988, "count": 988, "decode_str": " Sensitivity"} -{"id": 39620, "token": "\u0120condensate", "merges": "\u0120condens ate", "raw_count": 988, "count": 988, "decode_str": " condensate"} -{"id": 35135, "token": "\u0120placent", "merges": "\u0120pl acent", "raw_count": 154, "count": 988, "decode_str": " placent"} -{"id": 32016, "token": "\u0120Faculty", "merges": "\u0120Fac ulty", "raw_count": 988, "count": 988, "decode_str": " Faculty"} -{"id": 45715, "token": "ieurs", "merges": "ie urs", "raw_count": 988, "count": 988, "decode_str": "ieurs"} -{"id": 15652, "token": "displaystyle", "merges": "display style", "raw_count": 989, "count": 989, "decode_str": "displaystyle"} -{"id": 24955, "token": "\u0120Someone", "merges": "\u0120Some one", "raw_count": 989, "count": 989, "decode_str": " Someone"} -{"id": 17794, "token": "\u0120Argent", "merges": "\u0120Ar gent", "raw_count": 363, "count": 989, "decode_str": " Argent"} -{"id": 35814, "token": "\u0120Tum", "merges": "\u0120T um", "raw_count": 989, "count": 989, "decode_str": " Tum"} -{"id": 39967, "token": "\u0120Dart", "merges": "\u0120D art", "raw_count": 990, "count": 990, "decode_str": " Dart"} -{"id": 47819, "token": "\u0120whispers", "merges": "\u0120whis pers", "raw_count": 991, "count": 991, "decode_str": " whispers"} -{"id": 41854, "token": "\u0120forearm", "merges": "\u0120fore arm", "raw_count": 991, "count": 991, "decode_str": " forearm"} -{"id": 27261, "token": "\u0120Julia", "merges": "\u0120Jul ia", "raw_count": 991, "count": 991, "decode_str": " Julia"} -{"id": 43060, "token": "\u0120Wit", "merges": "\u0120W it", "raw_count": 991, "count": 991, "decode_str": " Wit"} -{"id": 35226, "token": "\u0120Programme", "merges": "\u0120Program me", "raw_count": 992, "count": 992, "decode_str": " Programme"} -{"id": 28595, "token": "\u0120toner", "merges": "\u0120ton er", "raw_count": 992, "count": 992, "decode_str": " toner"} -{"id": 34946, "token": "\u0120Kumar", "merges": "\u0120K umar", "raw_count": 992, "count": 992, "decode_str": " Kumar"} -{"id": 15946, "token": "\u0120Pitt", "merges": "\u0120P itt", "raw_count": 677, "count": 992, "decode_str": " Pitt"} -{"id": 27749, "token": "\u0120peu", "merges": "\u0120pe u", "raw_count": 992, "count": 992, "decode_str": " peu"} -{"id": 50150, "token": "\u0120ICO", "merges": "\u0120I CO", "raw_count": 992, "count": 992, "decode_str": " ICO"} -{"id": 50288, "token": "\u00cb\u013b", "merges": "\u00cb \u013b", "raw_count": 992, "count": 992, "decode_str": "\u02d9"} -{"id": 42016, "token": "amethasone", "merges": "ameth asone", "raw_count": 789, "count": 994, "decode_str": "amethasone"} -{"id": 33289, "token": "\u0120rearrang", "merges": "\u0120rearr ang", "raw_count": 175, "count": 994, "decode_str": " rearrang"} -{"id": 31088, "token": "\u0120suffices", "merges": "\u0120suff ices", "raw_count": 994, "count": 994, "decode_str": " suffices"} -{"id": 24360, "token": "\u0120endomet", "merges": "\u0120end omet", "raw_count": 146, "count": 994, "decode_str": " endomet"} -{"id": 28828, "token": "\u0120innings", "merges": "\u0120inn ings", "raw_count": 994, "count": 994, "decode_str": " innings"} -{"id": 33755, "token": "\u0120intercourse", "merges": "\u0120inter course", "raw_count": 995, "count": 995, "decode_str": " intercourse"} -{"id": 40388, "token": "\u0120Giant", "merges": "\u0120G iant", "raw_count": 995, "count": 995, "decode_str": " Giant"} -{"id": 28887, "token": "\u0120Tat", "merges": "\u0120T at", "raw_count": 995, "count": 995, "decode_str": " Tat"} -{"id": 25583, "token": "\\|\\", "merges": "\\ |\\", "raw_count": 995, "count": 995, "decode_str": "\\|\\"} -{"id": 33695, "token": "\u00e0\u00b5\u012f", "merges": "\u00e0\u00b5 \u012f", "raw_count": 995, "count": 995, "decode_str": "\u0d4d"} -{"id": 42337, "token": "\u0120Wellington", "merges": "\u0120W ellington", "raw_count": 996, "count": 996, "decode_str": " Wellington"} -{"id": 10586, "token": "\u0120Southern", "merges": "\u0120S outhern", "raw_count": 996, "count": 996, "decode_str": " Southern"} -{"id": 39293, "token": "\u0120Chal", "merges": "\u0120Ch al", "raw_count": 996, "count": 996, "decode_str": " Chal"} -{"id": 28642, "token": "\u0120Ana", "merges": "\u0120An a", "raw_count": 996, "count": 996, "decode_str": " Ana"} -{"id": 48909, "token": "\u0120Wn", "merges": "\u0120W n", "raw_count": 996, "count": 996, "decode_str": " Wn"} -{"id": 31247, "token": "\u0120Carr", "merges": "\u0120Car r", "raw_count": 997, "count": 997, "decode_str": " Carr"} -{"id": 27478, "token": "\u0120ESPN", "merges": "\u0120ESP N", "raw_count": 997, "count": 997, "decode_str": " ESPN"} -{"id": 50358, "token": "\u00e2\u0138\u0129", "merges": "\u00e2\u0138 \u0129", "raw_count": 997, "count": 997, "decode_str": "\u2587"} -{"id": 48147, "token": "\u0120glancing", "merges": "\u0120gl ancing", "raw_count": 998, "count": 998, "decode_str": " glancing"} -{"id": 30595, "token": "\u0120elast", "merges": "\u0120el ast", "raw_count": 998, "count": 998, "decode_str": " elast"} -{"id": 29761, "token": "\u0120Miles", "merges": "\u0120M iles", "raw_count": 998, "count": 998, "decode_str": " Miles"} -{"id": 20627, "token": "\u0120Nash", "merges": "\u0120N ash", "raw_count": 792, "count": 998, "decode_str": " Nash"} -{"id": 27344, "token": "\u0120\u00e2\u0123", "merges": "\u0120\u00e2 \u0123", "raw_count": 998, "count": 998, "decode_str": " \ufffd"} -{"id": 45210, "token": "\u0120borderline", "merges": "\u0120border line", "raw_count": 999, "count": 999, "decode_str": " borderline"} -{"id": 26958, "token": "\u0120Alexand", "merges": "\u0120Alex and", "raw_count": 635, "count": 1000, "decode_str": " Alexand"} -{"id": 49468, "token": "\u0120Galois", "merges": "\u0120Gal ois", "raw_count": 1000, "count": 1000, "decode_str": " Galois"} -{"id": 21969, "token": "\u0120m\u00c3\u00aame", "merges": "\u0120m \u00c3\u00aame", "raw_count": 1000, "count": 1000, "decode_str": " m\u00eame"} -{"id": 25943, "token": "\u0120supplementation", "merges": "\u0120supplement ation", "raw_count": 1001, "count": 1001, "decode_str": " supplementation"} -{"id": 49421, "token": "\u0120oscillating", "merges": "\u0120oscill ating", "raw_count": 1001, "count": 1001, "decode_str": " oscillating"} -{"id": 46342, "token": "\u0120grilled", "merges": "\u0120gr illed", "raw_count": 1001, "count": 1001, "decode_str": " grilled"} -{"id": 42544, "token": "\u0120uterus", "merges": "\u0120uter us", "raw_count": 1001, "count": 1001, "decode_str": " uterus"} -{"id": 14733, "token": "\u00cf\u0123\u00ce\u00bf", "merges": "\u00cf\u0123 \u00ce\u00bf", "raw_count": 827, "count": 1001, "decode_str": "\u03c1\u03bf"} -{"id": 41852, "token": "\u0120Wen", "merges": "\u0120W en", "raw_count": 1001, "count": 1001, "decode_str": " Wen"} -{"id": 22490, "token": "itoneal", "merges": "itone al", "raw_count": 113, "count": 1002, "decode_str": "itoneal"} -{"id": 34799, "token": "ococcal", "merges": "ococ cal", "raw_count": 1002, "count": 1002, "decode_str": "ococcal"} -{"id": 28294, "token": "\u0120monol", "merges": "\u0120mon ol", "raw_count": 774, "count": 1002, "decode_str": " monol"} -{"id": 38221, "token": "\u00e0\u00a6\u00b0", "merges": "\u00e0\u00a6 \u00b0", "raw_count": 1002, "count": 1002, "decode_str": "\u09b0"} -{"id": 31047, "token": "\u00d5\u00a1", "merges": "\u00d5 \u00a1", "raw_count": 196, "count": 1002, "decode_str": "\u0561"} -{"id": 32015, "token": "\u0120Partnership", "merges": "\u0120Part nership", "raw_count": 1003, "count": 1003, "decode_str": " Partnership"} -{"id": 14386, "token": "\u0120toxicity", "merges": "\u0120tox icity", "raw_count": 1003, "count": 1003, "decode_str": " toxicity"} -{"id": 40487, "token": "\u0120Mell", "merges": "\u0120M ell", "raw_count": 1003, "count": 1003, "decode_str": " Mell"} -{"id": 49480, "token": "\u0120Cors", "merges": "\u0120C ors", "raw_count": 1004, "count": 1004, "decode_str": " Cors"} -{"id": 27461, "token": "\u0120Lis", "merges": "\u0120L is", "raw_count": 897, "count": 1004, "decode_str": " Lis"} -{"id": 42845, "token": "\u0120jot", "merges": "\u0120j ot", "raw_count": 1004, "count": 1004, "decode_str": " jot"} -{"id": 43161, "token": "\u0120Improvement", "merges": "\u0120Improve ment", "raw_count": 1005, "count": 1005, "decode_str": " Improvement"} -{"id": 43585, "token": "\u0120dispersal", "merges": "\u0120dispers al", "raw_count": 1005, "count": 1005, "decode_str": " dispersal"} -{"id": 49006, "token": "\u0120nodding", "merges": "\u0120nod ding", "raw_count": 1005, "count": 1005, "decode_str": " nodding"} -{"id": 26993, "token": "\u0120Female", "merges": "\u0120F emale", "raw_count": 1005, "count": 1005, "decode_str": " Female"} -{"id": 44052, "token": "\u0120Yoga", "merges": "\u0120Y oga", "raw_count": 1005, "count": 1005, "decode_str": " Yoga"} -{"id": 36646, "token": "\u0120\u00c3\u00a7a", "merges": "\u0120\u00c3\u00a7 a", "raw_count": 1005, "count": 1005, "decode_str": " \u00e7a"} -{"id": 35912, "token": "\u0120pylori", "merges": "\u0120pyl ori", "raw_count": 1006, "count": 1006, "decode_str": " pylori"} -{"id": 48129, "token": "\u0120hydration", "merges": "\u0120hyd ration", "raw_count": 1007, "count": 1007, "decode_str": " hydration"} -{"id": 45829, "token": "\u0120scall", "merges": "\u0120sc all", "raw_count": 1007, "count": 1007, "decode_str": " scall"} -{"id": 27443, "token": "\u0120Ivan", "merges": "\u0120I van", "raw_count": 1007, "count": 1007, "decode_str": " Ivan"} -{"id": 46477, "token": "\u0120g\u00c3\u00a9n\u00c3\u00a9", "merges": "\u0120g \u00c3\u00a9n\u00c3\u00a9", "raw_count": 1008, "count": 1008, "decode_str": " g\u00e9n\u00e9"} -{"id": 26496, "token": "\u0120Woods", "merges": "\u0120Wood s", "raw_count": 1008, "count": 1008, "decode_str": " Woods"} -{"id": 27735, "token": "\u0120muit", "merges": "\u0120m uit", "raw_count": 349, "count": 1008, "decode_str": " muit"} -{"id": 46487, "token": "\u0120Tin", "merges": "\u0120T in", "raw_count": 1008, "count": 1008, "decode_str": " Tin"} -{"id": 43826, "token": "\u0120Edu", "merges": "\u0120E du", "raw_count": 1008, "count": 1008, "decode_str": " Edu"} -{"id": 49825, "token": "\u0120lifeless", "merges": "\u0120lif eless", "raw_count": 1009, "count": 1009, "decode_str": " lifeless"} -{"id": 31390, "token": "opoietic", "merges": "op oietic", "raw_count": 603, "count": 1009, "decode_str": "opoietic"} -{"id": 33042, "token": "\u0120Canal", "merges": "\u0120Can al", "raw_count": 1009, "count": 1009, "decode_str": " Canal"} -{"id": 40752, "token": "\u0120stratification", "merges": "\u0120strat ification", "raw_count": 1010, "count": 1010, "decode_str": " stratification"} -{"id": 35234, "token": "\u0120r\u00c3\u00a9g", "merges": "\u0120r\u00c3\u00a9 g", "raw_count": 1010, "count": 1010, "decode_str": " r\u00e9g"} -{"id": 31188, "token": "\u0120Census", "merges": "\u0120C ensus", "raw_count": 1011, "count": 1011, "decode_str": " Census"} -{"id": 38002, "token": "\u0120Glor", "merges": "\u0120G lor", "raw_count": 797, "count": 1011, "decode_str": " Glor"} -{"id": 39329, "token": "\u0120Hiro", "merges": "\u0120H iro", "raw_count": 1011, "count": 1011, "decode_str": " Hiro"} -{"id": 17757, "token": "\u00ce\u00bc\u00ce\u00b1", "merges": "\u00ce\u00bc \u00ce\u00b1", "raw_count": 1011, "count": 1011, "decode_str": "\u03bc\u03b1"} -{"id": 28567, "token": "\u0120implanted", "merges": "\u0120impl anted", "raw_count": 1012, "count": 1012, "decode_str": " implanted"} -{"id": 48805, "token": "\u0120Bulletin", "merges": "\u0120Bullet in", "raw_count": 1012, "count": 1012, "decode_str": " Bulletin"} -{"id": 41505, "token": "\u00d0\u00be\u00d0\u00b2\u00d0\u00be\u00d1\u0122", "merges": "\u00d0\u00be\u00d0\u00b2 \u00d0\u00be\u00d1\u0122", "raw_count": 1012, "count": 1012, "decode_str": "\u043e\u0432\u043e\u0440"} -{"id": 48661, "token": "\u0120microl", "merges": "\u0120mic rol", "raw_count": 1012, "count": 1012, "decode_str": " microl"} -{"id": 35887, "token": "\u0120Beast", "merges": "\u0120Be ast", "raw_count": 1012, "count": 1012, "decode_str": " Beast"} -{"id": 26211, "token": "\u0120Sullivan", "merges": "\u0120S ullivan", "raw_count": 1013, "count": 1013, "decode_str": " Sullivan"} -{"id": 40251, "token": "chrane", "merges": "chr ane", "raw_count": 839, "count": 1014, "decode_str": "chrane"} -{"id": 24569, "token": "\u0120Wells", "merges": "\u0120Well s", "raw_count": 1014, "count": 1014, "decode_str": " Wells"} -{"id": 27773, "token": "\u0120Blake", "merges": "\u0120Bl ake", "raw_count": 1014, "count": 1014, "decode_str": " Blake"} -{"id": 37179, "token": "\u0120suis", "merges": "\u0120su is", "raw_count": 1014, "count": 1014, "decode_str": " suis"} -{"id": 38140, "token": "\u0120FDR", "merges": "\u0120F DR", "raw_count": 1015, "count": 1015, "decode_str": " FDR"} -{"id": 43968, "token": "\u0120Cyp", "merges": "\u0120C yp", "raw_count": 1015, "count": 1015, "decode_str": " Cyp"} -{"id": 41561, "token": "\u0120Bac", "merges": "\u0120B ac", "raw_count": 1015, "count": 1015, "decode_str": " Bac"} -{"id": 14157, "token": ">::", "merges": "> ::", "raw_count": 1015, "count": 1015, "decode_str": ">::"} -{"id": 41886, "token": "\u0120convergent", "merges": "\u0120conver gent", "raw_count": 1016, "count": 1016, "decode_str": " convergent"} -{"id": 32550, "token": "\u0120Prophet", "merges": "\u0120Prop het", "raw_count": 1016, "count": 1016, "decode_str": " Prophet"} -{"id": 34825, "token": "\u0120Zeit", "merges": "\u0120Ze it", "raw_count": 1016, "count": 1016, "decode_str": " Zeit"} -{"id": 14411, "token": ")}(", "merges": ") }(", "raw_count": 1016, "count": 1016, "decode_str": ")}("} -{"id": 36674, "token": "\u0120subpoena", "merges": "\u0120subpo ena", "raw_count": 1017, "count": 1017, "decode_str": " subpoena"} -{"id": 35151, "token": "\u0120Terr", "merges": "\u0120T err", "raw_count": 1017, "count": 1017, "decode_str": " Terr"} -{"id": 32064, "token": "\u0120Kend", "merges": "\u0120K end", "raw_count": 1017, "count": 1017, "decode_str": " Kend"} -{"id": 43765, "token": "\u0120ORF", "merges": "\u0120OR F", "raw_count": 1017, "count": 1017, "decode_str": " ORF"} -{"id": 43758, "token": "\u0120continuance", "merges": "\u0120contin uance", "raw_count": 1018, "count": 1018, "decode_str": " continuance"} -{"id": 25010, "token": "\u0120Eventually", "merges": "\u0120Event ually", "raw_count": 1019, "count": 1019, "decode_str": " Eventually"} -{"id": 36456, "token": "\u0120pitching", "merges": "\u0120pitch ing", "raw_count": 1019, "count": 1019, "decode_str": " pitching"} -{"id": 38075, "token": "\u0120FIFA", "merges": "\u0120FIF A", "raw_count": 1019, "count": 1019, "decode_str": " FIFA"} -{"id": 42340, "token": "\u0120Wow", "merges": "\u0120W ow", "raw_count": 1019, "count": 1019, "decode_str": " Wow"} -{"id": 40024, "token": "r\u00c3\u00a1", "merges": "r \u00c3\u00a1", "raw_count": 1019, "count": 1019, "decode_str": "r\u00e1"} -{"id": 47532, "token": "\u00c3\u00a2te", "merges": "\u00c3\u00a2 te", "raw_count": 1020, "count": 1020, "decode_str": "\u00e2te"} -{"id": 50349, "token": "\u00e2\u0137\u0143", "merges": "\u00e2\u0137 \u0143", "raw_count": 1020, "count": 1020, "decode_str": "\u256d"} -{"id": 47224, "token": "\u0120umbilical", "merges": "\u0120umbil ical", "raw_count": 1021, "count": 1021, "decode_str": " umbilical"} -{"id": 34211, "token": "\u0120Million", "merges": "\u0120M illion", "raw_count": 1021, "count": 1021, "decode_str": " Million"} -{"id": 25882, "token": "\u0120stent", "merges": "\u0120st ent", "raw_count": 1021, "count": 1021, "decode_str": " stent"} -{"id": 43125, "token": "\u0120Dipl", "merges": "\u0120Di pl", "raw_count": 1021, "count": 1021, "decode_str": " Dipl"} -{"id": 43752, "token": "\u0120CNT", "merges": "\u0120C NT", "raw_count": 1021, "count": 1021, "decode_str": " CNT"} -{"id": 33345, "token": "\u0120importante", "merges": "\u0120important e", "raw_count": 1022, "count": 1022, "decode_str": " importante"} -{"id": 43417, "token": "\u0120Telescope", "merges": "\u0120Telesc ope", "raw_count": 1022, "count": 1022, "decode_str": " Telescope"} -{"id": 43633, "token": "\u0120Myth", "merges": "\u0120My th", "raw_count": 1022, "count": 1022, "decode_str": " Myth"} -{"id": 45473, "token": "teral", "merges": "ter al", "raw_count": 1022, "count": 1022, "decode_str": "teral"} -{"id": 45811, "token": "\u0120narrator", "merges": "\u0120narr ator", "raw_count": 1023, "count": 1023, "decode_str": " narrator"} -{"id": 30789, "token": "\u0120Kap", "merges": "\u0120K ap", "raw_count": 1023, "count": 1023, "decode_str": " Kap"} -{"id": 38566, "token": "\u0120Electro", "merges": "\u0120Elect ro", "raw_count": 1024, "count": 1024, "decode_str": " Electro"} -{"id": 26737, "token": "\u0120Johann", "merges": "\u0120Joh ann", "raw_count": 619, "count": 1024, "decode_str": " Johann"} -{"id": 37334, "token": "\u0120septic", "merges": "\u0120se ptic", "raw_count": 1024, "count": 1024, "decode_str": " septic"} -{"id": 36210, "token": "\u0120Venus", "merges": "\u0120Ven us", "raw_count": 1024, "count": 1024, "decode_str": " Venus"} -{"id": 34604, "token": "\u0120potency", "merges": "\u0120pot ency", "raw_count": 1025, "count": 1025, "decode_str": " potency"} -{"id": 23253, "token": "\u0120Holland", "merges": "\u0120Hol land", "raw_count": 1025, "count": 1025, "decode_str": " Holland"} -{"id": 23035, "token": "\u0120accret", "merges": "\u0120acc ret", "raw_count": 217, "count": 1025, "decode_str": " accret"} -{"id": 48020, "token": "\u0120Abuse", "merges": "\u0120Ab use", "raw_count": 1025, "count": 1025, "decode_str": " Abuse"} -{"id": 42971, "token": "\u0120TODAY", "merges": "\u0120TOD AY", "raw_count": 1025, "count": 1025, "decode_str": " TODAY"} -{"id": 20795, "token": "\u0120$,", "merges": "\u0120$ ,", "raw_count": 1025, "count": 1025, "decode_str": " $,"} -{"id": 28848, "token": "\u0120Galactic", "merges": "\u0120Gal actic", "raw_count": 1026, "count": 1026, "decode_str": " Galactic"} -{"id": 17330, "token": "\u0120Harvard", "merges": "\u0120Har vard", "raw_count": 1026, "count": 1026, "decode_str": " Harvard"} -{"id": 24910, "token": "\u0120einer", "merges": "\u0120e iner", "raw_count": 1026, "count": 1026, "decode_str": " einer"} -{"id": 47421, "token": "\u0120admittedly", "merges": "\u0120admitted ly", "raw_count": 1027, "count": 1027, "decode_str": " admittedly"} -{"id": 30393, "token": "\u0120anisotropy", "merges": "\u0120anisot ropy", "raw_count": 1027, "count": 1027, "decode_str": " anisotropy"} -{"id": 17179, "token": "\u0120Franklin", "merges": "\u0120Frank lin", "raw_count": 1027, "count": 1027, "decode_str": " Franklin"} -{"id": 48707, "token": "regulate", "merges": "reg ulate", "raw_count": 1027, "count": 1027, "decode_str": "regulate"} -{"id": 27432, "token": "\u0120einen", "merges": "\u0120ein en", "raw_count": 1027, "count": 1027, "decode_str": " einen"} -{"id": 7718, "token": "cdots", "merges": "cd ots", "raw_count": 1027, "count": 1027, "decode_str": "cdots"} -{"id": 43844, "token": "\u0120Zend", "merges": "\u0120Z end", "raw_count": 1027, "count": 1027, "decode_str": " Zend"} -{"id": 45453, "token": "\u0120retrograde", "merges": "\u0120retro grade", "raw_count": 1028, "count": 1028, "decode_str": " retrograde"} -{"id": 37849, "token": "\u0120\u00ce\u00a3", "merges": "\u0120\u00ce \u00a3", "raw_count": 1028, "count": 1028, "decode_str": " \u03a3"} -{"id": 20884, "token": "\u0120Military", "merges": "\u0120Mil itary", "raw_count": 1029, "count": 1029, "decode_str": " Military"} -{"id": 37711, "token": "\u0120aliqu", "merges": "\u0120al iqu", "raw_count": 1029, "count": 1029, "decode_str": " aliqu"} -{"id": 41481, "token": "\u0120Arms", "merges": "\u0120Ar ms", "raw_count": 1029, "count": 1029, "decode_str": " Arms"} -{"id": 29132, "token": "\u0120Rus", "merges": "\u0120R us", "raw_count": 1029, "count": 1029, "decode_str": " Rus"} -{"id": 25998, "token": "\u0120Apparently", "merges": "\u0120App arently", "raw_count": 1030, "count": 1030, "decode_str": " Apparently"} -{"id": 46983, "token": "\u0120fantasies", "merges": "\u0120fantas ies", "raw_count": 1030, "count": 1030, "decode_str": " fantasies"} -{"id": 32090, "token": ".\u00e2\u0122\u013b\u00e2\u0122\u013f", "merges": ".\u00e2\u0122\u013b \u00e2\u0122\u013f", "raw_count": 1030, "count": 1030, "decode_str": ".\u2019\u201d"} -{"id": 28810, "token": "\u0120Born", "merges": "\u0120B orn", "raw_count": 1030, "count": 1030, "decode_str": " Born"} -{"id": 47054, "token": "\u00e3\u0125\u0141", "merges": "\u00e3\u0125 \u0141", "raw_count": 1031, "count": 1031, "decode_str": "\u30df"} -{"id": 26327, "token": "\u0120Athlet", "merges": "\u0120Ath let", "raw_count": 170, "count": 1032, "decode_str": " Athlet"} -{"id": 45406, "token": "\u0120semif", "merges": "\u0120sem if", "raw_count": 1032, "count": 1032, "decode_str": " semif"} -{"id": 41100, "token": "\u0120Chef", "merges": "\u0120Che f", "raw_count": 1032, "count": 1032, "decode_str": " Chef"} -{"id": 17583, "token": "\u00c2\u00b9", "merges": "\u00c2 \u00b9", "raw_count": 1032, "count": 1032, "decode_str": "\u00b9"} -{"id": 21564, "token": "\u0120eryth", "merges": "\u0120ery th", "raw_count": 926, "count": 1033, "decode_str": " eryth"} -{"id": 31747, "token": "\u0120rheumat", "merges": "\u0120rhe umat", "raw_count": 615, "count": 1034, "decode_str": " rheumat"} -{"id": 42166, "token": "\u0120Singer", "merges": "\u0120S inger", "raw_count": 1034, "count": 1034, "decode_str": " Singer"} -{"id": 26503, "token": "\u0120Arabic", "merges": "\u0120Arab ic", "raw_count": 1034, "count": 1034, "decode_str": " Arabic"} -{"id": 42107, "token": "\u0120Caf", "merges": "\u0120C af", "raw_count": 1034, "count": 1034, "decode_str": " Caf"} -{"id": 44649, "token": "\u00e3\u0125\u0135", "merges": "\u00e3\u0125 \u0135", "raw_count": 1034, "count": 1034, "decode_str": "\u30d3"} -{"id": 24661, "token": ")}_", "merges": ") }_", "raw_count": 1034, "count": 1034, "decode_str": ")}_"} -{"id": 29256, "token": "\u0120Og", "merges": "\u0120O g", "raw_count": 1034, "count": 1034, "decode_str": " Og"} -{"id": 21910, "token": "\u0120Generally", "merges": "\u0120Gener ally", "raw_count": 1035, "count": 1035, "decode_str": " Generally"} -{"id": 42742, "token": "\u0120adorable", "merges": "\u0120ad orable", "raw_count": 1035, "count": 1035, "decode_str": " adorable"} -{"id": 34879, "token": "\u0120cerebro", "merges": "\u0120cere bro", "raw_count": 1035, "count": 1035, "decode_str": " cerebro"} -{"id": 22992, "token": "\u0120Earl", "merges": "\u0120E arl", "raw_count": 1035, "count": 1035, "decode_str": " Earl"} -{"id": 16908, "token": "\u0120Dave", "merges": "\u0120D ave", "raw_count": 1035, "count": 1035, "decode_str": " Dave"} -{"id": 23184, "token": "\u0120Das", "merges": "\u0120D as", "raw_count": 1037, "count": 1037, "decode_str": " Das"} -{"id": 35747, "token": "\u0120Bast", "merges": "\u0120B ast", "raw_count": 1038, "count": 1038, "decode_str": " Bast"} -{"id": 42724, "token": "\u0120Voy", "merges": "\u0120V oy", "raw_count": 1038, "count": 1038, "decode_str": " Voy"} -{"id": 48846, "token": "\u0120blockers", "merges": "\u0120block ers", "raw_count": 1039, "count": 1039, "decode_str": " blockers"} -{"id": 40308, "token": "\u0120indie", "merges": "\u0120ind ie", "raw_count": 1039, "count": 1039, "decode_str": " indie"} -{"id": 42957, "token": "galact", "merges": "gal act", "raw_count": 1039, "count": 1039, "decode_str": "galact"} -{"id": 14912, "token": "\u0120Diego", "merges": "\u0120Die go", "raw_count": 1039, "count": 1039, "decode_str": " Diego"} -{"id": 36769, "token": "astom", "merges": "ast om", "raw_count": 537, "count": 1039, "decode_str": "astom"} -{"id": 34098, "token": "\u0120Mathematical", "merges": "\u0120Mathemat ical", "raw_count": 1040, "count": 1040, "decode_str": " Mathematical"} -{"id": 45769, "token": "\u0120semen", "merges": "\u0120sem en", "raw_count": 1040, "count": 1040, "decode_str": " semen"} -{"id": 5655, "token": "bolds", "merges": "b olds", "raw_count": 198, "count": 1040, "decode_str": "bolds"} -{"id": 45397, "token": "\u0120Ivy", "merges": "\u0120I vy", "raw_count": 1040, "count": 1040, "decode_str": " Ivy"} -{"id": 29009, "token": "\u0120circuitry", "merges": "\u0120circuit ry", "raw_count": 1041, "count": 1041, "decode_str": " circuitry"} -{"id": 20903, "token": "\u0120sperm", "merges": "\u0120sper m", "raw_count": 1041, "count": 1041, "decode_str": " sperm"} -{"id": 43637, "token": "\u0120chuckled", "merges": "\u0120chuck led", "raw_count": 1042, "count": 1042, "decode_str": " chuckled"} -{"id": 15360, "token": "\u0120Portug", "merges": "\u0120Port ug", "raw_count": 338, "count": 1042, "decode_str": " Portug"} -{"id": 26979, "token": "\u0120pr\u00c3\u00a9s", "merges": "\u0120pr \u00c3\u00a9s", "raw_count": 1042, "count": 1042, "decode_str": " pr\u00e9s"} -{"id": 34445, "token": "\u0120Bil", "merges": "\u0120B il", "raw_count": 1042, "count": 1042, "decode_str": " Bil"} -{"id": 39233, "token": "\u0120Era", "merges": "\u0120E ra", "raw_count": 1042, "count": 1042, "decode_str": " Era"} -{"id": 21670, "token": "\u0120$_", "merges": "\u0120$ _", "raw_count": 1042, "count": 1042, "decode_str": " $_"} -{"id": 42019, "token": "\u0120deleterious", "merges": "\u0120deleter ious", "raw_count": 1043, "count": 1043, "decode_str": " deleterious"} -{"id": 23551, "token": "\u0120pathogenic", "merges": "\u0120path ogenic", "raw_count": 1043, "count": 1043, "decode_str": " pathogenic"} -{"id": 29915, "token": "\u0120Armstrong", "merges": "\u0120Arm strong", "raw_count": 1043, "count": 1043, "decode_str": " Armstrong"} -{"id": 32808, "token": "\u0120nitric", "merges": "\u0120nit ric", "raw_count": 1043, "count": 1043, "decode_str": " nitric"} -{"id": 27783, "token": "\u0120Barr", "merges": "\u0120B arr", "raw_count": 1043, "count": 1043, "decode_str": " Barr"} -{"id": 47342, "token": "\u0120eyebrow", "merges": "\u0120eyeb row", "raw_count": 1044, "count": 1044, "decode_str": " eyebrow"} -{"id": 7948, "token": "\u0120Tuesday", "merges": "\u0120T uesday", "raw_count": 1044, "count": 1044, "decode_str": " Tuesday"} -{"id": 30867, "token": "\u0120Fri", "merges": "\u0120F ri", "raw_count": 1044, "count": 1044, "decode_str": " Fri"} -{"id": 13069, "token": "\u00c5\u00a3", "merges": "\u00c5 \u00a3", "raw_count": 1008, "count": 1044, "decode_str": "\u0163"} -{"id": 23032, "token": "\u0120Imperial", "merges": "\u0120Im perial", "raw_count": 1045, "count": 1045, "decode_str": " Imperial"} -{"id": 42193, "token": "\u0120Fiction", "merges": "\u0120F iction", "raw_count": 1045, "count": 1045, "decode_str": " Fiction"} -{"id": 46018, "token": "\u0120Commod", "merges": "\u0120Com mod", "raw_count": 1045, "count": 1045, "decode_str": " Commod"} -{"id": 32974, "token": "\u0120Devil", "merges": "\u0120Dev il", "raw_count": 1045, "count": 1045, "decode_str": " Devil"} -{"id": 36490, "token": "\u0120familial", "merges": "\u0120famil ial", "raw_count": 1046, "count": 1046, "decode_str": " familial"} -{"id": 39783, "token": "\u0120screams", "merges": "\u0120sc reams", "raw_count": 1046, "count": 1046, "decode_str": " screams"} -{"id": 30521, "token": "\u0120Mend", "merges": "\u0120M end", "raw_count": 1046, "count": 1046, "decode_str": " Mend"} -{"id": 38608, "token": "\u0120Diss", "merges": "\u0120D iss", "raw_count": 1046, "count": 1046, "decode_str": " Diss"} -{"id": 43158, "token": "\u0120Crew", "merges": "\u0120C rew", "raw_count": 1046, "count": 1046, "decode_str": " Crew"} -{"id": 7780, "token": "}}{\\", "merges": "}} {\\", "raw_count": 1034, "count": 1046, "decode_str": "}}{\\"} -{"id": 47809, "token": "=================================", "merges": "================================ =", "raw_count": 1047, "count": 1047, "decode_str": "================================="} -{"id": 45264, "token": "\u0120arousal", "merges": "\u0120ar ousal", "raw_count": 1047, "count": 1047, "decode_str": " arousal"} -{"id": 44306, "token": "))/((", "merges": "))/ ((", "raw_count": 1047, "count": 1047, "decode_str": "))/(("} -{"id": 42216, "token": "\u0120Gob", "merges": "\u0120G ob", "raw_count": 1047, "count": 1047, "decode_str": " Gob"} -{"id": 36389, "token": "\u0120IJ", "merges": "\u0120I J", "raw_count": 1047, "count": 1047, "decode_str": " IJ"} -{"id": 41176, "token": "\u0120rhythms", "merges": "\u0120rhyth ms", "raw_count": 1048, "count": 1048, "decode_str": " rhythms"} -{"id": 44576, "token": "\u0120\u00d0\u00b3\u00d0\u00be\u00d0\u00b4", "merges": "\u0120\u00d0\u00b3 \u00d0\u00be\u00d0\u00b4", "raw_count": 1048, "count": 1048, "decode_str": " \u0433\u043e\u0434"} -{"id": 17384, "token": "ohist", "merges": "oh ist", "raw_count": 759, "count": 1049, "decode_str": "ohist"} -{"id": 29024, "token": "\u0120Trek", "merges": "\u0120Tre k", "raw_count": 1049, "count": 1049, "decode_str": " Trek"} -{"id": 20058, "token": "\u0120Together", "merges": "\u0120T ogether", "raw_count": 1050, "count": 1050, "decode_str": " Together"} -{"id": 50015, "token": "\u0120deceptive", "merges": "\u0120de ceptive", "raw_count": 1051, "count": 1051, "decode_str": " deceptive"} -{"id": 26738, "token": "\u0120knockout", "merges": "\u0120knock out", "raw_count": 1051, "count": 1051, "decode_str": " knockout"} -{"id": 49515, "token": "\u0120tangled", "merges": "\u0120tang led", "raw_count": 1051, "count": 1051, "decode_str": " tangled"} -{"id": 33555, "token": "\u0120pretreatment", "merges": "\u0120pret reatment", "raw_count": 1052, "count": 1052, "decode_str": " pretreatment"} -{"id": 49843, "token": "\u0120holographic", "merges": "\u0120holog raphic", "raw_count": 1052, "count": 1052, "decode_str": " holographic"} -{"id": 33821, "token": "\u0120Lauren", "merges": "\u0120Lau ren", "raw_count": 1052, "count": 1052, "decode_str": " Lauren"} -{"id": 12066, "token": "\u0120Viet", "merges": "\u0120V iet", "raw_count": 205, "count": 1052, "decode_str": " Viet"} -{"id": 46317, "token": "\u0120Alto", "merges": "\u0120Al to", "raw_count": 1052, "count": 1052, "decode_str": " Alto"} -{"id": 37379, "token": "\u0120contre", "merges": "\u0120cont re", "raw_count": 1053, "count": 1053, "decode_str": " contre"} -{"id": 18765, "token": "Though", "merges": "Th ough", "raw_count": 1053, "count": 1053, "decode_str": "Though"} -{"id": 19962, "token": "\u0120Swiss", "merges": "\u0120Sw iss", "raw_count": 1053, "count": 1053, "decode_str": " Swiss"} -{"id": 21442, "token": "polymers", "merges": "pol ymers", "raw_count": 1054, "count": 1054, "decode_str": "polymers"} -{"id": 17648, "token": "\u00cf\u0126\u00ce\u00b7", "merges": "\u00cf\u0126 \u00ce\u00b7", "raw_count": 953, "count": 1054, "decode_str": "\u03c4\u03b7"} -{"id": 43991, "token": "datepicker", "merges": "date picker", "raw_count": 1055, "count": 1055, "decode_str": "datepicker"} -{"id": 15420, "token": "\u0120Wales", "merges": "\u0120W ales", "raw_count": 1055, "count": 1055, "decode_str": " Wales"} -{"id": 204, "token": "\u011b", "merges": "NULL", "raw_count": 167, "count": 1055, "decode_str": "\u001b"} -{"id": 39778, "token": "\u0120conjugation", "merges": "\u0120conjug ation", "raw_count": 1056, "count": 1056, "decode_str": " conjugation"} -{"id": 31354, "token": "ningen", "merges": "ning en", "raw_count": 1056, "count": 1056, "decode_str": "ningen"} -{"id": 48023, "token": "\u0120\"$(", "merges": "\u0120\" $(", "raw_count": 1056, "count": 1056, "decode_str": " \"$("} -{"id": 42065, "token": "\u0120Electrical", "merges": "\u0120Elect rical", "raw_count": 1057, "count": 1057, "decode_str": " Electrical"} -{"id": 36448, "token": "\u0120causation", "merges": "\u0120caus ation", "raw_count": 1057, "count": 1057, "decode_str": " causation"} -{"id": 26420, "token": "\u0120solub", "merges": "\u0120sol ub", "raw_count": 101, "count": 1057, "decode_str": " solub"} -{"id": 14901, "token": "\u0120Turk", "merges": "\u0120Tur k", "raw_count": 557, "count": 1057, "decode_str": " Turk"} -{"id": 21664, "token": "\u0120Maur", "merges": "\u0120M aur", "raw_count": 539, "count": 1057, "decode_str": " Maur"} -{"id": 41884, "token": "\u0120Wii", "merges": "\u0120W ii", "raw_count": 1057, "count": 1057, "decode_str": " Wii"} -{"id": 50173, "token": "ocardial", "merges": "ocard ial", "raw_count": 1058, "count": 1058, "decode_str": "ocardial"} -{"id": 30330, "token": "\u0120Blues", "merges": "\u0120Bl ues", "raw_count": 1058, "count": 1058, "decode_str": " Blues"} -{"id": 24263, "token": "\u0120Penn", "merges": "\u0120P enn", "raw_count": 1058, "count": 1058, "decode_str": " Penn"} -{"id": 41540, "token": "\u0120Mang", "merges": "\u0120M ang", "raw_count": 1058, "count": 1058, "decode_str": " Mang"} -{"id": 47964, "token": "\u0120extremities", "merges": "\u0120extrem ities", "raw_count": 1059, "count": 1059, "decode_str": " extremities"} -{"id": 47233, "token": "\u0120conical", "merges": "\u0120con ical", "raw_count": 1059, "count": 1059, "decode_str": " conical"} -{"id": 40254, "token": "\u0120Corporate", "merges": "\u0120Corpor ate", "raw_count": 1060, "count": 1060, "decode_str": " Corporate"} -{"id": 49544, "token": "\u0120Feng", "merges": "\u0120F eng", "raw_count": 1060, "count": 1060, "decode_str": " Feng"} -{"id": 17317, "token": "\u0120\u00c3\u012b", "merges": "\u0120\u00c3 \u012b", "raw_count": 1020, "count": 1060, "decode_str": " \u00c9"} -{"id": 16254, "token": "\u0120placebo", "merges": "\u0120place bo", "raw_count": 1061, "count": 1061, "decode_str": " placebo"} -{"id": 27874, "token": "\u0120Remark", "merges": "\u0120Rem ark", "raw_count": 1061, "count": 1061, "decode_str": " Remark"} -{"id": 44485, "token": "\u0120Rent", "merges": "\u0120R ent", "raw_count": 1061, "count": 1061, "decode_str": " Rent"} -{"id": 38632, "token": "ubicin", "merges": "ub icin", "raw_count": 1022, "count": 1062, "decode_str": "ubicin"} -{"id": 41033, "token": "\u0120suppresses", "merges": "\u0120suppress es", "raw_count": 1063, "count": 1063, "decode_str": " suppresses"} -{"id": 16650, "token": "\u0120Fourth", "merges": "\u0120Four th", "raw_count": 1063, "count": 1063, "decode_str": " Fourth"} -{"id": 50051, "token": "\u0120Yuan", "merges": "\u0120Y uan", "raw_count": 1063, "count": 1063, "decode_str": " Yuan"} -{"id": 35127, "token": "\u00c3\u00b6m", "merges": "\u00c3\u00b6 m", "raw_count": 327, "count": 1063, "decode_str": "\u00f6m"} -{"id": 40889, "token": "\u0120asshole", "merges": "\u0120ass hole", "raw_count": 1065, "count": 1065, "decode_str": " asshole"} -{"id": 10044, "token": "\u0120\u00c3\u00ae", "merges": "\u0120\u00c3 \u00ae", "raw_count": 755, "count": 1065, "decode_str": " \u00ee"} -{"id": 46520, "token": "\u0120\u00c5\u013d", "merges": "\u0120\u00c5 \u013d", "raw_count": 1065, "count": 1065, "decode_str": " \u015b"} -{"id": 535, "token": "\u010a\u010a", "merges": "\u010a \u010a", "raw_count": 1062, "count": 1065, "decode_str": "\n\n"} -{"id": 43173, "token": "\u0120calves", "merges": "\u0120cal ves", "raw_count": 1066, "count": 1066, "decode_str": " calves"} -{"id": 24942, "token": "\u0120Foster", "merges": "\u0120F oster", "raw_count": 1066, "count": 1066, "decode_str": " Foster"} -{"id": 46121, "token": "GRect", "merges": "GR ect", "raw_count": 1066, "count": 1066, "decode_str": "GRect"} -{"id": 22787, "token": "\u0120Carm", "merges": "\u0120C arm", "raw_count": 1066, "count": 1066, "decode_str": " Carm"} -{"id": 6827, "token": "\u0120Mrs", "merges": "\u0120Mr s", "raw_count": 1066, "count": 1066, "decode_str": " Mrs"} -{"id": 22024, "token": "\u0120Shakespeare", "merges": "\u0120Sh akespeare", "raw_count": 1067, "count": 1067, "decode_str": " Shakespeare"} -{"id": 36046, "token": "\u0120disordered", "merges": "\u0120dis ordered", "raw_count": 1067, "count": 1067, "decode_str": " disordered"} -{"id": 40706, "token": "\u0120Telesc", "merges": "\u0120T elesc", "raw_count": 45, "count": 1067, "decode_str": " Telesc"} -{"id": 32612, "token": "c\u00c3\u00a9", "merges": "c \u00c3\u00a9", "raw_count": 1067, "count": 1067, "decode_str": "c\u00e9"} -{"id": 30297, "token": "\u0120edema", "merges": "\u0120ed ema", "raw_count": 1068, "count": 1068, "decode_str": " edema"} -{"id": 32203, "token": "\u0120Lor", "merges": "\u0120L or", "raw_count": 1068, "count": 1068, "decode_str": " Lor"} -{"id": 44730, "token": "\u0120skepticism", "merges": "\u0120skeptic ism", "raw_count": 1069, "count": 1069, "decode_str": " skepticism"} -{"id": 46444, "token": "\u0120Ranger", "merges": "\u0120R anger", "raw_count": 1069, "count": 1069, "decode_str": " Ranger"} -{"id": 28589, "token": "\u0120Lynch", "merges": "\u0120Lyn ch", "raw_count": 1069, "count": 1069, "decode_str": " Lynch"} -{"id": 28547, "token": "\u0120noch", "merges": "\u0120no ch", "raw_count": 1069, "count": 1069, "decode_str": " noch"} -{"id": 48271, "token": "\u0120Dip", "merges": "\u0120D ip", "raw_count": 1069, "count": 1069, "decode_str": " Dip"} -{"id": 12464, "token": "\u0120Lett", "merges": "\u0120Let t", "raw_count": 1070, "count": 1070, "decode_str": " Lett"} -{"id": 27470, "token": "\u0120FCC", "merges": "\u0120F CC", "raw_count": 1070, "count": 1070, "decode_str": " FCC"} -{"id": 27456, "token": "\u0120Nuclear", "merges": "\u0120N uclear", "raw_count": 1071, "count": 1071, "decode_str": " Nuclear"} -{"id": 41362, "token": "\u0120debuted", "merges": "\u0120debut ed", "raw_count": 1071, "count": 1071, "decode_str": " debuted"} -{"id": 49145, "token": "\u0120coy", "merges": "\u0120co y", "raw_count": 1071, "count": 1071, "decode_str": " coy"} -{"id": 45486, "token": "chrotron", "merges": "chro tron", "raw_count": 1072, "count": 1072, "decode_str": "chrotron"} -{"id": 47409, "token": "\u0120CAB", "merges": "\u0120C AB", "raw_count": 1072, "count": 1072, "decode_str": " CAB"} -{"id": 30850, "token": "oietic", "merges": "oi etic", "raw_count": 64, "count": 1073, "decode_str": "oietic"} -{"id": 24395, "token": "\u0120Lloyd", "merges": "\u0120Ll oyd", "raw_count": 1073, "count": 1073, "decode_str": " Lloyd"} -{"id": 27917, "token": "\u0120Chase", "merges": "\u0120Ch ase", "raw_count": 1073, "count": 1073, "decode_str": " Chase"} -{"id": 21710, "token": "\u0120Clay", "merges": "\u0120Cl ay", "raw_count": 697, "count": 1073, "decode_str": " Clay"} -{"id": 39308, "token": "\u0120Crisis", "merges": "\u0120Cris is", "raw_count": 1074, "count": 1074, "decode_str": " Crisis"} -{"id": 14439, "token": "\u00cf\u0126\u00ce\u00b1", "merges": "\u00cf\u0126 \u00ce\u00b1", "raw_count": 1074, "count": 1074, "decode_str": "\u03c4\u03b1"} -{"id": 49788, "token": "\u00d9\u012a\u00d8\u00af", "merges": "\u00d9\u012a \u00d8\u00af", "raw_count": 1074, "count": 1074, "decode_str": "\u0648\u062f"} -{"id": 49373, "token": "\u0120manipulations", "merges": "\u0120manip ulations", "raw_count": 1075, "count": 1075, "decode_str": " manipulations"} -{"id": 47292, "token": "Alright", "merges": "Al right", "raw_count": 1075, "count": 1075, "decode_str": "Alright"} -{"id": 38797, "token": "\u0120Planck", "merges": "\u0120Plan ck", "raw_count": 1075, "count": 1075, "decode_str": " Planck"} -{"id": 27286, "token": "\u0120Powell", "merges": "\u0120Pow ell", "raw_count": 1075, "count": 1075, "decode_str": " Powell"} -{"id": 38047, "token": "\u0120postnatal", "merges": "\u0120post natal", "raw_count": 1076, "count": 1076, "decode_str": " postnatal"} -{"id": 45960, "token": "\u0120hardcore", "merges": "\u0120hard core", "raw_count": 1076, "count": 1076, "decode_str": " hardcore"} -{"id": 8118, "token": "\u0120African", "merges": "\u0120Afric an", "raw_count": 1076, "count": 1076, "decode_str": " African"} -{"id": 41476, "token": "ovial", "merges": "ov ial", "raw_count": 1076, "count": 1076, "decode_str": "ovial"} -{"id": 7628, "token": "}=\\", "merges": "} =\\", "raw_count": 1077, "count": 1077, "decode_str": "}=\\"} -{"id": 52364, "token": "\u00e6\u00a8\u0133", "merges": "\u00e6\u00a8 \u0133", "raw_count": 1077, "count": 1077, "decode_str": "\u6a11"} -{"id": 13355, "token": "\u0120$.", "merges": "\u0120$ .", "raw_count": 1077, "count": 1077, "decode_str": " $."} -{"id": 27811, "token": "\u0120Commercial", "merges": "\u0120Com mercial", "raw_count": 1078, "count": 1078, "decode_str": " Commercial"} -{"id": 23325, "token": "\u0120Crime", "merges": "\u0120Cr ime", "raw_count": 1078, "count": 1078, "decode_str": " Crime"} -{"id": 46399, "token": "\u0120sectional", "merges": "\u0120section al", "raw_count": 1079, "count": 1079, "decode_str": " sectional"} -{"id": 32286, "token": "\u0120Theater", "merges": "\u0120The ater", "raw_count": 1079, "count": 1079, "decode_str": " Theater"} -{"id": 30066, "token": "\u0120SARS", "merges": "\u0120S ARS", "raw_count": 1079, "count": 1079, "decode_str": " SARS"} -{"id": 41659, "token": "\u0120Ply", "merges": "\u0120P ly", "raw_count": 1004, "count": 1079, "decode_str": " Ply"} -{"id": 35281, "token": "\u0120bullshit", "merges": "\u0120bull shit", "raw_count": 1080, "count": 1080, "decode_str": " bullshit"} -{"id": 39398, "token": "\u0120Belt", "merges": "\u0120B elt", "raw_count": 1080, "count": 1080, "decode_str": " Belt"} -{"id": 44341, "token": "\u0120MDR", "merges": "\u0120M DR", "raw_count": 1080, "count": 1080, "decode_str": " MDR"} -{"id": 47268, "token": "\u0120chicks", "merges": "\u0120ch icks", "raw_count": 1081, "count": 1081, "decode_str": " chicks"} -{"id": 48428, "token": "\u0120trat", "merges": "\u0120tr at", "raw_count": 1081, "count": 1081, "decode_str": " trat"} -{"id": 34518, "token": "\u0120FBS", "merges": "\u0120F BS", "raw_count": 1081, "count": 1081, "decode_str": " FBS"} -{"id": 36716, "token": "\u0120cirrhosis", "merges": "\u0120cirrh osis", "raw_count": 1082, "count": 1082, "decode_str": " cirrhosis"} -{"id": 31172, "token": "\u0120elongated", "merges": "\u0120elong ated", "raw_count": 1082, "count": 1082, "decode_str": " elongated"} -{"id": 37464, "token": "\u0120morphine", "merges": "\u0120morph ine", "raw_count": 1083, "count": 1083, "decode_str": " morphine"} -{"id": 31541, "token": "\u0120Chicken", "merges": "\u0120Ch icken", "raw_count": 1083, "count": 1083, "decode_str": " Chicken"} -{"id": 48884, "token": "\u0120Cruise", "merges": "\u0120Cru ise", "raw_count": 1083, "count": 1083, "decode_str": " Cruise"} -{"id": 33932, "token": "\u0120Rust", "merges": "\u0120R ust", "raw_count": 1083, "count": 1083, "decode_str": " Rust"} -{"id": 48877, "token": "\u0120Lal", "merges": "\u0120L al", "raw_count": 1083, "count": 1083, "decode_str": " Lal"} -{"id": 4820, "token": "operatorname", "merges": "operator name", "raw_count": 1084, "count": 1084, "decode_str": "operatorname"} -{"id": 41111, "token": "\u0120frivolous", "merges": "\u0120f rivolous", "raw_count": 1084, "count": 1084, "decode_str": " frivolous"} -{"id": 34835, "token": "\u0120lineages", "merges": "\u0120line ages", "raw_count": 1084, "count": 1084, "decode_str": " lineages"} -{"id": 27320, "token": "\u0120nucleic", "merges": "\u0120nucle ic", "raw_count": 1084, "count": 1084, "decode_str": " nucleic"} -{"id": 39131, "token": "\u0120Gott", "merges": "\u0120G ott", "raw_count": 1084, "count": 1084, "decode_str": " Gott"} -{"id": 45724, "token": "\u0120Pole", "merges": "\u0120P ole", "raw_count": 1084, "count": 1084, "decode_str": " Pole"} -{"id": 16874, "token": "\u0120Cruz", "merges": "\u0120Cru z", "raw_count": 1084, "count": 1084, "decode_str": " Cruz"} -{"id": 34120, "token": "\u0120Ein", "merges": "\u0120E in", "raw_count": 1084, "count": 1084, "decode_str": " Ein"} -{"id": 25769, "token": "\u0120\u00c2\u00bf", "merges": "\u0120\u00c2 \u00bf", "raw_count": 1084, "count": 1084, "decode_str": " \u00bf"} -{"id": 40860, "token": "\u0120midfield", "merges": "\u0120mid field", "raw_count": 1085, "count": 1085, "decode_str": " midfield"} -{"id": 25968, "token": "\u0120Butler", "merges": "\u0120But ler", "raw_count": 1085, "count": 1085, "decode_str": " Butler"} -{"id": 43472, "token": "Prefab", "merges": "Pref ab", "raw_count": 1085, "count": 1085, "decode_str": "Prefab"} -{"id": 24103, "token": "\u0120Fitz", "merges": "\u0120F itz", "raw_count": 639, "count": 1085, "decode_str": " Fitz"} -{"id": 24986, "token": "\u0120Kos", "merges": "\u0120K os", "raw_count": 1013, "count": 1085, "decode_str": " Kos"} -{"id": 143, "token": "\u00d3", "merges": "NULL", "raw_count": 1085, "count": 1085, "decode_str": "\ufffd"} -{"id": 155, "token": "\u00df", "merges": "NULL", "raw_count": 1085, "count": 1085, "decode_str": "\ufffd"} -{"id": 37864, "token": "\u0120ligament", "merges": "\u0120lig ament", "raw_count": 1086, "count": 1086, "decode_str": " ligament"} -{"id": 23423, "token": "\u0120follic", "merges": "\u0120fol lic", "raw_count": 627, "count": 1086, "decode_str": " follic"} -{"id": 50019, "token": "iella", "merges": "i ella", "raw_count": 1086, "count": 1086, "decode_str": "iella"} -{"id": 45967, "token": "\u0120hemp", "merges": "\u0120he mp", "raw_count": 1086, "count": 1086, "decode_str": " hemp"} -{"id": 37901, "token": "\u0120Nem", "merges": "\u0120N em", "raw_count": 1086, "count": 1086, "decode_str": " Nem"} -{"id": 49058, "token": "\u0120annoyance", "merges": "\u0120annoy ance", "raw_count": 1087, "count": 1087, "decode_str": " annoyance"} -{"id": 21836, "token": "\u0120Whatever", "merges": "\u0120Wh atever", "raw_count": 1087, "count": 1087, "decode_str": " Whatever"} -{"id": 42109, "token": "\u0120fists", "merges": "\u0120f ists", "raw_count": 1087, "count": 1087, "decode_str": " fists"} -{"id": 13668, "token": "$^{-", "merges": "$ ^{-", "raw_count": 1087, "count": 1087, "decode_str": "$^{-"} -{"id": 42509, "token": "\u0120shootings", "merges": "\u0120shoot ings", "raw_count": 1088, "count": 1088, "decode_str": " shootings"} -{"id": 19621, "token": "\u0120\u00d8\u00a7\u00d9\u0126\u00d8", "merges": "\u0120\u00d8\u00a7\u00d9\u0126 \u00d8", "raw_count": 933, "count": 1088, "decode_str": " \u0627\u0644\ufffd"} -{"id": 8842, "token": "\u0120Cath", "merges": "\u0120C ath", "raw_count": 496, "count": 1088, "decode_str": " Cath"} -{"id": 32780, "token": "\u0120PEG", "merges": "\u0120PE G", "raw_count": 1088, "count": 1088, "decode_str": " PEG"} -{"id": 27221, "token": "\u0120decays", "merges": "\u0120dec ays", "raw_count": 1089, "count": 1089, "decode_str": " decays"} -{"id": 23900, "token": "\u0120Kre", "merges": "\u0120K re", "raw_count": 1046, "count": 1089, "decode_str": " Kre"} -{"id": 17186, "token": "\u00cf\u0125\u00ce\u00b7", "merges": "\u00cf\u0125 \u00ce\u00b7", "raw_count": 876, "count": 1090, "decode_str": "\u03c3\u03b7"} -{"id": 26117, "token": "\u0120Municip", "merges": "\u0120M unicip", "raw_count": 636, "count": 1091, "decode_str": " Municip"} -{"id": 19046, "token": "\u0120Benjamin", "merges": "\u0120Ben jamin", "raw_count": 1092, "count": 1092, "decode_str": " Benjamin"} -{"id": 35003, "token": "\u0120peeled", "merges": "\u0120pe eled", "raw_count": 1092, "count": 1092, "decode_str": " peeled"} -{"id": 34130, "token": "\u0120ABOUT", "merges": "\u0120AB OUT", "raw_count": 1092, "count": 1092, "decode_str": " ABOUT"} -{"id": 37838, "token": "\u0120Frost", "merges": "\u0120F rost", "raw_count": 1092, "count": 1092, "decode_str": " Frost"} -{"id": 18117, "token": "\u0120dass", "merges": "\u0120d ass", "raw_count": 1092, "count": 1092, "decode_str": " dass"} -{"id": 32580, "token": "\u0120Ges", "merges": "\u0120G es", "raw_count": 1092, "count": 1092, "decode_str": " Ges"} -{"id": 34341, "token": "\u0120\u00d8\u00b3", "merges": "\u0120\u00d8 \u00b3", "raw_count": 1092, "count": 1092, "decode_str": " \u0633"} -{"id": 34663, "token": "\u0120chemically", "merges": "\u0120chem ically", "raw_count": 1093, "count": 1093, "decode_str": " chemically"} -{"id": 44317, "token": "\u0120dehydr", "merges": "\u0120de hydr", "raw_count": 1093, "count": 1093, "decode_str": " dehydr"} -{"id": 16404, "token": "\u0120Brief", "merges": "\u0120B rief", "raw_count": 1037, "count": 1093, "decode_str": " Brief"} -{"id": 39984, "token": "\u00e3\u0123\u013f\u00e3\u0124\u012e", "merges": "\u00e3\u0123\u013f \u00e3\u0124\u012e", "raw_count": 1093, "count": 1093, "decode_str": "\u305d\u308c"} -{"id": 41966, "token": "\u0120Refs", "merges": "\u0120Ref s", "raw_count": 1093, "count": 1093, "decode_str": " Refs"} -{"id": 43512, "token": "\u0120NOTICE", "merges": "\u0120NOT ICE", "raw_count": 1094, "count": 1094, "decode_str": " NOTICE"} -{"id": 39508, "token": "\u0120undergoes", "merges": "\u0120undergo es", "raw_count": 1095, "count": 1095, "decode_str": " undergoes"} -{"id": 31821, "token": "erably", "merges": "er ably", "raw_count": 1095, "count": 1095, "decode_str": "erably"} -{"id": 39692, "token": "\u00e3\u0124\u012b\u00e3\u0124\u012e", "merges": "\u00e3\u0124\u012b \u00e3\u0124\u012e", "raw_count": 1095, "count": 1095, "decode_str": "\u3089\u308c"} -{"id": 35187, "token": "\u0120scint", "merges": "\u0120sc int", "raw_count": 1095, "count": 1095, "decode_str": " scint"} -{"id": 27972, "token": "\u0120correlates", "merges": "\u0120correl ates", "raw_count": 1096, "count": 1096, "decode_str": " correlates"} -{"id": 38734, "token": "\u0120Friedman", "merges": "\u0120Fried man", "raw_count": 1096, "count": 1096, "decode_str": " Friedman"} -{"id": 29411, "token": "\u0120etching", "merges": "\u0120et ching", "raw_count": 1096, "count": 1096, "decode_str": " etching"} -{"id": 36313, "token": "\u00e3\u0123\u0126\u00e3\u0123\u00a6", "merges": "\u00e3\u0123\u0126 \u00e3\u0123\u00a6", "raw_count": 1096, "count": 1096, "decode_str": "\u3044\u3066"} -{"id": 44241, "token": "=$(", "merges": "= $(", "raw_count": 1096, "count": 1096, "decode_str": "=$("} -{"id": 49298, "token": "\u0120percussion", "merges": "\u0120perc ussion", "raw_count": 1097, "count": 1097, "decode_str": " percussion"} -{"id": 44061, "token": "\u0120flic", "merges": "\u0120f lic", "raw_count": 1097, "count": 1097, "decode_str": " flic"} -{"id": 32940, "token": "conjugated", "merges": "conjug ated", "raw_count": 1098, "count": 1098, "decode_str": "conjugated"} -{"id": 17138, "token": "\u0120Appendix", "merges": "\u0120App endix", "raw_count": 1098, "count": 1098, "decode_str": " Appendix"} -{"id": 41921, "token": "\u0120Eu", "merges": "\u0120E u", "raw_count": 1098, "count": 1098, "decode_str": " Eu"} -{"id": 42063, "token": "\u00e0\u00a7\u012f", "merges": "\u00e0\u00a7 \u012f", "raw_count": 1098, "count": 1098, "decode_str": "\u09cd"} -{"id": 34640, "token": "monella", "merges": "mon ella", "raw_count": 330, "count": 1099, "decode_str": "monella"} -{"id": 28182, "token": "\u0120Papers", "merges": "\u0120P apers", "raw_count": 1099, "count": 1099, "decode_str": " Papers"} -{"id": 41272, "token": "atosis", "merges": "at osis", "raw_count": 1099, "count": 1099, "decode_str": "atosis"} -{"id": 21122, "token": "\u0120Jerry", "merges": "\u0120Jer ry", "raw_count": 1099, "count": 1099, "decode_str": " Jerry"} -{"id": 13637, "token": "\u0120cultured", "merges": "\u0120cult ured", "raw_count": 1100, "count": 1100, "decode_str": " cultured"} -{"id": 34294, "token": "\u0120Therapy", "merges": "\u0120The rapy", "raw_count": 1100, "count": 1100, "decode_str": " Therapy"} -{"id": 49781, "token": "\u0120glances", "merges": "\u0120gl ances", "raw_count": 1100, "count": 1100, "decode_str": " glances"} -{"id": 13936, "token": "\u0120Holy", "merges": "\u0120Hol y", "raw_count": 1100, "count": 1100, "decode_str": " Holy"} -{"id": 14913, "token": "\u0120Duke", "merges": "\u0120Du ke", "raw_count": 1100, "count": 1100, "decode_str": " Duke"} -{"id": 45140, "token": "\u0120puncture", "merges": "\u0120punct ure", "raw_count": 1101, "count": 1101, "decode_str": " puncture"} -{"id": 49355, "token": "\u0120commentator", "merges": "\u0120comment ator", "raw_count": 1103, "count": 1103, "decode_str": " commentator"} -{"id": 39664, "token": "\u0120Instruments", "merges": "\u0120Instr uments", "raw_count": 1103, "count": 1103, "decode_str": " Instruments"} -{"id": 12746, "token": "\u0120Columbia", "merges": "\u0120Columb ia", "raw_count": 1103, "count": 1103, "decode_str": " Columbia"} -{"id": 27464, "token": "\u0120Revenue", "merges": "\u0120Rev enue", "raw_count": 1103, "count": 1103, "decode_str": " Revenue"} -{"id": 47781, "token": "\u0120blasted", "merges": "\u0120bl asted", "raw_count": 1103, "count": 1103, "decode_str": " blasted"} -{"id": 39375, "token": "\u0120microp", "merges": "\u0120mic rop", "raw_count": 1103, "count": 1103, "decode_str": " microp"} -{"id": 42712, "token": "\u0120Truck", "merges": "\u0120Tru ck", "raw_count": 1103, "count": 1103, "decode_str": " Truck"} -{"id": 30014, "token": "\u0120Berry", "merges": "\u0120Ber ry", "raw_count": 1103, "count": 1103, "decode_str": " Berry"} -{"id": 49556, "token": "\u0120clon", "merges": "\u0120cl on", "raw_count": 1103, "count": 1103, "decode_str": " clon"} -{"id": 36652, "token": "\u0120Lum", "merges": "\u0120L um", "raw_count": 1103, "count": 1103, "decode_str": " Lum"} -{"id": 32112, "token": "\u0120elicited", "merges": "\u0120elic ited", "raw_count": 1104, "count": 1104, "decode_str": " elicited"} -{"id": 39814, "token": "\u0120nella", "merges": "\u0120n ella", "raw_count": 1104, "count": 1104, "decode_str": " nella"} -{"id": 48968, "token": "\u0120Wien", "merges": "\u0120W ien", "raw_count": 1104, "count": 1104, "decode_str": " Wien"} -{"id": 31750, "token": "\u0120\u00cf\u0128", "merges": "\u0120 \u00cf\u0128", "raw_count": 1104, "count": 1104, "decode_str": " \u03c6"} -{"id": 45476, "token": "\u00d1\u0123\u00d1\u0124\u00d0\u00b2\u00d0\u00b5\u00d0\u00bd", "merges": "\u00d1\u0123\u00d1\u0124\u00d0\u00b2 \u00d0\u00b5\u00d0\u00bd", "raw_count": 1105, "count": 1105, "decode_str": "\u0441\u0442\u0432\u0435\u043d"} -{"id": 32705, "token": "\u0120Companies", "merges": "\u0120Compan ies", "raw_count": 1105, "count": 1105, "decode_str": " Companies"} -{"id": 19187, "token": "\u0120resection", "merges": "\u0120rese ction", "raw_count": 1105, "count": 1105, "decode_str": " resection"} -{"id": 39184, "token": "\u0120Genesis", "merges": "\u0120Gen esis", "raw_count": 1105, "count": 1105, "decode_str": " Genesis"} -{"id": 47493, "token": "\u0120Introdu", "merges": "\u0120Int rodu", "raw_count": 1105, "count": 1105, "decode_str": " Introdu"} -{"id": 39059, "token": "opropyl", "merges": "oprop yl", "raw_count": 1105, "count": 1105, "decode_str": "opropyl"} -{"id": 32419, "token": "uitary", "merges": "uit ary", "raw_count": 445, "count": 1105, "decode_str": "uitary"} -{"id": 26079, "token": "\u0120Bund", "merges": "\u0120B und", "raw_count": 825, "count": 1105, "decode_str": " Bund"} -{"id": 23845, "token": "\u0120Diet", "merges": "\u0120D iet", "raw_count": 1105, "count": 1105, "decode_str": " Diet"} -{"id": 43778, "token": "\u0120comedian", "merges": "\u0120comed ian", "raw_count": 1106, "count": 1106, "decode_str": " comedian"} -{"id": 26165, "token": "\u0120Bh", "merges": "\u0120B h", "raw_count": 1106, "count": 1106, "decode_str": " Bh"} -{"id": 41166, "token": "\u0120Employees", "merges": "\u0120Employ ees", "raw_count": 1107, "count": 1107, "decode_str": " Employees"} -{"id": 23091, "token": "\u0120Princess", "merges": "\u0120Pr incess", "raw_count": 1107, "count": 1107, "decode_str": " Princess"} -{"id": 36969, "token": "\u0120Vacc", "merges": "\u0120V acc", "raw_count": 1107, "count": 1107, "decode_str": " Vacc"} -{"id": 42048, "token": "\u0120toda", "merges": "\u0120to da", "raw_count": 1107, "count": 1107, "decode_str": " toda"} -{"id": 42828, "token": "\u0120Kang", "merges": "\u0120K ang", "raw_count": 1107, "count": 1107, "decode_str": " Kang"} -{"id": 39194, "token": "\u0120Raz", "merges": "\u0120R az", "raw_count": 1107, "count": 1107, "decode_str": " Raz"} -{"id": 35718, "token": "\u00c2\u00b0,", "merges": "\u00c2\u00b0 ,", "raw_count": 1107, "count": 1107, "decode_str": "\u00b0,"} -{"id": 36143, "token": "\u0120qualitatively", "merges": "\u0120qual itatively", "raw_count": 1108, "count": 1108, "decode_str": " qualitatively"} -{"id": 21741, "token": "\u0120Murphy", "merges": "\u0120Mur phy", "raw_count": 1108, "count": 1108, "decode_str": " Murphy"} -{"id": 47315, "token": "\u0120Poetry", "merges": "\u0120Po etry", "raw_count": 1108, "count": 1108, "decode_str": " Poetry"} -{"id": 45146, "token": "orbent", "merges": "orb ent", "raw_count": 1108, "count": 1108, "decode_str": "orbent"} -{"id": 45049, "token": "asmod", "merges": "as mod", "raw_count": 1108, "count": 1108, "decode_str": "asmod"} -{"id": 27627, "token": "\u0120aneurys", "merges": "\u0120aneur ys", "raw_count": 339, "count": 1109, "decode_str": " aneurys"} -{"id": 41931, "token": "\u0120Floyd", "merges": "\u0120Fl oyd", "raw_count": 1109, "count": 1109, "decode_str": " Floyd"} -{"id": 35412, "token": "\u0120Clin", "merges": "\u0120Cl in", "raw_count": 1109, "count": 1109, "decode_str": " Clin"} -{"id": 32962, "token": "\u0120Dawn", "merges": "\u0120Da wn", "raw_count": 1109, "count": 1109, "decode_str": " Dawn"} -{"id": 32739, "token": "\u0120urea", "merges": "\u0120ure a", "raw_count": 1109, "count": 1109, "decode_str": " urea"} -{"id": 28214, "token": "\u0120Mountains", "merges": "\u0120Mount ains", "raw_count": 1110, "count": 1110, "decode_str": " Mountains"} -{"id": 32500, "token": "\u0120SPSS", "merges": "\u0120S PSS", "raw_count": 1110, "count": 1110, "decode_str": " SPSS"} -{"id": 29459, "token": "\u0120Neu", "merges": "\u0120Ne u", "raw_count": 1110, "count": 1110, "decode_str": " Neu"} -{"id": 36113, "token": "\u0120Dw", "merges": "\u0120D w", "raw_count": 1110, "count": 1110, "decode_str": " Dw"} -{"id": 39000, "token": "$}", "merges": "$ }", "raw_count": 1110, "count": 1110, "decode_str": "$}"} -{"id": 47920, "token": "\u0120vibrational", "merges": "\u0120vibr ational", "raw_count": 1111, "count": 1111, "decode_str": " vibrational"} -{"id": 31903, "token": "\u0120Manuel", "merges": "\u0120Man uel", "raw_count": 1111, "count": 1111, "decode_str": " Manuel"} -{"id": 35018, "token": "\u0120Comics", "merges": "\u0120Com ics", "raw_count": 1111, "count": 1111, "decode_str": " Comics"} -{"id": 30374, "token": "\u0120abundances", "merges": "\u0120abund ances", "raw_count": 1112, "count": 1112, "decode_str": " abundances"} -{"id": 39383, "token": "\u0120theorems", "merges": "\u0120the orems", "raw_count": 1112, "count": 1112, "decode_str": " theorems"} -{"id": 20931, "token": "\u0120Benn", "merges": "\u0120B enn", "raw_count": 345, "count": 1112, "decode_str": " Benn"} -{"id": 24006, "token": "\u0120Edwards", "merges": "\u0120Ed wards", "raw_count": 1113, "count": 1113, "decode_str": " Edwards"} -{"id": 46016, "token": "\u00e3\u0123\u0139\u00e3\u0123\u0126", "merges": "\u00e3\u0123\u0139 \u00e3\u0123\u0126", "raw_count": 1113, "count": 1113, "decode_str": "\u3057\u3044"} -{"id": 44648, "token": "\u0120v\u00c3\u00a1", "merges": "\u0120v \u00c3\u00a1", "raw_count": 1113, "count": 1113, "decode_str": " v\u00e1"} -{"id": 31466, "token": "\u0120Interview", "merges": "\u0120Inter view", "raw_count": 1114, "count": 1114, "decode_str": " Interview"} -{"id": 28618, "token": "\u0120pentru", "merges": "\u0120pent ru", "raw_count": 1114, "count": 1114, "decode_str": " pentru"} -{"id": 32122, "token": "\u0120trache", "merges": "\u0120tr ache", "raw_count": 1114, "count": 1114, "decode_str": " trache"} -{"id": 13986, "token": "\u0120Dutch", "merges": "\u0120D utch", "raw_count": 1114, "count": 1114, "decode_str": " Dutch"} -{"id": 18151, "token": "poons", "merges": "po ons", "raw_count": 347, "count": 1114, "decode_str": "poons"} -{"id": 43054, "token": "\u0120leth", "merges": "\u0120le th", "raw_count": 1114, "count": 1114, "decode_str": " leth"} -{"id": 12388, "token": "\u00ce\u00b9\u00ce\u00ba", "merges": "\u00ce\u00b9 \u00ce\u00ba", "raw_count": 775, "count": 1114, "decode_str": "\u03b9\u03ba"} -{"id": 35117, "token": ".[^", "merges": ".[ ^", "raw_count": 1114, "count": 1114, "decode_str": ".[^"} -{"id": 38428, "token": "aphylococcus", "merges": "aphyl ococcus", "raw_count": 1115, "count": 1115, "decode_str": "aphylococcus"} -{"id": 50169, "token": "\u00e3\u0123\u00a3\u00e3\u0123\u00a6\u00e3\u0123\u0126\u00e3\u0124\u012d", "merges": "\u00e3\u0123\u00a3 \u00e3\u0123\u00a6\u00e3\u0123\u0126\u00e3\u0124\u012d", "raw_count": 1115, "count": 1115, "decode_str": "\u3063\u3066\u3044\u308b"} -{"id": 17966, "token": "\u0120Warren", "merges": "\u0120War ren", "raw_count": 1115, "count": 1115, "decode_str": " Warren"} -{"id": 19147, "token": "\u0120abnormalities", "merges": "\u0120abnormal ities", "raw_count": 1116, "count": 1116, "decode_str": " abnormalities"} -{"id": 41398, "token": "\u0120analytically", "merges": "\u0120analyt ically", "raw_count": 1116, "count": 1116, "decode_str": " analytically"} -{"id": 25554, "token": "ocarcinoma", "merges": "ocarcin oma", "raw_count": 749, "count": 1116, "decode_str": "ocarcinoma"} -{"id": 42632, "token": "acrylamide", "merges": "acry lamide", "raw_count": 1116, "count": 1116, "decode_str": "acrylamide"} -{"id": 43646, "token": "\u0120Guarant", "merges": "\u0120Gu arant", "raw_count": 1116, "count": 1116, "decode_str": " Guarant"} -{"id": 24777, "token": "\u0120Hb", "merges": "\u0120H b", "raw_count": 952, "count": 1116, "decode_str": " Hb"} -{"id": 27523, "token": "\u0120Reynolds", "merges": "\u0120Reyn olds", "raw_count": 1118, "count": 1118, "decode_str": " Reynolds"} -{"id": 45671, "token": "\u0120craving", "merges": "\u0120cra ving", "raw_count": 1118, "count": 1118, "decode_str": " craving"} -{"id": 42154, "token": "\u0120spinach", "merges": "\u0120spin ach", "raw_count": 1118, "count": 1118, "decode_str": " spinach"} -{"id": 44591, "token": "\u0120Hammer", "merges": "\u0120Ham mer", "raw_count": 1118, "count": 1118, "decode_str": " Hammer"} -{"id": 36780, "token": "\u0120PDE", "merges": "\u0120P DE", "raw_count": 1118, "count": 1118, "decode_str": " PDE"} -{"id": 43090, "token": "\u0120------------------------------", "merges": "\u0120---------------- --------------", "raw_count": 1119, "count": 1119, "decode_str": " ------------------------------"} -{"id": 31105, "token": "\u0120impeachment", "merges": "\u0120impe achment", "raw_count": 1119, "count": 1119, "decode_str": " impeachment"} -{"id": 48353, "token": "\u0120filmmakers", "merges": "\u0120filmm akers", "raw_count": 1119, "count": 1119, "decode_str": " filmmakers"} -{"id": 36345, "token": "\u0120Excell", "merges": "\u0120Ex cell", "raw_count": 349, "count": 1119, "decode_str": " Excell"} -{"id": 40882, "token": "\u0120phonon", "merges": "\u0120phon on", "raw_count": 1119, "count": 1119, "decode_str": " phonon"} -{"id": 41438, "token": "\u0120Hair", "merges": "\u0120H air", "raw_count": 1119, "count": 1119, "decode_str": " Hair"} -{"id": 28231, "token": "}[\\", "merges": "} [\\", "raw_count": 1119, "count": 1119, "decode_str": "}[\\"} -{"id": 47567, "token": "\u0120tutti", "merges": "\u0120tut ti", "raw_count": 1120, "count": 1120, "decode_str": " tutti"} -{"id": 49461, "token": "dried", "merges": "d ried", "raw_count": 1120, "count": 1120, "decode_str": "dried"} -{"id": 39399, "token": "\u0120DSM", "merges": "\u0120D SM", "raw_count": 1120, "count": 1120, "decode_str": " DSM"} -{"id": 22957, "token": "\u0120oscillations", "merges": "\u0120oscill ations", "raw_count": 1121, "count": 1121, "decode_str": " oscillations"} -{"id": 49148, "token": "\u0120favorably", "merges": "\u0120favor ably", "raw_count": 1121, "count": 1121, "decode_str": " favorably"} -{"id": 33708, "token": "\u0120incision", "merges": "\u0120inc ision", "raw_count": 1121, "count": 1121, "decode_str": " incision"} -{"id": 40441, "token": "\u0120COMPANY", "merges": "\u0120COMP ANY", "raw_count": 1121, "count": 1121, "decode_str": " COMPANY"} -{"id": 47121, "token": "\u0120fiddle", "merges": "\u0120f iddle", "raw_count": 1121, "count": 1121, "decode_str": " fiddle"} -{"id": 43769, "token": "\u0120Bacon", "merges": "\u0120B acon", "raw_count": 1121, "count": 1121, "decode_str": " Bacon"} -{"id": 19980, "token": "\u0120Mitchell", "merges": "\u0120Mit chell", "raw_count": 1122, "count": 1122, "decode_str": " Mitchell"} -{"id": 41708, "token": "\u0120photometry", "merges": "\u0120phot ometry", "raw_count": 1123, "count": 1123, "decode_str": " photometry"} -{"id": 14540, "token": "\u0120Immun", "merges": "\u0120Im mun", "raw_count": 1123, "count": 1123, "decode_str": " Immun"} -{"id": 19468, "token": "\u0120quark", "merges": "\u0120qu ark", "raw_count": 1123, "count": 1123, "decode_str": " quark"} -{"id": 25303, "token": "\u0120Burg", "merges": "\u0120B urg", "raw_count": 1123, "count": 1123, "decode_str": " Burg"} -{"id": 47597, "token": "\u0120Ia", "merges": "\u0120I a", "raw_count": 1123, "count": 1123, "decode_str": " Ia"} -{"id": 45554, "token": "\u0120precipitated", "merges": "\u0120precip itated", "raw_count": 1124, "count": 1124, "decode_str": " precipitated"} -{"id": 47902, "token": "\u0120agitated", "merges": "\u0120ag itated", "raw_count": 1124, "count": 1124, "decode_str": " agitated"} -{"id": 45287, "token": "\u0120Teaching", "merges": "\u0120Te aching", "raw_count": 1124, "count": 1124, "decode_str": " Teaching"} -{"id": 44456, "token": "otrophic", "merges": "ot rophic", "raw_count": 1124, "count": 1124, "decode_str": "otrophic"} -{"id": 22748, "token": "\u0120NaCl", "merges": "\u0120Na Cl", "raw_count": 1124, "count": 1124, "decode_str": " NaCl"} -{"id": 26709, "token": "\u0120Scar", "merges": "\u0120Sc ar", "raw_count": 1124, "count": 1124, "decode_str": " Scar"} -{"id": 17814, "token": "\u0120Everyone", "merges": "\u0120Every one", "raw_count": 1125, "count": 1125, "decode_str": " Everyone"} -{"id": 24640, "token": "\u0120Valent", "merges": "\u0120Val ent", "raw_count": 623, "count": 1125, "decode_str": " Valent"} -{"id": 37068, "token": "\u0120Cairo", "merges": "\u0120C airo", "raw_count": 1125, "count": 1125, "decode_str": " Cairo"} -{"id": 35914, "token": "Hence", "merges": "H ence", "raw_count": 1125, "count": 1125, "decode_str": "Hence"} -{"id": 9890, "token": "\u0120Italian", "merges": "\u0120It alian", "raw_count": 1126, "count": 1126, "decode_str": " Italian"} -{"id": 48500, "token": "\u0120ankles", "merges": "\u0120ank les", "raw_count": 1126, "count": 1126, "decode_str": " ankles"} -{"id": 41629, "token": "\u0120ainda", "merges": "\u0120a inda", "raw_count": 1126, "count": 1126, "decode_str": " ainda"} -{"id": 45814, "token": "\u0120oddly", "merges": "\u0120odd ly", "raw_count": 1126, "count": 1126, "decode_str": " oddly"} -{"id": 14313, "token": "\u00e2\u0126\u00a2", "merges": "\u00e2\u0126 \u00a2", "raw_count": 1058, "count": 1126, "decode_str": "\u2122"} -{"id": 30944, "token": "\u0120Meyer", "merges": "\u0120M eyer", "raw_count": 1127, "count": 1127, "decode_str": " Meyer"} -{"id": 35457, "token": "\u00c5\u0124a", "merges": "\u00c5\u0124 a", "raw_count": 1127, "count": 1127, "decode_str": "\u0142a"} -{"id": 16891, "token": "\u0120distal", "merges": "\u0120dist al", "raw_count": 1128, "count": 1128, "decode_str": " distal"} -{"id": 17413, "token": "\u0120Tokyo", "merges": "\u0120Tok yo", "raw_count": 1128, "count": 1128, "decode_str": " Tokyo"} -{"id": 43852, "token": "\u0120Eat", "merges": "\u0120E at", "raw_count": 1128, "count": 1128, "decode_str": " Eat"} -{"id": 40682, "token": "\u0120algun", "merges": "\u0120al gun", "raw_count": 1129, "count": 1129, "decode_str": " algun"} -{"id": 16225, "token": "\u0120Victoria", "merges": "\u0120Victor ia", "raw_count": 1130, "count": 1130, "decode_str": " Victoria"} -{"id": 32013, "token": "idepress", "merges": "ide press", "raw_count": 252, "count": 1130, "decode_str": "idepress"} -{"id": 44325, "token": "\u0120Zhu", "merges": "\u0120Z hu", "raw_count": 1130, "count": 1130, "decode_str": " Zhu"} -{"id": 46893, "token": "acycline", "merges": "acy cline", "raw_count": 1131, "count": 1131, "decode_str": "acycline"} -{"id": 39039, "token": "\u0120probed", "merges": "\u0120prob ed", "raw_count": 1131, "count": 1131, "decode_str": " probed"} -{"id": 34239, "token": "\u0120Bod", "merges": "\u0120B od", "raw_count": 1132, "count": 1132, "decode_str": " Bod"} -{"id": 50318, "token": "\u00e2\u012a\u0140", "merges": "\u00e2\u012a \u0140", "raw_count": 1132, "count": 1132, "decode_str": "\u221e"} -{"id": 48946, "token": "\u0120){", "merges": "\u0120 ){", "raw_count": 1132, "count": 1132, "decode_str": " ){"} -{"id": 36959, "token": "\u0120soll", "merges": "\u0120sol l", "raw_count": 1133, "count": 1133, "decode_str": " soll"} -{"id": 36533, "token": "\u0120Rex", "merges": "\u0120R ex", "raw_count": 1133, "count": 1133, "decode_str": " Rex"} -{"id": 13658, "token": "\u0120Specifically", "merges": "\u0120Spec ifically", "raw_count": 1134, "count": 1134, "decode_str": " Specifically"} -{"id": 26157, "token": "\u0120Opinion", "merges": "\u0120O pinion", "raw_count": 1134, "count": 1134, "decode_str": " Opinion"} -{"id": 27082, "token": "\u0120k\u00c3\u00a4", "merges": "\u0120k \u00c3\u00a4", "raw_count": 1134, "count": 1134, "decode_str": " k\u00e4"} -{"id": 34008, "token": "\u0120Coulomb", "merges": "\u0120Coul omb", "raw_count": 1135, "count": 1135, "decode_str": " Coulomb"} -{"id": 6112, "token": "\u0120Texas", "merges": "\u0120Tex as", "raw_count": 1135, "count": 1135, "decode_str": " Texas"} -{"id": 46839, "token": "\u0120Mink", "merges": "\u0120M ink", "raw_count": 1135, "count": 1135, "decode_str": " Mink"} -{"id": 35538, "token": "\u0120PSA", "merges": "\u0120P SA", "raw_count": 1135, "count": 1135, "decode_str": " PSA"} -{"id": 31796, "token": "Appendix", "merges": "App endix", "raw_count": 1136, "count": 1136, "decode_str": "Appendix"} -{"id": 48196, "token": "\u0120slut", "merges": "\u0120sl ut", "raw_count": 1136, "count": 1136, "decode_str": " slut"} -{"id": 44025, "token": "\u0120Tou", "merges": "\u0120T ou", "raw_count": 1137, "count": 1137, "decode_str": " Tou"} -{"id": 28142, "token": "\u0120Cf", "merges": "\u0120C f", "raw_count": 1137, "count": 1137, "decode_str": " Cf"} -{"id": 41381, "token": "\u0120pulsed", "merges": "\u0120pul sed", "raw_count": 1138, "count": 1138, "decode_str": " pulsed"} -{"id": 44406, "token": "plasty", "merges": "pl asty", "raw_count": 1138, "count": 1138, "decode_str": "plasty"} -{"id": 42008, "token": "\u0120alkal", "merges": "\u0120alk al", "raw_count": 1138, "count": 1138, "decode_str": " alkal"} -{"id": 45617, "token": "\u0120FOUR", "merges": "\u0120F OUR", "raw_count": 1138, "count": 1138, "decode_str": " FOUR"} -{"id": 36017, "token": "\u00e1\u0125\u0136", "merges": "\u00e1\u0125 \u0136", "raw_count": 168, "count": 1138, "decode_str": "\u10d4"} -{"id": 20185, "token": "\u0120asymptotic", "merges": "\u0120asympt otic", "raw_count": 1139, "count": 1139, "decode_str": " asymptotic"} -{"id": 47110, "token": "DECLARE", "merges": "DECL ARE", "raw_count": 1139, "count": 1139, "decode_str": "DECLARE"} -{"id": 43517, "token": "\u0120peered", "merges": "\u0120pe ered", "raw_count": 1139, "count": 1139, "decode_str": " peered"} -{"id": 43822, "token": "\u0120umbil", "merges": "\u0120umb il", "raw_count": 118, "count": 1139, "decode_str": " umbil"} -{"id": 44522, "token": "\u0120Boat", "merges": "\u0120Bo at", "raw_count": 1139, "count": 1139, "decode_str": " Boat"} -{"id": 16002, "token": "\u0120postoperative", "merges": "\u0120post operative", "raw_count": 1140, "count": 1140, "decode_str": " postoperative"} -{"id": 29362, "token": "\u0120transporter", "merges": "\u0120trans porter", "raw_count": 1140, "count": 1140, "decode_str": " transporter"} -{"id": 41486, "token": "\u0120Publishers", "merges": "\u0120Publ ishers", "raw_count": 1140, "count": 1140, "decode_str": " Publishers"} -{"id": 34481, "token": "\u0120steroids", "merges": "\u0120ster oids", "raw_count": 1140, "count": 1140, "decode_str": " steroids"} -{"id": 39632, "token": "\u0120Programs", "merges": "\u0120Pro grams", "raw_count": 1140, "count": 1140, "decode_str": " Programs"} -{"id": 43540, "token": "\u0120Rising", "merges": "\u0120R ising", "raw_count": 1140, "count": 1140, "decode_str": " Rising"} -{"id": 11442, "token": "\u0120Northern", "merges": "\u0120N orthern", "raw_count": 1141, "count": 1141, "decode_str": " Northern"} -{"id": 14757, "token": "\u0120induces", "merges": "\u0120indu ces", "raw_count": 1141, "count": 1141, "decode_str": " induces"} -{"id": 11867, "token": "\u0120Eastern", "merges": "\u0120E astern", "raw_count": 1141, "count": 1141, "decode_str": " Eastern"} -{"id": 18671, "token": "\u0120Marine", "merges": "\u0120Mar ine", "raw_count": 1141, "count": 1141, "decode_str": " Marine"} -{"id": 31540, "token": "\u0120Bach", "merges": "\u0120B ach", "raw_count": 1141, "count": 1141, "decode_str": " Bach"} -{"id": 17042, "token": "}$)", "merges": "}$ )", "raw_count": 1141, "count": 1141, "decode_str": "}$)"} -{"id": 30314, "token": "\u0120Initiative", "merges": "\u0120Init iative", "raw_count": 1142, "count": 1142, "decode_str": " Initiative"} -{"id": 20150, "token": "\u0120\u00c3\u00bcber", "merges": "\u0120\u00c3\u00bc ber", "raw_count": 1142, "count": 1142, "decode_str": " \u00fcber"} -{"id": 17549, "token": "\u0120Raj", "merges": "\u0120R aj", "raw_count": 1142, "count": 1142, "decode_str": " Raj"} -{"id": 26096, "token": "\u0120Kor", "merges": "\u0120K or", "raw_count": 1142, "count": 1142, "decode_str": " Kor"} -{"id": 20628, "token": "\u0120Samuel", "merges": "\u0120Sam uel", "raw_count": 1144, "count": 1144, "decode_str": " Samuel"} -{"id": 27269, "token": "\u0120aneur", "merges": "\u0120an eur", "raw_count": 35, "count": 1144, "decode_str": " aneur"} -{"id": 210, "token": "\u0121", "merges": "NULL", "raw_count": 1144, "count": 1144, "decode_str": "\u007f"} -{"id": 48688, "token": "\u0120Frontier", "merges": "\u0120Front ier", "raw_count": 1145, "count": 1145, "decode_str": " Frontier"} -{"id": 47852, "token": "\u0120narciss", "merges": "\u0120narc iss", "raw_count": 1145, "count": 1145, "decode_str": " narciss"} -{"id": 33904, "token": "\u0120Powers", "merges": "\u0120Pow ers", "raw_count": 1145, "count": 1145, "decode_str": " Powers"} -{"id": 31157, "token": "\u0120hilar", "merges": "\u0120h ilar", "raw_count": 438, "count": 1145, "decode_str": " hilar"} -{"id": 16067, "token": "\u0120glyc", "merges": "\u0120gly c", "raw_count": 430, "count": 1145, "decode_str": " glyc"} -{"id": 28230, "token": "\u0120Roth", "merges": "\u0120R oth", "raw_count": 1145, "count": 1145, "decode_str": " Roth"} -{"id": 36920, "token": "\u0120Sou", "merges": "\u0120S ou", "raw_count": 1145, "count": 1145, "decode_str": " Sou"} -{"id": 43071, "token": "\u0120Examination", "merges": "\u0120Ex amination", "raw_count": 1146, "count": 1146, "decode_str": " Examination"} -{"id": 17604, "token": "\u0120ventricular", "merges": "\u0120vent ricular", "raw_count": 1146, "count": 1146, "decode_str": " ventricular"} -{"id": 45697, "token": "\u0120anecd", "merges": "\u0120anec d", "raw_count": 1146, "count": 1146, "decode_str": " anecd"} -{"id": 40808, "token": "\u00e0\u00a4\u00b5", "merges": "\u00e0\u00a4 \u00b5", "raw_count": 1146, "count": 1146, "decode_str": "\u0935"} -{"id": 45167, "token": "\u0120recollection", "merges": "\u0120recol lection", "raw_count": 1147, "count": 1147, "decode_str": " recollection"} -{"id": 47348, "token": "\u0120scratching", "merges": "\u0120scr atching", "raw_count": 1147, "count": 1147, "decode_str": " scratching"} -{"id": 42027, "token": "\u0120Flying", "merges": "\u0120F lying", "raw_count": 1147, "count": 1147, "decode_str": " Flying"} -{"id": 28409, "token": "\u0120ounces", "merges": "\u0120oun ces", "raw_count": 1147, "count": 1147, "decode_str": " ounces"} -{"id": 19381, "token": "\u0120Marx", "merges": "\u0120Mar x", "raw_count": 1035, "count": 1147, "decode_str": " Marx"} -{"id": 42966, "token": "\u0120rien", "merges": "\u0120ri en", "raw_count": 1147, "count": 1147, "decode_str": " rien"} -{"id": 36783, "token": "\u0120fois", "merges": "\u0120fo is", "raw_count": 1147, "count": 1147, "decode_str": " fois"} -{"id": 9804, "token": "\u0120\u00c2\u00b5", "merges": "\u0120\u00c2 \u00b5", "raw_count": 829, "count": 1147, "decode_str": " \u00b5"} -{"id": 46704, "token": "\u0120precludes", "merges": "\u0120pre cludes", "raw_count": 1148, "count": 1148, "decode_str": " precludes"} -{"id": 50069, "token": "Previously", "merges": "Pre viously", "raw_count": 1148, "count": 1148, "decode_str": "Previously"} -{"id": 26648, "token": "NSString", "merges": "NS String", "raw_count": 1148, "count": 1148, "decode_str": "NSString"} -{"id": 18258, "token": "\u0120tumour", "merges": "\u0120tum our", "raw_count": 1148, "count": 1148, "decode_str": " tumour"} -{"id": 23916, "token": "\u0120venous", "merges": "\u0120ven ous", "raw_count": 1148, "count": 1148, "decode_str": " venous"} -{"id": 22012, "token": "\u0120DAM", "merges": "\u0120D AM", "raw_count": 819, "count": 1148, "decode_str": " DAM"} -{"id": 44364, "token": "addEventListener", "merges": "add EventListener", "raw_count": 1149, "count": 1149, "decode_str": "addEventListener"} -{"id": 50119, "token": "\u0120bijection", "merges": "\u0120bi jection", "raw_count": 1149, "count": 1149, "decode_str": " bijection"} -{"id": 39916, "token": "\u0120peppers", "merges": "\u0120pe ppers", "raw_count": 1149, "count": 1149, "decode_str": " peppers"} -{"id": 27942, "token": "cemia", "merges": "ce mia", "raw_count": 1149, "count": 1149, "decode_str": "cemia"} -{"id": 46759, "token": "\u0120Cars", "merges": "\u0120C ars", "raw_count": 1149, "count": 1149, "decode_str": " Cars"} -{"id": 36481, "token": "\u0120MLB", "merges": "\u0120ML B", "raw_count": 1149, "count": 1149, "decode_str": " MLB"} -{"id": 34770, "token": "\u0120electrochemical", "merges": "\u0120electro chemical", "raw_count": 1150, "count": 1150, "decode_str": " electrochemical"} -{"id": 48101, "token": "\u0120retarded", "merges": "\u0120ret arded", "raw_count": 1150, "count": 1150, "decode_str": " retarded"} -{"id": 27870, "token": "\u0120si\u00c4\u013b", "merges": "\u0120si \u00c4\u013b", "raw_count": 1150, "count": 1150, "decode_str": " si\u0119"} -{"id": 32025, "token": "REEK", "merges": "REE K", "raw_count": 551, "count": 1150, "decode_str": "REEK"} -{"id": 46978, "token": "\u00d8\u00a7\u00d8\u00b3", "merges": "\u00d8\u00a7\u00d8 \u00b3", "raw_count": 1150, "count": 1150, "decode_str": "\u0627\u0633"} -{"id": 49529, "token": "\u0120Dre", "merges": "\u0120D re", "raw_count": 1150, "count": 1150, "decode_str": " Dre"} -{"id": 11915, "token": "\u0120Uk", "merges": "\u0120U k", "raw_count": 814, "count": 1150, "decode_str": " Uk"} -{"id": 37903, "token": "\u0120scaffolds", "merges": "\u0120scaff olds", "raw_count": 1151, "count": 1151, "decode_str": " scaffolds"} -{"id": 29498, "token": "\u0120predis", "merges": "\u0120pred is", "raw_count": 1151, "count": 1151, "decode_str": " predis"} -{"id": 10889, "token": "ellee", "merges": "elle e", "raw_count": 1092, "count": 1151, "decode_str": "ellee"} -{"id": 24518, "token": "\u0120Reed", "merges": "\u0120Re ed", "raw_count": 1151, "count": 1151, "decode_str": " Reed"} -{"id": 29945, "token": "enchymal", "merges": "ench ymal", "raw_count": 778, "count": 1152, "decode_str": "enchymal"} -{"id": 24887, "token": "\u0120quel", "merges": "\u0120qu el", "raw_count": 1045, "count": 1152, "decode_str": " quel"} -{"id": 25686, "token": "\u0120Mans", "merges": "\u0120M ans", "raw_count": 1152, "count": 1152, "decode_str": " Mans"} -{"id": 26831, "token": "\u0120glycer", "merges": "\u0120gly cer", "raw_count": 820, "count": 1153, "decode_str": " glycer"} -{"id": 33985, "token": "\u0120donc", "merges": "\u0120don c", "raw_count": 1153, "count": 1153, "decode_str": " donc"} -{"id": 35540, "token": "\u0120Dust", "merges": "\u0120D ust", "raw_count": 1153, "count": 1153, "decode_str": " Dust"} -{"id": 22901, "token": "\u0120Guardian", "merges": "\u0120Guard ian", "raw_count": 1154, "count": 1154, "decode_str": " Guardian"} -{"id": 46191, "token": "\u0120Warrior", "merges": "\u0120War rior", "raw_count": 1154, "count": 1154, "decode_str": " Warrior"} -{"id": 4862, "token": "overline", "merges": "over line", "raw_count": 1154, "count": 1154, "decode_str": "overline"} -{"id": 49881, "token": "\u0120Fritz", "merges": "\u0120F ritz", "raw_count": 1154, "count": 1154, "decode_str": " Fritz"} -{"id": 40242, "token": "\u0120Equations", "merges": "\u0120Equ ations", "raw_count": 1155, "count": 1155, "decode_str": " Equations"} -{"id": 43284, "token": "\u0120avoir", "merges": "\u0120av oir", "raw_count": 1155, "count": 1155, "decode_str": " avoir"} -{"id": 21975, "token": "\u0120Alb", "merges": "\u0120Al b", "raw_count": 1045, "count": 1155, "decode_str": " Alb"} -{"id": 38004, "token": "\u0120Dum", "merges": "\u0120D um", "raw_count": 1155, "count": 1155, "decode_str": " Dum"} -{"id": 36878, "token": "\u0120quantitatively", "merges": "\u0120quant itatively", "raw_count": 1156, "count": 1156, "decode_str": " quantitatively"} -{"id": 32605, "token": "\u0120bifur", "merges": "\u0120bif ur", "raw_count": 557, "count": 1156, "decode_str": " bifur"} -{"id": 35603, "token": "\u00c3\u00bcller", "merges": "\u00c3\u00bc ller", "raw_count": 1076, "count": 1156, "decode_str": "\u00fcller"} -{"id": 41698, "token": "ibilit", "merges": "ib ilit", "raw_count": 1156, "count": 1156, "decode_str": "ibilit"} -{"id": 22633, "token": "\u0120Cla", "merges": "\u0120Cl a", "raw_count": 719, "count": 1156, "decode_str": " Cla"} -{"id": 31683, "token": "\u0120Oz", "merges": "\u0120O z", "raw_count": 1156, "count": 1156, "decode_str": " Oz"} -{"id": 38427, "token": "\u0120responders", "merges": "\u0120respond ers", "raw_count": 1157, "count": 1157, "decode_str": " responders"} -{"id": 35754, "token": "unreadable", "merges": "un readable", "raw_count": 1157, "count": 1157, "decode_str": "unreadable"} -{"id": 41453, "token": "\u0120battling", "merges": "\u0120batt ling", "raw_count": 1157, "count": 1157, "decode_str": " battling"} -{"id": 40732, "token": "\u0120trout", "merges": "\u0120tr out", "raw_count": 1157, "count": 1157, "decode_str": " trout"} -{"id": 32977, "token": "\u0120Hav", "merges": "\u0120H av", "raw_count": 1157, "count": 1157, "decode_str": " Hav"} -{"id": 32198, "token": "\u0120Ancient", "merges": "\u0120An cient", "raw_count": 1158, "count": 1158, "decode_str": " Ancient"} -{"id": 48400, "token": "\u0120Primer", "merges": "\u0120Pr imer", "raw_count": 1158, "count": 1158, "decode_str": " Primer"} -{"id": 38920, "token": "\u0120mildly", "merges": "\u0120mild ly", "raw_count": 1158, "count": 1158, "decode_str": " mildly"} -{"id": 50151, "token": "\u0120spirituality", "merges": "\u0120spirit uality", "raw_count": 1159, "count": 1159, "decode_str": " spirituality"} -{"id": 26414, "token": "\u0120converges", "merges": "\u0120conver ges", "raw_count": 1159, "count": 1159, "decode_str": " converges"} -{"id": 29034, "token": "\u0120playoff", "merges": "\u0120play off", "raw_count": 1159, "count": 1159, "decode_str": " playoff"} -{"id": 45582, "token": "\u0120disbelief", "merges": "\u0120dis belief", "raw_count": 1160, "count": 1160, "decode_str": " disbelief"} -{"id": 46721, "token": "\u0120drilled", "merges": "\u0120dr illed", "raw_count": 1160, "count": 1160, "decode_str": " drilled"} -{"id": 44963, "token": "\u0120acetic", "merges": "\u0120ac etic", "raw_count": 1160, "count": 1160, "decode_str": " acetic"} -{"id": 46636, "token": "\u0120calor", "merges": "\u0120cal or", "raw_count": 1160, "count": 1160, "decode_str": " calor"} -{"id": 40499, "token": "\u0120Activities", "merges": "\u0120Act ivities", "raw_count": 1161, "count": 1161, "decode_str": " Activities"} -{"id": 34370, "token": "\u0120Mari", "merges": "\u0120M ari", "raw_count": 1161, "count": 1161, "decode_str": " Mari"} -{"id": 39495, "token": "ieties", "merges": "iet ies", "raw_count": 1162, "count": 1162, "decode_str": "ieties"} -{"id": 44900, "token": "\u0120Ib", "merges": "\u0120I b", "raw_count": 1162, "count": 1162, "decode_str": " Ib"} -{"id": 29802, "token": "\u0120\u00d9\u0129", "merges": "\u0120 \u00d9\u0129", "raw_count": 1162, "count": 1162, "decode_str": " \u0647"} -{"id": 10681, "token": "\u00e0\u00b0", "merges": "\u00e0 \u00b0", "raw_count": 885, "count": 1162, "decode_str": "\ufffd"} -{"id": 21903, "token": "\u0120phenotypes", "merges": "\u0120phen otypes", "raw_count": 1163, "count": 1163, "decode_str": " phenotypes"} -{"id": 30706, "token": "\u0120Enjoy", "merges": "\u0120En joy", "raw_count": 1163, "count": 1163, "decode_str": " Enjoy"} -{"id": 49816, "token": "\u0120adjunct", "merges": "\u0120adj unct", "raw_count": 1164, "count": 1164, "decode_str": " adjunct"} -{"id": 44927, "token": "\u0120anhydr", "merges": "\u0120an hydr", "raw_count": 1164, "count": 1164, "decode_str": " anhydr"} -{"id": 16019, "token": "\u0120Phill", "merges": "\u0120Ph ill", "raw_count": 55, "count": 1164, "decode_str": " Phill"} -{"id": 26135, "token": "\u0120Cort", "merges": "\u0120C ort", "raw_count": 1164, "count": 1164, "decode_str": " Cort"} -{"id": 46769, "token": "\u0120Keeping", "merges": "\u0120Ke eping", "raw_count": 1165, "count": 1165, "decode_str": " Keeping"} -{"id": 39582, "token": "\u0120Drum", "merges": "\u0120Dr um", "raw_count": 1165, "count": 1165, "decode_str": " Drum"} -{"id": 18431, "token": "Several", "merges": "S everal", "raw_count": 1166, "count": 1166, "decode_str": "Several"} -{"id": 50121, "token": "\u0120ici", "merges": "\u0120 ici", "raw_count": 1166, "count": 1166, "decode_str": " ici"} -{"id": 44413, "token": "\u0120gripping", "merges": "\u0120gri pping", "raw_count": 1167, "count": 1167, "decode_str": " gripping"} -{"id": 24964, "token": "\u0120lymphoma", "merges": "\u0120lymph oma", "raw_count": 1167, "count": 1167, "decode_str": " lymphoma"} -{"id": 43483, "token": "\u0120Thinking", "merges": "\u0120Th inking", "raw_count": 1167, "count": 1167, "decode_str": " Thinking"} -{"id": 21788, "token": "\u0120Highway", "merges": "\u0120High way", "raw_count": 1167, "count": 1167, "decode_str": " Highway"} -{"id": 31928, "token": "\u0120a\u00c3\u00b1os", "merges": "\u0120a \u00c3\u00b1os", "raw_count": 1167, "count": 1167, "decode_str": " a\u00f1os"} -{"id": 34876, "token": "\u0120Sue", "merges": "\u0120S ue", "raw_count": 1167, "count": 1167, "decode_str": " Sue"} -{"id": 34754, "token": "\u0120approximations", "merges": "\u0120approxim ations", "raw_count": 1168, "count": 1168, "decode_str": " approximations"} -{"id": 43655, "token": "\u0120Principles", "merges": "\u0120Princ iples", "raw_count": 1168, "count": 1168, "decode_str": " Principles"} -{"id": 48414, "token": "\u0120comport", "merges": "\u0120comp ort", "raw_count": 1168, "count": 1168, "decode_str": " comport"} -{"id": 30921, "token": "\u0120Photos", "merges": "\u0120Phot os", "raw_count": 1168, "count": 1168, "decode_str": " Photos"} -{"id": 18770, "token": "\u0120Much", "merges": "\u0120M uch", "raw_count": 1168, "count": 1168, "decode_str": " Much"} -{"id": 40973, "token": "\u010a\u0109\u0109\u0120", "merges": "\u010a\u0109\u0109 \u0120", "raw_count": 1168, "count": 1168, "decode_str": "\n\t\t "} -{"id": 40603, "token": "\u0120haplotype", "merges": "\u0120hapl otype", "raw_count": 1169, "count": 1169, "decode_str": " haplotype"} -{"id": 43041, "token": "\u0120AFL", "merges": "\u0120A FL", "raw_count": 1169, "count": 1169, "decode_str": " AFL"} -{"id": 46294, "token": "'=>", "merges": "' =>", "raw_count": 1169, "count": 1169, "decode_str": "'=>"} -{"id": 34902, "token": "\u0120symmetries", "merges": "\u0120symmet ries", "raw_count": 1170, "count": 1170, "decode_str": " symmetries"} -{"id": 38167, "token": "\u0120parasitic", "merges": "\u0120paras itic", "raw_count": 1170, "count": 1170, "decode_str": " parasitic"} -{"id": 25849, "token": "\u0120\u00d8\u00b9", "merges": "\u0120\u00d8 \u00b9", "raw_count": 1170, "count": 1170, "decode_str": " \u0639"} -{"id": 48293, "token": "\u0120straightened", "merges": "\u0120straight ened", "raw_count": 1171, "count": 1171, "decode_str": " straightened"} -{"id": 39276, "token": "\u0120suicidal", "merges": "\u0120su icidal", "raw_count": 1171, "count": 1171, "decode_str": " suicidal"} -{"id": 50245, "token": "\u0120toddler", "merges": "\u0120todd ler", "raw_count": 1171, "count": 1171, "decode_str": " toddler"} -{"id": 22547, "token": "\u0120Bernard", "merges": "\u0120Bern ard", "raw_count": 1171, "count": 1171, "decode_str": " Bernard"} -{"id": 32703, "token": "\u0120-------------------------", "merges": "\u0120---------------- ---------", "raw_count": 1172, "count": 1172, "decode_str": " -------------------------"} -{"id": 43546, "token": "\u0120elasticity", "merges": "\u0120elastic ity", "raw_count": 1172, "count": 1172, "decode_str": " elasticity"} -{"id": 48364, "token": "\u0120accl", "merges": "\u0120ac cl", "raw_count": 1172, "count": 1172, "decode_str": " accl"} -{"id": 46414, "token": "\u0120SSR", "merges": "\u0120S SR", "raw_count": 1172, "count": 1172, "decode_str": " SSR"} -{"id": 17528, "token": "\u0120Affairs", "merges": "\u0120Aff airs", "raw_count": 1173, "count": 1173, "decode_str": " Affairs"} -{"id": 47251, "token": "\u0120(+)", "merges": "\u0120( +)", "raw_count": 1173, "count": 1173, "decode_str": " (+)"} -{"id": 11630, "token": "\u00cf\u012f", "merges": "\u00cf \u012f", "raw_count": 907, "count": 1173, "decode_str": "\u03cd"} -{"id": 40503, "token": "\u0120biodiversity", "merges": "\u0120biod iversity", "raw_count": 1174, "count": 1174, "decode_str": " biodiversity"} -{"id": 50012, "token": "\u0120Rings", "merges": "\u0120R ings", "raw_count": 1174, "count": 1174, "decode_str": " Rings"} -{"id": 34271, "token": "\u0120\u00e1\u0125", "merges": "\u0120 \u00e1\u0125", "raw_count": 1174, "count": 1174, "decode_str": " \ufffd"} -{"id": 12362, "token": "\u0120Tenn", "merges": "\u0120T enn", "raw_count": 1012, "count": 1175, "decode_str": " Tenn"} -{"id": 26789, "token": "\u0120Nine", "merges": "\u0120N ine", "raw_count": 1175, "count": 1175, "decode_str": " Nine"} -{"id": 46931, "token": "))^", "merges": ")) ^", "raw_count": 1175, "count": 1175, "decode_str": "))^"} -{"id": 38183, "token": "\u0120combinatorial", "merges": "\u0120combinator ial", "raw_count": 1176, "count": 1176, "decode_str": " combinatorial"} -{"id": 27939, "token": "\u0120degeneration", "merges": "\u0120de generation", "raw_count": 1176, "count": 1176, "decode_str": " degeneration"} -{"id": 8341, "token": "\u0120plaintiffs", "merges": "\u0120plaintiff s", "raw_count": 1176, "count": 1176, "decode_str": " plaintiffs"} -{"id": 35673, "token": "textwidth", "merges": "text width", "raw_count": 1176, "count": 1176, "decode_str": "textwidth"} -{"id": 41221, "token": "\u0120Edited", "merges": "\u0120Ed ited", "raw_count": 1176, "count": 1176, "decode_str": " Edited"} -{"id": 24126, "token": "\u0120Curt", "merges": "\u0120C urt", "raw_count": 587, "count": 1176, "decode_str": " Curt"} -{"id": 22718, "token": "\u0120Mathematics", "merges": "\u0120Mathemat ics", "raw_count": 1177, "count": 1177, "decode_str": " Mathematics"} -{"id": 47779, "token": "\u0120fractured", "merges": "\u0120fract ured", "raw_count": 1177, "count": 1177, "decode_str": " fractured"} -{"id": 45015, "token": "\u0120wrists", "merges": "\u0120wr ists", "raw_count": 1177, "count": 1177, "decode_str": " wrists"} -{"id": 50041, "token": "\u0120diodes", "merges": "\u0120di odes", "raw_count": 1178, "count": 1178, "decode_str": " diodes"} -{"id": 40713, "token": "\u0120Didn", "merges": "\u0120Did n", "raw_count": 1178, "count": 1178, "decode_str": " Didn"} -{"id": 43416, "token": "\u0120commut", "merges": "\u0120comm ut", "raw_count": 1179, "count": 1179, "decode_str": " commut"} -{"id": 45052, "token": "\u0120invas", "merges": "\u0120inv as", "raw_count": 1179, "count": 1179, "decode_str": " invas"} -{"id": 44348, "token": "ipore", "merges": "ip ore", "raw_count": 1179, "count": 1179, "decode_str": "ipore"} -{"id": 29182, "token": "\u0120cryptocurrency", "merges": "\u0120cryptocur rency", "raw_count": 1180, "count": 1180, "decode_str": " cryptocurrency"} -{"id": 18704, "token": "\u0120saline", "merges": "\u0120sal ine", "raw_count": 1180, "count": 1180, "decode_str": " saline"} -{"id": 30533, "token": "\u0120Ow", "merges": "\u0120O w", "raw_count": 943, "count": 1180, "decode_str": " Ow"} -{"id": 23061, "token": "\u0120Samsung", "merges": "\u0120Sams ung", "raw_count": 1181, "count": 1181, "decode_str": " Samsung"} -{"id": 13534, "token": "\u0120Bible", "merges": "\u0120B ible", "raw_count": 1181, "count": 1181, "decode_str": " Bible"} -{"id": 38973, "token": "\u0120Jung", "merges": "\u0120J ung", "raw_count": 1181, "count": 1181, "decode_str": " Jung"} -{"id": 21231, "token": "\u0120Ple", "merges": "\u0120P le", "raw_count": 1181, "count": 1181, "decode_str": " Ple"} -{"id": 37723, "token": "\u0120Dil", "merges": "\u0120D il", "raw_count": 1182, "count": 1182, "decode_str": " Dil"} -{"id": 50736, "token": "\u00e5\u0128\u00be", "merges": "\u00e5\u0128 \u00be", "raw_count": 1182, "count": 1182, "decode_str": "\u51be"} -{"id": 48019, "token": "\u0120stato", "merges": "\u0120stat o", "raw_count": 1183, "count": 1183, "decode_str": " stato"} -{"id": 15713, "token": "\u0120Hind", "merges": "\u0120H ind", "raw_count": 1022, "count": 1183, "decode_str": " Hind"} -{"id": 16543, "token": "\u0120Anna", "merges": "\u0120An na", "raw_count": 1183, "count": 1183, "decode_str": " Anna"} -{"id": 31156, "token": "\u0120longtime", "merges": "\u0120long time", "raw_count": 1184, "count": 1184, "decode_str": " longtime"} -{"id": 33721, "token": "iotensin", "merges": "iot ensin", "raw_count": 1028, "count": 1184, "decode_str": "iotensin"} -{"id": 17515, "token": "\u0120aqueous", "merges": "\u0120a queous", "raw_count": 1184, "count": 1184, "decode_str": " aqueous"} -{"id": 26456, "token": "\u0120Vincent", "merges": "\u0120Vin cent", "raw_count": 1184, "count": 1184, "decode_str": " Vincent"} -{"id": 10807, "token": "\u0120BOOST", "merges": "\u0120B OOST", "raw_count": 1184, "count": 1184, "decode_str": " BOOST"} -{"id": 40455, "token": "\u00e0\u00b9\u0123", "merges": "\u00e0\u00b9 \u0123", "raw_count": 1184, "count": 1184, "decode_str": "\u0e41"} -{"id": 49490, "token": "DCs", "merges": "D Cs", "raw_count": 1184, "count": 1184, "decode_str": "DCs"} -{"id": 31198, "token": "\u0120WordPress", "merges": "\u0120Word Press", "raw_count": 1185, "count": 1185, "decode_str": " WordPress"} -{"id": 20300, "token": "Rearrange", "merges": "Rear range", "raw_count": 1186, "count": 1186, "decode_str": "Rearrange"} -{"id": 38449, "token": "\u0120blinked", "merges": "\u0120blink ed", "raw_count": 1186, "count": 1186, "decode_str": " blinked"} -{"id": 10596, "token": "\u0120apoptosis", "merges": "\u0120apopt osis", "raw_count": 1187, "count": 1187, "decode_str": " apoptosis"} -{"id": 39548, "token": "acetic", "merges": "ac etic", "raw_count": 1187, "count": 1187, "decode_str": "acetic"} -{"id": 27824, "token": "\u0120l\u00c3\u0142", "merges": "\u0120l \u00c3\u0142", "raw_count": 1187, "count": 1187, "decode_str": " l\u00e0"} -{"id": 39580, "token": "\u0120QB", "merges": "\u0120Q B", "raw_count": 1187, "count": 1187, "decode_str": " QB"} -{"id": 49985, "token": "\u0120semiconduct", "merges": "\u0120semicon duct", "raw_count": 1188, "count": 1188, "decode_str": " semiconduct"} -{"id": 44148, "token": "\u0120caregiver", "merges": "\u0120careg iver", "raw_count": 1189, "count": 1189, "decode_str": " caregiver"} -{"id": 42054, "token": "\u0120Jensen", "merges": "\u0120J ensen", "raw_count": 1189, "count": 1189, "decode_str": " Jensen"} -{"id": 49207, "token": "\u0120acquittal", "merges": "\u0120acqu ittal", "raw_count": 1190, "count": 1190, "decode_str": " acquittal"} -{"id": 16184, "token": "\u0120lact", "merges": "\u0120l act", "raw_count": 1074, "count": 1190, "decode_str": " lact"} -{"id": 48199, "token": "\u0120prosthetic", "merges": "\u0120prost hetic", "raw_count": 1191, "count": 1191, "decode_str": " prosthetic"} -{"id": 43117, "token": "\u0120resembled", "merges": "\u0120resemb led", "raw_count": 1191, "count": 1191, "decode_str": " resembled"} -{"id": 46870, "token": "\u0120stitches", "merges": "\u0120st itches", "raw_count": 1191, "count": 1191, "decode_str": " stitches"} -{"id": 47259, "token": "STITUTE", "merges": "STIT UTE", "raw_count": 1191, "count": 1191, "decode_str": "STITUTE"} -{"id": 24161, "token": "\u0120Against", "merges": "\u0120Again st", "raw_count": 1192, "count": 1192, "decode_str": " Against"} -{"id": 32534, "token": "\u0120antif", "merges": "\u0120ant if", "raw_count": 1033, "count": 1192, "decode_str": " antif"} -{"id": 32758, "token": "rectomy", "merges": "rect omy", "raw_count": 1193, "count": 1193, "decode_str": "rectomy"} -{"id": 33103, "token": "\u0120translational", "merges": "\u0120transl ational", "raw_count": 1194, "count": 1194, "decode_str": " translational"} -{"id": 47431, "token": "\u0120cataract", "merges": "\u0120catar act", "raw_count": 1194, "count": 1194, "decode_str": " cataract"} -{"id": 26818, "token": "iviral", "merges": "iv iral", "raw_count": 476, "count": 1194, "decode_str": "iviral"} -{"id": 27971, "token": "veolar", "merges": "ve olar", "raw_count": 599, "count": 1194, "decode_str": "veolar"} -{"id": 21243, "token": "\u00c3\u00a4h", "merges": "\u00c3\u00a4 h", "raw_count": 1003, "count": 1194, "decode_str": "\u00e4h"} -{"id": 39936, "token": "\u00e1\u0141", "merges": "\u00e1 \u0141", "raw_count": 1194, "count": 1194, "decode_str": "\ufffd"} -{"id": 23607, "token": "\u0120Official", "merges": "\u0120Offic ial", "raw_count": 1195, "count": 1195, "decode_str": " Official"} -{"id": 21425, "token": "\u0120inhibits", "merges": "\u0120inhib its", "raw_count": 1196, "count": 1196, "decode_str": " inhibits"} -{"id": 48657, "token": "\u0120mundane", "merges": "\u0120mund ane", "raw_count": 1196, "count": 1196, "decode_str": " mundane"} -{"id": 35901, "token": "\u0120scav", "merges": "\u0120sc av", "raw_count": 1196, "count": 1196, "decode_str": " scav"} -{"id": 23803, "token": "\u0120intravenous", "merges": "\u0120intraven ous", "raw_count": 1197, "count": 1197, "decode_str": " intravenous"} -{"id": 39861, "token": "\u0120anaerobic", "merges": "\u0120ana erobic", "raw_count": 1199, "count": 1199, "decode_str": " anaerobic"} -{"id": 24618, "token": "\u0120Falls", "merges": "\u0120F alls", "raw_count": 1199, "count": 1199, "decode_str": " Falls"} -{"id": 29663, "token": "\u0120Lad", "merges": "\u0120L ad", "raw_count": 720, "count": 1199, "decode_str": " Lad"} -{"id": 13899, "token": "sime", "merges": "s ime", "raw_count": 1146, "count": 1199, "decode_str": "sime"} -{"id": 48220, "token": "\u0120Cannon", "merges": "\u0120C annon", "raw_count": 1200, "count": 1200, "decode_str": " Cannon"} -{"id": 35230, "token": "\u0120Gang", "merges": "\u0120G ang", "raw_count": 1200, "count": 1200, "decode_str": " Gang"} -{"id": 16163, "token": "\u00c8\u013b", "merges": "\u00c8 \u013b", "raw_count": 833, "count": 1200, "decode_str": "\u0219"} -{"id": 18623, "token": "\u0120Bron", "merges": "\u0120B ron", "raw_count": 781, "count": 1201, "decode_str": " Bron"} -{"id": 43358, "token": "\u0120LOT", "merges": "\u0120L OT", "raw_count": 1201, "count": 1201, "decode_str": " LOT"} -{"id": 38649, "token": "\u0120Aid", "merges": "\u0120A id", "raw_count": 1201, "count": 1201, "decode_str": " Aid"} -{"id": 21657, "token": "\u0120experimentally", "merges": "\u0120experiment ally", "raw_count": 1202, "count": 1202, "decode_str": " experimentally"} -{"id": 48605, "token": "\u0120playwright", "merges": "\u0120play wright", "raw_count": 1202, "count": 1202, "decode_str": " playwright"} -{"id": 12808, "token": "\u0120Kent", "merges": "\u0120K ent", "raw_count": 1046, "count": 1202, "decode_str": " Kent"} -{"id": 33377, "token": "\u0120Sach", "merges": "\u0120S ach", "raw_count": 289, "count": 1202, "decode_str": " Sach"} -{"id": 30537, "token": "](\\", "merges": "]( \\", "raw_count": 1202, "count": 1202, "decode_str": "](\\"} -{"id": 41598, "token": "\u0120Mint", "merges": "\u0120M int", "raw_count": 1203, "count": 1203, "decode_str": " Mint"} -{"id": 30303, "token": "\u00cf\u012a", "merges": "\u00cf \u012a", "raw_count": 1203, "count": 1203, "decode_str": "\u03c8"} -{"id": 20933, "token": "\u00ce\u00be", "merges": "\u00ce \u00be", "raw_count": 1203, "count": 1203, "decode_str": "\u03be"} -{"id": 24043, "token": "\u0120infarction", "merges": "\u0120infar ction", "raw_count": 1204, "count": 1204, "decode_str": " infarction"} -{"id": 28685, "token": "\u0120ventric", "merges": "\u0120vent ric", "raw_count": 397, "count": 1204, "decode_str": " ventric"} -{"id": 27634, "token": "\u0120prophyl", "merges": "\u0120pro phyl", "raw_count": 83, "count": 1205, "decode_str": " prophyl"} -{"id": 49613, "token": "\u0120spying", "merges": "\u0120sp ying", "raw_count": 1205, "count": 1205, "decode_str": " spying"} -{"id": 32188, "token": "\u0120cirrh", "merges": "\u0120cir rh", "raw_count": 123, "count": 1205, "decode_str": " cirrh"} -{"id": 47290, "token": "r\u00c3\u00b3", "merges": "r \u00c3\u00b3", "raw_count": 1205, "count": 1205, "decode_str": "r\u00f3"} -{"id": 38674, "token": "\u0120cavities", "merges": "\u0120cav ities", "raw_count": 1206, "count": 1206, "decode_str": " cavities"} -{"id": 33334, "token": "\u0120Carn", "merges": "\u0120C arn", "raw_count": 1206, "count": 1206, "decode_str": " Carn"} -{"id": 46161, "token": "iamo", "merges": "i amo", "raw_count": 1206, "count": 1206, "decode_str": "iamo"} -{"id": 49118, "token": "\u0120hens", "merges": "\u0120he ns", "raw_count": 1207, "count": 1207, "decode_str": " hens"} -{"id": 17366, "token": "\u00c3\u00a4l", "merges": "\u00c3\u00a4 l", "raw_count": 1048, "count": 1207, "decode_str": "\u00e4l"} -{"id": 41691, "token": "\u0120extremity", "merges": "\u0120extrem ity", "raw_count": 1208, "count": 1208, "decode_str": " extremity"} -{"id": 44891, "token": "\u0120Whats", "merges": "\u0120What s", "raw_count": 1208, "count": 1208, "decode_str": " Whats"} -{"id": 28309, "token": "\u0120muy", "merges": "\u0120m uy", "raw_count": 1208, "count": 1208, "decode_str": " muy"} -{"id": 6899, "token": "\u0120Theorem", "merges": "\u0120The orem", "raw_count": 1209, "count": 1209, "decode_str": " Theorem"} -{"id": 42233, "token": "\u0120malice", "merges": "\u0120mal ice", "raw_count": 1209, "count": 1209, "decode_str": " malice"} -{"id": 40803, "token": "\u0120wurde", "merges": "\u0120wur de", "raw_count": 1209, "count": 1209, "decode_str": " wurde"} -{"id": 33007, "token": "\u0120Bes", "merges": "\u0120B es", "raw_count": 1209, "count": 1209, "decode_str": " Bes"} -{"id": 48272, "token": "\u0120decidedly", "merges": "\u0120decided ly", "raw_count": 1210, "count": 1210, "decode_str": " decidedly"} -{"id": 8604, "token": "documentclass", "merges": "document class", "raw_count": 1211, "count": 1211, "decode_str": "documentclass"} -{"id": 49190, "token": "\u0120testifying", "merges": "\u0120test ifying", "raw_count": 1211, "count": 1211, "decode_str": " testifying"} -{"id": 46947, "token": "\u0120fain", "merges": "\u0120f ain", "raw_count": 1211, "count": 1211, "decode_str": " fain"} -{"id": 25393, "token": "\u0120\u00d9\u0123", "merges": "\u0120 \u00d9\u0123", "raw_count": 908, "count": 1211, "decode_str": " \u0641"} -{"id": 28382, "token": "\u00c3\u00a1t", "merges": "\u00c3\u00a1 t", "raw_count": 1211, "count": 1211, "decode_str": "\u00e1t"} -{"id": 28808, "token": "\u0120resonant", "merges": "\u0120reson ant", "raw_count": 1212, "count": 1212, "decode_str": " resonant"} -{"id": 23316, "token": "\u0120Carlos", "merges": "\u0120Carl os", "raw_count": 1212, "count": 1212, "decode_str": " Carlos"} -{"id": 23844, "token": "\u0120larvae", "merges": "\u0120lar vae", "raw_count": 1212, "count": 1212, "decode_str": " larvae"} -{"id": 31726, "token": "\u0120Cord", "merges": "\u0120C ord", "raw_count": 1212, "count": 1212, "decode_str": " Cord"} -{"id": 50100, "token": "\u0120regenerative", "merges": "\u0120regener ative", "raw_count": 1213, "count": 1213, "decode_str": " regenerative"} -{"id": 10298, "token": "\u00ce\u00b1\u00ce\u00b9", "merges": "\u00ce\u00b1 \u00ce\u00b9", "raw_count": 566, "count": 1213, "decode_str": "\u03b1\u03b9"} -{"id": 31252, "token": "ylic", "merges": "y lic", "raw_count": 1213, "count": 1213, "decode_str": "ylic"} -{"id": 9952, "token": "\\^", "merges": "\\ ^", "raw_count": 1133, "count": 1213, "decode_str": "\\^"} -{"id": 42958, "token": "\u0120Handbook", "merges": "\u0120Hand book", "raw_count": 1214, "count": 1214, "decode_str": " Handbook"} -{"id": 23299, "token": "\u0120leukemia", "merges": "\u0120leuk emia", "raw_count": 1214, "count": 1214, "decode_str": " leukemia"} -{"id": 31926, "token": "\u0120footballer", "merges": "\u0120football er", "raw_count": 1215, "count": 1215, "decode_str": " footballer"} -{"id": 27613, "token": "\u0120playoffs", "merges": "\u0120play offs", "raw_count": 1215, "count": 1215, "decode_str": " playoffs"} -{"id": 42094, "token": "\u0120cyclists", "merges": "\u0120cycl ists", "raw_count": 1216, "count": 1216, "decode_str": " cyclists"} -{"id": 25689, "token": "\u0120Arnold", "merges": "\u0120Arn old", "raw_count": 1216, "count": 1216, "decode_str": " Arnold"} -{"id": 31442, "token": "\u0120anemia", "merges": "\u0120an emia", "raw_count": 1216, "count": 1216, "decode_str": " anemia"} -{"id": 37683, "token": "idazole", "merges": "id azole", "raw_count": 1216, "count": 1216, "decode_str": "idazole"} -{"id": 45106, "token": "\u0120Vinc", "merges": "\u0120V inc", "raw_count": 1216, "count": 1216, "decode_str": " Vinc"} -{"id": 28324, "token": "\u0120conformation", "merges": "\u0120con formation", "raw_count": 1217, "count": 1217, "decode_str": " conformation"} -{"id": 49374, "token": "\u0120unexplained", "merges": "\u0120unexpl ained", "raw_count": 1217, "count": 1217, "decode_str": " unexplained"} -{"id": 45495, "token": "\u0120_________________________________", "merges": "\u0120_ ________________________________", "raw_count": 1218, "count": 1218, "decode_str": " _________________________________"} -{"id": 33626, "token": "WriteLine", "merges": "Write Line", "raw_count": 1218, "count": 1218, "decode_str": "WriteLine"} -{"id": 35516, "token": "\u0120encephal", "merges": "\u0120en cephal", "raw_count": 1218, "count": 1218, "decode_str": " encephal"} -{"id": 27353, "token": "\u0120Hopkins", "merges": "\u0120Hop kins", "raw_count": 1218, "count": 1218, "decode_str": " Hopkins"} -{"id": 44603, "token": "\u0120flakes", "merges": "\u0120fl akes", "raw_count": 1218, "count": 1218, "decode_str": " flakes"} -{"id": 37879, "token": "\u0120ITS", "merges": "\u0120I TS", "raw_count": 1218, "count": 1218, "decode_str": " ITS"} -{"id": 34233, "token": "\u0120doping", "merges": "\u0120dop ing", "raw_count": 1219, "count": 1219, "decode_str": " doping"} -{"id": 45816, "token": "\u0120Amin", "merges": "\u0120A min", "raw_count": 1219, "count": 1219, "decode_str": " Amin"} -{"id": 31353, "token": "ECs", "merges": "EC s", "raw_count": 1219, "count": 1219, "decode_str": "ECs"} -{"id": 45190, "token": "\u0120empirically", "merges": "\u0120empir ically", "raw_count": 1220, "count": 1220, "decode_str": " empirically"} -{"id": 50159, "token": "\u0120roadway", "merges": "\u0120road way", "raw_count": 1220, "count": 1220, "decode_str": " roadway"} -{"id": 47392, "token": "\u0120Luna", "merges": "\u0120L una", "raw_count": 1220, "count": 1220, "decode_str": " Luna"} -{"id": 11356, "token": "\u0120NJ", "merges": "\u0120N J", "raw_count": 1220, "count": 1220, "decode_str": " NJ"} -{"id": 44564, "token": "})-", "merges": "}) -", "raw_count": 1220, "count": 1220, "decode_str": "})-"} -{"id": 43188, "token": "\u0120Estado", "merges": "\u0120Est ado", "raw_count": 1221, "count": 1221, "decode_str": " Estado"} -{"id": 40389, "token": "\u0120econ", "merges": "\u0120e con", "raw_count": 1084, "count": 1221, "decode_str": " econ"} -{"id": 23773, "token": "\u0120Rice", "merges": "\u0120R ice", "raw_count": 1221, "count": 1221, "decode_str": " Rice"} -{"id": 47860, "token": "\u0120insightful", "merges": "\u0120insight ful", "raw_count": 1222, "count": 1222, "decode_str": " insightful"} -{"id": 24609, "token": "\u0120Commander", "merges": "\u0120Comm ander", "raw_count": 1222, "count": 1222, "decode_str": " Commander"} -{"id": 36190, "token": "\u0120Cardinal", "merges": "\u0120Card inal", "raw_count": 1222, "count": 1222, "decode_str": " Cardinal"} -{"id": 16358, "token": "\u0120Anthony", "merges": "\u0120Anth ony", "raw_count": 1222, "count": 1222, "decode_str": " Anthony"} -{"id": 50216, "token": "\u0120glimps", "merges": "\u0120gl imps", "raw_count": 1222, "count": 1222, "decode_str": " glimps"} -{"id": 22471, "token": "\u0120glycol", "merges": "\u0120gly col", "raw_count": 1222, "count": 1222, "decode_str": " glycol"} -{"id": 36029, "token": "\u0120Hein", "merges": "\u0120He in", "raw_count": 1222, "count": 1222, "decode_str": " Hein"} -{"id": 47751, "token": "\u0120interstellar", "merges": "\u0120inter stellar", "raw_count": 1223, "count": 1223, "decode_str": " interstellar"} -{"id": 36145, "token": "\u0120Previously", "merges": "\u0120Pre viously", "raw_count": 1223, "count": 1223, "decode_str": " Previously"} -{"id": 46812, "token": "ItemGroup", "merges": "Item Group", "raw_count": 1223, "count": 1223, "decode_str": "ItemGroup"} -{"id": 49186, "token": "oriously", "merges": "or iously", "raw_count": 1223, "count": 1223, "decode_str": "oriously"} -{"id": 45734, "token": "\u0120Meaning", "merges": "\u0120Mean ing", "raw_count": 1223, "count": 1223, "decode_str": " Meaning"} -{"id": 41482, "token": "\u0120shakes", "merges": "\u0120sh akes", "raw_count": 1223, "count": 1223, "decode_str": " shakes"} -{"id": 39959, "token": "\u0120Buzz", "merges": "\u0120Bu zz", "raw_count": 1223, "count": 1223, "decode_str": " Buzz"} -{"id": 50368, "token": "\u00e2\u0138\u00ba", "merges": "\u00e2\u0138 \u00ba", "raw_count": 1223, "count": 1223, "decode_str": "\u25ba"} -{"id": 21826, "token": "\u0120LICENSE", "merges": "\u0120L ICENSE", "raw_count": 1224, "count": 1224, "decode_str": " LICENSE"} -{"id": 28029, "token": "\u0120Ellis", "merges": "\u0120Ell is", "raw_count": 1224, "count": 1224, "decode_str": " Ellis"} -{"id": 18827, "token": "\u0120Jess", "merges": "\u0120J ess", "raw_count": 491, "count": 1224, "decode_str": " Jess"} -{"id": 19403, "token": "\u0120retrospective", "merges": "\u0120retros pective", "raw_count": 1225, "count": 1225, "decode_str": " retrospective"} -{"id": 31235, "token": "\u0120Pit", "merges": "\u0120P it", "raw_count": 1225, "count": 1225, "decode_str": " Pit"} -{"id": 46172, "token": "\u0120surreal", "merges": "\u0120sur real", "raw_count": 1226, "count": 1226, "decode_str": " surreal"} -{"id": 41806, "token": "\u0120autre", "merges": "\u0120aut re", "raw_count": 1226, "count": 1226, "decode_str": " autre"} -{"id": 46663, "token": "\u00e1\u00bb\u0123", "merges": "\u00e1\u00bb \u0123", "raw_count": 1226, "count": 1226, "decode_str": "\u1ec1"} -{"id": 28060, "token": "\u0120Emergency", "merges": "\u0120Emer gency", "raw_count": 1227, "count": 1227, "decode_str": " Emergency"} -{"id": 20718, "token": "\u0120Memorial", "merges": "\u0120Mem orial", "raw_count": 1227, "count": 1227, "decode_str": " Memorial"} -{"id": 45399, "token": "\u0120firefighters", "merges": "\u0120firef ighters", "raw_count": 1228, "count": 1228, "decode_str": " firefighters"} -{"id": 36802, "token": "InstanceState", "merges": "Instance State", "raw_count": 1228, "count": 1228, "decode_str": "InstanceState"} -{"id": 40674, "token": "\u0120syringe", "merges": "\u0120sy ringe", "raw_count": 1228, "count": 1228, "decode_str": " syringe"} -{"id": 40493, "token": "\u0120helical", "merges": "\u0120hel ical", "raw_count": 1228, "count": 1228, "decode_str": " helical"} -{"id": 39309, "token": "\u0120pissed", "merges": "\u0120piss ed", "raw_count": 1228, "count": 1228, "decode_str": " pissed"} -{"id": 38402, "token": "carbox", "merges": "car box", "raw_count": 1228, "count": 1228, "decode_str": "carbox"} -{"id": 43729, "token": "\u0120Lands", "merges": "\u0120L ands", "raw_count": 1228, "count": 1228, "decode_str": " Lands"} -{"id": 31721, "token": "\u0120Shir", "merges": "\u0120Sh ir", "raw_count": 578, "count": 1228, "decode_str": " Shir"} -{"id": 22948, "token": "\u0120Ern", "merges": "\u0120Er n", "raw_count": 162, "count": 1228, "decode_str": " Ern"} -{"id": 27527, "token": "CUSS", "merges": "C USS", "raw_count": 795, "count": 1228, "decode_str": "CUSS"} -{"id": 38619, "token": "\u00e0\u00a5\u0123", "merges": "\u00e0\u00a5 \u0123", "raw_count": 1228, "count": 1228, "decode_str": "\u0941"} -{"id": 46290, "token": "\u0120\u00c2\u00a1", "merges": "\u0120\u00c2 \u00a1", "raw_count": 1228, "count": 1228, "decode_str": " \u00a1"} -{"id": 44324, "token": "\u0120quenching", "merges": "\u0120qu enching", "raw_count": 1229, "count": 1229, "decode_str": " quenching"} -{"id": 42024, "token": "\u0120litig", "merges": "\u0120lit ig", "raw_count": 1229, "count": 1229, "decode_str": " litig"} -{"id": 48098, "token": "\u0120\u00d0\u00bb\u00d1\u0130", "merges": "\u0120\u00d0\u00bb \u00d1\u0130", "raw_count": 1229, "count": 1229, "decode_str": " \u043b\u044e"} -{"id": 7524, "token": "\u0120{{\\", "merges": "\u0120{ {\\", "raw_count": 1229, "count": 1229, "decode_str": " {{\\"} -{"id": 13803, "token": "\u0120\u00ce\u0136", "merges": "\u0120\u00ce \u0136", "raw_count": 1229, "count": 1229, "decode_str": " \u0394"} -{"id": 23969, "token": "\u0120\u00e0\u00a6", "merges": "\u0120 \u00e0\u00a6", "raw_count": 1229, "count": 1229, "decode_str": " \ufffd"} -{"id": 11643, "token": "\u0120Harry", "merges": "\u0120Har ry", "raw_count": 1230, "count": 1230, "decode_str": " Harry"} -{"id": 44595, "token": "TIOC", "merges": "TI OC", "raw_count": 1230, "count": 1230, "decode_str": "TIOC"} -{"id": 18823, "token": "\u0120Jenn", "merges": "\u0120J enn", "raw_count": 384, "count": 1231, "decode_str": " Jenn"} -{"id": 19329, "token": "\u0120KIND", "merges": "\u0120K IND", "raw_count": 1231, "count": 1231, "decode_str": " KIND"} -{"id": 41877, "token": "\u0120faut", "merges": "\u0120f aut", "raw_count": 1231, "count": 1231, "decode_str": " faut"} -{"id": 35160, "token": "\u0120Gor", "merges": "\u0120G or", "raw_count": 1231, "count": 1231, "decode_str": " Gor"} -{"id": 9028, "token": "\u0120\u00ce\u00ba", "merges": "\u0120\u00ce \u00ba", "raw_count": 681, "count": 1231, "decode_str": " \u03ba"} -{"id": 24468, "token": "\u0120inhibiting", "merges": "\u0120inhib iting", "raw_count": 1232, "count": 1232, "decode_str": " inhibiting"} -{"id": 35491, "token": "\u0120feminine", "merges": "\u0120fem inine", "raw_count": 1232, "count": 1232, "decode_str": " feminine"} -{"id": 43479, "token": "\u0120Pepper", "merges": "\u0120Pe pper", "raw_count": 1232, "count": 1232, "decode_str": " Pepper"} -{"id": 39727, "token": "\u00d9\u012a\u00d8\u00b1", "merges": "\u00d9\u012a \u00d8\u00b1", "raw_count": 1232, "count": 1232, "decode_str": "\u0648\u0631"} -{"id": 33472, "token": "\u00c3\u00bcl", "merges": "\u00c3\u00bc l", "raw_count": 1232, "count": 1232, "decode_str": "\u00fcl"} -{"id": 40366, "token": "\u00e0\u00b9\u0126", "merges": "\u00e0\u00b9 \u0126", "raw_count": 1232, "count": 1232, "decode_str": "\u0e44"} -{"id": 26773, "token": "\u0120radiotherapy", "merges": "\u0120radi otherapy", "raw_count": 1233, "count": 1233, "decode_str": " radiotherapy"} -{"id": 44572, "token": "asac", "merges": "as ac", "raw_count": 1233, "count": 1233, "decode_str": "asac"} -{"id": 25120, "token": "\u0120NSA", "merges": "\u0120N SA", "raw_count": 1233, "count": 1233, "decode_str": " NSA"} -{"id": 31467, "token": "Bigg", "merges": "Big g", "raw_count": 1233, "count": 1233, "decode_str": "Bigg"} -{"id": 7974, "token": "\u00c3\u0124", "merges": "\u00c3 \u0124", "raw_count": 1215, "count": 1233, "decode_str": "\u00c2"} -{"id": 45378, "token": "\u0120medalists", "merges": "\u0120medal ists", "raw_count": 1234, "count": 1234, "decode_str": " medalists"} -{"id": 28193, "token": "\u0120starring", "merges": "\u0120star ring", "raw_count": 1234, "count": 1234, "decode_str": " starring"} -{"id": 46693, "token": "\u0120Dollar", "merges": "\u0120D ollar", "raw_count": 1234, "count": 1234, "decode_str": " Dollar"} -{"id": 11308, "token": "\u0120Greek", "merges": "\u0120G reek", "raw_count": 1234, "count": 1234, "decode_str": " Greek"} -{"id": 49079, "token": "\u0120BACKGROUND", "merges": "\u0120BACK GROUND", "raw_count": 1235, "count": 1235, "decode_str": " BACKGROUND"} -{"id": 22758, "token": "\u0120Heaven", "merges": "\u0120He aven", "raw_count": 1235, "count": 1235, "decode_str": " Heaven"} -{"id": 31529, "token": "\u0120Loren", "merges": "\u0120L oren", "raw_count": 844, "count": 1235, "decode_str": " Loren"} -{"id": 43050, "token": "\u0120Dj", "merges": "\u0120D j", "raw_count": 1235, "count": 1235, "decode_str": " Dj"} -{"id": 40966, "token": "\u0120Magnetic", "merges": "\u0120M agnetic", "raw_count": 1236, "count": 1236, "decode_str": " Magnetic"} -{"id": 35955, "token": "\u0120../../", "merges": "\u0120 ../../", "raw_count": 1236, "count": 1236, "decode_str": " ../../"} -{"id": 49446, "token": "\u0120confl", "merges": "\u0120con fl", "raw_count": 1236, "count": 1236, "decode_str": " confl"} -{"id": 45589, "token": "\u0120characterizes", "merges": "\u0120character izes", "raw_count": 1237, "count": 1237, "decode_str": " characterizes"} -{"id": 37817, "token": "\u0120Leadership", "merges": "\u0120Lead ership", "raw_count": 1237, "count": 1237, "decode_str": " Leadership"} -{"id": 41403, "token": "\u0120insanity", "merges": "\u0120ins anity", "raw_count": 1237, "count": 1237, "decode_str": " insanity"} -{"id": 36690, "token": "\u0120branched", "merges": "\u0120branc hed", "raw_count": 1237, "count": 1237, "decode_str": " branched"} -{"id": 49897, "token": "ostatin", "merges": "ost atin", "raw_count": 1237, "count": 1237, "decode_str": "ostatin"} -{"id": 35140, "token": "\u0120apo", "merges": "\u0120ap o", "raw_count": 1237, "count": 1237, "decode_str": " apo"} -{"id": 33225, "token": "\u00e0\u00a6\u00be", "merges": "\u00e0\u00a6 \u00be", "raw_count": 1237, "count": 1237, "decode_str": "\u09be"} -{"id": 48591, "token": "Asked", "merges": "As ked", "raw_count": 1238, "count": 1238, "decode_str": "Asked"} -{"id": 13771, "token": "\u0120Rather", "merges": "\u0120R ather", "raw_count": 1239, "count": 1239, "decode_str": " Rather"} -{"id": 35500, "token": "\u0120pacing", "merges": "\u0120p acing", "raw_count": 1239, "count": 1239, "decode_str": " pacing"} -{"id": 34392, "token": "\u0120RSV", "merges": "\u0120R SV", "raw_count": 1239, "count": 1239, "decode_str": " RSV"} -{"id": 43389, "token": "\u0120\u00c2\u00a5", "merges": "\u0120\u00c2 \u00a5", "raw_count": 1239, "count": 1239, "decode_str": " \u00a5"} -{"id": 48491, "token": "\u0120pessoas", "merges": "\u0120pesso as", "raw_count": 1240, "count": 1240, "decode_str": " pessoas"} -{"id": 48822, "token": "\u0120playful", "merges": "\u0120play ful", "raw_count": 1240, "count": 1240, "decode_str": " playful"} -{"id": 44974, "token": "\u0120shouts", "merges": "\u0120sh outs", "raw_count": 1240, "count": 1240, "decode_str": " shouts"} -{"id": 49451, "token": "\u0120Submitted", "merges": "\u0120Sub mitted", "raw_count": 1241, "count": 1241, "decode_str": " Submitted"} -{"id": 47223, "token": "\u0120unpaired", "merges": "\u0120un paired", "raw_count": 1241, "count": 1241, "decode_str": " unpaired"} -{"id": 35158, "token": "apopt", "merges": "ap opt", "raw_count": 1135, "count": 1241, "decode_str": "apopt"} -{"id": 19619, "token": "\u0120Okay", "merges": "\u0120O kay", "raw_count": 1241, "count": 1241, "decode_str": " Okay"} -{"id": 49323, "token": "\u0120\u00d0\u00b2\u00d0\u00be", "merges": "\u0120\u00d0\u00b2 \u00d0\u00be", "raw_count": 1241, "count": 1241, "decode_str": " \u0432\u043e"} -{"id": 36702, "token": "\u0120Kot", "merges": "\u0120K ot", "raw_count": 1241, "count": 1241, "decode_str": " Kot"} -{"id": 49569, "token": "\u0120flares", "merges": "\u0120fl ares", "raw_count": 1242, "count": 1242, "decode_str": " flares"} -{"id": 11301, "token": "\u0120Bush", "merges": "\u0120B ush", "raw_count": 1242, "count": 1242, "decode_str": " Bush"} -{"id": 30912, "token": "\u0120Stre", "merges": "\u0120St re", "raw_count": 1242, "count": 1242, "decode_str": " Stre"} -{"id": 46823, "token": "\u00e2\u0122\u0136'", "merges": "\u00e2\u0122\u0136 '", "raw_count": 1242, "count": 1242, "decode_str": "\u2014'"} -{"id": 32133, "token": "\u0120Eisen", "merges": "\u0120E isen", "raw_count": 1243, "count": 1243, "decode_str": " Eisen"} -{"id": 26417, "token": "\u0120Nar", "merges": "\u0120N ar", "raw_count": 1243, "count": 1243, "decode_str": " Nar"} -{"id": 43074, "token": "\u0120mattered", "merges": "\u0120mat tered", "raw_count": 1244, "count": 1244, "decode_str": " mattered"} -{"id": 42694, "token": "atase", "merges": "at ase", "raw_count": 1244, "count": 1244, "decode_str": "atase"} -{"id": 34381, "token": "\u0120gew", "merges": "\u0120g ew", "raw_count": 1244, "count": 1244, "decode_str": " gew"} -{"id": 40491, "token": "\u0120halogen", "merges": "\u0120hal ogen", "raw_count": 1245, "count": 1245, "decode_str": " halogen"} -{"id": 35677, "token": "\u0120Stern", "merges": "\u0120S tern", "raw_count": 1245, "count": 1245, "decode_str": " Stern"} -{"id": 48397, "token": "\u0120contrasted", "merges": "\u0120contrast ed", "raw_count": 1246, "count": 1246, "decode_str": " contrasted"} -{"id": 39377, "token": "\u0120speculated", "merges": "\u0120spec ulated", "raw_count": 1246, "count": 1246, "decode_str": " speculated"} -{"id": 49358, "token": "\u0120monstrous", "merges": "\u0120mon strous", "raw_count": 1246, "count": 1246, "decode_str": " monstrous"} -{"id": 28200, "token": "\u0120Maxwell", "merges": "\u0120Max well", "raw_count": 1246, "count": 1246, "decode_str": " Maxwell"} -{"id": 44074, "token": "\u0120Lights", "merges": "\u0120L ights", "raw_count": 1246, "count": 1246, "decode_str": " Lights"} -{"id": 41196, "token": "\u0120Falcon", "merges": "\u0120Fal con", "raw_count": 1246, "count": 1246, "decode_str": " Falcon"} -{"id": 48195, "token": "\u0120SMC", "merges": "\u0120S MC", "raw_count": 1246, "count": 1246, "decode_str": " SMC"} -{"id": 34342, "token": "dimethyl", "merges": "dim ethyl", "raw_count": 1247, "count": 1247, "decode_str": "dimethyl"} -{"id": 32904, "token": "\u0120Plasma", "merges": "\u0120Pl asma", "raw_count": 1248, "count": 1248, "decode_str": " Plasma"} -{"id": 44676, "token": "\u0120twists", "merges": "\u0120tw ists", "raw_count": 1248, "count": 1248, "decode_str": " twists"} -{"id": 45385, "token": "\u0120Skype", "merges": "\u0120Sk ype", "raw_count": 1248, "count": 1248, "decode_str": " Skype"} -{"id": 35439, "token": "Lemma", "merges": "Lem ma", "raw_count": 1248, "count": 1248, "decode_str": "Lemma"} -{"id": 16329, "token": "\u0120susceptibility", "merges": "\u0120suscept ibility", "raw_count": 1249, "count": 1249, "decode_str": " susceptibility"} -{"id": 48504, "token": "\u0120excused", "merges": "\u0120exc used", "raw_count": 1249, "count": 1249, "decode_str": " excused"} -{"id": 43835, "token": "Whenever", "merges": "Whe never", "raw_count": 1249, "count": 1249, "decode_str": "Whenever"} -{"id": 17650, "token": "\u0120Walter", "merges": "\u0120Wal ter", "raw_count": 1249, "count": 1249, "decode_str": " Walter"} -{"id": 34827, "token": "\u0120Beg", "merges": "\u0120B eg", "raw_count": 1249, "count": 1249, "decode_str": " Beg"} -{"id": 23124, "token": "\u0120Jur", "merges": "\u0120J ur", "raw_count": 1249, "count": 1249, "decode_str": " Jur"} -{"id": 32044, "token": "<_", "merges": "< _", "raw_count": 1249, "count": 1249, "decode_str": "<_"} -{"id": 46672, "token": "\u0120caliber", "merges": "\u0120cal iber", "raw_count": 1250, "count": 1250, "decode_str": " caliber"} -{"id": 9643, "token": "\u0120Britain", "merges": "\u0120Brit ain", "raw_count": 1250, "count": 1250, "decode_str": " Britain"} -{"id": 31052, "token": "\u0120atyp", "merges": "\u0120at yp", "raw_count": 416, "count": 1250, "decode_str": " atyp"} -{"id": 41098, "token": "\u0120Shan", "merges": "\u0120Sh an", "raw_count": 1250, "count": 1250, "decode_str": " Shan"} -{"id": 14566, "token": "\u0120Having", "merges": "\u0120H aving", "raw_count": 1251, "count": 1251, "decode_str": " Having"} -{"id": 37477, "token": "\u0120Tong", "merges": "\u0120T ong", "raw_count": 1251, "count": 1251, "decode_str": " Tong"} -{"id": 31661, "token": "\u0120Cec", "merges": "\u0120C ec", "raw_count": 953, "count": 1251, "decode_str": " Cec"} -{"id": 20847, "token": "\u0120skeletal", "merges": "\u0120ske letal", "raw_count": 1252, "count": 1252, "decode_str": " skeletal"} -{"id": 21385, "token": "\u0120Rab", "merges": "\u0120R ab", "raw_count": 1214, "count": 1252, "decode_str": " Rab"} -{"id": 28377, "token": "\u0120Ras", "merges": "\u0120R as", "raw_count": 1252, "count": 1252, "decode_str": " Ras"} -{"id": 29267, "token": "\u0120dialysis", "merges": "\u0120dial ysis", "raw_count": 1253, "count": 1253, "decode_str": " dialysis"} -{"id": 26940, "token": "\u0120Authors", "merges": "\u0120Auth ors", "raw_count": 1253, "count": 1253, "decode_str": " Authors"} -{"id": 28992, "token": "ophilic", "merges": "ophil ic", "raw_count": 1253, "count": 1253, "decode_str": "ophilic"} -{"id": 41419, "token": "NotNull", "merges": "Not Null", "raw_count": 1253, "count": 1253, "decode_str": "NotNull"} -{"id": 15685, "token": "\u0120incubation", "merges": "\u0120incub ation", "raw_count": 1254, "count": 1254, "decode_str": " incubation"} -{"id": 37665, "token": "\u0120Cities", "merges": "\u0120C ities", "raw_count": 1254, "count": 1254, "decode_str": " Cities"} -{"id": 37745, "token": "\u0120Twin", "merges": "\u0120Tw in", "raw_count": 1254, "count": 1254, "decode_str": " Twin"} -{"id": 40916, "token": "innen", "merges": "inn en", "raw_count": 1254, "count": 1254, "decode_str": "innen"} -{"id": 38258, "token": "onyl", "merges": "on yl", "raw_count": 1254, "count": 1254, "decode_str": "onyl"} -{"id": 50206, "token": "\u0120groaned", "merges": "\u0120gro aned", "raw_count": 1255, "count": 1255, "decode_str": " groaned"} -{"id": 21789, "token": "\u0120Bah", "merges": "\u0120B ah", "raw_count": 1256, "count": 1256, "decode_str": " Bah"} -{"id": 17669, "token": "\u0120lui", "merges": "\u0120l ui", "raw_count": 1256, "count": 1256, "decode_str": " lui"} -{"id": 26601, "token": "\u00e0\u00ac", "merges": "\u00e0 \u00ac", "raw_count": 1256, "count": 1256, "decode_str": "\ufffd"} -{"id": 31400, "token": "\u0120Schmidt", "merges": "\u0120Sch midt", "raw_count": 1257, "count": 1257, "decode_str": " Schmidt"} -{"id": 39123, "token": "\u0120Canon", "merges": "\u0120Can on", "raw_count": 1257, "count": 1257, "decode_str": " Canon"} -{"id": 23801, "token": "\u0120Honor", "merges": "\u0120Hon or", "raw_count": 1257, "count": 1257, "decode_str": " Honor"} -{"id": 49573, "token": "\u0120Chow", "merges": "\u0120Ch ow", "raw_count": 1257, "count": 1257, "decode_str": " Chow"} -{"id": 24965, "token": "\u0120Collabor", "merges": "\u0120Coll abor", "raw_count": 716, "count": 1258, "decode_str": " Collabor"} -{"id": 24538, "token": "\u0120Berkeley", "merges": "\u0120Ber keley", "raw_count": 1258, "count": 1258, "decode_str": " Berkeley"} -{"id": 19995, "token": "\u0120Murray", "merges": "\u0120Mur ray", "raw_count": 1258, "count": 1258, "decode_str": " Murray"} -{"id": 47270, "token": "\u0120\u00d0\u00be\u00d0\u00bd", "merges": "\u0120\u00d0\u00be \u00d0\u00bd", "raw_count": 1258, "count": 1258, "decode_str": " \u043e\u043d"} -{"id": 23549, "token": "\u0120Dow", "merges": "\u0120D ow", "raw_count": 1258, "count": 1258, "decode_str": " Dow"} -{"id": 32212, "token": "\u0120Nutrition", "merges": "\u0120Nut rition", "raw_count": 1259, "count": 1259, "decode_str": " Nutrition"} -{"id": 44597, "token": "\u0120medically", "merges": "\u0120med ically", "raw_count": 1259, "count": 1259, "decode_str": " medically"} -{"id": 46449, "token": "\u0120causality", "merges": "\u0120caus ality", "raw_count": 1259, "count": 1259, "decode_str": " causality"} -{"id": 37645, "token": "\u0120Rapid", "merges": "\u0120Rap id", "raw_count": 1259, "count": 1259, "decode_str": " Rapid"} -{"id": 41075, "token": "\u0120exploratory", "merges": "\u0120explor atory", "raw_count": 1260, "count": 1260, "decode_str": " exploratory"} -{"id": 43707, "token": "\u0120joking", "merges": "\u0120j oking", "raw_count": 1260, "count": 1260, "decode_str": " joking"} -{"id": 37351, "token": "\u0120Facts", "merges": "\u0120F acts", "raw_count": 1260, "count": 1260, "decode_str": " Facts"} -{"id": 49485, "token": "geons", "merges": "ge ons", "raw_count": 1260, "count": 1260, "decode_str": "geons"} -{"id": 48060, "token": "\u0120enhancer", "merges": "\u0120enh ancer", "raw_count": 1261, "count": 1261, "decode_str": " enhancer"} -{"id": 46375, "token": "\u0120Rainbow", "merges": "\u0120Rain bow", "raw_count": 1261, "count": 1261, "decode_str": " Rainbow"} -{"id": 49623, "token": "Soviet", "merges": "Sov iet", "raw_count": 1261, "count": 1261, "decode_str": "Soviet"} -{"id": 18559, "token": "\u0120Jos", "merges": "\u0120J os", "raw_count": 1132, "count": 1261, "decode_str": " Jos"} -{"id": 50348, "token": "\u00e2\u0137\u0142", "merges": "\u00e2\u0137 \u0142", "raw_count": 1261, "count": 1261, "decode_str": "\u2560"} -{"id": 35600, "token": "\u0120trapping", "merges": "\u0120tra pping", "raw_count": 1262, "count": 1262, "decode_str": " trapping"} -{"id": 30309, "token": "\u0120ECM", "merges": "\u0120E CM", "raw_count": 1262, "count": 1262, "decode_str": " ECM"} -{"id": 12227, "token": "=\"../../", "merges": "=\" ../../", "raw_count": 1097, "count": 1263, "decode_str": "=\"../../"} -{"id": 48978, "token": "oplasma", "merges": "opl asma", "raw_count": 1263, "count": 1263, "decode_str": "oplasma"} -{"id": 22921, "token": "\u0120Eld", "merges": "\u0120E ld", "raw_count": 491, "count": 1263, "decode_str": " Eld"} -{"id": 19804, "token": "\u0120Regional", "merges": "\u0120Reg ional", "raw_count": 1264, "count": 1264, "decode_str": " Regional"} -{"id": 42133, "token": "\u0120amenable", "merges": "\u0120am enable", "raw_count": 1264, "count": 1264, "decode_str": " amenable"} -{"id": 19810, "token": "\u0120Others", "merges": "\u0120Other s", "raw_count": 1264, "count": 1264, "decode_str": " Others"} -{"id": 26995, "token": "INION", "merges": "IN ION", "raw_count": 1185, "count": 1264, "decode_str": "INION"} -{"id": 18221, "token": "\u00c3\u0127", "merges": "\u00c3 \u0127", "raw_count": 1264, "count": 1264, "decode_str": "\u00c5"} -{"id": 17883, "token": "\u0120myocardial", "merges": "\u0120myocard ial", "raw_count": 1265, "count": 1265, "decode_str": " myocardial"} -{"id": 33110, "token": "\u0120canine", "merges": "\u0120can ine", "raw_count": 1265, "count": 1265, "decode_str": " canine"} -{"id": 41410, "token": "PropertyGroup", "merges": "Property Group", "raw_count": 1266, "count": 1266, "decode_str": "PropertyGroup"} -{"id": 35781, "token": "rivolous", "merges": "rivol ous", "raw_count": 182, "count": 1266, "decode_str": "rivolous"} -{"id": 30668, "token": "\u0120mascul", "merges": "\u0120mas cul", "raw_count": 532, "count": 1266, "decode_str": " mascul"} -{"id": 42475, "token": "\u0120Chance", "merges": "\u0120Ch ance", "raw_count": 1266, "count": 1266, "decode_str": " Chance"} -{"id": 38732, "token": "\u0120hyste", "merges": "\u0120hy ste", "raw_count": 1266, "count": 1266, "decode_str": " hyste"} -{"id": 46119, "token": "ESULT", "merges": "ES ULT", "raw_count": 1266, "count": 1266, "decode_str": "ESULT"} -{"id": 30672, "token": "\u0120Nas", "merges": "\u0120N as", "raw_count": 1266, "count": 1266, "decode_str": " Nas"} -{"id": 46674, "token": "\u00e3\u0123\u00b3", "merges": "\u00e3\u0123 \u00b3", "raw_count": 1266, "count": 1266, "decode_str": "\u3073"} -{"id": 41776, "token": "\u0120prescribing", "merges": "\u0120pres cribing", "raw_count": 1267, "count": 1267, "decode_str": " prescribing"} -{"id": 27867, "token": "\u0120sequenced", "merges": "\u0120sequ enced", "raw_count": 1267, "count": 1267, "decode_str": " sequenced"} -{"id": 40737, "token": "\u0120Campus", "merges": "\u0120Camp us", "raw_count": 1267, "count": 1267, "decode_str": " Campus"} -{"id": 36797, "token": "\u0120Mutual", "merges": "\u0120Mut ual", "raw_count": 1267, "count": 1267, "decode_str": " Mutual"} -{"id": 44726, "token": "\u0120Rates", "merges": "\u0120R ates", "raw_count": 1267, "count": 1267, "decode_str": " Rates"} -{"id": 39636, "token": "\u00e3\u0124\u0124\u00e3\u0123\u00ae", "merges": "\u00e3\u0124\u0124 \u00e3\u0123\u00ae", "raw_count": 1267, "count": 1267, "decode_str": "\u3082\u306e"} -{"id": 50372, "token": "\u00e2\u0139\u0129", "merges": "\u00e2\u0139 \u0129", "raw_count": 1267, "count": 1267, "decode_str": "\u25c7"} -{"id": 39216, "token": "\u0120granules", "merges": "\u0120gran ules", "raw_count": 1268, "count": 1268, "decode_str": " granules"} -{"id": 52248, "token": "\u00e6\u0140\u00b1", "merges": "\u00e6\u0140 \u00b1", "raw_count": 1268, "count": 1268, "decode_str": "\u67b1"} -{"id": 46918, "token": "Qaeda", "merges": "Q aeda", "raw_count": 1269, "count": 1269, "decode_str": "Qaeda"} -{"id": 15088, "token": "\u0120secretion", "merges": "\u0120secret ion", "raw_count": 1270, "count": 1270, "decode_str": " secretion"} -{"id": 50352, "token": "\u00e2\u0137\u00b0", "merges": "\u00e2\u0137 \u00b0", "raw_count": 1270, "count": 1270, "decode_str": "\u2570"} -{"id": 21706, "token": "\u0120Hills", "merges": "\u0120H ills", "raw_count": 1271, "count": 1271, "decode_str": " Hills"} -{"id": 29741, "token": "\u00e3\u0123\u00a7\u00e3\u0123\u00af", "merges": "\u00e3\u0123\u00a7 \u00e3\u0123\u00af", "raw_count": 1271, "count": 1271, "decode_str": "\u3067\u306f"} -{"id": 22406, "token": "ocarcin", "merges": "oc arcin", "raw_count": 156, "count": 1272, "decode_str": "ocarcin"} -{"id": 45700, "token": "\u0120vibe", "merges": "\u0120v ibe", "raw_count": 1272, "count": 1272, "decode_str": " vibe"} -{"id": 45719, "token": ",'\"", "merges": ",' \"", "raw_count": 1272, "count": 1272, "decode_str": ",'\""} -{"id": 44880, "token": "\u0120therapists", "merges": "\u0120therap ists", "raw_count": 1273, "count": 1273, "decode_str": " therapists"} -{"id": 44696, "token": "\u0120hydroxide", "merges": "\u0120hydrox ide", "raw_count": 1273, "count": 1273, "decode_str": " hydroxide"} -{"id": 21872, "token": "\u0120Perry", "merges": "\u0120Per ry", "raw_count": 1273, "count": 1273, "decode_str": " Perry"} -{"id": 44892, "token": "\u0120Blind", "merges": "\u0120Bl ind", "raw_count": 1273, "count": 1273, "decode_str": " Blind"} -{"id": 29880, "token": "\u0120Pont", "merges": "\u0120P ont", "raw_count": 1273, "count": 1273, "decode_str": " Pont"} -{"id": 48167, "token": "][^", "merges": "] [^", "raw_count": 1273, "count": 1273, "decode_str": "][^"} -{"id": 48306, "token": "\u0120formaldehyde", "merges": "\u0120formal dehyde", "raw_count": 1274, "count": 1274, "decode_str": " formaldehyde"} -{"id": 50104, "token": "\u0120dramat", "merges": "\u0120dram at", "raw_count": 1274, "count": 1274, "decode_str": " dramat"} -{"id": 48230, "token": "\u0120spong", "merges": "\u0120sp ong", "raw_count": 1274, "count": 1274, "decode_str": " spong"} -{"id": 21954, "token": "\u0120Abd", "merges": "\u0120Ab d", "raw_count": 527, "count": 1274, "decode_str": " Abd"} -{"id": 43135, "token": "\u0120SES", "merges": "\u0120S ES", "raw_count": 1274, "count": 1274, "decode_str": " SES"} -{"id": 44220, "token": "\u0120Treasure", "merges": "\u0120Tre asure", "raw_count": 1275, "count": 1275, "decode_str": " Treasure"} -{"id": 7814, "token": "\u0120Saturday", "merges": "\u0120S aturday", "raw_count": 1275, "count": 1275, "decode_str": " Saturday"} -{"id": 23665, "token": "\u00c5\u00af", "merges": "\u00c5 \u00af", "raw_count": 1276, "count": 1276, "decode_str": "\u016f"} -{"id": 33344, "token": "\u0120tunneling", "merges": "\u0120tunn eling", "raw_count": 1277, "count": 1277, "decode_str": " tunneling"} -{"id": 28013, "token": "astolic", "merges": "ast olic", "raw_count": 834, "count": 1277, "decode_str": "astolic"} -{"id": 27907, "token": "\u0120Buch", "merges": "\u0120B uch", "raw_count": 1277, "count": 1277, "decode_str": " Buch"} -{"id": 49023, "token": "\u0120mysq", "merges": "\u0120my sq", "raw_count": 1277, "count": 1277, "decode_str": " mysq"} -{"id": 23583, "token": "\u0120Liberty", "merges": "\u0120Liber ty", "raw_count": 1278, "count": 1278, "decode_str": " Liberty"} -{"id": 38570, "token": "\u0120shoved", "merges": "\u0120sh oved", "raw_count": 1278, "count": 1278, "decode_str": " shoved"} -{"id": 22759, "token": "\u0120dairy", "merges": "\u0120d airy", "raw_count": 1278, "count": 1278, "decode_str": " dairy"} -{"id": 30739, "token": "\u0120Hir", "merges": "\u0120H ir", "raw_count": 1278, "count": 1278, "decode_str": " Hir"} -{"id": 21246, "token": "\u0120Stadium", "merges": "\u0120St adium", "raw_count": 1279, "count": 1279, "decode_str": " Stadium"} -{"id": 46132, "token": "\u0120diffus", "merges": "\u0120diff us", "raw_count": 1279, "count": 1279, "decode_str": " diffus"} -{"id": 39942, "token": "\u0120Tub", "merges": "\u0120T ub", "raw_count": 1279, "count": 1279, "decode_str": " Tub"} -{"id": 28318, "token": "\u0120Fol", "merges": "\u0120F ol", "raw_count": 1279, "count": 1279, "decode_str": " Fol"} -{"id": 49646, "token": "\u0120swallowing", "merges": "\u0120swallow ing", "raw_count": 1280, "count": 1280, "decode_str": " swallowing"} -{"id": 50193, "token": "\u0120ventured", "merges": "\u0120vent ured", "raw_count": 1280, "count": 1280, "decode_str": " ventured"} -{"id": 39365, "token": "\u0120Syndrome", "merges": "\u0120Synd rome", "raw_count": 1280, "count": 1280, "decode_str": " Syndrome"} -{"id": 30902, "token": "\u0120Stories", "merges": "\u0120St ories", "raw_count": 1280, "count": 1280, "decode_str": " Stories"} -{"id": 41434, "token": "cardia", "merges": "card ia", "raw_count": 1280, "count": 1280, "decode_str": "cardia"} -{"id": 26608, "token": "\u0120Camb", "merges": "\u0120C amb", "raw_count": 1192, "count": 1280, "decode_str": " Camb"} -{"id": 41452, "token": "\u0120Milk", "merges": "\u0120Mil k", "raw_count": 1280, "count": 1280, "decode_str": " Milk"} -{"id": 46792, "token": "\u0120Skills", "merges": "\u0120Sk ills", "raw_count": 1281, "count": 1281, "decode_str": " Skills"} -{"id": 17446, "token": "\u0120Ted", "merges": "\u0120T ed", "raw_count": 747, "count": 1281, "decode_str": " Ted"} -{"id": 27081, "token": "}/\\", "merges": "} /\\", "raw_count": 1281, "count": 1281, "decode_str": "}/\\"} -{"id": 38591, "token": "\u00e3\u0123\u0124\u00e3\u0124\u012c", "merges": "\u00e3\u0123\u0124 \u00e3\u0124\u012c", "raw_count": 1282, "count": 1282, "decode_str": "\u3042\u308a"} -{"id": 37621, "token": "\u0120Cock", "merges": "\u0120C ock", "raw_count": 1282, "count": 1282, "decode_str": " Cock"} -{"id": 49546, "token": "\u0120Anc", "merges": "\u0120An c", "raw_count": 1282, "count": 1282, "decode_str": " Anc"} -{"id": 31788, "token": "\u0120nicotine", "merges": "\u0120nic otine", "raw_count": 1283, "count": 1283, "decode_str": " nicotine"} -{"id": 36239, "token": "\u0120Lenn", "merges": "\u0120L enn", "raw_count": 1283, "count": 1283, "decode_str": " Lenn"} -{"id": 27402, "token": "\u0120Gol", "merges": "\u0120G ol", "raw_count": 1208, "count": 1283, "decode_str": " Gol"} -{"id": 50124, "token": "\u0120insulting", "merges": "\u0120insult ing", "raw_count": 1284, "count": 1284, "decode_str": " insulting"} -{"id": 37914, "token": "\u0120whipped", "merges": "\u0120wh ipped", "raw_count": 1284, "count": 1284, "decode_str": " whipped"} -{"id": 43647, "token": "\u0120Broadcasting", "merges": "\u0120Broad casting", "raw_count": 1285, "count": 1285, "decode_str": " Broadcasting"} -{"id": 47818, "token": "\u0120pelvis", "merges": "\u0120pel vis", "raw_count": 1285, "count": 1285, "decode_str": " pelvis"} -{"id": 20291, "token": "\u0120Isa", "merges": "\u0120Is a", "raw_count": 287, "count": 1285, "decode_str": " Isa"} -{"id": 52396, "token": "\u00e6\u0143\u0135", "merges": "\u00e6\u0143 \u0135", "raw_count": 1285, "count": 1285, "decode_str": "\u6b53"} -{"id": 17567, "token": "\\{\\", "merges": "\\ {\\", "raw_count": 1285, "count": 1285, "decode_str": "\\{\\"} -{"id": 48528, "token": "\u0120depiction", "merges": "\u0120dep iction", "raw_count": 1287, "count": 1287, "decode_str": " depiction"} -{"id": 33245, "token": "\u0120Cele", "merges": "\u0120C ele", "raw_count": 778, "count": 1287, "decode_str": " Cele"} -{"id": 40147, "token": "\u0120spectrophot", "merges": "\u0120spect rophot", "raw_count": 1288, "count": 1288, "decode_str": " spectrophot"} -{"id": 44951, "token": "\u00d0\u00be\u00d0\u00b3\u00d0\u00b4\u00d0\u00b0", "merges": "\u00d0\u00be\u00d0\u00b3 \u00d0\u00b4\u00d0\u00b0", "raw_count": 1288, "count": 1288, "decode_str": "\u043e\u0433\u0434\u0430"} -{"id": 37247, "token": "\u0120Weber", "merges": "\u0120We ber", "raw_count": 1288, "count": 1288, "decode_str": " Weber"} -{"id": 33655, "token": "\u0120Shin", "merges": "\u0120Sh in", "raw_count": 1288, "count": 1288, "decode_str": " Shin"} -{"id": 44589, "token": "\u0120Une", "merges": "\u0120U ne", "raw_count": 1288, "count": 1288, "decode_str": " Une"} -{"id": 39609, "token": "\u0120instincts", "merges": "\u0120instinct s", "raw_count": 1289, "count": 1289, "decode_str": " instincts"} -{"id": 27282, "token": "\u0120Politics", "merges": "\u0120Polit ics", "raw_count": 1289, "count": 1289, "decode_str": " Politics"} -{"id": 35023, "token": "ar\u00c3\u00a9", "merges": "ar \u00c3\u00a9", "raw_count": 1212, "count": 1289, "decode_str": "ar\u00e9"} -{"id": 22816, "token": "\u0120irreducible", "merges": "\u0120ir reducible", "raw_count": 1290, "count": 1290, "decode_str": " irreducible"} -{"id": 42402, "token": "\u0120midfielder", "merges": "\u0120mid fielder", "raw_count": 1290, "count": 1290, "decode_str": " midfielder"} -{"id": 37990, "token": "ferroni", "merges": "ferr oni", "raw_count": 1153, "count": 1290, "decode_str": "ferroni"} -{"id": 49151, "token": "\u00e0\u00b8\u012a", "merges": "\u00e0\u00b8 \u012a", "raw_count": 1290, "count": 1290, "decode_str": "\u0e08"} -{"id": 48913, "token": "\u0120biodegrad", "merges": "\u0120bi odegrad", "raw_count": 1291, "count": 1291, "decode_str": " biodegrad"} -{"id": 18673, "token": "\u0120Bruce", "merges": "\u0120Bru ce", "raw_count": 1291, "count": 1291, "decode_str": " Bruce"} -{"id": 20567, "token": "\u0120Kings", "merges": "\u0120K ings", "raw_count": 1291, "count": 1291, "decode_str": " Kings"} -{"id": 21871, "token": "\u0120thym", "merges": "\u0120th ym", "raw_count": 1291, "count": 1291, "decode_str": " thym"} -{"id": 19888, "token": "\u0120\u00c5\u00be", "merges": "\u0120\u00c5 \u00be", "raw_count": 1161, "count": 1291, "decode_str": " \u017e"} -{"id": 41976, "token": "\u0120Journey", "merges": "\u0120Jour ney", "raw_count": 1292, "count": 1292, "decode_str": " Journey"} -{"id": 49316, "token": "ICAg", "merges": "IC Ag", "raw_count": 1292, "count": 1292, "decode_str": "ICAg"} -{"id": 34190, "token": "\u0120transfusion", "merges": "\u0120trans fusion", "raw_count": 1293, "count": 1293, "decode_str": " transfusion"} -{"id": 42207, "token": "\u0120bacterium", "merges": "\u0120bacter ium", "raw_count": 1293, "count": 1293, "decode_str": " bacterium"} -{"id": 46698, "token": "\u0120prolific", "merges": "\u0120prol ific", "raw_count": 1293, "count": 1293, "decode_str": " prolific"} -{"id": 7671, "token": "\u0120Federal", "merges": "\u0120F ederal", "raw_count": 1293, "count": 1293, "decode_str": " Federal"} -{"id": 44926, "token": "\u0120SUMMARY", "merges": "\u0120SUM MARY", "raw_count": 1293, "count": 1293, "decode_str": " SUMMARY"} -{"id": 46805, "token": "\u0120forts", "merges": "\u0120for ts", "raw_count": 1293, "count": 1293, "decode_str": " forts"} -{"id": 31292, "token": "\u0120Kun", "merges": "\u0120K un", "raw_count": 1293, "count": 1293, "decode_str": " Kun"} -{"id": 32320, "token": "isi\u00c3\u00b3n", "merges": "is i\u00c3\u00b3n", "raw_count": 1285, "count": 1294, "decode_str": "isi\u00f3n"} -{"id": 35175, "token": "\u0120Shannon", "merges": "\u0120Sh annon", "raw_count": 1295, "count": 1295, "decode_str": " Shannon"} -{"id": 47395, "token": "\u0120slated", "merges": "\u0120sl ated", "raw_count": 1295, "count": 1295, "decode_str": " slated"} -{"id": 11725, "token": "\u0120kinase", "merges": "\u0120kin ase", "raw_count": 1295, "count": 1295, "decode_str": " kinase"} -{"id": 31958, "token": "\u0120Biology", "merges": "\u0120Bi ology", "raw_count": 1296, "count": 1296, "decode_str": " Biology"} -{"id": 32677, "token": "\u0120rins", "merges": "\u0120r ins", "raw_count": 906, "count": 1296, "decode_str": " rins"} -{"id": 47114, "token": "\u0120IOP", "merges": "\u0120I OP", "raw_count": 1296, "count": 1296, "decode_str": " IOP"} -{"id": 43986, "token": "\u0120redshifts", "merges": "\u0120red shifts", "raw_count": 1297, "count": 1297, "decode_str": " redshifts"} -{"id": 39469, "token": "\u0120microbes", "merges": "\u0120micro bes", "raw_count": 1297, "count": 1297, "decode_str": " microbes"} -{"id": 49961, "token": "\u0120conjunct", "merges": "\u0120conj unct", "raw_count": 1298, "count": 1298, "decode_str": " conjunct"} -{"id": 17885, "token": "\u0120Douglas", "merges": "\u0120Doug las", "raw_count": 1298, "count": 1298, "decode_str": " Douglas"} -{"id": 7650, "token": "\u0120Appe", "merges": "\u0120Ap pe", "raw_count": 951, "count": 1298, "decode_str": " Appe"} -{"id": 34594, "token": "\u0120XV", "merges": "\u0120X V", "raw_count": 1298, "count": 1298, "decode_str": " XV"} -{"id": 30259, "token": "\u0120exhibiting", "merges": "\u0120exhib iting", "raw_count": 1299, "count": 1299, "decode_str": " exhibiting"} -{"id": 49537, "token": "\u0120Qing", "merges": "\u0120Q ing", "raw_count": 1299, "count": 1299, "decode_str": " Qing"} -{"id": 35779, "token": "\u0120eds", "merges": "\u0120ed s", "raw_count": 1299, "count": 1299, "decode_str": " eds"} -{"id": 47541, "token": "\u0120inclusions", "merges": "\u0120in clusions", "raw_count": 1300, "count": 1300, "decode_str": " inclusions"} -{"id": 34463, "token": "\u0120HSP", "merges": "\u0120H SP", "raw_count": 1300, "count": 1300, "decode_str": " HSP"} -{"id": 43899, "token": "\u0120Ub", "merges": "\u0120U b", "raw_count": 1300, "count": 1300, "decode_str": " Ub"} -{"id": 19663, "token": "\u0120soluble", "merges": "\u0120sol uble", "raw_count": 1301, "count": 1301, "decode_str": " soluble"} -{"id": 46272, "token": "\u0120concede", "merges": "\u0120conced e", "raw_count": 1301, "count": 1301, "decode_str": " concede"} -{"id": 35992, "token": "\u0120Fur", "merges": "\u0120F ur", "raw_count": 1301, "count": 1301, "decode_str": " Fur"} -{"id": 45927, "token": "\u0120cheering", "merges": "\u0120che ering", "raw_count": 1302, "count": 1302, "decode_str": " cheering"} -{"id": 40534, "token": "\u0120Yo", "merges": "\u0120Y o", "raw_count": 1302, "count": 1302, "decode_str": " Yo"} -{"id": 39947, "token": "\u0120vertebra", "merges": "\u0120verte bra", "raw_count": 1303, "count": 1303, "decode_str": " vertebra"} -{"id": 34000, "token": "\u0120immature", "merges": "\u0120imm ature", "raw_count": 1303, "count": 1303, "decode_str": " immature"} -{"id": 25298, "token": "\u0120Pierre", "merges": "\u0120Pier re", "raw_count": 1303, "count": 1303, "decode_str": " Pierre"} -{"id": 41371, "token": "\u0120Parts", "merges": "\u0120Part s", "raw_count": 1303, "count": 1303, "decode_str": " Parts"} -{"id": 31812, "token": "\u0120isso", "merges": "\u0120is so", "raw_count": 1303, "count": 1303, "decode_str": " isso"} -{"id": 44793, "token": "arynx", "merges": "aryn x", "raw_count": 1303, "count": 1303, "decode_str": "arynx"} -{"id": 20699, "token": "\u0120Hus", "merges": "\u0120H us", "raw_count": 770, "count": 1303, "decode_str": " Hus"} -{"id": 43073, "token": "\u0120differentiating", "merges": "\u0120different iating", "raw_count": 1304, "count": 1304, "decode_str": " differentiating"} -{"id": 28870, "token": "\u0120nuest", "merges": "\u0120nu est", "raw_count": 1304, "count": 1304, "decode_str": " nuest"} -{"id": 15273, "token": "\u0120Kevin", "merges": "\u0120K evin", "raw_count": 1304, "count": 1304, "decode_str": " Kevin"} -{"id": 22125, "token": "i\u00c3\u00b3", "merges": "i \u00c3\u00b3", "raw_count": 1304, "count": 1304, "decode_str": "i\u00f3"} -{"id": 46553, "token": "\u0120Structural", "merges": "\u0120Struct ural", "raw_count": 1305, "count": 1305, "decode_str": " Structural"} -{"id": 31881, "token": "\u0120Inspector", "merges": "\u0120Ins pector", "raw_count": 1305, "count": 1305, "decode_str": " Inspector"} -{"id": 39884, "token": "\u0120degli", "merges": "\u0120deg li", "raw_count": 1305, "count": 1305, "decode_str": " degli"} -{"id": 30576, "token": "\u0120Parl", "merges": "\u0120Par l", "raw_count": 1305, "count": 1305, "decode_str": " Parl"} -{"id": 43806, "token": "ycin", "merges": "y cin", "raw_count": 1305, "count": 1305, "decode_str": "ycin"} -{"id": 26425, "token": "\u0120broth", "merges": "\u0120bro th", "raw_count": 1306, "count": 1306, "decode_str": " broth"} -{"id": 22757, "token": "\u0120Guy", "merges": "\u0120Gu y", "raw_count": 1307, "count": 1307, "decode_str": " Guy"} -{"id": 18626, "token": "\u00e2\u0122\u00b3", "merges": "\u00e2\u0122 \u00b3", "raw_count": 1308, "count": 1308, "decode_str": "\u2033"} -{"id": 31103, "token": "earchers", "merges": "ear chers", "raw_count": 1249, "count": 1309, "decode_str": "earchers"} -{"id": 12123, "token": "\u0120Zealand", "merges": "\u0120Ze aland", "raw_count": 1309, "count": 1309, "decode_str": " Zealand"} -{"id": 40414, "token": "\u0120tipped", "merges": "\u0120t ipped", "raw_count": 1309, "count": 1309, "decode_str": " tipped"} -{"id": 23555, "token": "\u0120Holmes", "merges": "\u0120Hol mes", "raw_count": 1309, "count": 1309, "decode_str": " Holmes"} -{"id": 39054, "token": "\u0120Ez", "merges": "\u0120E z", "raw_count": 1309, "count": 1309, "decode_str": " Ez"} -{"id": 39316, "token": "\u0120famously", "merges": "\u0120fam ously", "raw_count": 1310, "count": 1310, "decode_str": " famously"} -{"id": 35084, "token": "\u0120Silva", "merges": "\u0120Sil va", "raw_count": 1310, "count": 1310, "decode_str": " Silva"} -{"id": 28322, "token": "\u0120Ori", "merges": "\u0120O ri", "raw_count": 691, "count": 1310, "decode_str": " Ori"} -{"id": 34411, "token": "\u0120Lov", "merges": "\u0120L ov", "raw_count": 1310, "count": 1310, "decode_str": " Lov"} -{"id": 24532, "token": "\u0120schizophrenia", "merges": "\u0120schizophren ia", "raw_count": 1311, "count": 1311, "decode_str": " schizophrenia"} -{"id": 9883, "token": "\u0120Spanish", "merges": "\u0120Sp anish", "raw_count": 1311, "count": 1311, "decode_str": " Spanish"} -{"id": 47371, "token": "\u0120obliter", "merges": "\u0120ob liter", "raw_count": 1311, "count": 1311, "decode_str": " obliter"} -{"id": 42384, "token": "addClass", "merges": "add Class", "raw_count": 1311, "count": 1311, "decode_str": "addClass"} -{"id": 16553, "token": "\u0120Jason", "merges": "\u0120J ason", "raw_count": 1311, "count": 1311, "decode_str": " Jason"} -{"id": 29800, "token": "rotic", "merges": "ro tic", "raw_count": 1311, "count": 1311, "decode_str": "rotic"} -{"id": 44366, "token": "\u00c3\u0141e", "merges": "\u00c3\u0141 e", "raw_count": 1311, "count": 1311, "decode_str": "\u00dfe"} -{"id": 43067, "token": "----------------------------------------------------------------------", "merges": "---------------------------------------------------------------- ------", "raw_count": 1312, "count": 1312, "decode_str": "----------------------------------------------------------------------"} -{"id": 32572, "token": "\u0120sufficiency", "merges": "\u0120su fficiency", "raw_count": 1312, "count": 1312, "decode_str": " sufficiency"} -{"id": 20169, "token": "\u0120isomorphism", "merges": "\u0120is omorphism", "raw_count": 1312, "count": 1312, "decode_str": " isomorphism"} -{"id": 19081, "token": "\u0120inoc", "merges": "\u0120in oc", "raw_count": 612, "count": 1312, "decode_str": " inoc"} -{"id": 41336, "token": "\u0120dengue", "merges": "\u0120deng ue", "raw_count": 1313, "count": 1313, "decode_str": " dengue"} -{"id": 38569, "token": "bellum", "merges": "bell um", "raw_count": 918, "count": 1313, "decode_str": "bellum"} -{"id": 19342, "token": "\u0120Griff", "merges": "\u0120Gr iff", "raw_count": 165, "count": 1313, "decode_str": " Griff"} -{"id": 38493, "token": "\u0120queer", "merges": "\u0120que er", "raw_count": 1313, "count": 1313, "decode_str": " queer"} -{"id": 31037, "token": "\u0120Wiley", "merges": "\u0120W iley", "raw_count": 1313, "count": 1313, "decode_str": " Wiley"} -{"id": 23077, "token": "\u0120Thor", "merges": "\u0120Th or", "raw_count": 1314, "count": 1314, "decode_str": " Thor"} -{"id": 27014, "token": "\u0120Boys", "merges": "\u0120Bo ys", "raw_count": 1315, "count": 1315, "decode_str": " Boys"} -{"id": 48983, "token": "\u0120GOT", "merges": "\u0120G OT", "raw_count": 1315, "count": 1315, "decode_str": " GOT"} -{"id": 49865, "token": "\u0120contender", "merges": "\u0120cont ender", "raw_count": 1316, "count": 1316, "decode_str": " contender"} -{"id": 13953, "token": "\u0120nous", "merges": "\u0120n ous", "raw_count": 1316, "count": 1316, "decode_str": " nous"} -{"id": 46843, "token": "\u00e3\u0123\u0136", "merges": "\u00e3\u0123 \u0136", "raw_count": 1316, "count": 1316, "decode_str": "\u3054"} -{"id": 26294, "token": "\u0120entanglement", "merges": "\u0120entang lement", "raw_count": 1317, "count": 1317, "decode_str": " entanglement"} -{"id": 29084, "token": "\u0120Thought", "merges": "\u0120Th ought", "raw_count": 1318, "count": 1318, "decode_str": " Thought"} -{"id": 36140, "token": "\u0120anaest", "merges": "\u0120ana est", "raw_count": 1318, "count": 1318, "decode_str": " anaest"} -{"id": 48945, "token": "\u0120coined", "merges": "\u0120co ined", "raw_count": 1318, "count": 1318, "decode_str": " coined"} -{"id": 19254, "token": "\u0120antim", "merges": "\u0120ant im", "raw_count": 726, "count": 1318, "decode_str": " antim"} -{"id": 43172, "token": "\u0120Duty", "merges": "\u0120D uty", "raw_count": 1318, "count": 1318, "decode_str": " Duty"} -{"id": 6413, "token": "\u0120Supreme", "merges": "\u0120Sup reme", "raw_count": 1319, "count": 1319, "decode_str": " Supreme"} -{"id": 44580, "token": "ERTYPE", "merges": "ERT YPE", "raw_count": 1057, "count": 1319, "decode_str": "ERTYPE"} -{"id": 20322, "token": "\u0120%>", "merges": "\u0120% >", "raw_count": 1264, "count": 1319, "decode_str": " %>"} -{"id": 24365, "token": "\u0120implantation", "merges": "\u0120implant ation", "raw_count": 1320, "count": 1320, "decode_str": " implantation"} -{"id": 26492, "token": "\u0120methanol", "merges": "\u0120meth anol", "raw_count": 1320, "count": 1320, "decode_str": " methanol"} -{"id": 28728, "token": "\u0120analges", "merges": "\u0120anal ges", "raw_count": 738, "count": 1320, "decode_str": " analges"} -{"id": 32761, "token": "\u0120Above", "merges": "\u0120Ab ove", "raw_count": 1320, "count": 1320, "decode_str": " Above"} -{"id": 20069, "token": "\u0120Hend", "merges": "\u0120H end", "raw_count": 757, "count": 1320, "decode_str": " Hend"} -{"id": 23302, "token": "\u0120Mack", "merges": "\u0120M ack", "raw_count": 1320, "count": 1320, "decode_str": " Mack"} -{"id": 43502, "token": "\u0120inventors", "merges": "\u0120invent ors", "raw_count": 1321, "count": 1321, "decode_str": " inventors"} -{"id": 47921, "token": "\u0120trilogy", "merges": "\u0120tr ilogy", "raw_count": 1321, "count": 1321, "decode_str": " trilogy"} -{"id": 16863, "token": "\u0120Carter", "merges": "\u0120Car ter", "raw_count": 1321, "count": 1321, "decode_str": " Carter"} -{"id": 28970, "token": "\u0120MeV", "merges": "\u0120Me V", "raw_count": 1321, "count": 1321, "decode_str": " MeV"} -{"id": 41820, "token": "\u0120visitation", "merges": "\u0120vis itation", "raw_count": 1322, "count": 1322, "decode_str": " visitation"} -{"id": 44483, "token": "oarthritis", "merges": "oarth ritis", "raw_count": 1322, "count": 1322, "decode_str": "oarthritis"} -{"id": 15893, "token": "\u0120teaspoon", "merges": "\u0120teasp oon", "raw_count": 1322, "count": 1322, "decode_str": " teaspoon"} -{"id": 16985, "token": "////////////////////////////////", "merges": "//////////////// ////////////////", "raw_count": 701, "count": 1323, "decode_str": "////////////////////////////////"} -{"id": 38240, "token": "\u0120roasted", "merges": "\u0120ro asted", "raw_count": 1323, "count": 1323, "decode_str": " roasted"} -{"id": 45996, "token": "idently", "merges": "ident ly", "raw_count": 1323, "count": 1323, "decode_str": "idently"} -{"id": 14012, "token": "\u0120Ark", "merges": "\u0120Ar k", "raw_count": 1242, "count": 1323, "decode_str": " Ark"} -{"id": 28819, "token": "\u0120spatially", "merges": "\u0120spat ially", "raw_count": 1324, "count": 1324, "decode_str": " spatially"} -{"id": 30815, "token": "\u0120Hass", "merges": "\u0120H ass", "raw_count": 988, "count": 1324, "decode_str": " Hass"} -{"id": 47067, "token": "\u0120NIR", "merges": "\u0120N IR", "raw_count": 1324, "count": 1324, "decode_str": " NIR"} -{"id": 46694, "token": "].\\", "merges": "]. \\", "raw_count": 1324, "count": 1324, "decode_str": "].\\"} -{"id": 44841, "token": "izaci\u00c3\u00b3n", "merges": "iz aci\u00c3\u00b3n", "raw_count": 1325, "count": 1325, "decode_str": "izaci\u00f3n"} -{"id": 38236, "token": "\u0120Sang", "merges": "\u0120S ang", "raw_count": 1325, "count": 1325, "decode_str": " Sang"} -{"id": 30473, "token": "\u0120Abr", "merges": "\u0120A br", "raw_count": 1080, "count": 1325, "decode_str": " Abr"} -{"id": 27377, "token": "\u0120inferences", "merges": "\u0120in ferences", "raw_count": 1326, "count": 1326, "decode_str": " inferences"} -{"id": 39451, "token": "\u0120softened", "merges": "\u0120soft ened", "raw_count": 1326, "count": 1326, "decode_str": " softened"} -{"id": 38504, "token": "\u0120skeptic", "merges": "\u0120ske ptic", "raw_count": 257, "count": 1326, "decode_str": " skeptic"} -{"id": 23588, "token": "\u0120Male", "merges": "\u0120M ale", "raw_count": 1326, "count": 1326, "decode_str": " Male"} -{"id": 47097, "token": "irled", "merges": "ir led", "raw_count": 1327, "count": 1327, "decode_str": "irled"} -{"id": 29047, "token": "\u0120Cour", "merges": "\u0120C our", "raw_count": 1327, "count": 1327, "decode_str": " Cour"} -{"id": 29999, "token": "\u0120dismissing", "merges": "\u0120dismiss ing", "raw_count": 1328, "count": 1328, "decode_str": " dismissing"} -{"id": 11137, "token": "\u0120Scot", "merges": "\u0120Sc ot", "raw_count": 578, "count": 1328, "decode_str": " Scot"} -{"id": 45186, "token": "\u0120aliment", "merges": "\u0120al iment", "raw_count": 1329, "count": 1329, "decode_str": " aliment"} -{"id": 47434, "token": "\u00e3\u0125\u012c", "merges": "\u00e3\u0125 \u012c", "raw_count": 1329, "count": 1329, "decode_str": "\u30ca"} -{"id": 21066, "token": "\u0120synaptic", "merges": "\u0120syn aptic", "raw_count": 1330, "count": 1330, "decode_str": " synaptic"} -{"id": 30280, "token": "\u0120TEX", "merges": "\u0120T EX", "raw_count": 1305, "count": 1330, "decode_str": " TEX"} -{"id": 36056, "token": "\u0120--------------------------", "merges": "\u0120---------------- ----------", "raw_count": 1331, "count": 1331, "decode_str": " --------------------------"} -{"id": 44803, "token": "\u0120storyline", "merges": "\u0120story line", "raw_count": 1331, "count": 1331, "decode_str": " storyline"} -{"id": 17678, "token": "\u0120primers", "merges": "\u0120prim ers", "raw_count": 1331, "count": 1331, "decode_str": " primers"} -{"id": 15699, "token": "\u0120Overall", "merges": "\u0120Over all", "raw_count": 1331, "count": 1331, "decode_str": " Overall"} -{"id": 49719, "token": "\u0120Awesome", "merges": "\u0120Aw esome", "raw_count": 1331, "count": 1331, "decode_str": " Awesome"} -{"id": 48253, "token": "\u0120Ment", "merges": "\u0120M ent", "raw_count": 1331, "count": 1331, "decode_str": " Ment"} -{"id": 41455, "token": "\u0120Correspond", "merges": "\u0120Cor respond", "raw_count": 1332, "count": 1332, "decode_str": " Correspond"} -{"id": 48236, "token": "Portuguese", "merges": "Portug uese", "raw_count": 1332, "count": 1332, "decode_str": "Portuguese"} -{"id": 32592, "token": "\u0120Heavy", "merges": "\u0120He avy", "raw_count": 1332, "count": 1332, "decode_str": " Heavy"} -{"id": 48936, "token": "\u0120=&", "merges": "\u0120= &", "raw_count": 1332, "count": 1332, "decode_str": " =&"} -{"id": 41895, "token": "\u0120Pd", "merges": "\u0120P d", "raw_count": 1332, "count": 1332, "decode_str": " Pd"} -{"id": 43713, "token": "\u0120wonderfully", "merges": "\u0120wonder fully", "raw_count": 1333, "count": 1333, "decode_str": " wonderfully"} -{"id": 49963, "token": "\u0120clinging", "merges": "\u0120cl inging", "raw_count": 1333, "count": 1333, "decode_str": " clinging"} -{"id": 46220, "token": "oliberal", "merges": "ol iberal", "raw_count": 1333, "count": 1333, "decode_str": "oliberal"} -{"id": 48994, "token": "\u0120massively", "merges": "\u0120mass ively", "raw_count": 1334, "count": 1334, "decode_str": " massively"} -{"id": 4207, "token": "\\].", "merges": "\\] .", "raw_count": 1305, "count": 1334, "decode_str": "\\]."} -{"id": 43431, "token": "\u0120inhalation", "merges": "\u0120inhal ation", "raw_count": 1335, "count": 1335, "decode_str": " inhalation"} -{"id": 39914, "token": "\u0120Doll", "merges": "\u0120D oll", "raw_count": 1335, "count": 1335, "decode_str": " Doll"} -{"id": 43312, "token": "\u0120Beginning", "merges": "\u0120Begin ning", "raw_count": 1336, "count": 1336, "decode_str": " Beginning"} -{"id": 48490, "token": "\u0120sprayed", "merges": "\u0120spray ed", "raw_count": 1336, "count": 1336, "decode_str": " sprayed"} -{"id": 27166, "token": "\u0120anatomical", "merges": "\u0120anatom ical", "raw_count": 1337, "count": 1337, "decode_str": " anatomical"} -{"id": 34945, "token": "\u0120misdem", "merges": "\u0120mis dem", "raw_count": 1025, "count": 1337, "decode_str": " misdem"} -{"id": 45546, "token": "\u0120Danger", "merges": "\u0120D anger", "raw_count": 1337, "count": 1337, "decode_str": " Danger"} -{"id": 40992, "token": "\u0120cardio", "merges": "\u0120card io", "raw_count": 1337, "count": 1337, "decode_str": " cardio"} -{"id": 27338, "token": "\u0120parasites", "merges": "\u0120paras ites", "raw_count": 1338, "count": 1338, "decode_str": " parasites"} -{"id": 47830, "token": "\u0120frying", "merges": "\u0120f rying", "raw_count": 1338, "count": 1338, "decode_str": " frying"} -{"id": 48229, "token": "rifying", "merges": "r ifying", "raw_count": 1338, "count": 1338, "decode_str": "rifying"} -{"id": 24035, "token": "\u0120Keith", "merges": "\u0120Ke ith", "raw_count": 1338, "count": 1338, "decode_str": " Keith"} -{"id": 29480, "token": "\u0120Simpson", "merges": "\u0120Sim pson", "raw_count": 1339, "count": 1339, "decode_str": " Simpson"} -{"id": 21587, "token": "\u0120Juan", "merges": "\u0120J uan", "raw_count": 1339, "count": 1339, "decode_str": " Juan"} -{"id": 21193, "token": "\u0120Singh", "merges": "\u0120Sing h", "raw_count": 1340, "count": 1340, "decode_str": " Singh"} -{"id": 34396, "token": "\u0120Ran", "merges": "\u0120R an", "raw_count": 1340, "count": 1340, "decode_str": " Ran"} -{"id": 25311, "token": "\u0120ICU", "merges": "\u0120IC U", "raw_count": 1340, "count": 1340, "decode_str": " ICU"} -{"id": 47812, "token": "\u0120\u00d1\u0138", "merges": "\u0120\u00d1 \u0138", "raw_count": 1340, "count": 1340, "decode_str": " \u0456"} -{"id": 14690, "token": "\u0120Matthe", "merges": "\u0120Mat the", "raw_count": 26, "count": 1341, "decode_str": " Matthe"} -{"id": 10657, "token": "\u0120Pak", "merges": "\u0120P ak", "raw_count": 1025, "count": 1341, "decode_str": " Pak"} -{"id": 21929, "token": "ozygous", "merges": "ozyg ous", "raw_count": 784, "count": 1342, "decode_str": "ozygous"} -{"id": 40402, "token": "\u0120Fight", "merges": "\u0120F ight", "raw_count": 1342, "count": 1342, "decode_str": " Fight"} -{"id": 30483, "token": "\u0120Haus", "merges": "\u0120H aus", "raw_count": 1342, "count": 1342, "decode_str": " Haus"} -{"id": 44351, "token": "\u0120continu", "merges": "\u0120contin u", "raw_count": 1343, "count": 1343, "decode_str": " continu"} -{"id": 23142, "token": "\u0120Soph", "merges": "\u0120S oph", "raw_count": 1025, "count": 1343, "decode_str": " Soph"} -{"id": 31643, "token": "\u0120EXPRESS", "merges": "\u0120EX PRESS", "raw_count": 1344, "count": 1344, "decode_str": " EXPRESS"} -{"id": 38224, "token": "\u0120Stress", "merges": "\u0120St ress", "raw_count": 1344, "count": 1344, "decode_str": " Stress"} -{"id": 15526, "token": "\u0120Chair", "merges": "\u0120Ch air", "raw_count": 1105, "count": 1344, "decode_str": " Chair"} -{"id": 16155, "token": "\u0120Executive", "merges": "\u0120Exec utive", "raw_count": 1345, "count": 1345, "decode_str": " Executive"} -{"id": 43341, "token": "\u0120mimics", "merges": "\u0120mim ics", "raw_count": 1345, "count": 1345, "decode_str": " mimics"} -{"id": 23024, "token": "\u0120airway", "merges": "\u0120air way", "raw_count": 1345, "count": 1345, "decode_str": " airway"} -{"id": 11819, "token": "\u0120Steve", "merges": "\u0120Ste ve", "raw_count": 1345, "count": 1345, "decode_str": " Steve"} -{"id": 39688, "token": "\u0120Epic", "merges": "\u0120Ep ic", "raw_count": 1345, "count": 1345, "decode_str": " Epic"} -{"id": 49681, "token": "\u0120commuting", "merges": "\u0120comm uting", "raw_count": 1346, "count": 1346, "decode_str": " commuting"} -{"id": 35957, "token": "\u0120pictured", "merges": "\u0120pict ured", "raw_count": 1346, "count": 1346, "decode_str": " pictured"} -{"id": 37739, "token": "roidism", "merges": "roid ism", "raw_count": 1346, "count": 1346, "decode_str": "roidism"} -{"id": 16494, "token": "\u0120Debt", "merges": "\u0120De bt", "raw_count": 1222, "count": 1346, "decode_str": " Debt"} -{"id": 31933, "token": "\u0120Rush", "merges": "\u0120R ush", "raw_count": 1346, "count": 1346, "decode_str": " Rush"} -{"id": 40897, "token": "\u0120Dup", "merges": "\u0120D up", "raw_count": 1346, "count": 1346, "decode_str": " Dup"} -{"id": 41597, "token": "uitively", "merges": "uit ively", "raw_count": 1347, "count": 1347, "decode_str": "uitively"} -{"id": 12694, "token": "\u0120Elizabeth", "merges": "\u0120El izabeth", "raw_count": 1348, "count": 1348, "decode_str": " Elizabeth"} -{"id": 16991, "token": "\u0120electroph", "merges": "\u0120elect roph", "raw_count": 257, "count": 1349, "decode_str": " electroph"} -{"id": 15657, "token": "\u0120Ron", "merges": "\u0120R on", "raw_count": 1349, "count": 1349, "decode_str": " Ron"} -{"id": 22864, "token": "\u0120Fra", "merges": "\u0120F ra", "raw_count": 1349, "count": 1349, "decode_str": " Fra"} -{"id": 42390, "token": "\u0120startling", "merges": "\u0120start ling", "raw_count": 1350, "count": 1350, "decode_str": " startling"} -{"id": 20368, "token": "\u0120intraven", "merges": "\u0120intra ven", "raw_count": 153, "count": 1350, "decode_str": " intraven"} -{"id": 42250, "token": "\u0120novelist", "merges": "\u0120novel ist", "raw_count": 1350, "count": 1350, "decode_str": " novelist"} -{"id": 18096, "token": "\u0120Pho", "merges": "\u0120P ho", "raw_count": 483, "count": 1350, "decode_str": " Pho"} -{"id": 46231, "token": "\u0120GV", "merges": "\u0120G V", "raw_count": 1350, "count": 1350, "decode_str": " GV"} -{"id": 49273, "token": "\u0120unmistak", "merges": "\u0120unmist ak", "raw_count": 1351, "count": 1351, "decode_str": " unmistak"} -{"id": 18629, "token": "\u0120catheter", "merges": "\u0120cathe ter", "raw_count": 1351, "count": 1351, "decode_str": " catheter"} -{"id": 17508, "token": "\u0120hepatic", "merges": "\u0120hep atic", "raw_count": 1351, "count": 1351, "decode_str": " hepatic"} -{"id": 12961, "token": "\u0120Budd", "merges": "\u0120B udd", "raw_count": 227, "count": 1351, "decode_str": " Budd"} -{"id": 9000, "token": "\u0120apopt", "merges": "\u0120ap opt", "raw_count": 25, "count": 1352, "decode_str": " apopt"} -{"id": 29869, "token": "\u0120Sak", "merges": "\u0120S ak", "raw_count": 1352, "count": 1352, "decode_str": " Sak"} -{"id": 41102, "token": "\u00e3\u0123\u0139\u00e3\u0123\u00a6\u00e3\u0123\u0126\u00e3\u0124\u012d", "merges": "\u00e3\u0123\u0139 \u00e3\u0123\u00a6\u00e3\u0123\u0126\u00e3\u0124\u012d", "raw_count": 1353, "count": 1353, "decode_str": "\u3057\u3066\u3044\u308b"} -{"id": 29573, "token": "\u0120Television", "merges": "\u0120Tele vision", "raw_count": 1353, "count": 1353, "decode_str": " Television"} -{"id": 35527, "token": "\u0120endocrine", "merges": "\u0120end ocrine", "raw_count": 1353, "count": 1353, "decode_str": " endocrine"} -{"id": 39564, "token": "a\u00c3\u00b1", "merges": "a \u00c3\u00b1", "raw_count": 1354, "count": 1354, "decode_str": "a\u00f1"} -{"id": 38759, "token": "\u0120----------------------------", "merges": "\u0120---------------- ------------", "raw_count": 1355, "count": 1355, "decode_str": " ----------------------------"} -{"id": 30807, "token": "\u0120muttered", "merges": "\u0120mut tered", "raw_count": 1355, "count": 1355, "decode_str": " muttered"} -{"id": 44507, "token": "\u0120mound", "merges": "\u0120m ound", "raw_count": 1355, "count": 1355, "decode_str": " mound"} -{"id": 25548, "token": "\u0120cartilage", "merges": "\u0120cart ilage", "raw_count": 1356, "count": 1356, "decode_str": " cartilage"} -{"id": 48089, "token": "\u0120raison", "merges": "\u0120ra ison", "raw_count": 1356, "count": 1356, "decode_str": " raison"} -{"id": 32923, "token": "\u0120Pract", "merges": "\u0120P ract", "raw_count": 1356, "count": 1356, "decode_str": " Pract"} -{"id": 41759, "token": "\u0120comeback", "merges": "\u0120come back", "raw_count": 1357, "count": 1357, "decode_str": " comeback"} -{"id": 40233, "token": "\u0120Lambert", "merges": "\u0120Lam bert", "raw_count": 1357, "count": 1357, "decode_str": " Lambert"} -{"id": 41751, "token": "\u0120d\u00c3\u00a9j\u00c3\u0142", "merges": "\u0120d\u00c3\u00a9 j\u00c3\u0142", "raw_count": 1357, "count": 1357, "decode_str": " d\u00e9j\u00e0"} -{"id": 23814, "token": "\u00c4\u0139", "merges": "\u00c4 \u0139", "raw_count": 1357, "count": 1357, "decode_str": "\u0117"} -{"id": 41632, "token": "\u0120Formation", "merges": "\u0120Form ation", "raw_count": 1358, "count": 1358, "decode_str": " Formation"} -{"id": 31916, "token": "\u0120Titan", "merges": "\u0120T itan", "raw_count": 1358, "count": 1358, "decode_str": " Titan"} -{"id": 40505, "token": "\u0120WANT", "merges": "\u0120W ANT", "raw_count": 1358, "count": 1358, "decode_str": " WANT"} -{"id": 19811, "token": "\u0120Ald", "merges": "\u0120A ld", "raw_count": 1358, "count": 1358, "decode_str": " Ald"} -{"id": 34511, "token": "\u0120Din", "merges": "\u0120D in", "raw_count": 1358, "count": 1358, "decode_str": " Din"} -{"id": 24819, "token": "\u0120Tow", "merges": "\u0120T ow", "raw_count": 1358, "count": 1358, "decode_str": " Tow"} -{"id": 27339, "token": "\u00d7\u0133", "merges": "\u00d7 \u0133", "raw_count": 1358, "count": 1358, "decode_str": "\u05d1"} -{"id": 29493, "token": "\u0120nonprofit", "merges": "\u0120non profit", "raw_count": 1359, "count": 1359, "decode_str": " nonprofit"} -{"id": 27873, "token": "\u0120Benef", "merges": "\u0120Ben ef", "raw_count": 1093, "count": 1359, "decode_str": " Benef"} -{"id": 27409, "token": "\u0120Cot", "merges": "\u0120C ot", "raw_count": 725, "count": 1359, "decode_str": " Cot"} -{"id": 46820, "token": "\u0120Coh", "merges": "\u0120C oh", "raw_count": 1359, "count": 1359, "decode_str": " Coh"} -{"id": 26915, "token": "\u0120polymerization", "merges": "\u0120polymer ization", "raw_count": 1360, "count": 1360, "decode_str": " polymerization"} -{"id": 37148, "token": "inguishable", "merges": "inguish able", "raw_count": 409, "count": 1360, "decode_str": "inguishable"} -{"id": 35330, "token": "\u0120protons", "merges": "\u0120prot ons", "raw_count": 1360, "count": 1360, "decode_str": " protons"} -{"id": 30205, "token": "othal", "merges": "oth al", "raw_count": 971, "count": 1360, "decode_str": "othal"} -{"id": 42134, "token": "\u0120Concert", "merges": "\u0120Con cert", "raw_count": 1361, "count": 1361, "decode_str": " Concert"} -{"id": 42227, "token": "\u0120quadrup", "merges": "\u0120quadr up", "raw_count": 1361, "count": 1361, "decode_str": " quadrup"} -{"id": 46862, "token": "\u0120BBB", "merges": "\u0120B BB", "raw_count": 1361, "count": 1361, "decode_str": " BBB"} -{"id": 45680, "token": "\u0120ihm", "merges": "\u0120i hm", "raw_count": 1361, "count": 1361, "decode_str": " ihm"} -{"id": 36873, "token": "\u0120Chemistry", "merges": "\u0120Chem istry", "raw_count": 1362, "count": 1362, "decode_str": " Chemistry"} -{"id": 22056, "token": "\u0120ligands", "merges": "\u0120lig ands", "raw_count": 1362, "count": 1362, "decode_str": " ligands"} -{"id": 29732, "token": "\u0120Koh", "merges": "\u0120K oh", "raw_count": 1362, "count": 1362, "decode_str": " Koh"} -{"id": 23150, "token": "\u0120acetate", "merges": "\u0120acet ate", "raw_count": 1363, "count": 1363, "decode_str": " acetate"} -{"id": 47011, "token": "\u0120Artists", "merges": "\u0120Art ists", "raw_count": 1363, "count": 1363, "decode_str": " Artists"} -{"id": 16688, "token": "\u0120Being", "merges": "\u0120Be ing", "raw_count": 1363, "count": 1363, "decode_str": " Being"} -{"id": 38151, "token": "jours", "merges": "j ours", "raw_count": 976, "count": 1363, "decode_str": "jours"} -{"id": 41666, "token": "\u0120\u00d0\u00bd\u00d0\u00be", "merges": "\u0120\u00d0\u00bd \u00d0\u00be", "raw_count": 1363, "count": 1363, "decode_str": " \u043d\u043e"} -{"id": 26790, "token": "idyl", "merges": "id yl", "raw_count": 1293, "count": 1363, "decode_str": "idyl"} -{"id": 29218, "token": "\u0120Airlines", "merges": "\u0120Airl ines", "raw_count": 1364, "count": 1364, "decode_str": " Airlines"} -{"id": 41203, "token": "\u0120seeming", "merges": "\u0120seem ing", "raw_count": 1364, "count": 1364, "decode_str": " seeming"} -{"id": 22551, "token": "\u0120Apr", "merges": "\u0120A pr", "raw_count": 1364, "count": 1364, "decode_str": " Apr"} -{"id": 38800, "token": "\u0120cowork", "merges": "\u0120cow ork", "raw_count": 527, "count": 1365, "decode_str": " cowork"} -{"id": 39952, "token": "\u0120Rise", "merges": "\u0120R ise", "raw_count": 1365, "count": 1365, "decode_str": " Rise"} -{"id": 43023, "token": "acyl", "merges": "ac yl", "raw_count": 1365, "count": 1365, "decode_str": "acyl"} -{"id": 37562, "token": "\u0120obsess", "merges": "\u0120obs ess", "raw_count": 1366, "count": 1366, "decode_str": " obsess"} -{"id": 41837, "token": "\u0120pesso", "merges": "\u0120pess o", "raw_count": 126, "count": 1366, "decode_str": " pesso"} -{"id": 50187, "token": "\u0120Semi", "merges": "\u0120Sem i", "raw_count": 1366, "count": 1366, "decode_str": " Semi"} -{"id": 48722, "token": "\u0120choked", "merges": "\u0120ch oked", "raw_count": 1367, "count": 1367, "decode_str": " choked"} -{"id": 42907, "token": "iazep", "merges": "iaz ep", "raw_count": 1367, "count": 1367, "decode_str": "iazep"} -{"id": 39292, "token": "\u0120osteoporosis", "merges": "\u0120osteopor osis", "raw_count": 1368, "count": 1368, "decode_str": " osteoporosis"} -{"id": 49685, "token": "\u0120Purple", "merges": "\u0120Pur ple", "raw_count": 1368, "count": 1368, "decode_str": " Purple"} -{"id": 39775, "token": "\u0120jquery", "merges": "\u0120j query", "raw_count": 1368, "count": 1368, "decode_str": " jquery"} -{"id": 31965, "token": "\u0120Sections", "merges": "\u0120Se ctions", "raw_count": 1369, "count": 1369, "decode_str": " Sections"} -{"id": 40479, "token": "\u0120pathetic", "merges": "\u0120pat hetic", "raw_count": 1370, "count": 1370, "decode_str": " pathetic"} -{"id": 43565, "token": "\u0120LinkedIn", "merges": "\u0120Linked In", "raw_count": 1370, "count": 1370, "decode_str": " LinkedIn"} -{"id": 40901, "token": "enging", "merges": "eng ing", "raw_count": 1370, "count": 1370, "decode_str": "enging"} -{"id": 30751, "token": "\u0120mundo", "merges": "\u0120m undo", "raw_count": 1370, "count": 1370, "decode_str": " mundo"} -{"id": 41868, "token": "\u0120sensations", "merges": "\u0120sens ations", "raw_count": 1371, "count": 1371, "decode_str": " sensations"} -{"id": 31990, "token": "\u0120Kitchen", "merges": "\u0120Kit chen", "raw_count": 1371, "count": 1371, "decode_str": " Kitchen"} -{"id": 27876, "token": "\u0120Tesla", "merges": "\u0120Tes la", "raw_count": 1371, "count": 1371, "decode_str": " Tesla"} -{"id": 34636, "token": "\u0120Kle", "merges": "\u0120K le", "raw_count": 1371, "count": 1371, "decode_str": " Kle"} -{"id": 42455, "token": "\u0120contrasting", "merges": "\u0120contrast ing", "raw_count": 1372, "count": 1372, "decode_str": " contrasting"} -{"id": 15022, "token": "\u0120Clinical", "merges": "\u0120Cl inical", "raw_count": 1373, "count": 1373, "decode_str": " Clinical"} -{"id": 9651, "token": "\u0120Police", "merges": "\u0120Pol ice", "raw_count": 1373, "count": 1373, "decode_str": " Police"} -{"id": 47708, "token": "\u0120Stick", "merges": "\u0120St ick", "raw_count": 1373, "count": 1373, "decode_str": " Stick"} -{"id": 14861, "token": "\u0120Tony", "merges": "\u0120T ony", "raw_count": 1373, "count": 1373, "decode_str": " Tony"} -{"id": 44211, "token": "\u0120Horizon", "merges": "\u0120Hor izon", "raw_count": 1374, "count": 1374, "decode_str": " Horizon"} -{"id": 33618, "token": "\u0120tendon", "merges": "\u0120tend on", "raw_count": 1374, "count": 1374, "decode_str": " tendon"} -{"id": 48607, "token": "ninger", "merges": "ning er", "raw_count": 1375, "count": 1375, "decode_str": "ninger"} -{"id": 37764, "token": "\u0120vort", "merges": "\u0120v ort", "raw_count": 1375, "count": 1375, "decode_str": " vort"} -{"id": 30821, "token": "\u0120speculate", "merges": "\u0120spec ulate", "raw_count": 1376, "count": 1376, "decode_str": " speculate"} -{"id": 19027, "token": "\u0120Nelson", "merges": "\u0120N elson", "raw_count": 1376, "count": 1376, "decode_str": " Nelson"} -{"id": 35610, "token": "\u0120plated", "merges": "\u0120pl ated", "raw_count": 1376, "count": 1376, "decode_str": " plated"} -{"id": 38594, "token": "\u0120parap", "merges": "\u0120par ap", "raw_count": 1376, "count": 1376, "decode_str": " parap"} -{"id": 18404, "token": "\u0120pancreatic", "merges": "\u0120pancreat ic", "raw_count": 1377, "count": 1377, "decode_str": " pancreatic"} -{"id": 46165, "token": "\u0120Videos", "merges": "\u0120V ideos", "raw_count": 1377, "count": 1377, "decode_str": " Videos"} -{"id": 48858, "token": "\u0120diagnosing", "merges": "\u0120diagn osing", "raw_count": 1379, "count": 1379, "decode_str": " diagnosing"} -{"id": 32312, "token": "\u0120Initially", "merges": "\u0120Init ially", "raw_count": 1379, "count": 1379, "decode_str": " Initially"} -{"id": 42774, "token": "ocyst", "merges": "ocy st", "raw_count": 1379, "count": 1379, "decode_str": "ocyst"} -{"id": 45904, "token": "\u0120hypnot", "merges": "\u0120hyp not", "raw_count": 1380, "count": 1380, "decode_str": " hypnot"} -{"id": 28857, "token": "ectomy", "merges": "ect omy", "raw_count": 1380, "count": 1380, "decode_str": "ectomy"} -{"id": 42413, "token": "\u0120Tess", "merges": "\u0120T ess", "raw_count": 1380, "count": 1380, "decode_str": " Tess"} -{"id": 17476, "token": "\u00c3\u00aame", "merges": "\u00c3\u00aa me", "raw_count": 380, "count": 1380, "decode_str": "\u00eame"} -{"id": 35863, "token": "\u0120FAQ", "merges": "\u0120FA Q", "raw_count": 1380, "count": 1380, "decode_str": " FAQ"} -{"id": 16124, "token": "\u00c5\u0133", "merges": "\u00c5 \u0133", "raw_count": 1380, "count": 1380, "decode_str": "\u0151"} -{"id": 30501, "token": "\u0120undisputed", "merges": "\u0120undis puted", "raw_count": 1381, "count": 1381, "decode_str": " undisputed"} -{"id": 16598, "token": "\u0120Kennedy", "merges": "\u0120Kenn edy", "raw_count": 1381, "count": 1381, "decode_str": " Kennedy"} -{"id": 38578, "token": "ylase", "merges": "yl ase", "raw_count": 1381, "count": 1381, "decode_str": "ylase"} -{"id": 6691, "token": "\u0120Mex", "merges": "\u0120M ex", "raw_count": 350, "count": 1381, "decode_str": " Mex"} -{"id": 48012, "token": "\u0120Chu", "merges": "\u0120Ch u", "raw_count": 1381, "count": 1381, "decode_str": " Chu"} -{"id": 47980, "token": "\u0120BX", "merges": "\u0120B X", "raw_count": 1381, "count": 1381, "decode_str": " BX"} -{"id": 41292, "token": "\u0120connective", "merges": "\u0120connect ive", "raw_count": 1382, "count": 1382, "decode_str": " connective"} -{"id": 43150, "token": "\u0120perin", "merges": "\u0120per in", "raw_count": 1382, "count": 1382, "decode_str": " perin"} -{"id": 45961, "token": "\u0120Marathon", "merges": "\u0120Mar athon", "raw_count": 1383, "count": 1383, "decode_str": " Marathon"} -{"id": 23984, "token": "ocytosis", "merges": "ocyt osis", "raw_count": 1383, "count": 1383, "decode_str": "ocytosis"} -{"id": 36215, "token": "\u0120Foods", "merges": "\u0120Food s", "raw_count": 1383, "count": 1383, "decode_str": " Foods"} -{"id": 40672, "token": "\u0120bland", "merges": "\u0120bl and", "raw_count": 1383, "count": 1383, "decode_str": " bland"} -{"id": 48579, "token": "OMEM", "merges": "OM EM", "raw_count": 1383, "count": 1383, "decode_str": "OMEM"} -{"id": 16622, "token": "\\#", "merges": "\\ #", "raw_count": 1383, "count": 1383, "decode_str": "\\#"} -{"id": 31856, "token": "olymer", "merges": "oly mer", "raw_count": 691, "count": 1384, "decode_str": "olymer"} -{"id": 48546, "token": "\u0120v\u00c3\u0143", "merges": "\u0120v \u00c3\u0143", "raw_count": 1384, "count": 1384, "decode_str": " v\u00ed"} -{"id": 28972, "token": "\u0120steroid", "merges": "\u0120ster oid", "raw_count": 1385, "count": 1385, "decode_str": " steroid"} -{"id": 25784, "token": "\u0120tubular", "merges": "\u0120tub ular", "raw_count": 1385, "count": 1385, "decode_str": " tubular"} -{"id": 15797, "token": "\u0120Upon", "merges": "\u0120Up on", "raw_count": 1385, "count": 1385, "decode_str": " Upon"} -{"id": 12578, "token": "\u0120FBI", "merges": "\u0120F BI", "raw_count": 1385, "count": 1385, "decode_str": " FBI"} -{"id": 49664, "token": "\u0120instructive", "merges": "\u0120instruct ive", "raw_count": 1387, "count": 1387, "decode_str": " instructive"} -{"id": 46402, "token": "\u0120puck", "merges": "\u0120p uck", "raw_count": 1387, "count": 1387, "decode_str": " puck"} -{"id": 38691, "token": "\u0120impairments", "merges": "\u0120impair ments", "raw_count": 1388, "count": 1388, "decode_str": " impairments"} -{"id": 19244, "token": "\u0120Instit", "merges": "\u0120In stit", "raw_count": 1071, "count": 1388, "decode_str": " Instit"} -{"id": 12051, "token": "\u0120Wis", "merges": "\u0120W is", "raw_count": 1005, "count": 1388, "decode_str": " Wis"} -{"id": 47300, "token": "\u0120surfaced", "merges": "\u0120surf aced", "raw_count": 1389, "count": 1389, "decode_str": " surfaced"} -{"id": 47006, "token": "\u0120emergent", "merges": "\u0120emerg ent", "raw_count": 1389, "count": 1389, "decode_str": " emergent"} -{"id": 8823, "token": "bsy", "merges": "bs y", "raw_count": 1386, "count": 1389, "decode_str": "bsy"} -{"id": 42876, "token": "\u0120marginally", "merges": "\u0120marg inally", "raw_count": 1390, "count": 1390, "decode_str": " marginally"} -{"id": 48409, "token": "\u0120pudding", "merges": "\u0120pud ding", "raw_count": 1390, "count": 1390, "decode_str": " pudding"} -{"id": 32716, "token": "ch\u00c3\u00a9", "merges": "ch \u00c3\u00a9", "raw_count": 1390, "count": 1390, "decode_str": "ch\u00e9"} -{"id": 45763, "token": "\u0120Hert", "merges": "\u0120H ert", "raw_count": 1391, "count": 1391, "decode_str": " Hert"} -{"id": 16393, "token": "\u0120Nev", "merges": "\u0120N ev", "raw_count": 1143, "count": 1391, "decode_str": " Nev"} -{"id": 23323, "token": "\u0120Associated", "merges": "\u0120Associ ated", "raw_count": 1392, "count": 1392, "decode_str": " Associated"} -{"id": 38264, "token": "\u0120Adventure", "merges": "\u0120Advent ure", "raw_count": 1392, "count": 1392, "decode_str": " Adventure"} -{"id": 39764, "token": "\u0120aspirin", "merges": "\u0120aspir in", "raw_count": 1392, "count": 1392, "decode_str": " aspirin"} -{"id": 21703, "token": "\u0120agar", "merges": "\u0120ag ar", "raw_count": 1338, "count": 1392, "decode_str": " agar"} -{"id": 38731, "token": "\u0120Spar", "merges": "\u0120S par", "raw_count": 1392, "count": 1392, "decode_str": " Spar"} -{"id": 15472, "token": "\u00e0\u00a5\u0129", "merges": "\u00e0\u00a5 \u0129", "raw_count": 1392, "count": 1392, "decode_str": "\u0947"} -{"id": 28688, "token": "\u0120eller", "merges": "\u0120 eller", "raw_count": 1393, "count": 1393, "decode_str": " eller"} -{"id": 24309, "token": "\u0120medial", "merges": "\u0120med ial", "raw_count": 1394, "count": 1394, "decode_str": " medial"} -{"id": 28733, "token": "\u00e0\u00a4\u00b8", "merges": "\u00e0\u00a4 \u00b8", "raw_count": 1394, "count": 1394, "decode_str": "\u0938"} -{"id": 7247, "token": "\u0120Russian", "merges": "\u0120Russ ian", "raw_count": 1395, "count": 1395, "decode_str": " Russian"} -{"id": 25627, "token": "\u0120Annual", "merges": "\u0120Ann ual", "raw_count": 1395, "count": 1395, "decode_str": " Annual"} -{"id": 45806, "token": "ignant", "merges": "ign ant", "raw_count": 1395, "count": 1395, "decode_str": "ignant"} -{"id": 40881, "token": "\u0120fa\u00c3\u00a7", "merges": "\u0120fa \u00c3\u00a7", "raw_count": 1395, "count": 1395, "decode_str": " fa\u00e7"} -{"id": 35647, "token": "ktiv", "merges": "kt iv", "raw_count": 1395, "count": 1395, "decode_str": "ktiv"} -{"id": 44813, "token": "pmod", "merges": "p mod", "raw_count": 1395, "count": 1395, "decode_str": "pmod"} -{"id": 29738, "token": "\u0120conductance", "merges": "\u0120conduct ance", "raw_count": 1396, "count": 1396, "decode_str": " conductance"} -{"id": 27950, "token": "\u0120Horse", "merges": "\u0120H orse", "raw_count": 1397, "count": 1397, "decode_str": " Horse"} -{"id": 19536, "token": "\u0120Nort", "merges": "\u0120N ort", "raw_count": 484, "count": 1397, "decode_str": " Nort"} -{"id": 35123, "token": "\u0120mmHg", "merges": "\u0120mm Hg", "raw_count": 1397, "count": 1397, "decode_str": " mmHg"} -{"id": 49884, "token": ">{{", "merges": "> {{", "raw_count": 1397, "count": 1397, "decode_str": ">{{"} -{"id": 10162, "token": "\u0120mitochond", "merges": "\u0120mit ochond", "raw_count": 100, "count": 1398, "decode_str": " mitochond"} -{"id": 49199, "token": "\u0120Kepler", "merges": "\u0120Ke pler", "raw_count": 1398, "count": 1398, "decode_str": " Kepler"} -{"id": 41131, "token": "\u0120Amber", "merges": "\u0120A mber", "raw_count": 1398, "count": 1398, "decode_str": " Amber"} -{"id": 11739, "token": "\u0120Yeah", "merges": "\u0120Y eah", "raw_count": 1398, "count": 1398, "decode_str": " Yeah"} -{"id": 27841, "token": "\u0120negligent", "merges": "\u0120neglig ent", "raw_count": 1399, "count": 1399, "decode_str": " negligent"} -{"id": 46280, "token": "\u0120filthy", "merges": "\u0120fil thy", "raw_count": 1399, "count": 1399, "decode_str": " filthy"} -{"id": 49927, "token": "\u0120stator", "merges": "\u0120st ator", "raw_count": 1399, "count": 1399, "decode_str": " stator"} -{"id": 36634, "token": "\u0120SOD", "merges": "\u0120S OD", "raw_count": 1399, "count": 1399, "decode_str": " SOD"} -{"id": 48869, "token": "\u0120LAP", "merges": "\u0120L AP", "raw_count": 1399, "count": 1399, "decode_str": " LAP"} -{"id": 8568, "token": "\u00c3\u0133", "merges": "\u00c3 \u0133", "raw_count": 1394, "count": 1399, "decode_str": "\u00d1"} -{"id": 20146, "token": "\u0120Collins", "merges": "\u0120Coll ins", "raw_count": 1400, "count": 1400, "decode_str": " Collins"} -{"id": 48980, "token": "\u0120LINEAR", "merges": "\u0120LINE AR", "raw_count": 1400, "count": 1400, "decode_str": " LINEAR"} -{"id": 46050, "token": "\u0120Fiber", "merges": "\u0120F iber", "raw_count": 1400, "count": 1400, "decode_str": " Fiber"} -{"id": 23597, "token": "}|\\", "merges": "} |\\", "raw_count": 1400, "count": 1400, "decode_str": "}|\\"} -{"id": 38129, "token": "IImage", "merges": "II mage", "raw_count": 1401, "count": 1401, "decode_str": "IImage"} -{"id": 27334, "token": "\u0120Kil", "merges": "\u0120K il", "raw_count": 1401, "count": 1401, "decode_str": " Kil"} -{"id": 42003, "token": "\u0120occult", "merges": "\u0120occ ult", "raw_count": 1402, "count": 1402, "decode_str": " occult"} -{"id": 30070, "token": "\u0120zum", "merges": "\u0120z um", "raw_count": 1402, "count": 1402, "decode_str": " zum"} -{"id": 42277, "token": "--;", "merges": "-- ;", "raw_count": 1402, "count": 1402, "decode_str": "--;"} -{"id": 44517, "token": "\u00e3\u0123\u00a8\u00e3\u0123\u0139\u00e3\u0123\u00a6", "merges": "\u00e3\u0123\u00a8 \u00e3\u0123\u0139\u00e3\u0123\u00a6", "raw_count": 1403, "count": 1403, "decode_str": "\u3068\u3057\u3066"} -{"id": 49802, "token": "\u00c3\u00a7as", "merges": "\u00c3\u00a7 as", "raw_count": 1403, "count": 1403, "decode_str": "\u00e7as"} -{"id": 49201, "token": "\u00e3\u0124\u00b1", "merges": "\u00e3\u0124 \u00b1", "raw_count": 1403, "count": 1403, "decode_str": "\u30b1"} -{"id": 20967, "token": "\u0120neurological", "merges": "\u0120neurolog ical", "raw_count": 1404, "count": 1404, "decode_str": " neurological"} -{"id": 43542, "token": "\u0120Morse", "merges": "\u0120Mor se", "raw_count": 1404, "count": 1404, "decode_str": " Morse"} -{"id": 40985, "token": "\u0120Bom", "merges": "\u0120B om", "raw_count": 1404, "count": 1404, "decode_str": " Bom"} -{"id": 33083, "token": "\u0120momento", "merges": "\u0120moment o", "raw_count": 1405, "count": 1405, "decode_str": " momento"} -{"id": 46803, "token": "\u0120enamel", "merges": "\u0120en amel", "raw_count": 1405, "count": 1405, "decode_str": " enamel"} -{"id": 27264, "token": "\u0120Mario", "merges": "\u0120Mar io", "raw_count": 1405, "count": 1405, "decode_str": " Mario"} -{"id": 33614, "token": "\u0120Roc", "merges": "\u0120R oc", "raw_count": 1405, "count": 1405, "decode_str": " Roc"} -{"id": 40583, "token": "rendre", "merges": "rend re", "raw_count": 1406, "count": 1406, "decode_str": "rendre"} -{"id": 38459, "token": "\u0120Stim", "merges": "\u0120St im", "raw_count": 1406, "count": 1406, "decode_str": " Stim"} -{"id": 45639, "token": "\u0120dizz", "merges": "\u0120d izz", "raw_count": 1406, "count": 1406, "decode_str": " dizz"} -{"id": 33280, "token": "\u0120HIF", "merges": "\u0120H IF", "raw_count": 1407, "count": 1407, "decode_str": " HIF"} -{"id": 24381, "token": "\u00e0\u00a4\u0137", "merges": "\u00e0\u00a4 \u0137", "raw_count": 1407, "count": 1407, "decode_str": "\u0915"} -{"id": 35896, "token": "\u0120Grande", "merges": "\u0120Grand e", "raw_count": 1408, "count": 1408, "decode_str": " Grande"} -{"id": 43551, "token": "\u0120niece", "merges": "\u0120nie ce", "raw_count": 1408, "count": 1408, "decode_str": " niece"} -{"id": 43405, "token": "dominal", "merges": "dom inal", "raw_count": 1409, "count": 1409, "decode_str": "dominal"} -{"id": 44400, "token": "\u0120aides", "merges": "\u0120a ides", "raw_count": 1409, "count": 1409, "decode_str": " aides"} -{"id": 32294, "token": "\u00c3\u00a2n", "merges": "\u00c3\u00a2 n", "raw_count": 1409, "count": 1409, "decode_str": "\u00e2n"} -{"id": 17331, "token": "ifndef", "merges": "if ndef", "raw_count": 1410, "count": 1410, "decode_str": "ifndef"} -{"id": 48231, "token": "\u0120NEVER", "merges": "\u0120N EVER", "raw_count": 1410, "count": 1410, "decode_str": " NEVER"} -{"id": 46660, "token": "\u0120sill", "merges": "\u0120s ill", "raw_count": 1410, "count": 1410, "decode_str": " sill"} -{"id": 34573, "token": "rinos", "merges": "rin os", "raw_count": 599, "count": 1411, "decode_str": "rinos"} -{"id": 29961, "token": "\u0120Saw", "merges": "\u0120S aw", "raw_count": 1411, "count": 1411, "decode_str": " Saw"} -{"id": 47864, "token": "\u0120commercials", "merges": "\u0120commercial s", "raw_count": 1412, "count": 1412, "decode_str": " commercials"} -{"id": 47696, "token": "\u0120Meat", "merges": "\u0120Me at", "raw_count": 1412, "count": 1412, "decode_str": " Meat"} -{"id": 39867, "token": "\u00c5\u0124o", "merges": "\u00c5\u0124 o", "raw_count": 1412, "count": 1412, "decode_str": "\u0142o"} -{"id": 21759, "token": "\u0120detectable", "merges": "\u0120detect able", "raw_count": 1413, "count": 1413, "decode_str": " detectable"} -{"id": 46782, "token": "reptococcus", "merges": "rept ococcus", "raw_count": 1413, "count": 1413, "decode_str": "reptococcus"} -{"id": 22043, "token": "\u0120retinal", "merges": "\u0120ret inal", "raw_count": 1413, "count": 1413, "decode_str": " retinal"} -{"id": 16611, "token": "\u0120Creek", "merges": "\u0120C reek", "raw_count": 1413, "count": 1413, "decode_str": " Creek"} -{"id": 35618, "token": "\u0120osteopor", "merges": "\u0120oste opor", "raw_count": 46, "count": 1414, "decode_str": " osteopor"} -{"id": 18682, "token": "\u0120Lawrence", "merges": "\u0120Law rence", "raw_count": 1414, "count": 1414, "decode_str": " Lawrence"} -{"id": 50035, "token": "\u0120Pes", "merges": "\u0120P es", "raw_count": 1414, "count": 1414, "decode_str": " Pes"} -{"id": 38536, "token": "\u0120Questionnaire", "merges": "\u0120Question naire", "raw_count": 1415, "count": 1415, "decode_str": " Questionnaire"} -{"id": 33427, "token": "\u0120Plaza", "merges": "\u0120Pl aza", "raw_count": 1415, "count": 1415, "decode_str": " Plaza"} -{"id": 28317, "token": "\u0120Bath", "merges": "\u0120B ath", "raw_count": 1415, "count": 1415, "decode_str": " Bath"} -{"id": 50837, "token": "\u00e5\u012d\u00a7", "merges": "\u00e5\u012d \u00a7", "raw_count": 1415, "count": 1415, "decode_str": "\u52e7"} -{"id": 49349, "token": "\u00d0\u00b8\u00d1\u0124\u00d0\u00b5\u00d0\u00bb", "merges": "\u00d0\u00b8\u00d1\u0124 \u00d0\u00b5\u00d0\u00bb", "raw_count": 1416, "count": 1416, "decode_str": "\u0438\u0442\u0435\u043b"} -{"id": 47382, "token": "ropathy", "merges": "rop athy", "raw_count": 1416, "count": 1416, "decode_str": "ropathy"} -{"id": 50140, "token": "\u0120Seems", "merges": "\u0120Se ems", "raw_count": 1416, "count": 1416, "decode_str": " Seems"} -{"id": 44822, "token": "\u0120unnatural", "merges": "\u0120un natural", "raw_count": 1417, "count": 1417, "decode_str": " unnatural"} -{"id": 37074, "token": "\u0120saliva", "merges": "\u0120sal iva", "raw_count": 1417, "count": 1417, "decode_str": " saliva"} -{"id": 36185, "token": "\u0120s\u00c3\u0143", "merges": "\u0120s \u00c3\u0143", "raw_count": 1417, "count": 1417, "decode_str": " s\u00ed"} -{"id": 18571, "token": "\u0120arterial", "merges": "\u0120arter ial", "raw_count": 1418, "count": 1418, "decode_str": " arterial"} -{"id": 28913, "token": "\u0120ablation", "merges": "\u0120ab lation", "raw_count": 1418, "count": 1418, "decode_str": " ablation"} -{"id": 48736, "token": "\u0120abrog", "merges": "\u0120ab rog", "raw_count": 1418, "count": 1418, "decode_str": " abrog"} -{"id": 11531, "token": "\u0120inhibitors", "merges": "\u0120inhib itors", "raw_count": 1419, "count": 1419, "decode_str": " inhibitors"} -{"id": 36255, "token": "\u0120entangled", "merges": "\u0120entang led", "raw_count": 1419, "count": 1419, "decode_str": " entangled"} -{"id": 48541, "token": "\u0120plethora", "merges": "\u0120pleth ora", "raw_count": 1419, "count": 1419, "decode_str": " plethora"} -{"id": 46189, "token": "\u0120sinister", "merges": "\u0120sin ister", "raw_count": 1419, "count": 1419, "decode_str": " sinister"} -{"id": 34373, "token": "utively", "merges": "ut ively", "raw_count": 1419, "count": 1419, "decode_str": "utively"} -{"id": 16638, "token": "\u0120McK", "merges": "\u0120Mc K", "raw_count": 1118, "count": 1419, "decode_str": " McK"} -{"id": 37290, "token": "\u0120annihilation", "merges": "\u0120annih ilation", "raw_count": 1420, "count": 1420, "decode_str": " annihilation"} -{"id": 49532, "token": "\u0120temperament", "merges": "\u0120temper ament", "raw_count": 1420, "count": 1420, "decode_str": " temperament"} -{"id": 38054, "token": "\u0120momenta", "merges": "\u0120moment a", "raw_count": 1420, "count": 1420, "decode_str": " momenta"} -{"id": 12733, "token": "\u0120plasm", "merges": "\u0120pl asm", "raw_count": 759, "count": 1420, "decode_str": " plasm"} -{"id": 36526, "token": "\u00c3\u00a1z", "merges": "\u00c3\u00a1 z", "raw_count": 1420, "count": 1420, "decode_str": "\u00e1z"} -{"id": 26528, "token": "\u0120spleen", "merges": "\u0120sp leen", "raw_count": 1421, "count": 1421, "decode_str": " spleen"} -{"id": 47084, "token": "indicated", "merges": "ind icated", "raw_count": 1422, "count": 1422, "decode_str": "indicated"} -{"id": 39524, "token": "\u0120MVP", "merges": "\u0120M VP", "raw_count": 1422, "count": 1422, "decode_str": " MVP"} -{"id": 24020, "token": "\u0120regimen", "merges": "\u0120regim en", "raw_count": 1423, "count": 1423, "decode_str": " regimen"} -{"id": 41024, "token": "\u0120amused", "merges": "\u0120am used", "raw_count": 1423, "count": 1423, "decode_str": " amused"} -{"id": 28892, "token": "Theorem", "merges": "The orem", "raw_count": 1423, "count": 1423, "decode_str": "Theorem"} -{"id": 48440, "token": "usamm", "merges": "us amm", "raw_count": 1423, "count": 1423, "decode_str": "usamm"} -{"id": 36385, "token": "\u0120palp", "merges": "\u0120pal p", "raw_count": 1423, "count": 1423, "decode_str": " palp"} -{"id": 44323, "token": "\u0120Cake", "merges": "\u0120C ake", "raw_count": 1423, "count": 1423, "decode_str": " Cake"} -{"id": 21523, "token": "\u0120Rud", "merges": "\u0120R ud", "raw_count": 1423, "count": 1423, "decode_str": " Rud"} -{"id": 16861, "token": "\u0120Singapore", "merges": "\u0120Sing apore", "raw_count": 1424, "count": 1424, "decode_str": " Singapore"} -{"id": 19019, "token": "\u0120embryos", "merges": "\u0120embry os", "raw_count": 1424, "count": 1424, "decode_str": " embryos"} -{"id": 19670, "token": "\u0120Theatre", "merges": "\u0120The atre", "raw_count": 1424, "count": 1424, "decode_str": " Theatre"} -{"id": 46441, "token": "\u0120foliage", "merges": "\u0120foli age", "raw_count": 1424, "count": 1424, "decode_str": " foliage"} -{"id": 32469, "token": "\u0120simmer", "merges": "\u0120sim mer", "raw_count": 1424, "count": 1424, "decode_str": " simmer"} -{"id": 15876, "token": "binant", "merges": "bin ant", "raw_count": 667, "count": 1424, "decode_str": "binant"} -{"id": 41953, "token": "\u0120drm", "merges": "\u0120d rm", "raw_count": 1424, "count": 1424, "decode_str": " drm"} -{"id": 42156, "token": "\u0120natur", "merges": "\u0120nat ur", "raw_count": 1425, "count": 1425, "decode_str": " natur"} -{"id": 44294, "token": "\u0120phenomenal", "merges": "\u0120phenomen al", "raw_count": 1426, "count": 1426, "decode_str": " phenomenal"} -{"id": 26024, "token": "\u0120Molecular", "merges": "\u0120M olecular", "raw_count": 1426, "count": 1426, "decode_str": " Molecular"} -{"id": 29199, "token": "\u0120vanishing", "merges": "\u0120van ishing", "raw_count": 1426, "count": 1426, "decode_str": " vanishing"} -{"id": 44029, "token": "arroll", "merges": "ar roll", "raw_count": 795, "count": 1426, "decode_str": "arroll"} -{"id": 49612, "token": "\u0120tame", "merges": "\u0120t ame", "raw_count": 1426, "count": 1426, "decode_str": " tame"} -{"id": 47639, "token": "\u0120unmist", "merges": "\u0120unm ist", "raw_count": 76, "count": 1427, "decode_str": " unmist"} -{"id": 48393, "token": "\u0120skirts", "merges": "\u0120sk irts", "raw_count": 1427, "count": 1427, "decode_str": " skirts"} -{"id": 48202, "token": "\u0120gond", "merges": "\u0120g ond", "raw_count": 1427, "count": 1427, "decode_str": " gond"} -{"id": 25212, "token": "\u0120NGC", "merges": "\u0120N GC", "raw_count": 1427, "count": 1427, "decode_str": " NGC"} -{"id": 18736, "token": ")[(", "merges": ")[ (", "raw_count": 1428, "count": 1428, "decode_str": ")[("} -{"id": 39067, "token": "\u0120Volunte", "merges": "\u0120Vol unte", "raw_count": 1429, "count": 1429, "decode_str": " Volunte"} -{"id": 22301, "token": "\u0120Estate", "merges": "\u0120E state", "raw_count": 1429, "count": 1429, "decode_str": " Estate"} -{"id": 38652, "token": "propyl", "merges": "prop yl", "raw_count": 1429, "count": 1429, "decode_str": "propyl"} -{"id": 46881, "token": "\u0120outfits", "merges": "\u0120out fits", "raw_count": 1430, "count": 1430, "decode_str": " outfits"} -{"id": 27772, "token": "\u0120kann", "merges": "\u0120k ann", "raw_count": 1430, "count": 1430, "decode_str": " kann"} -{"id": 31963, "token": "\u0120\u00e2\u013b", "merges": "\u0120\u00e2 \u013b", "raw_count": 1430, "count": 1430, "decode_str": " \ufffd"} -{"id": 50095, "token": "afx", "merges": "af x", "raw_count": 1430, "count": 1430, "decode_str": "afx"} -{"id": 24366, "token": "\u0120conjecture", "merges": "\u0120conject ure", "raw_count": 1431, "count": 1431, "decode_str": " conjecture"} -{"id": 14798, "token": "\u0120affidav", "merges": "\u0120aff idav", "raw_count": 0, "count": 1431, "decode_str": " affidav"} -{"id": 41185, "token": "\u0120biting", "merges": "\u0120bit ing", "raw_count": 1431, "count": 1431, "decode_str": " biting"} -{"id": 12429, "token": "\u0120Matt", "merges": "\u0120M att", "raw_count": 1431, "count": 1431, "decode_str": " Matt"} -{"id": 30687, "token": "\u0120kans", "merges": "\u0120k ans", "raw_count": 1431, "count": 1431, "decode_str": " kans"} -{"id": 48342, "token": "\u0120theolog", "merges": "\u0120the olog", "raw_count": 1432, "count": 1432, "decode_str": " theolog"} -{"id": 22455, "token": "\u0120Mason", "merges": "\u0120M ason", "raw_count": 1432, "count": 1432, "decode_str": " Mason"} -{"id": 47156, "token": "\u0120muddy", "merges": "\u0120mud dy", "raw_count": 1432, "count": 1432, "decode_str": " muddy"} -{"id": 19935, "token": "\u0120aan", "merges": "\u0120a an", "raw_count": 1432, "count": 1432, "decode_str": " aan"} -{"id": 41274, "token": "\u0120bulky", "merges": "\u0120bul ky", "raw_count": 1433, "count": 1433, "decode_str": " bulky"} -{"id": 49899, "token": "icarbon", "merges": "icar bon", "raw_count": 1434, "count": 1434, "decode_str": "icarbon"} -{"id": 48708, "token": "!\");", "merges": "!\" );", "raw_count": 1434, "count": 1434, "decode_str": "!\");"} -{"id": 47895, "token": "\u0120authored", "merges": "\u0120auth ored", "raw_count": 1435, "count": 1435, "decode_str": " authored"} -{"id": 19386, "token": "\u0120jQuery", "merges": "\u0120j Query", "raw_count": 1436, "count": 1436, "decode_str": " jQuery"} -{"id": 47098, "token": "\u0120meats", "merges": "\u0120me ats", "raw_count": 1436, "count": 1436, "decode_str": " meats"} -{"id": 46564, "token": "\u0120dealership", "merges": "\u0120deal ership", "raw_count": 1437, "count": 1437, "decode_str": " dealership"} -{"id": 43569, "token": "\u0120tunes", "merges": "\u0120tun es", "raw_count": 1437, "count": 1437, "decode_str": " tunes"} -{"id": 24214, "token": "\u0120lept", "merges": "\u0120le pt", "raw_count": 995, "count": 1437, "decode_str": " lept"} -{"id": 39738, "token": "\u0120psychiatrist", "merges": "\u0120psychiat rist", "raw_count": 1438, "count": 1438, "decode_str": " psychiatrist"} -{"id": 49443, "token": "\u0120disdain", "merges": "\u0120dis dain", "raw_count": 1438, "count": 1438, "decode_str": " disdain"} -{"id": 33666, "token": "\u0120gluten", "merges": "\u0120gl uten", "raw_count": 1438, "count": 1438, "decode_str": " gluten"} -{"id": 41459, "token": "\u0120cages", "merges": "\u0120c ages", "raw_count": 1438, "count": 1438, "decode_str": " cages"} -{"id": 25157, "token": "\u0120Aus", "merges": "\u0120A us", "raw_count": 1439, "count": 1439, "decode_str": " Aus"} -{"id": 31077, "token": "\u0120GST", "merges": "\u0120G ST", "raw_count": 1439, "count": 1439, "decode_str": " GST"} -{"id": 47756, "token": "\u0120Dru", "merges": "\u0120D ru", "raw_count": 1439, "count": 1439, "decode_str": " Dru"} -{"id": 40518, "token": "\u0120Bd", "merges": "\u0120B d", "raw_count": 1439, "count": 1439, "decode_str": " Bd"} -{"id": 30415, "token": "\u0120hemorrhage", "merges": "\u0120hemorrh age", "raw_count": 1440, "count": 1440, "decode_str": " hemorrhage"} -{"id": 48842, "token": "\u0120newborns", "merges": "\u0120newborn s", "raw_count": 1440, "count": 1440, "decode_str": " newborns"} -{"id": 15435, "token": "\u0120Patrick", "merges": "\u0120Pat rick", "raw_count": 1440, "count": 1440, "decode_str": " Patrick"} -{"id": 47287, "token": "\u0120strlen", "merges": "\u0120str len", "raw_count": 1440, "count": 1440, "decode_str": " strlen"} -{"id": 48221, "token": "rists", "merges": "r ists", "raw_count": 1440, "count": 1440, "decode_str": "rists"} -{"id": 43821, "token": "\u0120axon", "merges": "\u0120ax on", "raw_count": 1440, "count": 1440, "decode_str": " axon"} -{"id": 30973, "token": "\u0120banc", "merges": "\u0120b anc", "raw_count": 1440, "count": 1440, "decode_str": " banc"} -{"id": 40322, "token": "\u0120Nacional", "merges": "\u0120N acional", "raw_count": 1441, "count": 1441, "decode_str": " Nacional"} -{"id": 33726, "token": "\u0120freshman", "merges": "\u0120fresh man", "raw_count": 1441, "count": 1441, "decode_str": " freshman"} -{"id": 36280, "token": "\u0120smelled", "merges": "\u0120sm elled", "raw_count": 1441, "count": 1441, "decode_str": " smelled"} -{"id": 15092, "token": "\u0120Within", "merges": "\u0120With in", "raw_count": 1441, "count": 1441, "decode_str": " Within"} -{"id": 44450, "token": "amais", "merges": "ama is", "raw_count": 1147, "count": 1441, "decode_str": "amais"} -{"id": 29937, "token": "\u00d8\u00b7", "merges": "\u00d8 \u00b7", "raw_count": 1441, "count": 1441, "decode_str": "\u0637"} -{"id": 47987, "token": "\u0120percol", "merges": "\u0120per col", "raw_count": 1442, "count": 1442, "decode_str": " percol"} -{"id": 34689, "token": "\u0120Phen", "merges": "\u0120P hen", "raw_count": 1442, "count": 1442, "decode_str": " Phen"} -{"id": 44560, "token": "\u0120Exposure", "merges": "\u0120Ex posure", "raw_count": 1443, "count": 1443, "decode_str": " Exposure"} -{"id": 34553, "token": "\u0120yelling", "merges": "\u0120y elling", "raw_count": 1443, "count": 1443, "decode_str": " yelling"} -{"id": 26864, "token": "\u0120Eagle", "merges": "\u0120E agle", "raw_count": 1444, "count": 1444, "decode_str": " Eagle"} -{"id": 24138, "token": "\u0120Reyn", "merges": "\u0120Re yn", "raw_count": 326, "count": 1444, "decode_str": " Reyn"} -{"id": 28420, "token": "ukary", "merges": "uk ary", "raw_count": 802, "count": 1444, "decode_str": "ukary"} -{"id": 40449, "token": "\u0120disgusting", "merges": "\u0120disgust ing", "raw_count": 1445, "count": 1445, "decode_str": " disgusting"} -{"id": 34264, "token": "\u0120XI", "merges": "\u0120X I", "raw_count": 1445, "count": 1445, "decode_str": " XI"} -{"id": 46386, "token": "\u0120Hole", "merges": "\u0120H ole", "raw_count": 1446, "count": 1446, "decode_str": " Hole"} -{"id": 29730, "token": "\u0120Aur", "merges": "\u0120A ur", "raw_count": 541, "count": 1446, "decode_str": " Aur"} -{"id": 46960, "token": "\u0120fertilization", "merges": "\u0120fert ilization", "raw_count": 1447, "count": 1447, "decode_str": " fertilization"} -{"id": 32141, "token": "\u00e1\u0125\u0132\u00e1\u0125", "merges": "\u00e1\u0125\u0132 \u00e1\u0125", "raw_count": 1447, "count": 1447, "decode_str": "\u10d0\ufffd"} -{"id": 42784, "token": "\u0120Tg", "merges": "\u0120T g", "raw_count": 1447, "count": 1447, "decode_str": " Tg"} -{"id": 36392, "token": "\u0120photometric", "merges": "\u0120phot ometric", "raw_count": 1448, "count": 1448, "decode_str": " photometric"} -{"id": 36568, "token": "\u0120undetect", "merges": "\u0120und etect", "raw_count": 1448, "count": 1448, "decode_str": " undetect"} -{"id": 46337, "token": "\u0120betrayal", "merges": "\u0120betray al", "raw_count": 1448, "count": 1448, "decode_str": " betrayal"} -{"id": 10406, "token": "\u0120Olymp", "merges": "\u0120O lymp", "raw_count": 492, "count": 1448, "decode_str": " Olymp"} -{"id": 27280, "token": "\u0120Nak", "merges": "\u0120N ak", "raw_count": 1448, "count": 1448, "decode_str": " Nak"} -{"id": 31593, "token": "\u0120Sed", "merges": "\u0120S ed", "raw_count": 1448, "count": 1448, "decode_str": " Sed"} -{"id": 50229, "token": "\u0120boarded", "merges": "\u0120board ed", "raw_count": 1449, "count": 1449, "decode_str": " boarded"} -{"id": 19285, "token": "\u0120infar", "merges": "\u0120inf ar", "raw_count": 245, "count": 1449, "decode_str": " infar"} -{"id": 33479, "token": "\u0120lugar", "merges": "\u0120l ugar", "raw_count": 1449, "count": 1449, "decode_str": " lugar"} -{"id": 7078, "token": "--------------------------------------------------------------------------------------------------------------------------------", "merges": "---------------------------------------------------------------- ----------------------------------------------------------------", "raw_count": 1127, "count": 1450, "decode_str": "--------------------------------------------------------------------------------------------------------------------------------"} -{"id": 39420, "token": "\u0120Lap", "merges": "\u0120L ap", "raw_count": 1450, "count": 1450, "decode_str": " Lap"} -{"id": 27516, "token": "\u0120Som", "merges": "\u0120S om", "raw_count": 1450, "count": 1450, "decode_str": " Som"} -{"id": 40536, "token": "\u0120antioxidants", "merges": "\u0120antioxid ants", "raw_count": 1451, "count": 1451, "decode_str": " antioxidants"} -{"id": 28281, "token": "\u0120HOW", "merges": "\u0120H OW", "raw_count": 1354, "count": 1451, "decode_str": " HOW"} -{"id": 27577, "token": "\u0120modulated", "merges": "\u0120mod ulated", "raw_count": 1452, "count": 1452, "decode_str": " modulated"} -{"id": 48450, "token": "\u0120inertial", "merges": "\u0120inert ial", "raw_count": 1452, "count": 1452, "decode_str": " inertial"} -{"id": 16835, "token": "\u0120Hung", "merges": "\u0120H ung", "raw_count": 842, "count": 1452, "decode_str": " Hung"} -{"id": 46175, "token": "\u00e0\u00a4\u00a6", "merges": "\u00e0\u00a4 \u00a6", "raw_count": 1452, "count": 1452, "decode_str": "\u0926"} -{"id": 49203, "token": "\u0120dilute", "merges": "\u0120dil ute", "raw_count": 1453, "count": 1453, "decode_str": " dilute"} -{"id": 27659, "token": "\u0120Stuart", "merges": "\u0120St uart", "raw_count": 1453, "count": 1453, "decode_str": " Stuart"} -{"id": 37568, "token": "\u0120lleg", "merges": "\u0120l leg", "raw_count": 1453, "count": 1453, "decode_str": " lleg"} -{"id": 40841, "token": "\u0120lors", "merges": "\u0120l ors", "raw_count": 1453, "count": 1453, "decode_str": " lors"} -{"id": 27737, "token": "\u0120Bog", "merges": "\u0120B og", "raw_count": 1453, "count": 1453, "decode_str": " Bog"} -{"id": 21899, "token": "\u0120observational", "merges": "\u0120observ ational", "raw_count": 1454, "count": 1454, "decode_str": " observational"} -{"id": 36416, "token": "uminescence", "merges": "umines cence", "raw_count": 1454, "count": 1454, "decode_str": "uminescence"} -{"id": 40762, "token": "\u0120inning", "merges": "\u0120in ning", "raw_count": 1454, "count": 1454, "decode_str": " inning"} -{"id": 43246, "token": "\u00d8\u00b3\u00d8\u00aa", "merges": "\u00d8\u00b3 \u00d8\u00aa", "raw_count": 1454, "count": 1454, "decode_str": "\u0633\u062a"} -{"id": 33327, "token": "Supporting", "merges": "Supp orting", "raw_count": 1455, "count": 1455, "decode_str": "Supporting"} -{"id": 41093, "token": "oarth", "merges": "o arth", "raw_count": 133, "count": 1455, "decode_str": "oarth"} -{"id": 25890, "token": "\u00c3\u00b4t", "merges": "\u00c3\u00b4 t", "raw_count": 1455, "count": 1455, "decode_str": "\u00f4t"} -{"id": 34348, "token": "\u0120transcribed", "merges": "\u0120trans cribed", "raw_count": 1456, "count": 1456, "decode_str": " transcribed"} -{"id": 15194, "token": "\u00c4\u0135", "merges": "\u00c4 \u0135", "raw_count": 1456, "count": 1456, "decode_str": "\u0113"} -{"id": 20163, "token": "\u0120Campbell", "merges": "\u0120Camp bell", "raw_count": 1457, "count": 1457, "decode_str": " Campbell"} -{"id": 40688, "token": "\u0120Into", "merges": "\u0120In to", "raw_count": 1457, "count": 1457, "decode_str": " Into"} -{"id": 49314, "token": "\u0120Wan", "merges": "\u0120W an", "raw_count": 1457, "count": 1457, "decode_str": " Wan"} -{"id": 26618, "token": "\u0120auditory", "merges": "\u0120aud itory", "raw_count": 1458, "count": 1458, "decode_str": " auditory"} -{"id": 15999, "token": "\u0120Unless", "merges": "\u0120Un less", "raw_count": 1458, "count": 1458, "decode_str": " Unless"} -{"id": 39669, "token": "\u0120EVERY", "merges": "\u0120EV ERY", "raw_count": 1458, "count": 1458, "decode_str": " EVERY"} -{"id": 26543, "token": "\u0120Luck", "merges": "\u0120L uck", "raw_count": 1240, "count": 1458, "decode_str": " Luck"} -{"id": 42425, "token": "cumin", "merges": "c umin", "raw_count": 1458, "count": 1458, "decode_str": "cumin"} -{"id": 14481, "token": "\u0120inhibited", "merges": "\u0120inhib ited", "raw_count": 1459, "count": 1459, "decode_str": " inhibited"} -{"id": 34349, "token": "\u0120Novel", "merges": "\u0120No vel", "raw_count": 1459, "count": 1459, "decode_str": " Novel"} -{"id": 40352, "token": "\u00e3\u0125\u012d", "merges": "\u00e3\u0125 \u012d", "raw_count": 1459, "count": 1459, "decode_str": "\u30cb"} -{"id": 31759, "token": ">()", "merges": "> ()", "raw_count": 1459, "count": 1459, "decode_str": ">()"} -{"id": 47735, "token": "\u00d1\u013a", "merges": "\u00d1 \u013a", "raw_count": 1459, "count": 1459, "decode_str": "\u0458"} -{"id": 33486, "token": "\u0120infamous", "merges": "\u0120inf amous", "raw_count": 1460, "count": 1460, "decode_str": " infamous"} -{"id": 38430, "token": "\u0120Neumann", "merges": "\u0120Ne umann", "raw_count": 1460, "count": 1460, "decode_str": " Neumann"} -{"id": 16693, "token": "\u0120\u00c5\u0141", "merges": "\u0120\u00c5 \u0141", "raw_count": 1442, "count": 1460, "decode_str": " \u015f"} -{"id": 45614, "token": "\u0120SiO", "merges": "\u0120Si O", "raw_count": 1461, "count": 1461, "decode_str": " SiO"} -{"id": 46404, "token": "empre", "merges": "em pre", "raw_count": 799, "count": 1462, "decode_str": "empre"} -{"id": 52407, "token": "\u00e6\u0143\u00b4", "merges": "\u00e6\u0143 \u00b4", "raw_count": 1462, "count": 1462, "decode_str": "\u6b74"} -{"id": 50205, "token": "\u0120oppressive", "merges": "\u0120opp ressive", "raw_count": 1463, "count": 1463, "decode_str": " oppressive"} -{"id": 44297, "token": "\u0120trenches", "merges": "\u0120tren ches", "raw_count": 1463, "count": 1463, "decode_str": " trenches"} -{"id": 37735, "token": "\u0120startups", "merges": "\u0120start ups", "raw_count": 1463, "count": 1463, "decode_str": " startups"} -{"id": 38684, "token": "\u0120Stark", "merges": "\u0120St ark", "raw_count": 1463, "count": 1463, "decode_str": " Stark"} -{"id": 32877, "token": "\u0120ethylene", "merges": "\u0120 ethylene", "raw_count": 1464, "count": 1464, "decode_str": " ethylene"} -{"id": 15396, "token": "\u0120mutants", "merges": "\u0120mut ants", "raw_count": 1464, "count": 1464, "decode_str": " mutants"} -{"id": 43653, "token": "\u0120taxonomic", "merges": "\u0120tax onomic", "raw_count": 1465, "count": 1465, "decode_str": " taxonomic"} -{"id": 35015, "token": "\u0120Sessions", "merges": "\u0120S essions", "raw_count": 1465, "count": 1465, "decode_str": " Sessions"} -{"id": 38326, "token": "\u0120pellets", "merges": "\u0120pel lets", "raw_count": 1465, "count": 1465, "decode_str": " pellets"} -{"id": 35054, "token": "\u0120memb", "merges": "\u0120mem b", "raw_count": 1465, "count": 1465, "decode_str": " memb"} -{"id": 49244, "token": "\u0120MTV", "merges": "\u0120M TV", "raw_count": 1465, "count": 1465, "decode_str": " MTV"} -{"id": 31107, "token": "\u0120Md", "merges": "\u0120M d", "raw_count": 1465, "count": 1465, "decode_str": " Md"} -{"id": 48249, "token": "\u0120fascination", "merges": "\u0120fasc ination", "raw_count": 1466, "count": 1466, "decode_str": " fascination"} -{"id": 37292, "token": "\u0120\u00c3\u00b8", "merges": "\u0120\u00c3 \u00b8", "raw_count": 1466, "count": 1466, "decode_str": " \u00f8"} -{"id": 38875, "token": "iasis", "merges": "i asis", "raw_count": 1467, "count": 1467, "decode_str": "iasis"} -{"id": 49438, "token": "ulif", "merges": "ul if", "raw_count": 1467, "count": 1467, "decode_str": "ulif"} -{"id": 39109, "token": "\u0120ophthal", "merges": "\u0120op hthal", "raw_count": 1468, "count": 1468, "decode_str": " ophthal"} -{"id": 42007, "token": "itosan", "merges": "itos an", "raw_count": 993, "count": 1468, "decode_str": "itosan"} -{"id": 28509, "token": "\u0120JUST", "merges": "\u0120J UST", "raw_count": 1468, "count": 1468, "decode_str": " JUST"} -{"id": 33515, "token": "\u0120Perl", "merges": "\u0120Per l", "raw_count": 1468, "count": 1468, "decode_str": " Perl"} -{"id": 26053, "token": "\u0120uit", "merges": "\u0120u it", "raw_count": 1468, "count": 1468, "decode_str": " uit"} -{"id": 34146, "token": "\u0120Lt", "merges": "\u0120L t", "raw_count": 1468, "count": 1468, "decode_str": " Lt"} -{"id": 7160, "token": "\u0120Their", "merges": "\u0120The ir", "raw_count": 1469, "count": 1469, "decode_str": " Their"} -{"id": 42765, "token": "\u0120Gri", "merges": "\u0120G ri", "raw_count": 1470, "count": 1470, "decode_str": " Gri"} -{"id": 41501, "token": "\u00d1\u0123\u00d1\u012e", "merges": "\u00d1\u0123 \u00d1\u012e", "raw_count": 1470, "count": 1470, "decode_str": "\u0441\u044c"} -{"id": 19705, "token": "\u0120Athe", "merges": "\u0120A the", "raw_count": 1231, "count": 1471, "decode_str": " Athe"} -{"id": 28504, "token": "\u0120Stay", "merges": "\u0120St ay", "raw_count": 1471, "count": 1471, "decode_str": " Stay"} -{"id": 26678, "token": "^--", "merges": "^ --", "raw_count": 1471, "count": 1471, "decode_str": "^--"} -{"id": 38986, "token": "\u0120SERVICES", "merges": "\u0120SERV ICES", "raw_count": 1472, "count": 1472, "decode_str": " SERVICES"} -{"id": 46957, "token": "\u0120decaying", "merges": "\u0120decay ing", "raw_count": 1472, "count": 1472, "decode_str": " decaying"} -{"id": 38375, "token": "ableView", "merges": "able View", "raw_count": 1472, "count": 1472, "decode_str": "ableView"} -{"id": 36854, "token": "\u0120polyp", "merges": "\u0120pol yp", "raw_count": 1472, "count": 1472, "decode_str": " polyp"} -{"id": 44727, "token": "\u0120Rouge", "merges": "\u0120Rou ge", "raw_count": 1472, "count": 1472, "decode_str": " Rouge"} -{"id": 39070, "token": "\u0120Eff", "merges": "\u0120E ff", "raw_count": 1472, "count": 1472, "decode_str": " Eff"} -{"id": 38992, "token": "\u0120batting", "merges": "\u0120bat ting", "raw_count": 1473, "count": 1473, "decode_str": " batting"} -{"id": 34201, "token": "escence", "merges": "es cence", "raw_count": 1283, "count": 1473, "decode_str": "escence"} -{"id": 20377, "token": "yscall", "merges": "ys call", "raw_count": 352, "count": 1473, "decode_str": "yscall"} -{"id": 39612, "token": "\u0120perceptual", "merges": "\u0120per ceptual", "raw_count": 1474, "count": 1474, "decode_str": " perceptual"} -{"id": 44395, "token": "\u0120bumps", "merges": "\u0120b umps", "raw_count": 1474, "count": 1474, "decode_str": " bumps"} -{"id": 26989, "token": "\u0120Asp", "merges": "\u0120A sp", "raw_count": 1474, "count": 1474, "decode_str": " Asp"} -{"id": 170, "token": "\u00ee", "merges": "NULL", "raw_count": 1474, "count": 1474, "decode_str": "\ufffd"} -{"id": 26344, "token": "\u00d7\u00a9", "merges": "\u00d7 \u00a9", "raw_count": 1475, "count": 1475, "decode_str": "\u05e9"} -{"id": 40453, "token": "Petition", "merges": "P etition", "raw_count": 1476, "count": 1476, "decode_str": "Petition"} -{"id": 40569, "token": "\u0120mailed", "merges": "\u0120m ailed", "raw_count": 1476, "count": 1476, "decode_str": " mailed"} -{"id": 24367, "token": "\u0120Sor", "merges": "\u0120S or", "raw_count": 1476, "count": 1476, "decode_str": " Sor"} -{"id": 46273, "token": "\u0120STM", "merges": "\u0120ST M", "raw_count": 1476, "count": 1476, "decode_str": " STM"} -{"id": 43147, "token": "v\u00c3\u00a9", "merges": "v \u00c3\u00a9", "raw_count": 1476, "count": 1476, "decode_str": "v\u00e9"} -{"id": 10623, "token": "\u00e1\u00bd", "merges": "\u00e1 \u00bd", "raw_count": 735, "count": 1476, "decode_str": "\ufffd"} -{"id": 27502, "token": "\u0120Hoff", "merges": "\u0120H off", "raw_count": 868, "count": 1477, "decode_str": " Hoff"} -{"id": 46952, "token": "\u0120avid", "merges": "\u0120av id", "raw_count": 1477, "count": 1477, "decode_str": " avid"} -{"id": 38433, "token": "\u0120dissoci", "merges": "\u0120diss oci", "raw_count": 1478, "count": 1478, "decode_str": " dissoci"} -{"id": 18364, "token": "\u0120thromb", "merges": "\u0120throm b", "raw_count": 648, "count": 1478, "decode_str": " thromb"} -{"id": 31802, "token": "\u0120Viv", "merges": "\u0120V iv", "raw_count": 1478, "count": 1478, "decode_str": " Viv"} -{"id": 41132, "token": "\u00e0\u00b8\u0137", "merges": "\u00e0\u00b8 \u0137", "raw_count": 1478, "count": 1478, "decode_str": "\u0e15"} -{"id": 22709, "token": "\u0120Rodrig", "merges": "\u0120Rod rig", "raw_count": 810, "count": 1479, "decode_str": " Rodrig"} -{"id": 28362, "token": "\u0120Gross", "merges": "\u0120G ross", "raw_count": 1479, "count": 1479, "decode_str": " Gross"} -{"id": 23972, "token": "\u0120Horn", "merges": "\u0120H orn", "raw_count": 1479, "count": 1479, "decode_str": " Horn"} -{"id": 28075, "token": "\u0120ionization", "merges": "\u0120ion ization", "raw_count": 1480, "count": 1480, "decode_str": " ionization"} -{"id": 27761, "token": "\u0120Standards", "merges": "\u0120Stand ards", "raw_count": 1480, "count": 1480, "decode_str": " Standards"} -{"id": 31165, "token": "\u0120\u00e0\u00ae", "merges": "\u0120 \u00e0\u00ae", "raw_count": 1480, "count": 1480, "decode_str": " \ufffd"} -{"id": 40460, "token": "\u0120corollary", "merges": "\u0120cor ollary", "raw_count": 1481, "count": 1481, "decode_str": " corollary"} -{"id": 18593, "token": "\u0120Nap", "merges": "\u0120N ap", "raw_count": 1221, "count": 1481, "decode_str": " Nap"} -{"id": 42291, "token": "\u0120Xu", "merges": "\u0120X u", "raw_count": 1481, "count": 1481, "decode_str": " Xu"} -{"id": 30265, "token": "\u00d8\u00b5", "merges": "\u00d8 \u00b5", "raw_count": 1481, "count": 1481, "decode_str": "\u0635"} -{"id": 37357, "token": "\u0120Problems", "merges": "\u0120Pro blems", "raw_count": 1482, "count": 1482, "decode_str": " Problems"} -{"id": 44997, "token": "\u0120passer", "merges": "\u0120pass er", "raw_count": 1482, "count": 1482, "decode_str": " passer"} -{"id": 33092, "token": "\u0120halluc", "merges": "\u0120hall uc", "raw_count": 1482, "count": 1482, "decode_str": " halluc"} -{"id": 47931, "token": "\u00d8\u00a7\u00d8\u00a8", "merges": "\u00d8\u00a7\u00d8 \u00a8", "raw_count": 1482, "count": 1482, "decode_str": "\u0627\u0628"} -{"id": 40407, "token": "\u0120Kub", "merges": "\u0120K ub", "raw_count": 1482, "count": 1482, "decode_str": " Kub"} -{"id": 45821, "token": "\u00d9\u00be", "merges": "\u00d9 \u00be", "raw_count": 1482, "count": 1482, "decode_str": "\u067e"} -{"id": 32184, "token": "\u0120metabolite", "merges": "\u0120metabol ite", "raw_count": 1483, "count": 1483, "decode_str": " metabolite"} -{"id": 22801, "token": "\u0120Stevens", "merges": "\u0120Ste vens", "raw_count": 941, "count": 1483, "decode_str": " Stevens"} -{"id": 31373, "token": "\u0120Whole", "merges": "\u0120Wh ole", "raw_count": 1483, "count": 1483, "decode_str": " Whole"} -{"id": 5786, "token": "otimes", "merges": "ot imes", "raw_count": 1483, "count": 1483, "decode_str": "otimes"} -{"id": 21582, "token": "\u0120quas", "merges": "\u0120qu as", "raw_count": 1483, "count": 1483, "decode_str": " quas"} -{"id": 33052, "token": "\u0120keV", "merges": "\u0120ke V", "raw_count": 1483, "count": 1483, "decode_str": " keV"} -{"id": 18323, "token": "\u0120biopsy", "merges": "\u0120bi opsy", "raw_count": 1484, "count": 1484, "decode_str": " biopsy"} -{"id": 49527, "token": "oughed", "merges": "oug hed", "raw_count": 1484, "count": 1484, "decode_str": "oughed"} -{"id": 44723, "token": "\u0120\u00e2\u0128\u0133", "merges": "\u0120\u00e2\u0128 \u0133", "raw_count": 1484, "count": 1484, "decode_str": " \u2191"} -{"id": 47210, "token": "omyc", "merges": "omy c", "raw_count": 1484, "count": 1484, "decode_str": "omyc"} -{"id": 41779, "token": "\u0120FY", "merges": "\u0120F Y", "raw_count": 1484, "count": 1484, "decode_str": " FY"} -{"id": 39074, "token": "\u0120autobi", "merges": "\u0120aut obi", "raw_count": 1485, "count": 1485, "decode_str": " autobi"} -{"id": 44108, "token": "\u0120softer", "merges": "\u0120so fter", "raw_count": 1485, "count": 1485, "decode_str": " softer"} -{"id": 37302, "token": "\u0120raced", "merges": "\u0120r aced", "raw_count": 1485, "count": 1485, "decode_str": " raced"} -{"id": 27807, "token": "\u0120intriguing", "merges": "\u0120intrig uing", "raw_count": 1486, "count": 1486, "decode_str": " intriguing"} -{"id": 23085, "token": "\u0120Andre", "merges": "\u0120And re", "raw_count": 900, "count": 1486, "decode_str": " Andre"} -{"id": 44601, "token": "\u0120blaming", "merges": "\u0120bl aming", "raw_count": 1487, "count": 1487, "decode_str": " blaming"} -{"id": 38969, "token": "\u0120passions", "merges": "\u0120pass ions", "raw_count": 1488, "count": 1488, "decode_str": " passions"} -{"id": 10956, "token": "\u0120Father", "merges": "\u0120F ather", "raw_count": 1488, "count": 1488, "decode_str": " Father"} -{"id": 37352, "token": "\u0120polyethylene", "merges": "\u0120poly ethylene", "raw_count": 1489, "count": 1489, "decode_str": " polyethylene"} -{"id": 45288, "token": "\u0120straps", "merges": "\u0120stra ps", "raw_count": 1489, "count": 1489, "decode_str": " straps"} -{"id": 45054, "token": "\u0120foli", "merges": "\u0120fol i", "raw_count": 65, "count": 1489, "decode_str": " foli"} -{"id": 39306, "token": "\u0120reproducing", "merges": "\u0120reprodu cing", "raw_count": 1490, "count": 1490, "decode_str": " reproducing"} -{"id": 45800, "token": "\u0120ascribed", "merges": "\u0120as cribed", "raw_count": 1490, "count": 1490, "decode_str": " ascribed"} -{"id": 35469, "token": "\u0120Outside", "merges": "\u0120Out side", "raw_count": 1490, "count": 1490, "decode_str": " Outside"} -{"id": 45567, "token": "strous", "merges": "str ous", "raw_count": 244, "count": 1490, "decode_str": "strous"} -{"id": 4397, "token": "\u0120September", "merges": "\u0120Sept ember", "raw_count": 1491, "count": 1491, "decode_str": " September"} -{"id": 26412, "token": "\u0120pleading", "merges": "\u0120ple ading", "raw_count": 1491, "count": 1491, "decode_str": " pleading"} -{"id": 16345, "token": "nutrients", "merges": "nut rients", "raw_count": 1491, "count": 1491, "decode_str": "nutrients"} -{"id": 45974, "token": ".\";", "merges": ".\" ;", "raw_count": 1491, "count": 1491, "decode_str": ".\";"} -{"id": 43520, "token": "\u0120resistivity", "merges": "\u0120resist ivity", "raw_count": 1492, "count": 1492, "decode_str": " resistivity"} -{"id": 38525, "token": "\u0120blogging", "merges": "\u0120blog ging", "raw_count": 1492, "count": 1492, "decode_str": " blogging"} -{"id": 15002, "token": "\u0120WITHOUT", "merges": "\u0120WITH OUT", "raw_count": 1492, "count": 1492, "decode_str": " WITHOUT"} -{"id": 27117, "token": "\u0120Yam", "merges": "\u0120Y am", "raw_count": 1492, "count": 1492, "decode_str": " Yam"} -{"id": 36328, "token": "\u0120Fen", "merges": "\u0120F en", "raw_count": 1492, "count": 1492, "decode_str": " Fen"} -{"id": 27508, "token": "\u0120@\"", "merges": "\u0120@ \"", "raw_count": 1492, "count": 1492, "decode_str": " @\""} -{"id": 14489, "token": "\u00e0\u00b2", "merges": "\u00e0 \u00b2", "raw_count": 1321, "count": 1492, "decode_str": "\ufffd"} -{"id": 34527, "token": "geries", "merges": "ger ies", "raw_count": 564, "count": 1493, "decode_str": "geries"} -{"id": 29292, "token": "\u0120penis", "merges": "\u0120pen is", "raw_count": 1493, "count": 1493, "decode_str": " penis"} -{"id": 21995, "token": "\u0120Sad", "merges": "\u0120S ad", "raw_count": 1104, "count": 1493, "decode_str": " Sad"} -{"id": 29876, "token": "\u0120Vic", "merges": "\u0120V ic", "raw_count": 1493, "count": 1493, "decode_str": " Vic"} -{"id": 43176, "token": "\u0120gripped", "merges": "\u0120gri pped", "raw_count": 1494, "count": 1494, "decode_str": " gripped"} -{"id": 46334, "token": "\u0120toutes", "merges": "\u0120tout es", "raw_count": 1494, "count": 1494, "decode_str": " toutes"} -{"id": 31786, "token": "\u0120famil", "merges": "\u0120fam il", "raw_count": 448, "count": 1494, "decode_str": " famil"} -{"id": 23789, "token": "\u0120Youth", "merges": "\u0120You th", "raw_count": 1494, "count": 1494, "decode_str": " Youth"} -{"id": 42731, "token": "ubunt", "merges": "ub unt", "raw_count": 1494, "count": 1494, "decode_str": "ubunt"} -{"id": 28978, "token": "\u0120diagnoses", "merges": "\u0120diagn oses", "raw_count": 1495, "count": 1495, "decode_str": " diagnoses"} -{"id": 46739, "token": "remia", "merges": "rem ia", "raw_count": 1495, "count": 1495, "decode_str": "remia"} -{"id": 38201, "token": "\u0120Weyl", "merges": "\u0120We yl", "raw_count": 1495, "count": 1495, "decode_str": " Weyl"} -{"id": 39251, "token": "\u00e0\u00b8\u00b4", "merges": "\u00e0\u00b8 \u00b4", "raw_count": 1495, "count": 1495, "decode_str": "\u0e34"} -{"id": 34593, "token": "\u0120persuasive", "merges": "\u0120persu asive", "raw_count": 1496, "count": 1496, "decode_str": " persuasive"} -{"id": 29655, "token": "\u0120Mull", "merges": "\u0120M ull", "raw_count": 1496, "count": 1496, "decode_str": " Mull"} -{"id": 25852, "token": "\u0120Lamb", "merges": "\u0120L amb", "raw_count": 1496, "count": 1496, "decode_str": " Lamb"} -{"id": 31640, "token": "\u0120robustness", "merges": "\u0120robust ness", "raw_count": 1497, "count": 1497, "decode_str": " robustness"} -{"id": 48256, "token": "crystalline", "merges": "crystall ine", "raw_count": 1497, "count": 1497, "decode_str": "crystalline"} -{"id": 24402, "token": "\u0120carot", "merges": "\u0120car ot", "raw_count": 754, "count": 1497, "decode_str": " carot"} -{"id": 43587, "token": "\u0120mejor", "merges": "\u0120me jor", "raw_count": 1497, "count": 1497, "decode_str": " mejor"} -{"id": 47304, "token": "\u0120Collections", "merges": "\u0120Col lections", "raw_count": 1498, "count": 1498, "decode_str": " Collections"} -{"id": 50217, "token": "\u0120relegated", "merges": "\u0120rele gated", "raw_count": 1498, "count": 1498, "decode_str": " relegated"} -{"id": 30429, "token": "\u0120cellulose", "merges": "\u0120cell ulose", "raw_count": 1498, "count": 1498, "decode_str": " cellulose"} -{"id": 47466, "token": "\u0120hinted", "merges": "\u0120hint ed", "raw_count": 1498, "count": 1498, "decode_str": " hinted"} -{"id": 43985, "token": "\u0120pleth", "merges": "\u0120ple th", "raw_count": 79, "count": 1498, "decode_str": " pleth"} -{"id": 11486, "token": "ARRANT", "merges": "ARR ANT", "raw_count": 1086, "count": 1498, "decode_str": "ARRANT"} -{"id": 45844, "token": "\u0120vara", "merges": "\u0120var a", "raw_count": 1498, "count": 1498, "decode_str": " vara"} -{"id": 35624, "token": "\u0120Resistance", "merges": "\u0120Res istance", "raw_count": 1500, "count": 1500, "decode_str": " Resistance"} -{"id": 25666, "token": "\u0120LIMITED", "merges": "\u0120LIM ITED", "raw_count": 1500, "count": 1500, "decode_str": " LIMITED"} -{"id": 48445, "token": "\u0120frown", "merges": "\u0120f rown", "raw_count": 1500, "count": 1500, "decode_str": " frown"} -{"id": 40924, "token": "\u0120exem", "merges": "\u0120ex em", "raw_count": 1500, "count": 1500, "decode_str": " exem"} -{"id": 25571, "token": "\u0120Riemann", "merges": "\u0120R iemann", "raw_count": 1138, "count": 1501, "decode_str": " Riemann"} -{"id": 31152, "token": "\u0120subpo", "merges": "\u0120sub po", "raw_count": 484, "count": 1501, "decode_str": " subpo"} -{"id": 46062, "token": "\u0120Means", "merges": "\u0120Me ans", "raw_count": 1501, "count": 1501, "decode_str": " Means"} -{"id": 25211, "token": "\u0120bowel", "merges": "\u0120bow el", "raw_count": 1501, "count": 1501, "decode_str": " bowel"} -{"id": 46185, "token": "\u0120Funds", "merges": "\u0120Fun ds", "raw_count": 1502, "count": 1502, "decode_str": " Funds"} -{"id": 49335, "token": "\u0120manic", "merges": "\u0120man ic", "raw_count": 1503, "count": 1503, "decode_str": " manic"} -{"id": 45828, "token": "\u0120Nil", "merges": "\u0120N il", "raw_count": 1503, "count": 1503, "decode_str": " Nil"} -{"id": 38095, "token": "\u00c3\u00b6l", "merges": "\u00c3\u00b6 l", "raw_count": 1503, "count": 1503, "decode_str": "\u00f6l"} -{"id": 41236, "token": "\u0120whiskey", "merges": "\u0120whis key", "raw_count": 1504, "count": 1504, "decode_str": " whiskey"} -{"id": 10035, "token": "\u0120Mike", "merges": "\u0120M ike", "raw_count": 1504, "count": 1504, "decode_str": " Mike"} -{"id": 48232, "token": "\u0120frig", "merges": "\u0120fr ig", "raw_count": 1504, "count": 1504, "decode_str": " frig"} -{"id": 47517, "token": "\u0120depressing", "merges": "\u0120dep ressing", "raw_count": 1505, "count": 1505, "decode_str": " depressing"} -{"id": 38981, "token": "\u0120parabolic", "merges": "\u0120par abolic", "raw_count": 1505, "count": 1505, "decode_str": " parabolic"} -{"id": 44907, "token": "\u0120Gaming", "merges": "\u0120G aming", "raw_count": 1505, "count": 1505, "decode_str": " Gaming"} -{"id": 39929, "token": "\u00c3\u00a9t\u00c3\u00a9", "merges": "\u00c3\u00a9t \u00c3\u00a9", "raw_count": 1505, "count": 1505, "decode_str": "\u00e9t\u00e9"} -{"id": 38338, "token": "Supplemental", "merges": "Supp lemental", "raw_count": 1506, "count": 1506, "decode_str": "Supplemental"} -{"id": 43235, "token": "\u0120seasoned", "merges": "\u0120season ed", "raw_count": 1506, "count": 1506, "decode_str": " seasoned"} -{"id": 16773, "token": "\u0120rape", "merges": "\u0120ra pe", "raw_count": 1506, "count": 1506, "decode_str": " rape"} -{"id": 49167, "token": "\u0120blinding", "merges": "\u0120bl inding", "raw_count": 1507, "count": 1507, "decode_str": " blinding"} -{"id": 31575, "token": "\u0120Champion", "merges": "\u0120Champ ion", "raw_count": 1507, "count": 1507, "decode_str": " Champion"} -{"id": 36188, "token": "\u0120qu\u00c3\u00a9", "merges": "\u0120qu \u00c3\u00a9", "raw_count": 1507, "count": 1507, "decode_str": " qu\u00e9"} -{"id": 22607, "token": "\u0120Wor", "merges": "\u0120W or", "raw_count": 1392, "count": 1507, "decode_str": " Wor"} -{"id": 47297, "token": "\u0120RAS", "merges": "\u0120R AS", "raw_count": 1507, "count": 1507, "decode_str": " RAS"} -{"id": 13295, "token": "\u0120Conserv", "merges": "\u0120Cons erv", "raw_count": 630, "count": 1508, "decode_str": " Conserv"} -{"id": 39214, "token": "\u0120punched", "merges": "\u0120pun ched", "raw_count": 1508, "count": 1508, "decode_str": " punched"} -{"id": 47683, "token": "\u0120famed", "merges": "\u0120fam ed", "raw_count": 1508, "count": 1508, "decode_str": " famed"} -{"id": 31100, "token": "\u0120CBD", "merges": "\u0120C BD", "raw_count": 1508, "count": 1508, "decode_str": " CBD"} -{"id": 42588, "token": "\u0120methamphetamine", "merges": "\u0120meth amphetamine", "raw_count": 1509, "count": 1509, "decode_str": " methamphetamine"} -{"id": 45115, "token": "\u0120dehydration", "merges": "\u0120de hydration", "raw_count": 1509, "count": 1509, "decode_str": " dehydration"} -{"id": 38182, "token": "\u0120Factors", "merges": "\u0120Fact ors", "raw_count": 1509, "count": 1509, "decode_str": " Factors"} -{"id": 30729, "token": "\u00e1\u0125\u013a", "merges": "\u00e1\u0125 \u013a", "raw_count": 630, "count": 1509, "decode_str": "\u10d8"} -{"id": 16446, "token": "$;", "merges": "$ ;", "raw_count": 1509, "count": 1509, "decode_str": "$;"} -{"id": 23212, "token": "\u0120Metro", "merges": "\u0120Met ro", "raw_count": 1510, "count": 1510, "decode_str": " Metro"} -{"id": 46324, "token": "\u0120scoop", "merges": "\u0120sc oop", "raw_count": 1510, "count": 1510, "decode_str": " scoop"} -{"id": 37836, "token": "\u0120stabbed", "merges": "\u0120stab bed", "raw_count": 1511, "count": 1511, "decode_str": " stabbed"} -{"id": 38420, "token": "\u0120amusing", "merges": "\u0120am using", "raw_count": 1511, "count": 1511, "decode_str": " amusing"} -{"id": 21622, "token": "it\u00c3\u0142", "merges": "it \u00c3\u0142", "raw_count": 1511, "count": 1511, "decode_str": "it\u00e0"} -{"id": 43260, "token": "\u00e0\u00b8\u00ab", "merges": "\u00e0\u00b8 \u00ab", "raw_count": 1511, "count": 1511, "decode_str": "\u0e2b"} -{"id": 50214, "token": "\u0120Aircraft", "merges": "\u0120A ircraft", "raw_count": 1512, "count": 1512, "decode_str": " Aircraft"} -{"id": 43981, "token": "\u0120tending", "merges": "\u0120t ending", "raw_count": 1512, "count": 1512, "decode_str": " tending"} -{"id": 43593, "token": "\u0120THREE", "merges": "\u0120TH REE", "raw_count": 1512, "count": 1512, "decode_str": " THREE"} -{"id": 3303, "token": "}$,", "merges": "}$ ,", "raw_count": 1446, "count": 1512, "decode_str": "}$,"} -{"id": 47330, "token": "\u0120thrilling", "merges": "\u0120thr illing", "raw_count": 1513, "count": 1513, "decode_str": " thrilling"} -{"id": 35166, "token": "\u0120Serve", "merges": "\u0120S erve", "raw_count": 1513, "count": 1513, "decode_str": " Serve"} -{"id": 38355, "token": "\u0120outrageous", "merges": "\u0120outrage ous", "raw_count": 1514, "count": 1514, "decode_str": " outrageous"} -{"id": 38871, "token": "\u0120curled", "merges": "\u0120cur led", "raw_count": 1514, "count": 1514, "decode_str": " curled"} -{"id": 44992, "token": "\u0120sacks", "merges": "\u0120s acks", "raw_count": 1514, "count": 1514, "decode_str": " sacks"} -{"id": 39461, "token": "j\u00c3\u0142", "merges": "j \u00c3\u0142", "raw_count": 157, "count": 1514, "decode_str": "j\u00e0"} -{"id": 43154, "token": "\u0120dislocation", "merges": "\u0120dis location", "raw_count": 1515, "count": 1515, "decode_str": " dislocation"} -{"id": 47955, "token": "\u0120mystical", "merges": "\u0120myst ical", "raw_count": 1515, "count": 1515, "decode_str": " mystical"} -{"id": 48972, "token": "\u0120cooks", "merges": "\u0120cook s", "raw_count": 1515, "count": 1515, "decode_str": " cooks"} -{"id": 21057, "token": "\u0120irradiation", "merges": "\u0120irrad iation", "raw_count": 1516, "count": 1516, "decode_str": " irradiation"} -{"id": 46821, "token": "inities", "merges": "in ities", "raw_count": 1516, "count": 1516, "decode_str": "inities"} -{"id": 50315, "token": "\u00e2\u012a\u0137", "merges": "\u00e2\u012a \u0137", "raw_count": 1516, "count": 1516, "decode_str": "\u2215"} -{"id": 50287, "token": "\u00cb\u0132", "merges": "\u00cb \u0132", "raw_count": 1516, "count": 1516, "decode_str": "\u02d0"} -{"id": 3918, "token": "\u0120President", "merges": "\u0120Pres ident", "raw_count": 1228, "count": 1517, "decode_str": " President"} -{"id": 42708, "token": "\u0120casually", "merges": "\u0120cas ually", "raw_count": 1517, "count": 1517, "decode_str": " casually"} -{"id": 35509, "token": "substituted", "merges": "sub stituted", "raw_count": 1518, "count": 1518, "decode_str": "substituted"} -{"id": 42497, "token": "\u0120Musk", "merges": "\u0120Mus k", "raw_count": 1518, "count": 1518, "decode_str": " Musk"} -{"id": 47425, "token": "\u0120sweating", "merges": "\u0120swe ating", "raw_count": 1519, "count": 1519, "decode_str": " sweating"} -{"id": 50136, "token": "\u0120traitor", "merges": "\u0120tra itor", "raw_count": 1520, "count": 1520, "decode_str": " traitor"} -{"id": 27848, "token": "\u0120Airl", "merges": "\u0120A irl", "raw_count": 156, "count": 1520, "decode_str": " Airl"} -{"id": 44970, "token": "\u0120noct", "merges": "\u0120no ct", "raw_count": 1520, "count": 1520, "decode_str": " noct"} -{"id": 45286, "token": "\u0120impregn", "merges": "\u0120imp regn", "raw_count": 1521, "count": 1521, "decode_str": " impregn"} -{"id": 30091, "token": "\u0120mening", "merges": "\u0120men ing", "raw_count": 1521, "count": 1521, "decode_str": " mening"} -{"id": 26048, "token": "\u0120Sweet", "merges": "\u0120S weet", "raw_count": 1521, "count": 1521, "decode_str": " Sweet"} -{"id": 9253, "token": "\u0120supra", "merges": "\u0120sup ra", "raw_count": 1521, "count": 1521, "decode_str": " supra"} -{"id": 46740, "token": "\u0120gallon", "merges": "\u0120gall on", "raw_count": 1522, "count": 1522, "decode_str": " gallon"} -{"id": 49125, "token": "\u0120Heter", "merges": "\u0120H eter", "raw_count": 1522, "count": 1522, "decode_str": " Heter"} -{"id": 46768, "token": "'\">", "merges": "' \">", "raw_count": 1522, "count": 1522, "decode_str": "'\">"} -{"id": 20316, "token": "\u0120Environmental", "merges": "\u0120Environment al", "raw_count": 1523, "count": 1523, "decode_str": " Environmental"} -{"id": 46203, "token": "\u0120dwarfs", "merges": "\u0120dwar fs", "raw_count": 1523, "count": 1523, "decode_str": " dwarfs"} -{"id": 47170, "token": "\u00c6\u00a1", "merges": "\u00c6 \u00a1", "raw_count": 1523, "count": 1523, "decode_str": "\u01a1"} -{"id": 45666, "token": "\u0120simplicial", "merges": "\u0120sim plicial", "raw_count": 1524, "count": 1524, "decode_str": " simplicial"} -{"id": 36307, "token": "\u0120noticing", "merges": "\u0120not icing", "raw_count": 1524, "count": 1524, "decode_str": " noticing"} -{"id": 26051, "token": "YRIGHT", "merges": "YR IGHT", "raw_count": 1266, "count": 1524, "decode_str": "YRIGHT"} -{"id": 29747, "token": "\u0120concomitant", "merges": "\u0120concomit ant", "raw_count": 1526, "count": 1526, "decode_str": " concomitant"} -{"id": 45036, "token": "\u0120capacitors", "merges": "\u0120capac itors", "raw_count": 1526, "count": 1526, "decode_str": " capacitors"} -{"id": 20757, "token": "\u0120Turner", "merges": "\u0120Turn er", "raw_count": 1526, "count": 1526, "decode_str": " Turner"} -{"id": 47257, "token": "fluoro", "merges": "flu oro", "raw_count": 1526, "count": 1526, "decode_str": "fluoro"} -{"id": 42031, "token": "Rather", "merges": "R ather", "raw_count": 1526, "count": 1526, "decode_str": "Rather"} -{"id": 37742, "token": "\u0120respiration", "merges": "\u0120resp iration", "raw_count": 1527, "count": 1527, "decode_str": " respiration"} -{"id": 20923, "token": "\u0120Stanley", "merges": "\u0120Stan ley", "raw_count": 1527, "count": 1527, "decode_str": " Stanley"} -{"id": 15594, "token": "\u0120Sure", "merges": "\u0120S ure", "raw_count": 1435, "count": 1527, "decode_str": " Sure"} -{"id": 22004, "token": "\u0120\\*\\*", "merges": "\u0120\\* \\*", "raw_count": 1527, "count": 1527, "decode_str": " \\*\\*"} -{"id": 50247, "token": "itons", "merges": "it ons", "raw_count": 1527, "count": 1527, "decode_str": "itons"} -{"id": 29675, "token": "omorphisms", "merges": "omorph isms", "raw_count": 1528, "count": 1528, "decode_str": "omorphisms"} -{"id": 46129, "token": "\u0120crystallization", "merges": "\u0120crystall ization", "raw_count": 1529, "count": 1529, "decode_str": " crystallization"} -{"id": 40691, "token": "terminus", "merges": "ter minus", "raw_count": 1529, "count": 1529, "decode_str": "terminus"} -{"id": 41905, "token": "\u0120\u00d0\u0135", "merges": "\u0120\u00d0 \u0135", "raw_count": 1529, "count": 1529, "decode_str": " \u0413"} -{"id": 25267, "token": "\u0120reagents", "merges": "\u0120re agents", "raw_count": 1530, "count": 1530, "decode_str": " reagents"} -{"id": 45963, "token": "\u0120identically", "merges": "\u0120ident ically", "raw_count": 1531, "count": 1531, "decode_str": " identically"} -{"id": 27878, "token": "\u0120Academic", "merges": "\u0120Academ ic", "raw_count": 1531, "count": 1531, "decode_str": " Academic"} -{"id": 43714, "token": "\u0120Cheese", "merges": "\u0120Che ese", "raw_count": 1531, "count": 1531, "decode_str": " Cheese"} -{"id": 45647, "token": "opedic", "merges": "oped ic", "raw_count": 1531, "count": 1531, "decode_str": "opedic"} -{"id": 46095, "token": "\u0120Ming", "merges": "\u0120M ing", "raw_count": 1531, "count": 1531, "decode_str": " Ming"} -{"id": 37002, "token": "\u0120seedlings", "merges": "\u0120seed lings", "raw_count": 1532, "count": 1532, "decode_str": " seedlings"} -{"id": 39972, "token": "imester", "merges": "imes ter", "raw_count": 832, "count": 1532, "decode_str": "imester"} -{"id": 41602, "token": "ulfide", "merges": "ulf ide", "raw_count": 1132, "count": 1532, "decode_str": "ulfide"} -{"id": 20192, "token": "\u0120pathogen", "merges": "\u0120path ogen", "raw_count": 1533, "count": 1533, "decode_str": " pathogen"} -{"id": 46211, "token": "Verlag", "merges": "Ver lag", "raw_count": 1534, "count": 1534, "decode_str": "Verlag"} -{"id": 47798, "token": "enties", "merges": "ent ies", "raw_count": 1534, "count": 1534, "decode_str": "enties"} -{"id": 50008, "token": "\u0120ranc", "merges": "\u0120r anc", "raw_count": 1534, "count": 1534, "decode_str": " ranc"} -{"id": 39928, "token": "\u0120psychic", "merges": "\u0120psych ic", "raw_count": 1535, "count": 1535, "decode_str": " psychic"} -{"id": 34816, "token": "\u00e0\u00b8\u00a2", "merges": "\u00e0\u00b8 \u00a2", "raw_count": 1535, "count": 1535, "decode_str": "\u0e22"} -{"id": 36052, "token": "\u0120Conduct", "merges": "\u0120Con duct", "raw_count": 1536, "count": 1536, "decode_str": " Conduct"} -{"id": 41721, "token": "\u0120Tier", "merges": "\u0120T ier", "raw_count": 1536, "count": 1536, "decode_str": " Tier"} -{"id": 33806, "token": "\u00c3\u0143c", "merges": "\u00c3\u0143 c", "raw_count": 1536, "count": 1536, "decode_str": "\u00edc"} -{"id": 19281, "token": "\u00c2\u00b3", "merges": "\u00c2 \u00b3", "raw_count": 1536, "count": 1536, "decode_str": "\u00b3"} -{"id": 43070, "token": "acrylate", "merges": "acry late", "raw_count": 1537, "count": 1537, "decode_str": "acrylate"} -{"id": 42188, "token": "ophan", "merges": "oph an", "raw_count": 1537, "count": 1537, "decode_str": "ophan"} -{"id": 40886, "token": "\u0120concave", "merges": "\u0120conc ave", "raw_count": 1538, "count": 1538, "decode_str": " concave"} -{"id": 31833, "token": "\u0120damned", "merges": "\u0120dam ned", "raw_count": 1538, "count": 1538, "decode_str": " damned"} -{"id": 31698, "token": "\u00e3\u0123\u0135\u00e3\u0123\u00ae", "merges": "\u00e3\u0123\u0135 \u00e3\u0123\u00ae", "raw_count": 1538, "count": 1538, "decode_str": "\u3053\u306e"} -{"id": 36613, "token": "brates", "merges": "br ates", "raw_count": 1539, "count": 1539, "decode_str": "brates"} -{"id": 40981, "token": "\u0120drap", "merges": "\u0120d rap", "raw_count": 1539, "count": 1539, "decode_str": " drap"} -{"id": 45469, "token": "\u0120Hip", "merges": "\u0120H ip", "raw_count": 1539, "count": 1539, "decode_str": " Hip"} -{"id": 42593, "token": "\u0120Clifford", "merges": "\u0120Cliff ord", "raw_count": 1540, "count": 1540, "decode_str": " Clifford"} -{"id": 34565, "token": "\u0120Evil", "merges": "\u0120Ev il", "raw_count": 1540, "count": 1540, "decode_str": " Evil"} -{"id": 35734, "token": "\u0120IMF", "merges": "\u0120IM F", "raw_count": 1540, "count": 1540, "decode_str": " IMF"} -{"id": 31793, "token": "\u0120regularity", "merges": "\u0120regular ity", "raw_count": 1541, "count": 1541, "decode_str": " regularity"} -{"id": 37511, "token": "\u0120Friedrich", "merges": "\u0120Fried rich", "raw_count": 1541, "count": 1541, "decode_str": " Friedrich"} -{"id": 31975, "token": "stained", "merges": "st ained", "raw_count": 1541, "count": 1541, "decode_str": "stained"} -{"id": 37855, "token": "partum", "merges": "part um", "raw_count": 908, "count": 1541, "decode_str": "partum"} -{"id": 48233, "token": "\u0120bully", "merges": "\u0120bul ly", "raw_count": 1541, "count": 1541, "decode_str": " bully"} -{"id": 50149, "token": "\u0120tamp", "merges": "\u0120t amp", "raw_count": 1541, "count": 1541, "decode_str": " tamp"} -{"id": 18300, "token": "\u0120Statistical", "merges": "\u0120Stat istical", "raw_count": 1542, "count": 1542, "decode_str": " Statistical"} -{"id": 40963, "token": "\u0120cosa", "merges": "\u0120c osa", "raw_count": 1542, "count": 1542, "decode_str": " cosa"} -{"id": 15904, "token": "\u0120Bureau", "merges": "\u0120B ureau", "raw_count": 1543, "count": 1543, "decode_str": " Bureau"} -{"id": 13114, "token": "\u0120Ryan", "merges": "\u0120R yan", "raw_count": 1543, "count": 1543, "decode_str": " Ryan"} -{"id": 29550, "token": "\u0120frowned", "merges": "\u0120f rowned", "raw_count": 1544, "count": 1544, "decode_str": " frowned"} -{"id": 49654, "token": "\u0120doubtless", "merges": "\u0120doubt less", "raw_count": 1545, "count": 1545, "decode_str": " doubtless"} -{"id": 41568, "token": "ionine", "merges": "ion ine", "raw_count": 1545, "count": 1545, "decode_str": "ionine"} -{"id": 22707, "token": "\u0120Lisa", "merges": "\u0120L isa", "raw_count": 1545, "count": 1545, "decode_str": " Lisa"} -{"id": 36619, "token": "\u0120Beer", "merges": "\u0120Be er", "raw_count": 1545, "count": 1545, "decode_str": " Beer"} -{"id": 41511, "token": "%%%%%%%%%%%%%%%%", "merges": "%%%%%%%% %%%%%%%%", "raw_count": 1546, "count": 1546, "decode_str": "%%%%%%%%%%%%%%%%"} -{"id": 41805, "token": "\u0120Effective", "merges": "\u0120Effect ive", "raw_count": 1546, "count": 1546, "decode_str": " Effective"} -{"id": 44116, "token": "\u0120Cheng", "merges": "\u0120Chen g", "raw_count": 1546, "count": 1546, "decode_str": " Cheng"} -{"id": 33218, "token": "\u0120prejudicial", "merges": "\u0120prejud icial", "raw_count": 1547, "count": 1547, "decode_str": " prejudicial"} -{"id": 49898, "token": "\u0120spines", "merges": "\u0120sp ines", "raw_count": 1547, "count": 1547, "decode_str": " spines"} -{"id": 36923, "token": "\u0120Marshal", "merges": "\u0120Mars hal", "raw_count": 1548, "count": 1548, "decode_str": " Marshal"} -{"id": 32069, "token": "\u0120Pav", "merges": "\u0120P av", "raw_count": 1548, "count": 1548, "decode_str": " Pav"} -{"id": 28608, "token": "\u0120Cer", "merges": "\u0120C er", "raw_count": 1548, "count": 1548, "decode_str": " Cer"} -{"id": 35008, "token": "\u0120mechanically", "merges": "\u0120mechan ically", "raw_count": 1549, "count": 1549, "decode_str": " mechanically"} -{"id": 45620, "token": "\u0120tenderness", "merges": "\u0120tender ness", "raw_count": 1549, "count": 1549, "decode_str": " tenderness"} -{"id": 49888, "token": "doctoral", "merges": "doctor al", "raw_count": 1549, "count": 1549, "decode_str": "doctoral"} -{"id": 32420, "token": "\u0120tucked", "merges": "\u0120t ucked", "raw_count": 1549, "count": 1549, "decode_str": " tucked"} -{"id": 42345, "token": "\u0120skinny", "merges": "\u0120sk inny", "raw_count": 1549, "count": 1549, "decode_str": " skinny"} -{"id": 43974, "token": "\u0120Fruit", "merges": "\u0120F ruit", "raw_count": 1549, "count": 1549, "decode_str": " Fruit"} -{"id": 39787, "token": "\u0120gasped", "merges": "\u0120gas ped", "raw_count": 1550, "count": 1550, "decode_str": " gasped"} -{"id": 38889, "token": "\u00c3\u00a9ment", "merges": "\u00c3\u00a9 ment", "raw_count": 1550, "count": 1550, "decode_str": "\u00e9ment"} -{"id": 44412, "token": "\u0120rumor", "merges": "\u0120rum or", "raw_count": 1550, "count": 1550, "decode_str": " rumor"} -{"id": 37563, "token": "\u0120autopsy", "merges": "\u0120aut opsy", "raw_count": 1551, "count": 1551, "decode_str": " autopsy"} -{"id": 11934, "token": "\u0120malign", "merges": "\u0120mal ign", "raw_count": 565, "count": 1551, "decode_str": " malign"} -{"id": 17673, "token": "$),", "merges": "$ ),", "raw_count": 1551, "count": 1551, "decode_str": "$),"} -{"id": 19295, "token": "\u0120SOFTWARE", "merges": "\u0120SO FTWARE", "raw_count": 1552, "count": 1552, "decode_str": " SOFTWARE"} -{"id": 37178, "token": "\u0120gelatin", "merges": "\u0120gel atin", "raw_count": 1552, "count": 1552, "decode_str": " gelatin"} -{"id": 31345, "token": "\u0120lumbar", "merges": "\u0120lum bar", "raw_count": 1552, "count": 1552, "decode_str": " lumbar"} -{"id": 40681, "token": "otoxic", "merges": "otox ic", "raw_count": 1552, "count": 1552, "decode_str": "otoxic"} -{"id": 12300, "token": "\u0120Rome", "merges": "\u0120R ome", "raw_count": 1552, "count": 1552, "decode_str": " Rome"} -{"id": 19173, "token": "\u0120Eli", "merges": "\u0120E li", "raw_count": 937, "count": 1553, "decode_str": " Eli"} -{"id": 26926, "token": "\u0120\u00c3\u00a9l", "merges": "\u0120\u00c3\u00a9 l", "raw_count": 1553, "count": 1553, "decode_str": " \u00e9l"} -{"id": 35309, "token": "\u0120Gad", "merges": "\u0120G ad", "raw_count": 1553, "count": 1553, "decode_str": " Gad"} -{"id": 44888, "token": "\u0120924", "merges": "\u01209 24", "raw_count": 1553, "count": 1553, "decode_str": " 924"} -{"id": 37268, "token": "\u0120Dear", "merges": "\u0120D ear", "raw_count": 1554, "count": 1554, "decode_str": " Dear"} -{"id": 48518, "token": "\u0120loaf", "merges": "\u0120lo af", "raw_count": 1554, "count": 1554, "decode_str": " loaf"} -{"id": 33588, "token": "\u0120piez", "merges": "\u0120pie z", "raw_count": 644, "count": 1555, "decode_str": " piez"} -{"id": 6476, "token": "\\!", "merges": "\\ !", "raw_count": 1149, "count": 1555, "decode_str": "\\!"} -{"id": 41626, "token": "\u0120stipulation", "merges": "\u0120stip ulation", "raw_count": 1556, "count": 1556, "decode_str": " stipulation"} -{"id": 4935, "token": "}}(", "merges": "}} (", "raw_count": 1555, "count": 1556, "decode_str": "}}("} -{"id": 33962, "token": "\u0120Soci", "merges": "\u0120S oci", "raw_count": 1557, "count": 1557, "decode_str": " Soci"} -{"id": 17012, "token": "\u0120Treatment", "merges": "\u0120T reatment", "raw_count": 1558, "count": 1558, "decode_str": " Treatment"} -{"id": 43170, "token": "\u0120lettuce", "merges": "\u0120lett uce", "raw_count": 1558, "count": 1558, "decode_str": " lettuce"} -{"id": 49329, "token": "\u0120Spons", "merges": "\u0120Sp ons", "raw_count": 1558, "count": 1558, "decode_str": " Spons"} -{"id": 24756, "token": "\u0120Hob", "merges": "\u0120H ob", "raw_count": 1558, "count": 1558, "decode_str": " Hob"} -{"id": 8293, "token": "\u0120Justice", "merges": "\u0120Just ice", "raw_count": 1559, "count": 1559, "decode_str": " Justice"} -{"id": 43219, "token": "\u0120rocking", "merges": "\u0120rock ing", "raw_count": 1559, "count": 1559, "decode_str": " rocking"} -{"id": 39565, "token": "\u0120fungus", "merges": "\u0120fun gus", "raw_count": 1559, "count": 1559, "decode_str": " fungus"} -{"id": 29108, "token": "\u0120glands", "merges": "\u0120gl ands", "raw_count": 1559, "count": 1559, "decode_str": " glands"} -{"id": 16993, "token": "queous", "merges": "que ous", "raw_count": 375, "count": 1559, "decode_str": "queous"} -{"id": 24369, "token": "\u0120Coul", "merges": "\u0120C oul", "raw_count": 424, "count": 1559, "decode_str": " Coul"} -{"id": 42185, "token": "\u0120sei", "merges": "\u0120se i", "raw_count": 1559, "count": 1559, "decode_str": " sei"} -{"id": 20118, "token": "\u0120antioxidant", "merges": "\u0120antioxid ant", "raw_count": 1560, "count": 1560, "decode_str": " antioxidant"} -{"id": 28762, "token": "\u0120pleadings", "merges": "\u0120plead ings", "raw_count": 1560, "count": 1560, "decode_str": " pleadings"} -{"id": 47378, "token": "\u0120ejected", "merges": "\u0120e jected", "raw_count": 1560, "count": 1560, "decode_str": " ejected"} -{"id": 28436, "token": "\u0120Bring", "merges": "\u0120B ring", "raw_count": 1560, "count": 1560, "decode_str": " Bring"} -{"id": 36962, "token": "\u0120superhero", "merges": "\u0120super hero", "raw_count": 1561, "count": 1561, "decode_str": " superhero"} -{"id": 36322, "token": "\u0120Resort", "merges": "\u0120Res ort", "raw_count": 1561, "count": 1561, "decode_str": " Resort"} -{"id": 21797, "token": "rosine", "merges": "ros ine", "raw_count": 1256, "count": 1561, "decode_str": "rosine"} -{"id": 41542, "token": "\u0120gigg", "merges": "\u0120gig g", "raw_count": 1561, "count": 1561, "decode_str": " gigg"} -{"id": 30825, "token": "\u0120carbohydrate", "merges": "\u0120carboh ydrate", "raw_count": 1562, "count": 1562, "decode_str": " carbohydrate"} -{"id": 33200, "token": "rivol", "merges": "riv ol", "raw_count": 296, "count": 1562, "decode_str": "rivol"} -{"id": 32207, "token": "\u0120ICC", "merges": "\u0120I CC", "raw_count": 1562, "count": 1562, "decode_str": " ICC"} -{"id": 4596, "token": "\u0120November", "merges": "\u0120N ovember", "raw_count": 1563, "count": 1563, "decode_str": " November"} -{"id": 24351, "token": "\u0120bronch", "merges": "\u0120bron ch", "raw_count": 1054, "count": 1563, "decode_str": " bronch"} -{"id": 40394, "token": "\u0120Workshop", "merges": "\u0120Works hop", "raw_count": 1564, "count": 1564, "decode_str": " Workshop"} -{"id": 39784, "token": "\u0120TeV", "merges": "\u0120Te V", "raw_count": 1564, "count": 1564, "decode_str": " TeV"} -{"id": 46060, "token": "\u0120purpos", "merges": "\u0120pur pos", "raw_count": 1565, "count": 1565, "decode_str": " purpos"} -{"id": 38285, "token": "entary", "merges": "ent ary", "raw_count": 623, "count": 1565, "decode_str": "entary"} -{"id": 21832, "token": "\u0120Trail", "merges": "\u0120Tra il", "raw_count": 1565, "count": 1565, "decode_str": " Trail"} -{"id": 36197, "token": "\u00c3\u00a9mon", "merges": "\u00c3\u00a9 mon", "raw_count": 889, "count": 1565, "decode_str": "\u00e9mon"} -{"id": 25400, "token": "ophila", "merges": "oph ila", "raw_count": 982, "count": 1566, "decode_str": "ophila"} -{"id": 21088, "token": "\u0120Marie", "merges": "\u0120Mar ie", "raw_count": 1566, "count": 1566, "decode_str": " Marie"} -{"id": 31121, "token": "\u0120Mong", "merges": "\u0120M ong", "raw_count": 1566, "count": 1566, "decode_str": " Mong"} -{"id": 8454, "token": "\u0120_{", "merges": "\u0120 _{", "raw_count": 1566, "count": 1566, "decode_str": " _{"} -{"id": 45942, "token": "\u0120chilling", "merges": "\u0120ch illing", "raw_count": 1567, "count": 1567, "decode_str": " chilling"} -{"id": 9693, "token": "\u0120Boston", "merges": "\u0120B oston", "raw_count": 1567, "count": 1567, "decode_str": " Boston"} -{"id": 10142, "token": "\u0120inflammatory", "merges": "\u0120infl ammatory", "raw_count": 1568, "count": 1568, "decode_str": " inflammatory"} -{"id": 36199, "token": "\u0120resemblance", "merges": "\u0120resem blance", "raw_count": 1568, "count": 1568, "decode_str": " resemblance"} -{"id": 27000, "token": "\u0120mellitus", "merges": "\u0120mell itus", "raw_count": 1568, "count": 1568, "decode_str": " mellitus"} -{"id": 32489, "token": "\u0120drawback", "merges": "\u0120draw back", "raw_count": 1568, "count": 1568, "decode_str": " drawback"} -{"id": 20399, "token": "\u0120hydroly", "merges": "\u0120hydro ly", "raw_count": 690, "count": 1568, "decode_str": " hydroly"} -{"id": 47145, "token": "\u0120docket", "merges": "\u0120d ocket", "raw_count": 1569, "count": 1569, "decode_str": " docket"} -{"id": 44458, "token": "dling", "merges": "d ling", "raw_count": 1569, "count": 1569, "decode_str": "dling"} -{"id": 31419, "token": "\u0120Mik", "merges": "\u0120M ik", "raw_count": 1569, "count": 1569, "decode_str": " Mik"} -{"id": 33746, "token": "\u0120Gust", "merges": "\u0120G ust", "raw_count": 1570, "count": 1570, "decode_str": " Gust"} -{"id": 42116, "token": "\u0120quin", "merges": "\u0120qu in", "raw_count": 1570, "count": 1570, "decode_str": " quin"} -{"id": 47787, "token": "interacting", "merges": "inter acting", "raw_count": 1571, "count": 1571, "decode_str": "interacting"} -{"id": 35192, "token": "\u0120elicit", "merges": "\u0120el icit", "raw_count": 1571, "count": 1571, "decode_str": " elicit"} -{"id": 27437, "token": "\u0120sein", "merges": "\u0120se in", "raw_count": 1571, "count": 1571, "decode_str": " sein"} -{"id": 43715, "token": "\u00c3\u00bct", "merges": "\u00c3\u00bc t", "raw_count": 1571, "count": 1571, "decode_str": "\u00fct"} -{"id": 32079, "token": "\u0120Industries", "merges": "\u0120Indust ries", "raw_count": 1572, "count": 1572, "decode_str": " Industries"} -{"id": 49195, "token": "\u0120amphib", "merges": "\u0120amph ib", "raw_count": 1572, "count": 1572, "decode_str": " amphib"} -{"id": 47739, "token": "\u0120Grow", "merges": "\u0120G row", "raw_count": 1572, "count": 1572, "decode_str": " Grow"} -{"id": 45113, "token": "\u0120comforting", "merges": "\u0120comfort ing", "raw_count": 1573, "count": 1573, "decode_str": " comforting"} -{"id": 46754, "token": "\u0120bouncing", "merges": "\u0120b ouncing", "raw_count": 1573, "count": 1573, "decode_str": " bouncing"} -{"id": 39975, "token": "\u0120insufficiency", "merges": "\u0120insu fficiency", "raw_count": 1574, "count": 1574, "decode_str": " insufficiency"} -{"id": 37871, "token": "\u0120twisting", "merges": "\u0120tw isting", "raw_count": 1574, "count": 1574, "decode_str": " twisting"} -{"id": 47214, "token": "\u0120hunted", "merges": "\u0120h unted", "raw_count": 1574, "count": 1574, "decode_str": " hunted"} -{"id": 45793, "token": "\u0120cleft", "merges": "\u0120c left", "raw_count": 1574, "count": 1574, "decode_str": " cleft"} -{"id": 42391, "token": "\u0120alkali", "merges": "\u0120alk ali", "raw_count": 1575, "count": 1575, "decode_str": " alkali"} -{"id": 37322, "token": ">).", "merges": "> ).", "raw_count": 1575, "count": 1575, "decode_str": ">)."} -{"id": 30972, "token": "\u0120Shen", "merges": "\u0120S hen", "raw_count": 1576, "count": 1576, "decode_str": " Shen"} -{"id": 43257, "token": "\u0120unfavorable", "merges": "\u0120unf avorable", "raw_count": 1577, "count": 1577, "decode_str": " unfavorable"} -{"id": 21003, "token": "\u0120Einstein", "merges": "\u0120E instein", "raw_count": 1577, "count": 1577, "decode_str": " Einstein"} -{"id": 31841, "token": "\">&", "merges": "\"> &", "raw_count": 1577, "count": 1577, "decode_str": "\">&"} -{"id": 35345, "token": "\u0120Nucle", "merges": "\u0120N ucle", "raw_count": 1578, "count": 1578, "decode_str": " Nucle"} -{"id": 42417, "token": "\u0120undercover", "merges": "\u0120under cover", "raw_count": 1579, "count": 1579, "decode_str": " undercover"} -{"id": 29799, "token": "\u0120encore", "merges": "\u0120enc ore", "raw_count": 1579, "count": 1579, "decode_str": " encore"} -{"id": 21925, "token": "\u0120Pant", "merges": "\u0120P ant", "raw_count": 1533, "count": 1579, "decode_str": " Pant"} -{"id": 18773, "token": "\u0120Yan", "merges": "\u0120Y an", "raw_count": 1498, "count": 1579, "decode_str": " Yan"} -{"id": 11218, "token": "\u0120Championship", "merges": "\u0120Ch ampionship", "raw_count": 1201, "count": 1580, "decode_str": " Championship"} -{"id": 19789, "token": "\u0120metabolites", "merges": "\u0120metabol ites", "raw_count": 1580, "count": 1580, "decode_str": " metabolites"} -{"id": 18746, "token": "\u0120STATES", "merges": "\u0120STAT ES", "raw_count": 1580, "count": 1580, "decode_str": " STATES"} -{"id": 42437, "token": "ructose", "merges": "ruct ose", "raw_count": 1580, "count": 1580, "decode_str": "ructose"} -{"id": 46531, "token": "\u0120cavern", "merges": "\u0120ca vern", "raw_count": 1580, "count": 1580, "decode_str": " cavern"} -{"id": 46233, "token": "\u00c4\u0133", "merges": "\u00c4 \u0133", "raw_count": 1580, "count": 1580, "decode_str": "\u0111"} -{"id": 22695, "token": "\u0120Commons", "merges": "\u0120Comm ons", "raw_count": 1581, "count": 1581, "decode_str": " Commons"} -{"id": 40467, "token": "elij", "merges": "el ij", "raw_count": 1581, "count": 1581, "decode_str": "elij"} -{"id": 21174, "token": "\u0120Kam", "merges": "\u0120K am", "raw_count": 1581, "count": 1581, "decode_str": " Kam"} -{"id": 34646, "token": "\u0120Than", "merges": "\u0120Th an", "raw_count": 1582, "count": 1582, "decode_str": " Than"} -{"id": 36256, "token": "\u0120catastrophic", "merges": "\u0120catast rophic", "raw_count": 1583, "count": 1583, "decode_str": " catastrophic"} -{"id": 43859, "token": "\u0120Sheets", "merges": "\u0120She ets", "raw_count": 1583, "count": 1583, "decode_str": " Sheets"} -{"id": 24999, "token": "\u0120Shaw", "merges": "\u0120Sh aw", "raw_count": 1583, "count": 1583, "decode_str": " Shaw"} -{"id": 20358, "token": "\u0120Tob", "merges": "\u0120T ob", "raw_count": 1317, "count": 1583, "decode_str": " Tob"} -{"id": 37472, "token": "\u0120h\u00c3\u00a1", "merges": "\u0120h \u00c3\u00a1", "raw_count": 1583, "count": 1583, "decode_str": " h\u00e1"} -{"id": 40704, "token": "\u0120hugely", "merges": "\u0120hug ely", "raw_count": 1584, "count": 1584, "decode_str": " hugely"} -{"id": 45654, "token": "\u0120intrinsically", "merges": "\u0120intrins ically", "raw_count": 1585, "count": 1585, "decode_str": " intrinsically"} -{"id": 29836, "token": "conviction", "merges": "conv iction", "raw_count": 1585, "count": 1585, "decode_str": "conviction"} -{"id": 34796, "token": "\u0120aerobic", "merges": "\u0120aer obic", "raw_count": 1585, "count": 1585, "decode_str": " aerobic"} -{"id": 38102, "token": "\u0120Bean", "merges": "\u0120Be an", "raw_count": 1585, "count": 1585, "decode_str": " Bean"} -{"id": 35218, "token": "\u0120Dob", "merges": "\u0120D ob", "raw_count": 1585, "count": 1585, "decode_str": " Dob"} -{"id": 26749, "token": "\u0120renormal", "merges": "\u0120ren ormal", "raw_count": 1264, "count": 1586, "decode_str": " renormal"} -{"id": 24136, "token": "\u0120Workers", "merges": "\u0120Work ers", "raw_count": 1586, "count": 1586, "decode_str": " Workers"} -{"id": 36866, "token": "\u0120fetus", "merges": "\u0120fet us", "raw_count": 1586, "count": 1586, "decode_str": " fetus"} -{"id": 49755, "token": "=${", "merges": "= ${", "raw_count": 1586, "count": 1586, "decode_str": "=${"} -{"id": 23983, "token": "\u0120?>", "merges": "\u0120? >", "raw_count": 1587, "count": 1587, "decode_str": " ?>"} -{"id": 41581, "token": "\u00e3\u0123\u013c", "merges": "\u00e3\u0123 \u013c", "raw_count": 1587, "count": 1587, "decode_str": "\u305a"} -{"id": 28098, "token": "\u0120Bir", "merges": "\u0120B ir", "raw_count": 1588, "count": 1588, "decode_str": " Bir"} -{"id": 50370, "token": "\u00e2\u0138\u00bd", "merges": "\u00e2\u0138 \u00bd", "raw_count": 1588, "count": 1588, "decode_str": "\u25bd"} -{"id": 37418, "token": "\u0120Iz", "merges": "\u0120I z", "raw_count": 1589, "count": 1589, "decode_str": " Iz"} -{"id": 11007, "token": "\u0120Chris", "merges": "\u0120Ch ris", "raw_count": 1590, "count": 1590, "decode_str": " Chris"} -{"id": 48136, "token": "\u0120Evening", "merges": "\u0120Even ing", "raw_count": 1591, "count": 1591, "decode_str": " Evening"} -{"id": 45975, "token": "\u0120butcher", "merges": "\u0120but cher", "raw_count": 1591, "count": 1591, "decode_str": " butcher"} -{"id": 45027, "token": "\u0120quilt", "merges": "\u0120qu ilt", "raw_count": 1591, "count": 1591, "decode_str": " quilt"} -{"id": 42758, "token": "\u0120hace", "merges": "\u0120h ace", "raw_count": 1591, "count": 1591, "decode_str": " hace"} -{"id": 35080, "token": "\u00c3\u00a8ne", "merges": "\u00c3\u00a8 ne", "raw_count": 1591, "count": 1591, "decode_str": "\u00e8ne"} -{"id": 21796, "token": "\u00c3\u00b8r", "merges": "\u00c3\u00b8 r", "raw_count": 1591, "count": 1591, "decode_str": "\u00f8r"} -{"id": 4287, "token": "rightarrow", "merges": "right arrow", "raw_count": 1345, "count": 1592, "decode_str": "rightarrow"} -{"id": 45398, "token": "\u0120Fighter", "merges": "\u0120F ighter", "raw_count": 1592, "count": 1592, "decode_str": " Fighter"} -{"id": 26064, "token": "\u0120Lud", "merges": "\u0120L ud", "raw_count": 625, "count": 1592, "decode_str": " Lud"} -{"id": 47614, "token": "ellt", "merges": "ell t", "raw_count": 1592, "count": 1592, "decode_str": "ellt"} -{"id": 18402, "token": "\u0120Hem", "merges": "\u0120H em", "raw_count": 1592, "count": 1592, "decode_str": " Hem"} -{"id": 33062, "token": "\u0120Applying", "merges": "\u0120App lying", "raw_count": 1593, "count": 1593, "decode_str": " Applying"} -{"id": 27067, "token": "\u0120implants", "merges": "\u0120impl ants", "raw_count": 1593, "count": 1593, "decode_str": " implants"} -{"id": 41238, "token": "\u0120PROF", "merges": "\u0120PR OF", "raw_count": 1572, "count": 1593, "decode_str": " PROF"} -{"id": 30333, "token": "\u0120functionally", "merges": "\u0120function ally", "raw_count": 1594, "count": 1594, "decode_str": " functionally"} -{"id": 43043, "token": "\u0120\u00d1\u0123\u00d0\u00b0\u00d0\u00bc", "merges": "\u0120\u00d1\u0123 \u00d0\u00b0\u00d0\u00bc", "raw_count": 1594, "count": 1594, "decode_str": " \u0441\u0430\u043c"} -{"id": 36348, "token": "\u0120dyes", "merges": "\u0120d yes", "raw_count": 1594, "count": 1594, "decode_str": " dyes"} -{"id": 42664, "token": "\u00c3\u00bck", "merges": "\u00c3\u00bc k", "raw_count": 1594, "count": 1594, "decode_str": "\u00fck"} -{"id": 15197, "token": "\u0120Howard", "merges": "\u0120How ard", "raw_count": 1595, "count": 1595, "decode_str": " Howard"} -{"id": 36984, "token": "\u0120sugars", "merges": "\u0120sug ars", "raw_count": 1595, "count": 1595, "decode_str": " sugars"} -{"id": 45878, "token": "\u0120Productions", "merges": "\u0120Produ ctions", "raw_count": 1596, "count": 1596, "decode_str": " Productions"} -{"id": 34885, "token": "\u0120minimally", "merges": "\u0120minim ally", "raw_count": 1596, "count": 1596, "decode_str": " minimally"} -{"id": 19498, "token": "\u0120Stewart", "merges": "\u0120Ste wart", "raw_count": 1596, "count": 1596, "decode_str": " Stewart"} -{"id": 20574, "token": "\u0120Freedom", "merges": "\u0120Fre edom", "raw_count": 1597, "count": 1597, "decode_str": " Freedom"} -{"id": 31449, "token": "\u0120Motors", "merges": "\u0120Mot ors", "raw_count": 1597, "count": 1597, "decode_str": " Motors"} -{"id": 23724, "token": "\u0120Woman", "merges": "\u0120W oman", "raw_count": 1597, "count": 1597, "decode_str": " Woman"} -{"id": 24268, "token": "\u0120sono", "merges": "\u0120son o", "raw_count": 1597, "count": 1597, "decode_str": " sono"} -{"id": 49003, "token": "\u00e2\u0122\u012e", "merges": "\u00e2\u0122 \u012e", "raw_count": 1597, "count": 1597, "decode_str": "\u200c"} -{"id": 41411, "token": "\u00c3\u00a1c", "merges": "\u00c3\u00a1 c", "raw_count": 1597, "count": 1597, "decode_str": "\u00e1c"} -{"id": 43499, "token": "\u0120VERY", "merges": "\u0120V ERY", "raw_count": 1598, "count": 1598, "decode_str": " VERY"} -{"id": 31106, "token": "\u0120abelian", "merges": "\u0120ab elian", "raw_count": 1599, "count": 1599, "decode_str": " abelian"} -{"id": 10255, "token": "\u0120Columb", "merges": "\u0120Col umb", "raw_count": 155, "count": 1599, "decode_str": " Columb"} -{"id": 49943, "token": "\u0120shroud", "merges": "\u0120shr oud", "raw_count": 1599, "count": 1599, "decode_str": " shroud"} -{"id": 17637, "token": ")+\\", "merges": ") +\\", "raw_count": 1599, "count": 1599, "decode_str": ")+\\"} -{"id": 39883, "token": "\u0120pounding", "merges": "\u0120p ounding", "raw_count": 1600, "count": 1600, "decode_str": " pounding"} -{"id": 50090, "token": "\u0120behaving", "merges": "\u0120behav ing", "raw_count": 1600, "count": 1600, "decode_str": " behaving"} -{"id": 50131, "token": "\u0120assortment", "merges": "\u0120assort ment", "raw_count": 1601, "count": 1601, "decode_str": " assortment"} -{"id": 32411, "token": "\u0120feminist", "merges": "\u0120femin ist", "raw_count": 1601, "count": 1601, "decode_str": " feminist"} -{"id": 43390, "token": "\u0120claws", "merges": "\u0120cl aws", "raw_count": 1601, "count": 1601, "decode_str": " claws"} -{"id": 43370, "token": "\u0120guts", "merges": "\u0120gut s", "raw_count": 1601, "count": 1601, "decode_str": " guts"} -{"id": 42798, "token": "\u0120unbelievable", "merges": "\u0120unbelie vable", "raw_count": 1602, "count": 1602, "decode_str": " unbelievable"} -{"id": 42115, "token": "\u0120inductive", "merges": "\u0120induct ive", "raw_count": 1602, "count": 1602, "decode_str": " inductive"} -{"id": 37312, "token": "\u0120vra", "merges": "\u0120v ra", "raw_count": 1602, "count": 1602, "decode_str": " vra"} -{"id": 44099, "token": "\u0120incarcerated", "merges": "\u0120incarcer ated", "raw_count": 1603, "count": 1603, "decode_str": " incarcerated"} -{"id": 21525, "token": "\u0120Taking", "merges": "\u0120T aking", "raw_count": 1603, "count": 1603, "decode_str": " Taking"} -{"id": 40095, "token": "\u0120oxides", "merges": "\u0120ox ides", "raw_count": 1603, "count": 1603, "decode_str": " oxides"} -{"id": 43754, "token": "\u0120Electronics", "merges": "\u0120Electron ics", "raw_count": 1604, "count": 1604, "decode_str": " Electronics"} -{"id": 20716, "token": "\u0120untreated", "merges": "\u0120un treated", "raw_count": 1604, "count": 1604, "decode_str": " untreated"} -{"id": 31672, "token": "\u0120cathode", "merges": "\u0120cath ode", "raw_count": 1604, "count": 1604, "decode_str": " cathode"} -{"id": 27361, "token": "\u0120cohorts", "merges": "\u0120coh orts", "raw_count": 1604, "count": 1604, "decode_str": " cohorts"} -{"id": 19547, "token": "\u0120Sams", "merges": "\u0120S ams", "raw_count": 423, "count": 1604, "decode_str": " Sams"} -{"id": 46197, "token": "\u0120paranoid", "merges": "\u0120paran oid", "raw_count": 1605, "count": 1605, "decode_str": " paranoid"} -{"id": 47971, "token": "chst", "merges": "ch st", "raw_count": 1605, "count": 1605, "decode_str": "chst"} -{"id": 13626, "token": "\u0120PBS", "merges": "\u0120P BS", "raw_count": 1605, "count": 1605, "decode_str": " PBS"} -{"id": 45402, "token": "\u0120scratched", "merges": "\u0120scr atched", "raw_count": 1606, "count": 1606, "decode_str": " scratched"} -{"id": 41640, "token": "\u0120Liquid", "merges": "\u0120Liqu id", "raw_count": 1606, "count": 1606, "decode_str": " Liquid"} -{"id": 23068, "token": "\u00e0\u00a4\u00a8", "merges": "\u00e0\u00a4 \u00a8", "raw_count": 1606, "count": 1606, "decode_str": "\u0928"} -{"id": 45646, "token": "\u0120politely", "merges": "\u0120polit ely", "raw_count": 1607, "count": 1607, "decode_str": " politely"} -{"id": 31075, "token": "\u0120Cultural", "merges": "\u0120C ultural", "raw_count": 1607, "count": 1607, "decode_str": " Cultural"} -{"id": 46086, "token": "\u0120experimenting", "merges": "\u0120experiment ing", "raw_count": 1608, "count": 1608, "decode_str": " experimenting"} -{"id": 25535, "token": "\u0120spectrometry", "merges": "\u0120spectrom etry", "raw_count": 1608, "count": 1608, "decode_str": " spectrometry"} -{"id": 35424, "token": "\u0120ging", "merges": "\u0120g ing", "raw_count": 1608, "count": 1608, "decode_str": " ging"} -{"id": 12272, "token": "\u00e1\u00bc", "merges": "\u00e1 \u00bc", "raw_count": 1013, "count": 1608, "decode_str": "\ufffd"} -{"id": 41702, "token": "\u0120Reality", "merges": "\u0120Re ality", "raw_count": 1609, "count": 1609, "decode_str": " Reality"} -{"id": 24744, "token": "\u0120Really", "merges": "\u0120Re ally", "raw_count": 1609, "count": 1609, "decode_str": " Really"} -{"id": 42447, "token": "ycler", "merges": "ycl er", "raw_count": 1609, "count": 1609, "decode_str": "ycler"} -{"id": 33393, "token": "\u0120Securities", "merges": "\u0120Sec urities", "raw_count": 1610, "count": 1610, "decode_str": " Securities"} -{"id": 30245, "token": "\u0120conceded", "merges": "\u0120conced ed", "raw_count": 1610, "count": 1610, "decode_str": " conceded"} -{"id": 13151, "token": "othelial", "merges": "ot helial", "raw_count": 707, "count": 1610, "decode_str": "othelial"} -{"id": 13717, "token": "\u0120marijuana", "merges": "\u0120m arijuana", "raw_count": 1611, "count": 1611, "decode_str": " marijuana"} -{"id": 47947, "token": "\u0120hallmark", "merges": "\u0120hall mark", "raw_count": 1611, "count": 1611, "decode_str": " hallmark"} -{"id": 45628, "token": "\u0120occupant", "merges": "\u0120occup ant", "raw_count": 1611, "count": 1611, "decode_str": " occupant"} -{"id": 44969, "token": "\u0120Mega", "merges": "\u0120M ega", "raw_count": 1611, "count": 1611, "decode_str": " Mega"} -{"id": 32131, "token": "'}\\", "merges": "' }\\", "raw_count": 1611, "count": 1611, "decode_str": "'}\\"} -{"id": 37643, "token": "\u0120immer", "merges": "\u0120im mer", "raw_count": 1612, "count": 1612, "decode_str": " immer"} -{"id": 47599, "token": "itum", "merges": "it um", "raw_count": 1612, "count": 1612, "decode_str": "itum"} -{"id": 40296, "token": "\u0120semic", "merges": "\u0120sem ic", "raw_count": 1613, "count": 1613, "decode_str": " semic"} -{"id": 27884, "token": "\u0120s\u00c3\u00b3", "merges": "\u0120s \u00c3\u00b3", "raw_count": 1218, "count": 1614, "decode_str": " s\u00f3"} -{"id": 25958, "token": "\u0120Bak", "merges": "\u0120B ak", "raw_count": 1614, "count": 1614, "decode_str": " Bak"} -{"id": 46616, "token": "\u0120silenced", "merges": "\u0120sil enced", "raw_count": 1615, "count": 1615, "decode_str": " silenced"} -{"id": 28006, "token": "\u0120idiot", "merges": "\u0120id iot", "raw_count": 1615, "count": 1615, "decode_str": " idiot"} -{"id": 47274, "token": "\u0120bum", "merges": "\u0120b um", "raw_count": 1615, "count": 1615, "decode_str": " bum"} -{"id": 47148, "token": "\u0120zal", "merges": "\u0120z al", "raw_count": 1615, "count": 1615, "decode_str": " zal"} -{"id": 34723, "token": "\u0120Published", "merges": "\u0120P ublished", "raw_count": 1616, "count": 1616, "decode_str": " Published"} -{"id": 28643, "token": "aryngeal", "merges": "arynge al", "raw_count": 1616, "count": 1616, "decode_str": "aryngeal"} -{"id": 5396, "token": "\u0120Indian", "merges": "\u0120Ind ian", "raw_count": 1295, "count": 1616, "decode_str": " Indian"} -{"id": 49514, "token": "ocious", "merges": "oc ious", "raw_count": 1617, "count": 1617, "decode_str": "ocious"} -{"id": 47765, "token": "\u0120stunt", "merges": "\u0120st unt", "raw_count": 1617, "count": 1617, "decode_str": " stunt"} -{"id": 45718, "token": "\u0120wsp", "merges": "\u0120w sp", "raw_count": 1617, "count": 1617, "decode_str": " wsp"} -{"id": 20809, "token": "bmatrix", "merges": "b matrix", "raw_count": 1618, "count": 1618, "decode_str": "bmatrix"} -{"id": 45969, "token": "autre", "merges": "aut re", "raw_count": 1618, "count": 1618, "decode_str": "autre"} -{"id": 43081, "token": "\u0120disruptive", "merges": "\u0120disrupt ive", "raw_count": 1619, "count": 1619, "decode_str": " disruptive"} -{"id": 42943, "token": "\u0120Defender", "merges": "\u0120Def ender", "raw_count": 1619, "count": 1619, "decode_str": " Defender"} -{"id": 45361, "token": "\u0120killers", "merges": "\u0120kill ers", "raw_count": 1619, "count": 1619, "decode_str": " killers"} -{"id": 14468, "token": "\u0120Brian", "merges": "\u0120B rian", "raw_count": 1619, "count": 1619, "decode_str": " Brian"} -{"id": 49204, "token": "\u0120defeats", "merges": "\u0120defe ats", "raw_count": 1620, "count": 1620, "decode_str": " defeats"} -{"id": 22456, "token": "\u0120Rogers", "merges": "\u0120Rog ers", "raw_count": 1620, "count": 1620, "decode_str": " Rogers"} -{"id": 27063, "token": "suppl", "merges": "supp l", "raw_count": 1620, "count": 1620, "decode_str": "suppl"} -{"id": 24839, "token": "\u0120Ton", "merges": "\u0120T on", "raw_count": 1167, "count": 1620, "decode_str": " Ton"} -{"id": 31645, "token": "\u0120Shi", "merges": "\u0120Sh i", "raw_count": 1620, "count": 1620, "decode_str": " Shi"} -{"id": 45425, "token": "\u0120propagator", "merges": "\u0120propag ator", "raw_count": 1621, "count": 1621, "decode_str": " propagator"} -{"id": 27110, "token": "\u0120asymmetry", "merges": "\u0120asym metry", "raw_count": 1621, "count": 1621, "decode_str": " asymmetry"} -{"id": 20068, "token": "\u0120amplified", "merges": "\u0120ampl ified", "raw_count": 1622, "count": 1622, "decode_str": " amplified"} -{"id": 36187, "token": "\u0120chees", "merges": "\u0120che es", "raw_count": 1622, "count": 1622, "decode_str": " chees"} -{"id": 47498, "token": "\u0120deity", "merges": "\u0120de ity", "raw_count": 1622, "count": 1622, "decode_str": " deity"} -{"id": 14961, "token": "\u0120myocard", "merges": "\u0120my ocard", "raw_count": 89, "count": 1623, "decode_str": " myocard"} -{"id": 25519, "token": "\u0120reagent", "merges": "\u0120re agent", "raw_count": 1623, "count": 1623, "decode_str": " reagent"} -{"id": 43605, "token": "\u0120Virt", "merges": "\u0120V irt", "raw_count": 1623, "count": 1623, "decode_str": " Virt"} -{"id": 37811, "token": "\u0120Away", "merges": "\u0120A way", "raw_count": 1623, "count": 1623, "decode_str": " Away"} -{"id": 43347, "token": "\u0120hors", "merges": "\u0120h ors", "raw_count": 1623, "count": 1623, "decode_str": " hors"} -{"id": 25783, "token": "\u0120isomorphic", "merges": "\u0120is omorphic", "raw_count": 1624, "count": 1624, "decode_str": " isomorphic"} -{"id": 26893, "token": "\u0120iconic", "merges": "\u0120icon ic", "raw_count": 1624, "count": 1624, "decode_str": " iconic"} -{"id": 27808, "token": "\u0120Pour", "merges": "\u0120P our", "raw_count": 1624, "count": 1624, "decode_str": " Pour"} -{"id": 18820, "token": "\u0120antibiotic", "merges": "\u0120antib iotic", "raw_count": 1625, "count": 1625, "decode_str": " antibiotic"} -{"id": 25609, "token": "oresis", "merges": "ores is", "raw_count": 815, "count": 1625, "decode_str": "oresis"} -{"id": 29632, "token": "\u0120WHAT", "merges": "\u0120WH AT", "raw_count": 1626, "count": 1626, "decode_str": " WHAT"} -{"id": 20781, "token": "\u0120k\u00c3\u00b6", "merges": "\u0120k \u00c3\u00b6", "raw_count": 1331, "count": 1626, "decode_str": " k\u00f6"} -{"id": 32415, "token": "\u0120Basically", "merges": "\u0120Bas ically", "raw_count": 1628, "count": 1628, "decode_str": " Basically"} -{"id": 5759, "token": "\u0120Congress", "merges": "\u0120Cong ress", "raw_count": 1620, "count": 1628, "decode_str": " Congress"} -{"id": 18410, "token": "\u0120Maj", "merges": "\u0120M aj", "raw_count": 1216, "count": 1628, "decode_str": " Maj"} -{"id": 47892, "token": "\u0120cynical", "merges": "\u0120cyn ical", "raw_count": 1629, "count": 1629, "decode_str": " cynical"} -{"id": 19048, "token": "\u0120VII", "merges": "\u0120V II", "raw_count": 1629, "count": 1629, "decode_str": " VII"} -{"id": 32943, "token": "\u0120hospitalized", "merges": "\u0120hospital ized", "raw_count": 1630, "count": 1630, "decode_str": " hospitalized"} -{"id": 39554, "token": "\u0120Criteria", "merges": "\u0120Crit eria", "raw_count": 1630, "count": 1630, "decode_str": " Criteria"} -{"id": 48009, "token": "\u0120impulses", "merges": "\u0120imp ulses", "raw_count": 1630, "count": 1630, "decode_str": " impulses"} -{"id": 26168, "token": "omeric", "merges": "om eric", "raw_count": 1630, "count": 1630, "decode_str": "omeric"} -{"id": 7048, "token": "\u0120appellant", "merges": "\u0120app ellant", "raw_count": 1631, "count": 1631, "decode_str": " appellant"} -{"id": 26755, "token": "\u0120Places", "merges": "\u0120Pl aces", "raw_count": 1631, "count": 1631, "decode_str": " Places"} -{"id": 21730, "token": "\u0120schizophren", "merges": "\u0120sch izophren", "raw_count": 321, "count": 1632, "decode_str": " schizophren"} -{"id": 31615, "token": "plectic", "merges": "ple ctic", "raw_count": 830, "count": 1632, "decode_str": "plectic"} -{"id": 49365, "token": "\u0120Xavier", "merges": "\u0120X avier", "raw_count": 1632, "count": 1632, "decode_str": " Xavier"} -{"id": 46908, "token": "\u0120unbe", "merges": "\u0120un be", "raw_count": 1632, "count": 1632, "decode_str": " unbe"} -{"id": 24941, "token": "\u0120Kur", "merges": "\u0120K ur", "raw_count": 1632, "count": 1632, "decode_str": " Kur"} -{"id": 35679, "token": "accharides", "merges": "acchar ides", "raw_count": 1633, "count": 1633, "decode_str": "accharides"} -{"id": 39561, "token": "\u0120Borg", "merges": "\u0120B org", "raw_count": 1633, "count": 1633, "decode_str": " Borg"} -{"id": 24537, "token": "\u0120innate", "merges": "\u0120inn ate", "raw_count": 1634, "count": 1634, "decode_str": " innate"} -{"id": 38869, "token": "aldehyde", "merges": "al dehyde", "raw_count": 1635, "count": 1635, "decode_str": "aldehyde"} -{"id": 39825, "token": "\u0120ventil", "merges": "\u0120vent il", "raw_count": 1635, "count": 1635, "decode_str": " ventil"} -{"id": 47465, "token": "\u0120darkened", "merges": "\u0120dark ened", "raw_count": 1636, "count": 1636, "decode_str": " darkened"} -{"id": 47519, "token": "\u00e3\u0124\u00bf\u00e3\u0125\u00bc", "merges": "\u00e3\u0124\u00bf \u00e3\u0125\u00bc", "raw_count": 1636, "count": 1636, "decode_str": "\u30bf\u30fc"} -{"id": 22662, "token": "\u0120Marc", "merges": "\u0120Mar c", "raw_count": 1636, "count": 1636, "decode_str": " Marc"} -{"id": 21561, "token": "\u0120Discussion", "merges": "\u0120D iscussion", "raw_count": 1637, "count": 1637, "decode_str": " Discussion"} -{"id": 28741, "token": "\u0120intestine", "merges": "\u0120int estine", "raw_count": 1637, "count": 1637, "decode_str": " intestine"} -{"id": 43252, "token": "\u0120Kindle", "merges": "\u0120K indle", "raw_count": 1637, "count": 1637, "decode_str": " Kindle"} -{"id": 16982, "token": "\u0120Nich", "merges": "\u0120N ich", "raw_count": 574, "count": 1637, "decode_str": " Nich"} -{"id": 12743, "token": "\u0120Officer", "merges": "\u0120Offic er", "raw_count": 1638, "count": 1638, "decode_str": " Officer"} -{"id": 46677, "token": "alanine", "merges": "al anine", "raw_count": 1638, "count": 1638, "decode_str": "alanine"} -{"id": 44102, "token": "\u0120Mining", "merges": "\u0120M ining", "raw_count": 1638, "count": 1638, "decode_str": " Mining"} -{"id": 28376, "token": "\u0120preg", "merges": "\u0120pre g", "raw_count": 1638, "count": 1638, "decode_str": " preg"} -{"id": 41059, "token": "\u0120NEWS", "merges": "\u0120NE WS", "raw_count": 1638, "count": 1638, "decode_str": " NEWS"} -{"id": 40393, "token": "\u0120Acid", "merges": "\u0120Ac id", "raw_count": 1638, "count": 1638, "decode_str": " Acid"} -{"id": 47485, "token": "\u0120fashioned", "merges": "\u0120fashion ed", "raw_count": 1639, "count": 1639, "decode_str": " fashioned"} -{"id": 30179, "token": "\u0120singularity", "merges": "\u0120singular ity", "raw_count": 1640, "count": 1640, "decode_str": " singularity"} -{"id": 46377, "token": "\u0120Wilhelm", "merges": "\u0120Wil helm", "raw_count": 1640, "count": 1640, "decode_str": " Wilhelm"} -{"id": 34903, "token": "\u0120blinded", "merges": "\u0120blind ed", "raw_count": 1640, "count": 1640, "decode_str": " blinded"} -{"id": 27818, "token": "\u0120Vas", "merges": "\u0120V as", "raw_count": 1641, "count": 1641, "decode_str": " Vas"} -{"id": 35027, "token": "\u0120spokeswoman", "merges": "\u0120spokes woman", "raw_count": 1642, "count": 1642, "decode_str": " spokeswoman"} -{"id": 38197, "token": "\u0120stimulates", "merges": "\u0120stimul ates", "raw_count": 1642, "count": 1642, "decode_str": " stimulates"} -{"id": 45853, "token": "\u0120brushing", "merges": "\u0120br ushing", "raw_count": 1642, "count": 1642, "decode_str": " brushing"} -{"id": 40131, "token": "\u0120intron", "merges": "\u0120int ron", "raw_count": 1642, "count": 1642, "decode_str": " intron"} -{"id": 19790, "token": "\u0120NMR", "merges": "\u0120N MR", "raw_count": 1642, "count": 1642, "decode_str": " NMR"} -{"id": 46123, "token": "ensibly", "merges": "ens ibly", "raw_count": 1643, "count": 1643, "decode_str": "ensibly"} -{"id": 22976, "token": "\u0120Fran", "merges": "\u0120Fr an", "raw_count": 1622, "count": 1643, "decode_str": " Fran"} -{"id": 26184, "token": "\u0120Kid", "merges": "\u0120K id", "raw_count": 1643, "count": 1643, "decode_str": " Kid"} -{"id": 42162, "token": "\u0120associative", "merges": "\u0120associ ative", "raw_count": 1644, "count": 1644, "decode_str": " associative"} -{"id": 46903, "token": "\u0120slippery", "merges": "\u0120slipp ery", "raw_count": 1644, "count": 1644, "decode_str": " slippery"} -{"id": 47280, "token": "\u0120Funk", "merges": "\u0120F unk", "raw_count": 1644, "count": 1644, "decode_str": " Funk"} -{"id": 24522, "token": "\u0120allege", "merges": "\u0120al lege", "raw_count": 1645, "count": 1645, "decode_str": " allege"} -{"id": 30294, "token": "\u0120retrospect", "merges": "\u0120retros pect", "raw_count": 1171, "count": 1647, "decode_str": " retrospect"} -{"id": 39571, "token": "\u0120Dong", "merges": "\u0120D ong", "raw_count": 1647, "count": 1647, "decode_str": " Dong"} -{"id": 36937, "token": "\u00e1\u00bb\u013b", "merges": "\u00e1\u00bb \u013b", "raw_count": 1647, "count": 1647, "decode_str": "\u1ed9"} -{"id": 47790, "token": "\u0120corroborated", "merges": "\u0120corrobor ated", "raw_count": 1648, "count": 1648, "decode_str": " corroborated"} -{"id": 38222, "token": "\u0120venom", "merges": "\u0120ven om", "raw_count": 1649, "count": 1649, "decode_str": " venom"} -{"id": 26917, "token": "Enron", "merges": "En ron", "raw_count": 1649, "count": 1649, "decode_str": "Enron"} -{"id": 36039, "token": "\u0120interplay", "merges": "\u0120inter play", "raw_count": 1650, "count": 1650, "decode_str": " interplay"} -{"id": 37076, "token": "\u0120Issues", "merges": "\u0120Iss ues", "raw_count": 1650, "count": 1650, "decode_str": " Issues"} -{"id": 39362, "token": "\u0120mesmo", "merges": "\u0120mes mo", "raw_count": 1650, "count": 1650, "decode_str": " mesmo"} -{"id": 41541, "token": "\u0120Achie", "merges": "\u0120A chie", "raw_count": 1650, "count": 1650, "decode_str": " Achie"} -{"id": 48580, "token": "\u0120soot", "merges": "\u0120so ot", "raw_count": 1650, "count": 1650, "decode_str": " soot"} -{"id": 35075, "token": "\u0120Orche", "merges": "\u0120Or che", "raw_count": 815, "count": 1651, "decode_str": " Orche"} -{"id": 15500, "token": "\u00c2\u00af", "merges": "\u00c2 \u00af", "raw_count": 1650, "count": 1651, "decode_str": "\u00af"} -{"id": 27103, "token": "\u0120_________________", "merges": "\u0120_ ________________", "raw_count": 1652, "count": 1652, "decode_str": " _________________"} -{"id": 44659, "token": "\u0120froze", "merges": "\u0120fro ze", "raw_count": 1652, "count": 1652, "decode_str": " froze"} -{"id": 47388, "token": "iably", "merges": "i ably", "raw_count": 1652, "count": 1652, "decode_str": "iably"} -{"id": 11910, "token": "\u00ce\u00b5\u00ce\u00b9", "merges": "\u00ce\u00b5 \u00ce\u00b9", "raw_count": 1291, "count": 1652, "decode_str": "\u03b5\u03b9"} -{"id": 24990, "token": "\u00d7\u00aa", "merges": "\u00d7 \u00aa", "raw_count": 1652, "count": 1652, "decode_str": "\u05ea"} -{"id": 48134, "token": "\u0120snatched", "merges": "\u0120sn atched", "raw_count": 1653, "count": 1653, "decode_str": " snatched"} -{"id": 45725, "token": "okrat", "merges": "ok rat", "raw_count": 1653, "count": 1653, "decode_str": "okrat"} -{"id": 41587, "token": "\u0120erroneously", "merges": "\u0120errone ously", "raw_count": 1654, "count": 1654, "decode_str": " erroneously"} -{"id": 46727, "token": "\u0120painfully", "merges": "\u0120pain fully", "raw_count": 1654, "count": 1654, "decode_str": " painfully"} -{"id": 28062, "token": "eanor", "merges": "ean or", "raw_count": 1342, "count": 1654, "decode_str": "eanor"} -{"id": 46127, "token": "\u0120assassin", "merges": "\u0120assass in", "raw_count": 1655, "count": 1655, "decode_str": " assassin"} -{"id": 29931, "token": "\u0120epilepsy", "merges": "\u0120epile psy", "raw_count": 1656, "count": 1656, "decode_str": " epilepsy"} -{"id": 47496, "token": "\u0120Aster", "merges": "\u0120A ster", "raw_count": 1656, "count": 1656, "decode_str": " Aster"} -{"id": 50122, "token": "\u0120IIS", "merges": "\u0120I IS", "raw_count": 1656, "count": 1656, "decode_str": " IIS"} -{"id": 30383, "token": "\u0120Opera", "merges": "\u0120Oper a", "raw_count": 1657, "count": 1657, "decode_str": " Opera"} -{"id": 38790, "token": "\u0120prz", "merges": "\u0120pr z", "raw_count": 1657, "count": 1657, "decode_str": " prz"} -{"id": 17802, "token": "\u0120Winter", "merges": "\u0120W inter", "raw_count": 1658, "count": 1658, "decode_str": " Winter"} -{"id": 44494, "token": "\u0120warmed", "merges": "\u0120war med", "raw_count": 1658, "count": 1658, "decode_str": " warmed"} -{"id": 47635, "token": "\u0120Maxim", "merges": "\u0120Max im", "raw_count": 1660, "count": 1660, "decode_str": " Maxim"} -{"id": 34858, "token": "\u0120Fc", "merges": "\u0120F c", "raw_count": 1660, "count": 1660, "decode_str": " Fc"} -{"id": 46650, "token": "rospective", "merges": "ros pective", "raw_count": 1661, "count": 1661, "decode_str": "rospective"} -{"id": 45650, "token": "\u0120obscured", "merges": "\u0120obsc ured", "raw_count": 1661, "count": 1661, "decode_str": " obscured"} -{"id": 40293, "token": "\u0120Cros", "merges": "\u0120C ros", "raw_count": 1661, "count": 1661, "decode_str": " Cros"} -{"id": 38654, "token": "\u0120Transcript", "merges": "\u0120Trans cript", "raw_count": 1662, "count": 1662, "decode_str": " Transcript"} -{"id": 32008, "token": "\u0120Sax", "merges": "\u0120S ax", "raw_count": 1662, "count": 1662, "decode_str": " Sax"} -{"id": 45394, "token": "\u0120bounced", "merges": "\u0120b ounced", "raw_count": 1663, "count": 1663, "decode_str": " bounced"} -{"id": 36216, "token": "\u0120Triple", "merges": "\u0120Tri ple", "raw_count": 1663, "count": 1663, "decode_str": " Triple"} -{"id": 15359, "token": "\u0120Barn", "merges": "\u0120B arn", "raw_count": 1053, "count": 1663, "decode_str": " Barn"} -{"id": 31749, "token": "\u0120Gaz", "merges": "\u0120G az", "raw_count": 1663, "count": 1663, "decode_str": " Gaz"} -{"id": 43733, "token": "\u0120magnets", "merges": "\u0120magn ets", "raw_count": 1664, "count": 1664, "decode_str": " magnets"} -{"id": 23626, "token": "\u0120Beyond", "merges": "\u0120Be yond", "raw_count": 1664, "count": 1664, "decode_str": " Beyond"} -{"id": 49110, "token": "\u0120vener", "merges": "\u0120v ener", "raw_count": 1664, "count": 1664, "decode_str": " vener"} -{"id": 39934, "token": "\u0120constitutive", "merges": "\u0120constit utive", "raw_count": 1666, "count": 1666, "decode_str": " constitutive"} -{"id": 43486, "token": "\u0120sweetness", "merges": "\u0120sweet ness", "raw_count": 1666, "count": 1666, "decode_str": " sweetness"} -{"id": 49198, "token": "\u0120assail", "merges": "\u0120ass ail", "raw_count": 1666, "count": 1666, "decode_str": " assail"} -{"id": 23060, "token": "\u0120Nord", "merges": "\u0120N ord", "raw_count": 1666, "count": 1666, "decode_str": " Nord"} -{"id": 39713, "token": "\u0120conductors", "merges": "\u0120conduct ors", "raw_count": 1667, "count": 1667, "decode_str": " conductors"} -{"id": 37030, "token": "romycin", "merges": "romy cin", "raw_count": 1667, "count": 1667, "decode_str": "romycin"} -{"id": 23637, "token": "PLIED", "merges": "PL IED", "raw_count": 1605, "count": 1667, "decode_str": "PLIED"} -{"id": 44409, "token": "\u0120turf", "merges": "\u0120tur f", "raw_count": 1667, "count": 1667, "decode_str": " turf"} -{"id": 43178, "token": "\u0120LW", "merges": "\u0120L W", "raw_count": 1667, "count": 1667, "decode_str": " LW"} -{"id": 40483, "token": "\u0120troph", "merges": "\u0120t roph", "raw_count": 1668, "count": 1668, "decode_str": " troph"} -{"id": 47867, "token": "\u0120Ajax", "merges": "\u0120A jax", "raw_count": 1668, "count": 1668, "decode_str": " Ajax"} -{"id": 20754, "token": "\u0120Cold", "merges": "\u0120C old", "raw_count": 1669, "count": 1669, "decode_str": " Cold"} -{"id": 29144, "token": "\u0120typeof", "merges": "\u0120type of", "raw_count": 1670, "count": 1670, "decode_str": " typeof"} -{"id": 22496, "token": "\u0120gastrointestinal", "merges": "\u0120gastro intestinal", "raw_count": 1672, "count": 1672, "decode_str": " gastrointestinal"} -{"id": 45350, "token": "\u0120arsenic", "merges": "\u0120arsen ic", "raw_count": 1672, "count": 1672, "decode_str": " arsenic"} -{"id": 31929, "token": "\u0120indist", "merges": "\u0120ind ist", "raw_count": 721, "count": 1672, "decode_str": " indist"} -{"id": 19029, "token": "lament", "merges": "l ament", "raw_count": 1436, "count": 1672, "decode_str": "lament"} -{"id": 25150, "token": "\u0120Pun", "merges": "\u0120P un", "raw_count": 1634, "count": 1672, "decode_str": " Pun"} -{"id": 42631, "token": "\u0120Rolling", "merges": "\u0120Rol ling", "raw_count": 1673, "count": 1673, "decode_str": " Rolling"} -{"id": 46226, "token": "\u0120CIT", "merges": "\u0120C IT", "raw_count": 1673, "count": 1673, "decode_str": " CIT"} -{"id": 47471, "token": "\u0120allergies", "merges": "\u0120allerg ies", "raw_count": 1674, "count": 1674, "decode_str": " allergies"} -{"id": 30443, "token": "\u0120grinned", "merges": "\u0120gr inned", "raw_count": 1674, "count": 1674, "decode_str": " grinned"} -{"id": 22725, "token": "\u0120arXiv", "merges": "\u0120ar Xiv", "raw_count": 1674, "count": 1674, "decode_str": " arXiv"} -{"id": 39279, "token": "\u0120WI", "merges": "\u0120W I", "raw_count": 1674, "count": 1674, "decode_str": " WI"} -{"id": 29620, "token": "\u00d8\u00b2", "merges": "\u00d8 \u00b2", "raw_count": 1674, "count": 1674, "decode_str": "\u0632"} -{"id": 26559, "token": "Illustration", "merges": "Ill ustration", "raw_count": 1675, "count": 1675, "decode_str": "Illustration"} -{"id": 48575, "token": "\u0120ISP", "merges": "\u0120IS P", "raw_count": 1676, "count": 1676, "decode_str": " ISP"} -{"id": 15175, "token": "\u00c3\u00a4\u00c3\u00a4", "merges": "\u00c3\u00a4 \u00c3\u00a4", "raw_count": 1676, "count": 1676, "decode_str": "\u00e4\u00e4"} -{"id": 41058, "token": "\u0120Sprint", "merges": "\u0120S print", "raw_count": 1677, "count": 1677, "decode_str": " Sprint"} -{"id": 33693, "token": "\u0120poder", "merges": "\u0120pod er", "raw_count": 1677, "count": 1677, "decode_str": " poder"} -{"id": 46852, "token": "\u0120randomization", "merges": "\u0120random ization", "raw_count": 1679, "count": 1679, "decode_str": " randomization"} -{"id": 48867, "token": "\u0120intimately", "merges": "\u0120int imately", "raw_count": 1679, "count": 1679, "decode_str": " intimately"} -{"id": 24022, "token": "\u0120embryonic", "merges": "\u0120embry onic", "raw_count": 1680, "count": 1680, "decode_str": " embryonic"} -{"id": 25027, "token": "\u0120parasite", "merges": "\u0120paras ite", "raw_count": 1680, "count": 1680, "decode_str": " parasite"} -{"id": 20728, "token": "ophagy", "merges": "ophag y", "raw_count": 1597, "count": 1680, "decode_str": "ophagy"} -{"id": 7705, "token": "\u0120FIG", "merges": "\u0120F IG", "raw_count": 1582, "count": 1680, "decode_str": " FIG"} -{"id": 46942, "token": "\u0120Tod", "merges": "\u0120T od", "raw_count": 1680, "count": 1680, "decode_str": " Tod"} -{"id": 37088, "token": "\u00e1\u00ba\u00a5", "merges": "\u00e1\u00ba \u00a5", "raw_count": 1681, "count": 1681, "decode_str": "\u1ea5"} -{"id": 31191, "token": "\u0120electrolyte", "merges": "\u0120electroly te", "raw_count": 1682, "count": 1682, "decode_str": " electrolyte"} -{"id": 43604, "token": "\u0120accompanies", "merges": "\u0120accompan ies", "raw_count": 1682, "count": 1682, "decode_str": " accompanies"} -{"id": 41275, "token": "\u0120Integrated", "merges": "\u0120Integr ated", "raw_count": 1682, "count": 1682, "decode_str": " Integrated"} -{"id": 40178, "token": "\u0120gamers", "merges": "\u0120gam ers", "raw_count": 1682, "count": 1682, "decode_str": " gamers"} -{"id": 46038, "token": "\u0120essa", "merges": "\u0120ess a", "raw_count": 1682, "count": 1682, "decode_str": " essa"} -{"id": 40878, "token": "\u0120contradicts", "merges": "\u0120contradict s", "raw_count": 1683, "count": 1683, "decode_str": " contradicts"} -{"id": 22499, "token": "\u0120Fermi", "merges": "\u0120Ferm i", "raw_count": 1683, "count": 1683, "decode_str": " Fermi"} -{"id": 49517, "token": "\u0120MSD", "merges": "\u0120M SD", "raw_count": 1683, "count": 1683, "decode_str": " MSD"} -{"id": 34954, "token": "$=", "merges": "$ =", "raw_count": 1683, "count": 1683, "decode_str": "$="} -{"id": 22394, "token": "\u0120cryptocur", "merges": "\u0120crypt ocur", "raw_count": 17, "count": 1684, "decode_str": " cryptocur"} -{"id": 49401, "token": "etine", "merges": "et ine", "raw_count": 1684, "count": 1684, "decode_str": "etine"} -{"id": 21677, "token": "\u00d7\u0132", "merges": "\u00d7 \u0132", "raw_count": 1684, "count": 1684, "decode_str": "\u05d0"} -{"id": 35196, "token": "\u0120activator", "merges": "\u0120activ ator", "raw_count": 1685, "count": 1685, "decode_str": " activator"} -{"id": 47753, "token": "\u0120remorse", "merges": "\u0120rem orse", "raw_count": 1685, "count": 1685, "decode_str": " remorse"} -{"id": 46348, "token": "pathetic", "merges": "pat hetic", "raw_count": 1685, "count": 1685, "decode_str": "pathetic"} -{"id": 44469, "token": "otherap", "merges": "othe rap", "raw_count": 1685, "count": 1685, "decode_str": "otherap"} -{"id": 46278, "token": "\u0120RTC", "merges": "\u0120R TC", "raw_count": 1685, "count": 1685, "decode_str": " RTC"} -{"id": 37753, "token": "))=", "merges": ")) =", "raw_count": 1685, "count": 1685, "decode_str": "))="} -{"id": 5774, "token": ".](", "merges": ". ](", "raw_count": 1685, "count": 1685, "decode_str": ".]("} -{"id": 35755, "token": "\u0120distilled", "merges": "\u0120dist illed", "raw_count": 1686, "count": 1686, "decode_str": " distilled"} -{"id": 24892, "token": "\u0120immob", "merges": "\u0120imm ob", "raw_count": 1216, "count": 1686, "decode_str": " immob"} -{"id": 21469, "token": "\u00c2\u0142\u00c2\u0142\u00c2\u0142", "merges": "\u00c2\u0142\u00c2\u0142 \u00c2\u0142", "raw_count": 1686, "count": 1686, "decode_str": "\u00a0\u00a0\u00a0"} -{"id": 21073, "token": "orectal", "merges": "orect al", "raw_count": 835, "count": 1687, "decode_str": "orectal"} -{"id": 34079, "token": "\u0120inmate", "merges": "\u0120in mate", "raw_count": 1687, "count": 1687, "decode_str": " inmate"} -{"id": 23715, "token": ".\");", "merges": ".\" );", "raw_count": 1687, "count": 1687, "decode_str": ".\");"} -{"id": 47191, "token": "\u0120looming", "merges": "\u0120lo oming", "raw_count": 1688, "count": 1688, "decode_str": " looming"} -{"id": 6445, "token": "\u0120Jes", "merges": "\u0120J es", "raw_count": 605, "count": 1688, "decode_str": " Jes"} -{"id": 21352, "token": "\u0120Civ", "merges": "\u0120C iv", "raw_count": 1688, "count": 1688, "decode_str": " Civ"} -{"id": 19809, "token": "\u0120EPA", "merges": "\u0120E PA", "raw_count": 1688, "count": 1688, "decode_str": " EPA"} -{"id": 39761, "token": "\u0120Lun", "merges": "\u0120L un", "raw_count": 1688, "count": 1688, "decode_str": " Lun"} -{"id": 31349, "token": "\u0120Reviews", "merges": "\u0120Review s", "raw_count": 1689, "count": 1689, "decode_str": " Reviews"} -{"id": 43360, "token": "\u0120GOD", "merges": "\u0120G OD", "raw_count": 1689, "count": 1689, "decode_str": " GOD"} -{"id": 30412, "token": "\u0120.\\", "merges": "\u0120. \\", "raw_count": 1689, "count": 1689, "decode_str": " .\\"} -{"id": 46387, "token": "\u0120elbows", "merges": "\u0120el bows", "raw_count": 1690, "count": 1690, "decode_str": " elbows"} -{"id": 15908, "token": "\u0120Hur", "merges": "\u0120H ur", "raw_count": 1461, "count": 1690, "decode_str": " Hur"} -{"id": 28300, "token": "\u0120Pom", "merges": "\u0120P om", "raw_count": 1457, "count": 1690, "decode_str": " Pom"} -{"id": 31907, "token": "\u0120teammates", "merges": "\u0120team mates", "raw_count": 1691, "count": 1691, "decode_str": " teammates"} -{"id": 41767, "token": "\u0120Levels", "merges": "\u0120Level s", "raw_count": 1691, "count": 1691, "decode_str": " Levels"} -{"id": 27922, "token": "\u0120Near", "merges": "\u0120N ear", "raw_count": 1691, "count": 1691, "decode_str": " Near"} -{"id": 35193, "token": "\u0120Feel", "merges": "\u0120Fe el", "raw_count": 1691, "count": 1691, "decode_str": " Feel"} -{"id": 18089, "token": "\u0120Antonio", "merges": "\u0120Anton io", "raw_count": 1692, "count": 1692, "decode_str": " Antonio"} -{"id": 42626, "token": "\u0120gaseous", "merges": "\u0120g aseous", "raw_count": 1692, "count": 1692, "decode_str": " gaseous"} -{"id": 36192, "token": "\u0120SCC", "merges": "\u0120S CC", "raw_count": 1692, "count": 1692, "decode_str": " SCC"} -{"id": 32737, "token": "\u0120Gel", "merges": "\u0120G el", "raw_count": 1692, "count": 1692, "decode_str": " Gel"} -{"id": 20770, "token": "\u00d7\u013e", "merges": "\u00d7 \u013e", "raw_count": 1692, "count": 1692, "decode_str": "\u05dc"} -{"id": 35142, "token": "\u0120pancreas", "merges": "\u0120pan creas", "raw_count": 1693, "count": 1693, "decode_str": " pancreas"} -{"id": 44628, "token": "\u0120APR", "merges": "\u0120A PR", "raw_count": 1693, "count": 1693, "decode_str": " APR"} -{"id": 41343, "token": "\u0120SED", "merges": "\u0120S ED", "raw_count": 1693, "count": 1693, "decode_str": " SED"} -{"id": 48635, "token": "\u0120grasping", "merges": "\u0120grasp ing", "raw_count": 1694, "count": 1694, "decode_str": " grasping"} -{"id": 36025, "token": "\u0120liberals", "merges": "\u0120liber als", "raw_count": 1694, "count": 1694, "decode_str": " liberals"} -{"id": 36189, "token": "\u0120Mood", "merges": "\u0120M ood", "raw_count": 1444, "count": 1694, "decode_str": " Mood"} -{"id": 31910, "token": "\u0120Lay", "merges": "\u0120L ay", "raw_count": 1694, "count": 1694, "decode_str": " Lay"} -{"id": 7415, "token": ")^{", "merges": ") ^{", "raw_count": 1694, "count": 1694, "decode_str": ")^{"} -{"id": 20560, "token": "\u0120subunit", "merges": "\u0120sub unit", "raw_count": 1695, "count": 1695, "decode_str": " subunit"} -{"id": 50330, "token": "\u00e2\u012b\u00a7", "merges": "\u00e2\u012b \u00a7", "raw_count": 1695, "count": 1695, "decode_str": "\u2267"} -{"id": 35617, "token": "\u0120vacated", "merges": "\u0120vac ated", "raw_count": 1696, "count": 1696, "decode_str": " vacated"} -{"id": 22463, "token": "\u0120Robin", "merges": "\u0120Rob in", "raw_count": 1696, "count": 1696, "decode_str": " Robin"} -{"id": 37024, "token": "\u0120Huang", "merges": "\u0120Hu ang", "raw_count": 1696, "count": 1696, "decode_str": " Huang"} -{"id": 49627, "token": "\u0120Customers", "merges": "\u0120Custom ers", "raw_count": 1697, "count": 1697, "decode_str": " Customers"} -{"id": 48423, "token": "\u0120fiercely", "merges": "\u0120fierc ely", "raw_count": 1697, "count": 1697, "decode_str": " fiercely"} -{"id": 27936, "token": "\u0120Cris", "merges": "\u0120C ris", "raw_count": 623, "count": 1697, "decode_str": " Cris"} -{"id": 25870, "token": "\u0120Gent", "merges": "\u0120G ent", "raw_count": 1697, "count": 1697, "decode_str": " Gent"} -{"id": 26805, "token": "\u00c3\u00a1r", "merges": "\u00c3\u00a1 r", "raw_count": 1697, "count": 1697, "decode_str": "\u00e1r"} -{"id": 42721, "token": "\u0120vaccinated", "merges": "\u0120vacc inated", "raw_count": 1698, "count": 1698, "decode_str": " vaccinated"} -{"id": 40134, "token": "\u00da\u00af", "merges": "\u00da \u00af", "raw_count": 1698, "count": 1698, "decode_str": "\u06af"} -{"id": 39646, "token": "StackTrace", "merges": "Stack Trace", "raw_count": 1373, "count": 1699, "decode_str": "StackTrace"} -{"id": 22542, "token": "\u0120GeV", "merges": "\u0120Ge V", "raw_count": 1699, "count": 1699, "decode_str": " GeV"} -{"id": 13850, "token": "\u0120\u00ce\u00b3", "merges": "\u0120\u00ce \u00b3", "raw_count": 1488, "count": 1699, "decode_str": " \u03b3"} -{"id": 15403, "token": "\u0120membranes", "merges": "\u0120membr anes", "raw_count": 1700, "count": 1700, "decode_str": " membranes"} -{"id": 42925, "token": "astric", "merges": "ast ric", "raw_count": 1700, "count": 1700, "decode_str": "astric"} -{"id": 37776, "token": "\u0120resins", "merges": "\u0120res ins", "raw_count": 1701, "count": 1701, "decode_str": " resins"} -{"id": 33403, "token": "\u00e3\u0123\u00ab\u00e3\u0123\u00aa", "merges": "\u00e3\u0123\u00ab \u00e3\u0123\u00aa", "raw_count": 1701, "count": 1701, "decode_str": "\u306b\u306a"} -{"id": 21495, "token": "\u0120foreach", "merges": "\u0120fore ach", "raw_count": 1702, "count": 1702, "decode_str": " foreach"} -{"id": 41656, "token": "\u0120uncor", "merges": "\u0120unc or", "raw_count": 1702, "count": 1702, "decode_str": " uncor"} -{"id": 29176, "token": "\u0120Pf", "merges": "\u0120P f", "raw_count": 1702, "count": 1702, "decode_str": " Pf"} -{"id": 32199, "token": "\u0120bastard", "merges": "\u0120bast ard", "raw_count": 1703, "count": 1703, "decode_str": " bastard"} -{"id": 34290, "token": "ialysis", "merges": "ial ysis", "raw_count": 1703, "count": 1703, "decode_str": "ialysis"} -{"id": 27200, "token": "\u0120Were", "merges": "\u0120We re", "raw_count": 1703, "count": 1703, "decode_str": " Were"} -{"id": 39092, "token": "\u0120protagonist", "merges": "\u0120protagon ist", "raw_count": 1704, "count": 1704, "decode_str": " protagonist"} -{"id": 15757, "token": "\u0120Convention", "merges": "\u0120Con vention", "raw_count": 1515, "count": 1704, "decode_str": " Convention"} -{"id": 48228, "token": "\u0120premiered", "merges": "\u0120premie red", "raw_count": 1704, "count": 1704, "decode_str": " premiered"} -{"id": 37238, "token": "\u0120obsession", "merges": "\u0120ob session", "raw_count": 1704, "count": 1704, "decode_str": " obsession"} -{"id": 50007, "token": "\u0120soften", "merges": "\u0120soft en", "raw_count": 1704, "count": 1704, "decode_str": " soften"} -{"id": 54246, "token": "\u00e9\u0136\u00ba", "merges": "\u00e9\u0136 \u00ba", "raw_count": 1704, "count": 1704, "decode_str": "\u953a"} -{"id": 46469, "token": "\u0120stout", "merges": "\u0120st out", "raw_count": 1705, "count": 1705, "decode_str": " stout"} -{"id": 44914, "token": "\u0120pedig", "merges": "\u0120ped ig", "raw_count": 1705, "count": 1705, "decode_str": " pedig"} -{"id": 21138, "token": "\u0120Karl", "merges": "\u0120K arl", "raw_count": 1705, "count": 1705, "decode_str": " Karl"} -{"id": 35247, "token": "\u0120terrifying", "merges": "\u0120terr ifying", "raw_count": 1706, "count": 1706, "decode_str": " terrifying"} -{"id": 34308, "token": "\u0120dissenting", "merges": "\u0120dissent ing", "raw_count": 1706, "count": 1706, "decode_str": " dissenting"} -{"id": 37162, "token": "\u0120diameters", "merges": "\u0120di ameters", "raw_count": 1706, "count": 1706, "decode_str": " diameters"} -{"id": 49136, "token": "\u0120downhill", "merges": "\u0120down hill", "raw_count": 1706, "count": 1706, "decode_str": " downhill"} -{"id": 32621, "token": "\u0120torus", "merges": "\u0120tor us", "raw_count": 1706, "count": 1706, "decode_str": " torus"} -{"id": 28657, "token": "orems", "merges": "ore ms", "raw_count": 594, "count": 1706, "decode_str": "orems"} -{"id": 47999, "token": "\u0120Ling", "merges": "\u0120L ing", "raw_count": 1706, "count": 1706, "decode_str": " Ling"} -{"id": 42744, "token": "\u0120(;", "merges": "\u0120( ;", "raw_count": 1706, "count": 1706, "decode_str": " (;"} -{"id": 47865, "token": "\u0120sprinkle", "merges": "\u0120spr inkle", "raw_count": 1707, "count": 1707, "decode_str": " sprinkle"} -{"id": 48883, "token": "\u0120Tb", "merges": "\u0120T b", "raw_count": 1707, "count": 1707, "decode_str": " Tb"} -{"id": 43492, "token": "\u0120AGA", "merges": "\u0120A GA", "raw_count": 1708, "count": 1708, "decode_str": " AGA"} -{"id": 44636, "token": "\u0120draining", "merges": "\u0120dra ining", "raw_count": 1710, "count": 1710, "decode_str": " draining"} -{"id": 16590, "token": "\u0120Disney", "merges": "\u0120Dis ney", "raw_count": 1710, "count": 1710, "decode_str": " Disney"} -{"id": 48258, "token": "\u0120shrew", "merges": "\u0120sh rew", "raw_count": 1710, "count": 1710, "decode_str": " shrew"} -{"id": 49412, "token": "\u0120NAV", "merges": "\u0120N AV", "raw_count": 1710, "count": 1710, "decode_str": " NAV"} -{"id": 33557, "token": "\u00c3\u00aate", "merges": "\u00c3\u00aa te", "raw_count": 1711, "count": 1711, "decode_str": "\u00eate"} -{"id": 17419, "token": "\u0120Gordon", "merges": "\u0120G ordon", "raw_count": 1712, "count": 1712, "decode_str": " Gordon"} -{"id": 46590, "token": "\u0120nests", "merges": "\u0120n ests", "raw_count": 1712, "count": 1712, "decode_str": " nests"} -{"id": 44806, "token": "\u0120Gan", "merges": "\u0120G an", "raw_count": 1712, "count": 1712, "decode_str": " Gan"} -{"id": 10680, "token": "\u0120inhibitor", "merges": "\u0120inhib itor", "raw_count": 1713, "count": 1713, "decode_str": " inhibitor"} -{"id": 41982, "token": "\u0120bloggers", "merges": "\u0120blog gers", "raw_count": 1713, "count": 1713, "decode_str": " bloggers"} -{"id": 17771, "token": "\u0120Morris", "merges": "\u0120Mor ris", "raw_count": 1713, "count": 1713, "decode_str": " Morris"} -{"id": 38543, "token": "\u0120synergistic", "merges": "\u0120synerg istic", "raw_count": 1714, "count": 1714, "decode_str": " synergistic"} -{"id": 49328, "token": "\u0120ensembles", "merges": "\u0120en sembles", "raw_count": 1714, "count": 1714, "decode_str": " ensembles"} -{"id": 44999, "token": "\u0120slurry", "merges": "\u0120sl urry", "raw_count": 1714, "count": 1714, "decode_str": " slurry"} -{"id": 40530, "token": "\u00d1\u0139", "merges": "\u00d1 \u0139", "raw_count": 1714, "count": 1714, "decode_str": "\u0457"} -{"id": 40943, "token": "\u0120bowls", "merges": "\u0120bow ls", "raw_count": 1715, "count": 1715, "decode_str": " bowls"} -{"id": 22596, "token": "\u0120opio", "merges": "\u0120op io", "raw_count": 50, "count": 1715, "decode_str": " opio"} -{"id": 29895, "token": "\u0120ASD", "merges": "\u0120A SD", "raw_count": 1715, "count": 1715, "decode_str": " ASD"} -{"id": 50063, "token": "\u0120admirable", "merges": "\u0120adm irable", "raw_count": 1716, "count": 1716, "decode_str": " admirable"} -{"id": 33871, "token": "\u0120cinnamon", "merges": "\u0120c innamon", "raw_count": 1716, "count": 1716, "decode_str": " cinnamon"} -{"id": 19006, "token": "\u0120urinary", "merges": "\u0120ur inary", "raw_count": 1716, "count": 1716, "decode_str": " urinary"} -{"id": 47783, "token": "\u0120Sword", "merges": "\u0120S word", "raw_count": 1716, "count": 1716, "decode_str": " Sword"} -{"id": 18749, "token": "\u0120Baker", "merges": "\u0120B aker", "raw_count": 1716, "count": 1716, "decode_str": " Baker"} -{"id": 45238, "token": "\u0120palate", "merges": "\u0120pal ate", "raw_count": 1717, "count": 1717, "decode_str": " palate"} -{"id": 50228, "token": "izability", "merges": "iz ability", "raw_count": 1718, "count": 1718, "decode_str": "izability"} -{"id": 42282, "token": "\u0120slips", "merges": "\u0120sl ips", "raw_count": 1718, "count": 1718, "decode_str": " slips"} -{"id": 39997, "token": "chte", "merges": "ch te", "raw_count": 1718, "count": 1718, "decode_str": "chte"} -{"id": 25632, "token": "\u0120Experimental", "merges": "\u0120Exper imental", "raw_count": 1719, "count": 1719, "decode_str": " Experimental"} -{"id": 39786, "token": "\u0120agitation", "merges": "\u0120ag itation", "raw_count": 1720, "count": 1720, "decode_str": " agitation"} -{"id": 22231, "token": "\u0120CONDITION", "merges": "\u0120CON DITION", "raw_count": 1328, "count": 1721, "decode_str": " CONDITION"} -{"id": 41472, "token": "\u0120painters", "merges": "\u0120pain ters", "raw_count": 1721, "count": 1721, "decode_str": " painters"} -{"id": 40411, "token": "orescent", "merges": "ores cent", "raw_count": 1721, "count": 1721, "decode_str": "orescent"} -{"id": 17405, "token": "ollary", "merges": "oll ary", "raw_count": 193, "count": 1721, "decode_str": "ollary"} -{"id": 7230, "token": "\u0120Flor", "merges": "\u0120Fl or", "raw_count": 1136, "count": 1721, "decode_str": " Flor"} -{"id": 42279, "token": "imide", "merges": "im ide", "raw_count": 1722, "count": 1722, "decode_str": "imide"} -{"id": 30827, "token": "\u0120Sett", "merges": "\u0120S ett", "raw_count": 1003, "count": 1723, "decode_str": " Sett"} -{"id": 32908, "token": "\u0120thermodynamic", "merges": "\u0120therm odynamic", "raw_count": 1724, "count": 1724, "decode_str": " thermodynamic"} -{"id": 37175, "token": "\u0120richness", "merges": "\u0120rich ness", "raw_count": 1724, "count": 1724, "decode_str": " richness"} -{"id": 27104, "token": "\u0120Darwin", "merges": "\u0120Dar win", "raw_count": 1724, "count": 1724, "decode_str": " Darwin"} -{"id": 30759, "token": "\u0120Medal", "merges": "\u0120Med al", "raw_count": 1724, "count": 1724, "decode_str": " Medal"} -{"id": 19544, "token": "\u0120Cohen", "merges": "\u0120Co hen", "raw_count": 1724, "count": 1724, "decode_str": " Cohen"} -{"id": 33428, "token": "\u0120adulthood", "merges": "\u0120adul thood", "raw_count": 1725, "count": 1725, "decode_str": " adulthood"} -{"id": 35524, "token": "\u0120obsessed", "merges": "\u0120obs essed", "raw_count": 1725, "count": 1725, "decode_str": " obsessed"} -{"id": 39670, "token": "\u0120oft", "merges": "\u0120of t", "raw_count": 1725, "count": 1725, "decode_str": " oft"} -{"id": 36719, "token": "\u0120characterised", "merges": "\u0120character ised", "raw_count": 1726, "count": 1726, "decode_str": " characterised"} -{"id": 42189, "token": "\u0120intensely", "merges": "\u0120intens ely", "raw_count": 1726, "count": 1726, "decode_str": " intensely"} -{"id": 29254, "token": "\u0120critique", "merges": "\u0120crit ique", "raw_count": 1726, "count": 1726, "decode_str": " critique"} -{"id": 16499, "token": "ylation", "merges": "yl ation", "raw_count": 1726, "count": 1726, "decode_str": "ylation"} -{"id": 37359, "token": "\u0120disastrous", "merges": "\u0120disast rous", "raw_count": 1727, "count": 1727, "decode_str": " disastrous"} -{"id": 25668, "token": "\u0120anesthesia", "merges": "\u0120anest hesia", "raw_count": 1727, "count": 1727, "decode_str": " anesthesia"} -{"id": 36521, "token": "\u0120awhile", "merges": "\u0120a while", "raw_count": 1727, "count": 1727, "decode_str": " awhile"} -{"id": 25806, "token": "\u0120finely", "merges": "\u0120fin ely", "raw_count": 1727, "count": 1727, "decode_str": " finely"} -{"id": 49779, "token": "\u0120sparing", "merges": "\u0120sp aring", "raw_count": 1728, "count": 1728, "decode_str": " sparing"} -{"id": 13236, "token": "\u0120teasp", "merges": "\u0120te asp", "raw_count": 5, "count": 1729, "decode_str": " teasp"} -{"id": 24471, "token": "\u0120Privacy", "merges": "\u0120Priv acy", "raw_count": 1730, "count": 1730, "decode_str": " Privacy"} -{"id": 19520, "token": "\u0120Bishop", "merges": "\u0120B ishop", "raw_count": 1730, "count": 1730, "decode_str": " Bishop"} -{"id": 21200, "token": "olytic", "merges": "ol ytic", "raw_count": 1730, "count": 1730, "decode_str": "olytic"} -{"id": 30493, "token": "athione", "merges": "ath ione", "raw_count": 1463, "count": 1731, "decode_str": "athione"} -{"id": 46853, "token": "\u0120exclus", "merges": "\u0120ex clus", "raw_count": 1731, "count": 1731, "decode_str": " exclus"} -{"id": 15562, "token": "\u0120Liber", "merges": "\u0120L iber", "raw_count": 428, "count": 1731, "decode_str": " Liber"} -{"id": 43915, "token": "\u0120quir", "merges": "\u0120qu ir", "raw_count": 1731, "count": 1731, "decode_str": " quir"} -{"id": 30453, "token": "\u0120drawbacks", "merges": "\u0120draw backs", "raw_count": 1732, "count": 1732, "decode_str": " drawbacks"} -{"id": 45086, "token": "\u0120thinkers", "merges": "\u0120think ers", "raw_count": 1732, "count": 1732, "decode_str": " thinkers"} -{"id": 16542, "token": "\u0120comme", "merges": "\u0120comm e", "raw_count": 1732, "count": 1732, "decode_str": " comme"} -{"id": 36069, "token": "\u0120fuer", "merges": "\u0120f uer", "raw_count": 1732, "count": 1732, "decode_str": " fuer"} -{"id": 33012, "token": "\u0120metaphys", "merges": "\u0120met aphys", "raw_count": 895, "count": 1733, "decode_str": " metaphys"} -{"id": 4535, "token": "varphi", "merges": "var phi", "raw_count": 1733, "count": 1733, "decode_str": "varphi"} -{"id": 23458, "token": "\u0120dilution", "merges": "\u0120dil ution", "raw_count": 1734, "count": 1734, "decode_str": " dilution"} -{"id": 48767, "token": "\u0120ICP", "merges": "\u0120I CP", "raw_count": 1734, "count": 1734, "decode_str": " ICP"} -{"id": 46401, "token": "\\+", "merges": "\\ +", "raw_count": 1734, "count": 1734, "decode_str": "\\+"} -{"id": 37576, "token": "\u0120assaulted", "merges": "\u0120assault ed", "raw_count": 1735, "count": 1735, "decode_str": " assaulted"} -{"id": 49726, "token": "\u0120sails", "merges": "\u0120sa ils", "raw_count": 1735, "count": 1735, "decode_str": " sails"} -{"id": 41465, "token": "\u0120contractions", "merges": "\u0120contra ctions", "raw_count": 1736, "count": 1736, "decode_str": " contractions"} -{"id": 30208, "token": "\u0120surgeons", "merges": "\u0120surge ons", "raw_count": 1736, "count": 1736, "decode_str": " surgeons"} -{"id": 23842, "token": "\u0120anatom", "merges": "\u0120an atom", "raw_count": 399, "count": 1736, "decode_str": " anatom"} -{"id": 43567, "token": "\u0120jaws", "merges": "\u0120j aws", "raw_count": 1736, "count": 1736, "decode_str": " jaws"} -{"id": 15104, "token": "\u0120", "merges": "\u0120-- >", "raw_count": 60844, "count": 60844, "decode_str": " -->"} -{"id": 16762, "token": "ivities", "merges": "iv ities", "raw_count": 59699, "count": 60860, "decode_str": "ivities"} -{"id": 26573, "token": "ATOR", "merges": "AT OR", "raw_count": 60872, "count": 60872, "decode_str": "ATOR"} -{"id": 15880, "token": "\u0120lessons", "merges": "\u0120less ons", "raw_count": 60873, "count": 60873, "decode_str": " lessons"} -{"id": 13384, "token": "\u0120pub", "merges": "\u0120p ub", "raw_count": 60873, "count": 60873, "decode_str": " pub"} -{"id": 6272, "token": "\u0120Are", "merges": "\u0120A re", "raw_count": 43709, "count": 60882, "decode_str": " Are"} -{"id": 29123, "token": "\u0120committees", "merges": "\u0120commit tees", "raw_count": 60887, "count": 60887, "decode_str": " committees"} -{"id": 35885, "token": "rift", "merges": "r ift", "raw_count": 60901, "count": 60901, "decode_str": "rift"} -{"id": 46236, "token": "NORM", "merges": "N ORM", "raw_count": 60908, "count": 60908, "decode_str": "NORM"} -{"id": 32466, "token": "INC", "merges": "IN C", "raw_count": 60915, "count": 60915, "decode_str": "INC"} -{"id": 29596, "token": "Detail", "merges": "Det ail", "raw_count": 60922, "count": 60922, "decode_str": "Detail"} -{"id": 6680, "token": "\u0120battle", "merges": "\u0120b attle", "raw_count": 56772, "count": 60926, "decode_str": " battle"} -{"id": 26998, "token": "Visible", "merges": "Vis ible", "raw_count": 60946, "count": 60946, "decode_str": "Visible"} -{"id": 24057, "token": "Extension", "merges": "Ext ension", "raw_count": 60972, "count": 60972, "decode_str": "Extension"} -{"id": 20771, "token": "ailability", "merges": "ail ability", "raw_count": 2585, "count": 60977, "decode_str": "ailability"} -{"id": 13918, "token": "\u01201950", "merges": "\u012019 50", "raw_count": 60985, "count": 60985, "decode_str": " 1950"} -{"id": 19676, "token": "\u0120authentication", "merges": "\u0120authentic ation", "raw_count": 61006, "count": 61006, "decode_str": " authentication"} -{"id": 33987, "token": "LENGTH", "merges": "LEN GTH", "raw_count": 61010, "count": 61010, "decode_str": "LENGTH"} -{"id": 33551, "token": "\u0120Delete", "merges": "\u0120De lete", "raw_count": 61028, "count": 61028, "decode_str": " Delete"} -{"id": 33303, "token": "\u0120zeros", "merges": "\u0120z eros", "raw_count": 61034, "count": 61034, "decode_str": " zeros"} -{"id": 13496, "token": "\u0120equipped", "merges": "\u0120equ ipped", "raw_count": 61046, "count": 61046, "decode_str": " equipped"} -{"id": 13716, "token": "\u0120rating", "merges": "\u0120r ating", "raw_count": 61047, "count": 61047, "decode_str": " rating"} -{"id": 37771, "token": "autom", "merges": "aut om", "raw_count": 61048, "count": 61048, "decode_str": "autom"} -{"id": 34836, "token": "Transfer", "merges": "Trans fer", "raw_count": 61056, "count": 61056, "decode_str": "Transfer"} -{"id": 12647, "token": "\u0120constitute", "merges": "\u0120constit ute", "raw_count": 61061, "count": 61061, "decode_str": " constitute"} -{"id": 39442, "token": "Canvas", "merges": "Can vas", "raw_count": 61064, "count": 61064, "decode_str": "Canvas"} -{"id": 13373, "token": "\u0120matched", "merges": "\u0120mat ched", "raw_count": 61067, "count": 61067, "decode_str": " matched"} -{"id": 36518, "token": "Catal", "merges": "C atal", "raw_count": 61073, "count": 61073, "decode_str": "Catal"} -{"id": 27073, "token": "oba", "merges": "ob a", "raw_count": 61094, "count": 61094, "decode_str": "oba"} -{"id": 11196, "token": "\u0120closing", "merges": "\u0120clos ing", "raw_count": 61104, "count": 61104, "decode_str": " closing"} -{"id": 35733, "token": "\u0120urges", "merges": "\u0120ur ges", "raw_count": 61117, "count": 61117, "decode_str": " urges"} -{"id": 7674, "token": "\u0120cab", "merges": "\u0120c ab", "raw_count": 22895, "count": 61130, "decode_str": " cab"} -{"id": 8680, "token": "\u0120feedback", "merges": "\u0120feed back", "raw_count": 61153, "count": 61153, "decode_str": " feedback"} -{"id": 19579, "token": "sensitive", "merges": "sens itive", "raw_count": 61157, "count": 61157, "decode_str": "sensitive"} -{"id": 14696, "token": "bullet", "merges": "bul let", "raw_count": 61172, "count": 61172, "decode_str": "bullet"} -{"id": 41492, "token": "\u00e7\u0131\u00be", "merges": "\u00e7\u0131 \u00be", "raw_count": 61172, "count": 61172, "decode_str": "\u73fe"} -{"id": 54458, "token": "\u00e9\u00a2\u00a1", "merges": "\u00e9\u00a2 \u00a1", "raw_count": 61179, "count": 61179, "decode_str": "\u98a1"} -{"id": 8635, "token": "aft", "merges": "a ft", "raw_count": 34378, "count": 61186, "decode_str": "aft"} -{"id": 12941, "token": "\u0120visits", "merges": "\u0120vis its", "raw_count": 61192, "count": 61192, "decode_str": " visits"} -{"id": 46204, "token": "Rick", "merges": "R ick", "raw_count": 61193, "count": 61193, "decode_str": "Rick"} -{"id": 9242, "token": "\u0120SU", "merges": "\u0120S U", "raw_count": 48683, "count": 61194, "decode_str": " SU"} -{"id": 43330, "token": "mj", "merges": "m j", "raw_count": 61196, "count": 61196, "decode_str": "mj"} -{"id": 29061, "token": "wheel", "merges": "whe el", "raw_count": 61214, "count": 61214, "decode_str": "wheel"} -{"id": 7419, "token": "\u0120apart", "merges": "\u0120ap art", "raw_count": 37929, "count": 61215, "decode_str": " apart"} -{"id": 15026, "token": "\u0120amend", "merges": "\u0120am end", "raw_count": 19087, "count": 61225, "decode_str": " amend"} -{"id": 24305, "token": "Ther", "merges": "T her", "raw_count": 51701, "count": 61231, "decode_str": "Ther"} -{"id": 7360, "token": "\u0120pod", "merges": "\u0120p od", "raw_count": 41513, "count": 61233, "decode_str": " pod"} -{"id": 13120, "token": "\u0120transportation", "merges": "\u0120transport ation", "raw_count": 61240, "count": 61240, "decode_str": " transportation"} -{"id": 30618, "token": "\u0120undertake", "merges": "\u0120undert ake", "raw_count": 61245, "count": 61245, "decode_str": " undertake"} -{"id": 8761, "token": "\u0120profession", "merges": "\u0120prof ession", "raw_count": 15028, "count": 61259, "decode_str": " profession"} -{"id": 25142, "token": "\u0120iterations", "merges": "\u0120iter ations", "raw_count": 61265, "count": 61265, "decode_str": " iterations"} -{"id": 5026, "token": "\u0120thick", "merges": "\u0120th ick", "raw_count": 21605, "count": 61271, "decode_str": " thick"} -{"id": 23433, "token": "Question", "merges": "Qu estion", "raw_count": 61273, "count": 61273, "decode_str": "Question"} -{"id": 13728, "token": "\u0120Ten", "merges": "\u0120T en", "raw_count": 61277, "count": 61277, "decode_str": " Ten"} -{"id": 4629, "token": "kay", "merges": "k ay", "raw_count": 29456, "count": 61328, "decode_str": "kay"} -{"id": 6973, "token": "\u0120outcomes", "merges": "\u0120out comes", "raw_count": 61335, "count": 61335, "decode_str": " outcomes"} -{"id": 38546, "token": "ACTION", "merges": "A CTION", "raw_count": 61349, "count": 61349, "decode_str": "ACTION"} -{"id": 43355, "token": "authors", "merges": "aut hors", "raw_count": 61355, "count": 61355, "decode_str": "authors"} -{"id": 29097, "token": "pressure", "merges": "press ure", "raw_count": 61356, "count": 61356, "decode_str": "pressure"} -{"id": 33539, "token": "IPV", "merges": "IP V", "raw_count": 61357, "count": 61357, "decode_str": "IPV"} -{"id": 30699, "token": "intent", "merges": "int ent", "raw_count": 61376, "count": 61376, "decode_str": "intent"} -{"id": 8584, "token": "uable", "merges": "u able", "raw_count": 6479, "count": 61384, "decode_str": "uable"} -{"id": 15055, "token": "eda", "merges": "ed a", "raw_count": 56985, "count": 61389, "decode_str": "eda"} -{"id": 9472, "token": "\u0120Color", "merges": "\u0120Col or", "raw_count": 61114, "count": 61405, "decode_str": " Color"} -{"id": 51258, "token": "\u00e5\u00a2\u0122", "merges": "\u00e5\u00a2 \u0122", "raw_count": 61412, "count": 61412, "decode_str": "\u5880"} -{"id": 19711, "token": "Age", "merges": "A ge", "raw_count": 61423, "count": 61423, "decode_str": "Age"} -{"id": 15077, "token": "oren", "merges": "ore n", "raw_count": 60190, "count": 61425, "decode_str": "oren"} -{"id": 24790, "token": "URN", "merges": "UR N", "raw_count": 32966, "count": 61456, "decode_str": "URN"} -{"id": 15720, "token": "written", "merges": "wr itten", "raw_count": 57900, "count": 61459, "decode_str": "written"} -{"id": 9048, "token": "reatment", "merges": "reat ment", "raw_count": 6999, "count": 61466, "decode_str": "reatment"} -{"id": 11722, "token": "urable", "merges": "ur able", "raw_count": 30083, "count": 61482, "decode_str": "urable"} -{"id": 13672, "token": "merce", "merges": "mer ce", "raw_count": 31793, "count": 61484, "decode_str": "merce"} -{"id": 47508, "token": "937", "merges": "9 37", "raw_count": 61491, "count": 61491, "decode_str": "937"} -{"id": 5783, "token": "\u0120confirmed", "merges": "\u0120conf irmed", "raw_count": 61492, "count": 61492, "decode_str": " confirmed"} -{"id": 49708, "token": "scaling", "merges": "sc aling", "raw_count": 61500, "count": 61500, "decode_str": "scaling"} -{"id": 32382, "token": "CAG", "merges": "C AG", "raw_count": 61502, "count": 61502, "decode_str": "CAG"} -{"id": 9570, "token": "isor", "merges": "is or", "raw_count": 32111, "count": 61512, "decode_str": "isor"} -{"id": 49518, "token": "Stone", "merges": "St one", "raw_count": 61535, "count": 61535, "decode_str": "Stone"} -{"id": 42596, "token": "1021", "merges": "10 21", "raw_count": 61535, "count": 61535, "decode_str": "1021"} -{"id": 37940, "token": "retval", "merges": "ret val", "raw_count": 61562, "count": 61562, "decode_str": "retval"} -{"id": 30043, "token": "icky", "merges": "ick y", "raw_count": 61565, "count": 61565, "decode_str": "icky"} -{"id": 39430, "token": "Heart", "merges": "He art", "raw_count": 61578, "count": 61578, "decode_str": "Heart"} -{"id": 44942, "token": "TK", "merges": "T K", "raw_count": 61581, "count": 61581, "decode_str": "TK"} -{"id": 40849, "token": "Ko", "merges": "K o", "raw_count": 61592, "count": 61592, "decode_str": "Ko"} -{"id": 28334, "token": "CoV", "merges": "Co V", "raw_count": 61594, "count": 61594, "decode_str": "CoV"} -{"id": 12027, "token": "\u0120dispute", "merges": "\u0120disput e", "raw_count": 61611, "count": 61611, "decode_str": " dispute"} -{"id": 10526, "token": "years", "merges": "year s", "raw_count": 61613, "count": 61613, "decode_str": "years"} -{"id": 35061, "token": "\u00ea\u00b0\u0122", "merges": "\u00ea\u00b0 \u0122", "raw_count": 61634, "count": 61634, "decode_str": "\uac00"} -{"id": 7501, "token": "\u0120warrant", "merges": "\u0120war rant", "raw_count": 37312, "count": 61638, "decode_str": " warrant"} -{"id": 9195, "token": "\u0120buildings", "merges": "\u0120build ings", "raw_count": 61650, "count": 61650, "decode_str": " buildings"} -{"id": 14480, "token": "\u0120merc", "merges": "\u0120m erc", "raw_count": 31448, "count": 61651, "decode_str": " merc"} -{"id": 16480, "token": "\u0120Account", "merges": "\u0120Acc ount", "raw_count": 61655, "count": 61655, "decode_str": " Account"} -{"id": 6923, "token": "\u0120jump", "merges": "\u0120j ump", "raw_count": 45173, "count": 61659, "decode_str": " jump"} -{"id": 38841, "token": "bz", "merges": "b z", "raw_count": 61662, "count": 61662, "decode_str": "bz"} -{"id": 15651, "token": "FFFF", "merges": "FF FF", "raw_count": 33278, "count": 61670, "decode_str": "FFFF"} -{"id": 22903, "token": "Die", "merges": "D ie", "raw_count": 61679, "count": 61679, "decode_str": "Die"} -{"id": 8653, "token": "\u0120displayed", "merges": "\u0120display ed", "raw_count": 61697, "count": 61697, "decode_str": " displayed"} -{"id": 14304, "token": "\u01201978", "merges": "\u012019 78", "raw_count": 61697, "count": 61697, "decode_str": " 1978"} -{"id": 38755, "token": "dos", "merges": "d os", "raw_count": 61701, "count": 61701, "decode_str": "dos"} -{"id": 30883, "token": "STER", "merges": "ST ER", "raw_count": 61717, "count": 61717, "decode_str": "STER"} -{"id": 12815, "token": "abbit", "merges": "ab bit", "raw_count": 21703, "count": 61725, "decode_str": "abbit"} -{"id": 9560, "token": "\u0120crucial", "merges": "\u0120cru cial", "raw_count": 61729, "count": 61729, "decode_str": " crucial"} -{"id": 18946, "token": "rena", "merges": "ren a", "raw_count": 59719, "count": 61742, "decode_str": "rena"} -{"id": 21689, "token": "chair", "merges": "ch air", "raw_count": 56590, "count": 61750, "decode_str": "chair"} -{"id": 3419, "token": "\u0120Ag", "merges": "\u0120A g", "raw_count": 11652, "count": 61754, "decode_str": " Ag"} -{"id": 24560, "token": "oks", "merges": "ok s", "raw_count": 61759, "count": 61759, "decode_str": "oks"} -{"id": 45538, "token": "LH", "merges": "L H", "raw_count": 61762, "count": 61762, "decode_str": "LH"} -{"id": 34548, "token": "OSE", "merges": "O SE", "raw_count": 61768, "count": 61768, "decode_str": "OSE"} -{"id": 2545, "token": "\u0120Eng", "merges": "\u0120E ng", "raw_count": 4981, "count": 61777, "decode_str": " Eng"} -{"id": 28784, "token": "COUNT", "merges": "C OUNT", "raw_count": 61783, "count": 61783, "decode_str": "COUNT"} -{"id": 6944, "token": "\u0120underlying", "merges": "\u0120under lying", "raw_count": 61795, "count": 61795, "decode_str": " underlying"} -{"id": 21517, "token": "\u0120freed", "merges": "\u0120fre ed", "raw_count": 8197, "count": 61796, "decode_str": " freed"} -{"id": 31826, "token": "Pair", "merges": "P air", "raw_count": 61813, "count": 61813, "decode_str": "Pair"} -{"id": 12781, "token": "bec", "merges": "b ec", "raw_count": 55850, "count": 61813, "decode_str": "bec"} -{"id": 27410, "token": "rength", "merges": "reng th", "raw_count": 15361, "count": 61829, "decode_str": "rength"} -{"id": 44023, "token": "ichael", "merges": "ich ael", "raw_count": 61832, "count": 61832, "decode_str": "ichael"} -{"id": 24293, "token": "pex", "merges": "pe x", "raw_count": 54972, "count": 61837, "decode_str": "pex"} -{"id": 6747, "token": "\u0120neither", "merges": "\u0120ne ither", "raw_count": 61838, "count": 61838, "decode_str": " neither"} -{"id": 3012, "token": "\u0120significantly", "merges": "\u0120significant ly", "raw_count": 61845, "count": 61845, "decode_str": " significantly"} -{"id": 17740, "token": "ENCE", "merges": "EN CE", "raw_count": 61369, "count": 61893, "decode_str": "ENCE"} -{"id": 28948, "token": "yet", "merges": "y et", "raw_count": 61895, "count": 61895, "decode_str": "yet"} -{"id": 43771, "token": "099", "merges": "0 99", "raw_count": 61905, "count": 61905, "decode_str": "099"} -{"id": 3876, "token": "\u00c3\u00b3n", "merges": "\u00c3\u00b3 n", "raw_count": 10226, "count": 61911, "decode_str": "\u00f3n"} -{"id": 10171, "token": "\u0120involvement", "merges": "\u0120involve ment", "raw_count": 61920, "count": 61920, "decode_str": " involvement"} -{"id": 19835, "token": "gon", "merges": "g on", "raw_count": 21613, "count": 61938, "decode_str": "gon"} -{"id": 19743, "token": "\u0120Simple", "merges": "\u0120Sim ple", "raw_count": 61947, "count": 61947, "decode_str": " Simple"} -{"id": 18483, "token": "Identifier", "merges": "Ident ifier", "raw_count": 61951, "count": 61951, "decode_str": "Identifier"} -{"id": 19265, "token": "\u0120backward", "merges": "\u0120back ward", "raw_count": 61954, "count": 61954, "decode_str": " backward"} -{"id": 40614, "token": "Ubuntu", "merges": "U buntu", "raw_count": 61959, "count": 61959, "decode_str": "Ubuntu"} -{"id": 44140, "token": "\u012a\u013a", "merges": "\u012a \u013a", "raw_count": 61967, "count": 61967, "decode_str": "\ufffd\ufffd"} -{"id": 12087, "token": "\u0120geometry", "merges": "\u0120ge ometry", "raw_count": 61970, "count": 61970, "decode_str": " geometry"} -{"id": 34795, "token": "\u0120cb", "merges": "\u0120c b", "raw_count": 61970, "count": 61970, "decode_str": " cb"} -{"id": 5686, "token": "\u0120born", "merges": "\u0120b orn", "raw_count": 61981, "count": 61981, "decode_str": " born"} -{"id": 14276, "token": "ordon", "merges": "ord on", "raw_count": 14342, "count": 61991, "decode_str": "ordon"} -{"id": 25129, "token": "ICAL", "merges": "IC AL", "raw_count": 62006, "count": 62006, "decode_str": "ICAL"} -{"id": 6770, "token": "alian", "merges": "al ian", "raw_count": 49239, "count": 62007, "decode_str": "alian"} -{"id": 5172, "token": "\u0120wa", "merges": "\u0120w a", "raw_count": 23328, "count": 62017, "decode_str": " wa"} -{"id": 14734, "token": "rus", "merges": "r us", "raw_count": 60191, "count": 62020, "decode_str": "rus"} -{"id": 15633, "token": "Background", "merges": "Back ground", "raw_count": 62021, "count": 62021, "decode_str": "Background"} -{"id": 3975, "token": "\u0120Art", "merges": "\u0120A rt", "raw_count": 20839, "count": 62028, "decode_str": " Art"} -{"id": 33993, "token": "Average", "merges": "A verage", "raw_count": 62031, "count": 62031, "decode_str": "Average"} -{"id": 23875, "token": "Sym", "merges": "S ym", "raw_count": 62047, "count": 62047, "decode_str": "Sym"} -{"id": 34498, "token": "needed", "merges": "ne eded", "raw_count": 62058, "count": 62058, "decode_str": "needed"} -{"id": 53728, "token": "\u00e8\u00a2\u00aa", "merges": "\u00e8\u00a2 \u00aa", "raw_count": 62068, "count": 62068, "decode_str": "\u88aa"} -{"id": 37585, "token": "minor", "merges": "min or", "raw_count": 62086, "count": 62086, "decode_str": "minor"} -{"id": 8884, "token": "\u0120declared", "merges": "\u0120decl ared", "raw_count": 62087, "count": 62087, "decode_str": " declared"} -{"id": 21007, "token": "\u0120urgent", "merges": "\u0120ur gent", "raw_count": 62090, "count": 62090, "decode_str": " urgent"} -{"id": 28905, "token": ")<", "merges": ") <", "raw_count": 62102, "count": 62102, "decode_str": ")<"} -{"id": 7786, "token": "\u0120\u00d1", "merges": "\u0120 \u00d1", "raw_count": 1855, "count": 62103, "decode_str": " \ufffd"} -{"id": 24169, "token": "\u00eb\u012c\u0136", "merges": "\u00eb\u012c \u0136", "raw_count": 62114, "count": 62114, "decode_str": "\ub294"} -{"id": 28293, "token": "catch", "merges": "c atch", "raw_count": 62116, "count": 62116, "decode_str": "catch"} -{"id": 11299, "token": "\u01201983", "merges": "\u012019 83", "raw_count": 62132, "count": 62132, "decode_str": " 1983"} -{"id": 9118, "token": "\u0120vertical", "merges": "\u0120vert ical", "raw_count": 62141, "count": 62141, "decode_str": " vertical"} -{"id": 44004, "token": "LDL", "merges": "L DL", "raw_count": 62143, "count": 62143, "decode_str": "LDL"} -{"id": 20942, "token": "\u0120warnings", "merges": "\u0120warn ings", "raw_count": 62148, "count": 62148, "decode_str": " warnings"} -{"id": 24159, "token": "performance", "merges": "per formance", "raw_count": 62153, "count": 62153, "decode_str": "performance"} -{"id": 48598, "token": "Moh", "merges": "M oh", "raw_count": 62158, "count": 62158, "decode_str": "Moh"} -{"id": 14915, "token": "larg", "merges": "l arg", "raw_count": 9752, "count": 62171, "decode_str": "larg"} -{"id": 3506, "token": "\u0120Ab", "merges": "\u0120A b", "raw_count": 24561, "count": 62174, "decode_str": " Ab"} -{"id": 9579, "token": "\u0120degrad", "merges": "\u0120de grad", "raw_count": 28656, "count": 62190, "decode_str": " degrad"} -{"id": 5728, "token": "\u0120collected", "merges": "\u0120col lected", "raw_count": 62201, "count": 62201, "decode_str": " collected"} -{"id": 45335, "token": "TU", "merges": "T U", "raw_count": 62222, "count": 62222, "decode_str": "TU"} -{"id": 47302, "token": "989", "merges": "9 89", "raw_count": 62228, "count": 62228, "decode_str": "989"} -{"id": 36378, "token": "Zhang", "merges": "Z hang", "raw_count": 62247, "count": 62247, "decode_str": "Zhang"} -{"id": 10414, "token": "\u0120references", "merges": "\u0120re ferences", "raw_count": 62253, "count": 62253, "decode_str": " references"} -{"id": 34181, "token": "REC", "merges": "RE C", "raw_count": 62273, "count": 62273, "decode_str": "REC"} -{"id": 4578, "token": "================================", "merges": "================ ================", "raw_count": 24848, "count": 62283, "decode_str": "================================"} -{"id": 4962, "token": "\u0120died", "merges": "\u0120d ied", "raw_count": 62283, "count": 62283, "decode_str": " died"} -{"id": 11818, "token": "cies", "merges": "c ies", "raw_count": 5797, "count": 62294, "decode_str": "cies"} -{"id": 6858, "token": "\u0120baby", "merges": "\u0120bab y", "raw_count": 62343, "count": 62343, "decode_str": " baby"} -{"id": 49029, "token": "Cha", "merges": "Ch a", "raw_count": 62350, "count": 62350, "decode_str": "Cha"} -{"id": 12855, "token": "vir", "merges": "v ir", "raw_count": 59745, "count": 62353, "decode_str": "vir"} -{"id": 39685, "token": "Ven", "merges": "V en", "raw_count": 62354, "count": 62354, "decode_str": "Ven"} -{"id": 32232, "token": "ressor", "merges": "ress or", "raw_count": 62366, "count": 62366, "decode_str": "ressor"} -{"id": 42125, "token": "\u0120Django", "merges": "\u0120D jango", "raw_count": 62371, "count": 62371, "decode_str": " Django"} -{"id": 18169, "token": "LIB", "merges": "L IB", "raw_count": 47989, "count": 62379, "decode_str": "LIB"} -{"id": 6138, "token": "\u0120announced", "merges": "\u0120announ ced", "raw_count": 62388, "count": 62388, "decode_str": " announced"} -{"id": 11259, "token": "\u0120orientation", "merges": "\u0120orient ation", "raw_count": 62396, "count": 62396, "decode_str": " orientation"} -{"id": 22019, "token": "estine", "merges": "est ine", "raw_count": 60779, "count": 62416, "decode_str": "estine"} -{"id": 46227, "token": "CHA", "merges": "CH A", "raw_count": 62417, "count": 62417, "decode_str": "CHA"} -{"id": 18064, "token": "ivan", "merges": "iv an", "raw_count": 25800, "count": 62441, "decode_str": "ivan"} -{"id": 10263, "token": "\u0120drawing", "merges": "\u0120draw ing", "raw_count": 62466, "count": 62466, "decode_str": " drawing"} -{"id": 10268, "token": "\u0120facing", "merges": "\u0120fac ing", "raw_count": 62467, "count": 62467, "decode_str": " facing"} -{"id": 5512, "token": "\u0120approximately", "merges": "\u0120approxim ately", "raw_count": 62470, "count": 62470, "decode_str": " approximately"} -{"id": 19531, "token": "igr", "merges": "ig r", "raw_count": 47844, "count": 62470, "decode_str": "igr"} -{"id": 36073, "token": "constructor", "merges": "construct or", "raw_count": 62472, "count": 62472, "decode_str": "constructor"} -{"id": 13049, "token": "thur", "merges": "th ur", "raw_count": 7264, "count": 62481, "decode_str": "thur"} -{"id": 32765, "token": "\u0120dd", "merges": "\u0120d d", "raw_count": 62482, "count": 62482, "decode_str": " dd"} -{"id": 22949, "token": "CHECK", "merges": "C HECK", "raw_count": 62505, "count": 62505, "decode_str": "CHECK"} -{"id": 42525, "token": "MARK", "merges": "M ARK", "raw_count": 62506, "count": 62506, "decode_str": "MARK"} -{"id": 34615, "token": "\u0120strengthened", "merges": "\u0120strengthen ed", "raw_count": 62507, "count": 62507, "decode_str": " strengthened"} -{"id": 17787, "token": "\u0120marine", "merges": "\u0120mar ine", "raw_count": 62507, "count": 62507, "decode_str": " marine"} -{"id": 14668, "token": "racted", "merges": "ract ed", "raw_count": 55915, "count": 62507, "decode_str": "racted"} -{"id": 34112, "token": "\u0120turkey", "merges": "\u0120tur key", "raw_count": 62521, "count": 62521, "decode_str": " turkey"} -{"id": 32511, "token": "terror", "merges": "ter ror", "raw_count": 9510, "count": 62537, "decode_str": "terror"} -{"id": 12749, "token": "tbl", "merges": "t bl", "raw_count": 62539, "count": 62539, "decode_str": "tbl"} -{"id": 46235, "token": "BK", "merges": "B K", "raw_count": 62541, "count": 62541, "decode_str": "BK"} -{"id": 37684, "token": "095", "merges": "0 95", "raw_count": 62550, "count": 62550, "decode_str": "095"} -{"id": 13789, "token": "\u0120capabilities", "merges": "\u0120cap abilities", "raw_count": 62555, "count": 62555, "decode_str": " capabilities"} -{"id": 38735, "token": "Earth", "merges": "E arth", "raw_count": 62556, "count": 62556, "decode_str": "Earth"} -{"id": 51820, "token": "\u00e6\u012a\u00a1", "merges": "\u00e6\u012a \u00a1", "raw_count": 62568, "count": 62568, "decode_str": "\u6221"} -{"id": 16104, "token": "rod", "merges": "ro d", "raw_count": 62596, "count": 62596, "decode_str": "rod"} -{"id": 43863, "token": "jq", "merges": "j q", "raw_count": 62596, "count": 62596, "decode_str": "jq"} -{"id": 26486, "token": "\u0120heap", "merges": "\u0120he ap", "raw_count": 62599, "count": 62599, "decode_str": " heap"} -{"id": 38742, "token": "LET", "merges": "LE T", "raw_count": 62601, "count": 62601, "decode_str": "LET"} -{"id": 52349, "token": "\u00e6\u00a7\u0123", "merges": "\u00e6\u00a7 \u0123", "raw_count": 62609, "count": 62609, "decode_str": "\u69c1"} -{"id": 6448, "token": "born", "merges": "b orn", "raw_count": 52048, "count": 62624, "decode_str": "born"} -{"id": 37323, "token": "fur", "merges": "f ur", "raw_count": 62636, "count": 62636, "decode_str": "fur"} -{"id": 27167, "token": "commend", "merges": "comm end", "raw_count": 60122, "count": 62647, "decode_str": "commend"} -{"id": 9841, "token": "\u0120newly", "merges": "\u0120new ly", "raw_count": 62647, "count": 62647, "decode_str": " newly"} -{"id": 8549, "token": "\u0120delivered", "merges": "\u0120del ivered", "raw_count": 62670, "count": 62670, "decode_str": " delivered"} -{"id": 25575, "token": "\u0120electoral", "merges": "\u0120elect oral", "raw_count": 62672, "count": 62672, "decode_str": " electoral"} -{"id": 7139, "token": "\u0120trees", "merges": "\u0120tre es", "raw_count": 62675, "count": 62675, "decode_str": " trees"} -{"id": 17594, "token": "\u0120KE", "merges": "\u0120K E", "raw_count": 6687, "count": 62675, "decode_str": " KE"} -{"id": 33642, "token": "decision", "merges": "dec ision", "raw_count": 62676, "count": 62676, "decode_str": "decision"} -{"id": 38863, "token": "Pu", "merges": "P u", "raw_count": 62677, "count": 62677, "decode_str": "Pu"} -{"id": 16152, "token": "\u0120attach", "merges": "\u0120att ach", "raw_count": 45160, "count": 62688, "decode_str": " attach"} -{"id": 42228, "token": "Academ", "merges": "Ac adem", "raw_count": 62700, "count": 62700, "decode_str": "Academ"} -{"id": 39487, "token": "[{", "merges": "[ {", "raw_count": 62707, "count": 62707, "decode_str": "[{"} -{"id": 11656, "token": "etr", "merges": "et r", "raw_count": 53997, "count": 62708, "decode_str": "etr"} -{"id": 21597, "token": "ounty", "merges": "oun ty", "raw_count": 28635, "count": 62733, "decode_str": "ounty"} -{"id": 22581, "token": "\u0120annotation", "merges": "\u0120annot ation", "raw_count": 62746, "count": 62746, "decode_str": " annotation"} -{"id": 13218, "token": "arding", "merges": "ard ing", "raw_count": 62278, "count": 62751, "decode_str": "arding"} -{"id": 12729, "token": "izable", "merges": "iz able", "raw_count": 60572, "count": 62792, "decode_str": "izable"} -{"id": 27111, "token": "Prefix", "merges": "Pref ix", "raw_count": 62799, "count": 62799, "decode_str": "Prefix"} -{"id": 22474, "token": "\u0120enhancing", "merges": "\u0120enh ancing", "raw_count": 62803, "count": 62803, "decode_str": " enhancing"} -{"id": 7771, "token": "\u0120fle", "merges": "\u0120f le", "raw_count": 13985, "count": 62815, "decode_str": " fle"} -{"id": 15278, "token": "\u0120nick", "merges": "\u0120n ick", "raw_count": 37716, "count": 62818, "decode_str": " nick"} -{"id": 47327, "token": "\u0120retry", "merges": "\u0120ret ry", "raw_count": 62833, "count": 62833, "decode_str": " retry"} -{"id": 15410, "token": "\u0120138", "merges": "\u01201 38", "raw_count": 62853, "count": 62853, "decode_str": " 138"} -{"id": 41032, "token": "Ger", "merges": "G er", "raw_count": 62886, "count": 62886, "decode_str": "Ger"} -{"id": 18870, "token": "\u0120sym", "merges": "\u0120sy m", "raw_count": 62086, "count": 62888, "decode_str": " sym"} -{"id": 7126, "token": "\u0120excellent", "merges": "\u0120excell ent", "raw_count": 62903, "count": 62903, "decode_str": " excellent"} -{"id": 30410, "token": "\u0120classifier", "merges": "\u0120class ifier", "raw_count": 62909, "count": 62909, "decode_str": " classifier"} -{"id": 23421, "token": "\u0120js", "merges": "\u0120j s", "raw_count": 62909, "count": 62909, "decode_str": " js"} -{"id": 17238, "token": "\u0120occupation", "merges": "\u0120occup ation", "raw_count": 62929, "count": 62929, "decode_str": " occupation"} -{"id": 48552, "token": "Processing", "merges": "Process ing", "raw_count": 62937, "count": 62937, "decode_str": "Processing"} -{"id": 9220, "token": "\u010a\u0109\u0109\u0109\u0109\u0109\u0109", "merges": "\u010a\u0109\u0109\u0109\u0109 \u0109\u0109", "raw_count": 42527, "count": 62951, "decode_str": "\n\t\t\t\t\t\t"} -{"id": 7418, "token": "\u0120numerous", "merges": "\u0120numer ous", "raw_count": 62968, "count": 62968, "decode_str": " numerous"} -{"id": 40796, "token": "Silver", "merges": "Sil ver", "raw_count": 62970, "count": 62970, "decode_str": "Silver"} -{"id": 45865, "token": "Dur", "merges": "D ur", "raw_count": 62978, "count": 62978, "decode_str": "Dur"} -{"id": 12692, "token": "\u0120installation", "merges": "\u0120install ation", "raw_count": 62985, "count": 62985, "decode_str": " installation"} -{"id": 13554, "token": "\u0120trends", "merges": "\u0120tren ds", "raw_count": 62990, "count": 62990, "decode_str": " trends"} -{"id": 3090, "token": "\u00c3\u00bc", "merges": "\u00c3 \u00bc", "raw_count": 35000, "count": 62995, "decode_str": "\u00fc"} -{"id": 32953, "token": "Tools", "merges": "Tool s", "raw_count": 62996, "count": 62996, "decode_str": "Tools"} -{"id": 6474, "token": "\u0120stable", "merges": "\u0120st able", "raw_count": 62998, "count": 62998, "decode_str": " stable"} -{"id": 12738, "token": "\u0120cod", "merges": "\u0120c od", "raw_count": 55079, "count": 63001, "decode_str": " cod"} -{"id": 17817, "token": "styles", "merges": "st yles", "raw_count": 48031, "count": 63008, "decode_str": "styles"} -{"id": 35159, "token": "Period", "merges": "Per iod", "raw_count": 63012, "count": 63012, "decode_str": "Period"} -{"id": 13737, "token": "\u0120inverse", "merges": "\u0120in verse", "raw_count": 63029, "count": 63029, "decode_str": " inverse"} -{"id": 45606, "token": "Ring", "merges": "R ing", "raw_count": 63030, "count": 63030, "decode_str": "Ring"} -{"id": 38902, "token": "gid", "merges": "g id", "raw_count": 63042, "count": 63042, "decode_str": "gid"} -{"id": 47773, "token": "Bucket", "merges": "Buck et", "raw_count": 63054, "count": 63054, "decode_str": "Bucket"} -{"id": 16735, "token": "liver", "merges": "li ver", "raw_count": 62101, "count": 63056, "decode_str": "liver"} -{"id": 11074, "token": "\u0120trav", "merges": "\u0120tra v", "raw_count": 8697, "count": 63059, "decode_str": " trav"} -{"id": 13133, "token": "\u0120restrictions", "merges": "\u0120restrict ions", "raw_count": 63071, "count": 63071, "decode_str": " restrictions"} -{"id": 22847, "token": "anka", "merges": "ank a", "raw_count": 62902, "count": 63072, "decode_str": "anka"} -{"id": 19248, "token": "\u0120honour", "merges": "\u0120hon our", "raw_count": 63073, "count": 63073, "decode_str": " honour"} -{"id": 23182, "token": "bird", "merges": "b ird", "raw_count": 63081, "count": 63081, "decode_str": "bird"} -{"id": 4282, "token": "\u0120wonder", "merges": "\u0120won der", "raw_count": 24192, "count": 63106, "decode_str": " wonder"} -{"id": 12786, "token": "\u0120collective", "merges": "\u0120collect ive", "raw_count": 63118, "count": 63118, "decode_str": " collective"} -{"id": 15030, "token": "aten", "merges": "at en", "raw_count": 21721, "count": 63128, "decode_str": "aten"} -{"id": 5110, "token": "\u0120portion", "merges": "\u0120port ion", "raw_count": 63144, "count": 63144, "decode_str": " portion"} -{"id": 17873, "token": "something", "merges": "s omething", "raw_count": 63151, "count": 63151, "decode_str": "something"} -{"id": 46631, "token": "mess", "merges": "m ess", "raw_count": 63155, "count": 63155, "decode_str": "mess"} -{"id": 35059, "token": "\u01204000", "merges": "\u01204 000", "raw_count": 63157, "count": 63157, "decode_str": " 4000"} -{"id": 10272, "token": "\u0120calculation", "merges": "\u0120calcul ation", "raw_count": 63158, "count": 63158, "decode_str": " calculation"} -{"id": 12720, "token": "\u0120intellectual", "merges": "\u0120intellect ual", "raw_count": 60274, "count": 63175, "decode_str": " intellectual"} -{"id": 27263, "token": "attery", "merges": "atter y", "raw_count": 60230, "count": 63184, "decode_str": "attery"} -{"id": 8630, "token": "\u0120flight", "merges": "\u0120fl ight", "raw_count": 63209, "count": 63209, "decode_str": " flight"} -{"id": 30507, "token": "Mah", "merges": "M ah", "raw_count": 63236, "count": 63236, "decode_str": "Mah"} -{"id": 7809, "token": "\u0120indicating", "merges": "\u0120indic ating", "raw_count": 63253, "count": 63253, "decode_str": " indicating"} -{"id": 42903, "token": "RSA", "merges": "R SA", "raw_count": 63262, "count": 63262, "decode_str": "RSA"} -{"id": 20929, "token": "\u0120Player", "merges": "\u0120Pl ayer", "raw_count": 63269, "count": 63269, "decode_str": " Player"} -{"id": 43910, "token": "versed", "merges": "vers ed", "raw_count": 63269, "count": 63269, "decode_str": "versed"} -{"id": 39007, "token": "Om", "merges": "O m", "raw_count": 63272, "count": 63272, "decode_str": "Om"} -{"id": 37132, "token": "Pic", "merges": "P ic", "raw_count": 63297, "count": 63297, "decode_str": "Pic"} -{"id": 28937, "token": "\u0120rg", "merges": "\u0120r g", "raw_count": 54412, "count": 63299, "decode_str": " rg"} -{"id": 16755, "token": "ALS", "merges": "AL S", "raw_count": 63309, "count": 63312, "decode_str": "ALS"} -{"id": 21681, "token": "\u0120owing", "merges": "\u0120o wing", "raw_count": 63317, "count": 63317, "decode_str": " owing"} -{"id": 43053, "token": "rss", "merges": "r ss", "raw_count": 63346, "count": 63346, "decode_str": "rss"} -{"id": 42611, "token": "exact", "merges": "ex act", "raw_count": 63350, "count": 63350, "decode_str": "exact"} -{"id": 28308, "token": "\u0120indexes", "merges": "\u0120index es", "raw_count": 63351, "count": 63351, "decode_str": " indexes"} -{"id": 6449, "token": "\u00e3\u0124\u0134", "merges": "\u00e3\u0124 \u0134", "raw_count": 63353, "count": 63353, "decode_str": "\u3092"} -{"id": 21671, "token": "xff", "merges": "x ff", "raw_count": 63353, "count": 63353, "decode_str": "xff"} -{"id": 24658, "token": "bio", "merges": "b io", "raw_count": 63385, "count": 63385, "decode_str": "bio"} -{"id": 45478, "token": "Jane", "merges": "J ane", "raw_count": 63397, "count": 63397, "decode_str": "Jane"} -{"id": 48127, "token": "Arn", "merges": "Ar n", "raw_count": 63410, "count": 63410, "decode_str": "Arn"} -{"id": 34238, "token": "Hal", "merges": "H al", "raw_count": 63426, "count": 63426, "decode_str": "Hal"} -{"id": 10491, "token": "\u0120sampling", "merges": "\u0120sam pling", "raw_count": 63443, "count": 63443, "decode_str": " sampling"} -{"id": 28878, "token": "\u0120APP", "merges": "\u0120AP P", "raw_count": 63497, "count": 63497, "decode_str": " APP"} -{"id": 32868, "token": "Education", "merges": "Educ ation", "raw_count": 63503, "count": 63503, "decode_str": "Education"} -{"id": 11775, "token": "\u0120az", "merges": "\u0120a z", "raw_count": 54120, "count": 63503, "decode_str": " az"} -{"id": 14283, "token": "idity", "merges": "id ity", "raw_count": 45890, "count": 63508, "decode_str": "idity"} -{"id": 15325, "token": "patient", "merges": "pat ient", "raw_count": 60632, "count": 63513, "decode_str": "patient"} -{"id": 38574, "token": "indy", "merges": "ind y", "raw_count": 63515, "count": 63515, "decode_str": "indy"} -{"id": 40026, "token": "Ul", "merges": "U l", "raw_count": 63527, "count": 63527, "decode_str": "Ul"} -{"id": 9814, "token": "\u0120reviewed", "merges": "\u0120review ed", "raw_count": 63541, "count": 63541, "decode_str": " reviewed"} -{"id": 8392, "token": "\u0120drawn", "merges": "\u0120dra wn", "raw_count": 63541, "count": 63541, "decode_str": " drawn"} -{"id": 10416, "token": "\u0120hung", "merges": "\u0120h ung", "raw_count": 51905, "count": 63543, "decode_str": " hung"} -{"id": 29072, "token": "\u0120parsing", "merges": "\u0120pars ing", "raw_count": 63547, "count": 63547, "decode_str": " parsing"} -{"id": 10479, "token": "hemat", "merges": "he mat", "raw_count": 21281, "count": 63553, "decode_str": "hemat"} -{"id": 3293, "token": "\u0120les", "merges": "\u0120l es", "raw_count": 59317, "count": 63574, "decode_str": " les"} -{"id": 44082, "token": "]\",", "merges": "] \",", "raw_count": 63577, "count": 63577, "decode_str": "]\","} -{"id": 9555, "token": "\u0120acknowled", "merges": "\u0120acknow led", "raw_count": 7192, "count": 63590, "decode_str": " acknowled"} -{"id": 10199, "token": "\u0120introduction", "merges": "\u0120introdu ction", "raw_count": 63604, "count": 63604, "decode_str": " introduction"} -{"id": 10421, "token": "\u0120Date", "merges": "\u0120D ate", "raw_count": 49043, "count": 63610, "decode_str": " Date"} -{"id": 5729, "token": "\u0120Pre", "merges": "\u0120P re", "raw_count": 49018, "count": 63612, "decode_str": " Pre"} -{"id": 43356, "token": "Vers", "merges": "V ers", "raw_count": 63636, "count": 63636, "decode_str": "Vers"} -{"id": 40075, "token": "LAS", "merges": "L AS", "raw_count": 63651, "count": 63651, "decode_str": "LAS"} -{"id": 13659, "token": "ennis", "merges": "enn is", "raw_count": 46127, "count": 63655, "decode_str": "ennis"} -{"id": 6405, "token": "\u0120conserv", "merges": "\u0120cons erv", "raw_count": 7664, "count": 63667, "decode_str": " conserv"} -{"id": 21805, "token": "agonal", "merges": "ag onal", "raw_count": 18734, "count": 63671, "decode_str": "agonal"} -{"id": 6769, "token": "\u0120colon", "merges": "\u0120col on", "raw_count": 18317, "count": 63672, "decode_str": " colon"} -{"id": 49522, "token": "Course", "merges": "C ourse", "raw_count": 63684, "count": 63684, "decode_str": "Course"} -{"id": 13692, "token": "cker", "merges": "ck er", "raw_count": 63109, "count": 63685, "decode_str": "cker"} -{"id": 49102, "token": "924", "merges": "9 24", "raw_count": 63716, "count": 63716, "decode_str": "924"} -{"id": 29792, "token": "\u0120\\'", "merges": "\u0120\\ '", "raw_count": 63718, "count": 63718, "decode_str": " \\'"} -{"id": 24824, "token": "\u0120workflow", "merges": "\u0120work flow", "raw_count": 63723, "count": 63723, "decode_str": " workflow"} -{"id": 37734, "token": "separator", "merges": "separ ator", "raw_count": 63731, "count": 63731, "decode_str": "separator"} -{"id": 20949, "token": "\u0120machinery", "merges": "\u0120mach inery", "raw_count": 63741, "count": 63741, "decode_str": " machinery"} -{"id": 9094, "token": "\u0120ye", "merges": "\u0120y e", "raw_count": 60566, "count": 63748, "decode_str": " ye"} -{"id": 25517, "token": "ODULE", "merges": "ODU LE", "raw_count": 5744, "count": 63758, "decode_str": "ODULE"} -{"id": 7166, "token": "\u0120ju", "merges": "\u0120j u", "raw_count": 26336, "count": 63762, "decode_str": " ju"} -{"id": 21580, "token": "ailand", "merges": "ail and", "raw_count": 63291, "count": 63814, "decode_str": "ailand"} -{"id": 11453, "token": "\u0120friendly", "merges": "\u0120friend ly", "raw_count": 63820, "count": 63820, "decode_str": " friendly"} -{"id": 4447, "token": "\u0120formed", "merges": "\u0120form ed", "raw_count": 63821, "count": 63821, "decode_str": " formed"} -{"id": 11107, "token": "\u012094", "merges": "\u01209 4", "raw_count": 63834, "count": 63834, "decode_str": " 94"} -{"id": 25392, "token": "Little", "merges": "L ittle", "raw_count": 63856, "count": 63856, "decode_str": "Little"} -{"id": 48102, "token": "Allen", "merges": "All en", "raw_count": 63878, "count": 63878, "decode_str": "Allen"} -{"id": 11337, "token": "\u0120],", "merges": "\u0120 ],", "raw_count": 63878, "count": 63878, "decode_str": " ],"} -{"id": 7035, "token": "\u0120Que", "merges": "\u0120Q ue", "raw_count": 58128, "count": 63895, "decode_str": " Que"} -{"id": 5016, "token": "\u0120interaction", "merges": "\u0120inter action", "raw_count": 63901, "count": 63901, "decode_str": " interaction"} -{"id": 37195, "token": "Named", "merges": "N amed", "raw_count": 63908, "count": 63908, "decode_str": "Named"} -{"id": 36502, "token": "FACE", "merges": "F ACE", "raw_count": 63913, "count": 63913, "decode_str": "FACE"} -{"id": 39845, "token": "GAN", "merges": "G AN", "raw_count": 63916, "count": 63916, "decode_str": "GAN"} -{"id": 11406, "token": "oned", "merges": "on ed", "raw_count": 44156, "count": 63950, "decode_str": "oned"} -{"id": 48183, "token": "\u0120sha", "merges": "\u0120sh a", "raw_count": 63958, "count": 63958, "decode_str": " sha"} -{"id": 12581, "token": "ulative", "merges": "ul ative", "raw_count": 37592, "count": 63960, "decode_str": "ulative"} -{"id": 39386, "token": "errno", "merges": "err no", "raw_count": 63961, "count": 63961, "decode_str": "errno"} -{"id": 39415, "token": "Exists", "merges": "Ex ists", "raw_count": 63968, "count": 63968, "decode_str": "Exists"} -{"id": 16272, "token": "risk", "merges": "r isk", "raw_count": 63969, "count": 63969, "decode_str": "risk"} -{"id": 46036, "token": "xu", "merges": "x u", "raw_count": 64013, "count": 64013, "decode_str": "xu"} -{"id": 32182, "token": "stri", "merges": "st ri", "raw_count": 64016, "count": 64016, "decode_str": "stri"} -{"id": 32512, "token": "Lang", "merges": "L ang", "raw_count": 64024, "count": 64024, "decode_str": "Lang"} -{"id": 48786, "token": "technology", "merges": "te chnology", "raw_count": 64025, "count": 64025, "decode_str": "technology"} -{"id": 37626, "token": "representation", "merges": "represent ation", "raw_count": 64029, "count": 64029, "decode_str": "representation"} -{"id": 42670, "token": "Cit", "merges": "C it", "raw_count": 64048, "count": 64048, "decode_str": "Cit"} -{"id": 6331, "token": "\u0120stopped", "merges": "\u0120sto pped", "raw_count": 64051, "count": 64051, "decode_str": " stopped"} -{"id": 38485, "token": "Lew", "merges": "L ew", "raw_count": 16390, "count": 64073, "decode_str": "Lew"} -{"id": 31240, "token": "oki", "merges": "ok i", "raw_count": 64075, "count": 64075, "decode_str": "oki"} -{"id": 30880, "token": "Features", "merges": "Fe atures", "raw_count": 64087, "count": 64087, "decode_str": "Features"} -{"id": 5460, "token": "\u0120severe", "merges": "\u0120se vere", "raw_count": 43901, "count": 64088, "decode_str": " severe"} -{"id": 18642, "token": "upt", "merges": "u pt", "raw_count": 58923, "count": 64107, "decode_str": "upt"} -{"id": 48993, "token": "Threshold", "merges": "Th reshold", "raw_count": 64122, "count": 64122, "decode_str": "Threshold"} -{"id": 22449, "token": "\u0120Multi", "merges": "\u0120Mult i", "raw_count": 64123, "count": 64123, "decode_str": " Multi"} -{"id": 15358, "token": "\u0120Try", "merges": "\u0120T ry", "raw_count": 64131, "count": 64131, "decode_str": " Try"} -{"id": 41303, "token": "corner", "merges": "cor ner", "raw_count": 64134, "count": 64134, "decode_str": "corner"} -{"id": 54588, "token": "\u00e9\u0136\u0134", "merges": "\u00e9\u0136 \u0134", "raw_count": 64140, "count": 64140, "decode_str": "\u9512"} -{"id": 44041, "token": "warm", "merges": "w arm", "raw_count": 64146, "count": 64146, "decode_str": "warm"} -{"id": 40587, "token": "Sarah", "merges": "Sar ah", "raw_count": 64160, "count": 64160, "decode_str": "Sarah"} -{"id": 14220, "token": "OVA", "merges": "OV A", "raw_count": 54305, "count": 64163, "decode_str": "OVA"} -{"id": 14275, "token": "\u0120independence", "merges": "\u0120independ ence", "raw_count": 64165, "count": 64165, "decode_str": " independence"} -{"id": 5950, "token": "\u0120recorded", "merges": "\u0120record ed", "raw_count": 64167, "count": 64167, "decode_str": " recorded"} -{"id": 29617, "token": "Contents", "merges": "Cont ents", "raw_count": 64173, "count": 64173, "decode_str": "Contents"} -{"id": 12881, "token": "\u0120pipe", "merges": "\u0120p ipe", "raw_count": 64173, "count": 64173, "decode_str": " pipe"} -{"id": 49027, "token": "describe", "merges": "des cribe", "raw_count": 64175, "count": 64175, "decode_str": "describe"} -{"id": 37905, "token": "\u0120blob", "merges": "\u0120bl ob", "raw_count": 64180, "count": 64180, "decode_str": " blob"} -{"id": 51581, "token": "\u00e5\u00ba\u00b9", "merges": "\u00e5\u00ba \u00b9", "raw_count": 64183, "count": 64183, "decode_str": "\u5eb9"} -{"id": 20225, "token": "^.", "merges": "^ .", "raw_count": 64201, "count": 64201, "decode_str": "^."} -{"id": 14516, "token": "\u0120hosts", "merges": "\u0120host s", "raw_count": 64211, "count": 64211, "decode_str": " hosts"} -{"id": 29367, "token": "OOGLE", "merges": "OO GLE", "raw_count": 62061, "count": 64213, "decode_str": "OOGLE"} -{"id": 18102, "token": "Math", "merges": "M ath", "raw_count": 64213, "count": 64213, "decode_str": "Math"} -{"id": 46110, "token": "\u0120ix", "merges": "\u0120i x", "raw_count": 64237, "count": 64237, "decode_str": " ix"} -{"id": 53598, "token": "\u00e8\u012b\u012d", "merges": "\u00e8\u012b \u012d", "raw_count": 64241, "count": 64241, "decode_str": "\u824b"} -{"id": 5384, "token": "\u0120mist", "merges": "\u0120m ist", "raw_count": 17170, "count": 64256, "decode_str": " mist"} -{"id": 7369, "token": "\u0120resulted", "merges": "\u0120result ed", "raw_count": 64260, "count": 64260, "decode_str": " resulted"} -{"id": 8006, "token": "ented", "merges": "ent ed", "raw_count": 27287, "count": 64260, "decode_str": "ented"} -{"id": 23113, "token": "0000000", "merges": "0000 000", "raw_count": 64263, "count": 64263, "decode_str": "0000000"} -{"id": 27500, "token": "Rows", "merges": "R ows", "raw_count": 64268, "count": 64268, "decode_str": "Rows"} -{"id": 40262, "token": "Royal", "merges": "R oyal", "raw_count": 64297, "count": 64297, "decode_str": "Royal"} -{"id": 31559, "token": "\u0120erad", "merges": "\u0120er ad", "raw_count": 64300, "count": 64300, "decode_str": " erad"} -{"id": 27303, "token": "Nov", "merges": "N ov", "raw_count": 64317, "count": 64317, "decode_str": "Nov"} -{"id": 5314, "token": "rely", "merges": "re ly", "raw_count": 10010, "count": 64318, "decode_str": "rely"} -{"id": 5587, "token": "\u0120Spec", "merges": "\u0120S pec", "raw_count": 34489, "count": 64336, "decode_str": " Spec"} -{"id": 7408, "token": "\u0120trip", "merges": "\u0120tri p", "raw_count": 64353, "count": 64353, "decode_str": " trip"} -{"id": 41672, "token": "Received", "merges": "Re ceived", "raw_count": 64355, "count": 64355, "decode_str": "Received"} -{"id": 34504, "token": "STD", "merges": "ST D", "raw_count": 64357, "count": 64357, "decode_str": "STD"} -{"id": 38251, "token": "Ram", "merges": "R am", "raw_count": 64388, "count": 64388, "decode_str": "Ram"} -{"id": 36340, "token": "Jackson", "merges": "Jack son", "raw_count": 64395, "count": 64395, "decode_str": "Jackson"} -{"id": 21503, "token": "\u0120SET", "merges": "\u0120S ET", "raw_count": 64402, "count": 64402, "decode_str": " SET"} -{"id": 7446, "token": "\u0120replic", "merges": "\u0120re plic", "raw_count": 15771, "count": 64417, "decode_str": " replic"} -{"id": 33799, "token": "facts", "merges": "f acts", "raw_count": 64424, "count": 64424, "decode_str": "facts"} -{"id": 29698, "token": "\u0120transforms", "merges": "\u0120transform s", "raw_count": 64425, "count": 64425, "decode_str": " transforms"} -{"id": 32311, "token": "MESS", "merges": "M ESS", "raw_count": 13987, "count": 64427, "decode_str": "MESS"} -{"id": 30240, "token": "Material", "merges": "M aterial", "raw_count": 64430, "count": 64430, "decode_str": "Material"} -{"id": 28782, "token": "Quick", "merges": "Qu ick", "raw_count": 64431, "count": 64431, "decode_str": "Quick"} -{"id": 22571, "token": "Austral", "merges": "Aust ral", "raw_count": 4397, "count": 64441, "decode_str": "Austral"} -{"id": 7379, "token": "\u0120UN", "merges": "\u0120U N", "raw_count": 64233, "count": 64443, "decode_str": " UN"} -{"id": 12246, "token": "\u0120bid", "merges": "\u0120b id", "raw_count": 64446, "count": 64446, "decode_str": " bid"} -{"id": 9839, "token": "\u0120phr", "merges": "\u0120ph r", "raw_count": 1920, "count": 64453, "decode_str": " phr"} -{"id": 7937, "token": "udd", "merges": "ud d", "raw_count": 53781, "count": 64467, "decode_str": "udd"} -{"id": 13928, "token": "hole", "merges": "h ole", "raw_count": 63413, "count": 64478, "decode_str": "hole"} -{"id": 7101, "token": "\u0120marked", "merges": "\u0120mark ed", "raw_count": 61153, "count": 64488, "decode_str": " marked"} -{"id": 34900, "token": "\u0120nt", "merges": "\u0120n t", "raw_count": 64500, "count": 64500, "decode_str": " nt"} -{"id": 4874, "token": "\u0120liqu", "merges": "\u0120li qu", "raw_count": 3360, "count": 64504, "decode_str": " liqu"} -{"id": 19241, "token": "\u0120queries", "merges": "\u0120qu eries", "raw_count": 64511, "count": 64511, "decode_str": " queries"} -{"id": 17638, "token": "igs", "merges": "ig s", "raw_count": 64511, "count": 64511, "decode_str": "igs"} -{"id": 7024, "token": "\u0120depends", "merges": "\u0120dep ends", "raw_count": 64519, "count": 64519, "decode_str": " depends"} -{"id": 27661, "token": "\u00e9\u0142", "merges": "\u00e9 \u0142", "raw_count": 63977, "count": 64523, "decode_str": "\ufffd"} -{"id": 16561, "token": "esian", "merges": "es ian", "raw_count": 60293, "count": 64530, "decode_str": "esian"} -{"id": 30862, "token": "strict", "merges": "st rict", "raw_count": 64537, "count": 64537, "decode_str": "strict"} -{"id": 29348, "token": "\u0120kos", "merges": "\u0120k os", "raw_count": 64573, "count": 64573, "decode_str": " kos"} -{"id": 7620, "token": "\u00d0\u00b8\u00d1\u0124", "merges": "\u00d0\u00b8 \u00d1\u0124", "raw_count": 20467, "count": 64610, "decode_str": "\u0438\u0442"} -{"id": 3910, "token": "\u0120differences", "merges": "\u0120diffe rences", "raw_count": 64623, "count": 64623, "decode_str": " differences"} -{"id": 31886, "token": "Loading", "merges": "Load ing", "raw_count": 64634, "count": 64634, "decode_str": "Loading"} -{"id": 10839, "token": "\u0120tun", "merges": "\u0120t un", "raw_count": 48525, "count": 64637, "decode_str": " tun"} -{"id": 10620, "token": "\u0120dealing", "merges": "\u0120deal ing", "raw_count": 64649, "count": 64649, "decode_str": " dealing"} -{"id": 44609, "token": "SOD", "merges": "S OD", "raw_count": 64651, "count": 64651, "decode_str": "SOD"} -{"id": 39440, "token": "Wilson", "merges": "Wil son", "raw_count": 64661, "count": 64661, "decode_str": "Wilson"} -{"id": 50165, "token": "MEN", "merges": "M EN", "raw_count": 64668, "count": 64668, "decode_str": "MEN"} -{"id": 36784, "token": "<>", "merges": "< >", "raw_count": 64668, "count": 64668, "decode_str": "<>"} -{"id": 24716, "token": "trim", "merges": "tr im", "raw_count": 64679, "count": 64679, "decode_str": "trim"} -{"id": 10685, "token": "Tex", "merges": "T ex", "raw_count": 47560, "count": 64711, "decode_str": "Tex"} -{"id": 33037, "token": "\u0120recursive", "merges": "\u0120recurs ive", "raw_count": 64722, "count": 64722, "decode_str": " recursive"} -{"id": 14899, "token": "inen", "merges": "in en", "raw_count": 18833, "count": 64724, "decode_str": "inen"} -{"id": 12894, "token": "igate", "merges": "ig ate", "raw_count": 33080, "count": 64728, "decode_str": "igate"} -{"id": 47301, "token": "nets", "merges": "n ets", "raw_count": 64731, "count": 64731, "decode_str": "nets"} -{"id": 27224, "token": "USH", "merges": "US H", "raw_count": 64755, "count": 64755, "decode_str": "USH"} -{"id": 30212, "token": "EVENT", "merges": "EV ENT", "raw_count": 64761, "count": 64761, "decode_str": "EVENT"} -{"id": 16283, "token": "lied", "merges": "l ied", "raw_count": 13527, "count": 64774, "decode_str": "lied"} -{"id": 7561, "token": "\u0120widely", "merges": "\u0120wid ely", "raw_count": 64791, "count": 64791, "decode_str": " widely"} -{"id": 31495, "token": "Software", "merges": "So ftware", "raw_count": 64803, "count": 64803, "decode_str": "Software"} -{"id": 26599, "token": "arker", "merges": "ark er", "raw_count": 64380, "count": 64809, "decode_str": "arker"} -{"id": 4051, "token": "\u0120Gl", "merges": "\u0120G l", "raw_count": 23299, "count": 64811, "decode_str": " Gl"} -{"id": 31697, "token": "\u0120pdf", "merges": "\u0120p df", "raw_count": 64815, "count": 64815, "decode_str": " pdf"} -{"id": 23332, "token": "\u0120civilians", "merges": "\u0120civil ians", "raw_count": 64823, "count": 64823, "decode_str": " civilians"} -{"id": 31674, "token": "Iss", "merges": "I ss", "raw_count": 27283, "count": 64823, "decode_str": "Iss"} -{"id": 14094, "token": "their", "merges": "the ir", "raw_count": 64827, "count": 64827, "decode_str": "their"} -{"id": 34244, "token": "\u0120tb", "merges": "\u0120t b", "raw_count": 64254, "count": 64829, "decode_str": " tb"} -{"id": 4675, "token": "\u0120hospital", "merges": "\u0120h ospital", "raw_count": 61025, "count": 64837, "decode_str": " hospital"} -{"id": 3200, "token": "\u0120motion", "merges": "\u0120mot ion", "raw_count": 64858, "count": 64858, "decode_str": " motion"} -{"id": 11782, "token": "\u0120Array", "merges": "\u0120Ar ray", "raw_count": 64035, "count": 64875, "decode_str": " Array"} -{"id": 16606, "token": "ete", "merges": "et e", "raw_count": 64883, "count": 64883, "decode_str": "ete"} -{"id": 47573, "token": "upgrade", "merges": "up grade", "raw_count": 64891, "count": 64891, "decode_str": "upgrade"} -{"id": 38878, "token": "tell", "merges": "t ell", "raw_count": 64892, "count": 64892, "decode_str": "tell"} -{"id": 40111, "token": "tracking", "merges": "tr acking", "raw_count": 64896, "count": 64896, "decode_str": "tracking"} -{"id": 35253, "token": "\u0120ls", "merges": "\u0120l s", "raw_count": 64902, "count": 64902, "decode_str": " ls"} -{"id": 27619, "token": "rates", "merges": "r ates", "raw_count": 64908, "count": 64908, "decode_str": "rates"} -{"id": 1603, "token": "}(", "merges": "} (", "raw_count": 47665, "count": 64918, "decode_str": "}("} -{"id": 27940, "token": "\u00ec\u0139\u0132", "merges": "\u00ec\u0139 \u0132", "raw_count": 64921, "count": 64921, "decode_str": "\uc5d0"} -{"id": 8225, "token": "\u0120tit", "merges": "\u0120t it", "raw_count": 28272, "count": 64928, "decode_str": " tit"} -{"id": 41074, "token": "Demo", "merges": "Dem o", "raw_count": 64931, "count": 64931, "decode_str": "Demo"} -{"id": 8084, "token": "\u0120sqrt", "merges": "\u0120s qrt", "raw_count": 64954, "count": 64954, "decode_str": " sqrt"} -{"id": 28352, "token": "KP", "merges": "K P", "raw_count": 64960, "count": 64960, "decode_str": "KP"} -{"id": 11439, "token": "\u012083", "merges": "\u01208 3", "raw_count": 64962, "count": 64962, "decode_str": " 83"} -{"id": 25343, "token": "Statement", "merges": "Stat ement", "raw_count": 64972, "count": 64972, "decode_str": "Statement"} -{"id": 5825, "token": "\u0120nut", "merges": "\u0120n ut", "raw_count": 12503, "count": 64998, "decode_str": " nut"} -{"id": 15452, "token": "\u0120publish", "merges": "\u0120publ ish", "raw_count": 65001, "count": 65001, "decode_str": " publish"} -{"id": 37280, "token": "\u0120ws", "merges": "\u0120w s", "raw_count": 65007, "count": 65007, "decode_str": " ws"} -{"id": 9552, "token": "\u0120sizes", "merges": "\u0120s izes", "raw_count": 65008, "count": 65008, "decode_str": " sizes"} -{"id": 20033, "token": "\u0120tradem", "merges": "\u0120trad em", "raw_count": 82, "count": 65024, "decode_str": " tradem"} -{"id": 31320, "token": "rites", "merges": "rit es", "raw_count": 65027, "count": 65027, "decode_str": "rites"} -{"id": 10792, "token": "\u0120marg", "merges": "\u0120m arg", "raw_count": 12273, "count": 65028, "decode_str": " marg"} -{"id": 19066, "token": "utation", "merges": "ut ation", "raw_count": 41323, "count": 65038, "decode_str": "utation"} -{"id": 19613, "token": "ogg", "merges": "og g", "raw_count": 65039, "count": 65039, "decode_str": "ogg"} -{"id": 9226, "token": "iden", "merges": "id en", "raw_count": 61751, "count": 65049, "decode_str": "iden"} -{"id": 10701, "token": "\u0120Network", "merges": "\u0120Net work", "raw_count": 65058, "count": 65058, "decode_str": " Network"} -{"id": 13646, "token": "onomy", "merges": "on omy", "raw_count": 43320, "count": 65058, "decode_str": "onomy"} -{"id": 5665, "token": "\u0120surround", "merges": "\u0120sur round", "raw_count": 4822, "count": 65068, "decode_str": " surround"} -{"id": 30345, "token": "places", "merges": "pl aces", "raw_count": 65079, "count": 65079, "decode_str": "places"} -{"id": 11992, "token": "\u0120municip", "merges": "\u0120m unicip", "raw_count": 1227, "count": 65081, "decode_str": " municip"} -{"id": 5046, "token": "\u0120maybe", "merges": "\u0120may be", "raw_count": 65104, "count": 65104, "decode_str": " maybe"} -{"id": 33836, "token": "\u00e8\u00b3", "merges": "\u00e8 \u00b3", "raw_count": 65109, "count": 65109, "decode_str": "\ufffd"} -{"id": 25191, "token": "Writ", "merges": "W rit", "raw_count": 32783, "count": 65113, "decode_str": "Writ"} -{"id": 39350, "token": "CAL", "merges": "C AL", "raw_count": 65115, "count": 65115, "decode_str": "CAL"} -{"id": 11456, "token": "\u012093", "merges": "\u01209 3", "raw_count": 65144, "count": 65144, "decode_str": " 93"} -{"id": 40861, "token": "ENG", "merges": "EN G", "raw_count": 65148, "count": 65148, "decode_str": "ENG"} -{"id": 4808, "token": "\u0120skin", "merges": "\u0120sk in", "raw_count": 65153, "count": 65153, "decode_str": " skin"} -{"id": 45791, "token": "hf", "merges": "h f", "raw_count": 65162, "count": 65162, "decode_str": "hf"} -{"id": 12989, "token": "\u0120topics", "merges": "\u0120top ics", "raw_count": 65177, "count": 65177, "decode_str": " topics"} -{"id": 39139, "token": "Export", "merges": "Ex port", "raw_count": 65187, "count": 65187, "decode_str": "Export"} -{"id": 14293, "token": "lag", "merges": "l ag", "raw_count": 63657, "count": 65191, "decode_str": "lag"} -{"id": 41516, "token": "Timestamp", "merges": "Tim estamp", "raw_count": 65199, "count": 65199, "decode_str": "Timestamp"} -{"id": 13868, "token": "\u0120saving", "merges": "\u0120s aving", "raw_count": 65212, "count": 65212, "decode_str": " saving"} -{"id": 8303, "token": "ributions", "merges": "ribut ions", "raw_count": 45886, "count": 65218, "decode_str": "ributions"} -{"id": 26804, "token": "scripts", "merges": "script s", "raw_count": 65220, "count": 65220, "decode_str": "scripts"} -{"id": 20315, "token": "\u0120commod", "merges": "\u0120comm od", "raw_count": 1110, "count": 65243, "decode_str": " commod"} -{"id": 36047, "token": "animation", "merges": "anim ation", "raw_count": 65249, "count": 65249, "decode_str": "animation"} -{"id": 4839, "token": "\u0120chance", "merges": "\u0120ch ance", "raw_count": 65257, "count": 65257, "decode_str": " chance"} -{"id": 8148, "token": "\u0120Cle", "merges": "\u0120C le", "raw_count": 10368, "count": 65279, "decode_str": " Cle"} -{"id": 15204, "token": "\u0120Block", "merges": "\u0120Bl ock", "raw_count": 61570, "count": 65293, "decode_str": " Block"} -{"id": 40622, "token": "thus", "merges": "th us", "raw_count": 65295, "count": 65295, "decode_str": "thus"} -{"id": 25828, "token": "\u0120customs", "merges": "\u0120custom s", "raw_count": 65297, "count": 65297, "decode_str": " customs"} -{"id": 7978, "token": "\u0120immig", "merges": "\u0120imm ig", "raw_count": 1632, "count": 65307, "decode_str": " immig"} -{"id": 38836, "token": "JE", "merges": "J E", "raw_count": 65308, "count": 65308, "decode_str": "JE"} -{"id": 3898, "token": "\u0120impl", "merges": "\u0120im pl", "raw_count": 24247, "count": 65309, "decode_str": " impl"} -{"id": 7954, "token": "\u0120fo", "merges": "\u0120f o", "raw_count": 43883, "count": 65310, "decode_str": " fo"} -{"id": 9955, "token": "]\\", "merges": "] \\", "raw_count": 65313, "count": 65313, "decode_str": "]\\"} -{"id": 22396, "token": "USA", "merges": "US A", "raw_count": 65324, "count": 65324, "decode_str": "USA"} -{"id": 28902, "token": "vac", "merges": "v ac", "raw_count": 65341, "count": 65341, "decode_str": "vac"} -{"id": 34926, "token": "dav", "merges": "d av", "raw_count": 65344, "count": 65344, "decode_str": "dav"} -{"id": 10194, "token": "\u0120steel", "merges": "\u0120ste el", "raw_count": 65348, "count": 65348, "decode_str": " steel"} -{"id": 12739, "token": "\u0120implications", "merges": "\u0120implic ations", "raw_count": 65359, "count": 65359, "decode_str": " implications"} -{"id": 39683, "token": "COR", "merges": "C OR", "raw_count": 65371, "count": 65371, "decode_str": "COR"} -{"id": 20336, "token": "raham", "merges": "ra ham", "raw_count": 64826, "count": 65383, "decode_str": "raham"} -{"id": 6642, "token": "\u0120estimate", "merges": "\u0120est imate", "raw_count": 65406, "count": 65406, "decode_str": " estimate"} -{"id": 42514, "token": "\u0120fulfil", "merges": "\u0120ful fil", "raw_count": 65408, "count": 65408, "decode_str": " fulfil"} -{"id": 9761, "token": "aph", "merges": "ap h", "raw_count": 58104, "count": 65410, "decode_str": "aph"} -{"id": 33268, "token": "\u0120NOTE", "merges": "\u0120NOT E", "raw_count": 65420, "count": 65420, "decode_str": " NOTE"} -{"id": 13606, "token": "oven", "merges": "ov en", "raw_count": 62202, "count": 65502, "decode_str": "oven"} -{"id": 10281, "token": "\u0120constitutional", "merges": "\u0120constitution al", "raw_count": 65515, "count": 65515, "decode_str": " constitutional"} -{"id": 24151, "token": "DateTime", "merges": "Date Time", "raw_count": 65518, "count": 65518, "decode_str": "DateTime"} -{"id": 26627, "token": "IRST", "merges": "IR ST", "raw_count": 5317, "count": 65519, "decode_str": "IRST"} -{"id": 16262, "token": "'>", "merges": "' >", "raw_count": 65522, "count": 65522, "decode_str": "'>"} -{"id": 25182, "token": "Sports", "merges": "S ports", "raw_count": 65537, "count": 65538, "decode_str": "Sports"} -{"id": 7128, "token": "itud", "merges": "it ud", "raw_count": 13216, "count": 65539, "decode_str": "itud"} -{"id": 35789, "token": "leave", "merges": "le ave", "raw_count": 65547, "count": 65547, "decode_str": "leave"} -{"id": 6126, "token": "\u0120stre", "merges": "\u0120st re", "raw_count": 7270, "count": 65553, "decode_str": " stre"} -{"id": 43017, "token": "Tel", "merges": "T el", "raw_count": 65557, "count": 65557, "decode_str": "Tel"} -{"id": 39491, "token": "GY", "merges": "G Y", "raw_count": 65559, "count": 65559, "decode_str": "GY"} -{"id": 21851, "token": "PSS", "merges": "PS S", "raw_count": 64457, "count": 65567, "decode_str": "PSS"} -{"id": 10245, "token": "orse", "merges": "or se", "raw_count": 39539, "count": 65571, "decode_str": "orse"} -{"id": 37532, "token": "ISPR", "merges": "IS PR", "raw_count": 65336, "count": 65604, "decode_str": "ISPR"} -{"id": 12339, "token": "\u0120penalty", "merges": "\u0120pen alty", "raw_count": 65618, "count": 65618, "decode_str": " penalty"} -{"id": 19522, "token": "ipal", "merges": "ip al", "raw_count": 44555, "count": 65619, "decode_str": "ipal"} -{"id": 10982, "token": "uality", "merges": "ual ity", "raw_count": 6698, "count": 65632, "decode_str": "uality"} -{"id": 6399, "token": "\u0120nan", "merges": "\u0120n an", "raw_count": 62009, "count": 65633, "decode_str": " nan"} -{"id": 17779, "token": "=\"/", "merges": "=\" /", "raw_count": 65634, "count": 65634, "decode_str": "=\"/"} -{"id": 53529, "token": "\u00e8\u0125\u00b4", "merges": "\u00e8\u0125 \u00b4", "raw_count": 65649, "count": 65649, "decode_str": "\u80f4"} -{"id": 25947, "token": "fen", "merges": "f en", "raw_count": 65651, "count": 65651, "decode_str": "fen"} -{"id": 28291, "token": "BLOCK", "merges": "BL OCK", "raw_count": 65668, "count": 65668, "decode_str": "BLOCK"} -{"id": 9446, "token": "\u0120recognize", "merges": "\u0120recogn ize", "raw_count": 65676, "count": 65676, "decode_str": " recognize"} -{"id": 29333, "token": "\u00ec\u0142", "merges": "\u00ec \u0142", "raw_count": 65681, "count": 65681, "decode_str": "\ufffd"} -{"id": 5311, "token": "\u0120blog", "merges": "\u0120bl og", "raw_count": 52907, "count": 65702, "decode_str": " blog"} -{"id": 35077, "token": "Contract", "merges": "Cont ract", "raw_count": 65705, "count": 65705, "decode_str": "Contract"} -{"id": 43008, "token": "083", "merges": "08 3", "raw_count": 65705, "count": 65705, "decode_str": "083"} -{"id": 40058, "token": "8080", "merges": "80 80", "raw_count": 65713, "count": 65713, "decode_str": "8080"} -{"id": 17705, "token": "\u0120criterion", "merges": "\u0120criter ion", "raw_count": 65722, "count": 65722, "decode_str": " criterion"} -{"id": 31696, "token": "Forward", "merges": "For ward", "raw_count": 65726, "count": 65726, "decode_str": "Forward"} -{"id": 6925, "token": "\u0120pert", "merges": "\u0120per t", "raw_count": 10258, "count": 65734, "decode_str": " pert"} -{"id": 41071, "token": "reports", "merges": "re ports", "raw_count": 65743, "count": 65743, "decode_str": "reports"} -{"id": 9551, "token": "\u0120teaching", "merges": "\u0120te aching", "raw_count": 65746, "count": 65746, "decode_str": " teaching"} -{"id": 28930, "token": "\u0120reservation", "merges": "\u0120reserv ation", "raw_count": 65789, "count": 65789, "decode_str": " reservation"} -{"id": 19126, "token": "\u0120apple", "merges": "\u0120app le", "raw_count": 65791, "count": 65791, "decode_str": " apple"} -{"id": 8280, "token": "\u0120www", "merges": "\u0120w ww", "raw_count": 65794, "count": 65794, "decode_str": " www"} -{"id": 21194, "token": "\u0120cf", "merges": "\u0120c f", "raw_count": 65807, "count": 65807, "decode_str": " cf"} -{"id": 42382, "token": "AFP", "merges": "A FP", "raw_count": 65812, "count": 65812, "decode_str": "AFP"} -{"id": 26028, "token": "Fixed", "merges": "F ixed", "raw_count": 65847, "count": 65847, "decode_str": "Fixed"} -{"id": 26621, "token": "moving", "merges": "m oving", "raw_count": 65857, "count": 65857, "decode_str": "moving"} -{"id": 36323, "token": "signed", "merges": "s igned", "raw_count": 65867, "count": 65867, "decode_str": "signed"} -{"id": 19220, "token": "\u0120GET", "merges": "\u0120G ET", "raw_count": 65867, "count": 65867, "decode_str": " GET"} -{"id": 5424, "token": "\u0120hus", "merges": "\u0120h us", "raw_count": 8202, "count": 65892, "decode_str": " hus"} -{"id": 5017, "token": "\u0120stuff", "merges": "\u0120st uff", "raw_count": 63395, "count": 65914, "decode_str": " stuff"} -{"id": 2058, "token": "\u0120At", "merges": "\u0120A t", "raw_count": 57508, "count": 65916, "decode_str": " At"} -{"id": 10624, "token": "rams", "merges": "r ams", "raw_count": 40191, "count": 65919, "decode_str": "rams"} -{"id": 20123, "token": "\u0120rehabilitation", "merges": "\u0120re habilitation", "raw_count": 65932, "count": 65932, "decode_str": " rehabilitation"} -{"id": 15378, "token": "\u0120configured", "merges": "\u0120config ured", "raw_count": 65933, "count": 65933, "decode_str": " configured"} -{"id": 16840, "token": "usalem", "merges": "usal em", "raw_count": 65674, "count": 65954, "decode_str": "usalem"} -{"id": 45737, "token": "\u0120unpack", "merges": "\u0120un pack", "raw_count": 65958, "count": 65958, "decode_str": " unpack"} -{"id": 5770, "token": "\u0120mg", "merges": "\u0120m g", "raw_count": 65965, "count": 65965, "decode_str": " mg"} -{"id": 15917, "token": "\u0120reserve", "merges": "\u0120res erve", "raw_count": 65966, "count": 65966, "decode_str": " reserve"} -{"id": 14158, "token": "\u0120deput", "merges": "\u0120de put", "raw_count": 546, "count": 65966, "decode_str": " deput"} -{"id": 7358, "token": "\u0120accum", "merges": "\u0120acc um", "raw_count": 19836, "count": 65970, "decode_str": " accum"} -{"id": 19001, "token": "dark", "merges": "d ark", "raw_count": 65983, "count": 65983, "decode_str": "dark"} -{"id": 12104, "token": "}})", "merges": "}} )", "raw_count": 65985, "count": 65985, "decode_str": "}})"} -{"id": 12436, "token": "rett", "merges": "ret t", "raw_count": 64637, "count": 66019, "decode_str": "rett"} -{"id": 26955, "token": "dal", "merges": "d al", "raw_count": 66022, "count": 66022, "decode_str": "dal"} -{"id": 43478, "token": "azure", "merges": "az ure", "raw_count": 66042, "count": 66042, "decode_str": "azure"} -{"id": 21173, "token": "Mill", "merges": "M ill", "raw_count": 66043, "count": 66043, "decode_str": "Mill"} -{"id": 15235, "token": "eland", "merges": "el and", "raw_count": 57938, "count": 66052, "decode_str": "eland"} -{"id": 30882, "token": "Identity", "merges": "Ident ity", "raw_count": 66074, "count": 66074, "decode_str": "Identity"} -{"id": 50868, "token": "\u00e5\u012f\u012f", "merges": "\u00e5\u012f \u012f", "raw_count": 66078, "count": 66078, "decode_str": "\u534d"} -{"id": 4707, "token": "\u0120hair", "merges": "\u0120ha ir", "raw_count": 63897, "count": 66088, "decode_str": " hair"} -{"id": 12869, "token": "\u0120roy", "merges": "\u0120ro y", "raw_count": 8456, "count": 66090, "decode_str": " roy"} -{"id": 34287, "token": "OPE", "merges": "OP E", "raw_count": 66090, "count": 66090, "decode_str": "OPE"} -{"id": 21118, "token": "quet", "merges": "qu et", "raw_count": 66097, "count": 66097, "decode_str": "quet"} -{"id": 20246, "token": "efficient", "merges": "e fficient", "raw_count": 58321, "count": 66109, "decode_str": "efficient"} -{"id": 50435, "token": "\u00e4\u00b9\u0124", "merges": "\u00e4\u00b9 \u0124", "raw_count": 66112, "count": 66112, "decode_str": "\u4e42"} -{"id": 7107, "token": "\u0120quiet", "merges": "\u0120qu iet", "raw_count": 56582, "count": 66115, "decode_str": " quiet"} -{"id": 44475, "token": "particip", "merges": "part icip", "raw_count": 66133, "count": 66133, "decode_str": "particip"} -{"id": 9096, "token": "\u0120circle", "merges": "\u0120circ le", "raw_count": 66142, "count": 66142, "decode_str": " circle"} -{"id": 24840, "token": "CMD", "merges": "CM D", "raw_count": 66150, "count": 66150, "decode_str": "CMD"} -{"id": 33151, "token": "street", "merges": "st reet", "raw_count": 66163, "count": 66163, "decode_str": "street"} -{"id": 21857, "token": "plementation", "merges": "plement ation", "raw_count": 15813, "count": 66181, "decode_str": "plementation"} -{"id": 14736, "token": "\u0120Search", "merges": "\u0120S earch", "raw_count": 66193, "count": 66193, "decode_str": " Search"} -{"id": 4235, "token": "\u0120Sw", "merges": "\u0120S w", "raw_count": 35138, "count": 66193, "decode_str": " Sw"} -{"id": 17441, "token": "Abstract", "merges": "Ab stract", "raw_count": 66237, "count": 66237, "decode_str": "Abstract"} -{"id": 13078, "token": "aton", "merges": "at on", "raw_count": 63718, "count": 66238, "decode_str": "aton"} -{"id": 4916, "token": "\u0120becomes", "merges": "\u0120be comes", "raw_count": 66246, "count": 66246, "decode_str": " becomes"} -{"id": 20253, "token": "asket", "merges": "ask et", "raw_count": 52852, "count": 66246, "decode_str": "asket"} -{"id": 18122, "token": "\u0120compile", "merges": "\u0120comp ile", "raw_count": 66257, "count": 66257, "decode_str": " compile"} -{"id": 38325, "token": "spark", "merges": "sp ark", "raw_count": 66262, "count": 66262, "decode_str": "spark"} -{"id": 33972, "token": "Hay", "merges": "H ay", "raw_count": 66266, "count": 66266, "decode_str": "Hay"} -{"id": 47413, "token": "Jonathan", "merges": "Jon athan", "raw_count": 66269, "count": 66269, "decode_str": "Jonathan"} -{"id": 44707, "token": "Filename", "merges": "Fil ename", "raw_count": 66276, "count": 66276, "decode_str": "Filename"} -{"id": 10167, "token": "spring", "merges": "sp ring", "raw_count": 56910, "count": 66289, "decode_str": "spring"} -{"id": 17627, "token": "\u0120increment", "merges": "\u0120incre ment", "raw_count": 51487, "count": 66305, "decode_str": " increment"} -{"id": 7576, "token": "\u0120accompl", "merges": "\u0120accom pl", "raw_count": 6869, "count": 66319, "decode_str": " accompl"} -{"id": 5646, "token": "ubuntu", "merges": "ub untu", "raw_count": 62387, "count": 66329, "decode_str": "ubuntu"} -{"id": 8267, "token": "Every", "merges": "E very", "raw_count": 31613, "count": 66359, "decode_str": "Every"} -{"id": 13640, "token": "\u0120participated", "merges": "\u0120particip ated", "raw_count": 66370, "count": 66370, "decode_str": " participated"} -{"id": 11621, "token": "\u0120tren", "merges": "\u0120t ren", "raw_count": 1922, "count": 66375, "decode_str": " tren"} -{"id": 14601, "token": "\u0120fitness", "merges": "\u0120f itness", "raw_count": 66377, "count": 66377, "decode_str": " fitness"} -{"id": 28132, "token": "scriptions", "merges": "script ions", "raw_count": 66379, "count": 66379, "decode_str": "scriptions"} -{"id": 48781, "token": "challenge", "merges": "ch allenge", "raw_count": 66384, "count": 66384, "decode_str": "challenge"} -{"id": 5698, "token": "\u0120vent", "merges": "\u0120v ent", "raw_count": 23117, "count": 66391, "decode_str": " vent"} -{"id": 5301, "token": "\u0120comparison", "merges": "\u0120compar ison", "raw_count": 66406, "count": 66406, "decode_str": " comparison"} -{"id": 9518, "token": "ogether", "merges": "og ether", "raw_count": 26181, "count": 66420, "decode_str": "ogether"} -{"id": 48157, "token": "Movie", "merges": "Mov ie", "raw_count": 66428, "count": 66428, "decode_str": "Movie"} -{"id": 34866, "token": "SUCCESS", "merges": "SU CCESS", "raw_count": 66433, "count": 66433, "decode_str": "SUCCESS"} -{"id": 50029, "token": "\u0120overwrite", "merges": "\u0120over write", "raw_count": 66443, "count": 66443, "decode_str": " overwrite"} -{"id": 24199, "token": "\u0120listener", "merges": "\u0120list ener", "raw_count": 66446, "count": 66446, "decode_str": " listener"} -{"id": 32272, "token": "PACK", "merges": "P ACK", "raw_count": 66447, "count": 66447, "decode_str": "PACK"} -{"id": 10336, "token": "\u0120architecture", "merges": "\u0120architect ure", "raw_count": 66454, "count": 66454, "decode_str": " architecture"} -{"id": 18944, "token": "acs", "merges": "ac s", "raw_count": 66455, "count": 66455, "decode_str": "acs"} -{"id": 29569, "token": "Story", "merges": "St ory", "raw_count": 66457, "count": 66457, "decode_str": "Story"} -{"id": 40315, "token": "\u0120guinea", "merges": "\u0120gu inea", "raw_count": 66459, "count": 66459, "decode_str": " guinea"} -{"id": 24575, "token": "Publ", "merges": "P ubl", "raw_count": 31907, "count": 66483, "decode_str": "Publ"} -{"id": 8881, "token": "\u0120debate", "merges": "\u0120deb ate", "raw_count": 66487, "count": 66487, "decode_str": " debate"} -{"id": 15312, "token": "\u0120wrapped", "merges": "\u0120wra pped", "raw_count": 66489, "count": 66489, "decode_str": " wrapped"} -{"id": 37638, "token": "finger", "merges": "f inger", "raw_count": 66492, "count": 66492, "decode_str": "finger"} -{"id": 26985, "token": "princ", "merges": "pr inc", "raw_count": 66516, "count": 66516, "decode_str": "princ"} -{"id": 24767, "token": "within", "merges": "with in", "raw_count": 66525, "count": 66525, "decode_str": "within"} -{"id": 26017, "token": "fits", "merges": "f its", "raw_count": 65102, "count": 66532, "decode_str": "fits"} -{"id": 24889, "token": "invest", "merges": "in vest", "raw_count": 66543, "count": 66543, "decode_str": "invest"} -{"id": 45329, "token": "mV", "merges": "m V", "raw_count": 66550, "count": 66550, "decode_str": "mV"} -{"id": 7875, "token": "\u0120marriage", "merges": "\u0120mar riage", "raw_count": 66567, "count": 66567, "decode_str": " marriage"} -{"id": 39113, "token": "\u0120formatted", "merges": "\u0120form atted", "raw_count": 66568, "count": 66568, "decode_str": " formatted"} -{"id": 29028, "token": "\u0120Connection", "merges": "\u0120Conne ction", "raw_count": 66570, "count": 66570, "decode_str": " Connection"} -{"id": 5905, "token": "coh", "merges": "c oh", "raw_count": 32668, "count": 66588, "decode_str": "coh"} -{"id": 29561, "token": "\u0120workshops", "merges": "\u0120works hops", "raw_count": 66592, "count": 66592, "decode_str": " workshops"} -{"id": 4720, "token": "\u0120finally", "merges": "\u0120fin ally", "raw_count": 66592, "count": 66592, "decode_str": " finally"} -{"id": 38645, "token": "Fair", "merges": "F air", "raw_count": 66593, "count": 66593, "decode_str": "Fair"} -{"id": 19611, "token": "Utils", "merges": "Util s", "raw_count": 66605, "count": 66605, "decode_str": "Utils"} -{"id": 24066, "token": "ORDER", "merges": "ORD ER", "raw_count": 66617, "count": 66617, "decode_str": "ORDER"} -{"id": 11351, "token": "stable", "merges": "st able", "raw_count": 52142, "count": 66619, "decode_str": "stable"} -{"id": 6233, "token": "\u0120earn", "merges": "\u0120e arn", "raw_count": 25211, "count": 66621, "decode_str": " earn"} -{"id": 28105, "token": "Vari", "merges": "V ari", "raw_count": 34205, "count": 66665, "decode_str": "Vari"} -{"id": 22585, "token": "Own", "merges": "O wn", "raw_count": 28513, "count": 66668, "decode_str": "Own"} -{"id": 34659, "token": "OPS", "merges": "OP S", "raw_count": 66672, "count": 66672, "decode_str": "OPS"} -{"id": 41051, "token": "Computer", "merges": "Comput er", "raw_count": 66674, "count": 66674, "decode_str": "Computer"} -{"id": 50010, "token": "\u0120provisional", "merges": "\u0120provision al", "raw_count": 66678, "count": 66678, "decode_str": " provisional"} -{"id": 28274, "token": "Less", "merges": "L ess", "raw_count": 66682, "count": 66682, "decode_str": "Less"} -{"id": 41464, "token": "PREFIX", "merges": "PRE FIX", "raw_count": 66727, "count": 66727, "decode_str": "PREFIX"} -{"id": 18541, "token": "RECT", "merges": "RE CT", "raw_count": 29572, "count": 66730, "decode_str": "RECT"} -{"id": 2869, "token": "\u00e0\u00b8", "merges": "\u00e0 \u00b8", "raw_count": 9767, "count": 66735, "decode_str": "\ufffd"} -{"id": 35111, "token": "SUM", "merges": "S UM", "raw_count": 66745, "count": 66745, "decode_str": "SUM"} -{"id": 48557, "token": "\u0120bb", "merges": "\u0120b b", "raw_count": 66773, "count": 66773, "decode_str": " bb"} -{"id": 13583, "token": "\u0120incorrect", "merges": "\u0120incor rect", "raw_count": 56851, "count": 66780, "decode_str": " incorrect"} -{"id": 15608, "token": "profit", "merges": "pro fit", "raw_count": 65428, "count": 66787, "decode_str": "profit"} -{"id": 22659, "token": "picture", "merges": "p icture", "raw_count": 66321, "count": 66812, "decode_str": "picture"} -{"id": 13018, "token": "binding", "merges": "b inding", "raw_count": 66817, "count": 66817, "decode_str": "binding"} -{"id": 12514, "token": "\u0120symp", "merges": "\u0120sy mp", "raw_count": 51266, "count": 66830, "decode_str": " symp"} -{"id": 33468, "token": "Ru", "merges": "R u", "raw_count": 66845, "count": 66845, "decode_str": "Ru"} -{"id": 8574, "token": "\u0120coffee", "merges": "\u0120cof fee", "raw_count": 66848, "count": 66848, "decode_str": " coffee"} -{"id": 27843, "token": "CEPT", "merges": "CE PT", "raw_count": 42913, "count": 66859, "decode_str": "CEPT"} -{"id": 11583, "token": "\u012091", "merges": "\u01209 1", "raw_count": 66878, "count": 66878, "decode_str": " 91"} -{"id": 35906, "token": "Roy", "merges": "R oy", "raw_count": 66899, "count": 66899, "decode_str": "Roy"} -{"id": 37912, "token": "Doug", "merges": "D oug", "raw_count": 66916, "count": 66916, "decode_str": "Doug"} -{"id": 5935, "token": "\u0120TO", "merges": "\u0120T O", "raw_count": 66941, "count": 66941, "decode_str": " TO"} -{"id": 14606, "token": "javascript", "merges": "j avascript", "raw_count": 66954, "count": 66954, "decode_str": "javascript"} -{"id": 31673, "token": "Sta", "merges": "S ta", "raw_count": 39973, "count": 66959, "decode_str": "Sta"} -{"id": 12071, "token": "five", "merges": "f ive", "raw_count": 66969, "count": 66969, "decode_str": "five"} -{"id": 33319, "token": "Ol", "merges": "O l", "raw_count": 66975, "count": 66975, "decode_str": "Ol"} -{"id": 9894, "token": "\u0120periods", "merges": "\u0120period s", "raw_count": 66977, "count": 66977, "decode_str": " periods"} -{"id": 10721, "token": "\u0120magic", "merges": "\u0120mag ic", "raw_count": 66985, "count": 66985, "decode_str": " magic"} -{"id": 32914, "token": "Hit", "merges": "H it", "raw_count": 66996, "count": 66996, "decode_str": "Hit"} -{"id": 46991, "token": "fraction", "merges": "f raction", "raw_count": 67028, "count": 67028, "decode_str": "fraction"} -{"id": 44051, "token": "XI", "merges": "X I", "raw_count": 67034, "count": 67034, "decode_str": "XI"} -{"id": 9159, "token": "\u0120offering", "merges": "\u0120off ering", "raw_count": 67039, "count": 67039, "decode_str": " offering"} -{"id": 15681, "token": "sea", "merges": "se a", "raw_count": 66832, "count": 67066, "decode_str": "sea"} -{"id": 32628, "token": "past", "merges": "p ast", "raw_count": 67068, "count": 67068, "decode_str": "past"} -{"id": 41943, "token": "Dot", "merges": "D ot", "raw_count": 67080, "count": 67080, "decode_str": "Dot"} -{"id": 7118, "token": "\u0120sections", "merges": "\u0120se ctions", "raw_count": 67081, "count": 67081, "decode_str": " sections"} -{"id": 35782, "token": "meter", "merges": "m eter", "raw_count": 67081, "count": 67081, "decode_str": "meter"} -{"id": 16237, "token": "\u0120bos", "merges": "\u0120b os", "raw_count": 66012, "count": 67084, "decode_str": " bos"} -{"id": 31993, "token": "\u0120TEST", "merges": "\u0120TE ST", "raw_count": 67099, "count": 67099, "decode_str": " TEST"} -{"id": 8804, "token": "\u00d0\u00be\u00d0\u00b4", "merges": "\u00d0\u00be\u00d0 \u00b4", "raw_count": 43807, "count": 67100, "decode_str": "\u043e\u0434"} -{"id": 14232, "token": "\u0120punishment", "merges": "\u0120pun ishment", "raw_count": 67123, "count": 67123, "decode_str": " punishment"} -{"id": 20666, "token": "income", "merges": "inc ome", "raw_count": 67141, "count": 67141, "decode_str": "income"} -{"id": 5504, "token": "uced", "merges": "u ced", "raw_count": 7620, "count": 67141, "decode_str": "uced"} -{"id": 8321, "token": "\u0120disappe", "merges": "\u0120dis appe", "raw_count": 68, "count": 67143, "decode_str": " disappe"} -{"id": 41676, "token": "Saint", "merges": "S aint", "raw_count": 67165, "count": 67165, "decode_str": "Saint"} -{"id": 5742, "token": "\u0120specifically", "merges": "\u0120spec ifically", "raw_count": 67168, "count": 67168, "decode_str": " specifically"} -{"id": 30568, "token": "nov", "merges": "n ov", "raw_count": 67171, "count": 67171, "decode_str": "nov"} -{"id": 15834, "token": "abstract", "merges": "ab stract", "raw_count": 67189, "count": 67189, "decode_str": "abstract"} -{"id": 10430, "token": "\u0120sending", "merges": "\u0120s ending", "raw_count": 67231, "count": 67231, "decode_str": " sending"} -{"id": 29597, "token": "\u00ec\u0126", "merges": "\u00ec \u0126", "raw_count": 32364, "count": 67233, "decode_str": "\ufffd"} -{"id": 44906, "token": "Maria", "merges": "M aria", "raw_count": 67234, "count": 67234, "decode_str": "Maria"} -{"id": 6519, "token": "\u0120speech", "merges": "\u0120spe ech", "raw_count": 67239, "count": 67239, "decode_str": " speech"} -{"id": 5659, "token": "\u0120programs", "merges": "\u0120pro grams", "raw_count": 67246, "count": 67246, "decode_str": " programs"} -{"id": 15326, "token": "arms", "merges": "ar ms", "raw_count": 39652, "count": 67253, "decode_str": "arms"} -{"id": 13233, "token": "gly", "merges": "g ly", "raw_count": 21180, "count": 67262, "decode_str": "gly"} -{"id": 41296, "token": "Song", "merges": "S ong", "raw_count": 67273, "count": 67273, "decode_str": "Song"} -{"id": 36289, "token": "pieces", "merges": "pie ces", "raw_count": 67286, "count": 67286, "decode_str": "pieces"} -{"id": 17553, "token": "0010", "merges": "00 10", "raw_count": 67297, "count": 67297, "decode_str": "0010"} -{"id": 35592, "token": "\u0120Parse", "merges": "\u0120Par se", "raw_count": 67298, "count": 67298, "decode_str": " Parse"} -{"id": 39943, "token": "confidence", "merges": "conf idence", "raw_count": 67302, "count": 67302, "decode_str": "confidence"} -{"id": 15280, "token": "owned", "merges": "own ed", "raw_count": 59351, "count": 67306, "decode_str": "owned"} -{"id": 23017, "token": "\u0120Save", "merges": "\u0120S ave", "raw_count": 67321, "count": 67321, "decode_str": " Save"} -{"id": 16538, "token": "undo", "merges": "und o", "raw_count": 62865, "count": 67321, "decode_str": "undo"} -{"id": 42299, "token": "Thom", "merges": "Th om", "raw_count": 67335, "count": 67335, "decode_str": "Thom"} -{"id": 41399, "token": "\u01201080", "merges": "\u012010 80", "raw_count": 67342, "count": 67342, "decode_str": " 1080"} -{"id": 30567, "token": "wk", "merges": "w k", "raw_count": 67345, "count": 67345, "decode_str": "wk"} -{"id": 34925, "token": "Scene", "merges": "Sc ene", "raw_count": 67373, "count": 67373, "decode_str": "Scene"} -{"id": 7537, "token": "\u0120sand", "merges": "\u0120s and", "raw_count": 52192, "count": 67384, "decode_str": " sand"} -{"id": 24573, "token": "America", "merges": "Americ a", "raw_count": 67392, "count": 67392, "decode_str": "America"} -{"id": 21868, "token": "\u0120ray", "merges": "\u0120r ay", "raw_count": 67441, "count": 67441, "decode_str": " ray"} -{"id": 20494, "token": "\u0120nested", "merges": "\u0120n ested", "raw_count": 67454, "count": 67454, "decode_str": " nested"} -{"id": 33878, "token": "Ter", "merges": "T er", "raw_count": 67455, "count": 67455, "decode_str": "Ter"} -{"id": 24681, "token": "Mom", "merges": "M om", "raw_count": 67474, "count": 67474, "decode_str": "Mom"} -{"id": 39324, "token": "Josh", "merges": "J osh", "raw_count": 67486, "count": 67486, "decode_str": "Josh"} -{"id": 9515, "token": "gence", "merges": "g ence", "raw_count": 19228, "count": 67497, "decode_str": "gence"} -{"id": 14093, "token": "\u0120lux", "merges": "\u0120l ux", "raw_count": 30473, "count": 67515, "decode_str": " lux"} -{"id": 24358, "token": "FORM", "merges": "FOR M", "raw_count": 55849, "count": 67517, "decode_str": "FORM"} -{"id": 7315, "token": "\u0120television", "merges": "\u0120tele vision", "raw_count": 67533, "count": 67533, "decode_str": " television"} -{"id": 15307, "token": "\u0120ta", "merges": "\u0120t a", "raw_count": 67540, "count": 67540, "decode_str": " ta"} -{"id": 4472, "token": "\u0120Stud", "merges": "\u0120St ud", "raw_count": 1003, "count": 67543, "decode_str": " Stud"} -{"id": 9583, "token": "\u0120engaged", "merges": "\u0120eng aged", "raw_count": 67549, "count": 67549, "decode_str": " engaged"} -{"id": 10893, "token": "\u0120intellect", "merges": "\u0120intel lect", "raw_count": 4377, "count": 67552, "decode_str": " intellect"} -{"id": 28965, "token": "atio", "merges": "at io", "raw_count": 20594, "count": 67560, "decode_str": "atio"} -{"id": 9509, "token": "\u0120facility", "merges": "\u0120fac ility", "raw_count": 67564, "count": 67564, "decode_str": " facility"} -{"id": 4813, "token": "\u0120exhib", "merges": "\u0120ex hib", "raw_count": 3050, "count": 67580, "decode_str": " exhib"} -{"id": 13190, "token": "ITION", "merges": "IT ION", "raw_count": 56802, "count": 67603, "decode_str": "ITION"} -{"id": 22854, "token": "asters", "merges": "as ters", "raw_count": 23425, "count": 67619, "decode_str": "asters"} -{"id": 13563, "token": "\u01201982", "merges": "\u012019 82", "raw_count": 67620, "count": 67620, "decode_str": " 1982"} -{"id": 8886, "token": "\u0120clock", "merges": "\u0120cl ock", "raw_count": 67621, "count": 67621, "decode_str": " clock"} -{"id": 3475, "token": "\u0120ox", "merges": "\u0120o x", "raw_count": 30352, "count": 67626, "decode_str": " ox"} -{"id": 12423, "token": "\u0120arc", "merges": "\u0120ar c", "raw_count": 67638, "count": 67638, "decode_str": " arc"} -{"id": 19969, "token": "\u0120observer", "merges": "\u0120obser ver", "raw_count": 67639, "count": 67639, "decode_str": " observer"} -{"id": 33483, "token": "ruce", "merges": "ru ce", "raw_count": 67644, "count": 67644, "decode_str": "ruce"} -{"id": 22166, "token": "Special", "merges": "Spec ial", "raw_count": 67653, "count": 67653, "decode_str": "Special"} -{"id": 5939, "token": "\u0120distributed", "merges": "\u0120dist ributed", "raw_count": 67657, "count": 67657, "decode_str": " distributed"} -{"id": 44243, "token": "QT", "merges": "Q T", "raw_count": 67663, "count": 67663, "decode_str": "QT"} -{"id": 12313, "token": "buntu", "merges": "b untu", "raw_count": 515, "count": 67666, "decode_str": "buntu"} -{"id": 5697, "token": "\u0120ideas", "merges": "\u0120ide as", "raw_count": 67697, "count": 67697, "decode_str": " ideas"} -{"id": 10988, "token": "\u0120stations", "merges": "\u0120st ations", "raw_count": 67703, "count": 67703, "decode_str": " stations"} -{"id": 30991, "token": "altern", "merges": "al tern", "raw_count": 67745, "count": 67745, "decode_str": "altern"} -{"id": 24608, "token": "TABLE", "merges": "T ABLE", "raw_count": 67757, "count": 67757, "decode_str": "TABLE"} -{"id": 6856, "token": "oking", "merges": "ok ing", "raw_count": 28518, "count": 67768, "decode_str": "oking"} -{"id": 46788, "token": "lite", "merges": "l ite", "raw_count": 67782, "count": 67782, "decode_str": "lite"} -{"id": 28130, "token": "},{", "merges": "}, {", "raw_count": 67785, "count": 67785, "decode_str": "},{"} -{"id": 28243, "token": "\u0120ui", "merges": "\u0120u i", "raw_count": 67799, "count": 67799, "decode_str": " ui"} -{"id": 10077, "token": "\u00d0\u00b5\u00d0\u00bc", "merges": "\u00d0\u00b5\u00d0 \u00bc", "raw_count": 56715, "count": 67806, "decode_str": "\u0435\u043c"} -{"id": 10591, "token": "\u0120refe", "merges": "\u0120re fe", "raw_count": 11280, "count": 67820, "decode_str": " refe"} -{"id": 18465, "token": "\u0120holy", "merges": "\u0120hol y", "raw_count": 67833, "count": 67833, "decode_str": " holy"} -{"id": 11407, "token": "\u0120executed", "merges": "\u0120exec uted", "raw_count": 67834, "count": 67834, "decode_str": " executed"} -{"id": 3500, "token": "\u0120hyp", "merges": "\u0120hy p", "raw_count": 29695, "count": 67856, "decode_str": " hyp"} -{"id": 38416, "token": "`:", "merges": "` :", "raw_count": 67860, "count": 67860, "decode_str": "`:"} -{"id": 25642, "token": "uba", "merges": "ub a", "raw_count": 67861, "count": 67861, "decode_str": "uba"} -{"id": 24991, "token": "schemas", "merges": "schem as", "raw_count": 67871, "count": 67871, "decode_str": "schemas"} -{"id": 8342, "token": "\u0120plain", "merges": "\u0120pl ain", "raw_count": 65403, "count": 67879, "decode_str": " plain"} -{"id": 47076, "token": "passed", "merges": "pass ed", "raw_count": 67885, "count": 67885, "decode_str": "passed"} -{"id": 9136, "token": "\u0120powers", "merges": "\u0120pow ers", "raw_count": 67899, "count": 67899, "decode_str": " powers"} -{"id": 5928, "token": "\u0120absence", "merges": "\u0120abs ence", "raw_count": 67908, "count": 67908, "decode_str": " absence"} -{"id": 8534, "token": "\u0120acting", "merges": "\u0120act ing", "raw_count": 67925, "count": 67925, "decode_str": " acting"} -{"id": 31073, "token": "GV", "merges": "G V", "raw_count": 67952, "count": 67952, "decode_str": "GV"} -{"id": 46415, "token": "yml", "merges": "ym l", "raw_count": 67954, "count": 67954, "decode_str": "yml"} -{"id": 37389, "token": "ENTER", "merges": "ENT ER", "raw_count": 67972, "count": 67972, "decode_str": "ENTER"} -{"id": 31766, "token": "Fn", "merges": "F n", "raw_count": 67981, "count": 67981, "decode_str": "Fn"} -{"id": 15607, "token": "\u0120permissions", "merges": "\u0120per missions", "raw_count": 68005, "count": 68005, "decode_str": " permissions"} -{"id": 17059, "token": "\u0120threads", "merges": "\u0120thread s", "raw_count": 68006, "count": 68006, "decode_str": " threads"} -{"id": 23210, "token": "flex", "merges": "f lex", "raw_count": 68028, "count": 68028, "decode_str": "flex"} -{"id": 40568, "token": "Hook", "merges": "H ook", "raw_count": 68028, "count": 68028, "decode_str": "Hook"} -{"id": 18536, "token": "\u0120anchor", "merges": "\u0120anch or", "raw_count": 68043, "count": 68043, "decode_str": " anchor"} -{"id": 32687, "token": "amazon", "merges": "amaz on", "raw_count": 68051, "count": 68051, "decode_str": "amazon"} -{"id": 50888, "token": "\u00e5\u012f\u00ae", "merges": "\u00e5\u012f \u00ae", "raw_count": 68055, "count": 68055, "decode_str": "\u536e"} -{"id": 29810, "token": "\u0120decoder", "merges": "\u0120dec oder", "raw_count": 68069, "count": 68069, "decode_str": " decoder"} -{"id": 12603, "token": "0002", "merges": "000 2", "raw_count": 68072, "count": 68072, "decode_str": "0002"} -{"id": 12650, "token": "\u0120normalized", "merges": "\u0120normal ized", "raw_count": 68080, "count": 68080, "decode_str": " normalized"} -{"id": 37151, "token": "DIV", "merges": "D IV", "raw_count": 68120, "count": 68120, "decode_str": "DIV"} -{"id": 28973, "token": "aurant", "merges": "aur ant", "raw_count": 63308, "count": 68136, "decode_str": "aurant"} -{"id": 20486, "token": "\u0120configure", "merges": "\u0120config ure", "raw_count": 68143, "count": 68143, "decode_str": " configure"} -{"id": 16696, "token": "\u0120criter", "merges": "\u0120crit er", "raw_count": 2424, "count": 68146, "decode_str": " criter"} -{"id": 26216, "token": "Aff", "merges": "A ff", "raw_count": 67361, "count": 68157, "decode_str": "Aff"} -{"id": 7171, "token": "\u0120beat", "merges": "\u0120be at", "raw_count": 58948, "count": 68165, "decode_str": " beat"} -{"id": 12472, "token": "\u0120116", "merges": "\u01201 16", "raw_count": 68190, "count": 68190, "decode_str": " 116"} -{"id": 13630, "token": "\u0120discount", "merges": "\u0120disc ount", "raw_count": 44366, "count": 68206, "decode_str": " discount"} -{"id": 35923, "token": "Pb", "merges": "P b", "raw_count": 68208, "count": 68208, "decode_str": "Pb"} -{"id": 7760, "token": "aped", "merges": "ap ed", "raw_count": 35711, "count": 68228, "decode_str": "aped"} -{"id": 27493, "token": "ulo", "merges": "ul o", "raw_count": 68234, "count": 68234, "decode_str": "ulo"} -{"id": 18030, "token": "Editor", "merges": "Ed itor", "raw_count": 68244, "count": 68244, "decode_str": "Editor"} -{"id": 27300, "token": "SEL", "merges": "SE L", "raw_count": 68249, "count": 68249, "decode_str": "SEL"} -{"id": 11762, "token": "\u0120worldwide", "merges": "\u0120world wide", "raw_count": 68250, "count": 68250, "decode_str": " worldwide"} -{"id": 9593, "token": "ican", "merges": "ic an", "raw_count": 67653, "count": 68251, "decode_str": "ican"} -{"id": 9732, "token": "\u0120teacher", "merges": "\u0120teac her", "raw_count": 68253, "count": 68253, "decode_str": " teacher"} -{"id": 19566, "token": "\u0120Write", "merges": "\u0120W rite", "raw_count": 68259, "count": 68259, "decode_str": " Write"} -{"id": 2678, "token": "\u0120Coun", "merges": "\u0120C oun", "raw_count": 1235, "count": 68259, "decode_str": " Coun"} -{"id": 50395, "token": "\u00e3\u0122\u0136", "merges": "\u00e3\u0122 \u0136", "raw_count": 68270, "count": 68270, "decode_str": "\u3014"} -{"id": 8537, "token": "zing", "merges": "z ing", "raw_count": 44312, "count": 68275, "decode_str": "zing"} -{"id": 29002, "token": "\u0120oversight", "merges": "\u0120over sight", "raw_count": 68279, "count": 68279, "decode_str": " oversight"} -{"id": 50396, "token": "\u00e3\u0122\u0137", "merges": "\u00e3\u0122 \u0137", "raw_count": 68294, "count": 68294, "decode_str": "\u3015"} -{"id": 39792, "token": "fet", "merges": "f et", "raw_count": 68317, "count": 68317, "decode_str": "fet"} -{"id": 10032, "token": "\u0120entr", "merges": "\u0120ent r", "raw_count": 19965, "count": 68320, "decode_str": " entr"} -{"id": 22983, "token": "\u00eb\u012c", "merges": "\u00eb \u012c", "raw_count": 6231, "count": 68345, "decode_str": "\ufffd"} -{"id": 9192, "token": "\u0120furn", "merges": "\u0120f urn", "raw_count": 5201, "count": 68347, "decode_str": " furn"} -{"id": 31742, "token": "Ty", "merges": "T y", "raw_count": 68354, "count": 68354, "decode_str": "Ty"} -{"id": 5666, "token": "enced", "merges": "en ced", "raw_count": 11918, "count": 68364, "decode_str": "enced"} -{"id": 8555, "token": "\u0120mic", "merges": "\u0120m ic", "raw_count": 35258, "count": 68367, "decode_str": " mic"} -{"id": 6242, "token": "\u0120existence", "merges": "\u0120exist ence", "raw_count": 68372, "count": 68372, "decode_str": " existence"} -{"id": 8028, "token": "\u0120listen", "merges": "\u0120list en", "raw_count": 57682, "count": 68382, "decode_str": " listen"} -{"id": 22178, "token": "RET", "merges": "RE T", "raw_count": 39892, "count": 68382, "decode_str": "RET"} -{"id": 13890, "token": "elli", "merges": "ell i", "raw_count": 68387, "count": 68387, "decode_str": "elli"} -{"id": 10138, "token": "\u0120conform", "merges": "\u0120con form", "raw_count": 31134, "count": 68389, "decode_str": " conform"} -{"id": 34943, "token": "literal", "merges": "lit eral", "raw_count": 68398, "count": 68398, "decode_str": "literal"} -{"id": 37272, "token": "IFE", "merges": "IF E", "raw_count": 65008, "count": 68398, "decode_str": "IFE"} -{"id": 31034, "token": "HQ", "merges": "H Q", "raw_count": 68423, "count": 68423, "decode_str": "HQ"} -{"id": 7242, "token": "\u0120abuse", "merges": "\u0120ab use", "raw_count": 68450, "count": 68450, "decode_str": " abuse"} -{"id": 4439, "token": "\u0120released", "merges": "\u0120rele ased", "raw_count": 68456, "count": 68456, "decode_str": " released"} -{"id": 46492, "token": "MAG", "merges": "M AG", "raw_count": 68468, "count": 68468, "decode_str": "MAG"} -{"id": 30151, "token": "\u0120chunks", "merges": "\u0120ch unks", "raw_count": 68494, "count": 68494, "decode_str": " chunks"} -{"id": 7184, "token": "wed", "merges": "w ed", "raw_count": 43454, "count": 68498, "decode_str": "wed"} -{"id": 33338, "token": "bol", "merges": "b ol", "raw_count": 68515, "count": 68515, "decode_str": "bol"} -{"id": 7169, "token": "\u0120granted", "merges": "\u0120grant ed", "raw_count": 68517, "count": 68517, "decode_str": " granted"} -{"id": 47134, "token": "Arc", "merges": "Ar c", "raw_count": 68518, "count": 68518, "decode_str": "Arc"} -{"id": 11343, "token": "\u0120115", "merges": "\u01201 15", "raw_count": 68532, "count": 68532, "decode_str": " 115"} -{"id": 28264, "token": "yx", "merges": "y x", "raw_count": 68537, "count": 68537, "decode_str": "yx"} -{"id": 5500, "token": "\u0120cup", "merges": "\u0120c up", "raw_count": 59982, "count": 68541, "decode_str": " cup"} -{"id": 6600, "token": "\u0120aware", "merges": "\u0120a ware", "raw_count": 68543, "count": 68543, "decode_str": " aware"} -{"id": 6715, "token": "\u00d1\u0127", "merges": "\u00d1 \u0127", "raw_count": 21797, "count": 68547, "decode_str": "\u0445"} -{"id": 43579, "token": "\u0120tai", "merges": "\u0120t ai", "raw_count": 68548, "count": 68548, "decode_str": " tai"} -{"id": 21901, "token": "ELD", "merges": "EL D", "raw_count": 23354, "count": 68556, "decode_str": "ELD"} -{"id": 10544, "token": "\u0120elected", "merges": "\u0120elect ed", "raw_count": 68559, "count": 68559, "decode_str": " elected"} -{"id": 18913, "token": "Europe", "merges": "E urope", "raw_count": 31104, "count": 68561, "decode_str": "Europe"} -{"id": 47391, "token": "Ye", "merges": "Y e", "raw_count": 68561, "count": 68561, "decode_str": "Ye"} -{"id": 18970, "token": "kar", "merges": "k ar", "raw_count": 68562, "count": 68562, "decode_str": "kar"} -{"id": 35147, "token": "Mas", "merges": "M as", "raw_count": 68582, "count": 68582, "decode_str": "Mas"} -{"id": 30081, "token": "Imp", "merges": "I mp", "raw_count": 68604, "count": 68604, "decode_str": "Imp"} -{"id": 14260, "token": "\u0120hi", "merges": "\u0120h i", "raw_count": 68643, "count": 68643, "decode_str": " hi"} -{"id": 14149, "token": "\u0120emerging", "merges": "\u0120emerg ing", "raw_count": 68645, "count": 68645, "decode_str": " emerging"} -{"id": 15975, "token": "\u0120tweet", "merges": "\u0120t weet", "raw_count": 67781, "count": 68647, "decode_str": " tweet"} -{"id": 6670, "token": "\u0120digit", "merges": "\u0120dig it", "raw_count": 66569, "count": 68660, "decode_str": " digit"} -{"id": 12712, "token": "\u0120contracts", "merges": "\u0120contract s", "raw_count": 68677, "count": 68677, "decode_str": " contracts"} -{"id": 6442, "token": "\u0120PD", "merges": "\u0120P D", "raw_count": 39932, "count": 68699, "decode_str": " PD"} -{"id": 18857, "token": "\u0120canvas", "merges": "\u0120can vas", "raw_count": 68702, "count": 68702, "decode_str": " canvas"} -{"id": 44240, "token": "Edward", "merges": "Ed ward", "raw_count": 68713, "count": 68713, "decode_str": "Edward"} -{"id": 7274, "token": "\u0120approaches", "merges": "\u0120appro aches", "raw_count": 68715, "count": 68715, "decode_str": " approaches"} -{"id": 35947, "token": "Safe", "merges": "S afe", "raw_count": 68716, "count": 68716, "decode_str": "Safe"} -{"id": 9998, "token": "-----------", "merges": "-------- ---", "raw_count": 56699, "count": 68722, "decode_str": "-----------"} -{"id": 48701, "token": "[_", "merges": "[ _", "raw_count": 68730, "count": 68730, "decode_str": "[_"} -{"id": 14979, "token": "\u0120Arg", "merges": "\u0120Ar g", "raw_count": 36984, "count": 68738, "decode_str": " Arg"} -{"id": 7027, "token": "\u0120lie", "merges": "\u0120l ie", "raw_count": 59196, "count": 68740, "decode_str": " lie"} -{"id": 24882, "token": "\u0120Output", "merges": "\u0120Out put", "raw_count": 68783, "count": 68783, "decode_str": " Output"} -{"id": 15811, "token": "erge", "merges": "er ge", "raw_count": 10851, "count": 68787, "decode_str": "erge"} -{"id": 23486, "token": "INST", "merges": "IN ST", "raw_count": 46670, "count": 68790, "decode_str": "INST"} -{"id": 8074, "token": "mosp", "merges": "m osp", "raw_count": 11875, "count": 68791, "decode_str": "mosp"} -{"id": 39061, "token": "forum", "merges": "for um", "raw_count": 68800, "count": 68800, "decode_str": "forum"} -{"id": 6913, "token": "\u0120nod", "merges": "\u0120n od", "raw_count": 54262, "count": 68800, "decode_str": " nod"} -{"id": 35296, "token": "\u00eb\u00a1\u013e", "merges": "\u00eb\u00a1 \u013e", "raw_count": 68806, "count": 68806, "decode_str": "\ub85c"} -{"id": 20036, "token": "\u0120departments", "merges": "\u0120depart ments", "raw_count": 68810, "count": 68810, "decode_str": " departments"} -{"id": 45947, "token": "\u0120Compute", "merges": "\u0120Comput e", "raw_count": 68818, "count": 68818, "decode_str": " Compute"} -{"id": 6364, "token": "ears", "merges": "ear s", "raw_count": 42874, "count": 68818, "decode_str": "ears"} -{"id": 7556, "token": "icious", "merges": "ic ious", "raw_count": 31618, "count": 68823, "decode_str": "icious"} -{"id": 10459, "token": "\u0120corporate", "merges": "\u0120corpor ate", "raw_count": 68828, "count": 68828, "decode_str": " corporate"} -{"id": 42096, "token": "mob", "merges": "m ob", "raw_count": 68828, "count": 68828, "decode_str": "mob"} -{"id": 9099, "token": "\u0120consequences", "merges": "\u0120consequ ences", "raw_count": 68839, "count": 68839, "decode_str": " consequences"} -{"id": 26477, "token": "Week", "merges": "We ek", "raw_count": 68857, "count": 68857, "decode_str": "Week"} -{"id": 18992, "token": "Release", "merges": "Re lease", "raw_count": 68861, "count": 68861, "decode_str": "Release"} -{"id": 8128, "token": "\u0120fees", "merges": "\u0120fe es", "raw_count": 68863, "count": 68863, "decode_str": " fees"} -{"id": 12501, "token": "Put", "merges": "P ut", "raw_count": 68875, "count": 68875, "decode_str": "Put"} -{"id": 6883, "token": "\u0120receiving", "merges": "\u0120rece iving", "raw_count": 68883, "count": 68883, "decode_str": " receiving"} -{"id": 34733, "token": "Depth", "merges": "Dep th", "raw_count": 68884, "count": 68884, "decode_str": "Depth"} -{"id": 31146, "token": "Failure", "merges": "F ailure", "raw_count": 68926, "count": 68926, "decode_str": "Failure"} -{"id": 1244, "token": "\u0120And", "merges": "\u0120An d", "raw_count": 40535, "count": 68945, "decode_str": " And"} -{"id": 20309, "token": "outing", "merges": "out ing", "raw_count": 68997, "count": 68997, "decode_str": "outing"} -{"id": 18812, "token": "Men", "merges": "M en", "raw_count": 68999, "count": 68999, "decode_str": "Men"} -{"id": 8624, "token": "\u0120principal", "merges": "\u0120princip al", "raw_count": 69035, "count": 69035, "decode_str": " principal"} -{"id": 48925, "token": "accum", "merges": "acc um", "raw_count": 69055, "count": 69055, "decode_str": "accum"} -{"id": 34586, "token": "prof", "merges": "pro f", "raw_count": 69056, "count": 69056, "decode_str": "prof"} -{"id": 21100, "token": "riz", "merges": "ri z", "raw_count": 63971, "count": 69056, "decode_str": "riz"} -{"id": 18980, "token": "akh", "merges": "ak h", "raw_count": 68965, "count": 69064, "decode_str": "akh"} -{"id": 25453, "token": "oshi", "merges": "os hi", "raw_count": 69084, "count": 69084, "decode_str": "oshi"} -{"id": 10178, "token": "had", "merges": "h ad", "raw_count": 69086, "count": 69086, "decode_str": "had"} -{"id": 24657, "token": "Ant", "merges": "An t", "raw_count": 69095, "count": 69095, "decode_str": "Ant"} -{"id": 51153, "token": "\u00e5\u013d\u012f", "merges": "\u00e5\u013d \u012f", "raw_count": 69096, "count": 69096, "decode_str": "\u56cd"} -{"id": 2766, "token": "+\\", "merges": "+ \\", "raw_count": 67160, "count": 69116, "decode_str": "+\\"} -{"id": 5400, "token": "\u0120album", "merges": "\u0120al bum", "raw_count": 57561, "count": 69130, "decode_str": " album"} -{"id": 5588, "token": "\u00c4\u00b1", "merges": "\u00c4 \u00b1", "raw_count": 43900, "count": 69141, "decode_str": "\u0131"} -{"id": 48683, "token": "chemy", "merges": "che my", "raw_count": 69150, "count": 69150, "decode_str": "chemy"} -{"id": 39334, "token": ">`", "merges": "> `", "raw_count": 69154, "count": 69154, "decode_str": ">`"} -{"id": 9623, "token": "iem", "merges": "i em", "raw_count": 57329, "count": 69157, "decode_str": "iem"} -{"id": 48369, "token": "biz", "merges": "b iz", "raw_count": 69157, "count": 69157, "decode_str": "biz"} -{"id": 7602, "token": "\u0120velocity", "merges": "\u0120veloc ity", "raw_count": 69159, "count": 69159, "decode_str": " velocity"} -{"id": 37680, "token": "Gre", "merges": "G re", "raw_count": 69175, "count": 69175, "decode_str": "Gre"} -{"id": 5131, "token": "\u0120Other", "merges": "\u0120O ther", "raw_count": 20608, "count": 69181, "decode_str": " Other"} -{"id": 8397, "token": "\u0120Dev", "merges": "\u0120D ev", "raw_count": 13337, "count": 69200, "decode_str": " Dev"} -{"id": 23376, "token": "\u0120\"*", "merges": "\u0120\" *", "raw_count": 69208, "count": 69208, "decode_str": " \"*"} -{"id": 15483, "token": "\u0120dated", "merges": "\u0120d ated", "raw_count": 69209, "count": 69209, "decode_str": " dated"} -{"id": 36868, "token": "LEVEL", "merges": "LEV EL", "raw_count": 69222, "count": 69222, "decode_str": "LEVEL"} -{"id": 6673, "token": "\u0120mel", "merges": "\u0120m el", "raw_count": 51907, "count": 69232, "decode_str": " mel"} -{"id": 2091, "token": "\u0120When", "merges": "\u0120W hen", "raw_count": 69262, "count": 69262, "decode_str": " When"} -{"id": 11848, "token": "\u0120expanded", "merges": "\u0120expand ed", "raw_count": 69282, "count": 69282, "decode_str": " expanded"} -{"id": 17893, "token": "itzerland", "merges": "itzer land", "raw_count": 68943, "count": 69307, "decode_str": "itzerland"} -{"id": 18504, "token": "\u0120sv", "merges": "\u0120s v", "raw_count": 69316, "count": 69316, "decode_str": " sv"} -{"id": 6015, "token": "\u0120repeated", "merges": "\u0120repe ated", "raw_count": 44891, "count": 69341, "decode_str": " repeated"} -{"id": 49718, "token": "urtle", "merges": "urt le", "raw_count": 69345, "count": 69345, "decode_str": "urtle"} -{"id": 9485, "token": "\u0120OS", "merges": "\u0120O S", "raw_count": 69358, "count": 69358, "decode_str": " OS"} -{"id": 19576, "token": "Help", "merges": "Hel p", "raw_count": 69409, "count": 69409, "decode_str": "Help"} -{"id": 36196, "token": "\u0120dc", "merges": "\u0120d c", "raw_count": 69470, "count": 69470, "decode_str": " dc"} -{"id": 21187, "token": "\u0120eu", "merges": "\u0120e u", "raw_count": 69481, "count": 69481, "decode_str": " eu"} -{"id": 13126, "token": "\u0120Product", "merges": "\u0120Pro duct", "raw_count": 60805, "count": 69493, "decode_str": " Product"} -{"id": 7687, "token": "\u0120od", "merges": "\u0120o d", "raw_count": 55112, "count": 69504, "decode_str": " od"} -{"id": 31659, "token": "pires", "merges": "pi res", "raw_count": 69508, "count": 69508, "decode_str": "pires"} -{"id": 31044, "token": "11111111", "merges": "1111 1111", "raw_count": 69521, "count": 69521, "decode_str": "11111111"} -{"id": 33426, "token": "pq", "merges": "p q", "raw_count": 69527, "count": 69527, "decode_str": "pq"} -{"id": 48351, "token": "DAC", "merges": "D AC", "raw_count": 69536, "count": 69536, "decode_str": "DAC"} -{"id": 6746, "token": "\u0120gar", "merges": "\u0120g ar", "raw_count": 21870, "count": 69544, "decode_str": " gar"} -{"id": 12874, "token": "\u0120CPU", "merges": "\u0120C PU", "raw_count": 69548, "count": 69548, "decode_str": " CPU"} -{"id": 16576, "token": "around", "merges": "ar ound", "raw_count": 57955, "count": 69551, "decode_str": "around"} -{"id": 17561, "token": "\u0120activate", "merges": "\u0120activ ate", "raw_count": 69555, "count": 69555, "decode_str": " activate"} -{"id": 29818, "token": "GTH", "merges": "G TH", "raw_count": 8569, "count": 69579, "decode_str": "GTH"} -{"id": 26672, "token": "adapt", "merges": "ad apt", "raw_count": 69602, "count": 69602, "decode_str": "adapt"} -{"id": 4865, "token": "\u0120binding", "merges": "\u0120b inding", "raw_count": 69613, "count": 69613, "decode_str": " binding"} -{"id": 15257, "token": "\u0120actively", "merges": "\u0120act ively", "raw_count": 69616, "count": 69616, "decode_str": " actively"} -{"id": 9001, "token": "\u0120sports", "merges": "\u0120s ports", "raw_count": 69617, "count": 69617, "decode_str": " sports"} -{"id": 16536, "token": "===", "merges": "== =", "raw_count": 66090, "count": 69621, "decode_str": "==="} -{"id": 9720, "token": "asi", "merges": "as i", "raw_count": 64187, "count": 69623, "decode_str": "asi"} -{"id": 48996, "token": "\u0120bs", "merges": "\u0120b s", "raw_count": 69631, "count": 69631, "decode_str": " bs"} -{"id": 20497, "token": "atible", "merges": "at ible", "raw_count": 1129, "count": 69649, "decode_str": "atible"} -{"id": 15671, "token": "phan", "merges": "ph an", "raw_count": 55906, "count": 69655, "decode_str": "phan"} -{"id": 12490, "token": "lined", "merges": "l ined", "raw_count": 35592, "count": 69676, "decode_str": "lined"} -{"id": 41000, "token": "\u0120'[", "merges": "\u0120' [", "raw_count": 69693, "count": 69693, "decode_str": " '["} -{"id": 32532, "token": "oracle", "merges": "or acle", "raw_count": 69709, "count": 69709, "decode_str": "oracle"} -{"id": 11131, "token": "irk", "merges": "ir k", "raw_count": 68722, "count": 69709, "decode_str": "irk"} -{"id": 3326, "token": "rote", "merges": "ro te", "raw_count": 16435, "count": 69718, "decode_str": "rote"} -{"id": 33951, "token": "bright", "merges": "b right", "raw_count": 69746, "count": 69746, "decode_str": "bright"} -{"id": 5963, "token": "\u0120judge", "merges": "\u0120jud ge", "raw_count": 69749, "count": 69749, "decode_str": " judge"} -{"id": 16626, "token": "habilitation", "merges": "habil itation", "raw_count": 3682, "count": 69752, "decode_str": "habilitation"} -{"id": 11646, "token": "\u0120codes", "merges": "\u0120c odes", "raw_count": 69760, "count": 69760, "decode_str": " codes"} -{"id": 24676, "token": "weighted", "merges": "weight ed", "raw_count": 69779, "count": 69779, "decode_str": "weighted"} -{"id": 29008, "token": "Bind", "merges": "B ind", "raw_count": 69779, "count": 69779, "decode_str": "Bind"} -{"id": 9781, "token": "\u0120liability", "merges": "\u0120li ability", "raw_count": 69781, "count": 69781, "decode_str": " liability"} -{"id": 19982, "token": "stick", "merges": "st ick", "raw_count": 69781, "count": 69781, "decode_str": "stick"} -{"id": 10141, "token": "\u0120checked", "merges": "\u0120check ed", "raw_count": 69782, "count": 69782, "decode_str": " checked"} -{"id": 19657, "token": "contr", "merges": "con tr", "raw_count": 26871, "count": 69811, "decode_str": "contr"} -{"id": 23693, "token": "techn", "merges": "te chn", "raw_count": 43230, "count": 69819, "decode_str": "techn"} -{"id": 39344, "token": "xz", "merges": "x z", "raw_count": 69826, "count": 69826, "decode_str": "xz"} -{"id": 7733, "token": "\u0120Work", "merges": "\u0120W ork", "raw_count": 63693, "count": 69852, "decode_str": " Work"} -{"id": 8338, "token": "\u0120explore", "merges": "\u0120expl ore", "raw_count": 59936, "count": 69855, "decode_str": " explore"} -{"id": 34881, "token": "transl", "merges": "trans l", "raw_count": 69873, "count": 69873, "decode_str": "transl"} -{"id": 12039, "token": "phy", "merges": "ph y", "raw_count": 68766, "count": 69874, "decode_str": "phy"} -{"id": 24431, "token": "Mouse", "merges": "M ouse", "raw_count": 69876, "count": 69876, "decode_str": "Mouse"} -{"id": 7605, "token": "\u0120statistical", "merges": "\u0120statist ical", "raw_count": 69877, "count": 69877, "decode_str": " statistical"} -{"id": 32357, "token": "Groups", "merges": "Gr oups", "raw_count": 69880, "count": 69880, "decode_str": "Groups"} -{"id": 9887, "token": "approx", "merges": "appro x", "raw_count": 69883, "count": 69883, "decode_str": "approx"} -{"id": 3780, "token": "\u0120anyone", "merges": "\u0120any one", "raw_count": 69890, "count": 69890, "decode_str": " anyone"} -{"id": 21727, "token": "Dam", "merges": "D am", "raw_count": 67744, "count": 69890, "decode_str": "Dam"} -{"id": 45840, "token": "Patrick", "merges": "Pat rick", "raw_count": 69892, "count": 69892, "decode_str": "Patrick"} -{"id": 24470, "token": "apa", "merges": "ap a", "raw_count": 69892, "count": 69892, "decode_str": "apa"} -{"id": 18748, "token": "\u0120filtered", "merges": "\u0120fil tered", "raw_count": 69896, "count": 69896, "decode_str": " filtered"} -{"id": 28463, "token": "Required", "merges": "Re quired", "raw_count": 69914, "count": 69914, "decode_str": "Required"} -{"id": 12748, "token": "\u0120difficulties", "merges": "\u0120difficult ies", "raw_count": 69921, "count": 69921, "decode_str": " difficulties"} -{"id": 4409, "token": "\u0120worth", "merges": "\u0120wor th", "raw_count": 52359, "count": 69927, "decode_str": " worth"} -{"id": 30813, "token": "pressed", "merges": "p ressed", "raw_count": 69917, "count": 69935, "decode_str": "pressed"} -{"id": 4734, "token": "\u0120pul", "merges": "\u0120p ul", "raw_count": 16863, "count": 69955, "decode_str": " pul"} -{"id": 40384, "token": "posal", "merges": "pos al", "raw_count": 69980, "count": 69980, "decode_str": "posal"} -{"id": 9760, "token": "unicip", "merges": "un icip", "raw_count": 3815, "count": 69987, "decode_str": "unicip"} -{"id": 30703, "token": "highlight", "merges": "high light", "raw_count": 69990, "count": 69990, "decode_str": "highlight"} -{"id": 8800, "token": "\u0120bear", "merges": "\u0120be ar", "raw_count": 59273, "count": 70000, "decode_str": " bear"} -{"id": 12141, "token": "\u0120guest", "merges": "\u0120gu est", "raw_count": 70001, "count": 70001, "decode_str": " guest"} -{"id": 42092, "token": "EG", "merges": "E G", "raw_count": 70003, "count": 70003, "decode_str": "EG"} -{"id": 17634, "token": "\u0120sanctions", "merges": "\u0120san ctions", "raw_count": 70008, "count": 70008, "decode_str": " sanctions"} -{"id": 12008, "token": "\u0120vice", "merges": "\u0120v ice", "raw_count": 70022, "count": 70022, "decode_str": " vice"} -{"id": 10881, "token": "abeth", "merges": "ab eth", "raw_count": 10013, "count": 70037, "decode_str": "abeth"} -{"id": 38034, "token": "Foundation", "merges": "Found ation", "raw_count": 70064, "count": 70064, "decode_str": "Foundation"} -{"id": 39052, "token": "kok", "merges": "k ok", "raw_count": 69746, "count": 70090, "decode_str": "kok"} -{"id": 19317, "token": "journal", "merges": "j ournal", "raw_count": 70118, "count": 70118, "decode_str": "journal"} -{"id": 45689, "token": "dong", "merges": "d ong", "raw_count": 70128, "count": 70128, "decode_str": "dong"} -{"id": 9092, "token": "\u0120tip", "merges": "\u0120t ip", "raw_count": 44148, "count": 70145, "decode_str": " tip"} -{"id": 12286, "token": "\u0120Pay", "merges": "\u0120P ay", "raw_count": 52804, "count": 70153, "decode_str": " Pay"} -{"id": 15336, "token": "\u0120bathroom", "merges": "\u0120bath room", "raw_count": 70177, "count": 70177, "decode_str": " bathroom"} -{"id": 8450, "token": "\u0120experiences", "merges": "\u0120experien ces", "raw_count": 70183, "count": 70183, "decode_str": " experiences"} -{"id": 38139, "token": "ifa", "merges": "if a", "raw_count": 70187, "count": 70187, "decode_str": "ifa"} -{"id": 8954, "token": "\u0120fro", "merges": "\u0120f ro", "raw_count": 37034, "count": 70188, "decode_str": " fro"} -{"id": 6773, "token": "\u0120fish", "merges": "\u0120f ish", "raw_count": 70190, "count": 70190, "decode_str": " fish"} -{"id": 21729, "token": "\u0120subscription", "merges": "\u0120sub scription", "raw_count": 70193, "count": 70193, "decode_str": " subscription"} -{"id": 43856, "token": ">\",", "merges": "> \",", "raw_count": 70195, "count": 70195, "decode_str": ">\","} -{"id": 3973, "token": "\u0120First", "merges": "\u0120F irst", "raw_count": 69771, "count": 70217, "decode_str": " First"} -{"id": 22656, "token": "OURCE", "merges": "OUR CE", "raw_count": 39326, "count": 70220, "decode_str": "OURCE"} -{"id": 13077, "token": "utt", "merges": "ut t", "raw_count": 53612, "count": 70238, "decode_str": "utt"} -{"id": 9149, "token": "\u0120BY", "merges": "\u0120B Y", "raw_count": 70243, "count": 70243, "decode_str": " BY"} -{"id": 29080, "token": "Constant", "merges": "Con stant", "raw_count": 70249, "count": 70249, "decode_str": "Constant"} -{"id": 12927, "token": "\u0120ocean", "merges": "\u0120o cean", "raw_count": 70287, "count": 70287, "decode_str": " ocean"} -{"id": 33812, "token": "Packet", "merges": "P acket", "raw_count": 70293, "count": 70293, "decode_str": "Packet"} -{"id": 26700, "token": "Neg", "merges": "N eg", "raw_count": 41503, "count": 70300, "decode_str": "Neg"} -{"id": 38675, "token": "\u00e7\u00b7", "merges": "\u00e7 \u00b7", "raw_count": 59397, "count": 70305, "decode_str": "\ufffd"} -{"id": 10166, "token": "\u0120trained", "merges": "\u0120tra ined", "raw_count": 70313, "count": 70313, "decode_str": " trained"} -{"id": 22425, "token": "tees", "merges": "te es", "raw_count": 9426, "count": 70313, "decode_str": "tees"} -{"id": 9766, "token": "\u0120manifest", "merges": "\u0120manif est", "raw_count": 51204, "count": 70324, "decode_str": " manifest"} -{"id": 5608, "token": "\u0120served", "merges": "\u0120serv ed", "raw_count": 70328, "count": 70328, "decode_str": " served"} -{"id": 16882, "token": "havior", "merges": "hav ior", "raw_count": 297, "count": 70347, "decode_str": "havior"} -{"id": 17591, "token": "iop", "merges": "i op", "raw_count": 70260, "count": 70354, "decode_str": "iop"} -{"id": 22107, "token": "\u0120transparency", "merges": "\u0120trans parency", "raw_count": 70379, "count": 70379, "decode_str": " transparency"} -{"id": 15050, "token": "\u0120routes", "merges": "\u0120rout es", "raw_count": 70405, "count": 70405, "decode_str": " routes"} -{"id": 7932, "token": "\u0120replaced", "merges": "\u0120repl aced", "raw_count": 70409, "count": 70409, "decode_str": " replaced"} -{"id": 15467, "token": "boost", "merges": "bo ost", "raw_count": 70420, "count": 70420, "decode_str": "boost"} -{"id": 5918, "token": "\u0120gal", "merges": "\u0120g al", "raw_count": 39172, "count": 70427, "decode_str": " gal"} -{"id": 31393, "token": "afka", "merges": "af ka", "raw_count": 70430, "count": 70430, "decode_str": "afka"} -{"id": 34752, "token": "Broad", "merges": "B road", "raw_count": 70442, "count": 70442, "decode_str": "Broad"} -{"id": 31956, "token": "\u00eb\u00a5", "merges": "\u00eb \u00a5", "raw_count": 16056, "count": 70455, "decode_str": "\ufffd"} -{"id": 15619, "token": "REF", "merges": "RE F", "raw_count": 69563, "count": 70468, "decode_str": "REF"} -{"id": 5536, "token": "\u0120heavy", "merges": "\u0120heav y", "raw_count": 70478, "count": 70478, "decode_str": " heavy"} -{"id": 14646, "token": "\u0120neighbour", "merges": "\u0120neigh bour", "raw_count": 24887, "count": 70483, "decode_str": " neighbour"} -{"id": 30655, "token": "\u0120deprecated", "merges": "\u0120dep recated", "raw_count": 70500, "count": 70500, "decode_str": " deprecated"} -{"id": 8137, "token": "\u0120identification", "merges": "\u0120ident ification", "raw_count": 70510, "count": 70510, "decode_str": " identification"} -{"id": 25814, "token": "049", "merges": "04 9", "raw_count": 70521, "count": 70521, "decode_str": "049"} -{"id": 6631, "token": "\u0120Service", "merges": "\u0120S ervice", "raw_count": 70524, "count": 70524, "decode_str": " Service"} -{"id": 47869, "token": "Unity", "merges": "Un ity", "raw_count": 70534, "count": 70534, "decode_str": "Unity"} -{"id": 27684, "token": "iw", "merges": "i w", "raw_count": 70534, "count": 70534, "decode_str": "iw"} -{"id": 4484, "token": "\u0120cool", "merges": "\u0120co ol", "raw_count": 42715, "count": 70545, "decode_str": " cool"} -{"id": 24306, "token": "Fields", "merges": "Field s", "raw_count": 70558, "count": 70558, "decode_str": "Fields"} -{"id": 9838, "token": "\u0120rein", "merges": "\u0120re in", "raw_count": 13000, "count": 70581, "decode_str": " rein"} -{"id": 47510, "token": "alex", "merges": "al ex", "raw_count": 70591, "count": 70591, "decode_str": "alex"} -{"id": 23885, "token": "\u0120ministers", "merges": "\u0120min isters", "raw_count": 70608, "count": 70608, "decode_str": " ministers"} -{"id": 5491, "token": "iced", "merges": "ic ed", "raw_count": 37735, "count": 70631, "decode_str": "iced"} -{"id": 42245, "token": "Angle", "merges": "An gle", "raw_count": 70639, "count": 70639, "decode_str": "Angle"} -{"id": 22454, "token": "\u0120TABLE", "merges": "\u0120T ABLE", "raw_count": 70650, "count": 70650, "decode_str": " TABLE"} -{"id": 29872, "token": "Dictionary", "merges": "D ictionary", "raw_count": 70651, "count": 70651, "decode_str": "Dictionary"} -{"id": 4718, "token": "};", "merges": "} ;", "raw_count": 51849, "count": 70693, "decode_str": "};"} -{"id": 39982, "token": "ainers", "merges": "ain ers", "raw_count": 70738, "count": 70738, "decode_str": "ainers"} -{"id": 5446, "token": "\u0120AD", "merges": "\u0120A D", "raw_count": 47158, "count": 70743, "decode_str": " AD"} -{"id": 7356, "token": "\u0120stick", "merges": "\u0120st ick", "raw_count": 33920, "count": 70752, "decode_str": " stick"} -{"id": 46481, "token": "ZX", "merges": "Z X", "raw_count": 70768, "count": 70768, "decode_str": "ZX"} -{"id": 46250, "token": "Paper", "merges": "P aper", "raw_count": 70773, "count": 70773, "decode_str": "Paper"} -{"id": 39874, "token": "director", "merges": "d irector", "raw_count": 70800, "count": 70800, "decode_str": "director"} -{"id": 7303, "token": "\u0120managed", "merges": "\u0120manag ed", "raw_count": 70805, "count": 70805, "decode_str": " managed"} -{"id": 32842, "token": "Remote", "merges": "Rem ote", "raw_count": 70829, "count": 70829, "decode_str": "Remote"} -{"id": 31792, "token": "oslav", "merges": "os lav", "raw_count": 70777, "count": 70830, "decode_str": "oslav"} -{"id": 40339, "token": "Jet", "merges": "J et", "raw_count": 70833, "count": 70833, "decode_str": "Jet"} -{"id": 32442, "token": "bay", "merges": "b ay", "raw_count": 70838, "count": 70838, "decode_str": "bay"} -{"id": 46225, "token": "York", "merges": "Y ork", "raw_count": 70853, "count": 70853, "decode_str": "York"} -{"id": 12883, "token": "\u0120muse", "merges": "\u0120mus e", "raw_count": 2085, "count": 70855, "decode_str": " muse"} -{"id": 51062, "token": "\u00e5\u0135\u0131", "merges": "\u00e5\u0135 \u0131", "raw_count": 70858, "count": 70858, "decode_str": "\u54cf"} -{"id": 24321, "token": "\u0120digits", "merges": "\u0120dig its", "raw_count": 70859, "count": 70859, "decode_str": " digits"} -{"id": 37547, "token": "STOP", "merges": "ST OP", "raw_count": 70866, "count": 70866, "decode_str": "STOP"} -{"id": 8493, "token": "\u0120reducing", "merges": "\u0120redu cing", "raw_count": 70869, "count": 70869, "decode_str": " reducing"} -{"id": 29255, "token": "Pot", "merges": "P ot", "raw_count": 70883, "count": 70883, "decode_str": "Pot"} -{"id": 6127, "token": "\u0120patterns", "merges": "\u0120pattern s", "raw_count": 70890, "count": 70890, "decode_str": " patterns"} -{"id": 8394, "token": "\u0120proportion", "merges": "\u0120proport ion", "raw_count": 70896, "count": 70896, "decode_str": " proportion"} -{"id": 9842, "token": "ermine", "merges": "erm ine", "raw_count": 27111, "count": 70896, "decode_str": "ermine"} -{"id": 15109, "token": "\u0120satellite", "merges": "\u0120satell ite", "raw_count": 70897, "count": 70897, "decode_str": " satellite"} -{"id": 9207, "token": "yst", "merges": "y st", "raw_count": 60396, "count": 70918, "decode_str": "yst"} -{"id": 8185, "token": "inton", "merges": "int on", "raw_count": 70346, "count": 70926, "decode_str": "inton"} -{"id": 33044, "token": "GAL", "merges": "G AL", "raw_count": 70929, "count": 70929, "decode_str": "GAL"} -{"id": 31420, "token": "ciliation", "merges": "cil iation", "raw_count": 14297, "count": 70933, "decode_str": "ciliation"} -{"id": 14277, "token": "", "merges": "\" />", "raw_count": 73068, "count": 73068, "decode_str": "\"/>"} -{"id": 23333, "token": "loading", "merges": "load ing", "raw_count": 73071, "count": 73071, "decode_str": "loading"} -{"id": 41392, "token": "Liu", "merges": "L iu", "raw_count": 73074, "count": 73074, "decode_str": "Liu"} -{"id": 13620, "token": "\u0120135", "merges": "\u01201 35", "raw_count": 73080, "count": 73080, "decode_str": " 135"} -{"id": 11078, "token": "rin", "merges": "r in", "raw_count": 71672, "count": 73083, "decode_str": "rin"} -{"id": 6647, "token": "\u0120AR", "merges": "\u0120A R", "raw_count": 65327, "count": 73099, "decode_str": " AR"} -{"id": 42278, "token": "Disk", "merges": "D isk", "raw_count": 73105, "count": 73105, "decode_str": "Disk"} -{"id": 4825, "token": "\u0120Em", "merges": "\u0120E m", "raw_count": 17712, "count": 73106, "decode_str": " Em"} -{"id": 44178, "token": "sales", "merges": "s ales", "raw_count": 73119, "count": 73119, "decode_str": "sales"} -{"id": 30872, "token": "sdk", "merges": "sd k", "raw_count": 73121, "count": 73121, "decode_str": "sdk"} -{"id": 50708, "token": "\u00e5\u0128\u0128", "merges": "\u00e5\u0128 \u0128", "raw_count": 73129, "count": 73129, "decode_str": "\u5186"} -{"id": 7997, "token": "\u0120instructions", "merges": "\u0120inst ructions", "raw_count": 73133, "count": 73133, "decode_str": " instructions"} -{"id": 24925, "token": "community", "merges": "commun ity", "raw_count": 73146, "count": 73146, "decode_str": "community"} -{"id": 14664, "token": "\u0120buff", "merges": "\u0120bu ff", "raw_count": 56535, "count": 73169, "decode_str": " buff"} -{"id": 45872, "token": "clos", "merges": "cl os", "raw_count": 73170, "count": 73170, "decode_str": "clos"} -{"id": 12590, "token": "\u0120::", "merges": "\u0120: :", "raw_count": 73170, "count": 73170, "decode_str": " ::"} -{"id": 12034, "token": "\u01201987", "merges": "\u012019 87", "raw_count": 73171, "count": 73171, "decode_str": " 1987"} -{"id": 22902, "token": "################################", "merges": "################ ################", "raw_count": 73172, "count": 73172, "decode_str": "################################"} -{"id": 7691, "token": "\u0120cof", "merges": "\u0120co f", "raw_count": 6324, "count": 73172, "decode_str": " cof"} -{"id": 32720, "token": "051", "merges": "05 1", "raw_count": 73179, "count": 73179, "decode_str": "051"} -{"id": 25224, "token": "hon", "merges": "h on", "raw_count": 73192, "count": 73192, "decode_str": "hon"} -{"id": 39504, "token": "\u0120Initialize", "merges": "\u0120Init ialize", "raw_count": 73204, "count": 73204, "decode_str": " Initialize"} -{"id": 14254, "token": "\u0120province", "merges": "\u0120prov ince", "raw_count": 73207, "count": 73207, "decode_str": " province"} -{"id": 42378, "token": "Advanced", "merges": "Adv anced", "raw_count": 73211, "count": 73211, "decode_str": "Advanced"} -{"id": 20607, "token": "Library", "merges": "L ibrary", "raw_count": 73216, "count": 73216, "decode_str": "Library"} -{"id": 13349, "token": "Pres", "merges": "P res", "raw_count": 60481, "count": 73219, "decode_str": "Pres"} -{"id": 6080, "token": "Some", "merges": "S ome", "raw_count": 67134, "count": 73234, "decode_str": "Some"} -{"id": 12086, "token": "anded", "merges": "and ed", "raw_count": 67799, "count": 73241, "decode_str": "anded"} -{"id": 8515, "token": "ifts", "merges": "if ts", "raw_count": 15847, "count": 73268, "decode_str": "ifts"} -{"id": 8703, "token": "**(", "merges": "** (", "raw_count": 70766, "count": 73272, "decode_str": "**("} -{"id": 8913, "token": "\u0120ban", "merges": "\u0120b an", "raw_count": 67570, "count": 73292, "decode_str": " ban"} -{"id": 5253, "token": "\u0120glass", "merges": "\u0120gl ass", "raw_count": 62800, "count": 73293, "decode_str": " glass"} -{"id": 54548, "token": "\u00e7\u00ac\u0137", "merges": "\u00e7\u00ac \u0137", "raw_count": 73294, "count": 73294, "decode_str": "\u7b15"} -{"id": 9923, "token": "fficients", "merges": "ffic ients", "raw_count": 36374, "count": 73313, "decode_str": "fficients"} -{"id": 27797, "token": "\u0120congress", "merges": "\u0120con gress", "raw_count": 73327, "count": 73327, "decode_str": " congress"} -{"id": 6520, "token": "\u0120flex", "merges": "\u0120f lex", "raw_count": 24354, "count": 73329, "decode_str": " flex"} -{"id": 30990, "token": "\u0120accountability", "merges": "\u0120account ability", "raw_count": 73349, "count": 73349, "decode_str": " accountability"} -{"id": 39455, "token": "bod", "merges": "b od", "raw_count": 73350, "count": 73350, "decode_str": "bod"} -{"id": 39985, "token": "vf", "merges": "v f", "raw_count": 73369, "count": 73369, "decode_str": "vf"} -{"id": 30170, "token": "\u0120booking", "merges": "\u0120book ing", "raw_count": 73373, "count": 73373, "decode_str": " booking"} -{"id": 9258, "token": "inson", "merges": "ins on", "raw_count": 70845, "count": 73390, "decode_str": "inson"} -{"id": 28086, "token": "MN", "merges": "M N", "raw_count": 73394, "count": 73394, "decode_str": "MN"} -{"id": 41145, "token": "Cool", "merges": "C ool", "raw_count": 73410, "count": 73410, "decode_str": "Cool"} -{"id": 21429, "token": "\u0120archive", "merges": "\u0120arch ive", "raw_count": 73415, "count": 73415, "decode_str": " archive"} -{"id": 41349, "token": "Financial", "merges": "Fin ancial", "raw_count": 73432, "count": 73432, "decode_str": "Financial"} -{"id": 33550, "token": "ACA", "merges": "AC A", "raw_count": 73439, "count": 73439, "decode_str": "ACA"} -{"id": 21568, "token": "emp", "merges": "em p", "raw_count": 73440, "count": 73440, "decode_str": "emp"} -{"id": 14475, "token": "\u0120arising", "merges": "\u0120ar ising", "raw_count": 73473, "count": 73473, "decode_str": " arising"} -{"id": 28823, "token": "\u0120iterator", "merges": "\u0120iter ator", "raw_count": 73493, "count": 73493, "decode_str": " iterator"} -{"id": 9411, "token": "\u0120vehicles", "merges": "\u0120veh icles", "raw_count": 73510, "count": 73510, "decode_str": " vehicles"} -{"id": 8576, "token": "\u0120kitchen", "merges": "\u0120kit chen", "raw_count": 73518, "count": 73518, "decode_str": " kitchen"} -{"id": 31646, "token": "agem", "merges": "ag em", "raw_count": 73545, "count": 73545, "decode_str": "agem"} -{"id": 8160, "token": "\u0120ON", "merges": "\u0120O N", "raw_count": 65880, "count": 73545, "decode_str": " ON"} -{"id": 36001, "token": "Reset", "merges": "Res et", "raw_count": 73554, "count": 73554, "decode_str": "Reset"} -{"id": 21626, "token": "\u0120timer", "merges": "\u0120tim er", "raw_count": 73561, "count": 73561, "decode_str": " timer"} -{"id": 4920, "token": "\u0120mort", "merges": "\u0120m ort", "raw_count": 8981, "count": 73568, "decode_str": " mort"} -{"id": 47360, "token": "lens", "merges": "l ens", "raw_count": 73570, "count": 73570, "decode_str": "lens"} -{"id": 40016, "token": "Kar", "merges": "K ar", "raw_count": 73570, "count": 73570, "decode_str": "Kar"} -{"id": 40923, "token": "\u0120\".\"", "merges": "\u0120\" .\"", "raw_count": 73593, "count": 73593, "decode_str": " \".\""} -{"id": 13278, "token": "\u0120108", "merges": "\u012010 8", "raw_count": 73598, "count": 73598, "decode_str": " 108"} -{"id": 16458, "token": "hips", "merges": "hip s", "raw_count": 73600, "count": 73600, "decode_str": "hips"} -{"id": 10687, "token": "\u0120withdraw", "merges": "\u0120with draw", "raw_count": 33948, "count": 73614, "decode_str": " withdraw"} -{"id": 30123, "token": "\u0120Query", "merges": "\u0120Qu ery", "raw_count": 73640, "count": 73640, "decode_str": " Query"} -{"id": 6819, "token": "omes", "merges": "om es", "raw_count": 54616, "count": 73648, "decode_str": "omes"} -{"id": 33816, "token": "afety", "merges": "af ety", "raw_count": 73650, "count": 73650, "decode_str": "afety"} -{"id": 30251, "token": "RY", "merges": "R Y", "raw_count": 73658, "count": 73658, "decode_str": "RY"} -{"id": 9503, "token": "\u0120roles", "merges": "\u0120ro les", "raw_count": 73671, "count": 73671, "decode_str": " roles"} -{"id": 29339, "token": "\u0120DEFAULT", "merges": "\u0120DE FAULT", "raw_count": 73675, "count": 73675, "decode_str": " DEFAULT"} -{"id": 24352, "token": "ICATION", "merges": "IC ATION", "raw_count": 60963, "count": 73684, "decode_str": "ICATION"} -{"id": 37517, "token": "Buy", "merges": "B uy", "raw_count": 73735, "count": 73735, "decode_str": "Buy"} -{"id": 11685, "token": "\u0120HTML", "merges": "\u0120HT ML", "raw_count": 73740, "count": 73740, "decode_str": " HTML"} -{"id": 51342, "token": "\u00e5\u00a6\u00a3", "merges": "\u00e5\u00a6 \u00a3", "raw_count": 73768, "count": 73768, "decode_str": "\u59a3"} -{"id": 5709, "token": "[\\", "merges": "[ \\", "raw_count": 72506, "count": 73775, "decode_str": "[\\"} -{"id": 16314, "token": "proof", "merges": "pro of", "raw_count": 73781, "count": 73781, "decode_str": "proof"} -{"id": 4336, "token": "\u0120completely", "merges": "\u0120complet ely", "raw_count": 73784, "count": 73784, "decode_str": " completely"} -{"id": 9628, "token": "\u0120sharing", "merges": "\u0120sh aring", "raw_count": 73792, "count": 73792, "decode_str": " sharing"} -{"id": 24289, "token": "PARAM", "merges": "PAR AM", "raw_count": 73793, "count": 73793, "decode_str": "PARAM"} -{"id": 17305, "token": "enh", "merges": "en h", "raw_count": 62039, "count": 73798, "decode_str": "enh"} -{"id": 41771, "token": "('',", "merges": "(' ',", "raw_count": 73850, "count": 73850, "decode_str": "('',"} -{"id": 22466, "token": "airo", "merges": "ai ro", "raw_count": 72759, "count": 73884, "decode_str": "airo"} -{"id": 25490, "token": "TIM", "merges": "T IM", "raw_count": 73886, "count": 73886, "decode_str": "TIM"} -{"id": 30056, "token": "Axis", "merges": "Ax is", "raw_count": 73898, "count": 73898, "decode_str": "Axis"} -{"id": 30768, "token": "057", "merges": "05 7", "raw_count": 73898, "count": 73898, "decode_str": "057"} -{"id": 7275, "token": "\u0120tom", "merges": "\u0120to m", "raw_count": 34175, "count": 73910, "decode_str": " tom"} -{"id": 15298, "token": "nia", "merges": "n ia", "raw_count": 69793, "count": 73918, "decode_str": "nia"} -{"id": 22279, "token": "Private", "merges": "P rivate", "raw_count": 73926, "count": 73926, "decode_str": "Private"} -{"id": 10907, "token": "\u0120banks", "merges": "\u0120b anks", "raw_count": 73944, "count": 73944, "decode_str": " banks"} -{"id": 18712, "token": "Definition", "merges": "Def inition", "raw_count": 73967, "count": 73967, "decode_str": "Definition"} -{"id": 38218, "token": "zd", "merges": "z d", "raw_count": 73968, "count": 73968, "decode_str": "zd"} -{"id": 21999, "token": "\u0120verification", "merges": "\u0120ver ification", "raw_count": 73990, "count": 73990, "decode_str": " verification"} -{"id": 5662, "token": "\u0120older", "merges": "\u0120old er", "raw_count": 74011, "count": 74011, "decode_str": " older"} -{"id": 7491, "token": "\u0120boot", "merges": "\u0120b oot", "raw_count": 46837, "count": 74013, "decode_str": " boot"} -{"id": 24325, "token": "\u0120mont", "merges": "\u0120m ont", "raw_count": 74015, "count": 74015, "decode_str": " mont"} -{"id": 4370, "token": "\u0120dog", "merges": "\u0120d og", "raw_count": 56603, "count": 74020, "decode_str": " dog"} -{"id": 18868, "token": "London", "merges": "L ondon", "raw_count": 74025, "count": 74025, "decode_str": "London"} -{"id": 22099, "token": "Trace", "merges": "Tr ace", "raw_count": 72334, "count": 74033, "decode_str": "Trace"} -{"id": 3718, "token": "\u0120favor", "merges": "\u0120fav or", "raw_count": 23600, "count": 74035, "decode_str": " favor"} -{"id": 18672, "token": "\u0120170", "merges": "\u012017 0", "raw_count": 74038, "count": 74038, "decode_str": " 170"} -{"id": 14345, "token": "uto", "merges": "ut o", "raw_count": 74039, "count": 74039, "decode_str": "uto"} -{"id": 38289, "token": "Tour", "merges": "T our", "raw_count": 74042, "count": 74042, "decode_str": "Tour"} -{"id": 39246, "token": "(((", "merges": "(( (", "raw_count": 74045, "count": 74045, "decode_str": "((("} -{"id": 38885, "token": "employee", "merges": "employ ee", "raw_count": 74057, "count": 74057, "decode_str": "employee"} -{"id": 41793, "token": "Made", "merges": "M ade", "raw_count": 74068, "count": 74068, "decode_str": "Made"} -{"id": 45250, "token": "\u0120{:", "merges": "\u0120{ :", "raw_count": 74073, "count": 74073, "decode_str": " {:"} -{"id": 12131, "token": "\u0120104", "merges": "\u012010 4", "raw_count": 74081, "count": 74081, "decode_str": " 104"} -{"id": 20444, "token": "inea", "merges": "ine a", "raw_count": 7349, "count": 74102, "decode_str": "inea"} -{"id": 21401, "token": "arma", "merges": "ar ma", "raw_count": 74136, "count": 74136, "decode_str": "arma"} -{"id": 44031, "token": "\u0120slug", "merges": "\u0120sl ug", "raw_count": 74159, "count": 74159, "decode_str": " slug"} -{"id": 35894, "token": "IMAGE", "merges": "IM AGE", "raw_count": 74159, "count": 74159, "decode_str": "IMAGE"} -{"id": 16646, "token": "\u0120lon", "merges": "\u0120l on", "raw_count": 60961, "count": 74180, "decode_str": " lon"} -{"id": 15649, "token": "\u0120ug", "merges": "\u0120 ug", "raw_count": 59545, "count": 74185, "decode_str": " ug"} -{"id": 19291, "token": "Japan", "merges": "J apan", "raw_count": 63858, "count": 74197, "decode_str": "Japan"} -{"id": 31492, "token": "DEL", "merges": "DE L", "raw_count": 74202, "count": 74202, "decode_str": "DEL"} -{"id": 24139, "token": "Les", "merges": "L es", "raw_count": 74250, "count": 74250, "decode_str": "Les"} -{"id": 30986, "token": "jun", "merges": "j un", "raw_count": 74251, "count": 74251, "decode_str": "jun"} -{"id": 36693, "token": "Contains", "merges": "Cont ains", "raw_count": 74254, "count": 74254, "decode_str": "Contains"} -{"id": 11487, "token": "\u012082", "merges": "\u01208 2", "raw_count": 74255, "count": 74255, "decode_str": " 82"} -{"id": 24691, "token": "MSG", "merges": "MS G", "raw_count": 74260, "count": 74260, "decode_str": "MSG"} -{"id": 15890, "token": "\u0120accounting", "merges": "\u0120account ing", "raw_count": 74263, "count": 74263, "decode_str": " accounting"} -{"id": 7293, "token": "\u0120depending", "merges": "\u0120dep ending", "raw_count": 74281, "count": 74281, "decode_str": " depending"} -{"id": 20941, "token": "FW", "merges": "F W", "raw_count": 74299, "count": 74299, "decode_str": "FW"} -{"id": 3260, "token": "\u0120knew", "merges": "\u0120k new", "raw_count": 74303, "count": 74303, "decode_str": " knew"} -{"id": 11271, "token": "\u0120Pass", "merges": "\u0120P ass", "raw_count": 41861, "count": 74305, "decode_str": " Pass"} -{"id": 14784, "token": "\u0120XML", "merges": "\u0120X ML", "raw_count": 74309, "count": 74309, "decode_str": " XML"} -{"id": 37884, "token": "\u0120bureau", "merges": "\u0120b ureau", "raw_count": 74315, "count": 74315, "decode_str": " bureau"} -{"id": 7423, "token": "\u0120hall", "merges": "\u0120h all", "raw_count": 63105, "count": 74323, "decode_str": " hall"} -{"id": 7921, "token": "\u0120relax", "merges": "\u0120rel ax", "raw_count": 34894, "count": 74340, "decode_str": " relax"} -{"id": 22705, "token": "Human", "merges": "H uman", "raw_count": 74340, "count": 74340, "decode_str": "Human"} -{"id": 9729, "token": "\u0120bridge", "merges": "\u0120br idge", "raw_count": 74351, "count": 74351, "decode_str": " bridge"} -{"id": 4453, "token": "\u0120looks", "merges": "\u0120look s", "raw_count": 74353, "count": 74353, "decode_str": " looks"} -{"id": 28240, "token": "Uns", "merges": "U ns", "raw_count": 74361, "count": 74361, "decode_str": "Uns"} -{"id": 7496, "token": "\u0120guard", "merges": "\u0120gu ard", "raw_count": 49589, "count": 74363, "decode_str": " guard"} -{"id": 53058, "token": "\u00e7\u0142\u0139", "merges": "\u00e7\u0142 \u0139", "raw_count": 74377, "count": 74377, "decode_str": "\u7817"} -{"id": 34706, "token": "Sus", "merges": "S us", "raw_count": 74382, "count": 74382, "decode_str": "Sus"} -{"id": 12984, "token": "\u00e2\u012b", "merges": "\u00e2 \u012b", "raw_count": 1218, "count": 74382, "decode_str": "\ufffd"} -{"id": 50103, "token": "instruction", "merges": "inst ruction", "raw_count": 74383, "count": 74383, "decode_str": "instruction"} -{"id": 4456, "token": "\u0120remember", "merges": "\u0120rem ember", "raw_count": 70781, "count": 74393, "decode_str": " remember"} -{"id": 21247, "token": "ILD", "merges": "IL D", "raw_count": 34507, "count": 74400, "decode_str": "ILD"} -{"id": 19541, "token": "\u0120ali", "merges": "\u0120al i", "raw_count": 45649, "count": 74408, "decode_str": " ali"} -{"id": 9137, "token": "\u0120marketing", "merges": "\u0120market ing", "raw_count": 74421, "count": 74421, "decode_str": " marketing"} -{"id": 14793, "token": "\u0120timely", "merges": "\u0120tim ely", "raw_count": 74423, "count": 74423, "decode_str": " timely"} -{"id": 30846, "token": "scre", "merges": "s cre", "raw_count": 74449, "count": 74449, "decode_str": "scre"} -{"id": 7759, "token": "\u0120degrees", "merges": "\u0120deg rees", "raw_count": 74457, "count": 74457, "decode_str": " degrees"} -{"id": 28211, "token": "Mont", "merges": "M ont", "raw_count": 74472, "count": 74472, "decode_str": "Mont"} -{"id": 7470, "token": "\u0120suitable", "merges": "\u0120suit able", "raw_count": 74495, "count": 74495, "decode_str": " suitable"} -{"id": 27681, "token": "Ce", "merges": "C e", "raw_count": 74508, "count": 74508, "decode_str": "Ce"} -{"id": 40907, "token": "numer", "merges": "num er", "raw_count": 74514, "count": 74514, "decode_str": "numer"} -{"id": 22068, "token": "CRIPT", "merges": "CR IPT", "raw_count": 42757, "count": 74517, "decode_str": "CRIPT"} -{"id": 16175, "token": "\u0120ethnic", "merges": "\u0120eth nic", "raw_count": 74520, "count": 74520, "decode_str": " ethnic"} -{"id": 10502, "token": "\u0120risks", "merges": "\u0120ris ks", "raw_count": 74520, "count": 74520, "decode_str": " risks"} -{"id": 5322, "token": "\u0120nice", "merges": "\u0120n ice", "raw_count": 74532, "count": 74532, "decode_str": " nice"} -{"id": 37632, "token": "Setup", "merges": "Set up", "raw_count": 74542, "count": 74542, "decode_str": "Setup"} -{"id": 23112, "token": "toggle", "merges": "t oggle", "raw_count": 74553, "count": 74553, "decode_str": "toggle"} -{"id": 38351, "token": "ivot", "merges": "iv ot", "raw_count": 74578, "count": 74578, "decode_str": "ivot"} -{"id": 30930, "token": "rn", "merges": "r n", "raw_count": 74600, "count": 74600, "decode_str": "rn"} -{"id": 7617, "token": "\u0120decide", "merges": "\u0120dec ide", "raw_count": 74606, "count": 74606, "decode_str": " decide"} -{"id": 28614, "token": "OVER", "merges": "OV ER", "raw_count": 74655, "count": 74655, "decode_str": "OVER"} -{"id": 15387, "token": "nor", "merges": "n or", "raw_count": 61591, "count": 74669, "decode_str": "nor"} -{"id": 19623, "token": "different", "merges": "d ifferent", "raw_count": 74674, "count": 74674, "decode_str": "different"} -{"id": 11507, "token": ".),", "merges": ". ),", "raw_count": 74687, "count": 74687, "decode_str": ".),"} -{"id": 27384, "token": "Vertex", "merges": "Ver tex", "raw_count": 74698, "count": 74698, "decode_str": "Vertex"} -{"id": 23750, "token": "ongs", "merges": "ong s", "raw_count": 67699, "count": 74699, "decode_str": "ongs"} -{"id": 21321, "token": "++++", "merges": "++ ++", "raw_count": 29879, "count": 74703, "decode_str": "++++"} -{"id": 4497, "token": "Well", "merges": "W ell", "raw_count": 74709, "count": 74709, "decode_str": "Well"} -{"id": 24917, "token": "\u0120logged", "merges": "\u0120log ged", "raw_count": 74713, "count": 74713, "decode_str": " logged"} -{"id": 28510, "token": "CHO", "merges": "CH O", "raw_count": 74713, "count": 74713, "decode_str": "CHO"} -{"id": 16041, "token": "\u0120comply", "merges": "\u0120comp ly", "raw_count": 74734, "count": 74734, "decode_str": " comply"} -{"id": 38595, "token": "texture", "merges": "text ure", "raw_count": 74734, "count": 74734, "decode_str": "texture"} -{"id": 12210, "token": "\u01201985", "merges": "\u012019 85", "raw_count": 74740, "count": 74740, "decode_str": " 1985"} -{"id": 40331, "token": "Buff", "merges": "B uff", "raw_count": 74740, "count": 74740, "decode_str": "Buff"} -{"id": 34966, "token": "study", "merges": "stud y", "raw_count": 74742, "count": 74742, "decode_str": "study"} -{"id": 52359, "token": "\u00e6\u00a7\u00b2", "merges": "\u00e6\u00a7 \u00b2", "raw_count": 74752, "count": 74752, "decode_str": "\u69f2"} -{"id": 17700, "token": "ilization", "merges": "il ization", "raw_count": 40487, "count": 74757, "decode_str": "ilization"} -{"id": 44665, "token": "contrib", "merges": "cont rib", "raw_count": 74773, "count": 74773, "decode_str": "contrib"} -{"id": 25620, "token": "\u0120runner", "merges": "\u0120run ner", "raw_count": 74777, "count": 74777, "decode_str": " runner"} -{"id": 21808, "token": "those", "merges": "th ose", "raw_count": 74791, "count": 74791, "decode_str": "those"} -{"id": 2615, "token": "\u0120Can", "merges": "\u0120C an", "raw_count": 67199, "count": 74795, "decode_str": " Can"} -{"id": 20756, "token": "ARCH", "merges": "AR CH", "raw_count": 74801, "count": 74801, "decode_str": "ARCH"} -{"id": 31085, "token": "REM", "merges": "RE M", "raw_count": 74819, "count": 74819, "decode_str": "REM"} -{"id": 51527, "token": "\u00e5\u00b8\u0133", "merges": "\u00e5\u00b8 \u0133", "raw_count": 74837, "count": 74837, "decode_str": "\u5e11"} -{"id": 7214, "token": "\u0120Only", "merges": "\u0120On ly", "raw_count": 74861, "count": 74861, "decode_str": " Only"} -{"id": 26803, "token": "hig", "merges": "h ig", "raw_count": 9630, "count": 74866, "decode_str": "hig"} -{"id": 8055, "token": "ounded", "merges": "ound ed", "raw_count": 34286, "count": 74873, "decode_str": "ounded"} -{"id": 33295, "token": "\u0120paragraphs", "merges": "\u0120paragraph s", "raw_count": 74889, "count": 74889, "decode_str": " paragraphs"} -{"id": 10398, "token": "chem", "merges": "che m", "raw_count": 45248, "count": 74893, "decode_str": "chem"} -{"id": 24434, "token": "CALL", "merges": "C ALL", "raw_count": 74900, "count": 74900, "decode_str": "CALL"} -{"id": 44333, "token": "feedback", "merges": "feed back", "raw_count": 74905, "count": 74905, "decode_str": "feedback"} -{"id": 7797, "token": "clusions", "merges": "clus ions", "raw_count": 18094, "count": 74917, "decode_str": "clusions"} -{"id": 40805, "token": "Anna", "merges": "An na", "raw_count": 74918, "count": 74918, "decode_str": "Anna"} -{"id": 40013, "token": "Actions", "merges": "A ctions", "raw_count": 74943, "count": 74943, "decode_str": "Actions"} -{"id": 11600, "token": "\u0120beach", "merges": "\u0120be ach", "raw_count": 74953, "count": 74953, "decode_str": " beach"} -{"id": 4547, "token": "osite", "merges": "os ite", "raw_count": 15258, "count": 74957, "decode_str": "osite"} -{"id": 7466, "token": "\u0120expansion", "merges": "\u0120exp ansion", "raw_count": 74985, "count": 74985, "decode_str": " expansion"} -{"id": 38435, "token": "\u0120wi", "merges": "\u0120w i", "raw_count": 74993, "count": 74993, "decode_str": " wi"} -{"id": 22908, "token": "\u0120900", "merges": "\u01209 00", "raw_count": 75012, "count": 75012, "decode_str": " 900"} -{"id": 31200, "token": "slow", "merges": "s low", "raw_count": 75017, "count": 75017, "decode_str": "slow"} -{"id": 54587, "token": "\u00e7\u012c\u0129", "merges": "\u00e7\u012c \u0129", "raw_count": 75020, "count": 75020, "decode_str": "\u7287"} -{"id": 6492, "token": "\u0120indicates", "merges": "\u0120indic ates", "raw_count": 75032, "count": 75032, "decode_str": " indicates"} -{"id": 33049, "token": "heading", "merges": "head ing", "raw_count": 75033, "count": 75033, "decode_str": "heading"} -{"id": 6195, "token": "\u0120lit", "merges": "\u0120l it", "raw_count": 23196, "count": 75050, "decode_str": " lit"} -{"id": 27276, "token": "individual", "merges": "ind ividual", "raw_count": 75057, "count": 75057, "decode_str": "individual"} -{"id": 7695, "token": "ching", "merges": "ch ing", "raw_count": 66770, "count": 75057, "decode_str": "ching"} -{"id": 9365, "token": "\u0120faces", "merges": "\u0120f aces", "raw_count": 75061, "count": 75061, "decode_str": " faces"} -{"id": 37685, "token": "\u0120iii", "merges": "\u0120i ii", "raw_count": 75063, "count": 75063, "decode_str": " iii"} -{"id": 41586, "token": "factors", "merges": "fact ors", "raw_count": 75071, "count": 75071, "decode_str": "factors"} -{"id": 14773, "token": "\u0120donor", "merges": "\u0120don or", "raw_count": 75073, "count": 75073, "decode_str": " donor"} -{"id": 33443, "token": "bull", "merges": "b ull", "raw_count": 75079, "count": 75079, "decode_str": "bull"} -{"id": 16405, "token": "iga", "merges": "ig a", "raw_count": 75081, "count": 75081, "decode_str": "iga"} -{"id": 5006, "token": "\u0120boy", "merges": "\u0120b oy", "raw_count": 65930, "count": 75083, "decode_str": " boy"} -{"id": 51785, "token": "\u00e6\u0126\u0128", "merges": "\u00e6\u0126 \u0128", "raw_count": 75085, "count": 75085, "decode_str": "\u6106"} -{"id": 44496, "token": "814", "merges": "8 14", "raw_count": 75106, "count": 75106, "decode_str": "814"} -{"id": 19797, "token": "\u0120achievement", "merges": "\u0120achieve ment", "raw_count": 75118, "count": 75118, "decode_str": " achievement"} -{"id": 5189, "token": "\u0120detected", "merges": "\u0120detect ed", "raw_count": 75123, "count": 75123, "decode_str": " detected"} -{"id": 27271, "token": "choose", "merges": "cho ose", "raw_count": 75124, "count": 75124, "decode_str": "choose"} -{"id": 6427, "token": "\u0120attract", "merges": "\u0120att ract", "raw_count": 27458, "count": 75126, "decode_str": " attract"} -{"id": 1853, "token": "\u00e2\u012a", "merges": "\u00e2 \u012a", "raw_count": 5514, "count": 75145, "decode_str": "\ufffd"} -{"id": 16006, "token": "\u0120judges", "merges": "\u0120jud ges", "raw_count": 75146, "count": 75146, "decode_str": " judges"} -{"id": 37528, "token": "Gh", "merges": "G h", "raw_count": 75152, "count": 75152, "decode_str": "Gh"} -{"id": 39419, "token": "Ban", "merges": "B an", "raw_count": 75160, "count": 75160, "decode_str": "Ban"} -{"id": 22795, "token": "Ir", "merges": "I r", "raw_count": 70318, "count": 75162, "decode_str": "Ir"} -{"id": 12140, "token": "\u01201986", "merges": "\u012019 86", "raw_count": 75188, "count": 75188, "decode_str": " 1986"} -{"id": 5575, "token": "\u0120alleged", "merges": "\u0120alleg ed", "raw_count": 53563, "count": 75200, "decode_str": " alleged"} -{"id": 10884, "token": "\u0120returning", "merges": "\u0120return ing", "raw_count": 75205, "count": 75205, "decode_str": " returning"} -{"id": 12876, "token": "ieve", "merges": "ie ve", "raw_count": 55551, "count": 75205, "decode_str": "ieve"} -{"id": 7702, "token": "\u0120encoun", "merges": "\u0120enc oun", "raw_count": 21, "count": 75208, "decode_str": " encoun"} -{"id": 3804, "token": "fra", "merges": "f ra", "raw_count": 39327, "count": 75211, "decode_str": "fra"} -{"id": 32224, "token": "Tip", "merges": "T ip", "raw_count": 75230, "count": 75230, "decode_str": "Tip"} -{"id": 30766, "token": "vidia", "merges": "vid ia", "raw_count": 72244, "count": 75237, "decode_str": "vidia"} -{"id": 2684, "token": "\u0120performed", "merges": "\u0120perform ed", "raw_count": 75245, "count": 75245, "decode_str": " performed"} -{"id": 12822, "token": "Ms", "merges": "M s", "raw_count": 75248, "count": 75248, "decode_str": "Ms"} -{"id": 41892, "token": "953", "merges": "95 3", "raw_count": 75279, "count": 75279, "decode_str": "953"} -{"id": 1893, "token": "\u0120So", "merges": "\u0120S o", "raw_count": 48404, "count": 75286, "decode_str": " So"} -{"id": 34320, "token": "Lines", "merges": "L ines", "raw_count": 75292, "count": 75292, "decode_str": "Lines"} -{"id": 8113, "token": "\u0120vision", "merges": "\u0120v ision", "raw_count": 75295, "count": 75295, "decode_str": " vision"} -{"id": 4620, "token": "\u0120appears", "merges": "\u0120appe ars", "raw_count": 75300, "count": 75300, "decode_str": " appears"} -{"id": 3618, "token": "\u0120weeks", "merges": "\u0120we eks", "raw_count": 75304, "count": 75304, "decode_str": " weeks"} -{"id": 9054, "token": "\u0120enemy", "merges": "\u0120enem y", "raw_count": 75319, "count": 75319, "decode_str": " enemy"} -{"id": 15853, "token": "Aug", "merges": "A ug", "raw_count": 41664, "count": 75328, "decode_str": "Aug"} -{"id": 4597, "token": "\u0120Det", "merges": "\u0120D et", "raw_count": 14237, "count": 75331, "decode_str": " Det"} -{"id": 34483, "token": "inja", "merges": "in ja", "raw_count": 75342, "count": 75342, "decode_str": "inja"} -{"id": 14653, "token": "filled", "merges": "f illed", "raw_count": 55300, "count": 75349, "decode_str": "filled"} -{"id": 40595, "token": "TestCase", "merges": "Test Case", "raw_count": 75356, "count": 75356, "decode_str": "TestCase"} -{"id": 7327, "token": "\u0120Field", "merges": "\u0120F ield", "raw_count": 68740, "count": 75362, "decode_str": " Field"} -{"id": 26971, "token": "secure", "merges": "sec ure", "raw_count": 67454, "count": 75366, "decode_str": "secure"} -{"id": 44983, "token": "EMA", "merges": "EM A", "raw_count": 75383, "count": 75383, "decode_str": "EMA"} -{"id": 10700, "token": "town", "merges": "t own", "raw_count": 62356, "count": 75397, "decode_str": "town"} -{"id": 17799, "token": "irected", "merges": "ire cted", "raw_count": 52166, "count": 75399, "decode_str": "irected"} -{"id": 7138, "token": "\u0120brand", "merges": "\u0120br and", "raw_count": 69217, "count": 75423, "decode_str": " brand"} -{"id": 28747, "token": "Objects", "merges": "Object s", "raw_count": 75439, "count": 75439, "decode_str": "Objects"} -{"id": 23642, "token": "liv", "merges": "l iv", "raw_count": 73544, "count": 75441, "decode_str": "liv"} -{"id": 5241, "token": "\u0120peak", "merges": "\u0120pe ak", "raw_count": 54997, "count": 75451, "decode_str": " peak"} -{"id": 16927, "token": "Notes", "merges": "Not es", "raw_count": 75463, "count": 75463, "decode_str": "Notes"} -{"id": 36569, "token": "Marg", "merges": "M arg", "raw_count": 75471, "count": 75471, "decode_str": "Marg"} -{"id": 6898, "token": "\u0120filled", "merges": "\u0120f illed", "raw_count": 75473, "count": 75473, "decode_str": " filled"} -{"id": 8773, "token": "\u0120escape", "merges": "\u0120esc ape", "raw_count": 75488, "count": 75488, "decode_str": " escape"} -{"id": 13826, "token": "GFR", "merges": "GF R", "raw_count": 27813, "count": 75492, "decode_str": "GFR"} -{"id": 21305, "token": "\u0120Stop", "merges": "\u0120St op", "raw_count": 75493, "count": 75493, "decode_str": " Stop"} -{"id": 25379, "token": "elines", "merges": "el ines", "raw_count": 66691, "count": 75499, "decode_str": "elines"} -{"id": 16427, "token": "eu", "merges": "e u", "raw_count": 71212, "count": 75521, "decode_str": "eu"} -{"id": 17596, "token": "\u0120ports", "merges": "\u0120port s", "raw_count": 75536, "count": 75536, "decode_str": " ports"} -{"id": 7945, "token": "\u0120concluded", "merges": "\u0120con cluded", "raw_count": 75547, "count": 75547, "decode_str": " concluded"} -{"id": 15189, "token": "forced", "merges": "for ced", "raw_count": 24717, "count": 75554, "decode_str": "forced"} -{"id": 4833, "token": "\u0120influence", "merges": "\u0120influ ence", "raw_count": 75560, "count": 75560, "decode_str": " influence"} -{"id": 28533, "token": "yson", "merges": "ys on", "raw_count": 75350, "count": 75561, "decode_str": "yson"} -{"id": 31308, "token": "\u0120Convert", "merges": "\u0120Con vert", "raw_count": 75568, "count": 75568, "decode_str": " Convert"} -{"id": 21465, "token": "\u00eb\u012d\u00a4", "merges": "\u00eb\u012d \u00a4", "raw_count": 47840, "count": 75592, "decode_str": "\ub2e4"} -{"id": 8802, "token": "\u0120Us", "merges": "\u0120U s", "raw_count": 6637, "count": 75596, "decode_str": " Us"} -{"id": 10301, "token": "\u0120restaurant", "merges": "\u0120restaur ant", "raw_count": 75610, "count": 75610, "decode_str": " restaurant"} -{"id": 9954, "token": "\u0120aircraft", "merges": "\u0120a ircraft", "raw_count": 75613, "count": 75613, "decode_str": " aircraft"} -{"id": 15152, "token": "ench", "merges": "en ch", "raw_count": 74477, "count": 75629, "decode_str": "ench"} -{"id": 26717, "token": "critical", "merges": "c ritical", "raw_count": 75637, "count": 75637, "decode_str": "critical"} -{"id": 8550, "token": "ivated", "merges": "iv ated", "raw_count": 13607, "count": 75637, "decode_str": "ivated"} -{"id": 32786, "token": "zk", "merges": "z k", "raw_count": 75638, "count": 75638, "decode_str": "zk"} -{"id": 29467, "token": "AML", "merges": "AM L", "raw_count": 75640, "count": 75640, "decode_str": "AML"} -{"id": 15041, "token": "Ill", "merges": "I ll", "raw_count": 73979, "count": 75654, "decode_str": "Ill"} -{"id": 27265, "token": "Enable", "merges": "En able", "raw_count": 75669, "count": 75669, "decode_str": "Enable"} -{"id": 14520, "token": "generation", "merges": "gen eration", "raw_count": 74505, "count": 75681, "decode_str": "generation"} -{"id": 12181, "token": "HECK", "merges": "HE CK", "raw_count": 2203, "count": 75691, "decode_str": "HECK"} -{"id": 47764, "token": "\u0120tz", "merges": "\u0120t z", "raw_count": 75715, "count": 75715, "decode_str": " tz"} -{"id": 10720, "token": "\u0120fifth", "merges": "\u0120fif th", "raw_count": 75728, "count": 75728, "decode_str": " fifth"} -{"id": 16384, "token": "\u0120wrap", "merges": "\u0120w rap", "raw_count": 75730, "count": 75730, "decode_str": " wrap"} -{"id": 34429, "token": "SOC", "merges": "S OC", "raw_count": 75739, "count": 75739, "decode_str": "SOC"} -{"id": 26025, "token": "}))", "merges": "} ))", "raw_count": 75753, "count": 75753, "decode_str": "}))"} -{"id": 6308, "token": "\u0120spot", "merges": "\u0120sp ot", "raw_count": 71994, "count": 75757, "decode_str": " spot"} -{"id": 16128, "token": "iche", "merges": "ic he", "raw_count": 69409, "count": 75798, "decode_str": "iche"} -{"id": 47878, "token": "documents", "merges": "doc uments", "raw_count": 75813, "count": 75813, "decode_str": "documents"} -{"id": 14612, "token": "rowth", "merges": "row th", "raw_count": 31911, "count": 75820, "decode_str": "rowth"} -{"id": 12737, "token": "raine", "merges": "ra ine", "raw_count": 74830, "count": 75829, "decode_str": "raine"} -{"id": 38741, "token": "Anton", "merges": "An ton", "raw_count": 75841, "count": 75841, "decode_str": "Anton"} -{"id": 14683, "token": "\u0120sentences", "merges": "\u0120sent ences", "raw_count": 75865, "count": 75865, "decode_str": " sentences"} -{"id": 9201, "token": "anol", "merges": "an ol", "raw_count": 68466, "count": 75874, "decode_str": "anol"} -{"id": 45230, "token": "therefore", "merges": "the refore", "raw_count": 75880, "count": 75880, "decode_str": "therefore"} -{"id": 24164, "token": "initions", "merges": "in itions", "raw_count": 62245, "count": 75882, "decode_str": "initions"} -{"id": 10955, "token": "\u0120bench", "merges": "\u0120ben ch", "raw_count": 15294, "count": 75888, "decode_str": " bench"} -{"id": 19854, "token": "inar", "merges": "in ar", "raw_count": 34054, "count": 75896, "decode_str": "inar"} -{"id": 21348, "token": "036", "merges": "0 36", "raw_count": 75900, "count": 75900, "decode_str": "036"} -{"id": 4038, "token": "\u0120density", "merges": "\u0120d ensity", "raw_count": 75906, "count": 75906, "decode_str": " density"} -{"id": 31095, "token": "Tags", "merges": "T ags", "raw_count": 75929, "count": 75929, "decode_str": "Tags"} -{"id": 50986, "token": "\u00e5\u0132\u00bd", "merges": "\u00e5\u0132 \u00bd", "raw_count": 75960, "count": 75960, "decode_str": "\u543d"} -{"id": 8087, "token": "\u0120rail", "merges": "\u0120ra il", "raw_count": 32852, "count": 75982, "decode_str": " rail"} -{"id": 9190, "token": "CIT", "merges": "C IT", "raw_count": 75984, "count": 75984, "decode_str": "CIT"} -{"id": 47763, "token": "969", "merges": "9 69", "raw_count": 76008, "count": 76008, "decode_str": "969"} -{"id": 10329, "token": "\u0120garden", "merges": "\u0120g arden", "raw_count": 76029, "count": 76029, "decode_str": " garden"} -{"id": 11334, "token": "\u0120111", "merges": "\u01201 11", "raw_count": 76029, "count": 76029, "decode_str": " 111"} -{"id": 36765, "token": "dry", "merges": "d ry", "raw_count": 76054, "count": 76054, "decode_str": "dry"} -{"id": 48200, "token": "manage", "merges": "man age", "raw_count": 76057, "count": 76057, "decode_str": "manage"} -{"id": 12047, "token": "\u0120Custom", "merges": "\u0120C ustom", "raw_count": 51038, "count": 76059, "decode_str": " Custom"} -{"id": 5760, "token": "\u0120controls", "merges": "\u0120control s", "raw_count": 76070, "count": 76070, "decode_str": " controls"} -{"id": 17070, "token": "Factor", "merges": "F actor", "raw_count": 76079, "count": 76079, "decode_str": "Factor"} -{"id": 47582, "token": "\u0120strides", "merges": "\u0120str ides", "raw_count": 76081, "count": 76081, "decode_str": " strides"} -{"id": 39154, "token": "0123", "merges": "01 23", "raw_count": 76091, "count": 76091, "decode_str": "0123"} -{"id": 14154, "token": "Debug", "merges": "Deb ug", "raw_count": 76095, "count": 76095, "decode_str": "Debug"} -{"id": 10279, "token": "\u0120mad", "merges": "\u0120m ad", "raw_count": 73535, "count": 76098, "decode_str": " mad"} -{"id": 10841, "token": "plet", "merges": "ple t", "raw_count": 37673, "count": 76101, "decode_str": "plet"} -{"id": 47314, "token": "Chi", "merges": "Ch i", "raw_count": 76120, "count": 76120, "decode_str": "Chi"} -{"id": 9174, "token": "rition", "merges": "r ition", "raw_count": 17600, "count": 76158, "decode_str": "rition"} -{"id": 7591, "token": "\u0120unable", "merges": "\u0120un able", "raw_count": 76173, "count": 76173, "decode_str": " unable"} -{"id": 16208, "token": "aders", "merges": "ad ers", "raw_count": 31545, "count": 76184, "decode_str": "aders"} -{"id": 10910, "token": "bell", "merges": "b ell", "raw_count": 73424, "count": 76194, "decode_str": "bell"} -{"id": 47774, "token": "UMP", "merges": "U MP", "raw_count": 76199, "count": 76199, "decode_str": "UMP"} -{"id": 18933, "token": "Kn", "merges": "K n", "raw_count": 64052, "count": 76199, "decode_str": "Kn"} -{"id": 10291, "token": "\u0120connections", "merges": "\u0120conne ctions", "raw_count": 76209, "count": 76209, "decode_str": " connections"} -{"id": 15040, "token": "\u0120expertise", "merges": "\u0120expert ise", "raw_count": 76226, "count": 76226, "decode_str": " expertise"} -{"id": 9404, "token": "\u0120CS", "merges": "\u0120C S", "raw_count": 30562, "count": 76237, "decode_str": " CS"} -{"id": 6447, "token": "\u0120uniform", "merges": "\u0120un iform", "raw_count": 60474, "count": 76243, "decode_str": " uniform"} -{"id": 9158, "token": "\u0120operators", "merges": "\u0120oper ators", "raw_count": 76257, "count": 76257, "decode_str": " operators"} -{"id": 19030, "token": "Selected", "merges": "Se lected", "raw_count": 76266, "count": 76266, "decode_str": "Selected"} -{"id": 7660, "token": "\u0120attached", "merges": "\u0120att ached", "raw_count": 76281, "count": 76281, "decode_str": " attached"} -{"id": 9700, "token": "\u0120Order", "merges": "\u0120Or der", "raw_count": 76285, "count": 76285, "decode_str": " Order"} -{"id": 15980, "token": "stim", "merges": "st im", "raw_count": 49242, "count": 76316, "decode_str": "stim"} -{"id": 8406, "token": "\u0120writer", "merges": "\u0120writ er", "raw_count": 76323, "count": 76323, "decode_str": " writer"} -{"id": 15141, "token": "olin", "merges": "ol in", "raw_count": 76100, "count": 76345, "decode_str": "olin"} -{"id": 14041, "token": "\u0120merg", "merges": "\u0120m erg", "raw_count": 8640, "count": 76352, "decode_str": " merg"} -{"id": 50120, "token": "kp", "merges": "k p", "raw_count": 76370, "count": 76370, "decode_str": "kp"} -{"id": 5406, "token": "\u0120picture", "merges": "\u0120pict ure", "raw_count": 76374, "count": 76374, "decode_str": " picture"} -{"id": 19064, "token": "pes", "merges": "p es", "raw_count": 71281, "count": 76378, "decode_str": "pes"} -{"id": 19470, "token": "\u0120|=", "merges": "\u0120| =", "raw_count": 76379, "count": 76379, "decode_str": " |="} -{"id": 10340, "token": "putation", "merges": "put ation", "raw_count": 52561, "count": 76387, "decode_str": "putation"} -{"id": 25479, "token": "ippet", "merges": "ipp et", "raw_count": 56785, "count": 76392, "decode_str": "ippet"} -{"id": 42232, "token": "951", "merges": "95 1", "raw_count": 76400, "count": 76400, "decode_str": "951"} -{"id": 30419, "token": "Charl", "merges": "Ch arl", "raw_count": 32628, "count": 76416, "decode_str": "Charl"} -{"id": 38571, "token": "Testing", "merges": "Test ing", "raw_count": 76418, "count": 76418, "decode_str": "Testing"} -{"id": 49474, "token": "Solid", "merges": "S olid", "raw_count": 76429, "count": 76429, "decode_str": "Solid"} -{"id": 36913, "token": "calendar", "merges": "cal endar", "raw_count": 76443, "count": 76443, "decode_str": "calendar"} -{"id": 12784, "token": "imm", "merges": "im m", "raw_count": 75997, "count": 76467, "decode_str": "imm"} -{"id": 38837, "token": "\u0120loader", "merges": "\u0120load er", "raw_count": 76468, "count": 76468, "decode_str": " loader"} -{"id": 41643, "token": "954", "merges": "95 4", "raw_count": 76486, "count": 76486, "decode_str": "954"} -{"id": 12510, "token": "\u0120effectiveness", "merges": "\u0120effect iveness", "raw_count": 76493, "count": 76493, "decode_str": " effectiveness"} -{"id": 4934, "token": "\u0120kept", "merges": "\u0120ke pt", "raw_count": 76505, "count": 76505, "decode_str": " kept"} -{"id": 11436, "token": "rell", "merges": "re ll", "raw_count": 61404, "count": 76508, "decode_str": "rell"} -{"id": 51239, "token": "\u00e5\u0141\u00b5", "merges": "\u00e5\u0141 \u00b5", "raw_count": 76510, "count": 76510, "decode_str": "\u57f5"} -{"id": 15577, "token": "\u0120mutual", "merges": "\u0120mut ual", "raw_count": 76532, "count": 76532, "decode_str": " mutual"} -{"id": 48265, "token": "Blo", "merges": "B lo", "raw_count": 76542, "count": 76542, "decode_str": "Blo"} -{"id": 38332, "token": "opo", "merges": "op o", "raw_count": 76542, "count": 76542, "decode_str": "opo"} -{"id": 8218, "token": "lectric", "merges": "lect ric", "raw_count": 39913, "count": 76571, "decode_str": "lectric"} -{"id": 2786, "token": "\u0120concent", "merges": "\u0120con cent", "raw_count": 1385, "count": 76584, "decode_str": " concent"} -{"id": 44018, "token": "Ross", "merges": "R oss", "raw_count": 76584, "count": 76584, "decode_str": "Ross"} -{"id": 8121, "token": "\u0120editor", "merges": "\u0120ed itor", "raw_count": 68961, "count": 76589, "decode_str": " editor"} -{"id": 24913, "token": "crit", "merges": "c rit", "raw_count": 76592, "count": 76592, "decode_str": "crit"} -{"id": 18032, "token": "\u0120unto", "merges": "\u0120un to", "raw_count": 76595, "count": 76595, "decode_str": " unto"} -{"id": 7548, "token": "\u0120boundary", "merges": "\u0120bound ary", "raw_count": 76603, "count": 76603, "decode_str": " boundary"} -{"id": 13211, "token": "ications", "merges": "ic ations", "raw_count": 41346, "count": 76611, "decode_str": "ications"} -{"id": 9074, "token": "\u0120Fil", "merges": "\u0120F il", "raw_count": 22869, "count": 76624, "decode_str": " Fil"} -{"id": 20014, "token": "mor", "merges": "m or", "raw_count": 54358, "count": 76629, "decode_str": "mor"} -{"id": 22074, "token": "\u0120builder", "merges": "\u0120bu ilder", "raw_count": 76631, "count": 76631, "decode_str": " builder"} -{"id": 46594, "token": "vg", "merges": "v g", "raw_count": 76656, "count": 76656, "decode_str": "vg"} -{"id": 9355, "token": "\u0120planned", "merges": "\u0120pl anned", "raw_count": 76662, "count": 76662, "decode_str": " planned"} -{"id": 34583, "token": "club", "merges": "cl ub", "raw_count": 76675, "count": 76675, "decode_str": "club"} -{"id": 42693, "token": "compress", "merges": "comp ress", "raw_count": 76681, "count": 76681, "decode_str": "compress"} -{"id": 37206, "token": "Bor", "merges": "B or", "raw_count": 76710, "count": 76710, "decode_str": "Bor"} -{"id": 32201, "token": "DY", "merges": "D Y", "raw_count": 76726, "count": 76726, "decode_str": "DY"} -{"id": 37791, "token": "oS", "merges": "o S", "raw_count": 76729, "count": 76729, "decode_str": "oS"} -{"id": 32798, "token": "\u0120gh", "merges": "\u0120g h", "raw_count": 76734, "count": 76734, "decode_str": " gh"} -{"id": 11392, "token": "\u0120reflected", "merges": "\u0120ref lected", "raw_count": 76743, "count": 76743, "decode_str": " reflected"} -{"id": 6306, "token": "\u0120standing", "merges": "\u0120stand ing", "raw_count": 76747, "count": 76747, "decode_str": " standing"} -{"id": 45343, "token": "862", "merges": "86 2", "raw_count": 76776, "count": 76776, "decode_str": "862"} -{"id": 6311, "token": "\u0120learned", "merges": "\u0120learn ed", "raw_count": 76778, "count": 76778, "decode_str": " learned"} -{"id": 11329, "token": "\u0120sel", "merges": "\u0120s el", "raw_count": 59628, "count": 76778, "decode_str": " sel"} -{"id": 10992, "token": "\u0120aux", "merges": "\u0120a ux", "raw_count": 61255, "count": 76781, "decode_str": " aux"} -{"id": 14721, "token": "tain", "merges": "t ain", "raw_count": 20459, "count": 76789, "decode_str": "tain"} -{"id": 8326, "token": "\u0120chart", "merges": "\u0120ch art", "raw_count": 63943, "count": 76790, "decode_str": " chart"} -{"id": 30583, "token": "CCESS", "merges": "CC ESS", "raw_count": 10383, "count": 76816, "decode_str": "CCESS"} -{"id": 10811, "token": "cludes", "merges": "clud es", "raw_count": 19809, "count": 76833, "decode_str": "cludes"} -{"id": 12917, "token": "\u0120Function", "merges": "\u0120F unction", "raw_count": 74595, "count": 76864, "decode_str": " Function"} -{"id": 48121, "token": "BAS", "merges": "B AS", "raw_count": 76879, "count": 76879, "decode_str": "BAS"} -{"id": 4630, "token": "\u0120stru", "merges": "\u0120st ru", "raw_count": 4127, "count": 76880, "decode_str": " stru"} -{"id": 16873, "token": "xtures", "merges": "xt ures", "raw_count": 61228, "count": 76881, "decode_str": "xtures"} -{"id": 20245, "token": "\u00e2\u0137\u0132", "merges": "\u00e2\u0137 \u0132", "raw_count": 8493, "count": 76885, "decode_str": "\u2550"} -{"id": 8041, "token": "\u0120attend", "merges": "\u0120att end", "raw_count": 51242, "count": 76892, "decode_str": " attend"} -{"id": 11702, "token": "\u0120spons", "merges": "\u0120sp ons", "raw_count": 13511, "count": 76896, "decode_str": " spons"} -{"id": 3556, "token": "haps", "merges": "h aps", "raw_count": 5610, "count": 76912, "decode_str": "haps"} -{"id": 43335, "token": "SAM", "merges": "S AM", "raw_count": 76931, "count": 76931, "decode_str": "SAM"} -{"id": 34552, "token": "Front", "merges": "Fr ont", "raw_count": 76946, "count": 76946, "decode_str": "Front"} -{"id": 21212, "token": "ository", "merges": "os itory", "raw_count": 19971, "count": 76947, "decode_str": "ository"} -{"id": 5422, "token": "ensional", "merges": "ens ional", "raw_count": 4921, "count": 76966, "decode_str": "ensional"} -{"id": 24386, "token": "scriber", "merges": "sc riber", "raw_count": 60672, "count": 76985, "decode_str": "scriber"} -{"id": 15115, "token": "\u0120pixels", "merges": "\u0120pix els", "raw_count": 76990, "count": 76990, "decode_str": " pixels"} -{"id": 35634, "token": "enary", "merges": "en ary", "raw_count": 77015, "count": 77015, "decode_str": "enary"} -{"id": 16660, "token": "\u0120Ale", "merges": "\u0120A le", "raw_count": 77016, "count": 77016, "decode_str": " Ale"} -{"id": 3597, "token": "\u0120tried", "merges": "\u0120tri ed", "raw_count": 77034, "count": 77034, "decode_str": " tried"} -{"id": 35978, "token": "\u0120ku", "merges": "\u0120k u", "raw_count": 77069, "count": 77069, "decode_str": " ku"} -{"id": 40391, "token": "/,", "merges": "/ ,", "raw_count": 77077, "count": 77077, "decode_str": "/,"} -{"id": 9200, "token": "\u0120shel", "merges": "\u0120she l", "raw_count": 13629, "count": 77079, "decode_str": " shel"} -{"id": 49558, "token": "detection", "merges": "det ection", "raw_count": 77111, "count": 77111, "decode_str": "detection"} -{"id": 39850, "token": "AES", "merges": "A ES", "raw_count": 77145, "count": 77145, "decode_str": "AES"} -{"id": 15855, "token": "published", "merges": "p ublished", "raw_count": 74298, "count": 77154, "decode_str": "published"} -{"id": 10280, "token": "\u0120repeat", "merges": "\u0120repe at", "raw_count": 77163, "count": 77163, "decode_str": " repeat"} -{"id": 47699, "token": "bv", "merges": "b v", "raw_count": 77172, "count": 77172, "decode_str": "bv"} -{"id": 30292, "token": "IGH", "merges": "IG H", "raw_count": 77194, "count": 77194, "decode_str": "IGH"} -{"id": 28044, "token": "Expr", "merges": "Ex pr", "raw_count": 77201, "count": 77201, "decode_str": "Expr"} -{"id": 19174, "token": "Comment", "merges": "Com ment", "raw_count": 77202, "count": 77202, "decode_str": "Comment"} -{"id": 8787, "token": "\u00d0\u00b1", "merges": "\u00d0 \u00b1", "raw_count": 43017, "count": 77268, "decode_str": "\u0431"} -{"id": 10081, "token": "endo", "merges": "end o", "raw_count": 35785, "count": 77279, "decode_str": "endo"} -{"id": 21373, "token": "ovation", "merges": "ov ation", "raw_count": 64639, "count": 77290, "decode_str": "ovation"} -{"id": 8961, "token": "\u00d1\u0128", "merges": "\u00d1 \u0128", "raw_count": 20570, "count": 77296, "decode_str": "\u0446"} -{"id": 7885, "token": "yer", "merges": "y er", "raw_count": 51547, "count": 77299, "decode_str": "yer"} -{"id": 48742, "token": "jump", "merges": "j ump", "raw_count": 77327, "count": 77327, "decode_str": "jump"} -{"id": 30948, "token": "OTE", "merges": "OT E", "raw_count": 77328, "count": 77328, "decode_str": "OTE"} -{"id": 6561, "token": "\u0120secondary", "merges": "\u0120second ary", "raw_count": 77348, "count": 77348, "decode_str": " secondary"} -{"id": 33220, "token": "053", "merges": "05 3", "raw_count": 77353, "count": 77353, "decode_str": "053"} -{"id": 19111, "token": "obi", "merges": "ob i", "raw_count": 75869, "count": 77354, "decode_str": "obi"} -{"id": 3001, "token": "\u0120=>", "merges": "\u0120= >", "raw_count": 77363, "count": 77363, "decode_str": " =>"} -{"id": 12164, "token": "\u0120supplied", "merges": "\u0120suppl ied", "raw_count": 77392, "count": 77392, "decode_str": " supplied"} -{"id": 910, "token": "){", "merges": ") {", "raw_count": 39571, "count": 77400, "decode_str": "){"} -{"id": 7841, "token": "azine", "merges": "az ine", "raw_count": 49449, "count": 77403, "decode_str": "azine"} -{"id": 31503, "token": "concept", "merges": "con cept", "raw_count": 77416, "count": 77416, "decode_str": "concept"} -{"id": 36173, "token": "Boot", "merges": "B oot", "raw_count": 77418, "count": 77418, "decode_str": "Boot"} -{"id": 39171, "token": "\u0120\u010a\u0109", "merges": "\u0120 \u010a\u0109", "raw_count": 77449, "count": 77449, "decode_str": " \n\t"} -{"id": 5463, "token": "ilos", "merges": "il os", "raw_count": 34176, "count": 77470, "decode_str": "ilos"} -{"id": 2728, "token": "\u0120disease", "merges": "\u0120dise ase", "raw_count": 77497, "count": 77497, "decode_str": " disease"} -{"id": 8284, "token": "\u0120requirement", "merges": "\u0120require ment", "raw_count": 77523, "count": 77523, "decode_str": " requirement"} -{"id": 31762, "token": "BAR", "merges": "B AR", "raw_count": 77562, "count": 77562, "decode_str": "BAR"} -{"id": 8808, "token": "unte", "merges": "un te", "raw_count": 19046, "count": 77577, "decode_str": "unte"} -{"id": 24182, "token": "esp", "merges": "es p", "raw_count": 77579, "count": 77579, "decode_str": "esp"} -{"id": 10028, "token": "\u0120alert", "merges": "\u0120al ert", "raw_count": 62061, "count": 77584, "decode_str": " alert"} -{"id": 35484, "token": "Stock", "merges": "St ock", "raw_count": 77585, "count": 77585, "decode_str": "Stock"} -{"id": 48095, "token": "RPC", "merges": "R PC", "raw_count": 77590, "count": 77590, "decode_str": "RPC"} -{"id": 28956, "token": "species", "merges": "spec ies", "raw_count": 77620, "count": 77620, "decode_str": "species"} -{"id": 12679, "token": "opher", "merges": "op her", "raw_count": 72665, "count": 77652, "decode_str": "opher"} -{"id": 25916, "token": "-----------------------", "merges": "---------------- -------", "raw_count": 77667, "count": 77667, "decode_str": "-----------------------"} -{"id": 4133, "token": "\u0120liter", "merges": "\u0120l iter", "raw_count": 11687, "count": 77677, "decode_str": " liter"} -{"id": 5773, "token": "ulf", "merges": "ul f", "raw_count": 58052, "count": 77681, "decode_str": "ulf"} -{"id": 38306, "token": "Mot", "merges": "M ot", "raw_count": 77681, "count": 77681, "decode_str": "Mot"} -{"id": 10935, "token": "\u0120loading", "merges": "\u0120load ing", "raw_count": 77688, "count": 77688, "decode_str": " loading"} -{"id": 7471, "token": "\u0120purchase", "merges": "\u0120purch ase", "raw_count": 77690, "count": 77690, "decode_str": " purchase"} -{"id": 18846, "token": "obby", "merges": "ob by", "raw_count": 68893, "count": 77697, "decode_str": "obby"} -{"id": 47322, "token": "Bridge", "merges": "Br idge", "raw_count": 77702, "count": 77702, "decode_str": "Bridge"} -{"id": 9267, "token": "\u0120soc", "merges": "\u0120s oc", "raw_count": 12095, "count": 77715, "decode_str": " soc"} -{"id": 31804, "token": "\u0120ny", "merges": "\u0120n y", "raw_count": 77729, "count": 77729, "decode_str": " ny"} -{"id": 42147, "token": "RIGHT", "merges": "R IGHT", "raw_count": 77741, "count": 77741, "decode_str": "RIGHT"} -{"id": 3875, "token": "otic", "merges": "ot ic", "raw_count": 53164, "count": 77753, "decode_str": "otic"} -{"id": 2429, "token": "\u0120compared", "merges": "\u0120comp ared", "raw_count": 77756, "count": 77756, "decode_str": " compared"} -{"id": 14134, "token": "ilipp", "merges": "ili pp", "raw_count": 76892, "count": 77764, "decode_str": "ilipp"} -{"id": 27658, "token": "uron", "merges": "ur on", "raw_count": 77781, "count": 77781, "decode_str": "uron"} -{"id": 12149, "token": "\u0120packages", "merges": "\u0120pack ages", "raw_count": 77788, "count": 77788, "decode_str": " packages"} -{"id": 24976, "token": "ubs", "merges": "ub s", "raw_count": 77793, "count": 77793, "decode_str": "ubs"} -{"id": 48410, "token": "Fake", "merges": "F ake", "raw_count": 77798, "count": 77798, "decode_str": "Fake"} -{"id": 5019, "token": "\u0120combination", "merges": "\u0120comb ination", "raw_count": 77801, "count": 77801, "decode_str": " combination"} -{"id": 5108, "token": "\u0120happen", "merges": "\u0120happ en", "raw_count": 77804, "count": 77804, "decode_str": " happen"} -{"id": 46206, "token": "\u0120rgb", "merges": "\u0120r gb", "raw_count": 77804, "count": 77804, "decode_str": " rgb"} -{"id": 12198, "token": "sit", "merges": "s it", "raw_count": 66266, "count": 77816, "decode_str": "sit"} -{"id": 35564, "token": "\u0120xx", "merges": "\u0120x x", "raw_count": 77816, "count": 77816, "decode_str": " xx"} -{"id": 11422, "token": "\u012087", "merges": "\u01208 7", "raw_count": 77828, "count": 77828, "decode_str": " 87"} -{"id": 24540, "token": "\u0120appreciation", "merges": "\u0120apprec iation", "raw_count": 77831, "count": 77831, "decode_str": " appreciation"} -{"id": 38256, "token": "pretty", "merges": "pret ty", "raw_count": 77840, "count": 77840, "decode_str": "pretty"} -{"id": 6008, "token": "\u0120eat", "merges": "\u0120e at", "raw_count": 68416, "count": 77847, "decode_str": " eat"} -{"id": 19691, "token": "\u0120END", "merges": "\u0120E ND", "raw_count": 77851, "count": 77851, "decode_str": " END"} -{"id": 32401, "token": "Lit", "merges": "L it", "raw_count": 18999, "count": 77861, "decode_str": "Lit"} -{"id": 16176, "token": "\u0120350", "merges": "\u01203 50", "raw_count": 77865, "count": 77865, "decode_str": " 350"} -{"id": 34082, "token": "\u0120ff", "merges": "\u0120f f", "raw_count": 77882, "count": 77882, "decode_str": " ff"} -{"id": 23507, "token": "\u0120sparse", "merges": "\u0120sp arse", "raw_count": 77904, "count": 77904, "decode_str": " sparse"} -{"id": 7313, "token": "\u0120observations", "merges": "\u0120observ ations", "raw_count": 77914, "count": 77914, "decode_str": " observations"} -{"id": 34053, "token": "CONT", "merges": "CON T", "raw_count": 77924, "count": 77924, "decode_str": "CONT"} -{"id": 11952, "token": "being", "merges": "be ing", "raw_count": 74483, "count": 77933, "decode_str": "being"} -{"id": 12669, "token": "\u0120checking", "merges": "\u0120check ing", "raw_count": 77936, "count": 77936, "decode_str": " checking"} -{"id": 30532, "token": "Pars", "merges": "P ars", "raw_count": 77939, "count": 77939, "decode_str": "Pars"} -{"id": 23502, "token": "ALE", "merges": "AL E", "raw_count": 77955, "count": 77955, "decode_str": "ALE"} -{"id": 6536, "token": "\u0120dra", "merges": "\u0120d ra", "raw_count": 10206, "count": 77990, "decode_str": " dra"} -{"id": 6037, "token": "\u0120Air", "merges": "\u0120A ir", "raw_count": 74624, "count": 77997, "decode_str": " Air"} -{"id": 17822, "token": "erce", "merges": "er ce", "raw_count": 38783, "count": 78000, "decode_str": "erce"} -{"id": 9083, "token": "Phys", "merges": "Ph ys", "raw_count": 43912, "count": 78005, "decode_str": "Phys"} -{"id": 12642, "token": "cycl", "merges": "cy cl", "raw_count": 32396, "count": 78005, "decode_str": "cycl"} -{"id": 3981, "token": "\u0120saying", "merges": "\u0120say ing", "raw_count": 78012, "count": 78012, "decode_str": " saying"} -{"id": 49085, "token": "Gary", "merges": "G ary", "raw_count": 78017, "count": 78017, "decode_str": "Gary"} -{"id": 8335, "token": "\u0120sheet", "merges": "\u0120she et", "raw_count": 78041, "count": 78041, "decode_str": " sheet"} -{"id": 35690, "token": "imag", "merges": "im ag", "raw_count": 78049, "count": 78049, "decode_str": "imag"} -{"id": 22277, "token": "maker", "merges": "m aker", "raw_count": 78054, "count": 78054, "decode_str": "maker"} -{"id": 33271, "token": "acion", "merges": "ac ion", "raw_count": 78084, "count": 78084, "decode_str": "acion"} -{"id": 50047, "token": "Anthony", "merges": "Anth ony", "raw_count": 78095, "count": 78095, "decode_str": "Anthony"} -{"id": 8049, "token": "\u0120Project", "merges": "\u0120Pro ject", "raw_count": 74502, "count": 78106, "decode_str": " Project"} -{"id": 7512, "token": "\u0120photo", "merges": "\u0120phot o", "raw_count": 78130, "count": 78130, "decode_str": " photo"} -{"id": 48985, "token": "international", "merges": "intern ational", "raw_count": 78138, "count": 78138, "decode_str": "international"} -{"id": 33720, "token": "Split", "merges": "S plit", "raw_count": 78156, "count": 78156, "decode_str": "Split"} -{"id": 12406, "token": "angular", "merges": "ang ular", "raw_count": 54333, "count": 78168, "decode_str": "angular"} -{"id": 32829, "token": "fine", "merges": "f ine", "raw_count": 78168, "count": 78168, "decode_str": "fine"} -{"id": 14047, "token": "\u0120authorized", "merges": "\u0120author ized", "raw_count": 78171, "count": 78171, "decode_str": " authorized"} -{"id": 54579, "token": "\u00e9\u00bb\u00a2", "merges": "\u00e9\u00bb \u00a2", "raw_count": 78172, "count": 78172, "decode_str": "\u9ee2"} -{"id": 37493, "token": "894", "merges": "89 4", "raw_count": 78193, "count": 78193, "decode_str": "894"} -{"id": 19262, "token": "Prom", "merges": "P rom", "raw_count": 69321, "count": 78227, "decode_str": "Prom"} -{"id": 21116, "token": "\u0120sixty", "merges": "\u0120six ty", "raw_count": 78232, "count": 78232, "decode_str": " sixty"} -{"id": 23315, "token": "Self", "merges": "S elf", "raw_count": 78241, "count": 78241, "decode_str": "Self"} -{"id": 44217, "token": "wu", "merges": "w u", "raw_count": 78252, "count": 78252, "decode_str": "wu"} -{"id": 10127, "token": "caps", "merges": "c aps", "raw_count": 78171, "count": 78258, "decode_str": "caps"} -{"id": 52343, "token": "\u00e6\u00a5\u00ae", "merges": "\u00e6\u00a5 \u00ae", "raw_count": 78259, "count": 78259, "decode_str": "\u696e"} -{"id": 15589, "token": "\u0120jew", "merges": "\u0120j ew", "raw_count": 61390, "count": 78263, "decode_str": " jew"} -{"id": 37908, "token": "Qi", "merges": "Q i", "raw_count": 77765, "count": 78265, "decode_str": "Qi"} -{"id": 10387, "token": "including", "merges": "in cluding", "raw_count": 78266, "count": 78266, "decode_str": "including"} -{"id": 8980, "token": "\u0120bind", "merges": "\u0120b ind", "raw_count": 55772, "count": 78266, "decode_str": " bind"} -{"id": 32259, "token": "Rod", "merges": "R od", "raw_count": 78268, "count": 78268, "decode_str": "Rod"} -{"id": 9775, "token": "\u0120instruction", "merges": "\u0120inst ruction", "raw_count": 78272, "count": 78272, "decode_str": " instruction"} -{"id": 7425, "token": "\u0120dil", "merges": "\u0120d il", "raw_count": 13074, "count": 78276, "decode_str": " dil"} -{"id": 18754, "token": "abi", "merges": "ab i", "raw_count": 78291, "count": 78291, "decode_str": "abi"} -{"id": 26364, "token": "flux", "merges": "fl ux", "raw_count": 77668, "count": 78298, "decode_str": "flux"} -{"id": 33300, "token": "Ess", "merges": "E ss", "raw_count": 78317, "count": 78317, "decode_str": "Ess"} -{"id": 17150, "token": "\u0120terrorist", "merges": "\u0120terror ist", "raw_count": 78321, "count": 78321, "decode_str": " terrorist"} -{"id": 7042, "token": "ells", "merges": "ell s", "raw_count": 40020, "count": 78358, "decode_str": "ells"} -{"id": 12111, "token": "dra", "merges": "d ra", "raw_count": 30290, "count": 78361, "decode_str": "dra"} -{"id": 3753, "token": "\u0120nature", "merges": "\u0120n ature", "raw_count": 78393, "count": 78393, "decode_str": " nature"} -{"id": 10230, "token": "\u0120apartment", "merges": "\u0120ap artment", "raw_count": 78401, "count": 78401, "decode_str": " apartment"} -{"id": 5620, "token": "cin", "merges": "c in", "raw_count": 64999, "count": 78401, "decode_str": "cin"} -{"id": 21713, "token": "\u0120MAX", "merges": "\u0120MA X", "raw_count": 78407, "count": 78407, "decode_str": " MAX"} -{"id": 9747, "token": "ende", "merges": "end e", "raw_count": 30945, "count": 78438, "decode_str": "ende"} -{"id": 50614, "token": "\u00e4\u00bf\u00b3", "merges": "\u00e4\u00bf \u00b3", "raw_count": 78462, "count": 78462, "decode_str": "\u4ff3"} -{"id": 12920, "token": "\u0120pm", "merges": "\u0120p m", "raw_count": 78473, "count": 78473, "decode_str": " pm"} -{"id": 14319, "token": "rio", "merges": "ri o", "raw_count": 62906, "count": 78484, "decode_str": "rio"} -{"id": 6726, "token": "\u0120forced", "merges": "\u0120for ced", "raw_count": 78513, "count": 78513, "decode_str": " forced"} -{"id": 9864, "token": "\u0120simulation", "merges": "\u0120sim ulation", "raw_count": 78528, "count": 78528, "decode_str": " simulation"} -{"id": 23925, "token": "jc", "merges": "j c", "raw_count": 78519, "count": 78532, "decode_str": "jc"} -{"id": 25170, "token": "Elements", "merges": "E lements", "raw_count": 78573, "count": 78573, "decode_str": "Elements"} -{"id": 36794, "token": "nz", "merges": "n z", "raw_count": 78593, "count": 78593, "decode_str": "nz"} -{"id": 31268, "token": "\u01201200", "merges": "\u012012 00", "raw_count": 78610, "count": 78610, "decode_str": " 1200"} -{"id": 17192, "token": "plication", "merges": "plic ation", "raw_count": 62054, "count": 78618, "decode_str": "plication"} -{"id": 40446, "token": "alignment", "merges": "al ignment", "raw_count": 78641, "count": 78641, "decode_str": "alignment"} -{"id": 11161, "token": "\u01201989", "merges": "\u012019 89", "raw_count": 78643, "count": 78643, "decode_str": " 1989"} -{"id": 13681, "token": "\u0120dar", "merges": "\u0120d ar", "raw_count": 73977, "count": 78644, "decode_str": " dar"} -{"id": 31889, "token": "Wire", "merges": "W ire", "raw_count": 78644, "count": 78644, "decode_str": "Wire"} -{"id": 18450, "token": "\u0120700", "merges": "\u01207 00", "raw_count": 78665, "count": 78665, "decode_str": " 700"} -{"id": 4321, "token": "\u0120earlier", "merges": "\u0120ear lier", "raw_count": 78668, "count": 78668, "decode_str": " earlier"} -{"id": 139, "token": "\u00cf", "merges": "NULL", "raw_count": 2888, "count": 78669, "decode_str": "\ufffd"} -{"id": 8981, "token": "\u0120recognition", "merges": "\u0120recogn ition", "raw_count": 78680, "count": 78680, "decode_str": " recognition"} -{"id": 20262, "token": "jax", "merges": "j ax", "raw_count": 68927, "count": 78706, "decode_str": "jax"} -{"id": 27232, "token": ")})", "merges": ") })", "raw_count": 78708, "count": 78708, "decode_str": ")})"} -{"id": 13361, "token": "\u0120ml", "merges": "\u0120m l", "raw_count": 78710, "count": 78710, "decode_str": " ml"} -{"id": 19543, "token": "\u0120inventory", "merges": "\u0120invent ory", "raw_count": 78719, "count": 78719, "decode_str": " inventory"} -{"id": 17676, "token": "gra", "merges": "g ra", "raw_count": 73189, "count": 78736, "decode_str": "gra"} -{"id": 4709, "token": "\u0120fear", "merges": "\u0120f ear", "raw_count": 63730, "count": 78739, "decode_str": " fear"} -{"id": 15098, "token": "\u0120corp", "merges": "\u0120cor p", "raw_count": 19480, "count": 78739, "decode_str": " corp"} -{"id": 21132, "token": "ierra", "merges": "ier ra", "raw_count": 78195, "count": 78747, "decode_str": "ierra"} -{"id": 48223, "token": "gay", "merges": "g ay", "raw_count": 78752, "count": 78752, "decode_str": "gay"} -{"id": 34911, "token": "ourses", "merges": "ours es", "raw_count": 78756, "count": 78756, "decode_str": "ourses"} -{"id": 4475, "token": "\u0120wife", "merges": "\u0120w ife", "raw_count": 78771, "count": 78771, "decode_str": " wife"} -{"id": 6099, "token": "\u0120\u00d0\u00be", "merges": "\u0120\u00d0 \u00be", "raw_count": 22429, "count": 78773, "decode_str": " \u043e"} -{"id": 5526, "token": "rical", "merges": "r ical", "raw_count": 28732, "count": 78780, "decode_str": "rical"} -{"id": 32231, "token": "perform", "merges": "per form", "raw_count": 78786, "count": 78786, "decode_str": "perform"} -{"id": 8075, "token": "ials", "merges": "ial s", "raw_count": 69865, "count": 78799, "decode_str": "ials"} -{"id": 26207, "token": "Christian", "merges": "Christ ian", "raw_count": 78805, "count": 78805, "decode_str": "Christian"} -{"id": 28659, "token": "yellow", "merges": "y ellow", "raw_count": 78821, "count": 78821, "decode_str": "yellow"} -{"id": 4577, "token": "\u0120smaller", "merges": "\u0120small er", "raw_count": 78829, "count": 78829, "decode_str": " smaller"} -{"id": 13087, "token": "urations", "merges": "ur ations", "raw_count": 47488, "count": 78865, "decode_str": "urations"} -{"id": 17967, "token": "South", "merges": "S outh", "raw_count": 78882, "count": 78882, "decode_str": "South"} -{"id": 20209, "token": "\u0120unh", "merges": "\u0120un h", "raw_count": 71687, "count": 78885, "decode_str": " unh"} -{"id": 52247, "token": "\u00e6\u0140\u00b0", "merges": "\u00e6\u0140 \u00b0", "raw_count": 78924, "count": 78924, "decode_str": "\u67b0"} -{"id": 31734, "token": "\u0120partnerships", "merges": "\u0120partnership s", "raw_count": 78931, "count": 78931, "decode_str": " partnerships"} -{"id": 11168, "token": "onom", "merges": "on om", "raw_count": 21408, "count": 78934, "decode_str": "onom"} -{"id": 14508, "token": "imation", "merges": "im ation", "raw_count": 27531, "count": 78959, "decode_str": "imation"} -{"id": 27220, "token": "Mapping", "merges": "M apping", "raw_count": 78959, "count": 78959, "decode_str": "Mapping"} -{"id": 41566, "token": "\u0120illicit", "merges": "\u0120ill icit", "raw_count": 78982, "count": 78982, "decode_str": " illicit"} -{"id": 31554, "token": "\u00eb\u00a1", "merges": "\u00eb \u00a1", "raw_count": 10192, "count": 78998, "decode_str": "\ufffd"} -{"id": 5484, "token": "\u0120drink", "merges": "\u0120dr ink", "raw_count": 48190, "count": 79000, "decode_str": " drink"} -{"id": 8011, "token": "^-", "merges": "^ -", "raw_count": 78787, "count": 79000, "decode_str": "^-"} -{"id": 17466, "token": "Flags", "merges": "Fl ags", "raw_count": 79003, "count": 79003, "decode_str": "Flags"} -{"id": 28360, "token": "FG", "merges": "F G", "raw_count": 79019, "count": 79019, "decode_str": "FG"} -{"id": 9772, "token": "attice", "merges": "att ice", "raw_count": 57344, "count": 79021, "decode_str": "attice"} -{"id": 16497, "token": "\u0120translate", "merges": "\u0120transl ate", "raw_count": 79027, "count": 79027, "decode_str": " translate"} -{"id": 9796, "token": "\u0120favour", "merges": "\u0120fav our", "raw_count": 48436, "count": 79038, "decode_str": " favour"} -{"id": 2796, "token": "\u0120(*", "merges": "\u0120( *", "raw_count": 79038, "count": 79038, "decode_str": " (*"} -{"id": 20319, "token": "\u0120sync", "merges": "\u0120syn c", "raw_count": 79053, "count": 79053, "decode_str": " sync"} -{"id": 36853, "token": "Operator", "merges": "Oper ator", "raw_count": 79057, "count": 79057, "decode_str": "Operator"} -{"id": 8588, "token": "\u0120weather", "merges": "\u0120we ather", "raw_count": 79073, "count": 79073, "decode_str": " weather"} -{"id": 34611, "token": "MIC", "merges": "M IC", "raw_count": 79093, "count": 79093, "decode_str": "MIC"} -{"id": 31093, "token": "IENT", "merges": "I ENT", "raw_count": 79098, "count": 79098, "decode_str": "IENT"} -{"id": 44827, "token": "brow", "merges": "b row", "raw_count": 79125, "count": 79125, "decode_str": "brow"} -{"id": 21747, "token": "Final", "merges": "F inal", "raw_count": 79129, "count": 79129, "decode_str": "Final"} -{"id": 44396, "token": "connector", "merges": "conne ctor", "raw_count": 79130, "count": 79130, "decode_str": "connector"} -{"id": 6027, "token": "\u00c3\u0139", "merges": "\u00c3 \u0139", "raw_count": 79136, "count": 79136, "decode_str": "\u00d7"} -{"id": 14654, "token": "\u0120fis", "merges": "\u0120f is", "raw_count": 37083, "count": 79149, "decode_str": " fis"} -{"id": 42988, "token": "hint", "merges": "h int", "raw_count": 79162, "count": 79162, "decode_str": "hint"} -{"id": 28541, "token": "Side", "merges": "S ide", "raw_count": 79167, "count": 79167, "decode_str": "Side"} -{"id": 20875, "token": "die", "merges": "d ie", "raw_count": 79002, "count": 79172, "decode_str": "die"} -{"id": 47416, "token": "Training", "merges": "Tra ining", "raw_count": 79186, "count": 79186, "decode_str": "Training"} -{"id": 37164, "token": "\u0120cached", "merges": "\u0120c ached", "raw_count": 79188, "count": 79188, "decode_str": " cached"} -{"id": 12239, "token": "overs", "merges": "o vers", "raw_count": 76830, "count": 79190, "decode_str": "overs"} -{"id": 7866, "token": "\u0120starts", "merges": "\u0120start s", "raw_count": 79197, "count": 79197, "decode_str": " starts"} -{"id": 26699, "token": "\u0120displaced", "merges": "\u0120displ aced", "raw_count": 79199, "count": 79199, "decode_str": " displaced"} -{"id": 30844, "token": "park", "merges": "p ark", "raw_count": 79210, "count": 79210, "decode_str": "park"} -{"id": 6494, "token": "\u0120billion", "merges": "\u0120b illion", "raw_count": 78282, "count": 79212, "decode_str": " billion"} -{"id": 28674, "token": "\u0120Session", "merges": "\u0120S ession", "raw_count": 79216, "count": 79216, "decode_str": " Session"} -{"id": 19221, "token": "school", "merges": "s chool", "raw_count": 79219, "count": 79219, "decode_str": "school"} -{"id": 45535, "token": "1006", "merges": "100 6", "raw_count": 79228, "count": 79228, "decode_str": "1006"} -{"id": 45057, "token": "XM", "merges": "X M", "raw_count": 79229, "count": 79229, "decode_str": "XM"} -{"id": 4729, "token": "ifornia", "merges": "iforn ia", "raw_count": 37857, "count": 79236, "decode_str": "ifornia"} -{"id": 12353, "token": "\u0120actor", "merges": "\u0120act or", "raw_count": 79254, "count": 79254, "decode_str": " actor"} -{"id": 18256, "token": "hum", "merges": "h um", "raw_count": 79258, "count": 79258, "decode_str": "hum"} -{"id": 6054, "token": "\u0120rise", "merges": "\u0120r ise", "raw_count": 79264, "count": 79264, "decode_str": " rise"} -{"id": 7782, "token": "ivered", "merges": "ive red", "raw_count": 16604, "count": 79274, "decode_str": "ivered"} -{"id": 8979, "token": "\u0120shop", "merges": "\u0120sh op", "raw_count": 79287, "count": 79287, "decode_str": " shop"} -{"id": 5818, "token": "\u0120ring", "merges": "\u0120r ing", "raw_count": 76607, "count": 79300, "decode_str": " ring"} -{"id": 24069, "token": "zu", "merges": "z u", "raw_count": 79304, "count": 79304, "decode_str": "zu"} -{"id": 39816, "token": "trip", "merges": "t rip", "raw_count": 79307, "count": 79307, "decode_str": "trip"} -{"id": 8104, "token": "\u0120attacks", "merges": "\u0120attack s", "raw_count": 79308, "count": 79308, "decode_str": " attacks"} -{"id": 14008, "token": "\u0120mol", "merges": "\u0120m ol", "raw_count": 76704, "count": 79310, "decode_str": " mol"} -{"id": 25696, "token": "IJ", "merges": "I J", "raw_count": 79323, "count": 79323, "decode_str": "IJ"} -{"id": 25781, "token": "nat", "merges": "n at", "raw_count": 79350, "count": 79350, "decode_str": "nat"} -{"id": 50222, "token": "744", "merges": "7 44", "raw_count": 79358, "count": 79358, "decode_str": "744"} -{"id": 15272, "token": "\u0120conflicts", "merges": "\u0120conflic ts", "raw_count": 79368, "count": 79368, "decode_str": " conflicts"} -{"id": 10677, "token": "\u012074", "merges": "\u01207 4", "raw_count": 79373, "count": 79373, "decode_str": " 74"} -{"id": 26161, "token": "structor", "merges": "struct or", "raw_count": 27203, "count": 79375, "decode_str": "structor"} -{"id": 37813, "token": "sites", "merges": "s ites", "raw_count": 79387, "count": 79387, "decode_str": "sites"} -{"id": 21529, "token": "kr", "merges": "k r", "raw_count": 79393, "count": 79393, "decode_str": "kr"} -{"id": 31748, "token": "spaces", "merges": "sp aces", "raw_count": 79407, "count": 79407, "decode_str": "spaces"} -{"id": 22586, "token": "\u0120workshop", "merges": "\u0120works hop", "raw_count": 79414, "count": 79414, "decode_str": " workshop"} -{"id": 13200, "token": "\u0120governing", "merges": "\u0120gover ning", "raw_count": 79417, "count": 79417, "decode_str": " governing"} -{"id": 12282, "token": "\u0120dates", "merges": "\u0120d ates", "raw_count": 79427, "count": 79427, "decode_str": " dates"} -{"id": 5481, "token": "\u0120detection", "merges": "\u0120det ection", "raw_count": 79430, "count": 79430, "decode_str": " detection"} -{"id": 26576, "token": "bh", "merges": "b h", "raw_count": 79430, "count": 79430, "decode_str": "bh"} -{"id": 13905, "token": "\u0120span", "merges": "\u0120sp an", "raw_count": 79443, "count": 79443, "decode_str": " span"} -{"id": 10220, "token": "\u0120explo", "merges": "\u0120expl o", "raw_count": 2437, "count": 79454, "decode_str": " explo"} -{"id": 41584, "token": "CW", "merges": "C W", "raw_count": 79462, "count": 79462, "decode_str": "CW"} -{"id": 47123, "token": "LOW", "merges": "L OW", "raw_count": 79464, "count": 79464, "decode_str": "LOW"} -{"id": 40695, "token": "Jam", "merges": "J am", "raw_count": 79477, "count": 79477, "decode_str": "Jam"} -{"id": 42937, "token": "SOCK", "merges": "S OCK", "raw_count": 79499, "count": 79499, "decode_str": "SOCK"} -{"id": 52903, "token": "\u00e7\u0138\u0136", "merges": "\u00e7\u0138 \u0136", "raw_count": 79505, "count": 79505, "decode_str": "\u7594"} -{"id": 3405, "token": "\u0120stra", "merges": "\u0120st ra", "raw_count": 18019, "count": 79507, "decode_str": " stra"} -{"id": 23855, "token": "SHA", "merges": "SH A", "raw_count": 79510, "count": 79510, "decode_str": "SHA"} -{"id": 40700, "token": "Ju", "merges": "J u", "raw_count": 79525, "count": 79525, "decode_str": "Ju"} -{"id": 17752, "token": "atern", "merges": "ater n", "raw_count": 51081, "count": 79528, "decode_str": "atern"} -{"id": 9436, "token": "\u0120conversion", "merges": "\u0120con version", "raw_count": 79568, "count": 79568, "decode_str": " conversion"} -{"id": 38727, "token": "Spect", "merges": "S pect", "raw_count": 79573, "count": 79573, "decode_str": "Spect"} -{"id": 2773, "token": "That", "merges": "T hat", "raw_count": 79573, "count": 79573, "decode_str": "That"} -{"id": 7221, "token": "\u0120minim", "merges": "\u0120min im", "raw_count": 20949, "count": 79576, "decode_str": " minim"} -{"id": 6890, "token": "\u0120changing", "merges": "\u0120chang ing", "raw_count": 79621, "count": 79621, "decode_str": " changing"} -{"id": 42328, "token": "WARNING", "merges": "WARN ING", "raw_count": 79635, "count": 79635, "decode_str": "WARNING"} -{"id": 42773, "token": "UTC", "merges": "UT C", "raw_count": 79652, "count": 79652, "decode_str": "UTC"} -{"id": 17147, "token": "\u0120defence", "merges": "\u0120def ence", "raw_count": 79666, "count": 79666, "decode_str": " defence"} -{"id": 42814, "token": "\u0120Conv", "merges": "\u0120Con v", "raw_count": 79669, "count": 79669, "decode_str": " Conv"} -{"id": 39126, "token": "077", "merges": "0 77", "raw_count": 79673, "count": 79673, "decode_str": "077"} -{"id": 3182, "token": "define", "merges": "def ine", "raw_count": 79677, "count": 79677, "decode_str": "define"} -{"id": 24416, "token": "invoke", "merges": "inv oke", "raw_count": 79691, "count": 79691, "decode_str": "invoke"} -{"id": 30764, "token": "WORK", "merges": "W ORK", "raw_count": 79725, "count": 79725, "decode_str": "WORK"} -{"id": 38406, "token": "Lex", "merges": "L ex", "raw_count": 79732, "count": 79732, "decode_str": "Lex"} -{"id": 32883, "token": "Env", "merges": "En v", "raw_count": 79761, "count": 79761, "decode_str": "Env"} -{"id": 53090, "token": "\u00e7\u00a2\u0135", "merges": "\u00e7\u00a2 \u0135", "raw_count": 79775, "count": 79775, "decode_str": "\u7893"} -{"id": 9314, "token": "erk", "merges": "er k", "raw_count": 68911, "count": 79780, "decode_str": "erk"} -{"id": 6857, "token": "icated", "merges": "ic ated", "raw_count": 18375, "count": 79785, "decode_str": "icated"} -{"id": 15349, "token": "agment", "merges": "ag ment", "raw_count": 2521, "count": 79795, "decode_str": "agment"} -{"id": 5704, "token": "etry", "merges": "et ry", "raw_count": 51198, "count": 79810, "decode_str": "etry"} -{"id": 7541, "token": "andon", "merges": "and on", "raw_count": 45905, "count": 79829, "decode_str": "andon"} -{"id": 23578, "token": "ints", "merges": "int s", "raw_count": 79832, "count": 79832, "decode_str": "ints"} -{"id": 36058, "token": "bk", "merges": "b k", "raw_count": 79832, "count": 79832, "decode_str": "bk"} -{"id": 23706, "token": "solid", "merges": "s olid", "raw_count": 79841, "count": 79841, "decode_str": "solid"} -{"id": 34245, "token": "dispatch", "merges": "disp atch", "raw_count": 79859, "count": 79859, "decode_str": "dispatch"} -{"id": 31447, "token": "FORMAT", "merges": "FOR MAT", "raw_count": 79868, "count": 79868, "decode_str": "FORMAT"} -{"id": 17408, "token": "fred", "merges": "f red", "raw_count": 78133, "count": 79897, "decode_str": "fred"} -{"id": 11595, "token": "\u0120manual", "merges": "\u0120man ual", "raw_count": 79899, "count": 79899, "decode_str": " manual"} -{"id": 10513, "token": "\u0120creates", "merges": "\u0120creat es", "raw_count": 79905, "count": 79905, "decode_str": " creates"} -{"id": 9289, "token": "anish", "merges": "an ish", "raw_count": 78604, "count": 79915, "decode_str": "anish"} -{"id": 18880, "token": "\u0120suite", "merges": "\u0120su ite", "raw_count": 79916, "count": 79916, "decode_str": " suite"} -{"id": 32876, "token": "Coord", "merges": "Co ord", "raw_count": 79930, "count": 79930, "decode_str": "Coord"} -{"id": 51242, "token": "\u00e5\u0141\u00bc", "merges": "\u00e5\u0141 \u00bc", "raw_count": 79935, "count": 79935, "decode_str": "\u57fc"} -{"id": 5207, "token": "\u0120whom", "merges": "\u0120wh om", "raw_count": 79958, "count": 79958, "decode_str": " whom"} -{"id": 10250, "token": "\u0120wal", "merges": "\u0120w al", "raw_count": 22628, "count": 79974, "decode_str": " wal"} -{"id": 17198, "token": "izard", "merges": "iz ard", "raw_count": 59118, "count": 79975, "decode_str": "izard"} -{"id": 12072, "token": "erated", "merges": "er ated", "raw_count": 58153, "count": 79986, "decode_str": "erated"} -{"id": 14492, "token": "\u0120decimal", "merges": "\u0120dec imal", "raw_count": 80026, "count": 80026, "decode_str": " decimal"} -{"id": 30220, "token": "GROUP", "merges": "GR OUP", "raw_count": 80032, "count": 80032, "decode_str": "GROUP"} -{"id": 42651, "token": "\u0120ld", "merges": "\u0120l d", "raw_count": 80035, "count": 80035, "decode_str": " ld"} -{"id": 22297, "token": "equals", "merges": "equ als", "raw_count": 80041, "count": 80041, "decode_str": "equals"} -{"id": 24121, "token": "Events", "merges": "Ev ents", "raw_count": 80093, "count": 80093, "decode_str": "Events"} -{"id": 9302, "token": "\u0120succeed", "merges": "\u0120suc ceed", "raw_count": 34948, "count": 80094, "decode_str": " succeed"} -{"id": 4440, "token": "\u0120imag", "merges": "\u0120im ag", "raw_count": 29405, "count": 80105, "decode_str": " imag"} -{"id": 8579, "token": ")|", "merges": ") |", "raw_count": 79792, "count": 80105, "decode_str": ")|"} -{"id": 13891, "token": "\u0120reversed", "merges": "\u0120revers ed", "raw_count": 80124, "count": 80124, "decode_str": " reversed"} -{"id": 15755, "token": "\u0120Command", "merges": "\u0120Com mand", "raw_count": 80125, "count": 80125, "decode_str": " Command"} -{"id": 4130, "token": "\u0120everyone", "merges": "\u0120every one", "raw_count": 80132, "count": 80132, "decode_str": " everyone"} -{"id": 7209, "token": "reek", "merges": "ree k", "raw_count": 65336, "count": 80132, "decode_str": "reek"} -{"id": 7351, "token": "\u0120bag", "merges": "\u0120b ag", "raw_count": 69315, "count": 80142, "decode_str": " bag"} -{"id": 9695, "token": "\u0120advoc", "merges": "\u0120adv oc", "raw_count": 152, "count": 80144, "decode_str": " advoc"} -{"id": 6970, "token": "\u0120curve", "merges": "\u0120cur ve", "raw_count": 80157, "count": 80157, "decode_str": " curve"} -{"id": 29445, "token": "atial", "merges": "at ial", "raw_count": 80172, "count": 80172, "decode_str": "atial"} -{"id": 21542, "token": "checked", "merges": "check ed", "raw_count": 80178, "count": 80178, "decode_str": "checked"} -{"id": 49062, "token": "Kelly", "merges": "K elly", "raw_count": 80185, "count": 80185, "decode_str": "Kelly"} -{"id": 13431, "token": "amo", "merges": "am o", "raw_count": 78875, "count": 80217, "decode_str": "amo"} -{"id": 4929, "token": "\u0120brother", "merges": "\u0120bro ther", "raw_count": 54330, "count": 80231, "decode_str": " brother"} -{"id": 25125, "token": "urchase", "merges": "urch ase", "raw_count": 75565, "count": 80235, "decode_str": "urchase"} -{"id": 48778, "token": "\u0120999", "merges": "\u01209 99", "raw_count": 80239, "count": 80239, "decode_str": " 999"} -{"id": 8351, "token": "\u0120terminal", "merges": "\u0120term inal", "raw_count": 80243, "count": 80243, "decode_str": " terminal"} -{"id": 5320, "token": "\u0120extrem", "merges": "\u0120ext rem", "raw_count": 21055, "count": 80271, "decode_str": " extrem"} -{"id": 6425, "token": "\u0120equivalent", "merges": "\u0120equival ent", "raw_count": 80284, "count": 80284, "decode_str": " equivalent"} -{"id": 43726, "token": "893", "merges": "89 3", "raw_count": 80285, "count": 80285, "decode_str": "893"} -{"id": 7762, "token": "\u00d0\u00b7", "merges": "\u00d0 \u00b7", "raw_count": 29109, "count": 80296, "decode_str": "\u0437"} -{"id": 6814, "token": "\u0120measurement", "merges": "\u0120measure ment", "raw_count": 80312, "count": 80312, "decode_str": " measurement"} -{"id": 9037, "token": "\u0120episode", "merges": "\u0120epis ode", "raw_count": 80315, "count": 80315, "decode_str": " episode"} -{"id": 6831, "token": "\u0120college", "merges": "\u0120col lege", "raw_count": 80322, "count": 80322, "decode_str": " college"} -{"id": 13256, "token": "alg", "merges": "al g", "raw_count": 73622, "count": 80339, "decode_str": "alg"} -{"id": 13526, "token": "\u00e2\u0136\u0122\u00e2\u0136\u0122", "merges": "\u00e2\u0136\u0122 \u00e2\u0136\u0122", "raw_count": 29395, "count": 80349, "decode_str": "\u2500\u2500"} -{"id": 27902, "token": "Sync", "merges": "S ync", "raw_count": 80371, "count": 80371, "decode_str": "Sync"} -{"id": 39363, "token": "Motion", "merges": "M otion", "raw_count": 80385, "count": 80385, "decode_str": "Motion"} -{"id": 18139, "token": "Exper", "merges": "Ex per", "raw_count": 72376, "count": 80415, "decode_str": "Exper"} -{"id": 36301, "token": "Optional", "merges": "Opt ional", "raw_count": 80425, "count": 80425, "decode_str": "Optional"} -{"id": 21236, "token": "\u0120Item", "merges": "\u0120It em", "raw_count": 80430, "count": 80430, "decode_str": " Item"} -{"id": 9095, "token": "rolled", "merges": "roll ed", "raw_count": 46001, "count": 80464, "decode_str": "rolled"} -{"id": 14833, "token": "0028", "merges": "00 28", "raw_count": 80472, "count": 80472, "decode_str": "0028"} -{"id": 16918, "token": "\u0120240", "merges": "\u01202 40", "raw_count": 80472, "count": 80472, "decode_str": " 240"} -{"id": 28206, "token": "want", "merges": "w ant", "raw_count": 80490, "count": 80490, "decode_str": "want"} -{"id": 12862, "token": "ocols", "merges": "oc ols", "raw_count": 30398, "count": 80525, "decode_str": "ocols"} -{"id": 14676, "token": "habil", "merges": "h abil", "raw_count": 10774, "count": 80526, "decode_str": "habil"} -{"id": 45767, "token": "matching", "merges": "match ing", "raw_count": 80528, "count": 80528, "decode_str": "matching"} -{"id": 28853, "token": "shots", "merges": "sh ots", "raw_count": 80540, "count": 80540, "decode_str": "shots"} -{"id": 8150, "token": "\u0120toler", "merges": "\u0120to ler", "raw_count": 6764, "count": 80556, "decode_str": " toler"} -{"id": 27657, "token": "\u0120rc", "merges": "\u0120r c", "raw_count": 80574, "count": 80574, "decode_str": " rc"} -{"id": 30045, "token": "Radio", "merges": "Rad io", "raw_count": 80591, "count": 80591, "decode_str": "Radio"} -{"id": 45410, "token": "draft", "merges": "d raft", "raw_count": 80614, "count": 80614, "decode_str": "draft"} -{"id": 7065, "token": "\u00d0\u00b0\u00d1\u0124", "merges": "\u00d0\u00b0 \u00d1\u0124", "raw_count": 42564, "count": 80614, "decode_str": "\u0430\u0442"} -{"id": 16753, "token": "\u0120pose", "merges": "\u0120p ose", "raw_count": 80616, "count": 80616, "decode_str": " pose"} -{"id": 8993, "token": "\u0120immediate", "merges": "\u0120immedi ate", "raw_count": 80619, "count": 80619, "decode_str": " immediate"} -{"id": 32269, "token": "Vir", "merges": "V ir", "raw_count": 44497, "count": 80622, "decode_str": "Vir"} -{"id": 5352, "token": "\u0120fresh", "merges": "\u0120f resh", "raw_count": 68459, "count": 80628, "decode_str": " fresh"} -{"id": 48795, "token": "\u0120treaties", "merges": "\u0120treat ies", "raw_count": 80630, "count": 80630, "decode_str": " treaties"} -{"id": 20867, "token": "eme", "merges": "em e", "raw_count": 80631, "count": 80631, "decode_str": "eme"} -{"id": 10723, "token": "aire", "merges": "a ire", "raw_count": 78971, "count": 80651, "decode_str": "aire"} -{"id": 17244, "token": "andra", "merges": "and ra", "raw_count": 80652, "count": 80652, "decode_str": "andra"} -{"id": 11103, "token": "\u0120Build", "merges": "\u0120B uild", "raw_count": 70848, "count": 80665, "decode_str": " Build"} -{"id": 52005, "token": "\u00e6\u0130\u00b4", "merges": "\u00e6\u0130 \u00b4", "raw_count": 80666, "count": 80666, "decode_str": "\u63b4"} -{"id": 5098, "token": "\u0120books", "merges": "\u0120book s", "raw_count": 80669, "count": 80669, "decode_str": " books"} -{"id": 21276, "token": "Family", "merges": "F amily", "raw_count": 80689, "count": 80689, "decode_str": "Family"} -{"id": 11700, "token": "\u0120SQL", "merges": "\u0120S QL", "raw_count": 80702, "count": 80702, "decode_str": " SQL"} -{"id": 3432, "token": "\u0120surv", "merges": "\u0120sur v", "raw_count": 1171, "count": 80706, "decode_str": " surv"} -{"id": 9607, "token": "estival", "merges": "est ival", "raw_count": 42576, "count": 80719, "decode_str": "estival"} -{"id": 31871, "token": "Temp", "merges": "Tem p", "raw_count": 80720, "count": 80720, "decode_str": "Temp"} -{"id": 4566, "token": "\u0120goes", "merges": "\u0120go es", "raw_count": 80729, "count": 80729, "decode_str": " goes"} -{"id": 17577, "token": "Runtime", "merges": "R untime", "raw_count": 80565, "count": 80772, "decode_str": "Runtime"} -{"id": 4410, "token": "\u0120Red", "merges": "\u0120R ed", "raw_count": 75227, "count": 80774, "decode_str": " Red"} -{"id": 5822, "token": "\u0120\u00d0\u00b8", "merges": "\u0120\u00d0 \u00b8", "raw_count": 37912, "count": 80777, "decode_str": " \u0438"} -{"id": 33862, "token": "Crypt", "merges": "C rypt", "raw_count": 80803, "count": 80803, "decode_str": "Crypt"} -{"id": 23313, "token": "\u0120jer", "merges": "\u0120j er", "raw_count": 70961, "count": 80811, "decode_str": " jer"} -{"id": 12453, "token": "\u0120addresses", "merges": "\u0120address es", "raw_count": 80822, "count": 80822, "decode_str": " addresses"} -{"id": 13434, "token": "\u0120scalar", "merges": "\u0120scal ar", "raw_count": 80832, "count": 80832, "decode_str": " scalar"} -{"id": 43193, "token": "tel", "merges": "t el", "raw_count": 80833, "count": 80833, "decode_str": "tel"} -{"id": 30377, "token": "Ele", "merges": "E le", "raw_count": 80853, "count": 80853, "decode_str": "Ele"} -{"id": 21109, "token": "IONS", "merges": "ION S", "raw_count": 80857, "count": 80857, "decode_str": "IONS"} -{"id": 46591, "token": "xico", "merges": "x ico", "raw_count": 80867, "count": 80867, "decode_str": "xico"} -{"id": 5750, "token": "\u0120advantage", "merges": "\u0120advant age", "raw_count": 76981, "count": 80895, "decode_str": " advantage"} -{"id": 8429, "token": "\u0120pu", "merges": "\u0120p u", "raw_count": 45822, "count": 80912, "decode_str": " pu"} -{"id": 31395, "token": "JA", "merges": "J A", "raw_count": 80942, "count": 80942, "decode_str": "JA"} -{"id": 31724, "token": "IDs", "merges": "ID s", "raw_count": 80949, "count": 80949, "decode_str": "IDs"} -{"id": 8951, "token": "\u0120CL", "merges": "\u0120C L", "raw_count": 44006, "count": 80950, "decode_str": " CL"} -{"id": 2594, "token": "\u0120See", "merges": "\u0120Se e", "raw_count": 80697, "count": 80952, "decode_str": " See"} -{"id": 28893, "token": "DU", "merges": "D U", "raw_count": 80954, "count": 80954, "decode_str": "DU"} -{"id": 23938, "token": "Enum", "merges": "En um", "raw_count": 80958, "count": 80958, "decode_str": "Enum"} -{"id": 31305, "token": "VIEW", "merges": "V IEW", "raw_count": 81009, "count": 81009, "decode_str": "VIEW"} -{"id": 8306, "token": "rac", "merges": "r ac", "raw_count": 78449, "count": 81020, "decode_str": "rac"} -{"id": 7934, "token": "\u0120sole", "merges": "\u0120so le", "raw_count": 48756, "count": 81032, "decode_str": " sole"} -{"id": 16032, "token": "elligence", "merges": "ellig ence", "raw_count": 61367, "count": 81035, "decode_str": "elligence"} -{"id": 5721, "token": "\u0120Fe", "merges": "\u0120F e", "raw_count": 18449, "count": 81038, "decode_str": " Fe"} -{"id": 3834, "token": "ashing", "merges": "ash ing", "raw_count": 32098, "count": 81051, "decode_str": "ashing"} -{"id": 14827, "token": "auc", "merges": "a uc", "raw_count": 71350, "count": 81052, "decode_str": "auc"} -{"id": 47586, "token": "infer", "merges": "in fer", "raw_count": 81059, "count": 81059, "decode_str": "infer"} -{"id": 12841, "token": "\u0120ignored", "merges": "\u0120ign ored", "raw_count": 81062, "count": 81062, "decode_str": " ignored"} -{"id": 16540, "token": "\u0120raises", "merges": "\u0120ra ises", "raw_count": 81071, "count": 81071, "decode_str": " raises"} -{"id": 37009, "token": "LIM", "merges": "L IM", "raw_count": 81097, "count": 81097, "decode_str": "LIM"} -{"id": 27223, "token": "Chinese", "merges": "Ch inese", "raw_count": 81100, "count": 81100, "decode_str": "Chinese"} -{"id": 22355, "token": "VALUE", "merges": "VAL UE", "raw_count": 81100, "count": 81100, "decode_str": "VALUE"} -{"id": 11953, "token": "\u0120FL", "merges": "\u0120F L", "raw_count": 23844, "count": 81113, "decode_str": " FL"} -{"id": 21840, "token": "ATTR", "merges": "AT TR", "raw_count": 81124, "count": 81124, "decode_str": "ATTR"} -{"id": 3762, "token": "\u0120theory", "merges": "\u0120the ory", "raw_count": 81140, "count": 81140, "decode_str": " theory"} -{"id": 6835, "token": "\u0120intellig", "merges": "\u0120int ellig", "raw_count": 3260, "count": 81153, "decode_str": " intellig"} -{"id": 13616, "token": "ede", "merges": "ed e", "raw_count": 81177, "count": 81177, "decode_str": "ede"} -{"id": 26836, "token": "--\"", "merges": "-- \"", "raw_count": 81201, "count": 81201, "decode_str": "--\""} -{"id": 12567, "token": ".:", "merges": ". :", "raw_count": 81205, "count": 81205, "decode_str": ".:"} -{"id": 27691, "token": "\u0120conferences", "merges": "\u0120con ferences", "raw_count": 81223, "count": 81223, "decode_str": " conferences"} -{"id": 41612, "token": "842", "merges": "84 2", "raw_count": 81247, "count": 81247, "decode_str": "842"} -{"id": 9232, "token": "\u0120capture", "merges": "\u0120capt ure", "raw_count": 81249, "count": 81249, "decode_str": " capture"} -{"id": 11194, "token": "rose", "merges": "ro se", "raw_count": 66243, "count": 81258, "decode_str": "rose"} -{"id": 14268, "token": "\u0120cookies", "merges": "\u0120cook ies", "raw_count": 81263, "count": 81263, "decode_str": " cookies"} -{"id": 9727, "token": "\u0120moves", "merges": "\u0120mov es", "raw_count": 81263, "count": 81263, "decode_str": " moves"} -{"id": 33464, "token": "horizontal", "merges": "hor izontal", "raw_count": 81282, "count": 81282, "decode_str": "horizontal"} -{"id": 31258, "token": "]'", "merges": "] '", "raw_count": 81287, "count": 81287, "decode_str": "]'"} -{"id": 39842, "token": "manual", "merges": "man ual", "raw_count": 81292, "count": 81292, "decode_str": "manual"} -{"id": 26336, "token": "CUR", "merges": "C UR", "raw_count": 47278, "count": 81295, "decode_str": "CUR"} -{"id": 33798, "token": "Pier", "merges": "P ier", "raw_count": 30678, "count": 81312, "decode_str": "Pier"} -{"id": 12466, "token": "gered", "merges": "ge red", "raw_count": 49551, "count": 81341, "decode_str": "gered"} -{"id": 19431, "token": "fund", "merges": "f und", "raw_count": 69238, "count": 81353, "decode_str": "fund"} -{"id": 4369, "token": "\u0120psych", "merges": "\u0120ps ych", "raw_count": 14682, "count": 81364, "decode_str": " psych"} -{"id": 5694, "token": "\u0120motor", "merges": "\u0120mot or", "raw_count": 76158, "count": 81366, "decode_str": " motor"} -{"id": 29793, "token": "\u0120conventions", "merges": "\u0120con ventions", "raw_count": 81383, "count": 81383, "decode_str": " conventions"} -{"id": 10630, "token": "\u0120consumer", "merges": "\u0120consum er", "raw_count": 81388, "count": 81388, "decode_str": " consumer"} -{"id": 10358, "token": "\u0120plug", "merges": "\u0120pl ug", "raw_count": 28898, "count": 81412, "decode_str": " plug"} -{"id": 35769, "token": "Ash", "merges": "A sh", "raw_count": 81415, "count": 81415, "decode_str": "Ash"} -{"id": 8416, "token": "\u0120finish", "merges": "\u0120fin ish", "raw_count": 81416, "count": 81416, "decode_str": " finish"} -{"id": 8578, "token": "\u0120subset", "merges": "\u0120sub set", "raw_count": 69687, "count": 81455, "decode_str": " subset"} -{"id": 49241, "token": "Exchange", "merges": "Ex change", "raw_count": 81464, "count": 81464, "decode_str": "Exchange"} -{"id": 35640, "token": "suggest", "merges": "s uggest", "raw_count": 81475, "count": 81475, "decode_str": "suggest"} -{"id": 14244, "token": "\u0120***", "merges": "\u0120** *", "raw_count": 81477, "count": 81477, "decode_str": " ***"} -{"id": 9440, "token": "idential", "merges": "ident ial", "raw_count": 20175, "count": 81483, "decode_str": "idential"} -{"id": 9786, "token": "urse", "merges": "ur se", "raw_count": 49788, "count": 81497, "decode_str": "urse"} -{"id": 35097, "token": "\u0120Token", "merges": "\u0120T oken", "raw_count": 81505, "count": 81505, "decode_str": " Token"} -{"id": 13350, "token": "plete", "merges": "ple te", "raw_count": 4608, "count": 81524, "decode_str": "plete"} -{"id": 46341, "token": "Labels", "merges": "Lab els", "raw_count": 81537, "count": 81537, "decode_str": "Labels"} -{"id": 4365, "token": "\u0120swe", "merges": "\u0120s we", "raw_count": 8292, "count": 81544, "decode_str": " swe"} -{"id": 44266, "token": "dream", "merges": "d ream", "raw_count": 81548, "count": 81548, "decode_str": "dream"} -{"id": 10123, "token": "\u0120reviews", "merges": "\u0120review s", "raw_count": 81582, "count": 81582, "decode_str": " reviews"} -{"id": 33339, "token": "Central", "merges": "Cent ral", "raw_count": 81584, "count": 81584, "decode_str": "Central"} -{"id": 20201, "token": "URI", "merges": "UR I", "raw_count": 81473, "count": 81592, "decode_str": "URI"} -{"id": 21848, "token": "due", "merges": "d ue", "raw_count": 81627, "count": 81627, "decode_str": "due"} -{"id": 9236, "token": "ige", "merges": "ig e", "raw_count": 77220, "count": 81660, "decode_str": "ige"} -{"id": 6815, "token": "\u0120nic", "merges": "\u0120n ic", "raw_count": 61168, "count": 81661, "decode_str": " nic"} -{"id": 9261, "token": "\u0120transformation", "merges": "\u0120trans formation", "raw_count": 81663, "count": 81663, "decode_str": " transformation"} -{"id": 11102, "token": "\u012071", "merges": "\u01207 1", "raw_count": 81668, "count": 81668, "decode_str": " 71"} -{"id": 40539, "token": "installed", "merges": "install ed", "raw_count": 81679, "count": 81679, "decode_str": "installed"} -{"id": 9459, "token": "\u0120regime", "merges": "\u0120reg ime", "raw_count": 81701, "count": 81701, "decode_str": " regime"} -{"id": 8538, "token": "erior", "merges": "er ior", "raw_count": 31527, "count": 81705, "decode_str": "erior"} -{"id": 28119, "token": "sudo", "merges": "s udo", "raw_count": 81716, "count": 81716, "decode_str": "sudo"} -{"id": 16029, "token": "inery", "merges": "in ery", "raw_count": 18001, "count": 81742, "decode_str": "inery"} -{"id": 48361, "token": "\u0120xs", "merges": "\u0120x s", "raw_count": 81750, "count": 81750, "decode_str": " xs"} -{"id": 36755, "token": "VOL", "merges": "V OL", "raw_count": 81776, "count": 81776, "decode_str": "VOL"} -{"id": 10098, "token": "\u0120launched", "merges": "\u0120laun ched", "raw_count": 81801, "count": 81801, "decode_str": " launched"} -{"id": 15375, "token": "apore", "merges": "ap ore", "raw_count": 80383, "count": 81807, "decode_str": "apore"} -{"id": 19385, "token": "uki", "merges": "uk i", "raw_count": 81313, "count": 81807, "decode_str": "uki"} -{"id": 25055, "token": "LAY", "merges": "LA Y", "raw_count": 67848, "count": 81813, "decode_str": "LAY"} -{"id": 14002, "token": "\u0120cancel", "merges": "\u0120can cel", "raw_count": 70938, "count": 81831, "decode_str": " cancel"} -{"id": 19932, "token": "Der", "merges": "D er", "raw_count": 71841, "count": 81832, "decode_str": "Der"} -{"id": 11047, "token": "cule", "merges": "c ule", "raw_count": 3706, "count": 81857, "decode_str": "cule"} -{"id": 8244, "token": "\u0120closely", "merges": "\u0120clos ely", "raw_count": 81865, "count": 81865, "decode_str": " closely"} -{"id": 5272, "token": "\u0120reasonable", "merges": "\u0120reason able", "raw_count": 81867, "count": 81867, "decode_str": " reasonable"} -{"id": 13560, "token": "iah", "merges": "ia h", "raw_count": 81784, "count": 81867, "decode_str": "iah"} -{"id": 47941, "token": "jac", "merges": "j ac", "raw_count": 81889, "count": 81889, "decode_str": "jac"} -{"id": 22997, "token": "Analysis", "merges": "An alysis", "raw_count": 81893, "count": 81893, "decode_str": "Analysis"} -{"id": 10850, "token": "\u0120Game", "merges": "\u0120G ame", "raw_count": 81910, "count": 81910, "decode_str": " Game"} -{"id": 41160, "token": "Yang", "merges": "Y ang", "raw_count": 81921, "count": 81921, "decode_str": "Yang"} -{"id": 38479, "token": "capital", "merges": "cap ital", "raw_count": 81925, "count": 81925, "decode_str": "capital"} -{"id": 31264, "token": "COMM", "merges": "COM M", "raw_count": 81954, "count": 81954, "decode_str": "COMM"} -{"id": 27730, "token": "olerance", "merges": "oler ance", "raw_count": 51478, "count": 81970, "decode_str": "olerance"} -{"id": 18890, "token": "\u0120ib", "merges": "\u0120 ib", "raw_count": 80015, "count": 81984, "decode_str": " ib"} -{"id": 3452, "token": "\u0120Bo", "merges": "\u0120B o", "raw_count": 11750, "count": 81987, "decode_str": " Bo"} -{"id": 8164, "token": "\u0120instant", "merges": "\u0120inst ant", "raw_count": 79060, "count": 81990, "decode_str": " instant"} -{"id": 18886, "token": "mine", "merges": "m ine", "raw_count": 63097, "count": 81995, "decode_str": "mine"} -{"id": 11347, "token": "istence", "merges": "ist ence", "raw_count": 45947, "count": 82017, "decode_str": "istence"} -{"id": 16629, "token": "\u0120sovereign", "merges": "\u0120so vereign", "raw_count": 31891, "count": 82024, "decode_str": " sovereign"} -{"id": 26698, "token": "Insert", "merges": "Ins ert", "raw_count": 82029, "count": 82029, "decode_str": "Insert"} -{"id": 46736, "token": "GUI", "merges": "G UI", "raw_count": 82046, "count": 82046, "decode_str": "GUI"} -{"id": 4122, "token": "\u0120highly", "merges": "\u0120high ly", "raw_count": 82089, "count": 82089, "decode_str": " highly"} -{"id": 39220, "token": "bw", "merges": "b w", "raw_count": 82095, "count": 82095, "decode_str": "bw"} -{"id": 38659, "token": "compat", "merges": "comp at", "raw_count": 82100, "count": 82100, "decode_str": "compat"} -{"id": 2470, "token": "\u0120([", "merges": "\u0120( [", "raw_count": 82074, "count": 82110, "decode_str": " (["} -{"id": 39990, "token": "descriptor", "merges": "des criptor", "raw_count": 82122, "count": 82122, "decode_str": "descriptor"} -{"id": 6110, "token": "\u0120interested", "merges": "\u0120interest ed", "raw_count": 82123, "count": 82123, "decode_str": " interested"} -{"id": 10885, "token": "\u0120handling", "merges": "\u0120hand ling", "raw_count": 82139, "count": 82139, "decode_str": " handling"} -{"id": 6777, "token": "\u0120chosen", "merges": "\u0120ch osen", "raw_count": 82149, "count": 82149, "decode_str": " chosen"} -{"id": 24527, "token": "\u0120Label", "merges": "\u0120L abel", "raw_count": 82156, "count": 82156, "decode_str": " Label"} -{"id": 4020, "token": "\u0120approxim", "merges": "\u0120appro xim", "raw_count": 3057, "count": 82157, "decode_str": " approxim"} -{"id": 5467, "token": "\u0120assume", "merges": "\u0120ass ume", "raw_count": 82180, "count": 82180, "decode_str": " assume"} -{"id": 34547, "token": "LB", "merges": "L B", "raw_count": 82191, "count": 82191, "decode_str": "LB"} -{"id": 4452, "token": "ifically", "merges": "if ically", "raw_count": 2397, "count": 82213, "decode_str": "ifically"} -{"id": 12706, "token": "ici", "merges": "ic i", "raw_count": 60874, "count": 82226, "decode_str": "ici"} -{"id": 37130, "token": "Geometry", "merges": "Ge ometry", "raw_count": 82251, "count": 82251, "decode_str": "Geometry"} -{"id": 19550, "token": "\u0120cookie", "merges": "\u0120cook ie", "raw_count": 82293, "count": 82293, "decode_str": " cookie"} -{"id": 12192, "token": "\u0120tips", "merges": "\u0120t ips", "raw_count": 82293, "count": 82293, "decode_str": " tips"} -{"id": 31266, "token": "Gall", "merges": "G all", "raw_count": 82306, "count": 82306, "decode_str": "Gall"} -{"id": 8179, "token": "ftware", "merges": "ft ware", "raw_count": 4283, "count": 82319, "decode_str": "ftware"} -{"id": 4289, "token": "\u0120hundred", "merges": "\u0120h undred", "raw_count": 46262, "count": 82336, "decode_str": " hundred"} -{"id": 28129, "token": "\u0120alias", "merges": "\u0120al ias", "raw_count": 82339, "count": 82339, "decode_str": " alias"} -{"id": 28489, "token": "maybe", "merges": "may be", "raw_count": 82340, "count": 82340, "decode_str": "maybe"} -{"id": 7998, "token": "\u0120\"(", "merges": "\u0120\" (", "raw_count": 82343, "count": 82343, "decode_str": " \"("} -{"id": 34675, "token": "ERO", "merges": "ER O", "raw_count": 82389, "count": 82389, "decode_str": "ERO"} -{"id": 3095, "token": "\u0120someone", "merges": "\u0120some one", "raw_count": 82390, "count": 82390, "decode_str": " someone"} -{"id": 575, "token": "\u00c2\u0142", "merges": "\u00c2 \u0142", "raw_count": 41697, "count": 82396, "decode_str": "\u00a0"} -{"id": 18656, "token": "Il", "merges": "I l", "raw_count": 82405, "count": 82405, "decode_str": "Il"} -{"id": 45033, "token": "starting", "merges": "start ing", "raw_count": 82412, "count": 82412, "decode_str": "starting"} -{"id": 6550, "token": "\u0120Class", "merges": "\u0120Cl ass", "raw_count": 62362, "count": 82435, "decode_str": " Class"} -{"id": 6885, "token": "\u0120protected", "merges": "\u0120prote cted", "raw_count": 82462, "count": 82462, "decode_str": " protected"} -{"id": 17806, "token": "Platform", "merges": "Pl atform", "raw_count": 82466, "count": 82466, "decode_str": "Platform"} -{"id": 22875, "token": "riber", "merges": "ri ber", "raw_count": 5493, "count": 82478, "decode_str": "riber"} -{"id": 40207, "token": "EXP", "merges": "EX P", "raw_count": 82509, "count": 82509, "decode_str": "EXP"} -{"id": 25765, "token": "central", "merges": "cent ral", "raw_count": 82525, "count": 82525, "decode_str": "central"} -{"id": 33069, "token": "OWS", "merges": "OW S", "raw_count": 82539, "count": 82539, "decode_str": "OWS"} -{"id": 40056, "token": "SERVER", "merges": "SERV ER", "raw_count": 82559, "count": 82559, "decode_str": "SERVER"} -{"id": 16759, "token": "ERY", "merges": "ER Y", "raw_count": 79506, "count": 82562, "decode_str": "ERY"} -{"id": 49510, "token": "726", "merges": "7 26", "raw_count": 82564, "count": 82564, "decode_str": "726"} -{"id": 4599, "token": "iforn", "merges": "if orn", "raw_count": 3359, "count": 82595, "decode_str": "iforn"} -{"id": 31406, "token": "pain", "merges": "p ain", "raw_count": 82609, "count": 82609, "decode_str": "pain"} -{"id": 23256, "token": "\u0120pg", "merges": "\u0120p g", "raw_count": 82630, "count": 82630, "decode_str": " pg"} -{"id": 20476, "token": "launch", "merges": "la unch", "raw_count": 76946, "count": 82645, "decode_str": "launch"} -{"id": 16933, "token": "\u0120corruption", "merges": "\u0120cor ruption", "raw_count": 82658, "count": 82658, "decode_str": " corruption"} -{"id": 12715, "token": "LY", "merges": "L Y", "raw_count": 45199, "count": 82658, "decode_str": "LY"} -{"id": 6607, "token": "\u0120represented", "merges": "\u0120represent ed", "raw_count": 82667, "count": 82667, "decode_str": " represented"} -{"id": 31102, "token": "WHERE", "merges": "WH ERE", "raw_count": 82672, "count": 82672, "decode_str": "WHERE"} -{"id": 5561, "token": "\u0120rock", "merges": "\u0120ro ck", "raw_count": 53078, "count": 82678, "decode_str": " rock"} -{"id": 12779, "token": "semble", "merges": "sem ble", "raw_count": 46661, "count": 82704, "decode_str": "semble"} -{"id": 8665, "token": "Other", "merges": "O ther", "raw_count": 54978, "count": 82716, "decode_str": "Other"} -{"id": 35462, "token": "Pt", "merges": "P t", "raw_count": 82744, "count": 82744, "decode_str": "Pt"} -{"id": 5289, "token": "\u0120structures", "merges": "\u0120struct ures", "raw_count": 82751, "count": 82751, "decode_str": " structures"} -{"id": 38584, "token": "bill", "merges": "b ill", "raw_count": 82758, "count": 82758, "decode_str": "bill"} -{"id": 6641, "token": "\u0120veloc", "merges": "\u0120vel oc", "raw_count": 3334, "count": 82786, "decode_str": " veloc"} -{"id": 26001, "token": "hops", "merges": "h ops", "raw_count": 16220, "count": 82812, "decode_str": "hops"} -{"id": 36705, "token": "Bell", "merges": "B ell", "raw_count": 82845, "count": 82845, "decode_str": "Bell"} -{"id": 12908, "token": "alities", "merges": "al ities", "raw_count": 18807, "count": 82869, "decode_str": "alities"} -{"id": 6698, "token": "\u0120journal", "merges": "\u0120j ournal", "raw_count": 40686, "count": 82886, "decode_str": " journal"} -{"id": 4546, "token": "\u0120played", "merges": "\u0120play ed", "raw_count": 82888, "count": 82888, "decode_str": " played"} -{"id": 4013, "token": "Oh", "merges": "O h", "raw_count": 77331, "count": 82897, "decode_str": "Oh"} -{"id": 11130, "token": "\u012084", "merges": "\u01208 4", "raw_count": 82923, "count": 82923, "decode_str": " 84"} -{"id": 12287, "token": "arer", "merges": "are r", "raw_count": 71790, "count": 82928, "decode_str": "arer"} -{"id": 42556, "token": "Room", "merges": "R oom", "raw_count": 82928, "count": 82928, "decode_str": "Room"} -{"id": 38997, "token": "Queen", "merges": "Que en", "raw_count": 82937, "count": 82937, "decode_str": "Queen"} -{"id": 30932, "token": "('#", "merges": "(' #", "raw_count": 82937, "count": 82937, "decode_str": "('#"} -{"id": 52808, "token": "\u00e7\u0130\u0142", "merges": "\u00e7\u0130 \u0142", "raw_count": 82944, "count": 82944, "decode_str": "\u73a0"} -{"id": 19606, "token": "tion", "merges": "t ion", "raw_count": 30528, "count": 82951, "decode_str": "tion"} -{"id": 34124, "token": "\u0120Json", "merges": "\u0120J son", "raw_count": 82957, "count": 82957, "decode_str": " Json"} -{"id": 34972, "token": "Brad", "merges": "B rad", "raw_count": 82958, "count": 82958, "decode_str": "Brad"} -{"id": 43635, "token": "BAD", "merges": "B AD", "raw_count": 82963, "count": 82963, "decode_str": "BAD"} -{"id": 25049, "token": "matched", "merges": "mat ched", "raw_count": 82973, "count": 82973, "decode_str": "matched"} -{"id": 34718, "token": "\u0120Beautiful", "merges": "\u0120Beaut iful", "raw_count": 82979, "count": 82979, "decode_str": " Beautiful"} -{"id": 8097, "token": "\u0120ven", "merges": "\u0120v en", "raw_count": 36962, "count": 82981, "decode_str": " ven"} -{"id": 33312, "token": "beam", "merges": "be am", "raw_count": 82981, "count": 82981, "decode_str": "beam"} -{"id": 3917, "token": "\u00e3\u0123\u00ae", "merges": "\u00e3\u0123 \u00ae", "raw_count": 75887, "count": 82983, "decode_str": "\u306e"} -{"id": 11155, "token": "eman", "merges": "em an", "raw_count": 77750, "count": 83021, "decode_str": "eman"} -{"id": 15701, "token": "zt", "merges": "z t", "raw_count": 83027, "count": 83027, "decode_str": "zt"} -{"id": 14958, "token": "did", "merges": "d id", "raw_count": 76547, "count": 83029, "decode_str": "did"} -{"id": 7985, "token": "\u0120visible", "merges": "\u0120vis ible", "raw_count": 83031, "count": 83031, "decode_str": " visible"} -{"id": 23731, "token": "jp", "merges": "j p", "raw_count": 83043, "count": 83043, "decode_str": "jp"} -{"id": 25580, "token": "Transaction", "merges": "Trans action", "raw_count": 83048, "count": 83048, "decode_str": "Transaction"} -{"id": 6564, "token": "\u0120\u00d0\u00b4", "merges": "\u0120\u00d0 \u00b4", "raw_count": 56257, "count": 83054, "decode_str": " \u0434"} -{"id": 6083, "token": "\u0120agents", "merges": "\u0120ag ents", "raw_count": 83055, "count": 83055, "decode_str": " agents"} -{"id": 17369, "token": "kan", "merges": "k an", "raw_count": 83113, "count": 83113, "decode_str": "kan"} -{"id": 21997, "token": "license", "merges": "lic ense", "raw_count": 83124, "count": 83124, "decode_str": "license"} -{"id": 4510, "token": "\u0120prefer", "merges": "\u0120pre fer", "raw_count": 30633, "count": 83137, "decode_str": " prefer"} -{"id": 26927, "token": "obar", "merges": "ob ar", "raw_count": 83142, "count": 83142, "decode_str": "obar"} -{"id": 22927, "token": "\u0120*,", "merges": "\u0120* ,", "raw_count": 83146, "count": 83146, "decode_str": " *,"} -{"id": 4307, "token": "\u0120worked", "merges": "\u0120work ed", "raw_count": 83159, "count": 83159, "decode_str": " worked"} -{"id": 21686, "token": "NAL", "merges": "NA L", "raw_count": 83160, "count": 83160, "decode_str": "NAL"} -{"id": 27116, "token": "ei", "merges": "e i", "raw_count": 83172, "count": 83172, "decode_str": "ei"} -{"id": 6179, "token": "\u0120waiting", "merges": "\u0120wait ing", "raw_count": 83176, "count": 83176, "decode_str": " waiting"} -{"id": 17624, "token": "Short", "merges": "Sh ort", "raw_count": 83185, "count": 83185, "decode_str": "Short"} -{"id": 7155, "token": "\u0120percentage", "merges": "\u0120percent age", "raw_count": 83188, "count": 83188, "decode_str": " percentage"} -{"id": 4549, "token": "\u0120appeal", "merges": "\u0120appe al", "raw_count": 83189, "count": 83189, "decode_str": " appeal"} -{"id": 9235, "token": "\u0120HT", "merges": "\u0120H T", "raw_count": 9451, "count": 83191, "decode_str": " HT"} -{"id": 39089, "token": "KC", "merges": "K C", "raw_count": 83193, "count": 83193, "decode_str": "KC"} -{"id": 42070, "token": "classification", "merges": "class ification", "raw_count": 83195, "count": 83195, "decode_str": "classification"} -{"id": 36793, "token": "891", "merges": "89 1", "raw_count": 83196, "count": 83196, "decode_str": "891"} -{"id": 19214, "token": "NL", "merges": "N L", "raw_count": 83201, "count": 83201, "decode_str": "NL"} -{"id": 28794, "token": "Pack", "merges": "P ack", "raw_count": 83233, "count": 83233, "decode_str": "Pack"} -{"id": 11390, "token": "\u0120vectors", "merges": "\u0120ve ctors", "raw_count": 83234, "count": 83234, "decode_str": " vectors"} -{"id": 6709, "token": "istor", "merges": "ist or", "raw_count": 15923, "count": 83248, "decode_str": "istor"} -{"id": 6529, "token": "aine", "merges": "ain e", "raw_count": 77060, "count": 83260, "decode_str": "aine"} -{"id": 37910, "token": "Asset", "merges": "Ass et", "raw_count": 83294, "count": 83294, "decode_str": "Asset"} -{"id": 8390, "token": "eper", "merges": "e per", "raw_count": 35713, "count": 83297, "decode_str": "eper"} -{"id": 18815, "token": "ortex", "merges": "ort ex", "raw_count": 80702, "count": 83308, "decode_str": "ortex"} -{"id": 19369, "token": "aha", "merges": "ah a", "raw_count": 83309, "count": 83309, "decode_str": "aha"} -{"id": 4784, "token": "\u0120mit", "merges": "\u0120m it", "raw_count": 25351, "count": 83326, "decode_str": " mit"} -{"id": 44689, "token": "credit", "merges": "c redit", "raw_count": 83327, "count": 83327, "decode_str": "credit"} -{"id": 26313, "token": "0012", "merges": "00 12", "raw_count": 83332, "count": 83332, "decode_str": "0012"} -{"id": 9306, "token": "ned", "merges": "n ed", "raw_count": 53303, "count": 83339, "decode_str": "ned"} -{"id": 26679, "token": "LINK", "merges": "L INK", "raw_count": 83343, "count": 83343, "decode_str": "LINK"} -{"id": 3417, "token": "\u0120species", "merges": "\u0120spec ies", "raw_count": 83347, "count": 83347, "decode_str": " species"} -{"id": 27415, "token": "Ts", "merges": "T s", "raw_count": 83353, "count": 83353, "decode_str": "Ts"} -{"id": 9634, "token": "uting", "merges": "ut ing", "raw_count": 43446, "count": 83389, "decode_str": "uting"} -{"id": 34437, "token": "Han", "merges": "H an", "raw_count": 83440, "count": 83440, "decode_str": "Han"} -{"id": 23655, "token": "gmail", "merges": "g mail", "raw_count": 83459, "count": 83459, "decode_str": "gmail"} -{"id": 43718, "token": "ATS", "merges": "AT S", "raw_count": 83489, "count": 83489, "decode_str": "ATS"} -{"id": 7672, "token": ")*(", "merges": ")* (", "raw_count": 83491, "count": 83491, "decode_str": ")*("} -{"id": 12133, "token": "bes", "merges": "b es", "raw_count": 81798, "count": 83494, "decode_str": "bes"} -{"id": 41665, "token": "\u0120vars", "merges": "\u0120var s", "raw_count": 83499, "count": 83499, "decode_str": " vars"} -{"id": 6687, "token": "\u0120diag", "merges": "\u0120di ag", "raw_count": 23045, "count": 83522, "decode_str": " diag"} -{"id": 15462, "token": "Sort", "merges": "S ort", "raw_count": 83538, "count": 83538, "decode_str": "Sort"} -{"id": 18568, "token": "rystal", "merges": "ryst al", "raw_count": 80092, "count": 83542, "decode_str": "rystal"} -{"id": 29180, "token": "\u0120cs", "merges": "\u0120c s", "raw_count": 83545, "count": 83545, "decode_str": " cs"} -{"id": 40919, "token": "RW", "merges": "R W", "raw_count": 83568, "count": 83568, "decode_str": "RW"} -{"id": 19379, "token": "\u0120bilateral", "merges": "\u0120bil ateral", "raw_count": 83575, "count": 83575, "decode_str": " bilateral"} -{"id": 5434, "token": "\u0120danger", "merges": "\u0120d anger", "raw_count": 37740, "count": 83578, "decode_str": " danger"} -{"id": 14881, "token": "ocom", "merges": "oc om", "raw_count": 62018, "count": 83592, "decode_str": "ocom"} -{"id": 4373, "token": "\u0120hyper", "merges": "\u0120hy per", "raw_count": 74554, "count": 83596, "decode_str": " hyper"} -{"id": 13122, "token": "\u0120transactions", "merges": "\u0120trans actions", "raw_count": 83600, "count": 83600, "decode_str": " transactions"} -{"id": 8832, "token": "ffff", "merges": "ff ff", "raw_count": 22376, "count": 83601, "decode_str": "ffff"} -{"id": 27074, "token": "cj", "merges": "c j", "raw_count": 83637, "count": 83643, "decode_str": "cj"} -{"id": 9806, "token": "\u0120intel", "merges": "\u0120int el", "raw_count": 16098, "count": 83650, "decode_str": " intel"} -{"id": 5270, "token": "\u0120Table", "merges": "\u0120T able", "raw_count": 83653, "count": 83653, "decode_str": " Table"} -{"id": 5833, "token": "\u0120complaint", "merges": "\u0120compl aint", "raw_count": 33832, "count": 83655, "decode_str": " complaint"} -{"id": 27595, "token": "Jones", "merges": "J ones", "raw_count": 83678, "count": 83678, "decode_str": "Jones"} -{"id": 4933, "token": "\u0120giving", "merges": "\u0120giv ing", "raw_count": 83683, "count": 83683, "decode_str": " giving"} -{"id": 39464, "token": "games", "merges": "g ames", "raw_count": 83718, "count": 83718, "decode_str": "games"} -{"id": 3538, "token": "\u0120deriv", "merges": "\u0120der iv", "raw_count": 12025, "count": 83723, "decode_str": " deriv"} -{"id": 8353, "token": "\u0120consumption", "merges": "\u0120consum ption", "raw_count": 83728, "count": 83728, "decode_str": " consumption"} -{"id": 36092, "token": "Cra", "merges": "C ra", "raw_count": 83728, "count": 83728, "decode_str": "Cra"} -{"id": 6871, "token": "\u0120iron", "merges": "\u0120 iron", "raw_count": 78618, "count": 83732, "decode_str": " iron"} -{"id": 12240, "token": "\u0120completion", "merges": "\u0120complet ion", "raw_count": 83739, "count": 83739, "decode_str": " completion"} -{"id": 46014, "token": "864", "merges": "8 64", "raw_count": 83746, "count": 83746, "decode_str": "864"} -{"id": 21047, "token": "\u0120agriculture", "merges": "\u0120agric ulture", "raw_count": 83750, "count": 83750, "decode_str": " agriculture"} -{"id": 5181, "token": "\u0120touch", "merges": "\u0120tou ch", "raw_count": 73926, "count": 83760, "decode_str": " touch"} -{"id": 13519, "token": "\u0120courses", "merges": "\u0120cour ses", "raw_count": 83775, "count": 83775, "decode_str": " courses"} -{"id": 29679, "token": "\u0120snapshot", "merges": "\u0120snap shot", "raw_count": 83799, "count": 83799, "decode_str": " snapshot"} -{"id": 44751, "token": "Risk", "merges": "R isk", "raw_count": 83805, "count": 83805, "decode_str": "Risk"} -{"id": 11369, "token": "\u0120engineering", "merges": "\u0120engine ering", "raw_count": 83807, "count": 83807, "decode_str": " engineering"} -{"id": 7145, "token": "\u0120corner", "merges": "\u0120cor ner", "raw_count": 83817, "count": 83817, "decode_str": " corner"} -{"id": 34542, "token": "south", "merges": "s outh", "raw_count": 83830, "count": 83830, "decode_str": "south"} -{"id": 5878, "token": "\u0120mix", "merges": "\u0120m ix", "raw_count": 56040, "count": 83830, "decode_str": " mix"} -{"id": 11859, "token": "\u0120concrete", "merges": "\u0120con crete", "raw_count": 83852, "count": 83852, "decode_str": " concrete"} -{"id": 44756, "token": "Swift", "merges": "Sw ift", "raw_count": 83914, "count": 83914, "decode_str": "Swift"} -{"id": 38404, "token": "Ball", "merges": "B all", "raw_count": 83936, "count": 83936, "decode_str": "Ball"} -{"id": 8086, "token": "\u0120arbitr", "merges": "\u0120arbit r", "raw_count": 8582, "count": 83938, "decode_str": " arbitr"} -{"id": 49975, "token": "\u0120sr", "merges": "\u0120s r", "raw_count": 83943, "count": 83943, "decode_str": " sr"} -{"id": 17170, "token": "\u0120achieving", "merges": "\u0120achie ving", "raw_count": 83968, "count": 83968, "decode_str": " achieving"} -{"id": 9265, "token": "ircraft", "merges": "irc raft", "raw_count": 6851, "count": 83976, "decode_str": "ircraft"} -{"id": 49660, "token": "817", "merges": "8 17", "raw_count": 83981, "count": 83981, "decode_str": "817"} -{"id": 15042, "token": "\u0120restore", "merges": "\u0120rest ore", "raw_count": 83991, "count": 83991, "decode_str": " restore"} -{"id": 46297, "token": "ISBN", "merges": "IS BN", "raw_count": 84036, "count": 84036, "decode_str": "ISBN"} -{"id": 39735, "token": "already", "merges": "al ready", "raw_count": 84061, "count": 84061, "decode_str": "already"} -{"id": 37482, "token": "AUTH", "merges": "A UTH", "raw_count": 84089, "count": 84089, "decode_str": "AUTH"} -{"id": 41634, "token": "riterion", "merges": "riter ion", "raw_count": 84094, "count": 84094, "decode_str": "riterion"} -{"id": 17119, "token": "\u0120backup", "merges": "\u0120back up", "raw_count": 84098, "count": 84098, "decode_str": " backup"} -{"id": 32136, "token": "Signal", "merges": "Sign al", "raw_count": 84115, "count": 84115, "decode_str": "Signal"} -{"id": 44953, "token": "781", "merges": "78 1", "raw_count": 84151, "count": 84151, "decode_str": "781"} -{"id": 17265, "token": "\u0120revised", "merges": "\u0120rev ised", "raw_count": 84155, "count": 84155, "decode_str": " revised"} -{"id": 14785, "token": "mind", "merges": "m ind", "raw_count": 75338, "count": 84162, "decode_str": "mind"} -{"id": 16714, "token": "develop", "merges": "de velop", "raw_count": 42085, "count": 84181, "decode_str": "develop"} -{"id": 7464, "token": "\u0120Windows", "merges": "\u0120W indows", "raw_count": 84183, "count": 84183, "decode_str": " Windows"} -{"id": 45818, "token": "(#", "merges": "( #", "raw_count": 84184, "count": 84184, "decode_str": "(#"} -{"id": 4360, "token": "ibly", "merges": "ib ly", "raw_count": 15678, "count": 84185, "decode_str": "ibly"} -{"id": 46022, "token": "Steven", "merges": "Ste ven", "raw_count": 84186, "count": 84186, "decode_str": "Steven"} -{"id": 30217, "token": "rw", "merges": "r w", "raw_count": 84190, "count": 84190, "decode_str": "rw"} -{"id": 6385, "token": "\u0120mir", "merges": "\u0120m ir", "raw_count": 24060, "count": 84191, "decode_str": " mir"} -{"id": 21127, "token": "harm", "merges": "h arm", "raw_count": 72671, "count": 84196, "decode_str": "harm"} -{"id": 27091, "token": "\u01201500", "merges": "\u012015 00", "raw_count": 84197, "count": 84197, "decode_str": " 1500"} -{"id": 49082, "token": "785", "merges": "7 85", "raw_count": 84208, "count": 84208, "decode_str": "785"} -{"id": 51752, "token": "\u00e6\u0124\u00b1", "merges": "\u00e6\u0124 \u00b1", "raw_count": 84225, "count": 84225, "decode_str": "\u60b1"} -{"id": 16024, "token": "\u0120tear", "merges": "\u0120t ear", "raw_count": 84230, "count": 84230, "decode_str": " tear"} -{"id": 23079, "token": "chrome", "merges": "ch rome", "raw_count": 83473, "count": 84231, "decode_str": "chrome"} -{"id": 46510, "token": "ctype", "merges": "ct ype", "raw_count": 84290, "count": 84290, "decode_str": "ctype"} -{"id": 17124, "token": "great", "merges": "g reat", "raw_count": 41567, "count": 84295, "decode_str": "great"} -{"id": 7106, "token": "\u0120focused", "merges": "\u0120focus ed", "raw_count": 84319, "count": 84319, "decode_str": " focused"} -{"id": 49554, "token": "\u00e5\u0137\u0131", "merges": "\u00e5\u0137 \u0131", "raw_count": 84351, "count": 84351, "decode_str": "\u554f"} -{"id": 37979, "token": "Taylor", "merges": "T aylor", "raw_count": 84362, "count": 84362, "decode_str": "Taylor"} -{"id": 12248, "token": "\u0120TE", "merges": "\u0120T E", "raw_count": 17272, "count": 84371, "decode_str": " TE"} -{"id": 17610, "token": "\u0120voluntary", "merges": "\u0120volunt ary", "raw_count": 84379, "count": 84379, "decode_str": " voluntary"} -{"id": 9508, "token": "\u0120versions", "merges": "\u0120vers ions", "raw_count": 84387, "count": 84387, "decode_str": " versions"} -{"id": 15627, "token": "too", "merges": "to o", "raw_count": 81546, "count": 84389, "decode_str": "too"} -{"id": 25935, "token": "Weight", "merges": "We ight", "raw_count": 84410, "count": 84410, "decode_str": "Weight"} -{"id": 7031, "token": "\u0120coverage", "merges": "\u0120co verage", "raw_count": 84433, "count": 84433, "decode_str": " coverage"} -{"id": 15316, "token": "\u0120periodic", "merges": "\u0120period ic", "raw_count": 84454, "count": 84454, "decode_str": " periodic"} -{"id": 41734, "token": "JM", "merges": "J M", "raw_count": 84456, "count": 84456, "decode_str": "JM"} -{"id": 6980, "token": "\u0120princip", "merges": "\u0120princ ip", "raw_count": 9838, "count": 84457, "decode_str": " princip"} -{"id": 14761, "token": "\u0120subsid", "merges": "\u0120subs id", "raw_count": 15732, "count": 84458, "decode_str": " subsid"} -{"id": 40342, "token": "\u0120alia", "merges": "\u0120al ia", "raw_count": 84464, "count": 84464, "decode_str": " alia"} -{"id": 464, "token": "{\\", "merges": "{ \\", "raw_count": 42296, "count": 84465, "decode_str": "{\\"} -{"id": 18265, "token": "must", "merges": "m ust", "raw_count": 84480, "count": 84480, "decode_str": "must"} -{"id": 12652, "token": "\u0120109", "merges": "\u012010 9", "raw_count": 84480, "count": 84480, "decode_str": " 109"} -{"id": 6371, "token": "\u0120wire", "merges": "\u0120w ire", "raw_count": 43809, "count": 84489, "decode_str": " wire"} -{"id": 6593, "token": "\u0120forth", "merges": "\u0120for th", "raw_count": 65538, "count": 84490, "decode_str": " forth"} -{"id": 15688, "token": "\u0120robot", "merges": "\u0120rob ot", "raw_count": 84530, "count": 84530, "decode_str": " robot"} -{"id": 8227, "token": "\u0120suc", "merges": "\u0120su c", "raw_count": 3957, "count": 84545, "decode_str": " suc"} -{"id": 31425, "token": "Mu", "merges": "M u", "raw_count": 84562, "count": 84562, "decode_str": "Mu"} -{"id": 4912, "token": "\u0120medic", "merges": "\u0120med ic", "raw_count": 5006, "count": 84564, "decode_str": " medic"} -{"id": 29943, "token": "inel", "merges": "in el", "raw_count": 84570, "count": 84570, "decode_str": "inel"} -{"id": 5642, "token": "\u0120CH", "merges": "\u0120C H", "raw_count": 67567, "count": 84603, "decode_str": " CH"} -{"id": 4844, "token": "atever", "merges": "ate ver", "raw_count": 301, "count": 84610, "decode_str": "atever"} -{"id": 18520, "token": "\u0120revision", "merges": "\u0120rev ision", "raw_count": 84620, "count": 84620, "decode_str": " revision"} -{"id": 35455, "token": "Hall", "merges": "H all", "raw_count": 84627, "count": 84627, "decode_str": "Hall"} -{"id": 18625, "token": "guard", "merges": "gu ard", "raw_count": 63183, "count": 84629, "decode_str": "guard"} -{"id": 24344, "token": "\u01201949", "merges": "\u012019 49", "raw_count": 84637, "count": 84637, "decode_str": " 1949"} -{"id": 25600, "token": "Comm", "merges": "Com m", "raw_count": 84642, "count": 84642, "decode_str": "Comm"} -{"id": 14493, "token": "\u0120bounds", "merges": "\u0120b ounds", "raw_count": 84651, "count": 84651, "decode_str": " bounds"} -{"id": 11947, "token": "\u0120trading", "merges": "\u0120trad ing", "raw_count": 84674, "count": 84674, "decode_str": " trading"} -{"id": 11822, "token": "alling", "merges": "all ing", "raw_count": 82846, "count": 84690, "decode_str": "alling"} -{"id": 23643, "token": "0011", "merges": "00 11", "raw_count": 84695, "count": 84695, "decode_str": "0011"} -{"id": 45621, "token": "Tan", "merges": "T an", "raw_count": 84704, "count": 84704, "decode_str": "Tan"} -{"id": 5049, "token": "\u0120circuit", "merges": "\u0120circ uit", "raw_count": 83665, "count": 84706, "decode_str": " circuit"} -{"id": 4228, "token": "\u0120static", "merges": "\u0120stat ic", "raw_count": 84760, "count": 84760, "decode_str": " static"} -{"id": 38322, "token": "\u0120ops", "merges": "\u0120o ps", "raw_count": 84786, "count": 84786, "decode_str": " ops"} -{"id": 42542, "token": "\u0120\":", "merges": "\u0120\" :", "raw_count": 84792, "count": 84792, "decode_str": " \":"} -{"id": 40317, "token": "wordpress", "merges": "word press", "raw_count": 84798, "count": 84798, "decode_str": "wordpress"} -{"id": 3240, "token": "\u0120quite", "merges": "\u0120qu ite", "raw_count": 84802, "count": 84802, "decode_str": " quite"} -{"id": 11924, "token": "anti", "merges": "ant i", "raw_count": 69334, "count": 84809, "decode_str": "anti"} -{"id": 44037, "token": "782", "merges": "78 2", "raw_count": 84815, "count": 84815, "decode_str": "782"} -{"id": 41933, "token": "nod", "merges": "n od", "raw_count": 84817, "count": 84817, "decode_str": "nod"} -{"id": 29046, "token": "Symbol", "merges": "S ymbol", "raw_count": 84828, "count": 84828, "decode_str": "Symbol"} -{"id": 10750, "token": "ported", "merges": "port ed", "raw_count": 31331, "count": 84848, "decode_str": "ported"} -{"id": 6613, "token": "\u0120runs", "merges": "\u0120run s", "raw_count": 84848, "count": 84848, "decode_str": " runs"} -{"id": 7787, "token": "\u0120limits", "merges": "\u0120lim its", "raw_count": 84849, "count": 84849, "decode_str": " limits"} -{"id": 7060, "token": "\u0120smart", "merges": "\u0120sm art", "raw_count": 73171, "count": 84856, "decode_str": " smart"} -{"id": 20144, "token": "ADDR", "merges": "AD DR", "raw_count": 46558, "count": 84860, "decode_str": "ADDR"} -{"id": 5907, "token": "\u0120offered", "merges": "\u0120of fered", "raw_count": 84867, "count": 84867, "decode_str": " offered"} -{"id": 5533, "token": "\u0120bond", "merges": "\u0120b ond", "raw_count": 49951, "count": 84875, "decode_str": " bond"} -{"id": 3619, "token": "\u0120Ed", "merges": "\u0120E d", "raw_count": 26109, "count": 84918, "decode_str": " Ed"} -{"id": 10806, "token": "\u0120constraints", "merges": "\u0120constraint s", "raw_count": 84924, "count": 84924, "decode_str": " constraints"} -{"id": 7861, "token": "\u0120pil", "merges": "\u0120p il", "raw_count": 22376, "count": 84935, "decode_str": " pil"} -{"id": 10675, "token": "\u0120broadcast", "merges": "\u0120broad cast", "raw_count": 57093, "count": 84942, "decode_str": " broadcast"} -{"id": 30187, "token": "Sy", "merges": "S y", "raw_count": 84943, "count": 84943, "decode_str": "Sy"} -{"id": 5224, "token": "\u0120indicate", "merges": "\u0120indic ate", "raw_count": 84983, "count": 84983, "decode_str": " indicate"} -{"id": 39621, "token": "952", "merges": "95 2", "raw_count": 85016, "count": 85016, "decode_str": "952"} -{"id": 3815, "token": "\u0120alone", "merges": "\u0120al one", "raw_count": 85042, "count": 85042, "decode_str": " alone"} -{"id": 2540, "token": "\u0120observed", "merges": "\u0120observ ed", "raw_count": 85057, "count": 85057, "decode_str": " observed"} -{"id": 12446, "token": "\u0120105", "merges": "\u012010 5", "raw_count": 85062, "count": 85062, "decode_str": " 105"} -{"id": 15047, "token": "\u0120upgrade", "merges": "\u0120up grade", "raw_count": 85090, "count": 85090, "decode_str": " upgrade"} -{"id": 37266, "token": "\u0120dic", "merges": "\u0120d ic", "raw_count": 85098, "count": 85098, "decode_str": " dic"} -{"id": 12279, "token": "\u0120satell", "merges": "\u0120sat ell", "raw_count": 213, "count": 85114, "decode_str": " satell"} -{"id": 29439, "token": "\u0120fd", "merges": "\u0120f d", "raw_count": 85114, "count": 85114, "decode_str": " fd"} -{"id": 39164, "token": "Philip", "merges": "Phil ip", "raw_count": 85130, "count": 85130, "decode_str": "Philip"} -{"id": 22256, "token": "(@", "merges": "( @", "raw_count": 85132, "count": 85132, "decode_str": "(@"} -{"id": 41736, "token": "Alexander", "merges": "Alex ander", "raw_count": 85153, "count": 85153, "decode_str": "Alexander"} -{"id": 40084, "token": "inside", "merges": "ins ide", "raw_count": 85159, "count": 85159, "decode_str": "inside"} -{"id": 44059, "token": "CRT", "merges": "CR T", "raw_count": 85179, "count": 85179, "decode_str": "CRT"} -{"id": 32607, "token": "weather", "merges": "we ather", "raw_count": 85188, "count": 85188, "decode_str": "weather"} -{"id": 52376, "token": "\u00e6\u00a9\u0132", "merges": "\u00e6\u00a9 \u0132", "raw_count": 85192, "count": 85192, "decode_str": "\u6a50"} -{"id": 19117, "token": "Byte", "merges": "By te", "raw_count": 85208, "count": 85208, "decode_str": "Byte"} -{"id": 12153, "token": "\u0120foundation", "merges": "\u0120found ation", "raw_count": 85241, "count": 85241, "decode_str": " foundation"} -{"id": 8583, "token": "kes", "merges": "k es", "raw_count": 64924, "count": 85246, "decode_str": "kes"} -{"id": 38432, "token": "Ada", "merges": "A da", "raw_count": 85258, "count": 85258, "decode_str": "Ada"} -{"id": 12424, "token": "abe", "merges": "ab e", "raw_count": 85277, "count": 85277, "decode_str": "abe"} -{"id": 12684, "token": "\u0120fi", "merges": "\u0120f i", "raw_count": 28840, "count": 85278, "decode_str": " fi"} -{"id": 7708, "token": "iverse", "merges": "iver se", "raw_count": 47603, "count": 85282, "decode_str": "iverse"} -{"id": 15974, "token": "\u0120addressing", "merges": "\u0120address ing", "raw_count": 85288, "count": 85288, "decode_str": " addressing"} -{"id": 15168, "token": "Es", "merges": "E s", "raw_count": 85291, "count": 85291, "decode_str": "Es"} -{"id": 24458, "token": "STRING", "merges": "STR ING", "raw_count": 85296, "count": 85296, "decode_str": "STRING"} -{"id": 12745, "token": "etary", "merges": "et ary", "raw_count": 21285, "count": 85309, "decode_str": "etary"} -{"id": 1292, "token": "\u0120But", "merges": "\u0120B ut", "raw_count": 24982, "count": 85318, "decode_str": " But"} -{"id": 53289, "token": "\u00e7\u00b3\u00ac", "merges": "\u00e7\u00b3 \u00ac", "raw_count": 85355, "count": 85355, "decode_str": "\u7cec"} -{"id": 46076, "token": "783", "merges": "78 3", "raw_count": 85382, "count": 85382, "decode_str": "783"} -{"id": 5379, "token": "stitution", "merges": "stit ution", "raw_count": 47792, "count": 85425, "decode_str": "stitution"} -{"id": 7314, "token": "\u0120advert", "merges": "\u0120ad vert", "raw_count": 6538, "count": 85428, "decode_str": " advert"} -{"id": 6392, "token": "\u0120CO", "merges": "\u0120C O", "raw_count": 40170, "count": 85428, "decode_str": " CO"} -{"id": 37718, "token": "numeric", "merges": "num eric", "raw_count": 85451, "count": 85451, "decode_str": "numeric"} -{"id": 26330, "token": "Region", "merges": "Reg ion", "raw_count": 85507, "count": 85507, "decode_str": "Region"} -{"id": 38333, "token": "OUTPUT", "merges": "OUT PUT", "raw_count": 85511, "count": 85511, "decode_str": "OUTPUT"} -{"id": 31174, "token": "Williams", "merges": "Willi ams", "raw_count": 85548, "count": 85548, "decode_str": "Williams"} -{"id": 53084, "token": "\u00e7\u00a2\u0129", "merges": "\u00e7\u00a2 \u0129", "raw_count": 85554, "count": 85554, "decode_str": "\u7887"} -{"id": 10423, "token": "limits", "merges": "lim its", "raw_count": 85555, "count": 85555, "decode_str": "limits"} -{"id": 16034, "token": "vereign", "merges": "vere ign", "raw_count": 3540, "count": 85564, "decode_str": "vereign"} -{"id": 30362, "token": "magn", "merges": "m agn", "raw_count": 85564, "count": 85564, "decode_str": "magn"} -{"id": 6719, "token": "eles", "merges": "el es", "raw_count": 55786, "count": 85584, "decode_str": "eles"} -{"id": 5678, "token": "\u0120combined", "merges": "\u0120comb ined", "raw_count": 85589, "count": 85589, "decode_str": " combined"} -{"id": 12470, "token": "\u0120invited", "merges": "\u0120inv ited", "raw_count": 85596, "count": 85596, "decode_str": " invited"} -{"id": 14631, "token": "\u0120establishing", "merges": "\u0120establ ishing", "raw_count": 85602, "count": 85602, "decode_str": " establishing"} -{"id": 36492, "token": "jiang", "merges": "ji ang", "raw_count": 85623, "count": 85623, "decode_str": "jiang"} -{"id": 9704, "token": "\u0120Oper", "merges": "\u0120O per", "raw_count": 16615, "count": 85635, "decode_str": " Oper"} -{"id": 10858, "token": "\u0120settlement", "merges": "\u0120sett lement", "raw_count": 85637, "count": 85637, "decode_str": " settlement"} -{"id": 33612, "token": "Greg", "merges": "G reg", "raw_count": 85675, "count": 85675, "decode_str": "Greg"} -{"id": 29878, "token": "gres", "merges": "g res", "raw_count": 85679, "count": 85679, "decode_str": "gres"} -{"id": 6389, "token": "\u0120farm", "merges": "\u0120f arm", "raw_count": 35356, "count": 85696, "decode_str": " farm"} -{"id": 21081, "token": "\u0120fmt", "merges": "\u0120f mt", "raw_count": 85699, "count": 85699, "decode_str": " fmt"} -{"id": 30704, "token": "REAM", "merges": "RE AM", "raw_count": 26804, "count": 85703, "decode_str": "REAM"} -{"id": 11178, "token": "irms", "merges": "ir ms", "raw_count": 39707, "count": 85756, "decode_str": "irms"} -{"id": 31588, "token": "Scan", "merges": "Sc an", "raw_count": 85793, "count": 85793, "decode_str": "Scan"} -{"id": 34102, "token": "Runner", "merges": "Run ner", "raw_count": 85797, "count": 85797, "decode_str": "Runner"} -{"id": 48876, "token": "ZO", "merges": "Z O", "raw_count": 85819, "count": 85819, "decode_str": "ZO"} -{"id": 14637, "token": "\u0120constants", "merges": "\u0120const ants", "raw_count": 85824, "count": 85824, "decode_str": " constants"} -{"id": 35331, "token": "lf", "merges": "l f", "raw_count": 85832, "count": 85832, "decode_str": "lf"} -{"id": 7627, "token": "\u0120horiz", "merges": "\u0120hor iz", "raw_count": 7093, "count": 85833, "decode_str": " horiz"} -{"id": 32893, "token": "Bra", "merges": "B ra", "raw_count": 85861, "count": 85861, "decode_str": "Bra"} -{"id": 21206, "token": "omi", "merges": "om i", "raw_count": 85878, "count": 85878, "decode_str": "omi"} -{"id": 28058, "token": "Gene", "merges": "G ene", "raw_count": 85892, "count": 85892, "decode_str": "Gene"} -{"id": 27984, "token": "DOC", "merges": "D OC", "raw_count": 85943, "count": 85943, "decode_str": "DOC"} -{"id": 39028, "token": "dq", "merges": "d q", "raw_count": 85944, "count": 85944, "decode_str": "dq"} -{"id": 5747, "token": "\u0120despite", "merges": "\u0120des pite", "raw_count": 85948, "count": 85948, "decode_str": " despite"} -{"id": 14659, "token": "\u0120encouraged", "merges": "\u0120encour aged", "raw_count": 85963, "count": 85963, "decode_str": " encouraged"} -{"id": 27121, "token": "States", "merges": "St ates", "raw_count": 85996, "count": 85996, "decode_str": "States"} -{"id": 40481, "token": "978", "merges": "9 78", "raw_count": 85999, "count": 85999, "decode_str": "978"} -{"id": 11053, "token": "\u0120southern", "merges": "\u0120s outhern", "raw_count": 86003, "count": 86003, "decode_str": " southern"} -{"id": 8470, "token": "\u0120spaces", "merges": "\u0120sp aces", "raw_count": 86011, "count": 86011, "decode_str": " spaces"} -{"id": 32646, "token": "RG", "merges": "R G", "raw_count": 86024, "count": 86024, "decode_str": "RG"} -{"id": 11087, "token": "\u012073", "merges": "\u01207 3", "raw_count": 86030, "count": 86030, "decode_str": " 73"} -{"id": 39168, "token": "trig", "merges": "tr ig", "raw_count": 86046, "count": 86046, "decode_str": "trig"} -{"id": 21004, "token": "\u0120vec", "merges": "\u0120ve c", "raw_count": 86073, "count": 86073, "decode_str": " vec"} -{"id": 39506, "token": "841", "merges": "84 1", "raw_count": 86097, "count": 86097, "decode_str": "841"} -{"id": 8037, "token": "\u0120gap", "merges": "\u0120g ap", "raw_count": 86103, "count": 86103, "decode_str": " gap"} -{"id": 11140, "token": "\u0120125", "merges": "\u01201 25", "raw_count": 86114, "count": 86114, "decode_str": " 125"} -{"id": 48144, "token": "Eye", "merges": "E ye", "raw_count": 86115, "count": 86115, "decode_str": "Eye"} -{"id": 50457, "token": "\u00e4\u00b9\u00a9", "merges": "\u00e4\u00b9 \u00a9", "raw_count": 86129, "count": 86129, "decode_str": "\u4e69"} -{"id": 30785, "token": "Zn", "merges": "Z n", "raw_count": 86146, "count": 86146, "decode_str": "Zn"} -{"id": 18487, "token": "ktop", "merges": "k top", "raw_count": 7684, "count": 86154, "decode_str": "ktop"} -{"id": 4031, "token": "\u0120Id", "merges": "\u0120I d", "raw_count": 48569, "count": 86157, "decode_str": " Id"} -{"id": 29541, "token": "median", "merges": "med ian", "raw_count": 86158, "count": 86158, "decode_str": "median"} -{"id": 38337, "token": "cores", "merges": "co res", "raw_count": 86212, "count": 86212, "decode_str": "cores"} -{"id": 22210, "token": "fed", "merges": "f ed", "raw_count": 86214, "count": 86214, "decode_str": "fed"} -{"id": 16245, "token": "again", "merges": "ag ain", "raw_count": 53462, "count": 86224, "decode_str": "again"} -{"id": 6009, "token": "\u0120faith", "merges": "\u0120fa ith", "raw_count": 71997, "count": 86240, "decode_str": " faith"} -{"id": 40631, "token": "Suite", "merges": "Su ite", "raw_count": 86316, "count": 86316, "decode_str": "Suite"} -{"id": 22320, "token": "\u0120Beaut", "merges": "\u0120Be aut", "raw_count": 615, "count": 86324, "decode_str": " Beaut"} -{"id": 53517, "token": "\u00e8\u0125\u013f", "merges": "\u00e8\u0125 \u013f", "raw_count": 86359, "count": 86359, "decode_str": "\u80dd"} -{"id": 28997, "token": "NAM", "merges": "NA M", "raw_count": 86359, "count": 86359, "decode_str": "NAM"} -{"id": 10014, "token": "\u0120theme", "merges": "\u0120them e", "raw_count": 86403, "count": 86403, "decode_str": " theme"} -{"id": 5795, "token": "\u0120alternative", "merges": "\u0120altern ative", "raw_count": 86409, "count": 86409, "decode_str": " alternative"} -{"id": 10694, "token": "\u012097", "merges": "\u01209 7", "raw_count": 86410, "count": 86410, "decode_str": " 97"} -{"id": 43784, "token": "6789", "merges": "67 89", "raw_count": 86431, "count": 86431, "decode_str": "6789"} -{"id": 7266, "token": "\u0120pp", "merges": "\u0120p p", "raw_count": 86489, "count": 86489, "decode_str": " pp"} -{"id": 5890, "token": "\u0120warm", "merges": "\u0120w arm", "raw_count": 68013, "count": 86498, "decode_str": " warm"} -{"id": 46429, "token": "inverse", "merges": "in verse", "raw_count": 86511, "count": 86511, "decode_str": "inverse"} -{"id": 43114, "token": "593", "merges": "59 3", "raw_count": 86518, "count": 86518, "decode_str": "593"} -{"id": 27732, "token": "Diff", "merges": "D iff", "raw_count": 86526, "count": 86526, "decode_str": "Diff"} -{"id": 11833, "token": "\u0120dipl", "merges": "\u0120di pl", "raw_count": 9192, "count": 86540, "decode_str": " dipl"} -{"id": 18916, "token": "determ", "merges": "det erm", "raw_count": 39947, "count": 86544, "decode_str": "determ"} -{"id": 4834, "token": "\u0120yourself", "merges": "\u0120your self", "raw_count": 86549, "count": 86549, "decode_str": " yourself"} -{"id": 5453, "token": "\u0120club", "merges": "\u0120cl ub", "raw_count": 71706, "count": 86550, "decode_str": " club"} -{"id": 8270, "token": "seud", "merges": "se ud", "raw_count": 770, "count": 86551, "decode_str": "seud"} -{"id": 16210, "token": "herry", "merges": "her ry", "raw_count": 21263, "count": 86566, "decode_str": "herry"} -{"id": 4458, "token": "\u0120Int", "merges": "\u0120In t", "raw_count": 62947, "count": 86591, "decode_str": " Int"} -{"id": 40779, "token": "Words", "merges": "W ords", "raw_count": 86604, "count": 86604, "decode_str": "Words"} -{"id": 52832, "token": "\u00e7\u0131\u00a3", "merges": "\u00e7\u0131 \u00a3", "raw_count": 86614, "count": 86614, "decode_str": "\u73e3"} -{"id": 16709, "token": "bsite", "merges": "bs ite", "raw_count": 632, "count": 86619, "decode_str": "bsite"} -{"id": 21822, "token": "Single", "merges": "Sing le", "raw_count": 86620, "count": 86620, "decode_str": "Single"} -{"id": 30519, "token": "Must", "merges": "M ust", "raw_count": 86631, "count": 86631, "decode_str": "Must"} -{"id": 43575, "token": "paragraph", "merges": "par agraph", "raw_count": 86637, "count": 86637, "decode_str": "paragraph"} -{"id": 7529, "token": "\u0120parallel", "merges": "\u0120par allel", "raw_count": 86640, "count": 86640, "decode_str": " parallel"} -{"id": 46818, "token": "registration", "merges": "reg istration", "raw_count": 86651, "count": 86651, "decode_str": "registration"} -{"id": 21943, "token": "reach", "merges": "re ach", "raw_count": 55026, "count": 86724, "decode_str": "reach"} -{"id": 36840, "token": "Missing", "merges": "Miss ing", "raw_count": 86767, "count": 86767, "decode_str": "Missing"} -{"id": 15239, "token": "\u0120slot", "merges": "\u0120sl ot", "raw_count": 86771, "count": 86771, "decode_str": " slot"} -{"id": 54541, "token": "\u00e7\u00bb\u0139", "merges": "\u00e7\u00bb \u0139", "raw_count": 86772, "count": 86772, "decode_str": "\u7ed7"} -{"id": 27879, "token": "Pac", "merges": "P ac", "raw_count": 33692, "count": 86774, "decode_str": "Pac"} -{"id": 14990, "token": "aman", "merges": "am an", "raw_count": 86798, "count": 86798, "decode_str": "aman"} -{"id": 32328, "token": "paces", "merges": "p aces", "raw_count": 86809, "count": 86809, "decode_str": "paces"} -{"id": 31686, "token": "ideos", "merges": "ide os", "raw_count": 85462, "count": 86839, "decode_str": "ideos"} -{"id": 15941, "token": "\u0120Graph", "merges": "\u0120G raph", "raw_count": 79693, "count": 86848, "decode_str": " Graph"} -{"id": 37789, "token": "STA", "merges": "ST A", "raw_count": 86881, "count": 86881, "decode_str": "STA"} -{"id": 12509, "token": "bold", "merges": "b old", "raw_count": 86878, "count": 86898, "decode_str": "bold"} -{"id": 41394, "token": "gain", "merges": "g ain", "raw_count": 86899, "count": 86899, "decode_str": "gain"} -{"id": 9657, "token": "\u0120*)", "merges": "\u0120* )", "raw_count": 86911, "count": 86911, "decode_str": " *)"} -{"id": 29727, "token": "Secret", "merges": "Se cret", "raw_count": 86923, "count": 86923, "decode_str": "Secret"} -{"id": 5877, "token": "\u0120holding", "merges": "\u0120hold ing", "raw_count": 86924, "count": 86924, "decode_str": " holding"} -{"id": 7870, "token": "\u0120dynamic", "merges": "\u0120dynam ic", "raw_count": 86933, "count": 86933, "decode_str": " dynamic"} -{"id": 30235, "token": "Fa", "merges": "F a", "raw_count": 86952, "count": 86952, "decode_str": "Fa"} -{"id": 11752, "token": "Under", "merges": "Un der", "raw_count": 86957, "count": 86957, "decode_str": "Under"} -{"id": 22050, "token": "FROM", "merges": "FR OM", "raw_count": 86986, "count": 86986, "decode_str": "FROM"} -{"id": 17048, "token": "026", "merges": "0 26", "raw_count": 87002, "count": 87002, "decode_str": "026"} -{"id": 4354, "token": "\u0120easily", "merges": "\u0120eas ily", "raw_count": 87007, "count": 87007, "decode_str": " easily"} -{"id": 7365, "token": "\u0120independ", "merges": "\u0120ind epend", "raw_count": 2367, "count": 87053, "decode_str": " independ"} -{"id": 40077, "token": "Checked", "merges": "Check ed", "raw_count": 87070, "count": 87070, "decode_str": "Checked"} -{"id": 43451, "token": "arrays", "merges": "arr ays", "raw_count": 87088, "count": 87088, "decode_str": "arrays"} -{"id": 22730, "token": "microsoft", "merges": "m icrosoft", "raw_count": 87093, "count": 87093, "decode_str": "microsoft"} -{"id": 29160, "token": "056", "merges": "05 6", "raw_count": 87113, "count": 87113, "decode_str": "056"} -{"id": 52106, "token": "\u00e6\u0139\u0125", "merges": "\u00e6\u0139 \u0125", "raw_count": 87164, "count": 87164, "decode_str": "\u65c3"} -{"id": 40997, "token": "vote", "merges": "v ote", "raw_count": 87171, "count": 87171, "decode_str": "vote"} -{"id": 13263, "token": "season", "merges": "se ason", "raw_count": 86479, "count": 87183, "decode_str": "season"} -{"id": 17174, "token": "Os", "merges": "O s", "raw_count": 87183, "count": 87183, "decode_str": "Os"} -{"id": 7651, "token": "\u0120NO", "merges": "\u0120N O", "raw_count": 87193, "count": 87193, "decode_str": " NO"} -{"id": 6446, "token": "\u0120ing", "merges": "\u0120 ing", "raw_count": 41792, "count": 87215, "decode_str": " ing"} -{"id": 8291, "token": ",_", "merges": ", _", "raw_count": 87259, "count": 87259, "decode_str": ",_"} -{"id": 21642, "token": "RU", "merges": "R U", "raw_count": 82976, "count": 87264, "decode_str": "RU"} -{"id": 5393, "token": "\u0120mentioned", "merges": "\u0120mention ed", "raw_count": 87313, "count": 87313, "decode_str": " mentioned"} -{"id": 6032, "token": "\u0120smooth", "merges": "\u0120sm ooth", "raw_count": 62887, "count": 87317, "decode_str": " smooth"} -{"id": 9912, "token": "\u0120blank", "merges": "\u0120bl ank", "raw_count": 78566, "count": 87317, "decode_str": " blank"} -{"id": 7066, "token": "\u0120Web", "merges": "\u0120We b", "raw_count": 86824, "count": 87336, "decode_str": " Web"} -{"id": 24265, "token": "ITS", "merges": "IT S", "raw_count": 87324, "count": 87345, "decode_str": "ITS"} -{"id": 6793, "token": "\u0120rich", "merges": "\u0120r ich", "raw_count": 85624, "count": 87348, "decode_str": " rich"} -{"id": 20406, "token": "argo", "merges": "arg o", "raw_count": 55542, "count": 87369, "decode_str": "argo"} -{"id": 25857, "token": "birth", "merges": "b irth", "raw_count": 87385, "count": 87385, "decode_str": "birth"} -{"id": 22016, "token": "\u0120dissemin", "merges": "\u0120disse min", "raw_count": 31013, "count": 87386, "decode_str": " dissemin"} -{"id": 49875, "token": "widgets", "merges": "widget s", "raw_count": 87386, "count": 87386, "decode_str": "widgets"} -{"id": 5433, "token": "\u0120regul", "merges": "\u0120reg ul", "raw_count": 1095, "count": 87386, "decode_str": " regul"} -{"id": 19207, "token": "ctl", "merges": "ct l", "raw_count": 87401, "count": 87401, "decode_str": "ctl"} -{"id": 41628, "token": "capture", "merges": "capt ure", "raw_count": 87407, "count": 87407, "decode_str": "capture"} -{"id": 22439, "token": "038", "merges": "0 38", "raw_count": 87426, "count": 87426, "decode_str": "038"} -{"id": 32896, "token": "Examples", "merges": "Ex amples", "raw_count": 87459, "count": 87459, "decode_str": "Examples"} -{"id": 6948, "token": "ashed", "merges": "as hed", "raw_count": 63287, "count": 87461, "decode_str": "ashed"} -{"id": 36626, "token": "uds", "merges": "ud s", "raw_count": 87489, "count": 87489, "decode_str": "uds"} -{"id": 48923, "token": "722", "merges": "7 22", "raw_count": 87501, "count": 87501, "decode_str": "722"} -{"id": 3512, "token": "\u0120Part", "merges": "\u0120P art", "raw_count": 56464, "count": 87522, "decode_str": " Part"} -{"id": 43217, "token": "Prem", "merges": "P rem", "raw_count": 87533, "count": 87533, "decode_str": "Prem"} -{"id": 14743, "token": "amy", "merges": "am y", "raw_count": 85166, "count": 87554, "decode_str": "amy"} -{"id": 41493, "token": "872", "merges": "87 2", "raw_count": 87559, "count": 87559, "decode_str": "872"} -{"id": 6614, "token": "mittee", "merges": "mit tee", "raw_count": 25503, "count": 87560, "decode_str": "mittee"} -{"id": 5125, "token": "\u0120suggested", "merges": "\u0120suggest ed", "raw_count": 87580, "count": 87580, "decode_str": " suggested"} -{"id": 10789, "token": "usal", "merges": "us al", "raw_count": 6570, "count": 87611, "decode_str": "usal"} -{"id": 20794, "token": "Sat", "merges": "S at", "raw_count": 87633, "count": 87633, "decode_str": "Sat"} -{"id": 4936, "token": "\u0120grand", "merges": "\u0120gr and", "raw_count": 61776, "count": 87641, "decode_str": " grand"} -{"id": 18688, "token": "BLE", "merges": "B LE", "raw_count": 47813, "count": 87642, "decode_str": "BLE"} -{"id": 15843, "token": "CHAR", "merges": "CH AR", "raw_count": 72609, "count": 87661, "decode_str": "CHAR"} -{"id": 3825, "token": "iments", "merges": "im ents", "raw_count": 56405, "count": 87670, "decode_str": "iments"} -{"id": 35980, "token": "Corp", "merges": "Cor p", "raw_count": 87716, "count": 87716, "decode_str": "Corp"} -{"id": 27788, "token": "Ten", "merges": "T en", "raw_count": 87720, "count": 87720, "decode_str": "Ten"} -{"id": 39960, "token": "atype", "merges": "at ype", "raw_count": 87726, "count": 87726, "decode_str": "atype"} -{"id": 27545, "token": "chin", "merges": "ch in", "raw_count": 87726, "count": 87726, "decode_str": "chin"} -{"id": 7590, "token": "\u0120pet", "merges": "\u0120p et", "raw_count": 62788, "count": 87728, "decode_str": " pet"} -{"id": 45514, "token": "ESH", "merges": "ES H", "raw_count": 87733, "count": 87733, "decode_str": "ESH"} -{"id": 11229, "token": "ublished", "merges": "ubl ished", "raw_count": 1009, "count": 87740, "decode_str": "ublished"} -{"id": 10943, "token": ".]", "merges": ". ]", "raw_count": 87744, "count": 87744, "decode_str": ".]"} -{"id": 4536, "token": "\u0120sometimes", "merges": "\u0120somet imes", "raw_count": 87752, "count": 87752, "decode_str": " sometimes"} -{"id": 6960, "token": "\u0120ordered", "merges": "\u0120or dered", "raw_count": 87768, "count": 87768, "decode_str": " ordered"} -{"id": 52898, "token": "\u00e7\u0137\u00b9", "merges": "\u00e7\u0137 \u00b9", "raw_count": 87785, "count": 87785, "decode_str": "\u7579"} -{"id": 14142, "token": "\u0120actors", "merges": "\u0120act ors", "raw_count": 87793, "count": 87793, "decode_str": " actors"} -{"id": 15354, "token": "aro", "merges": "ar o", "raw_count": 87812, "count": 87812, "decode_str": "aro"} -{"id": 23751, "token": "Audio", "merges": "Aud io", "raw_count": 87826, "count": 87826, "decode_str": "Audio"} -{"id": 25637, "token": "boys", "merges": "bo ys", "raw_count": 87762, "count": 87828, "decode_str": "boys"} -{"id": 29653, "token": "Integr", "merges": "Inte gr", "raw_count": 87833, "count": 87833, "decode_str": "Integr"} -{"id": 4067, "token": "\u0120larger", "merges": "\u0120lar ger", "raw_count": 87834, "count": 87834, "decode_str": " larger"} -{"id": 11513, "token": "\u01201988", "merges": "\u012019 88", "raw_count": 87839, "count": 87839, "decode_str": " 1988"} -{"id": 12639, "token": "\u0120Process", "merges": "\u0120Pro cess", "raw_count": 77792, "count": 87849, "decode_str": " Process"} -{"id": 24239, "token": "YES", "merges": "Y ES", "raw_count": 87860, "count": 87860, "decode_str": "YES"} -{"id": 3150, "token": "\u0120die", "merges": "\u0120d ie", "raw_count": 85560, "count": 87873, "decode_str": " die"} -{"id": 11198, "token": "\u0120Ent", "merges": "\u0120E nt", "raw_count": 16187, "count": 87899, "decode_str": " Ent"} -{"id": 37331, "token": "Push", "merges": "P ush", "raw_count": 87916, "count": 87916, "decode_str": "Push"} -{"id": 6467, "token": "\u0120\u00d0\u00ba", "merges": "\u0120\u00d0 \u00ba", "raw_count": 57348, "count": 87950, "decode_str": " \u043a"} -{"id": 19264, "token": "uet", "merges": "u et", "raw_count": 33842, "count": 87968, "decode_str": "uet"} -{"id": 1124, "token": "frac", "merges": "fr ac", "raw_count": 87197, "count": 87993, "decode_str": "frac"} -{"id": 31628, "token": "Bey", "merges": "B ey", "raw_count": 16410, "count": 88024, "decode_str": "Bey"} -{"id": 9231, "token": "rants", "merges": "r ants", "raw_count": 12187, "count": 88031, "decode_str": "rants"} -{"id": 12157, "token": "because", "merges": "b ecause", "raw_count": 88040, "count": 88040, "decode_str": "because"} -{"id": 22890, "token": "ienna", "merges": "ien na", "raw_count": 87457, "count": 88047, "decode_str": "ienna"} -{"id": 9918, "token": "razil", "merges": "raz il", "raw_count": 81832, "count": 88052, "decode_str": "razil"} -{"id": 5717, "token": "\u0120thank", "merges": "\u0120than k", "raw_count": 70090, "count": 88074, "decode_str": " thank"} -{"id": 5235, "token": "\u0120variety", "merges": "\u0120vari ety", "raw_count": 88083, "count": 88083, "decode_str": " variety"} -{"id": 13703, "token": "oga", "merges": "og a", "raw_count": 76293, "count": 88091, "decode_str": "oga"} -{"id": 8852, "token": "\u0120coast", "merges": "\u0120co ast", "raw_count": 55042, "count": 88093, "decode_str": " coast"} -{"id": 47507, "token": "587", "merges": "5 87", "raw_count": 88093, "count": 88093, "decode_str": "587"} -{"id": 7505, "token": "\u0120bug", "merges": "\u0120b ug", "raw_count": 75837, "count": 88122, "decode_str": " bug"} -{"id": 33014, "token": "igi", "merges": "ig i", "raw_count": 88189, "count": 88189, "decode_str": "igi"} -{"id": 14208, "token": "\u0120rs", "merges": "\u0120r s", "raw_count": 88197, "count": 88197, "decode_str": " rs"} -{"id": 5879, "token": "\u0109\u0109\u0109\u0109", "merges": "\u0109\u0109 \u0109\u0109", "raw_count": 20544, "count": 88210, "decode_str": "\t\t\t\t"} -{"id": 40074, "token": "ZA", "merges": "Z A", "raw_count": 88215, "count": 88215, "decode_str": "ZA"} -{"id": 10224, "token": "\u0120fails", "merges": "\u0120fail s", "raw_count": 88224, "count": 88224, "decode_str": " fails"} -{"id": 26139, "token": "east", "merges": "e ast", "raw_count": 88224, "count": 88224, "decode_str": "east"} -{"id": 31838, "token": "Usage", "merges": "Us age", "raw_count": 88229, "count": 88229, "decode_str": "Usage"} -{"id": 15131, "token": "Effect", "merges": "E ffect", "raw_count": 69816, "count": 88249, "decode_str": "Effect"} -{"id": 43453, "token": "Learning", "merges": "Lear ning", "raw_count": 88289, "count": 88289, "decode_str": "Learning"} -{"id": 19169, "token": "\u0120lin", "merges": "\u0120l in", "raw_count": 88326, "count": 88326, "decode_str": " lin"} -{"id": 37701, "token": "Anth", "merges": "An th", "raw_count": 10235, "count": 88330, "decode_str": "Anth"} -{"id": 18374, "token": "\u0120Sequ", "merges": "\u0120Se qu", "raw_count": 27693, "count": 88332, "decode_str": " Sequ"} -{"id": 4089, "token": "\u0120hear", "merges": "\u0120he ar", "raw_count": 76461, "count": 88350, "decode_str": " hear"} -{"id": 5263, "token": "\u0120arrest", "merges": "\u0120ar rest", "raw_count": 42449, "count": 88362, "decode_str": " arrest"} -{"id": 4518, "token": "\u0120clearly", "merges": "\u0120cle arly", "raw_count": 88397, "count": 88397, "decode_str": " clearly"} -{"id": 15062, "token": "\u0120disse", "merges": "\u0120dis se", "raw_count": 616, "count": 88400, "decode_str": " disse"} -{"id": 27002, "token": "FAIL", "merges": "FA IL", "raw_count": 88418, "count": 88418, "decode_str": "FAIL"} -{"id": 26049, "token": "motion", "merges": "m otion", "raw_count": 88419, "count": 88419, "decode_str": "motion"} -{"id": 20645, "token": "schem", "merges": "sc hem", "raw_count": 20578, "count": 88449, "decode_str": "schem"} -{"id": 12802, "token": "\u0120retriev", "merges": "\u0120ret riev", "raw_count": 11519, "count": 88456, "decode_str": " retriev"} -{"id": 3545, "token": "\u0120Per", "merges": "\u0120P er", "raw_count": 47527, "count": 88475, "decode_str": " Per"} -{"id": 25115, "token": "deal", "merges": "de al", "raw_count": 88498, "count": 88498, "decode_str": "deal"} -{"id": 39217, "token": "sell", "merges": "s ell", "raw_count": 88517, "count": 88517, "decode_str": "sell"} -{"id": 19710, "token": "Prote", "merges": "Pro te", "raw_count": 76483, "count": 88528, "decode_str": "Prote"} -{"id": 7473, "token": "\u0120formal", "merges": "\u0120form al", "raw_count": 86393, "count": 88539, "decode_str": " formal"} -{"id": 10165, "token": "\u0120choices", "merges": "\u0120cho ices", "raw_count": 88550, "count": 88550, "decode_str": " choices"} -{"id": 12638, "token": "archy", "merges": "arch y", "raw_count": 59434, "count": 88554, "decode_str": "archy"} -{"id": 44030, "token": "791", "merges": "79 1", "raw_count": 88556, "count": 88556, "decode_str": "791"} -{"id": 11448, "token": "worth", "merges": "w orth", "raw_count": 77963, "count": 88559, "decode_str": "worth"} -{"id": 29724, "token": "Loop", "merges": "Lo op", "raw_count": 88569, "count": 88569, "decode_str": "Loop"} -{"id": 28652, "token": "OPEN", "merges": "OP EN", "raw_count": 88583, "count": 88583, "decode_str": "OPEN"} -{"id": 10535, "token": "\u0120Hand", "merges": "\u0120H and", "raw_count": 24228, "count": 88591, "decode_str": " Hand"} -{"id": 26170, "token": "Language", "merges": "L anguage", "raw_count": 88601, "count": 88601, "decode_str": "Language"} -{"id": 15017, "token": "0004", "merges": "000 4", "raw_count": 88621, "count": 88621, "decode_str": "0004"} -{"id": 12943, "token": "ounce", "merges": "oun ce", "raw_count": 76480, "count": 88626, "decode_str": "ounce"} -{"id": 25360, "token": "dll", "merges": "d ll", "raw_count": 88632, "count": 88632, "decode_str": "dll"} -{"id": 14204, "token": "\u0120certificate", "merges": "\u0120cert ificate", "raw_count": 88648, "count": 88648, "decode_str": " certificate"} -{"id": 5553, "token": "\u0120radio", "merges": "\u0120rad io", "raw_count": 85343, "count": 88656, "decode_str": " radio"} -{"id": 38184, "token": "794", "merges": "79 4", "raw_count": 88704, "count": 88704, "decode_str": "794"} -{"id": 24314, "token": "Limit", "merges": "L imit", "raw_count": 88711, "count": 88711, "decode_str": "Limit"} -{"id": 35649, "token": "NAT", "merges": "N AT", "raw_count": 88717, "count": 88717, "decode_str": "NAT"} -{"id": 3543, "token": "\u0120felt", "merges": "\u0120f elt", "raw_count": 88733, "count": 88733, "decode_str": " felt"} -{"id": 5299, "token": "\u0120labor", "merges": "\u0120l abor", "raw_count": 48363, "count": 88734, "decode_str": " labor"} -{"id": 23524, "token": "\u0120ss", "merges": "\u0120s s", "raw_count": 88734, "count": 88734, "decode_str": " ss"} -{"id": 10963, "token": "\u0120compensation", "merges": "\u0120compens ation", "raw_count": 88745, "count": 88745, "decode_str": " compensation"} -{"id": 14199, "token": "\u0120membership", "merges": "\u0120members hip", "raw_count": 88762, "count": 88762, "decode_str": " membership"} -{"id": 6183, "token": "\u0120manif", "merges": "\u0120man if", "raw_count": 221, "count": 88794, "decode_str": " manif"} -{"id": 12188, "token": "bing", "merges": "b ing", "raw_count": 82382, "count": 88795, "decode_str": "bing"} -{"id": 27068, "token": "Interval", "merges": "Inter val", "raw_count": 88801, "count": 88801, "decode_str": "Interval"} -{"id": 27931, "token": "\u0120economies", "merges": "\u0120econom ies", "raw_count": 88862, "count": 88862, "decode_str": " economies"} -{"id": 49891, "token": "813", "merges": "8 13", "raw_count": 88862, "count": 88862, "decode_str": "813"} -{"id": 22647, "token": "\u0120sender", "merges": "\u0120s ender", "raw_count": 88879, "count": 88879, "decode_str": " sender"} -{"id": 13340, "token": "ucl", "merges": "u cl", "raw_count": 38651, "count": 88882, "decode_str": "ucl"} -{"id": 17899, "token": "\u0120google", "merges": "\u0120go ogle", "raw_count": 88889, "count": 88889, "decode_str": " google"} -{"id": 16056, "token": "spin", "merges": "sp in", "raw_count": 88919, "count": 88919, "decode_str": "spin"} -{"id": 34739, "token": "Done", "merges": "D one", "raw_count": 88947, "count": 88947, "decode_str": "Done"} -{"id": 48419, "token": "634", "merges": "6 34", "raw_count": 88947, "count": 88947, "decode_str": "634"} -{"id": 44260, "token": "637", "merges": "6 37", "raw_count": 88981, "count": 88981, "decode_str": "637"} -{"id": 1950, "token": "\u00c3\u0143", "merges": "\u00c3 \u0143", "raw_count": 42025, "count": 88983, "decode_str": "\u00ed"} -{"id": 36031, "token": "RV", "merges": "R V", "raw_count": 88994, "count": 88994, "decode_str": "RV"} -{"id": 17811, "token": "\u0120Vector", "merges": "\u0120V ector", "raw_count": 88998, "count": 88998, "decode_str": " Vector"} -{"id": 6351, "token": "\u0120gain", "merges": "\u0120g ain", "raw_count": 89021, "count": 89021, "decode_str": " gain"} -{"id": 8131, "token": "\u0120predicted", "merges": "\u0120predict ed", "raw_count": 89045, "count": 89045, "decode_str": " predicted"} -{"id": 12924, "token": "\u0120neighb", "merges": "\u0120neigh b", "raw_count": 1111, "count": 89071, "decode_str": " neighb"} -{"id": 35255, "token": "fro", "merges": "f ro", "raw_count": 89074, "count": 89074, "decode_str": "fro"} -{"id": 7869, "token": "\u00d0\u00be\u00d0\u00bb", "merges": "\u00d0\u00be\u00d0 \u00bb", "raw_count": 46583, "count": 89090, "decode_str": "\u043e\u043b"} -{"id": 31473, "token": "subscribe", "merges": "sub scribe", "raw_count": 89100, "count": 89100, "decode_str": "subscribe"} -{"id": 21659, "token": "Assert", "merges": "Ass ert", "raw_count": 89126, "count": 89126, "decode_str": "Assert"} -{"id": 27033, "token": "\u00e6\u013b\u0124", "merges": "\u00e6 \u013b\u0124", "raw_count": 89130, "count": 89130, "decode_str": "\u6642"} -{"id": 2951, "token": "\u0120Ste", "merges": "\u0120S te", "raw_count": 11550, "count": 89140, "decode_str": " Ste"} -{"id": 10671, "token": "\u0120quantity", "merges": "\u0120quant ity", "raw_count": 89144, "count": 89144, "decode_str": " quantity"} -{"id": 40651, "token": "difference", "merges": "d ifference", "raw_count": 89149, "count": 89149, "decode_str": "difference"} -{"id": 21183, "token": "\u0120consultation", "merges": "\u0120consult ation", "raw_count": 89157, "count": 89157, "decode_str": " consultation"} -{"id": 5469, "token": "\u0120discussed", "merges": "\u0120discuss ed", "raw_count": 89170, "count": 89170, "decode_str": " discussed"} -{"id": 17989, "token": "economic", "merges": "e conomic", "raw_count": 80356, "count": 89177, "decode_str": "economic"} -{"id": 9822, "token": "ynom", "merges": "yn om", "raw_count": 53446, "count": 89177, "decode_str": "ynom"} -{"id": 3879, "token": "\u0120behavior", "merges": "\u0120behav ior", "raw_count": 85489, "count": 89189, "decode_str": " behavior"} -{"id": 14725, "token": "Provider", "merges": "Prov ider", "raw_count": 89195, "count": 89195, "decode_str": "Provider"} -{"id": 24042, "token": "reading", "merges": "read ing", "raw_count": 89211, "count": 89211, "decode_str": "reading"} -{"id": 8482, "token": "\u0120subt", "merges": "\u0120sub t", "raw_count": 47189, "count": 89214, "decode_str": " subt"} -{"id": 4646, "token": "\u0120medium", "merges": "\u0120med ium", "raw_count": 89227, "count": 89227, "decode_str": " medium"} -{"id": 36176, "token": "956", "merges": "95 6", "raw_count": 89227, "count": 89227, "decode_str": "956"} -{"id": 30767, "token": "creation", "merges": "cre ation", "raw_count": 89234, "count": 89234, "decode_str": "creation"} -{"id": 16960, "token": "Expression", "merges": "Exp ression", "raw_count": 89247, "count": 89247, "decode_str": "Expression"} -{"id": 29710, "token": "Sent", "merges": "S ent", "raw_count": 89279, "count": 89279, "decode_str": "Sent"} -{"id": 5415, "token": "\u0120continuous", "merges": "\u0120contin uous", "raw_count": 64962, "count": 89292, "decode_str": " continuous"} -{"id": 4541, "token": "\u0120quickly", "merges": "\u0120quick ly", "raw_count": 89295, "count": 89295, "decode_str": " quickly"} -{"id": 20408, "token": "\u0120elimination", "merges": "\u0120elim ination", "raw_count": 89296, "count": 89296, "decode_str": " elimination"} -{"id": 45112, "token": "Jay", "merges": "J ay", "raw_count": 89298, "count": 89298, "decode_str": "Jay"} -{"id": 40427, "token": "etype", "merges": "et ype", "raw_count": 89322, "count": 89322, "decode_str": "etype"} -{"id": 6671, "token": "\u0120teams", "merges": "\u0120te ams", "raw_count": 89327, "count": 89327, "decode_str": " teams"} -{"id": 20331, "token": "irq", "merges": "ir q", "raw_count": 89328, "count": 89328, "decode_str": "irq"} -{"id": 23080, "token": "Lat", "merges": "L at", "raw_count": 89335, "count": 89335, "decode_str": "Lat"} -{"id": 19318, "token": "parency", "merges": "pa rency", "raw_count": 18960, "count": 89339, "decode_str": "parency"} -{"id": 34109, "token": "065", "merges": "0 65", "raw_count": 89352, "count": 89352, "decode_str": "065"} -{"id": 5782, "token": "\u0120proport", "merges": "\u0120pro port", "raw_count": 74, "count": 89363, "decode_str": " proport"} -{"id": 7143, "token": "\u0120duty", "merges": "\u0120dut y", "raw_count": 89377, "count": 89377, "decode_str": " duty"} -{"id": 3637, "token": "\u0120follows", "merges": "\u0120follow s", "raw_count": 89390, "count": 89390, "decode_str": " follows"} -{"id": 28532, "token": "\")]", "merges": "\") ]", "raw_count": 89407, "count": 89407, "decode_str": "\")]"} -{"id": 49463, "token": "Flex", "merges": "F lex", "raw_count": 89412, "count": 89412, "decode_str": "Flex"} -{"id": 48549, "token": "732", "merges": "7 32", "raw_count": 89465, "count": 89465, "decode_str": "732"} -{"id": 27183, "token": "peak", "merges": "pe ak", "raw_count": 89471, "count": 89471, "decode_str": "peak"} -{"id": 42815, "token": "793", "merges": "79 3", "raw_count": 89483, "count": 89483, "decode_str": "793"} -{"id": 28895, "token": "Dar", "merges": "D ar", "raw_count": 89486, "count": 89486, "decode_str": "Dar"} -{"id": 49403, "token": "ZH", "merges": "Z H", "raw_count": 89500, "count": 89500, "decode_str": "ZH"} -{"id": 5517, "token": "\u0120witness", "merges": "\u0120w itness", "raw_count": 34128, "count": 89516, "decode_str": " witness"} -{"id": 16670, "token": "\u0120exclude", "merges": "\u0120ex clude", "raw_count": 89517, "count": 89517, "decode_str": " exclude"} -{"id": 7644, "token": "\u0120disp", "merges": "\u0120dis p", "raw_count": 36578, "count": 89520, "decode_str": " disp"} -{"id": 7289, "token": "\u0120sale", "merges": "\u0120s ale", "raw_count": 89521, "count": 89521, "decode_str": " sale"} -{"id": 7334, "token": "posed", "merges": "pos ed", "raw_count": 67088, "count": 89524, "decode_str": "posed"} -{"id": 47539, "token": "regions", "merges": "reg ions", "raw_count": 89541, "count": 89541, "decode_str": "regions"} -{"id": 11603, "token": "\u0120conflic", "merges": "\u0120conf lic", "raw_count": 185, "count": 89591, "decode_str": " conflic"} -{"id": 8138, "token": "\u0120waste", "merges": "\u0120was te", "raw_count": 79897, "count": 89610, "decode_str": " waste"} -{"id": 13670, "token": "jet", "merges": "j et", "raw_count": 89635, "count": 89635, "decode_str": "jet"} -{"id": 13156, "token": "bur", "merges": "b ur", "raw_count": 67778, "count": 89649, "decode_str": "bur"} -{"id": 29146, "token": "Grad", "merges": "Gr ad", "raw_count": 44069, "count": 89650, "decode_str": "Grad"} -{"id": 29807, "token": "DAY", "merges": "DA Y", "raw_count": 89656, "count": 89656, "decode_str": "DAY"} -{"id": 14261, "token": "\u0120dot", "merges": "\u0120d ot", "raw_count": 89717, "count": 89717, "decode_str": " dot"} -{"id": 22262, "token": "Contin", "merges": "Cont in", "raw_count": 52126, "count": 89766, "decode_str": "Contin"} -{"id": 37104, "token": "apk", "merges": "ap k", "raw_count": 89766, "count": 89766, "decode_str": "apk"} -{"id": 48340, "token": "\u0120pandas", "merges": "\u0120pand as", "raw_count": 89792, "count": 89792, "decode_str": " pandas"} -{"id": 31524, "token": "yang", "merges": "y ang", "raw_count": 89822, "count": 89822, "decode_str": "yang"} -{"id": 45883, "token": "colour", "merges": "col our", "raw_count": 89826, "count": 89826, "decode_str": "colour"} -{"id": 8646, "token": "atural", "merges": "at ural", "raw_count": 3854, "count": 89853, "decode_str": "atural"} -{"id": 52358, "token": "\u00e6\u00a7\u0143", "merges": "\u00e6\u00a7 \u0143", "raw_count": 89862, "count": 89862, "decode_str": "\u69ed"} -{"id": 49643, "token": "wers", "merges": "w ers", "raw_count": 89868, "count": 89868, "decode_str": "wers"} -{"id": 4540, "token": "\u0120discl", "merges": "\u0120dis cl", "raw_count": 3246, "count": 89881, "decode_str": " discl"} -{"id": 27686, "token": "jb", "merges": "j b", "raw_count": 89897, "count": 89897, "decode_str": "jb"} -{"id": 19502, "token": "\u0120iteration", "merges": "\u0120it eration", "raw_count": 89900, "count": 89900, "decode_str": " iteration"} -{"id": 20425, "token": "density", "merges": "d ensity", "raw_count": 89940, "count": 89940, "decode_str": "density"} -{"id": 7764, "token": "\u0120Please", "merges": "\u0120P lease", "raw_count": 89942, "count": 89942, "decode_str": " Please"} -{"id": 7756, "token": "\u0120improvement", "merges": "\u0120improve ment", "raw_count": 89956, "count": 89956, "decode_str": " improvement"} -{"id": 4624, "token": "iques", "merges": "iqu es", "raw_count": 36766, "count": 89963, "decode_str": "iques"} -{"id": 14756, "token": "\u0120ze", "merges": "\u0120z e", "raw_count": 87042, "count": 89966, "decode_str": " ze"} -{"id": 19313, "token": "\u0120notification", "merges": "\u0120not ification", "raw_count": 89982, "count": 89982, "decode_str": " notification"} -{"id": 42050, "token": "listen", "merges": "list en", "raw_count": 89999, "count": 89999, "decode_str": "listen"} -{"id": 19035, "token": "0006", "merges": "000 6", "raw_count": 90018, "count": 90018, "decode_str": "0006"} -{"id": 27041, "token": "Environment", "merges": "En vironment", "raw_count": 90022, "count": 90022, "decode_str": "Environment"} -{"id": 7981, "token": "\u0120license", "merges": "\u0120l icense", "raw_count": 90028, "count": 90028, "decode_str": " license"} -{"id": 11677, "token": "\u0120Inte", "merges": "\u0120In te", "raw_count": 2378, "count": 90031, "decode_str": " Inte"} -{"id": 30023, "token": "god", "merges": "g od", "raw_count": 90035, "count": 90035, "decode_str": "god"} -{"id": 43995, "token": "564", "merges": "5 64", "raw_count": 90036, "count": 90036, "decode_str": "564"} -{"id": 18052, "token": "\u0120specialized", "merges": "\u0120special ized", "raw_count": 90057, "count": 90057, "decode_str": " specialized"} -{"id": 38839, "token": "attempt", "merges": "att empt", "raw_count": 90059, "count": 90059, "decode_str": "attempt"} -{"id": 35446, "token": "INPUT", "merges": "IN PUT", "raw_count": 90064, "count": 90064, "decode_str": "INPUT"} -{"id": 12355, "token": "oni", "merges": "on i", "raw_count": 88806, "count": 90096, "decode_str": "oni"} -{"id": 7098, "token": "\u0120gra", "merges": "\u0120g ra", "raw_count": 31331, "count": 90104, "decode_str": " gra"} -{"id": 19047, "token": "MED", "merges": "M ED", "raw_count": 90090, "count": 90107, "decode_str": "MED"} -{"id": 22643, "token": "Seq", "merges": "S eq", "raw_count": 90119, "count": 90119, "decode_str": "Seq"} -{"id": 14904, "token": "\u0120obligation", "merges": "\u0120oblig ation", "raw_count": 90148, "count": 90148, "decode_str": " obligation"} -{"id": 17340, "token": "\u0120agricultural", "merges": "\u0120agric ultural", "raw_count": 90157, "count": 90157, "decode_str": " agricultural"} -{"id": 13910, "token": "\u0120pending", "merges": "\u0120p ending", "raw_count": 90158, "count": 90158, "decode_str": " pending"} -{"id": 23595, "token": "\u0120registry", "merges": "\u0120reg istry", "raw_count": 90159, "count": 90159, "decode_str": " registry"} -{"id": 22984, "token": "HV", "merges": "H V", "raw_count": 90163, "count": 90163, "decode_str": "HV"} -{"id": 21712, "token": "_:", "merges": "_ :", "raw_count": 90175, "count": 90175, "decode_str": "_:"} -{"id": 10836, "token": "pson", "merges": "ps on", "raw_count": 86772, "count": 90189, "decode_str": "pson"} -{"id": 48793, "token": "547", "merges": "5 47", "raw_count": 90233, "count": 90233, "decode_str": "547"} -{"id": 6310, "token": "\u0120catal", "merges": "\u0120c atal", "raw_count": 12675, "count": 90264, "decode_str": " catal"} -{"id": 6007, "token": "\u0120bill", "merges": "\u0120b ill", "raw_count": 82819, "count": 90281, "decode_str": " bill"} -{"id": 26765, "token": "PART", "merges": "P ART", "raw_count": 90289, "count": 90289, "decode_str": "PART"} -{"id": 10909, "token": "\u012076", "merges": "\u01207 6", "raw_count": 90294, "count": 90294, "decode_str": " 76"} -{"id": 23170, "token": "boolean", "merges": "bo olean", "raw_count": 90329, "count": 90329, "decode_str": "boolean"} -{"id": 52145, "token": "\u00e6\u013a\u00b4", "merges": "\u00e6\u013a \u00b4", "raw_count": 90351, "count": 90351, "decode_str": "\u6634"} -{"id": 24953, "token": "Hard", "merges": "H ard", "raw_count": 90398, "count": 90398, "decode_str": "Hard"} -{"id": 51159, "token": "\u00e5\u013d\u0141", "merges": "\u00e5\u013d \u0141", "raw_count": 90408, "count": 90408, "decode_str": "\u56df"} -{"id": 8163, "token": "oked", "merges": "ok ed", "raw_count": 37864, "count": 90409, "decode_str": "oked"} -{"id": 9406, "token": "\u0120aggreg", "merges": "\u0120ag greg", "raw_count": 10745, "count": 90415, "decode_str": " aggreg"} -{"id": 34480, "token": "caption", "merges": "capt ion", "raw_count": 90423, "count": 90423, "decode_str": "caption"} -{"id": 34834, "token": "!/", "merges": "! /", "raw_count": 90447, "count": 90447, "decode_str": "!/"} -{"id": 11614, "token": "\u012086", "merges": "\u01208 6", "raw_count": 90450, "count": 90450, "decode_str": " 86"} -{"id": 48027, "token": "sampling", "merges": "sam pling", "raw_count": 90463, "count": 90463, "decode_str": "sampling"} -{"id": 1284, "token": "\u0120As", "merges": "\u0120A s", "raw_count": 53514, "count": 90465, "decode_str": " As"} -{"id": 18085, "token": "Year", "merges": "Y ear", "raw_count": 90467, "count": 90467, "decode_str": "Year"} -{"id": 10705, "token": "\u0120marker", "merges": "\u0120mark er", "raw_count": 90479, "count": 90479, "decode_str": " marker"} -{"id": 47253, "token": "cms", "merges": "c ms", "raw_count": 90506, "count": 90506, "decode_str": "cms"} -{"id": 43819, "token": "Sales", "merges": "S ales", "raw_count": 90508, "count": 90508, "decode_str": "Sales"} -{"id": 14147, "token": "usp", "merges": "us p", "raw_count": 60449, "count": 90519, "decode_str": "usp"} -{"id": 41747, "token": "\u0120django", "merges": "\u0120d jango", "raw_count": 90526, "count": 90526, "decode_str": " django"} -{"id": 13938, "token": "\u0120\"#", "merges": "\u0120\" #", "raw_count": 90533, "count": 90533, "decode_str": " \"#"} -{"id": 4743, "token": "\u0120opinion", "merges": "\u0120opin ion", "raw_count": 90561, "count": 90561, "decode_str": " opinion"} -{"id": 30007, "token": "zb", "merges": "z b", "raw_count": 87295, "count": 90581, "decode_str": "zb"} -{"id": 30035, "token": "Sheet", "merges": "She et", "raw_count": 90592, "count": 90592, "decode_str": "Sheet"} -{"id": 14249, "token": "'(", "merges": "' (", "raw_count": 90652, "count": 90652, "decode_str": "'("} -{"id": 9178, "token": "\u01201980", "merges": "\u012019 80", "raw_count": 90654, "count": 90654, "decode_str": " 1980"} -{"id": 3880, "token": "\u0120driv", "merges": "\u0120d riv", "raw_count": 1265, "count": 90709, "decode_str": " driv"} -{"id": 8254, "token": "\u0120clar", "merges": "\u0120cl ar", "raw_count": 21913, "count": 90714, "decode_str": " clar"} -{"id": 47938, "token": "nw", "merges": "n w", "raw_count": 90719, "count": 90719, "decode_str": "nw"} -{"id": 29473, "token": "Henry", "merges": "Hen ry", "raw_count": 90730, "count": 90730, "decode_str": "Henry"} -{"id": 43160, "token": "Michel", "merges": "Mic hel", "raw_count": 90796, "count": 90796, "decode_str": "Michel"} -{"id": 4087, "token": "ously", "merges": "ous ly", "raw_count": 38104, "count": 90816, "decode_str": "ously"} -{"id": 45898, "token": "Alan", "merges": "Al an", "raw_count": 90832, "count": 90832, "decode_str": "Alan"} -{"id": 22176, "token": "Ham", "merges": "H am", "raw_count": 58889, "count": 90838, "decode_str": "Ham"} -{"id": 13853, "token": "acles", "merges": "ac les", "raw_count": 37299, "count": 90843, "decode_str": "acles"} -{"id": 22302, "token": "wire", "merges": "w ire", "raw_count": 90854, "count": 90854, "decode_str": "wire"} -{"id": 15394, "token": "\u0120disaster", "merges": "\u0120dis aster", "raw_count": 90869, "count": 90869, "decode_str": " disaster"} -{"id": 2797, "token": "\u0120obtained", "merges": "\u0120obt ained", "raw_count": 90890, "count": 90890, "decode_str": " obtained"} -{"id": 18347, "token": "sight", "merges": "s ight", "raw_count": 22620, "count": 90899, "decode_str": "sight"} -{"id": 40265, "token": "basis", "merges": "b asis", "raw_count": 90899, "count": 90899, "decode_str": "basis"} -{"id": 11659, "token": "\u0120availability", "merges": "\u0120avail ability", "raw_count": 90928, "count": 90928, "decode_str": " availability"} -{"id": 34006, "token": "smooth", "merges": "sm ooth", "raw_count": 90939, "count": 90939, "decode_str": "smooth"} -{"id": 25875, "token": "CREATE", "merges": "CRE ATE", "raw_count": 90960, "count": 90960, "decode_str": "CREATE"} -{"id": 37854, "token": "Encoder", "merges": "Enc oder", "raw_count": 90978, "count": 90978, "decode_str": "Encoder"} -{"id": 12584, "token": "alo", "merges": "al o", "raw_count": 88860, "count": 90980, "decode_str": "alo"} -{"id": 34700, "token": "merged", "merges": "mer ged", "raw_count": 88917, "count": 90988, "decode_str": "merged"} -{"id": 5920, "token": "\u0120frag", "merges": "\u0120fr ag", "raw_count": 16679, "count": 90992, "decode_str": " frag"} -{"id": 39265, "token": "Franc", "merges": "Fr anc", "raw_count": 90995, "count": 90995, "decode_str": "Franc"} -{"id": 3447, "token": "refore", "merges": "ref ore", "raw_count": 4219, "count": 91008, "decode_str": "refore"} -{"id": 4349, "token": "athe", "merges": "at he", "raw_count": 43874, "count": 91015, "decode_str": "athe"} -{"id": 6397, "token": "\u0120Mat", "merges": "\u0120M at", "raw_count": 30604, "count": 91034, "decode_str": " Mat"} -{"id": 19139, "token": "liers", "merges": "li ers", "raw_count": 33043, "count": 91035, "decode_str": "liers"} -{"id": 27589, "token": "Shell", "merges": "She ll", "raw_count": 91044, "count": 91044, "decode_str": "Shell"} -{"id": 38359, "token": "Hill", "merges": "H ill", "raw_count": 91045, "count": 91045, "decode_str": "Hill"} -{"id": 6035, "token": "ione", "merges": "ion e", "raw_count": 57681, "count": 91074, "decode_str": "ione"} -{"id": 34549, "token": "obo", "merges": "ob o", "raw_count": 91075, "count": 91075, "decode_str": "obo"} -{"id": 9612, "token": "\u0120approval", "merges": "\u0120appro val", "raw_count": 91118, "count": 91118, "decode_str": " approval"} -{"id": 16417, "token": "\u0120arrays", "merges": "\u0120arr ays", "raw_count": 91131, "count": 91131, "decode_str": " arrays"} -{"id": 54589, "token": "\u00e5\u013b\u013a", "merges": "\u00e5\u013b \u013a", "raw_count": 91131, "count": 91131, "decode_str": "\u5658"} -{"id": 24975, "token": "Pattern", "merges": "Pat tern", "raw_count": 91150, "count": 91150, "decode_str": "Pattern"} -{"id": 5812, "token": "\u0120NULL", "merges": "\u0120N ULL", "raw_count": 91192, "count": 91192, "decode_str": " NULL"} -{"id": 52173, "token": "\u00e6\u013b\u00b7", "merges": "\u00e6\u013b \u00b7", "raw_count": 91209, "count": 91209, "decode_str": "\u6677"} -{"id": 11516, "token": "\u0120converted", "merges": "\u0120convert ed", "raw_count": 91212, "count": 91212, "decode_str": " converted"} -{"id": 25123, "token": "Social", "merges": "S ocial", "raw_count": 91228, "count": 91228, "decode_str": "Social"} -{"id": 10317, "token": "orial", "merges": "or ial", "raw_count": 28760, "count": 91239, "decode_str": "orial"} -{"id": 5534, "token": "\u0120wood", "merges": "\u0120w ood", "raw_count": 53849, "count": 91244, "decode_str": " wood"} -{"id": 15037, "token": "igration", "merges": "ig ration", "raw_count": 85047, "count": 91256, "decode_str": "igration"} -{"id": 34686, "token": "Quest", "merges": "Qu est", "raw_count": 81364, "count": 91278, "decode_str": "Quest"} -{"id": 5997, "token": "\u0120causes", "merges": "\u0120caus es", "raw_count": 91280, "count": 91280, "decode_str": " causes"} -{"id": 35431, "token": "daily", "merges": "d aily", "raw_count": 91324, "count": 91324, "decode_str": "daily"} -{"id": 28658, "token": "HG", "merges": "H G", "raw_count": 91332, "count": 91332, "decode_str": "HG"} -{"id": 11655, "token": "\u0120losses", "merges": "\u0120loss es", "raw_count": 91334, "count": 91334, "decode_str": " losses"} -{"id": 23687, "token": "UPDATE", "merges": "U PDATE", "raw_count": 91341, "count": 91341, "decode_str": "UPDATE"} -{"id": 35376, "token": "Ros", "merges": "R os", "raw_count": 91353, "count": 91353, "decode_str": "Ros"} -{"id": 29487, "token": "rong", "merges": "r ong", "raw_count": 79900, "count": 91362, "decode_str": "rong"} -{"id": 17425, "token": "ritic", "merges": "rit ic", "raw_count": 90951, "count": 91377, "decode_str": "ritic"} -{"id": 36342, "token": "Easy", "merges": "E asy", "raw_count": 91410, "count": 91410, "decode_str": "Easy"} -{"id": 36430, "token": "('./", "merges": "(' ./", "raw_count": 91411, "count": 91411, "decode_str": "('./"} -{"id": 27419, "token": "ubernetes", "merges": "ubern etes", "raw_count": 63898, "count": 91416, "decode_str": "ubernetes"} -{"id": 23963, "token": "native", "merges": "n ative", "raw_count": 91417, "count": 91417, "decode_str": "native"} -{"id": 18145, "token": "gets", "merges": "get s", "raw_count": 91419, "count": 91419, "decode_str": "gets"} -{"id": 20131, "token": "\u0120logs", "merges": "\u0120log s", "raw_count": 91463, "count": 91463, "decode_str": " logs"} -{"id": 8268, "token": "\u0120exceed", "merges": "\u0120ex ceed", "raw_count": 31593, "count": 91470, "decode_str": " exceed"} -{"id": 21793, "token": "PIN", "merges": "P IN", "raw_count": 91472, "count": 91472, "decode_str": "PIN"} -{"id": 28411, "token": "\u0120reiter", "merges": "\u0120re iter", "raw_count": 55394, "count": 91489, "decode_str": " reiter"} -{"id": 17230, "token": "\u0120clip", "merges": "\u0120cl ip", "raw_count": 91489, "count": 91489, "decode_str": " clip"} -{"id": 52842, "token": "\u00e7\u0132\u0129", "merges": "\u00e7\u0132 \u0129", "raw_count": 91490, "count": 91490, "decode_str": "\u7407"} -{"id": 3531, "token": "\u0120turned", "merges": "\u0120turn ed", "raw_count": 91510, "count": 91510, "decode_str": " turned"} -{"id": 40324, "token": "started", "merges": "start ed", "raw_count": 91510, "count": 91510, "decode_str": "started"} -{"id": 2342, "token": "\u0120defend", "merges": "\u0120def end", "raw_count": 33625, "count": 91518, "decode_str": " defend"} -{"id": 49642, "token": "aaaaaaaa", "merges": "aaaa aaaa", "raw_count": 91522, "count": 91522, "decode_str": "aaaaaaaa"} -{"id": 10376, "token": "\u0120pursuant", "merges": "\u0120pursu ant", "raw_count": 91524, "count": 91524, "decode_str": " pursuant"} -{"id": 50170, "token": "Rain", "merges": "R ain", "raw_count": 91524, "count": 91524, "decode_str": "Rain"} -{"id": 7975, "token": "\u0120fold", "merges": "\u0120f old", "raw_count": 43977, "count": 91533, "decode_str": " fold"} -{"id": 22286, "token": "}),", "merges": "} ),", "raw_count": 91564, "count": 91564, "decode_str": "}),"} -{"id": 4757, "token": "\u0120strength", "merges": "\u0120streng th", "raw_count": 80335, "count": 91573, "decode_str": " strength"} -{"id": 10273, "token": "ande", "merges": "and e", "raw_count": 71851, "count": 91574, "decode_str": "ande"} -{"id": 1680, "token": "\u0120Is", "merges": "\u0120I s", "raw_count": 78145, "count": 91582, "decode_str": " Is"} -{"id": 8364, "token": "\u0120cards", "merges": "\u0120c ards", "raw_count": 91606, "count": 91606, "decode_str": " cards"} -{"id": 7361, "token": "\u0120ris", "merges": "\u0120r is", "raw_count": 6827, "count": 91614, "decode_str": " ris"} -{"id": 38246, "token": "guid", "merges": "gu id", "raw_count": 91627, "count": 91627, "decode_str": "guid"} -{"id": 6818, "token": "\u0120twenty", "merges": "\u0120tw enty", "raw_count": 91631, "count": 91631, "decode_str": " twenty"} -{"id": 7994, "token": "Vert", "merges": "V ert", "raw_count": 63265, "count": 91631, "decode_str": "Vert"} -{"id": 47871, "token": "745", "merges": "7 45", "raw_count": 91632, "count": 91632, "decode_str": "745"} -{"id": 20598, "token": "Old", "merges": "O ld", "raw_count": 91645, "count": 91645, "decode_str": "Old"} -{"id": 45675, "token": "\u0120sqlite", "merges": "\u0120sql ite", "raw_count": 91655, "count": 91655, "decode_str": " sqlite"} -{"id": 7236, "token": "\u0120fuel", "merges": "\u0120f uel", "raw_count": 89806, "count": 91665, "decode_str": " fuel"} -{"id": 16862, "token": "linked", "merges": "link ed", "raw_count": 91666, "count": 91666, "decode_str": "linked"} -{"id": 14366, "token": "\u0120ot", "merges": "\u0120o t", "raw_count": 88688, "count": 91672, "decode_str": " ot"} -{"id": 6619, "token": "\u0120relief", "merges": "\u0120rel ief", "raw_count": 91700, "count": 91700, "decode_str": " relief"} -{"id": 33343, "token": "iply", "merges": "ip ly", "raw_count": 80508, "count": 91724, "decode_str": "iply"} -{"id": 25292, "token": "BACK", "merges": "B ACK", "raw_count": 91737, "count": 91737, "decode_str": "BACK"} -{"id": 17233, "token": "Russ", "merges": "R uss", "raw_count": 75611, "count": 91754, "decode_str": "Russ"} -{"id": 14043, "token": "\u0120vulnerable", "merges": "\u0120vulner able", "raw_count": 91782, "count": 91782, "decode_str": " vulnerable"} -{"id": 12506, "token": "\u0120oh", "merges": "\u0120o h", "raw_count": 91821, "count": 91821, "decode_str": " oh"} -{"id": 32618, "token": "Joseph", "merges": "Jose ph", "raw_count": 91870, "count": 91870, "decode_str": "Joseph"} -{"id": 7085, "token": "\u0120hell", "merges": "\u0120he ll", "raw_count": 31977, "count": 91890, "decode_str": " hell"} -{"id": 31994, "token": "\u0120lookup", "merges": "\u0120look up", "raw_count": 91916, "count": 91916, "decode_str": " lookup"} -{"id": 19715, "token": "\u0120responsibilities", "merges": "\u0120respons ibilities", "raw_count": 91920, "count": 91920, "decode_str": " responsibilities"} -{"id": 29845, "token": "Chem", "merges": "C hem", "raw_count": 91932, "count": 91932, "decode_str": "Chem"} -{"id": 28749, "token": "Lead", "merges": "L ead", "raw_count": 91935, "count": 91935, "decode_str": "Lead"} -{"id": 13836, "token": "Inv", "merges": "In v", "raw_count": 73681, "count": 91935, "decode_str": "Inv"} -{"id": 6098, "token": ":**", "merges": ": **", "raw_count": 91939, "count": 91939, "decode_str": ":**"} -{"id": 46671, "token": "\u0120shuffle", "merges": "\u0120sh uffle", "raw_count": 92004, "count": 92004, "decode_str": " shuffle"} -{"id": 2026, "token": "}_{", "merges": "} _{", "raw_count": 90902, "count": 92006, "decode_str": "}_{"} -{"id": 30741, "token": "BUT", "merges": "B UT", "raw_count": 92021, "count": 92021, "decode_str": "BUT"} -{"id": 11586, "token": "United", "merges": "Un ited", "raw_count": 92035, "count": 92035, "decode_str": "United"} -{"id": 28716, "token": "ccc", "merges": "cc c", "raw_count": 92082, "count": 92082, "decode_str": "ccc"} -{"id": 7571, "token": "\u0120jurisdiction", "merges": "\u0120jurisd iction", "raw_count": 92083, "count": 92083, "decode_str": " jurisdiction"} -{"id": 39315, "token": "trunc", "merges": "tr unc", "raw_count": 92098, "count": 92098, "decode_str": "trunc"} -{"id": 23853, "token": "cro", "merges": "c ro", "raw_count": 79362, "count": 92098, "decode_str": "cro"} -{"id": 20419, "token": "generated", "merges": "gener ated", "raw_count": 92113, "count": 92113, "decode_str": "generated"} -{"id": 54293, "token": "\u00e9\u013a\u0129", "merges": "\u00e9\u013a \u0129", "raw_count": 92137, "count": 92137, "decode_str": "\u9607"} -{"id": 2938, "token": "\u0120flu", "merges": "\u0120fl u", "raw_count": 17558, "count": 92138, "decode_str": " flu"} -{"id": 48948, "token": "Asia", "merges": "As ia", "raw_count": 92182, "count": 92182, "decode_str": "Asia"} -{"id": 8960, "token": "iana", "merges": "ian a", "raw_count": 91622, "count": 92195, "decode_str": "iana"} -{"id": 16932, "token": "\u0120consolid", "merges": "\u0120cons olid", "raw_count": 33383, "count": 92201, "decode_str": " consolid"} -{"id": 3164, "token": "\u0120probably", "merges": "\u0120prob ably", "raw_count": 92232, "count": 92232, "decode_str": " probably"} -{"id": 8548, "token": "\u0120clients", "merges": "\u0120cl ients", "raw_count": 92236, "count": 92236, "decode_str": " clients"} -{"id": 22942, "token": "\u0120cd", "merges": "\u0120c d", "raw_count": 92237, "count": 92237, "decode_str": " cd"} -{"id": 40148, "token": "Img", "merges": "Im g", "raw_count": 92246, "count": 92246, "decode_str": "Img"} -{"id": 7191, "token": "\u0120Form", "merges": "\u0120F orm", "raw_count": 46231, "count": 92270, "decode_str": " Form"} -{"id": 49310, "token": "775", "merges": "7 75", "raw_count": 92279, "count": 92279, "decode_str": "775"} -{"id": 18401, "token": "Properties", "merges": "Pro perties", "raw_count": 92285, "count": 92285, "decode_str": "Properties"} -{"id": 5835, "token": "\u0120drugs", "merges": "\u0120drug s", "raw_count": 92339, "count": 92339, "decode_str": " drugs"} -{"id": 19433, "token": "ISE", "merges": "IS E", "raw_count": 70574, "count": 92354, "decode_str": "ISE"} -{"id": 7947, "token": "rior", "merges": "ri or", "raw_count": 21228, "count": 92392, "decode_str": "rior"} -{"id": 44713, "token": "ittest", "merges": "itt est", "raw_count": 92409, "count": 92409, "decode_str": "ittest"} -{"id": 9291, "token": "lymp", "merges": "ly mp", "raw_count": 60644, "count": 92412, "decode_str": "lymp"} -{"id": 14684, "token": "uction", "merges": "u ction", "raw_count": 28930, "count": 92449, "decode_str": "uction"} -{"id": 25040, "token": "\u0120informal", "merges": "\u0120inform al", "raw_count": 92464, "count": 92464, "decode_str": " informal"} -{"id": 29113, "token": "Vec", "merges": "V ec", "raw_count": 92470, "count": 92470, "decode_str": "Vec"} -{"id": 14997, "token": "\u0120tickets", "merges": "\u0120tick ets", "raw_count": 92477, "count": 92477, "decode_str": " tickets"} -{"id": 4488, "token": "opl", "merges": "op l", "raw_count": 67459, "count": 92478, "decode_str": "opl"} -{"id": 4131, "token": "\u0120morning", "merges": "\u0120mor ning", "raw_count": 92492, "count": 92492, "decode_str": " morning"} -{"id": 10179, "token": "cit", "merges": "c it", "raw_count": 81151, "count": 92502, "decode_str": "cit"} -{"id": 9817, "token": "Like", "merges": "L ike", "raw_count": 92510, "count": 92510, "decode_str": "Like"} -{"id": 25462, "token": "istered", "merges": "ist ered", "raw_count": 20043, "count": 92523, "decode_str": "istered"} -{"id": 49498, "token": "Sho", "merges": "S ho", "raw_count": 92531, "count": 92531, "decode_str": "Sho"} -{"id": 17526, "token": "\u0120Task", "merges": "\u0120T ask", "raw_count": 92588, "count": 92588, "decode_str": " Task"} -{"id": 26219, "token": "sever", "merges": "se ver", "raw_count": 44468, "count": 92596, "decode_str": "sever"} -{"id": 6164, "token": "\u0120anc", "merges": "\u0120an c", "raw_count": 13705, "count": 92598, "decode_str": " anc"} -{"id": 45935, "token": "pitch", "merges": "p itch", "raw_count": 92615, "count": 92615, "decode_str": "pitch"} -{"id": 25419, "token": "ITER", "merges": "IT ER", "raw_count": 89337, "count": 92687, "decode_str": "ITER"} -{"id": 15145, "token": "riends", "merges": "ri ends", "raw_count": 32110, "count": 92720, "decode_str": "riends"} -{"id": 13429, "token": "amer", "merges": "am er", "raw_count": 92760, "count": 92760, "decode_str": "amer"} -{"id": 25557, "token": "\u0120helper", "merges": "\u0120hel per", "raw_count": 92788, "count": 92788, "decode_str": " helper"} -{"id": 12970, "token": "\u0120override", "merges": "\u0120over ride", "raw_count": 92809, "count": 92809, "decode_str": " override"} -{"id": 6346, "token": "\u0120neighbor", "merges": "\u0120neigh bor", "raw_count": 61409, "count": 92814, "decode_str": " neighbor"} -{"id": 5217, "token": "\u0120equival", "merges": "\u0120equ ival", "raw_count": 2893, "count": 92822, "decode_str": " equival"} -{"id": 7545, "token": "iences", "merges": "ien ces", "raw_count": 50797, "count": 92840, "decode_str": "iences"} -{"id": 37956, "token": "Vi", "merges": "V i", "raw_count": 92911, "count": 92911, "decode_str": "Vi"} -{"id": 41968, "token": "ibo", "merges": "ib o", "raw_count": 92936, "count": 92936, "decode_str": "ibo"} -{"id": 7194, "token": "\u0120mainly", "merges": "\u0120main ly", "raw_count": 92941, "count": 92941, "decode_str": " mainly"} -{"id": 45019, "token": "recent", "merges": "re cent", "raw_count": 92966, "count": 92966, "decode_str": "recent"} -{"id": 2418, "token": "\u0120State", "merges": "\u0120St ate", "raw_count": 93010, "count": 93010, "decode_str": " State"} -{"id": 46488, "token": "tracks", "merges": "tr acks", "raw_count": 93019, "count": 93019, "decode_str": "tracks"} -{"id": 10796, "token": "\u0120multip", "merges": "\u0120mult ip", "raw_count": 51787, "count": 93043, "decode_str": " multip"} -{"id": 7829, "token": "\u0120courts", "merges": "\u0120court s", "raw_count": 93046, "count": 93046, "decode_str": " courts"} -{"id": 3406, "token": "rapy", "merges": "rap y", "raw_count": 55018, "count": 93046, "decode_str": "rapy"} -{"id": 15683, "token": "roc", "merges": "ro c", "raw_count": 77903, "count": 93074, "decode_str": "roc"} -{"id": 5956, "token": "\u0120comfort", "merges": "\u0120com fort", "raw_count": 43802, "count": 93119, "decode_str": " comfort"} -{"id": 7188, "token": "\u0120Ver", "merges": "\u0120V er", "raw_count": 92942, "count": 93148, "decode_str": " Ver"} -{"id": 31620, "token": "Cursor", "merges": "C ursor", "raw_count": 93171, "count": 93171, "decode_str": "Cursor"} -{"id": 5946, "token": "iat", "merges": "i at", "raw_count": 69492, "count": 93173, "decode_str": "iat"} -{"id": 6128, "token": "\u0120responses", "merges": "\u0120respons es", "raw_count": 93190, "count": 93190, "decode_str": " responses"} -{"id": 8796, "token": "\u0120purs", "merges": "\u0120pur s", "raw_count": 2831, "count": 93201, "decode_str": " purs"} -{"id": 28077, "token": "ARC", "merges": "AR C", "raw_count": 93209, "count": 93209, "decode_str": "ARC"} -{"id": 25247, "token": "ceil", "merges": "ce il", "raw_count": 93089, "count": 93232, "decode_str": "ceil"} -{"id": 4953, "token": "atur", "merges": "at ur", "raw_count": 53995, "count": 93238, "decode_str": "atur"} -{"id": 13331, "token": "\u0120Server", "merges": "\u0120Ser ver", "raw_count": 93248, "count": 93248, "decode_str": " Server"} -{"id": 14376, "token": "English", "merges": "Eng lish", "raw_count": 93257, "count": 93257, "decode_str": "English"} -{"id": 9172, "token": "\u0120answers", "merges": "\u0120answ ers", "raw_count": 93261, "count": 93261, "decode_str": " answers"} -{"id": 6132, "token": "\u0120election", "merges": "\u0120e lection", "raw_count": 93278, "count": 93278, "decode_str": " election"} -{"id": 8722, "token": "\u0120manage", "merges": "\u0120man age", "raw_count": 90417, "count": 93278, "decode_str": " manage"} -{"id": 30985, "token": "Setting", "merges": "Set ting", "raw_count": 93283, "count": 93283, "decode_str": "Setting"} -{"id": 26806, "token": "vertical", "merges": "vert ical", "raw_count": 93285, "count": 93285, "decode_str": "vertical"} -{"id": 23300, "token": "amaz", "merges": "am az", "raw_count": 25237, "count": 93288, "decode_str": "amaz"} -{"id": 6125, "token": "\u0120represents", "merges": "\u0120rep resents", "raw_count": 93315, "count": 93315, "decode_str": " represents"} -{"id": 20959, "token": "\u00ec\u013f\u00b4", "merges": "\u00ec\u013f \u00b4", "raw_count": 93320, "count": 93320, "decode_str": "\uc774"} -{"id": 8563, "token": "\u0120depos", "merges": "\u0120de pos", "raw_count": 14429, "count": 93322, "decode_str": " depos"} -{"id": 22026, "token": "ANY", "merges": "AN Y", "raw_count": 92222, "count": 93343, "decode_str": "ANY"} -{"id": 11282, "token": "adi", "merges": "ad i", "raw_count": 93347, "count": 93347, "decode_str": "adi"} -{"id": 5075, "token": "\u0120weak", "merges": "\u0120we ak", "raw_count": 67112, "count": 93363, "decode_str": " weak"} -{"id": 43838, "token": "motor", "merges": "m otor", "raw_count": 93398, "count": 93398, "decode_str": "motor"} -{"id": 6738, "token": "\u0120sho", "merges": "\u0120sh o", "raw_count": 10306, "count": 93422, "decode_str": " sho"} -{"id": 5195, "token": "\u0120spread", "merges": "\u0120sp read", "raw_count": 68637, "count": 93429, "decode_str": " spread"} -{"id": 23351, "token": "ubern", "merges": "ub ern", "raw_count": 2016, "count": 93432, "decode_str": "ubern"} -{"id": 10293, "token": "isition", "merges": "is ition", "raw_count": 8778, "count": 93437, "decode_str": "isition"} -{"id": 31940, "token": "\u0120vm", "merges": "\u0120v m", "raw_count": 93453, "count": 93453, "decode_str": " vm"} -{"id": 26949, "token": "\u0120territories", "merges": "\u0120territ ories", "raw_count": 93456, "count": 93456, "decode_str": " territories"} -{"id": 54594, "token": "\u00ef\u00bd\u0140", "merges": "\u00ef\u00bd \u0140", "raw_count": 93458, "count": 93458, "decode_str": "\uff5e"} -{"id": 5211, "token": "\u0120happy", "merges": "\u0120happ y", "raw_count": 93467, "count": 93467, "decode_str": " happy"} -{"id": 35866, "token": "853", "merges": "85 3", "raw_count": 93467, "count": 93467, "decode_str": "853"} -{"id": 6059, "token": "umin", "merges": "um in", "raw_count": 54867, "count": 93507, "decode_str": "umin"} -{"id": 21496, "token": "\u0120embedding", "merges": "\u0120embed ding", "raw_count": 93539, "count": 93539, "decode_str": " embedding"} -{"id": 16936, "token": "\u0120developments", "merges": "\u0120develop ments", "raw_count": 93560, "count": 93560, "decode_str": " developments"} -{"id": 46088, "token": "raid", "merges": "ra id", "raw_count": 93564, "count": 93564, "decode_str": "raid"} -{"id": 45392, "token": "Embed", "merges": "Emb ed", "raw_count": 93571, "count": 93571, "decode_str": "Embed"} -{"id": 16227, "token": "Photo", "merges": "Ph oto", "raw_count": 93573, "count": 93573, "decode_str": "Photo"} -{"id": 45047, "token": "domains", "merges": "dom ains", "raw_count": 93597, "count": 93597, "decode_str": "domains"} -{"id": 40531, "token": "Autom", "merges": "Aut om", "raw_count": 93626, "count": 93626, "decode_str": "Autom"} -{"id": 7367, "token": "\u0120orders", "merges": "\u0120ord ers", "raw_count": 93627, "count": 93627, "decode_str": " orders"} -{"id": 7942, "token": "\u0120cash", "merges": "\u0120c ash", "raw_count": 93629, "count": 93629, "decode_str": " cash"} -{"id": 20768, "token": "Est", "merges": "E st", "raw_count": 93636, "count": 93636, "decode_str": "Est"} -{"id": 42310, "token": "563", "merges": "56 3", "raw_count": 93685, "count": 93685, "decode_str": "563"} -{"id": 5337, "token": "ustr", "merges": "ust r", "raw_count": 58607, "count": 93716, "decode_str": "ustr"} -{"id": 25376, "token": "Clear", "merges": "Cle ar", "raw_count": 93721, "count": 93721, "decode_str": "Clear"} -{"id": 27256, "token": "generic", "merges": "gen eric", "raw_count": 93730, "count": 93730, "decode_str": "generic"} -{"id": 4054, "token": "\u0120ult", "merges": "\u0120 ult", "raw_count": 9574, "count": 93755, "decode_str": " ult"} -{"id": 9017, "token": "\u0120extend", "merges": "\u0120ext end", "raw_count": 93768, "count": 93768, "decode_str": " extend"} -{"id": 33080, "token": "chapter", "merges": "ch apter", "raw_count": 93784, "count": 93784, "decode_str": "chapter"} -{"id": 36379, "token": "dependencies", "merges": "depend encies", "raw_count": 93798, "count": 93798, "decode_str": "dependencies"} -{"id": 8779, "token": "inating", "merges": "in ating", "raw_count": 15385, "count": 93798, "decode_str": "inating"} -{"id": 11108, "token": "osity", "merges": "os ity", "raw_count": 86643, "count": 93806, "decode_str": "osity"} -{"id": 18170, "token": "Common", "merges": "Com mon", "raw_count": 93808, "count": 93808, "decode_str": "Common"} -{"id": 9407, "token": "\u0120asc", "merges": "\u0120as c", "raw_count": 51494, "count": 93809, "decode_str": " asc"} -{"id": 4353, "token": "void", "merges": "v oid", "raw_count": 81189, "count": 93830, "decode_str": "void"} -{"id": 20780, "token": "Timeout", "merges": "Time out", "raw_count": 93860, "count": 93860, "decode_str": "Timeout"} -{"id": 8281, "token": "\u0120river", "merges": "\u0120ri ver", "raw_count": 93866, "count": 93866, "decode_str": " river"} -{"id": 6240, "token": "\u0120adding", "merges": "\u0120add ing", "raw_count": 93878, "count": 93878, "decode_str": " adding"} -{"id": 16202, "token": "\u0120encoded", "merges": "\u0120enc oded", "raw_count": 93881, "count": 93881, "decode_str": " encoded"} -{"id": 5366, "token": "\u0120bab", "merges": "\u0120b ab", "raw_count": 23393, "count": 93904, "decode_str": " bab"} -{"id": 25727, "token": "Organ", "merges": "Or gan", "raw_count": 93911, "count": 93911, "decode_str": "Organ"} -{"id": 23096, "token": "avi", "merges": "av i", "raw_count": 93921, "count": 93921, "decode_str": "avi"} -{"id": 13598, "token": "\u0120occupied", "merges": "\u0120occup ied", "raw_count": 93987, "count": 93987, "decode_str": " occupied"} -{"id": 45830, "token": "\u0120ct", "merges": "\u0120c t", "raw_count": 94014, "count": 94014, "decode_str": " ct"} -{"id": 12337, "token": "\u0120elections", "merges": "\u0120ele ctions", "raw_count": 94019, "count": 94019, "decode_str": " elections"} -{"id": 54008, "token": "\u00e8\u00b7\u00b9", "merges": "\u00e8\u00b7 \u00b9", "raw_count": 94029, "count": 94029, "decode_str": "\u8df9"} -{"id": 25201, "token": "ORM", "merges": "OR M", "raw_count": 33128, "count": 94036, "decode_str": "ORM"} -{"id": 24989, "token": "KR", "merges": "K R", "raw_count": 94048, "count": 94048, "decode_str": "KR"} -{"id": 38200, "token": "Ryan", "merges": "R yan", "raw_count": 94071, "count": 94071, "decode_str": "Ryan"} -{"id": 1879, "token": "\u0120Fr", "merges": "\u0120F r", "raw_count": 14151, "count": 94106, "decode_str": " Fr"} -{"id": 7477, "token": "\u0120mine", "merges": "\u0120m ine", "raw_count": 94138, "count": 94138, "decode_str": " mine"} -{"id": 30736, "token": "corn", "merges": "c orn", "raw_count": 94139, "count": 94139, "decode_str": "corn"} -{"id": 35545, "token": "ravel", "merges": "ra vel", "raw_count": 91511, "count": 94141, "decode_str": "ravel"} -{"id": 4258, "token": "\u0120somet", "merges": "\u0120som et", "raw_count": 1468, "count": 94156, "decode_str": " somet"} -{"id": 40591, "token": "flo", "merges": "fl o", "raw_count": 94170, "count": 94170, "decode_str": "flo"} -{"id": 3926, "token": "\u0120dro", "merges": "\u0120d ro", "raw_count": 13162, "count": 94171, "decode_str": " dro"} -{"id": 25094, "token": "moment", "merges": "mom ent", "raw_count": 40261, "count": 94177, "decode_str": "moment"} -{"id": 15343, "token": "Bel", "merges": "B el", "raw_count": 87663, "count": 94179, "decode_str": "Bel"} -{"id": 28016, "token": "rapped", "merges": "ra pped", "raw_count": 94214, "count": 94214, "decode_str": "rapped"} -{"id": 7117, "token": "\u0120listed", "merges": "\u0120list ed", "raw_count": 94248, "count": 94248, "decode_str": " listed"} -{"id": 19421, "token": "\u0120git", "merges": "\u0120g it", "raw_count": 94262, "count": 94262, "decode_str": " git"} -{"id": 23067, "token": "Mass", "merges": "M ass", "raw_count": 94281, "count": 94281, "decode_str": "Mass"} -{"id": 25071, "token": "htm", "merges": "ht m", "raw_count": 94308, "count": 94308, "decode_str": "htm"} -{"id": 47049, "token": "cleanup", "merges": "clean up", "raw_count": 94314, "count": 94314, "decode_str": "cleanup"} -{"id": 18432, "token": "whe", "merges": "w he", "raw_count": 33114, "count": 94328, "decode_str": "whe"} -{"id": 4358, "token": "\u0120las", "merges": "\u0120l as", "raw_count": 48709, "count": 94335, "decode_str": " las"} -{"id": 51235, "token": "\u00e5\u0141\u0139", "merges": "\u00e5\u0141 \u0139", "raw_count": 94376, "count": 94376, "decode_str": "\u57d7"} -{"id": 39282, "token": "792", "merges": "79 2", "raw_count": 94378, "count": 94378, "decode_str": "792"} -{"id": 10769, "token": "associ", "merges": "ass oci", "raw_count": 68950, "count": 94392, "decode_str": "associ"} -{"id": 13252, "token": "ureau", "merges": "ure au", "raw_count": 18567, "count": 94425, "decode_str": "ureau"} -{"id": 9851, "token": "\u0120heads", "merges": "\u0120head s", "raw_count": 94428, "count": 94428, "decode_str": " heads"} -{"id": 30989, "token": "Zone", "merges": "Z one", "raw_count": 94428, "count": 94428, "decode_str": "Zone"} -{"id": 47537, "token": "attachment", "merges": "att achment", "raw_count": 94431, "count": 94431, "decode_str": "attachment"} -{"id": 11318, "token": "aland", "merges": "al and", "raw_count": 93134, "count": 94443, "decode_str": "aland"} -{"id": 40187, "token": "761", "merges": "76 1", "raw_count": 94447, "count": 94447, "decode_str": "761"} -{"id": 3644, "token": "\u0120dark", "merges": "\u0120d ark", "raw_count": 71581, "count": 94448, "decode_str": " dark"} -{"id": 15861, "token": "aco", "merges": "ac o", "raw_count": 94450, "count": 94450, "decode_str": "aco"} -{"id": 48344, "token": "\u0120':", "merges": "\u0120' :", "raw_count": 94461, "count": 94461, "decode_str": " ':"} -{"id": 10464, "token": "\u0120bat", "merges": "\u0120b at", "raw_count": 55948, "count": 94503, "decode_str": " bat"} -{"id": 6105, "token": "\u0120church", "merges": "\u0120ch urch", "raw_count": 94510, "count": 94510, "decode_str": " church"} -{"id": 40305, "token": "zhou", "merges": "z hou", "raw_count": 94555, "count": 94555, "decode_str": "zhou"} -{"id": 6169, "token": "ville", "merges": "v ille", "raw_count": 94314, "count": 94567, "decode_str": "ville"} -{"id": 4030, "token": "\u0120fine", "merges": "\u0120f ine", "raw_count": 94605, "count": 94605, "decode_str": " fine"} -{"id": 7212, "token": "\u0120formula", "merges": "\u0120form ula", "raw_count": 94655, "count": 94655, "decode_str": " formula"} -{"id": 21785, "token": "~/", "merges": "~ /", "raw_count": 94696, "count": 94696, "decode_str": "~/"} -{"id": 42536, "token": "vehicle", "merges": "veh icle", "raw_count": 94711, "count": 94711, "decode_str": "vehicle"} -{"id": 13618, "token": "God", "merges": "G od", "raw_count": 94724, "count": 94724, "decode_str": "God"} -{"id": 18367, "token": "dz", "merges": "d z", "raw_count": 94725, "count": 94725, "decode_str": "dz"} -{"id": 39687, "token": "1008", "merges": "100 8", "raw_count": 94739, "count": 94739, "decode_str": "1008"} -{"id": 25449, "token": "asper", "merges": "as per", "raw_count": 94762, "count": 94762, "decode_str": "asper"} -{"id": 11457, "token": "ibration", "merges": "ib ration", "raw_count": 54148, "count": 94769, "decode_str": "ibration"} -{"id": 9071, "token": "\u0120flo", "merges": "\u0120fl o", "raw_count": 7221, "count": 94785, "decode_str": " flo"} -{"id": 29076, "token": "letters", "merges": "let ters", "raw_count": 90810, "count": 94814, "decode_str": "letters"} -{"id": 19712, "token": "?_", "merges": "? _", "raw_count": 94814, "count": 94814, "decode_str": "?_"} -{"id": 20805, "token": "(:", "merges": "( :", "raw_count": 94814, "count": 94814, "decode_str": "(:"} -{"id": 27198, "token": "umi", "merges": "um i", "raw_count": 94847, "count": 94847, "decode_str": "umi"} -{"id": 7137, "token": "\u0120traffic", "merges": "\u0120tra ffic", "raw_count": 94893, "count": 94893, "decode_str": " traffic"} -{"id": 26094, "token": "assets", "merges": "ass ets", "raw_count": 94902, "count": 94902, "decode_str": "assets"} -{"id": 54547, "token": "\u00e8\u00b2\u012b", "merges": "\u00e8\u00b2 \u012b", "raw_count": 94911, "count": 94911, "decode_str": "\u8c89"} -{"id": 34059, "token": "Wave", "merges": "W ave", "raw_count": 94923, "count": 94923, "decode_str": "Wave"} -{"id": 44034, "token": "714", "merges": "7 14", "raw_count": 94938, "count": 94938, "decode_str": "714"} -{"id": 40545, "token": "listing", "merges": "list ing", "raw_count": 94962, "count": 94962, "decode_str": "listing"} -{"id": 10666, "token": "ethe", "merges": "et he", "raw_count": 58596, "count": 94974, "decode_str": "ethe"} -{"id": 15826, "token": "\u0120bg", "merges": "\u0120b g", "raw_count": 90029, "count": 95007, "decode_str": " bg"} -{"id": 17116, "token": "\u0120INTO", "merges": "\u0120IN TO", "raw_count": 95055, "count": 95055, "decode_str": " INTO"} -{"id": 45997, "token": "sequences", "merges": "sequ ences", "raw_count": 95072, "count": 95072, "decode_str": "sequences"} -{"id": 5389, "token": "\u0120beautiful", "merges": "\u0120beaut iful", "raw_count": 88544, "count": 95077, "decode_str": " beautiful"} -{"id": 5191, "token": "ingu", "merges": "ing u", "raw_count": 23409, "count": 95091, "decode_str": "ingu"} -{"id": 20293, "token": "WO", "merges": "W O", "raw_count": 92016, "count": 95097, "decode_str": "WO"} -{"id": 48658, "token": "Mess", "merges": "M ess", "raw_count": 95114, "count": 95114, "decode_str": "Mess"} -{"id": 9676, "token": "\u0120illegal", "merges": "\u0120il legal", "raw_count": 95134, "count": 95134, "decode_str": " illegal"} -{"id": 5093, "token": "\u0120seven", "merges": "\u0120se ven", "raw_count": 95149, "count": 95149, "decode_str": " seven"} -{"id": 3786, "token": "\u0120previously", "merges": "\u0120previous ly", "raw_count": 95151, "count": 95151, "decode_str": " previously"} -{"id": 5882, "token": "\u0120firm", "merges": "\u0120f irm", "raw_count": 58481, "count": 95151, "decode_str": " firm"} -{"id": 5817, "token": "\u00e2\u0122\u00a2", "merges": "\u00e2\u0122 \u00a2", "raw_count": 95168, "count": 95168, "decode_str": "\u2022"} -{"id": 21955, "token": "ancer", "merges": "an cer", "raw_count": 93939, "count": 95200, "decode_str": "ancer"} -{"id": 22402, "token": "issues", "merges": "iss ues", "raw_count": 95206, "count": 95206, "decode_str": "issues"} -{"id": 48463, "token": "838", "merges": "8 38", "raw_count": 95224, "count": 95224, "decode_str": "838"} -{"id": 41386, "token": "shi", "merges": "sh i", "raw_count": 95227, "count": 95227, "decode_str": "shi"} -{"id": 43539, "token": "Ip", "merges": "I p", "raw_count": 95237, "count": 95237, "decode_str": "Ip"} -{"id": 32655, "token": "Fred", "merges": "F red", "raw_count": 95244, "count": 95244, "decode_str": "Fred"} -{"id": 43677, "token": "deck", "merges": "de ck", "raw_count": 95247, "count": 95247, "decode_str": "deck"} -{"id": 24013, "token": "mot", "merges": "m ot", "raw_count": 95258, "count": 95258, "decode_str": "mot"} -{"id": 19589, "token": "Person", "merges": "P erson", "raw_count": 95294, "count": 95294, "decode_str": "Person"} -{"id": 30138, "token": "Son", "merges": "S on", "raw_count": 95320, "count": 95320, "decode_str": "Son"} -{"id": 39892, "token": "leader", "merges": "le ader", "raw_count": 95321, "count": 95321, "decode_str": "leader"} -{"id": 5149, "token": "\u0120wave", "merges": "\u0120w ave", "raw_count": 80500, "count": 95355, "decode_str": " wave"} -{"id": 11186, "token": "\u0120northern", "merges": "\u0120n orthern", "raw_count": 95360, "count": 95360, "decode_str": " northern"} -{"id": 29537, "token": "RUN", "merges": "R UN", "raw_count": 95385, "count": 95385, "decode_str": "RUN"} -{"id": 21616, "token": "business", "merges": "b usiness", "raw_count": 95391, "count": 95391, "decode_str": "business"} -{"id": 52333, "token": "\u00e6\u00a3\u00b9", "merges": "\u00e6\u00a3 \u00b9", "raw_count": 95456, "count": 95456, "decode_str": "\u68f9"} -{"id": 32447, "token": "\u0120enterprises", "merges": "\u0120enter prises", "raw_count": 95507, "count": 95507, "decode_str": " enterprises"} -{"id": 32192, "token": "Machine", "merges": "M achine", "raw_count": 95514, "count": 95514, "decode_str": "Machine"} -{"id": 46420, "token": "\u0120yaml", "merges": "\u0120y aml", "raw_count": 95552, "count": 95552, "decode_str": " yaml"} -{"id": 9183, "token": "\u0120candidates", "merges": "\u0120candid ates", "raw_count": 95554, "count": 95554, "decode_str": " candidates"} -{"id": 2029, "token": "=\\", "merges": "= \\", "raw_count": 44989, "count": 95593, "decode_str": "=\\"} -{"id": 16330, "token": "Pers", "merges": "P ers", "raw_count": 61013, "count": 95615, "decode_str": "Pers"} -{"id": 9023, "token": "\u0120promise", "merges": "\u0120prom ise", "raw_count": 95626, "count": 95626, "decode_str": " promise"} -{"id": 5998, "token": "\u0120estimated", "merges": "\u0120estim ated", "raw_count": 95628, "count": 95628, "decode_str": " estimated"} -{"id": 48224, "token": "812", "merges": "8 12", "raw_count": 95655, "count": 95655, "decode_str": "812"} -{"id": 14206, "token": "/.", "merges": "/ .", "raw_count": 95665, "count": 95665, "decode_str": "/."} -{"id": 45100, "token": "corr", "merges": "cor r", "raw_count": 95669, "count": 95669, "decode_str": "corr"} -{"id": 53169, "token": "\u00e7\u00a8\u0139", "merges": "\u00e7\u00a8 \u0139", "raw_count": 95682, "count": 95682, "decode_str": "\u7a17"} -{"id": 5866, "token": "\u0120occurred", "merges": "\u0120occur red", "raw_count": 95690, "count": 95690, "decode_str": " occurred"} -{"id": 8474, "token": "\u0120senior", "merges": "\u0120sen ior", "raw_count": 95711, "count": 95711, "decode_str": " senior"} -{"id": 45897, "token": "STAR", "merges": "ST AR", "raw_count": 95718, "count": 95718, "decode_str": "STAR"} -{"id": 7269, "token": "\u0120advanced", "merges": "\u0120adv anced", "raw_count": 95720, "count": 95720, "decode_str": " advanced"} -{"id": 18043, "token": "jack", "merges": "j ack", "raw_count": 87332, "count": 95738, "decode_str": "jack"} -{"id": 13719, "token": "\u0120fifty", "merges": "\u0120fif ty", "raw_count": 95746, "count": 95746, "decode_str": " fifty"} -{"id": 12228, "token": "\u0120volunt", "merges": "\u0120vol unt", "raw_count": 647, "count": 95786, "decode_str": " volunt"} -{"id": 20350, "token": "IPT", "merges": "IP T", "raw_count": 21281, "count": 95798, "decode_str": "IPT"} -{"id": 11742, "token": "\u0120processed", "merges": "\u0120process ed", "raw_count": 95818, "count": 95818, "decode_str": " processed"} -{"id": 9550, "token": "\u0120leadership", "merges": "\u0120lead ership", "raw_count": 95830, "count": 95830, "decode_str": " leadership"} -{"id": 12076, "token": "onical", "merges": "on ical", "raw_count": 15288, "count": 95832, "decode_str": "onical"} -{"id": 27597, "token": "AMS", "merges": "AM S", "raw_count": 95834, "count": 95834, "decode_str": "AMS"} -{"id": 30730, "token": "locked", "merges": "lock ed", "raw_count": 95841, "count": 95841, "decode_str": "locked"} -{"id": 12710, "token": "made", "merges": "m ade", "raw_count": 95861, "count": 95861, "decode_str": "made"} -{"id": 22560, "token": "aky", "merges": "ak y", "raw_count": 95862, "count": 95862, "decode_str": "aky"} -{"id": 5139, "token": "\u0120je", "merges": "\u0120j e", "raw_count": 70678, "count": 95872, "decode_str": " je"} -{"id": 3133, "token": "\u0120seems", "merges": "\u0120seem s", "raw_count": 95903, "count": 95903, "decode_str": " seems"} -{"id": 32170, "token": "Virtual", "merges": "V irtual", "raw_count": 95909, "count": 95909, "decode_str": "Virtual"} -{"id": 9114, "token": "lie", "merges": "l ie", "raw_count": 91093, "count": 95938, "decode_str": "lie"} -{"id": 11911, "token": "\u0120modules", "merges": "\u0120mod ules", "raw_count": 95944, "count": 95944, "decode_str": " modules"} -{"id": 25174, "token": "Services", "merges": "Serv ices", "raw_count": 95970, "count": 95970, "decode_str": "Services"} -{"id": 33730, "token": "562", "merges": "56 2", "raw_count": 95974, "count": 95974, "decode_str": "562"} -{"id": 9393, "token": "ifer", "merges": "if er", "raw_count": 94721, "count": 95991, "decode_str": "ifer"} -{"id": 10061, "token": "\u0120proceedings", "merges": "\u0120proceed ings", "raw_count": 95992, "count": 95992, "decode_str": " proceedings"} -{"id": 27547, "token": "Attr", "merges": "At tr", "raw_count": 96006, "count": 96006, "decode_str": "Attr"} -{"id": 11523, "token": "sex", "merges": "se x", "raw_count": 92435, "count": 96014, "decode_str": "sex"} -{"id": 17352, "token": "between", "merges": "bet ween", "raw_count": 96027, "count": 96027, "decode_str": "between"} -{"id": 41605, "token": ")...", "merges": "). ..", "raw_count": 96039, "count": 96039, "decode_str": ")..."} -{"id": 4145, "token": "\u0120OR", "merges": "\u0120O R", "raw_count": 66320, "count": 96090, "decode_str": " OR"} -{"id": 25213, "token": "\u0120welcomed", "merges": "\u0120wel comed", "raw_count": 96113, "count": 96113, "decode_str": " welcomed"} -{"id": 12856, "token": "hom", "merges": "h om", "raw_count": 95438, "count": 96140, "decode_str": "hom"} -{"id": 11985, "token": "\u0120discussions", "merges": "\u0120discuss ions", "raw_count": 96152, "count": 96152, "decode_str": " discussions"} -{"id": 19634, "token": "032", "merges": "0 32", "raw_count": 96164, "count": 96164, "decode_str": "032"} -{"id": 4197, "token": "\u0120produced", "merges": "\u0120produ ced", "raw_count": 96174, "count": 96174, "decode_str": " produced"} -{"id": 15413, "token": "Has", "merges": "H as", "raw_count": 96201, "count": 96201, "decode_str": "Has"} -{"id": 50246, "token": "767", "merges": "7 67", "raw_count": 96230, "count": 96230, "decode_str": "767"} -{"id": 12612, "token": "Section", "merges": "S ection", "raw_count": 96241, "count": 96241, "decode_str": "Section"} -{"id": 33424, "token": "WB", "merges": "W B", "raw_count": 96243, "count": 96243, "decode_str": "WB"} -{"id": 31953, "token": "baz", "merges": "b az", "raw_count": 96245, "count": 96245, "decode_str": "baz"} -{"id": 9794, "token": "---------", "merges": "-------- -", "raw_count": 58362, "count": 96246, "decode_str": "---------"} -{"id": 4245, "token": "\u0120gives", "merges": "\u0120giv es", "raw_count": 96254, "count": 96254, "decode_str": " gives"} -{"id": 6171, "token": "\u0120employees", "merges": "\u0120employ ees", "raw_count": 96279, "count": 96279, "decode_str": " employees"} -{"id": 5912, "token": "\u0120probability", "merges": "\u0120prob ability", "raw_count": 96310, "count": 96310, "decode_str": " probability"} -{"id": 26380, "token": "placement", "merges": "pl acement", "raw_count": 96346, "count": 96346, "decode_str": "placement"} -{"id": 6843, "token": "\u0120explicit", "merges": "\u0120expl icit", "raw_count": 42084, "count": 96360, "decode_str": " explicit"} -{"id": 19206, "token": "Import", "merges": "Im port", "raw_count": 96368, "count": 96368, "decode_str": "Import"} -{"id": 8000, "token": "\u0120accel", "merges": "\u0120acc el", "raw_count": 7813, "count": 96375, "decode_str": " accel"} -{"id": 34255, "token": "Qual", "merges": "Q ual", "raw_count": 96375, "count": 96375, "decode_str": "Qual"} -{"id": 41475, "token": "\u0120uri", "merges": "\u0120ur i", "raw_count": 96417, "count": 96417, "decode_str": " uri"} -{"id": 16249, "token": "rock", "merges": "ro ck", "raw_count": 96428, "count": 96428, "decode_str": "rock"} -{"id": 51176, "token": "\u00e5\u013e\u0126", "merges": "\u00e5\u013e \u0126", "raw_count": 96446, "count": 96446, "decode_str": "\u5704"} -{"id": 24375, "token": "VIS", "merges": "V IS", "raw_count": 96297, "count": 96457, "decode_str": "VIS"} -{"id": 5159, "token": "\u0120kill", "merges": "\u0120k ill", "raw_count": 75241, "count": 96485, "decode_str": " kill"} -{"id": 25718, "token": "abulary", "merges": "abul ary", "raw_count": 59123, "count": 96498, "decode_str": "abulary"} -{"id": 22113, "token": "Package", "merges": "P ackage", "raw_count": 96514, "count": 96514, "decode_str": "Package"} -{"id": 13871, "token": "strap", "merges": "st rap", "raw_count": 22151, "count": 96528, "decode_str": "strap"} -{"id": 11270, "token": "\u0120Comput", "merges": "\u0120Com put", "raw_count": 10782, "count": 96557, "decode_str": " Comput"} -{"id": 28830, "token": "Fort", "merges": "F ort", "raw_count": 96557, "count": 96557, "decode_str": "Fort"} -{"id": 15417, "token": "variant", "merges": "v ariant", "raw_count": 96562, "count": 96562, "decode_str": "variant"} -{"id": 19873, "token": "ADD", "merges": "AD D", "raw_count": 96565, "count": 96565, "decode_str": "ADD"} -{"id": 35119, "token": "Brian", "merges": "B rian", "raw_count": 96575, "count": 96575, "decode_str": "Brian"} -{"id": 30000, "token": "Admin", "merges": "Ad min", "raw_count": 96595, "count": 96595, "decode_str": "Admin"} -{"id": 45552, "token": "deploy", "merges": "de ploy", "raw_count": 96598, "count": 96598, "decode_str": "deploy"} -{"id": 9052, "token": "\u0120Ext", "merges": "\u0120E xt", "raw_count": 30259, "count": 96619, "decode_str": " Ext"} -{"id": 13586, "token": "\u0120tar", "merges": "\u0120t ar", "raw_count": 74714, "count": 96619, "decode_str": " tar"} -{"id": 48902, "token": "\u0120\",\"", "merges": "\u0120\" ,\"", "raw_count": 96620, "count": 96620, "decode_str": " \",\""} -{"id": 48713, "token": "AO", "merges": "A O", "raw_count": 96659, "count": 96659, "decode_str": "AO"} -{"id": 2434, "token": "\u0120Co", "merges": "\u0120C o", "raw_count": 63439, "count": 96666, "decode_str": " Co"} -{"id": 23372, "token": "Attributes", "merges": "Att ributes", "raw_count": 96728, "count": 96728, "decode_str": "Attributes"} -{"id": 14906, "token": "lee", "merges": "le e", "raw_count": 96738, "count": 96738, "decode_str": "lee"} -{"id": 34725, "token": "\u0120Variable", "merges": "\u0120V ariable", "raw_count": 96739, "count": 96739, "decode_str": " Variable"} -{"id": 3413, "token": "\u0120determined", "merges": "\u0120determ ined", "raw_count": 96749, "count": 96749, "decode_str": " determined"} -{"id": 15567, "token": "\u0120123", "merges": "\u012012 3", "raw_count": 96757, "count": 96757, "decode_str": " 123"} -{"id": 4250, "token": "\u0120heat", "merges": "\u0120he at", "raw_count": 96794, "count": 96794, "decode_str": " heat"} -{"id": 46639, "token": "866", "merges": "8 66", "raw_count": 96809, "count": 96809, "decode_str": "866"} -{"id": 7882, "token": "\u0120stability", "merges": "\u0120st ability", "raw_count": 96824, "count": 96824, "decode_str": " stability"} -{"id": 44281, "token": "refs", "merges": "ref s", "raw_count": 96829, "count": 96829, "decode_str": "refs"} -{"id": 17047, "token": "ORK", "merges": "OR K", "raw_count": 9796, "count": 96850, "decode_str": "ORK"} -{"id": 5966, "token": "\u0120entered", "merges": "\u0120ent ered", "raw_count": 96877, "count": 96877, "decode_str": " entered"} -{"id": 51172, "token": "\u00e5\u013d\u00b9", "merges": "\u00e5\u013d \u00b9", "raw_count": 96879, "count": 96879, "decode_str": "\u56f9"} -{"id": 52567, "token": "\u00e6\u00b4\u00b9", "merges": "\u00e6\u00b4 \u00b9", "raw_count": 96896, "count": 96896, "decode_str": "\u6d39"} -{"id": 34967, "token": "Mit", "merges": "M it", "raw_count": 96912, "count": 96912, "decode_str": "Mit"} -{"id": 13412, "token": "itzer", "merges": "itz er", "raw_count": 27624, "count": 96931, "decode_str": "itzer"} -{"id": 3839, "token": "\u0120generally", "merges": "\u0120gener ally", "raw_count": 96938, "count": 96938, "decode_str": " generally"} -{"id": 9056, "token": "\u0120respective", "merges": "\u0120respect ive", "raw_count": 96946, "count": 96946, "decode_str": " respective"} -{"id": 10592, "token": "ILL", "merges": "I LL", "raw_count": 93438, "count": 96950, "decode_str": "ILL"} -{"id": 6135, "token": "\u0120doll", "merges": "\u0120d oll", "raw_count": 6757, "count": 96957, "decode_str": " doll"} -{"id": 44745, "token": "\u0120%.", "merges": "\u0120% .", "raw_count": 96978, "count": 96978, "decode_str": " %."} -{"id": 34307, "token": "994", "merges": "99 4", "raw_count": 96981, "count": 96981, "decode_str": "994"} -{"id": 23971, "token": "\u0120priorities", "merges": "\u0120prior ities", "raw_count": 96983, "count": 96983, "decode_str": " priorities"} -{"id": 11302, "token": "\u0120vertex", "merges": "\u0120ver tex", "raw_count": 97004, "count": 97004, "decode_str": " vertex"} -{"id": 11907, "token": "\u0120encourage", "merges": "\u0120encour age", "raw_count": 97024, "count": 97024, "decode_str": " encourage"} -{"id": 30470, "token": "\u0120defaults", "merges": "\u0120default s", "raw_count": 97036, "count": 97036, "decode_str": " defaults"} -{"id": 47225, "token": "729", "merges": "7 29", "raw_count": 97043, "count": 97043, "decode_str": "729"} -{"id": 45794, "token": "boundary", "merges": "bound ary", "raw_count": 97064, "count": 97064, "decode_str": "boundary"} -{"id": 35537, "token": "874", "merges": "87 4", "raw_count": 97071, "count": 97071, "decode_str": "874"} -{"id": 7179, "token": "\u00d0\u00bf", "merges": "\u00d0 \u00bf", "raw_count": 47316, "count": 97087, "decode_str": "\u043f"} -{"id": 28774, "token": "\u00ec\u0140", "merges": "\u00ec \u0140", "raw_count": 97087, "count": 97087, "decode_str": "\ufffd"} -{"id": 53636, "token": "\u00e8\u012d\u0126", "merges": "\u00e8\u012d \u0126", "raw_count": 97091, "count": 97091, "decode_str": "\u82c4"} -{"id": 25215, "token": "\u0120cc", "merges": "\u0120c c", "raw_count": 97108, "count": 97108, "decode_str": " cc"} -{"id": 48492, "token": "\u0120pkg", "merges": "\u0120p kg", "raw_count": 97110, "count": 97110, "decode_str": " pkg"} -{"id": 16902, "token": "ORS", "merges": "OR S", "raw_count": 97024, "count": 97125, "decode_str": "ORS"} -{"id": 8544, "token": "\u0120army", "merges": "\u0120ar my", "raw_count": 97135, "count": 97135, "decode_str": " army"} -{"id": 3617, "token": "\u0120Go", "merges": "\u0120G o", "raw_count": 46819, "count": 97149, "decode_str": " Go"} -{"id": 42681, "token": "cipher", "merges": "c ipher", "raw_count": 97169, "count": 97169, "decode_str": "cipher"} -{"id": 17423, "token": "USE", "merges": "U SE", "raw_count": 97171, "count": 97171, "decode_str": "USE"} -{"id": 24798, "token": "WARN", "merges": "W ARN", "raw_count": 17544, "count": 97179, "decode_str": "WARN"} -{"id": 36945, "token": "Simon", "merges": "Sim on", "raw_count": 97201, "count": 97201, "decode_str": "Simon"} -{"id": 39104, "token": "Nik", "merges": "N ik", "raw_count": 97213, "count": 97213, "decode_str": "Nik"} -{"id": 21731, "token": "\u0120civilian", "merges": "\u0120civil ian", "raw_count": 97237, "count": 97237, "decode_str": " civilian"} -{"id": 6508, "token": "\u0120extended", "merges": "\u0120ext ended", "raw_count": 97271, "count": 97271, "decode_str": " extended"} -{"id": 22501, "token": "+-", "merges": "+ -", "raw_count": 89361, "count": 97287, "decode_str": "+-"} -{"id": 34726, "token": "patcher", "merges": "pat cher", "raw_count": 83172, "count": 97295, "decode_str": "patcher"} -{"id": 31515, "token": "Sand", "merges": "S and", "raw_count": 97305, "count": 97305, "decode_str": "Sand"} -{"id": 33140, "token": "orical", "merges": "or ical", "raw_count": 97331, "count": 97331, "decode_str": "orical"} -{"id": 52369, "token": "\u00e6\u00a8\u00af", "merges": "\u00e6\u00a8 \u00af", "raw_count": 97353, "count": 97353, "decode_str": "\u6a2f"} -{"id": 9746, "token": "ilib", "merges": "il ib", "raw_count": 77207, "count": 97382, "decode_str": "ilib"} -{"id": 6143, "token": "apers", "merges": "ap ers", "raw_count": 12384, "count": 97399, "decode_str": "apers"} -{"id": 17662, "token": "inda", "merges": "ind a", "raw_count": 96273, "count": 97399, "decode_str": "inda"} -{"id": 25290, "token": "\u0120fs", "merges": "\u0120f s", "raw_count": 97413, "count": 97413, "decode_str": " fs"} -{"id": 3212, "token": "\u0120behind", "merges": "\u0120beh ind", "raw_count": 97416, "count": 97416, "decode_str": " behind"} -{"id": 35832, "token": "Ak", "merges": "A k", "raw_count": 97426, "count": 97426, "decode_str": "Ak"} -{"id": 40263, "token": "6666", "merges": "66 66", "raw_count": 97432, "count": 97432, "decode_str": "6666"} -{"id": 13919, "token": "\u0120equality", "merges": "\u0120equ ality", "raw_count": 97500, "count": 97500, "decode_str": " equality"} -{"id": 33752, "token": "GPIO", "merges": "GP IO", "raw_count": 97503, "count": 97503, "decode_str": "GPIO"} -{"id": 4318, "token": "\u0120voice", "merges": "\u0120vo ice", "raw_count": 97515, "count": 97515, "decode_str": " voice"} -{"id": 16147, "token": "rans", "merges": "r ans", "raw_count": 90258, "count": 97570, "decode_str": "rans"} -{"id": 7002, "token": "\u0120fourth", "merges": "\u0120four th", "raw_count": 97577, "count": 97577, "decode_str": " fourth"} -{"id": 7526, "token": "anning", "merges": "an ning", "raw_count": 64377, "count": 97580, "decode_str": "anning"} -{"id": 9875, "token": "scape", "merges": "sc ape", "raw_count": 72497, "count": 97611, "decode_str": "scape"} -{"id": 3130, "token": "\u0120Pol", "merges": "\u0120P ol", "raw_count": 41622, "count": 97628, "decode_str": " Pol"} -{"id": 27543, "token": "Brown", "merges": "B rown", "raw_count": 97631, "count": 97631, "decode_str": "Brown"} -{"id": 43262, "token": "JK", "merges": "J K", "raw_count": 97636, "count": 97636, "decode_str": "JK"} -{"id": 32475, "token": "Buck", "merges": "B uck", "raw_count": 34584, "count": 97638, "decode_str": "Buck"} -{"id": 40377, "token": "\u0120txt", "merges": "\u0120t xt", "raw_count": 97656, "count": 97656, "decode_str": " txt"} -{"id": 46703, "token": "pause", "merges": "p ause", "raw_count": 97688, "count": 97688, "decode_str": "pause"} -{"id": 34395, "token": "Cart", "merges": "C art", "raw_count": 97725, "count": 97725, "decode_str": "Cart"} -{"id": 7431, "token": "\u0120candidate", "merges": "\u0120candid ate", "raw_count": 97752, "count": 97752, "decode_str": " candidate"} -{"id": 11192, "token": "opes", "merges": "op es", "raw_count": 88944, "count": 97752, "decode_str": "opes"} -{"id": 8874, "token": "\u0120Acc", "merges": "\u0120A cc", "raw_count": 36097, "count": 97752, "decode_str": " Acc"} -{"id": 43581, "token": "591", "merges": "59 1", "raw_count": 97758, "count": 97758, "decode_str": "591"} -{"id": 4863, "token": "oses", "merges": "os es", "raw_count": 76869, "count": 97764, "decode_str": "oses"} -{"id": 20769, "token": "ABA", "merges": "AB A", "raw_count": 97049, "count": 97794, "decode_str": "ABA"} -{"id": 15527, "token": "\u0120VAL", "merges": "\u0120V AL", "raw_count": 25935, "count": 97799, "decode_str": " VAL"} -{"id": 11415, "token": "awa", "merges": "aw a", "raw_count": 89235, "count": 97801, "decode_str": "awa"} -{"id": 5865, "token": "\u0120digital", "merges": "\u0120dig ital", "raw_count": 97808, "count": 97808, "decode_str": " digital"} -{"id": 44566, "token": "624", "merges": "6 24", "raw_count": 97812, "count": 97812, "decode_str": "624"} -{"id": 37525, "token": "jin", "merges": "j in", "raw_count": 97818, "count": 97818, "decode_str": "jin"} -{"id": 29849, "token": "Stats", "merges": "St ats", "raw_count": 97821, "count": 97821, "decode_str": "Stats"} -{"id": 49600, "token": "Brand", "merges": "Br and", "raw_count": 97825, "count": 97825, "decode_str": "Brand"} -{"id": 23798, "token": "bond", "merges": "b ond", "raw_count": 97830, "count": 97830, "decode_str": "bond"} -{"id": 35419, "token": "Victor", "merges": "V ictor", "raw_count": 97835, "count": 97835, "decode_str": "Victor"} -{"id": 45908, "token": "consumer", "merges": "consum er", "raw_count": 97840, "count": 97840, "decode_str": "consumer"} -{"id": 12697, "token": "History", "merges": "H istory", "raw_count": 97846, "count": 97846, "decode_str": "History"} -{"id": 32049, "token": "\u0120encoder", "merges": "\u0120enc oder", "raw_count": 97852, "count": 97852, "decode_str": " encoder"} -{"id": 6805, "token": "\u0120architect", "merges": "\u0120arch itect", "raw_count": 9783, "count": 97857, "decode_str": " architect"} -{"id": 46830, "token": "manifest", "merges": "manif est", "raw_count": 97872, "count": 97872, "decode_str": "manifest"} -{"id": 5908, "token": "\u0120officer", "merges": "\u0120offic er", "raw_count": 97884, "count": 97884, "decode_str": " officer"} -{"id": 48379, "token": "716", "merges": "7 16", "raw_count": 97890, "count": 97890, "decode_str": "716"} -{"id": 33298, "token": "Happy", "merges": "H appy", "raw_count": 97903, "count": 97903, "decode_str": "Happy"} -{"id": 14103, "token": "far", "merges": "f ar", "raw_count": 87126, "count": 97919, "decode_str": "far"} -{"id": 16130, "token": "ez", "merges": "e z", "raw_count": 97952, "count": 97952, "decode_str": "ez"} -{"id": 39677, "token": "1301", "merges": "13 01", "raw_count": 97978, "count": 97978, "decode_str": "1301"} -{"id": 52228, "token": "\u00e6\u013f\u00bc", "merges": "\u00e6\u013f \u00bc", "raw_count": 97984, "count": 97984, "decode_str": "\u677c"} -{"id": 19946, "token": "former", "merges": "form er", "raw_count": 94023, "count": 98020, "decode_str": "former"} -{"id": 2614, "token": "\u0120blood", "merges": "\u0120bl ood", "raw_count": 92554, "count": 98031, "decode_str": " blood"} -{"id": 35313, "token": "Ever", "merges": "E ver", "raw_count": 98040, "count": 98040, "decode_str": "Ever"} -{"id": 4429, "token": "\u0120thous", "merges": "\u0120th ous", "raw_count": 111, "count": 98052, "decode_str": " thous"} -{"id": 49046, "token": "543", "merges": "5 43", "raw_count": 98052, "count": 98052, "decode_str": "543"} -{"id": 2512, "token": "There", "merges": "The re", "raw_count": 98093, "count": 98093, "decode_str": "There"} -{"id": 14647, "token": "ODU", "merges": "OD U", "raw_count": 13417, "count": 98093, "decode_str": "ODU"} -{"id": 8346, "token": "\u0120outer", "merges": "\u0120out er", "raw_count": 98106, "count": 98106, "decode_str": " outer"} -{"id": 6361, "token": "opic", "merges": "op ic", "raw_count": 35656, "count": 98134, "decode_str": "opic"} -{"id": 1337, "token": ",\\", "merges": ", \\", "raw_count": 77555, "count": 98139, "decode_str": ",\\"} -{"id": 2646, "token": "ogen", "merges": "og en", "raw_count": 54221, "count": 98143, "decode_str": "ogen"} -{"id": 5576, "token": "ographic", "merges": "ograph ic", "raw_count": 56311, "count": 98153, "decode_str": "ographic"} -{"id": 32589, "token": "\u0120'\"", "merges": "\u0120' \"", "raw_count": 98155, "count": 98155, "decode_str": " '\""} -{"id": 49934, "token": "kid", "merges": "k id", "raw_count": 98156, "count": 98156, "decode_str": "kid"} -{"id": 6376, "token": "\u0120remained", "merges": "\u0120rem ained", "raw_count": 98161, "count": 98161, "decode_str": " remained"} -{"id": 24326, "token": "theme", "merges": "the me", "raw_count": 98165, "count": 98165, "decode_str": "theme"} -{"id": 49754, "token": "633", "merges": "6 33", "raw_count": 98166, "count": 98166, "decode_str": "633"} -{"id": 50534, "token": "\u00e4\u00bc\u00a2", "merges": "\u00e4\u00bc \u00a2", "raw_count": 98172, "count": 98172, "decode_str": "\u4f22"} -{"id": 3920, "token": "augh", "merges": "aug h", "raw_count": 24676, "count": 98191, "decode_str": "augh"} -{"id": 11657, "token": "ATED", "merges": "AT ED", "raw_count": 97274, "count": 98197, "decode_str": "ATED"} -{"id": 6483, "token": "\u0120cas", "merges": "\u0120c as", "raw_count": 45932, "count": 98197, "decode_str": " cas"} -{"id": 13969, "token": "\u0120consensus", "merges": "\u0120cons ensus", "raw_count": 98199, "count": 98199, "decode_str": " consensus"} -{"id": 10391, "token": "eld", "merges": "el d", "raw_count": 52153, "count": 98215, "decode_str": "eld"} -{"id": 42932, "token": "\u0120procurement", "merges": "\u0120procure ment", "raw_count": 98224, "count": 98224, "decode_str": " procurement"} -{"id": 34742, "token": "\u0120sep", "merges": "\u0120se p", "raw_count": 98227, "count": 98227, "decode_str": " sep"} -{"id": 53037, "token": "\u00e7\u0141\u012f", "merges": "\u00e7\u0141 \u012f", "raw_count": 98243, "count": 98243, "decode_str": "\u77cd"} -{"id": 6861, "token": "\u0120amb", "merges": "\u0120am b", "raw_count": 24175, "count": 98252, "decode_str": " amb"} -{"id": 41420, "token": "PAD", "merges": "P AD", "raw_count": 98287, "count": 98287, "decode_str": "PAD"} -{"id": 21053, "token": "\u00ec\u0139", "merges": "\u00ec \u0139", "raw_count": 33370, "count": 98291, "decode_str": "\ufffd"} -{"id": 51045, "token": "\u00e5\u0134\u00b2", "merges": "\u00e5\u0134 \u00b2", "raw_count": 98312, "count": 98312, "decode_str": "\u54b2"} -{"id": 41441, "token": "1002", "merges": "100 2", "raw_count": 98319, "count": 98319, "decode_str": "1002"} -{"id": 11705, "token": "\u0120strip", "merges": "\u0120stri p", "raw_count": 95291, "count": 98324, "decode_str": " strip"} -{"id": 17177, "token": "\u0120crop", "merges": "\u0120c rop", "raw_count": 98326, "count": 98326, "decode_str": " crop"} -{"id": 27757, "token": "Wrapper", "merges": "W rapper", "raw_count": 98352, "count": 98352, "decode_str": "Wrapper"} -{"id": 18832, "token": "039", "merges": "0 39", "raw_count": 98364, "count": 98364, "decode_str": "039"} -{"id": 5258, "token": "\u0120unc", "merges": "\u0120un c", "raw_count": 51939, "count": 98425, "decode_str": " unc"} -{"id": 6462, "token": "oyal", "merges": "oy al", "raw_count": 13981, "count": 98450, "decode_str": "oyal"} -{"id": 30310, "token": "bundle", "merges": "b undle", "raw_count": 98455, "count": 98455, "decode_str": "bundle"} -{"id": 6107, "token": "\u0120covered", "merges": "\u0120c overed", "raw_count": 98469, "count": 98469, "decode_str": " covered"} -{"id": 8748, "token": "\u0120laun", "merges": "\u0120la un", "raw_count": 9597, "count": 98471, "decode_str": " laun"} -{"id": 9372, "token": "\u0120counts", "merges": "\u0120count s", "raw_count": 98473, "count": 98473, "decode_str": " counts"} -{"id": 19951, "token": "\u0120peaceful", "merges": "\u0120peace ful", "raw_count": 98520, "count": 98520, "decode_str": " peaceful"} -{"id": 36539, "token": "096", "merges": "09 6", "raw_count": 98542, "count": 98542, "decode_str": "096"} -{"id": 6659, "token": "________________", "merges": "________ ________", "raw_count": 54426, "count": 98544, "decode_str": "________________"} -{"id": 12987, "token": "jar", "merges": "j ar", "raw_count": 98544, "count": 98544, "decode_str": "jar"} -{"id": 41239, "token": "YA", "merges": "Y A", "raw_count": 98564, "count": 98564, "decode_str": "YA"} -{"id": 28726, "token": "\u0120dummy", "merges": "\u0120d ummy", "raw_count": 98586, "count": 98586, "decode_str": " dummy"} -{"id": 44100, "token": "Jordan", "merges": "J ordan", "raw_count": 98617, "count": 98617, "decode_str": "Jordan"} -{"id": 11105, "token": "azz", "merges": "az z", "raw_count": 86713, "count": 98634, "decode_str": "azz"} -{"id": 21177, "token": "encil", "merges": "enc il", "raw_count": 89060, "count": 98674, "decode_str": "encil"} -{"id": 35548, "token": "Strategy", "merges": "Str ategy", "raw_count": 98696, "count": 98696, "decode_str": "Strategy"} -{"id": 43046, "token": "WOR", "merges": "W OR", "raw_count": 98718, "count": 98718, "decode_str": "WOR"} -{"id": 16328, "token": "olas", "merges": "ol as", "raw_count": 97304, "count": 98748, "decode_str": "olas"} -{"id": 32636, "token": "\u0120recommends", "merges": "\u0120recomm ends", "raw_count": 98759, "count": 98759, "decode_str": " recommends"} -{"id": 19007, "token": "\u0120deployment", "merges": "\u0120deploy ment", "raw_count": 98776, "count": 98776, "decode_str": " deployment"} -{"id": 7176, "token": "ITH", "merges": "IT H", "raw_count": 43672, "count": 98801, "decode_str": "ITH"} -{"id": 15740, "token": "oler", "merges": "ol er", "raw_count": 13833, "count": 98806, "decode_str": "oler"} -{"id": 4277, "token": "psilon", "merges": "ps ilon", "raw_count": 97827, "count": 98829, "decode_str": "psilon"} -{"id": 3075, "token": "\u0120pain", "merges": "\u0120p ain", "raw_count": 47762, "count": 98865, "decode_str": " pain"} -{"id": 4886, "token": "\u0120moving", "merges": "\u0120mov ing", "raw_count": 98883, "count": 98883, "decode_str": " moving"} -{"id": 51964, "token": "\u00e6\u012f\u012e", "merges": "\u00e6\u012f \u012e", "raw_count": 98885, "count": 98885, "decode_str": "\u634c"} -{"id": 23435, "token": "HO", "merges": "H O", "raw_count": 98890, "count": 98890, "decode_str": "HO"} -{"id": 29857, "token": "fab", "merges": "f ab", "raw_count": 74068, "count": 98898, "decode_str": "fab"} -{"id": 3085, "token": "\u0120film", "merges": "\u0120fil m", "raw_count": 95650, "count": 98910, "decode_str": " film"} -{"id": 18172, "token": "\u0120indicators", "merges": "\u0120indic ators", "raw_count": 98934, "count": 98934, "decode_str": " indicators"} -{"id": 9982, "token": "\u0120obst", "merges": "\u0120ob st", "raw_count": 6190, "count": 98945, "decode_str": " obst"} -{"id": 4876, "token": "\u0120letters", "merges": "\u0120let ters", "raw_count": 98987, "count": 98987, "decode_str": " letters"} -{"id": 20007, "token": "Double", "merges": "D ouble", "raw_count": 98991, "count": 98991, "decode_str": "Double"} -{"id": 18503, "token": "eros", "merges": "er os", "raw_count": 37967, "count": 99001, "decode_str": "eros"} -{"id": 16794, "token": "apper", "merges": "app er", "raw_count": 71043, "count": 99002, "decode_str": "apper"} -{"id": 49511, "token": "Ui", "merges": "U i", "raw_count": 99002, "count": 99002, "decode_str": "Ui"} -{"id": 38119, "token": "843", "merges": "84 3", "raw_count": 99007, "count": 99007, "decode_str": "843"} -{"id": 54574, "token": "\u00e8\u012d\u0130", "merges": "\u00e8\u012d \u0130", "raw_count": 99015, "count": 99015, "decode_str": "\u82ce"} -{"id": 6220, "token": "\u0120incorpor", "merges": "\u0120incor por", "raw_count": 224, "count": 99047, "decode_str": " incorpor"} -{"id": 25220, "token": "IEW", "merges": "IE W", "raw_count": 18042, "count": 99051, "decode_str": "IEW"} -{"id": 21215, "token": "agents", "merges": "ag ents", "raw_count": 97529, "count": 99059, "decode_str": "agents"} -{"id": 4395, "token": "\u0120moved", "merges": "\u0120mov ed", "raw_count": 99066, "count": 99066, "decode_str": " moved"} -{"id": 11331, "token": "\u0120educational", "merges": "\u0120educ ational", "raw_count": 99112, "count": 99112, "decode_str": " educational"} -{"id": 8374, "token": "\u0120lic", "merges": "\u0120l ic", "raw_count": 34688, "count": 99127, "decode_str": " lic"} -{"id": 37433, "token": "Nic", "merges": "N ic", "raw_count": 99135, "count": 99135, "decode_str": "Nic"} -{"id": 35323, "token": "796", "merges": "79 6", "raw_count": 99168, "count": 99168, "decode_str": "796"} -{"id": 25918, "token": "Arr", "merges": "A rr", "raw_count": 99213, "count": 99213, "decode_str": "Arr"} -{"id": 17462, "token": "\u0120expend", "merges": "\u0120exp end", "raw_count": 1973, "count": 99306, "decode_str": " expend"} -{"id": 42519, "token": "\u0120Validation", "merges": "\u0120Val idation", "raw_count": 99313, "count": 99313, "decode_str": " Validation"} -{"id": 36266, "token": "Formatter", "merges": "Form atter", "raw_count": 99340, "count": 99340, "decode_str": "Formatter"} -{"id": 3096, "token": "\u0120Ge", "merges": "\u0120G e", "raw_count": 58789, "count": 99354, "decode_str": " Ge"} -{"id": 8526, "token": "avel", "merges": "av el", "raw_count": 39921, "count": 99360, "decode_str": "avel"} -{"id": 28022, "token": "\u0120stakeholders", "merges": "\u0120stake holders", "raw_count": 99368, "count": 99368, "decode_str": " stakeholders"} -{"id": 30570, "token": "QP", "merges": "Q P", "raw_count": 99382, "count": 99382, "decode_str": "QP"} -{"id": 10389, "token": "rig", "merges": "r ig", "raw_count": 97909, "count": 99388, "decode_str": "rig"} -{"id": 33771, "token": "ISC", "merges": "IS C", "raw_count": 99437, "count": 99437, "decode_str": "ISC"} -{"id": 25734, "token": "CLASS", "merges": "CL ASS", "raw_count": 99462, "count": 99462, "decode_str": "CLASS"} -{"id": 14644, "token": "than", "merges": "th an", "raw_count": 99466, "count": 99466, "decode_str": "than"} -{"id": 5610, "token": "anging", "merges": "ang ing", "raw_count": 20166, "count": 99521, "decode_str": "anging"} -{"id": 6072, "token": "Cs", "merges": "C s", "raw_count": 90052, "count": 99524, "decode_str": "Cs"} -{"id": 32849, "token": "Binary", "merges": "B inary", "raw_count": 99547, "count": 99547, "decode_str": "Binary"} -{"id": 15593, "token": "rea", "merges": "re a", "raw_count": 99176, "count": 99549, "decode_str": "rea"} -{"id": 47014, "token": "727", "merges": "7 27", "raw_count": 99558, "count": 99558, "decode_str": "727"} -{"id": 6079, "token": "\u0120dry", "merges": "\u0120d ry", "raw_count": 90976, "count": 99592, "decode_str": " dry"} -{"id": 12594, "token": "away", "merges": "a way", "raw_count": 99592, "count": 99592, "decode_str": "away"} -{"id": 14083, "token": "icture", "merges": "ict ure", "raw_count": 1779, "count": 99594, "decode_str": "icture"} -{"id": 53987, "token": "\u00e8\u00b6\u00ba", "merges": "\u00e8\u00b6 \u00ba", "raw_count": 99607, "count": 99607, "decode_str": "\u8dba"} -{"id": 22383, "token": "wy", "merges": "w y", "raw_count": 99616, "count": 99616, "decode_str": "wy"} -{"id": 10153, "token": "iration", "merges": "ir ation", "raw_count": 54259, "count": 99643, "decode_str": "iration"} -{"id": 31756, "token": "orientation", "merges": "orient ation", "raw_count": 99652, "count": 99652, "decode_str": "orientation"} -{"id": 23940, "token": "Cert", "merges": "C ert", "raw_count": 54079, "count": 99666, "decode_str": "Cert"} -{"id": 23874, "token": "comed", "merges": "com ed", "raw_count": 3555, "count": 99668, "decode_str": "comed"} -{"id": 43847, "token": "873", "merges": "87 3", "raw_count": 99678, "count": 99678, "decode_str": "873"} -{"id": 26042, "token": "Water", "merges": "W ater", "raw_count": 99705, "count": 99705, "decode_str": "Water"} -{"id": 50185, "token": "SQ", "merges": "S Q", "raw_count": 99816, "count": 99816, "decode_str": "SQ"} -{"id": 12610, "token": "zzle", "merges": "zz le", "raw_count": 68864, "count": 99818, "decode_str": "zzle"} -{"id": 33959, "token": "LEFT", "merges": "LE FT", "raw_count": 99851, "count": 99851, "decode_str": "LEFT"} -{"id": 3666, "token": "\u0120Des", "merges": "\u0120D es", "raw_count": 49820, "count": 99858, "decode_str": " Des"} -{"id": 38978, "token": "861", "merges": "86 1", "raw_count": 99865, "count": 99865, "decode_str": "861"} -{"id": 34276, "token": "john", "merges": "j ohn", "raw_count": 99876, "count": 99876, "decode_str": "john"} -{"id": 14617, "token": "cz", "merges": "c z", "raw_count": 99898, "count": 99898, "decode_str": "cz"} -{"id": 17104, "token": "Users", "merges": "Us ers", "raw_count": 99907, "count": 99907, "decode_str": "Users"} -{"id": 10593, "token": "unct", "merges": "un ct", "raw_count": 80984, "count": 99940, "decode_str": "unct"} -{"id": 40097, "token": "WIDTH", "merges": "W IDTH", "raw_count": 99942, "count": 99942, "decode_str": "WIDTH"} -{"id": 48934, "token": "recurs", "merges": "re curs", "raw_count": 99949, "count": 99949, "decode_str": "recurs"} -{"id": 27474, "token": "DQ", "merges": "D Q", "raw_count": 99951, "count": 99951, "decode_str": "DQ"} -{"id": 4551, "token": "aught", "merges": "aug ht", "raw_count": 30360, "count": 99983, "decode_str": "aught"} -{"id": 28521, "token": "Association", "merges": "Ass ociation", "raw_count": 100021, "count": 100021, "decode_str": "Association"} -{"id": 7661, "token": "\u0120revers", "merges": "\u0120re vers", "raw_count": 4881, "count": 100024, "decode_str": " revers"} -{"id": 20339, "token": "Ann", "merges": "An n", "raw_count": 100031, "count": 100031, "decode_str": "Ann"} -{"id": 27191, "token": "\u0120cp", "merges": "\u0120c p", "raw_count": 100043, "count": 100043, "decode_str": " cp"} -{"id": 31315, "token": "Trust", "merges": "Tr ust", "raw_count": 100064, "count": 100064, "decode_str": "Trust"} -{"id": 3442, "token": "Delta", "merges": "D elta", "raw_count": 100095, "count": 100095, "decode_str": "Delta"} -{"id": 49698, "token": "Lau", "merges": "L au", "raw_count": 100095, "count": 100095, "decode_str": "Lau"} -{"id": 38723, "token": "1005", "merges": "100 5", "raw_count": 100113, "count": 100113, "decode_str": "1005"} -{"id": 8542, "token": "\u0120practical", "merges": "\u0120pract ical", "raw_count": 100118, "count": 100118, "decode_str": " practical"} -{"id": 8027, "token": "\u0120launch", "merges": "\u0120la unch", "raw_count": 80472, "count": 100226, "decode_str": " launch"} -{"id": 5381, "token": "\u0120wat", "merges": "\u0120w at", "raw_count": 25165, "count": 100244, "decode_str": " wat"} -{"id": 19320, "token": "ANCE", "merges": "AN CE", "raw_count": 100258, "count": 100258, "decode_str": "ANCE"} -{"id": 23544, "token": "RAY", "merges": "RA Y", "raw_count": 77928, "count": 100276, "decode_str": "RAY"} -{"id": 32336, "token": "Johnson", "merges": "John son", "raw_count": 100303, "count": 100303, "decode_str": "Johnson"} -{"id": 10598, "token": "onymous", "merges": "onym ous", "raw_count": 42465, "count": 100347, "decode_str": "onymous"} -{"id": 18549, "token": "stan", "merges": "st an", "raw_count": 96248, "count": 100403, "decode_str": "stan"} -{"id": 27603, "token": "Metric", "merges": "M etric", "raw_count": 62391, "count": 100407, "decode_str": "Metric"} -{"id": 11828, "token": "vance", "merges": "v ance", "raw_count": 74039, "count": 100426, "decode_str": "vance"} -{"id": 11753, "token": "lot", "merges": "l ot", "raw_count": 93360, "count": 100445, "decode_str": "lot"} -{"id": 10660, "token": "\u0120renew", "merges": "\u0120re new", "raw_count": 24629, "count": 100476, "decode_str": " renew"} -{"id": 19842, "token": "GIN", "merges": "G IN", "raw_count": 82233, "count": 100488, "decode_str": "GIN"} -{"id": 16284, "token": "Panel", "merges": "Pan el", "raw_count": 100496, "count": 100496, "decode_str": "Panel"} -{"id": 5909, "token": "\u0120opening", "merges": "\u0120open ing", "raw_count": 100503, "count": 100503, "decode_str": " opening"} -{"id": 49895, "token": "542", "merges": "5 42", "raw_count": 100515, "count": 100515, "decode_str": "542"} -{"id": 7578, "token": "\u0120consent", "merges": "\u0120cons ent", "raw_count": 97790, "count": 100527, "decode_str": " consent"} -{"id": 29796, "token": "Ur", "merges": "U r", "raw_count": 100527, "count": 100527, "decode_str": "Ur"} -{"id": 9534, "token": "\u0120situations", "merges": "\u0120situ ations", "raw_count": 100543, "count": 100543, "decode_str": " situations"} -{"id": 54564, "token": "\u00e9\u0136\u0125", "merges": "\u00e9\u0136 \u0125", "raw_count": 100553, "count": 100553, "decode_str": "\u9503"} -{"id": 17296, "token": "xb", "merges": "x b", "raw_count": 100578, "count": 100578, "decode_str": "xb"} -{"id": 40210, "token": "713", "merges": "7 13", "raw_count": 100586, "count": 100586, "decode_str": "713"} -{"id": 10523, "token": "\u012078", "merges": "\u01207 8", "raw_count": 100601, "count": 100601, "decode_str": " 78"} -{"id": 37070, "token": "Rose", "merges": "R ose", "raw_count": 100621, "count": 100621, "decode_str": "Rose"} -{"id": 21771, "token": "FN", "merges": "F N", "raw_count": 100631, "count": 100631, "decode_str": "FN"} -{"id": 22549, "token": "/?", "merges": "/ ?", "raw_count": 100654, "count": 100654, "decode_str": "/?"} -{"id": 42238, "token": "Fu", "merges": "F u", "raw_count": 100728, "count": 100728, "decode_str": "Fu"} -{"id": 21359, "token": "OUP", "merges": "OU P", "raw_count": 7204, "count": 100759, "decode_str": "OUP"} -{"id": 7880, "token": "\u0120absolute", "merges": "\u0120absol ute", "raw_count": 100762, "count": 100762, "decode_str": " absolute"} -{"id": 53969, "token": "\u00e8\u00b5\u00a7", "merges": "\u00e8\u00b5 \u00a7", "raw_count": 100780, "count": 100780, "decode_str": "\u8d67"} -{"id": 12306, "token": "fish", "merges": "f ish", "raw_count": 100588, "count": 100783, "decode_str": "fish"} -{"id": 19752, "token": "NK", "merges": "N K", "raw_count": 100761, "count": 100785, "decode_str": "NK"} -{"id": 4102, "token": "\u0120recently", "merges": "\u0120rec ently", "raw_count": 100818, "count": 100818, "decode_str": " recently"} -{"id": 14730, "token": "\u0120eastern", "merges": "\u0120eas tern", "raw_count": 100846, "count": 100846, "decode_str": " eastern"} -{"id": 5675, "token": "\u0120growing", "merges": "\u0120grow ing", "raw_count": 100867, "count": 100867, "decode_str": " growing"} -{"id": 12216, "token": "utter", "merges": "ut ter", "raw_count": 98313, "count": 100869, "decode_str": "utter"} -{"id": 3773, "token": "\u0120players", "merges": "\u0120play ers", "raw_count": 100873, "count": 100873, "decode_str": " players"} -{"id": 35481, "token": "Expected", "merges": "Ex pected", "raw_count": 100896, "count": 100896, "decode_str": "Expected"} -{"id": 7102, "token": "\u0120guide", "merges": "\u0120gu ide", "raw_count": 100904, "count": 100904, "decode_str": " guide"} -{"id": 45976, "token": "Jess", "merges": "J ess", "raw_count": 100928, "count": 100928, "decode_str": "Jess"} -{"id": 7922, "token": "\u0120assigned", "merges": "\u0120ass igned", "raw_count": 100946, "count": 100946, "decode_str": " assigned"} -{"id": 32462, "token": "Ze", "merges": "Z e", "raw_count": 100963, "count": 100963, "decode_str": "Ze"} -{"id": 4806, "token": "\u0120sto", "merges": "\u0120st o", "raw_count": 14329, "count": 100964, "decode_str": " sto"} -{"id": 5807, "token": "\u0120sch", "merges": "\u0120s ch", "raw_count": 58487, "count": 100976, "decode_str": " sch"} -{"id": 14868, "token": "Pref", "merges": "P ref", "raw_count": 37097, "count": 100981, "decode_str": "Pref"} -{"id": 19846, "token": "North", "merges": "N orth", "raw_count": 101002, "count": 101002, "decode_str": "North"} -{"id": 6388, "token": "\u0120involve", "merges": "\u0120invol ve", "raw_count": 39083, "count": 101003, "decode_str": " involve"} -{"id": 10059, "token": "anny", "merges": "ann y", "raw_count": 98643, "count": 101012, "decode_str": "anny"} -{"id": 13199, "token": "\u0120specify", "merges": "\u0120spec ify", "raw_count": 101043, "count": 101043, "decode_str": " specify"} -{"id": 6034, "token": "\u0120intended", "merges": "\u0120int ended", "raw_count": 101049, "count": 101049, "decode_str": " intended"} -{"id": 2719, "token": "\u0120Rep", "merges": "\u0120R ep", "raw_count": 42324, "count": 101061, "decode_str": " Rep"} -{"id": 11786, "token": "\u0120gradient", "merges": "\u0120grad ient", "raw_count": 101062, "count": 101062, "decode_str": " gradient"} -{"id": 50177, "token": "iffany", "merges": "iff any", "raw_count": 101112, "count": 101112, "decode_str": "iffany"} -{"id": 19306, "token": "lav", "merges": "l av", "raw_count": 30295, "count": 101125, "decode_str": "lav"} -{"id": 30098, "token": "Wood", "merges": "W ood", "raw_count": 101156, "count": 101156, "decode_str": "Wood"} -{"id": 5896, "token": "riage", "merges": "ri age", "raw_count": 19235, "count": 101161, "decode_str": "riage"} -{"id": 54195, "token": "\u00e9\u0127\u00a2", "merges": "\u00e9\u0127 \u00a2", "raw_count": 101162, "count": 101162, "decode_str": "\u9162"} -{"id": 8310, "token": "\u0120observation", "merges": "\u0120observ ation", "raw_count": 101164, "count": 101164, "decode_str": " observation"} -{"id": 51877, "token": "\u00e6\u012c\u0141", "merges": "\u00e6\u012c \u0141", "raw_count": 101222, "count": 101222, "decode_str": "\u629f"} -{"id": 11075, "token": "\u0120Start", "merges": "\u0120St art", "raw_count": 88739, "count": 101261, "decode_str": " Start"} -{"id": 40731, "token": "Generate", "merges": "Gener ate", "raw_count": 101344, "count": 101344, "decode_str": "Generate"} -{"id": 20261, "token": "although", "merges": "alth ough", "raw_count": 101359, "count": 101359, "decode_str": "although"} -{"id": 34920, "token": "957", "merges": "95 7", "raw_count": 101360, "count": 101360, "decode_str": "957"} -{"id": 51815, "token": "\u00e6\u012a\u0137", "merges": "\u00e6\u012a \u0137", "raw_count": 101363, "count": 101363, "decode_str": "\u6215"} -{"id": 50070, "token": "qr", "merges": "q r", "raw_count": 101369, "count": 101369, "decode_str": "qr"} -{"id": 44160, "token": "833", "merges": "8 33", "raw_count": 101370, "count": 101370, "decode_str": "833"} -{"id": 12949, "token": "\u0120mini", "merges": "\u0120min i", "raw_count": 97686, "count": 101375, "decode_str": " mini"} -{"id": 11886, "token": "\u0120anch", "merges": "\u0120an ch", "raw_count": 7299, "count": 101383, "decode_str": " anch"} -{"id": 16796, "token": "Aust", "merges": "A ust", "raw_count": 11871, "count": 101391, "decode_str": "Aust"} -{"id": 22529, "token": "Turn", "merges": "T urn", "raw_count": 101418, "count": 101418, "decode_str": "Turn"} -{"id": 2926, "token": "\u0120story", "merges": "\u0120st ory", "raw_count": 99129, "count": 101431, "decode_str": " story"} -{"id": 37343, "token": "enario", "merges": "en ario", "raw_count": 101448, "count": 101448, "decode_str": "enario"} -{"id": 29695, "token": "054", "merges": "05 4", "raw_count": 101476, "count": 101476, "decode_str": "054"} -{"id": 3777, "token": "\u0120reduced", "merges": "\u0120redu ced", "raw_count": 101522, "count": 101522, "decode_str": " reduced"} -{"id": 51238, "token": "\u00e5\u0141\u00a4", "merges": "\u00e5\u0141 \u00a4", "raw_count": 101536, "count": 101536, "decode_str": "\u57e4"} -{"id": 40028, "token": "extensions", "merges": "ext ensions", "raw_count": 101546, "count": 101546, "decode_str": "extensions"} -{"id": 10226, "token": "\u01201991", "merges": "\u0120199 1", "raw_count": 101562, "count": 101562, "decode_str": " 1991"} -{"id": 48694, "token": "728", "merges": "7 28", "raw_count": 101577, "count": 101577, "decode_str": "728"} -{"id": 8840, "token": "\u0120lowest", "merges": "\u0120low est", "raw_count": 101581, "count": 101581, "decode_str": " lowest"} -{"id": 14387, "token": "heart", "merges": "he art", "raw_count": 95148, "count": 101598, "decode_str": "heart"} -{"id": 9985, "token": "\u0120Find", "merges": "\u0120F ind", "raw_count": 101396, "count": 101641, "decode_str": " Find"} -{"id": 32305, "token": "\u0120quer", "merges": "\u0120qu er", "raw_count": 101659, "count": 101659, "decode_str": " quer"} -{"id": 28517, "token": "Timer", "merges": "T imer", "raw_count": 101668, "count": 101668, "decode_str": "Timer"} -{"id": 7043, "token": "\u0120salt", "merges": "\u0120s alt", "raw_count": 101672, "count": 101672, "decode_str": " salt"} -{"id": 34585, "token": "Pin", "merges": "P in", "raw_count": 101716, "count": 101716, "decode_str": "Pin"} -{"id": 10378, "token": "olly", "merges": "ol ly", "raw_count": 73722, "count": 101728, "decode_str": "olly"} -{"id": 21697, "token": "alph", "merges": "al ph", "raw_count": 100988, "count": 101743, "decode_str": "alph"} -{"id": 29981, "token": "Cred", "merges": "C red", "raw_count": 101781, "count": 101781, "decode_str": "Cred"} -{"id": 19247, "token": "STATE", "merges": "ST ATE", "raw_count": 101807, "count": 101807, "decode_str": "STATE"} -{"id": 48416, "token": "638", "merges": "6 38", "raw_count": 101807, "count": 101807, "decode_str": "638"} -{"id": 35946, "token": "attack", "merges": "att ack", "raw_count": 101815, "count": 101815, "decode_str": "attack"} -{"id": 26809, "token": "HU", "merges": "H U", "raw_count": 101822, "count": 101822, "decode_str": "HU"} -{"id": 20646, "token": "CLA", "merges": "CL A", "raw_count": 98716, "count": 101825, "decode_str": "CLA"} -{"id": 7097, "token": "inations", "merges": "in ations", "raw_count": 28023, "count": 101826, "decode_str": "inations"} -{"id": 22362, "token": "MON", "merges": "M ON", "raw_count": 101830, "count": 101830, "decode_str": "MON"} -{"id": 23291, "token": "Sup", "merges": "S up", "raw_count": 53431, "count": 101856, "decode_str": "Sup"} -{"id": 53692, "token": "\u00e8\u013b\u00bb", "merges": "\u00e8\u013b \u00bb", "raw_count": 101857, "count": 101857, "decode_str": "\u867b"} -{"id": 20127, "token": "Ok", "merges": "O k", "raw_count": 101874, "count": 101874, "decode_str": "Ok"} -{"id": 6119, "token": "\u0120kit", "merges": "\u0120k it", "raw_count": 28368, "count": 101886, "decode_str": " kit"} -{"id": 5847, "token": "\u0120pros", "merges": "\u0120pro s", "raw_count": 7544, "count": 101895, "decode_str": " pros"} -{"id": 26567, "token": "Direct", "merges": "D irect", "raw_count": 101901, "count": 101901, "decode_str": "Direct"} -{"id": 11682, "token": "construction", "merges": "const ruction", "raw_count": 45906, "count": 101917, "decode_str": "construction"} -{"id": 42365, "token": "catalog", "merges": "catal og", "raw_count": 101930, "count": 101930, "decode_str": "catalog"} -{"id": 5020, "token": "\u0120majority", "merges": "\u0120major ity", "raw_count": 101962, "count": 101962, "decode_str": " majority"} -{"id": 19783, "token": "parallel", "merges": "par allel", "raw_count": 101964, "count": 101964, "decode_str": "parallel"} -{"id": 49735, "token": "lx", "merges": "l x", "raw_count": 102012, "count": 102012, "decode_str": "lx"} -{"id": 6502, "token": "\u0120enem", "merges": "\u0120en em", "raw_count": 1916, "count": 102027, "decode_str": " enem"} -{"id": 29829, "token": "emy", "merges": "em y", "raw_count": 102053, "count": 102053, "decode_str": "emy"} -{"id": 7190, "token": "cial", "merges": "c ial", "raw_count": 9769, "count": 102095, "decode_str": "cial"} -{"id": 9631, "token": "onder", "merges": "on der", "raw_count": 95101, "count": 102124, "decode_str": "onder"} -{"id": 3897, "token": "\u0120los", "merges": "\u0120l os", "raw_count": 69797, "count": 102157, "decode_str": " los"} -{"id": 6974, "token": "\u0120scheme", "merges": "\u0120sche me", "raw_count": 102165, "count": 102165, "decode_str": " scheme"} -{"id": 29529, "token": "FileName", "merges": "File Name", "raw_count": 102166, "count": 102166, "decode_str": "FileName"} -{"id": 5448, "token": "\u0120wind", "merges": "\u0120w ind", "raw_count": 88959, "count": 102187, "decode_str": " wind"} -{"id": 17768, "token": "KH", "merges": "K H", "raw_count": 101993, "count": 102187, "decode_str": "KH"} -{"id": 6959, "token": ")/(", "merges": ")/ (", "raw_count": 102149, "count": 102197, "decode_str": ")/("} -{"id": 1422, "token": "\u0120You", "merges": "\u0120Y ou", "raw_count": 92760, "count": 102201, "decode_str": " You"} -{"id": 19622, "token": "GER", "merges": "G ER", "raw_count": 54772, "count": 102218, "decode_str": "GER"} -{"id": 51488, "token": "\u00e5\u00b1\u0132", "merges": "\u00e5\u00b1 \u0132", "raw_count": 102220, "count": 102220, "decode_str": "\u5c50"} -{"id": 5722, "token": "\u0120award", "merges": "\u0120a ward", "raw_count": 69012, "count": 102255, "decode_str": " award"} -{"id": 14112, "token": "\u0120legislative", "merges": "\u0120legisl ative", "raw_count": 102258, "count": 102258, "decode_str": " legislative"} -{"id": 7257, "token": "\u0120deliver", "merges": "\u0120del iver", "raw_count": 73031, "count": 102262, "decode_str": " deliver"} -{"id": 33191, "token": "okia", "merges": "ok ia", "raw_count": 101432, "count": 102269, "decode_str": "okia"} -{"id": 17169, "token": "\u0120\"'", "merges": "\u0120\" '", "raw_count": 102270, "count": 102270, "decode_str": " \"'"} -{"id": 19192, "token": "story", "merges": "st ory", "raw_count": 102271, "count": 102271, "decode_str": "story"} -{"id": 21662, "token": "uggest", "merges": "ug gest", "raw_count": 7232, "count": 102283, "decode_str": "uggest"} -{"id": 6928, "token": "\u0120networks", "merges": "\u0120net works", "raw_count": 102284, "count": 102284, "decode_str": " networks"} -{"id": 2859, "token": "rho", "merges": "r ho", "raw_count": 102252, "count": 102304, "decode_str": "rho"} -{"id": 42066, "token": "Money", "merges": "M oney", "raw_count": 102307, "count": 102307, "decode_str": "Money"} -{"id": 26537, "token": "azy", "merges": "az y", "raw_count": 102308, "count": 102308, "decode_str": "azy"} -{"id": 27689, "token": "Login", "merges": "Log in", "raw_count": 102311, "count": 102311, "decode_str": "Login"} -{"id": 33608, "token": "896", "merges": "89 6", "raw_count": 102313, "count": 102313, "decode_str": "896"} -{"id": 15264, "token": "\u0120buf", "merges": "\u0120bu f", "raw_count": 95716, "count": 102353, "decode_str": " buf"} -{"id": 8238, "token": "\u0120cities", "merges": "\u0120c ities", "raw_count": 102356, "count": 102356, "decode_str": " cities"} -{"id": 3039, "token": "When", "merges": "W hen", "raw_count": 102382, "count": 102382, "decode_str": "When"} -{"id": 17810, "token": "ociation", "merges": "oci ation", "raw_count": 1800, "count": 102443, "decode_str": "ociation"} -{"id": 53075, "token": "\u00e7\u00a1\u0132", "merges": "\u00e7\u00a1 \u0132", "raw_count": 102459, "count": 102459, "decode_str": "\u7850"} -{"id": 11275, "token": "\u012079", "merges": "\u01207 9", "raw_count": 102471, "count": 102471, "decode_str": " 79"} -{"id": 5153, "token": "\u0120histor", "merges": "\u0120hist or", "raw_count": 3148, "count": 102478, "decode_str": " histor"} -{"id": 4521, "token": "othes", "merges": "ot hes", "raw_count": 43466, "count": 102505, "decode_str": "othes"} -{"id": 30941, "token": "erial", "merges": "er ial", "raw_count": 102506, "count": 102506, "decode_str": "erial"} -{"id": 5596, "token": "appa", "merges": "app a", "raw_count": 68332, "count": 102544, "decode_str": "appa"} -{"id": 22348, "token": "heat", "merges": "he at", "raw_count": 102569, "count": 102569, "decode_str": "heat"} -{"id": 17489, "token": "\u0120mesh", "merges": "\u0120mes h", "raw_count": 102577, "count": 102577, "decode_str": " mesh"} -{"id": 37599, "token": "Vel", "merges": "V el", "raw_count": 102578, "count": 102578, "decode_str": "Vel"} -{"id": 17219, "token": "Json", "merges": "J son", "raw_count": 102594, "count": 102594, "decode_str": "Json"} -{"id": 9176, "token": "\u0120pin", "merges": "\u0120p in", "raw_count": 97965, "count": 102602, "decode_str": " pin"} -{"id": 19465, "token": "\u0120sectors", "merges": "\u0120se ctors", "raw_count": 102619, "count": 102619, "decode_str": " sectors"} -{"id": 10225, "token": "ois", "merges": "o is", "raw_count": 88239, "count": 102628, "decode_str": "ois"} -{"id": 29969, "token": "Fox", "merges": "F ox", "raw_count": 102669, "count": 102669, "decode_str": "Fox"} -{"id": 45259, "token": "544", "merges": "5 44", "raw_count": 102734, "count": 102734, "decode_str": "544"} -{"id": 29877, "token": "\u0120procure", "merges": "\u0120proc ure", "raw_count": 4535, "count": 102759, "decode_str": " procure"} -{"id": 7572, "token": "fess", "merges": "f ess", "raw_count": 8041, "count": 102773, "decode_str": "fess"} -{"id": 20912, "token": "meth", "merges": "m eth", "raw_count": 102781, "count": 102781, "decode_str": "meth"} -{"id": 27979, "token": "WF", "merges": "W F", "raw_count": 102794, "count": 102794, "decode_str": "WF"} -{"id": 32978, "token": "conditions", "merges": "cond itions", "raw_count": 102803, "count": 102803, "decode_str": "conditions"} -{"id": 25974, "token": "transition", "merges": "trans ition", "raw_count": 102820, "count": 102820, "decode_str": "transition"} -{"id": 34934, "token": "Daily", "merges": "D aily", "raw_count": 102840, "count": 102840, "decode_str": "Daily"} -{"id": 24831, "token": "ANC", "merges": "AN C", "raw_count": 102849, "count": 102849, "decode_str": "ANC"} -{"id": 10243, "token": "\u0120Line", "merges": "\u0120L ine", "raw_count": 59203, "count": 102862, "decode_str": " Line"} -{"id": 47954, "token": "completed", "merges": "comple ted", "raw_count": 102881, "count": 102881, "decode_str": "completed"} -{"id": 7231, "token": "\u0120religious", "merges": "\u0120relig ious", "raw_count": 102891, "count": 102891, "decode_str": " religious"} -{"id": 6630, "token": "\u0120survey", "merges": "\u0120sur vey", "raw_count": 97237, "count": 102894, "decode_str": " survey"} -{"id": 16601, "token": "Register", "merges": "Reg ister", "raw_count": 102904, "count": 102904, "decode_str": "Register"} -{"id": 54546, "token": "\u00e7\u013c\u00b2", "merges": "\u00e7\u013c \u00b2", "raw_count": 102906, "count": 102906, "decode_str": "\u76b2"} -{"id": 4073, "token": "\u0120stress", "merges": "\u0120st ress", "raw_count": 69185, "count": 102947, "decode_str": " stress"} -{"id": 3961, "token": "\u0120band", "merges": "\u0120b and", "raw_count": 83415, "count": 102947, "decode_str": " band"} -{"id": 6945, "token": "\u0120alt", "merges": "\u0120al t", "raw_count": 67616, "count": 102961, "decode_str": " alt"} -{"id": 11269, "token": "\u0120updates", "merges": "\u0120upd ates", "raw_count": 102982, "count": 102982, "decode_str": " updates"} -{"id": 15752, "token": "arity", "merges": "ar ity", "raw_count": 62755, "count": 102996, "decode_str": "arity"} -{"id": 8501, "token": "flu", "merges": "fl u", "raw_count": 41031, "count": 102999, "decode_str": "flu"} -{"id": 23058, "token": "hentication", "merges": "hentic ation", "raw_count": 65636, "count": 103006, "decode_str": "hentication"} -{"id": 4930, "token": "asion", "merges": "as ion", "raw_count": 23510, "count": 103040, "decode_str": "asion"} -{"id": 19530, "token": "mos", "merges": "m os", "raw_count": 103063, "count": 103063, "decode_str": "mos"} -{"id": 7926, "token": "\u0120recip", "merges": "\u0120rec ip", "raw_count": 2035, "count": 103082, "decode_str": " recip"} -{"id": 3083, "token": "\u0120Man", "merges": "\u0120M an", "raw_count": 39036, "count": 103083, "decode_str": " Man"} -{"id": 7380, "token": "akers", "merges": "ak ers", "raw_count": 66703, "count": 103099, "decode_str": "akers"} -{"id": 5978, "token": "\u0120generation", "merges": "\u0120gener ation", "raw_count": 103124, "count": 103124, "decode_str": " generation"} -{"id": 14346, "token": "xa", "merges": "x a", "raw_count": 103125, "count": 103125, "decode_str": "xa"} -{"id": 6866, "token": "\u0120criteria", "merges": "\u0120crit eria", "raw_count": 103137, "count": 103137, "decode_str": " criteria"} -{"id": 7442, "token": "\u0120orient", "merges": "\u0120o rient", "raw_count": 23451, "count": 103138, "decode_str": " orient"} -{"id": 3162, "token": "\u0120Act", "merges": "\u0120A ct", "raw_count": 45774, "count": 103139, "decode_str": " Act"} -{"id": 9456, "token": "mond", "merges": "m ond", "raw_count": 100136, "count": 103154, "decode_str": "mond"} -{"id": 52784, "token": "\u00e7\u012b\u00af", "merges": "\u00e7\u012b \u00af", "raw_count": 103163, "count": 103163, "decode_str": "\u726f"} -{"id": 52833, "token": "\u00e7\u0131\u00a5", "merges": "\u00e7\u0131 \u00a5", "raw_count": 103193, "count": 103193, "decode_str": "\u73e5"} -{"id": 24463, "token": "authorized", "merges": "author ized", "raw_count": 69779, "count": 103196, "decode_str": "authorized"} -{"id": 48084, "token": "sx", "merges": "s x", "raw_count": 103208, "count": 103208, "decode_str": "sx"} -{"id": 5809, "token": "\u0120vac", "merges": "\u0120v ac", "raw_count": 24064, "count": 103209, "decode_str": " vac"} -{"id": 8109, "token": "\u0120supporting", "merges": "\u0120support ing", "raw_count": 103210, "count": 103210, "decode_str": " supporting"} -{"id": 32552, "token": "\u0120checkpoint", "merges": "\u0120check point", "raw_count": 103213, "count": 103213, "decode_str": " checkpoint"} -{"id": 20004, "token": "\u0120Remove", "merges": "\u0120Rem ove", "raw_count": 103215, "count": 103215, "decode_str": " Remove"} -{"id": 10584, "token": "\u0120hook", "merges": "\u0120h ook", "raw_count": 79685, "count": 103217, "decode_str": " hook"} -{"id": 52829, "token": "\u00e7\u0131\u013b", "merges": "\u00e7\u0131 \u013b", "raw_count": 103246, "count": 103246, "decode_str": "\u73d9"} -{"id": 9886, "token": "\u0120bits", "merges": "\u0120b its", "raw_count": 103282, "count": 103282, "decode_str": " bits"} -{"id": 13603, "token": "\u0120disabled", "merges": "\u0120dis abled", "raw_count": 103310, "count": 103310, "decode_str": " disabled"} -{"id": 43794, "token": "Unable", "merges": "Un able", "raw_count": 103310, "count": 103310, "decode_str": "Unable"} -{"id": 3115, "token": "tau", "merges": "ta u", "raw_count": 103328, "count": 103328, "decode_str": "tau"} -{"id": 18713, "token": "\u013b\u0124", "merges": "\u013b \u0124", "raw_count": 13826, "count": 103328, "decode_str": "\ufffd\ufffd"} -{"id": 4495, "token": "\u0120meaning", "merges": "\u0120mean ing", "raw_count": 68714, "count": 103332, "decode_str": " meaning"} -{"id": 3962, "token": "\u0120perfect", "merges": "\u0120per fect", "raw_count": 84456, "count": 103347, "decode_str": " perfect"} -{"id": 2745, "token": "\u0120Te", "merges": "\u0120T e", "raw_count": 13844, "count": 103352, "decode_str": " Te"} -{"id": 20670, "token": "\u0120interpol", "merges": "\u0120inter pol", "raw_count": 46724, "count": 103368, "decode_str": " interpol"} -{"id": 17383, "token": "folio", "merges": "fol io", "raw_count": 61772, "count": 103371, "decode_str": "folio"} -{"id": 7837, "token": "acent", "merges": "ac ent", "raw_count": 64751, "count": 103380, "decode_str": "acent"} -{"id": 34284, "token": "897", "merges": "89 7", "raw_count": 103395, "count": 103395, "decode_str": "897"} -{"id": 9161, "token": "\u012096", "merges": "\u01209 6", "raw_count": 103433, "count": 103433, "decode_str": " 96"} -{"id": 29284, "token": "decor", "merges": "de cor", "raw_count": 93503, "count": 103437, "decode_str": "decor"} -{"id": 9565, "token": "gypt", "merges": "gy pt", "raw_count": 102690, "count": 103442, "decode_str": "gypt"} -{"id": 13112, "token": "\u0120atom", "merges": "\u0120at om", "raw_count": 103491, "count": 103491, "decode_str": " atom"} -{"id": 17551, "token": "jan", "merges": "j an", "raw_count": 103498, "count": 103498, "decode_str": "jan"} -{"id": 6997, "token": "\u0120acknow", "merges": "\u0120a cknow", "raw_count": 103, "count": 103525, "decode_str": " acknow"} -{"id": 39027, "token": "882", "merges": "88 2", "raw_count": 103532, "count": 103532, "decode_str": "882"} -{"id": 13467, "token": "elect", "merges": "e lect", "raw_count": 53527, "count": 103542, "decode_str": "elect"} -{"id": 12517, "token": "craft", "merges": "c raft", "raw_count": 94537, "count": 103549, "decode_str": "craft"} -{"id": 2952, "token": "\u0120season", "merges": "\u0120se ason", "raw_count": 96191, "count": 103587, "decode_str": " season"} -{"id": 38352, "token": "\u0120delim", "merges": "\u0120del im", "raw_count": 103632, "count": 103632, "decode_str": " delim"} -{"id": 49462, "token": "DK", "merges": "D K", "raw_count": 103655, "count": 103655, "decode_str": "DK"} -{"id": 10356, "token": "iano", "merges": "ian o", "raw_count": 89657, "count": 103660, "decode_str": "iano"} -{"id": 21911, "token": "Memory", "merges": "Mem ory", "raw_count": 103681, "count": 103681, "decode_str": "Memory"} -{"id": 18281, "token": "Share", "merges": "Sh are", "raw_count": 103712, "count": 103712, "decode_str": "Share"} -{"id": 3641, "token": "\u0120mi", "merges": "\u0120m i", "raw_count": 78203, "count": 103714, "decode_str": " mi"} -{"id": 47161, "token": "614", "merges": "6 14", "raw_count": 103741, "count": 103741, "decode_str": "614"} -{"id": 8411, "token": "\u0120violation", "merges": "\u0120viol ation", "raw_count": 103749, "count": 103749, "decode_str": " violation"} -{"id": 3078, "token": "\u0120wanted", "merges": "\u0120want ed", "raw_count": 103764, "count": 103764, "decode_str": " wanted"} -{"id": 36010, "token": "Fab", "merges": "F ab", "raw_count": 103764, "count": 103764, "decode_str": "Fab"} -{"id": 11440, "token": "\u0120continuing", "merges": "\u0120contin uing", "raw_count": 103767, "count": 103767, "decode_str": " continuing"} -{"id": 5185, "token": "\u0120consistent", "merges": "\u0120consist ent", "raw_count": 103774, "count": 103774, "decode_str": " consistent"} -{"id": 23495, "token": "Place", "merges": "Pl ace", "raw_count": 103786, "count": 103786, "decode_str": "Place"} -{"id": 10242, "token": "\u0120invent", "merges": "\u0120inv ent", "raw_count": 16766, "count": 103834, "decode_str": " invent"} -{"id": 30321, "token": "\u012010000", "merges": "\u01201 0000", "raw_count": 103856, "count": 103856, "decode_str": " 10000"} -{"id": 16699, "token": "CODE", "merges": "CO DE", "raw_count": 103886, "count": 103886, "decode_str": "CODE"} -{"id": 30524, "token": "ractor", "merges": "ract or", "raw_count": 103887, "count": 103887, "decode_str": "ractor"} -{"id": 29532, "token": "Grand", "merges": "Gr and", "raw_count": 103896, "count": 103896, "decode_str": "Grand"} -{"id": 3735, "token": "\u0120heard", "merges": "\u0120he ard", "raw_count": 103921, "count": 103921, "decode_str": " heard"} -{"id": 24039, "token": "\u0120axes", "merges": "\u0120ax es", "raw_count": 103924, "count": 103924, "decode_str": " axes"} -{"id": 26701, "token": "ursor", "merges": "urs or", "raw_count": 10762, "count": 103933, "decode_str": "ursor"} -{"id": 17584, "token": "oggle", "merges": "og gle", "raw_count": 9816, "count": 103938, "decode_str": "oggle"} -{"id": 21416, "token": "Xi", "merges": "X i", "raw_count": 103968, "count": 103968, "decode_str": "Xi"} -{"id": 22680, "token": "\u0120detention", "merges": "\u0120det ention", "raw_count": 103995, "count": 103995, "decode_str": " detention"} -{"id": 5383, "token": "\u0120Inter", "merges": "\u0120In ter", "raw_count": 61763, "count": 104003, "decode_str": " Inter"} -{"id": 26532, "token": "\u00ea\u00b0", "merges": "\u00ea \u00b0", "raw_count": 42369, "count": 104003, "decode_str": "\ufffd"} -{"id": 26031, "token": "Bus", "merges": "B us", "raw_count": 104023, "count": 104023, "decode_str": "Bus"} -{"id": 26078, "token": "Focus", "merges": "F ocus", "raw_count": 104034, "count": 104034, "decode_str": "Focus"} -{"id": 5779, "token": "\u0120Post", "merges": "\u0120P ost", "raw_count": 99260, "count": 104047, "decode_str": " Post"} -{"id": 5378, "token": "pir", "merges": "p ir", "raw_count": 49464, "count": 104058, "decode_str": "pir"} -{"id": 6283, "token": "\u0120properly", "merges": "\u0120proper ly", "raw_count": 104062, "count": 104062, "decode_str": " properly"} -{"id": 15748, "token": "ulse", "merges": "ul se", "raw_count": 48011, "count": 104095, "decode_str": "ulse"} -{"id": 9357, "token": "ped", "merges": "p ed", "raw_count": 97832, "count": 104095, "decode_str": "ped"} -{"id": 18920, "token": "para", "merges": "par a", "raw_count": 104119, "count": 104119, "decode_str": "para"} -{"id": 7508, "token": "\u00d0\u00b5\u00d1\u0124", "merges": "\u00d0\u00b5 \u00d1\u0124", "raw_count": 67242, "count": 104141, "decode_str": "\u0435\u0442"} -{"id": 23290, "token": "pull", "merges": "p ull", "raw_count": 104153, "count": 104153, "decode_str": "pull"} -{"id": 5839, "token": "\u0120investigation", "merges": "\u0120investig ation", "raw_count": 104190, "count": 104190, "decode_str": " investigation"} -{"id": 25811, "token": "\u0120\u00ed", "merges": "\u0120 \u00ed", "raw_count": 104198, "count": 104198, "decode_str": " \ufffd"} -{"id": 43467, "token": "(\"<", "merges": "(\" <", "raw_count": 104206, "count": 104206, "decode_str": "(\"<"} -{"id": 27418, "token": "tron", "merges": "tr on", "raw_count": 103137, "count": 104209, "decode_str": "tron"} -{"id": 33498, "token": "Poly", "merges": "Pol y", "raw_count": 104224, "count": 104224, "decode_str": "Poly"} -{"id": 6360, "token": "outhern", "merges": "out hern", "raw_count": 3686, "count": 104247, "decode_str": "outhern"} -{"id": 25431, "token": "alia", "merges": "al ia", "raw_count": 104252, "count": 104252, "decode_str": "alia"} -{"id": 22624, "token": "Fund", "merges": "F und", "raw_count": 98742, "count": 104283, "decode_str": "Fund"} -{"id": 14976, "token": "IFT", "merges": "IF T", "raw_count": 78821, "count": 104308, "decode_str": "IFT"} -{"id": 33786, "token": "\u0120pid", "merges": "\u0120p id", "raw_count": 104312, "count": 104312, "decode_str": " pid"} -{"id": 35744, "token": "bj", "merges": "b j", "raw_count": 104355, "count": 104355, "decode_str": "bj"} -{"id": 22738, "token": "bag", "merges": "b ag", "raw_count": 104360, "count": 104360, "decode_str": "bag"} -{"id": 4326, "token": "\u0120substant", "merges": "\u0120sub stant", "raw_count": 13460, "count": 104386, "decode_str": " substant"} -{"id": 3551, "token": "\u0120coming", "merges": "\u0120com ing", "raw_count": 104392, "count": 104392, "decode_str": " coming"} -{"id": 19250, "token": "PDATE", "merges": "PD ATE", "raw_count": 272, "count": 104449, "decode_str": "PDATE"} -{"id": 51574, "token": "\u00e5\u00ba\u0142", "merges": "\u00e5\u00ba \u0142", "raw_count": 104472, "count": 104472, "decode_str": "\u5ea0"} -{"id": 33922, "token": "Ids", "merges": "I ds", "raw_count": 104485, "count": 104485, "decode_str": "Ids"} -{"id": 25090, "token": "TY", "merges": "T Y", "raw_count": 104496, "count": 104496, "decode_str": "TY"} -{"id": 19765, "token": "0008", "merges": "000 8", "raw_count": 104525, "count": 104525, "decode_str": "0008"} -{"id": 5243, "token": "\u0120lif", "merges": "\u0120l if", "raw_count": 39401, "count": 104530, "decode_str": " lif"} -{"id": 3365, "token": "\u0120simply", "merges": "\u0120sim ply", "raw_count": 104540, "count": 104540, "decode_str": " simply"} -{"id": 9882, "token": "\u0120browser", "merges": "\u0120brow ser", "raw_count": 104559, "count": 104559, "decode_str": " browser"} -{"id": 4553, "token": "After", "merges": "A fter", "raw_count": 104564, "count": 104564, "decode_str": "After"} -{"id": 5061, "token": "\u0120uns", "merges": "\u0120un s", "raw_count": 47935, "count": 104579, "decode_str": " uns"} -{"id": 9250, "token": "yles", "merges": "y les", "raw_count": 10659, "count": 104615, "decode_str": "yles"} -{"id": 14448, "token": "\u0120collaboration", "merges": "\u0120collabor ation", "raw_count": 104682, "count": 104682, "decode_str": " collaboration"} -{"id": 15003, "token": "Http", "merges": "H ttp", "raw_count": 104686, "count": 104686, "decode_str": "Http"} -{"id": 11849, "token": "making", "merges": "m aking", "raw_count": 104733, "count": 104733, "decode_str": "making"} -{"id": 20712, "token": "ENC", "merges": "EN C", "raw_count": 104737, "count": 104737, "decode_str": "ENC"} -{"id": 8525, "token": "\u0120supports", "merges": "\u0120support s", "raw_count": 104795, "count": 104795, "decode_str": " supports"} -{"id": 6182, "token": "rape", "merges": "ra pe", "raw_count": 45537, "count": 104795, "decode_str": "rape"} -{"id": 6725, "token": "\u0120SE", "merges": "\u0120S E", "raw_count": 78475, "count": 104813, "decode_str": " SE"} -{"id": 11939, "token": "bow", "merges": "b ow", "raw_count": 90680, "count": 104820, "decode_str": "bow"} -{"id": 52215, "token": "\u00e6\u013f\u0135", "merges": "\u00e6\u013f \u0135", "raw_count": 104840, "count": 104840, "decode_str": "\u6753"} -{"id": 16591, "token": "Express", "merges": "Exp ress", "raw_count": 104862, "count": 104862, "decode_str": "Express"} -{"id": 4927, "token": "\u0120si", "merges": "\u0120s i", "raw_count": 103002, "count": 104886, "decode_str": " si"} -{"id": 38069, "token": "restore", "merges": "rest ore", "raw_count": 104887, "count": 104887, "decode_str": "restore"} -{"id": 9632, "token": "\u0120trigger", "merges": "\u0120trig ger", "raw_count": 98234, "count": 104891, "decode_str": " trigger"} -{"id": 45970, "token": "College", "merges": "Col lege", "raw_count": 104907, "count": 104907, "decode_str": "College"} -{"id": 3146, "token": "atively", "merges": "at ively", "raw_count": 27565, "count": 104917, "decode_str": "atively"} -{"id": 36228, "token": "CRO", "merges": "CR O", "raw_count": 104934, "count": 104934, "decode_str": "CRO"} -{"id": 9409, "token": "onia", "merges": "on ia", "raw_count": 102049, "count": 104949, "decode_str": "onia"} -{"id": 6139, "token": "\u0120implic", "merges": "\u0120im plic", "raw_count": 2343, "count": 104956, "decode_str": " implic"} -{"id": 17622, "token": "imo", "merges": "im o", "raw_count": 104959, "count": 104959, "decode_str": "imo"} -{"id": 4444, "token": "\u0120plant", "merges": "\u0120pl ant", "raw_count": 87745, "count": 104987, "decode_str": " plant"} -{"id": 34935, "token": "Rog", "merges": "R og", "raw_count": 44337, "count": 104994, "decode_str": "Rog"} -{"id": 35101, "token": "Mov", "merges": "M ov", "raw_count": 38578, "count": 105006, "decode_str": "Mov"} -{"id": 10370, "token": "\u0120bil", "merges": "\u0120b il", "raw_count": 21200, "count": 105009, "decode_str": " bil"} -{"id": 6881, "token": "jud", "merges": "j ud", "raw_count": 29879, "count": 105054, "decode_str": "jud"} -{"id": 51219, "token": "\u00e5\u0140\u013c", "merges": "\u00e5\u0140 \u013c", "raw_count": 105061, "count": 105061, "decode_str": "\u579a"} -{"id": 29760, "token": "Fast", "merges": "F ast", "raw_count": 105069, "count": 105069, "decode_str": "Fast"} -{"id": 12925, "token": "\u0120guidance", "merges": "\u0120guid ance", "raw_count": 105079, "count": 105079, "decode_str": " guidance"} -{"id": 4977, "token": "othe", "merges": "ot he", "raw_count": 82124, "count": 105081, "decode_str": "othe"} -{"id": 51188, "token": "\u00e5\u013e\u00bb", "merges": "\u00e5\u013e \u00bb", "raw_count": 105089, "count": 105089, "decode_str": "\u573b"} -{"id": 38503, "token": "574", "merges": "57 4", "raw_count": 105101, "count": 105101, "decode_str": "574"} -{"id": 27327, "token": "Site", "merges": "S ite", "raw_count": 105112, "count": 105112, "decode_str": "Site"} -{"id": 37308, "token": "594", "merges": "59 4", "raw_count": 105166, "count": 105166, "decode_str": "594"} -{"id": 7180, "token": "\u0120tables", "merges": "\u0120t ables", "raw_count": 103624, "count": 105174, "decode_str": " tables"} -{"id": 4711, "token": "\u0120produce", "merges": "\u0120produ ce", "raw_count": 105175, "count": 105175, "decode_str": " produce"} -{"id": 7223, "token": "\u0120pages", "merges": "\u0120p ages", "raw_count": 105175, "count": 105175, "decode_str": " pages"} -{"id": 16586, "token": "ordered", "merges": "or dered", "raw_count": 104137, "count": 105204, "decode_str": "ordered"} -{"id": 19352, "token": "Sample", "merges": "S ample", "raw_count": 105215, "count": 105215, "decode_str": "Sample"} -{"id": 24354, "token": "Mur", "merges": "M ur", "raw_count": 105221, "count": 105221, "decode_str": "Mur"} -{"id": 46676, "token": "735", "merges": "7 35", "raw_count": 105311, "count": 105311, "decode_str": "735"} -{"id": 33822, "token": "Distance", "merges": "D istance", "raw_count": 105342, "count": 105342, "decode_str": "Distance"} -{"id": 39336, "token": "feel", "merges": "fe el", "raw_count": 105348, "count": 105348, "decode_str": "feel"} -{"id": 14762, "token": "ritical", "merges": "rit ical", "raw_count": 2377, "count": 105357, "decode_str": "ritical"} -{"id": 7450, "token": "\u0120push", "merges": "\u0120p ush", "raw_count": 105360, "count": 105360, "decode_str": " push"} -{"id": 12290, "token": "aser", "merges": "as er", "raw_count": 97060, "count": 105411, "decode_str": "aser"} -{"id": 47460, "token": "formatter", "merges": "form atter", "raw_count": 105442, "count": 105442, "decode_str": "formatter"} -{"id": 26256, "token": "Adv", "merges": "Ad v", "raw_count": 32257, "count": 105468, "decode_str": "Adv"} -{"id": 3564, "token": "\u0120hands", "merges": "\u0120hand s", "raw_count": 99181, "count": 105472, "decode_str": " hands"} -{"id": 7321, "token": "\u0120modified", "merges": "\u0120mod ified", "raw_count": 105473, "count": 105473, "decode_str": " modified"} -{"id": 36942, "token": "Pick", "merges": "P ick", "raw_count": 105476, "count": 105476, "decode_str": "Pick"} -{"id": 22246, "token": "Children", "merges": "Child ren", "raw_count": 105525, "count": 105525, "decode_str": "Children"} -{"id": 52687, "token": "\u00e6\u00ba\u00b1", "merges": "\u00e6\u00ba \u00b1", "raw_count": 105546, "count": 105546, "decode_str": "\u6eb1"} -{"id": 7202, "token": "\u0120unknown", "merges": "\u0120un known", "raw_count": 105574, "count": 105574, "decode_str": " unknown"} -{"id": 33142, "token": "\u0120Invalid", "merges": "\u0120In valid", "raw_count": 105622, "count": 105622, "decode_str": " Invalid"} -{"id": 7324, "token": "\u0120competition", "merges": "\u0120comp etition", "raw_count": 97851, "count": 105636, "decode_str": " competition"} -{"id": 8597, "token": "\u0120desk", "merges": "\u0120des k", "raw_count": 81761, "count": 105650, "decode_str": " desk"} -{"id": 18641, "token": "protected", "merges": "prote cted", "raw_count": 105682, "count": 105682, "decode_str": "protected"} -{"id": 20605, "token": "\u0120async", "merges": "\u0120as ync", "raw_count": 105739, "count": 105739, "decode_str": " async"} -{"id": 10108, "token": "ilation", "merges": "il ation", "raw_count": 69357, "count": 105766, "decode_str": "ilation"} -{"id": 18491, "token": "\u0120repository", "merges": "\u0120repos itory", "raw_count": 105778, "count": 105778, "decode_str": " repository"} -{"id": 7029, "token": "\u00d0\u00b5\u00d1\u0122", "merges": "\u00d0\u00b5 \u00d1\u0122", "raw_count": 80634, "count": 105783, "decode_str": "\u0435\u0440"} -{"id": 14873, "token": "ogue", "merges": "og ue", "raw_count": 90343, "count": 105788, "decode_str": "ogue"} -{"id": 14311, "token": "\u0120Run", "merges": "\u0120R un", "raw_count": 105807, "count": 105807, "decode_str": " Run"} -{"id": 23105, "token": "\u0120ai", "merges": "\u0120a i", "raw_count": 105823, "count": 105823, "decode_str": " ai"} -{"id": 38022, "token": "AMA", "merges": "AM A", "raw_count": 105830, "count": 105830, "decode_str": "AMA"} -{"id": 23542, "token": "\u0120mp", "merges": "\u0120m p", "raw_count": 105846, "count": 105846, "decode_str": " mp"} -{"id": 52382, "token": "\u00e6\u00a9\u00bc", "merges": "\u00e6\u00a9 \u00bc", "raw_count": 105851, "count": 105851, "decode_str": "\u6a7c"} -{"id": 10037, "token": "alls", "merges": "all s", "raw_count": 58422, "count": 105853, "decode_str": "alls"} -{"id": 25467, "token": "Metadata", "merges": "Met adata", "raw_count": 105862, "count": 105862, "decode_str": "Metadata"} -{"id": 29181, "token": "Union", "merges": "Un ion", "raw_count": 105922, "count": 105922, "decode_str": "Union"} -{"id": 35938, "token": "MAR", "merges": "M AR", "raw_count": 105924, "count": 105924, "decode_str": "MAR"} -{"id": 7839, "token": "ilton", "merges": "il ton", "raw_count": 66029, "count": 105943, "decode_str": "ilton"} -{"id": 42186, "token": "ticket", "merges": "t icket", "raw_count": 105980, "count": 105980, "decode_str": "ticket"} -{"id": 4845, "token": "\u0120placed", "merges": "\u0120pl aced", "raw_count": 106003, "count": 106003, "decode_str": " placed"} -{"id": 7903, "token": "\u0120Max", "merges": "\u0120M ax", "raw_count": 88294, "count": 106006, "decode_str": " Max"} -{"id": 24583, "token": "youtube", "merges": "y outube", "raw_count": 106017, "count": 106017, "decode_str": "youtube"} -{"id": 8023, "token": "apse", "merges": "ap se", "raw_count": 56539, "count": 106047, "decode_str": "apse"} -{"id": 32117, "token": "minutes", "merges": "min utes", "raw_count": 106055, "count": 106055, "decode_str": "minutes"} -{"id": 21637, "token": "social", "merges": "s ocial", "raw_count": 106064, "count": 106064, "decode_str": "social"} -{"id": 10875, "token": "\u0120liber", "merges": "\u0120l iber", "raw_count": 67307, "count": 106073, "decode_str": " liber"} -{"id": 4201, "token": "\u0120birth", "merges": "\u0120bir th", "raw_count": 68371, "count": 106091, "decode_str": " birth"} -{"id": 11068, "token": "\u0120privacy", "merges": "\u0120priv acy", "raw_count": 106103, "count": 106103, "decode_str": " privacy"} -{"id": 24436, "token": "Raw", "merges": "R aw", "raw_count": 106133, "count": 106133, "decode_str": "Raw"} -{"id": 3704, "token": "****************", "merges": "******** ********", "raw_count": 24390, "count": 106150, "decode_str": "****************"} -{"id": 29777, "token": "tele", "merges": "te le", "raw_count": 106170, "count": 106170, "decode_str": "tele"} -{"id": 21362, "token": "ulu", "merges": "ul u", "raw_count": 106203, "count": 106203, "decode_str": "ulu"} -{"id": 53209, "token": "\u00e7\u00ac\u0131", "merges": "\u00e7\u00ac \u0131", "raw_count": 106207, "count": 106207, "decode_str": "\u7b0f"} -{"id": 8039, "token": "\u0120housing", "merges": "\u0120hous ing", "raw_count": 106228, "count": 106228, "decode_str": " housing"} -{"id": 30428, "token": "Sol", "merges": "S ol", "raw_count": 106234, "count": 106234, "decode_str": "Sol"} -{"id": 41528, "token": "algorithm", "merges": "al gorithm", "raw_count": 106241, "count": 106241, "decode_str": "algorithm"} -{"id": 10112, "token": "\u0120welcome", "merges": "\u0120wel come", "raw_count": 106260, "count": 106260, "decode_str": " welcome"} -{"id": 16533, "token": "eded", "merges": "ed ed", "raw_count": 44204, "count": 106262, "decode_str": "eded"} -{"id": 22357, "token": "uli", "merges": "ul i", "raw_count": 106294, "count": 106294, "decode_str": "uli"} -{"id": 13009, "token": "\u0120frames", "merges": "\u0120fr ames", "raw_count": 106306, "count": 106306, "decode_str": " frames"} -{"id": 13364, "token": "Eval", "merges": "E val", "raw_count": 58042, "count": 106341, "decode_str": "Eval"} -{"id": 8593, "token": "\u0120locations", "merges": "\u0120loc ations", "raw_count": 106343, "count": 106343, "decode_str": " locations"} -{"id": 2070, "token": "\u0120Le", "merges": "\u0120L e", "raw_count": 40197, "count": 106355, "decode_str": " Le"} -{"id": 47628, "token": "nested", "merges": "n ested", "raw_count": 106379, "count": 106379, "decode_str": "nested"} -{"id": 19656, "token": "allenge", "merges": "all enge", "raw_count": 34736, "count": 106411, "decode_str": "allenge"} -{"id": 7163, "token": "\u0120nom", "merges": "\u0120n om", "raw_count": 32165, "count": 106418, "decode_str": " nom"} -{"id": 9457, "token": "rene", "merges": "ren e", "raw_count": 49309, "count": 106420, "decode_str": "rene"} -{"id": 53747, "token": "\u00e8\u00a3\u00be", "merges": "\u00e8\u00a3 \u00be", "raw_count": 106441, "count": 106441, "decode_str": "\u88fe"} -{"id": 31853, "token": "Nick", "merges": "N ick", "raw_count": 106471, "count": 106471, "decode_str": "Nick"} -{"id": 3622, "token": "\u0120ago", "merges": "\u0120ag o", "raw_count": 106477, "count": 106477, "decode_str": " ago"} -{"id": 44975, "token": "andidates", "merges": "andid ates", "raw_count": 106499, "count": 106499, "decode_str": "andidates"} -{"id": 22573, "token": "\u0120encode", "merges": "\u0120enc ode", "raw_count": 106508, "count": 106508, "decode_str": " encode"} -{"id": 8371, "token": "\u0120academ", "merges": "\u0120ac adem", "raw_count": 12813, "count": 106509, "decode_str": " academ"} -{"id": 4001, "token": "undred", "merges": "und red", "raw_count": 4113, "count": 106529, "decode_str": "undred"} -{"id": 34363, "token": "992", "merges": "99 2", "raw_count": 106548, "count": 106548, "decode_str": "992"} -{"id": 26175, "token": "cool", "merges": "c ool", "raw_count": 106552, "count": 106552, "decode_str": "cool"} -{"id": 50929, "token": "\u00e5\u0131\u00a1", "merges": "\u00e5\u0131 \u00a1", "raw_count": 106578, "count": 106578, "decode_str": "\u53e1"} -{"id": 10130, "token": "\u0120schedule", "merges": "\u0120sche dule", "raw_count": 106580, "count": 106580, "decode_str": " schedule"} -{"id": 10251, "token": "\u0120emphas", "merges": "\u0120emph as", "raw_count": 3763, "count": 106593, "decode_str": " emphas"} -{"id": 8323, "token": "\u0120windows", "merges": "\u0120window s", "raw_count": 106608, "count": 106608, "decode_str": " windows"} -{"id": 23250, "token": "763", "merges": "76 3", "raw_count": 106608, "count": 106608, "decode_str": "763"} -{"id": 23485, "token": "camp", "merges": "c amp", "raw_count": 56753, "count": 106617, "decode_str": "camp"} -{"id": 13535, "token": "idi", "merges": "id i", "raw_count": 106628, "count": 106628, "decode_str": "idi"} -{"id": 8857, "token": "\u0120chapter", "merges": "\u0120ch apter", "raw_count": 106685, "count": 106685, "decode_str": " chapter"} -{"id": 10234, "token": "\u0120translation", "merges": "\u0120trans lation", "raw_count": 106694, "count": 106694, "decode_str": " translation"} -{"id": 6314, "token": "\u0120epis", "merges": "\u0120ep is", "raw_count": 3777, "count": 106695, "decode_str": " epis"} -{"id": 2994, "token": "\u0120himself", "merges": "\u0120him self", "raw_count": 106702, "count": 106702, "decode_str": " himself"} -{"id": 37644, "token": "571", "merges": "57 1", "raw_count": 106708, "count": 106708, "decode_str": "571"} -{"id": 29193, "token": "LIN", "merges": "L IN", "raw_count": 106723, "count": 106723, "decode_str": "LIN"} -{"id": 8105, "token": "\u0120tail", "merges": "\u0120t ail", "raw_count": 85641, "count": 106730, "decode_str": " tail"} -{"id": 40712, "token": "phrase", "merges": "ph rase", "raw_count": 106732, "count": 106732, "decode_str": "phrase"} -{"id": 13650, "token": "\u0120predictions", "merges": "\u0120predict ions", "raw_count": 106736, "count": 106736, "decode_str": " predictions"} -{"id": 6503, "token": "\u0120insurance", "merges": "\u0120ins urance", "raw_count": 106745, "count": 106745, "decode_str": " insurance"} -{"id": 2864, "token": "\u0120decre", "merges": "\u0120de cre", "raw_count": 15296, "count": 106747, "decode_str": " decre"} -{"id": 12939, "token": "\u0120chat", "merges": "\u0120ch at", "raw_count": 104382, "count": 106799, "decode_str": " chat"} -{"id": 10951, "token": "Second", "merges": "Se cond", "raw_count": 65807, "count": 106803, "decode_str": "Second"} -{"id": 23873, "token": "\u0120audit", "merges": "\u0120aud it", "raw_count": 106806, "count": 106806, "decode_str": " audit"} -{"id": 41081, "token": "561", "merges": "56 1", "raw_count": 106813, "count": 106813, "decode_str": "561"} -{"id": 36423, "token": "easy", "merges": "e asy", "raw_count": 106843, "count": 106843, "decode_str": "easy"} -{"id": 27739, "token": "\u00e2\u0139", "merges": "\u00e2 \u0139", "raw_count": 3803, "count": 106843, "decode_str": "\ufffd"} -{"id": 39705, "token": "\u0120))", "merges": "\u0120 ))", "raw_count": 106870, "count": 106870, "decode_str": " ))"} -{"id": 3416, "token": "\u0120woman", "merges": "\u0120wom an", "raw_count": 106897, "count": 106897, "decode_str": " woman"} -{"id": 6965, "token": "apped", "merges": "app ed", "raw_count": 47775, "count": 106908, "decode_str": "apped"} -{"id": 10346, "token": "\u0120migration", "merges": "\u0120mig ration", "raw_count": 106921, "count": 106921, "decode_str": " migration"} -{"id": 25512, "token": "fif", "merges": "f if", "raw_count": 106941, "count": 106941, "decode_str": "fif"} -{"id": 10510, "token": "aron", "merges": "ar on", "raw_count": 105998, "count": 106947, "decode_str": "aron"} -{"id": 6419, "token": "ishes", "merges": "is hes", "raw_count": 29716, "count": 106956, "decode_str": "ishes"} -{"id": 5174, "token": "otype", "merges": "ot ype", "raw_count": 63390, "count": 106968, "decode_str": "otype"} -{"id": 4153, "token": "Omega", "merges": "O mega", "raw_count": 106974, "count": 106974, "decode_str": "Omega"} -{"id": 23296, "token": "ICA", "merges": "IC A", "raw_count": 106755, "count": 106982, "decode_str": "ICA"} -{"id": 22395, "token": "SPE", "merges": "S PE", "raw_count": 81563, "count": 107007, "decode_str": "SPE"} -{"id": 29823, "token": "Matt", "merges": "M att", "raw_count": 107022, "count": 107022, "decode_str": "Matt"} -{"id": 29516, "token": "\u0120Iter", "merges": "\u0120I ter", "raw_count": 107032, "count": 107032, "decode_str": " Iter"} -{"id": 11515, "token": "\u0120languages", "merges": "\u0120l anguages", "raw_count": 107034, "count": 107034, "decode_str": " languages"} -{"id": 50053, "token": "Redirect", "merges": "Red irect", "raw_count": 107055, "count": 107055, "decode_str": "Redirect"} -{"id": 37812, "token": "0027", "merges": "00 27", "raw_count": 107061, "count": 107061, "decode_str": "0027"} -{"id": 5331, "token": "\u0120century", "merges": "\u0120cent ury", "raw_count": 107062, "count": 107062, "decode_str": " century"} -{"id": 34769, "token": "692", "merges": "69 2", "raw_count": 107095, "count": 107095, "decode_str": "692"} -{"id": 7832, "token": "\u0120partner", "merges": "\u0120part ner", "raw_count": 107159, "count": 107159, "decode_str": " partner"} -{"id": 5233, "token": "\u0120rapid", "merges": "\u0120ra pid", "raw_count": 65884, "count": 107159, "decode_str": " rapid"} -{"id": 21845, "token": "trial", "merges": "t rial", "raw_count": 107198, "count": 107198, "decode_str": "trial"} -{"id": 53985, "token": "\u00e8\u00b6\u00b5", "merges": "\u00e8\u00b6 \u00b5", "raw_count": 107204, "count": 107204, "decode_str": "\u8db5"} -{"id": 35413, "token": "received", "merges": "re ceived", "raw_count": 107207, "count": 107207, "decode_str": "received"} -{"id": 54542, "token": "\u00e6\u00a5\u00a6", "merges": "\u00e6\u00a5 \u00a6", "raw_count": 107210, "count": 107210, "decode_str": "\u6966"} -{"id": 2849, "token": "\u0120magn", "merges": "\u0120m agn", "raw_count": 13043, "count": 107213, "decode_str": " magn"} -{"id": 25233, "token": "_\"", "merges": "_ \"", "raw_count": 107215, "count": 107215, "decode_str": "_\""} -{"id": 2934, "token": "\u0120idea", "merges": "\u0120ide a", "raw_count": 107226, "count": 107226, "decode_str": " idea"} -{"id": 43924, "token": "573", "merges": "57 3", "raw_count": 107243, "count": 107243, "decode_str": "573"} -{"id": 34345, "token": "Idx", "merges": "Id x", "raw_count": 107258, "count": 107258, "decode_str": "Idx"} -{"id": 16374, "token": "large", "merges": "lar ge", "raw_count": 100599, "count": 107261, "decode_str": "large"} -{"id": 3731, "token": "\u0120mis", "merges": "\u0120m is", "raw_count": 51061, "count": 107267, "decode_str": " mis"} -{"id": 52611, "token": "\u00e6\u00b6\u0142", "merges": "\u00e6\u00b6 \u0142", "raw_count": 107279, "count": 107279, "decode_str": "\u6da0"} -{"id": 8366, "token": "\u0120overl", "merges": "\u0120over l", "raw_count": 4299, "count": 107281, "decode_str": " overl"} -{"id": 20707, "token": "mart", "merges": "m art", "raw_count": 107158, "count": 107281, "decode_str": "mart"} -{"id": 27190, "token": "drive", "merges": "d rive", "raw_count": 107298, "count": 107298, "decode_str": "drive"} -{"id": 40379, "token": "771", "merges": "77 1", "raw_count": 107307, "count": 107307, "decode_str": "771"} -{"id": 38092, "token": "additional", "merges": "addition al", "raw_count": 107316, "count": 107316, "decode_str": "additional"} -{"id": 24490, "token": "Tri", "merges": "T ri", "raw_count": 107325, "count": 107325, "decode_str": "Tri"} -{"id": 24966, "token": "wl", "merges": "w l", "raw_count": 107326, "count": 107326, "decode_str": "wl"} -{"id": 3863, "token": "\u0120published", "merges": "\u0120publ ished", "raw_count": 107329, "count": 107329, "decode_str": " published"} -{"id": 6440, "token": "\u0120movie", "merges": "\u0120mov ie", "raw_count": 107333, "count": 107333, "decode_str": " movie"} -{"id": 18060, "token": "\u0120pand", "merges": "\u0120p and", "raw_count": 8982, "count": 107339, "decode_str": " pand"} -{"id": 9598, "token": "estion", "merges": "est ion", "raw_count": 10329, "count": 107351, "decode_str": "estion"} -{"id": 29300, "token": "Walk", "merges": "W alk", "raw_count": 56341, "count": 107362, "decode_str": "Walk"} -{"id": 42633, "token": "553", "merges": "55 3", "raw_count": 107401, "count": 107401, "decode_str": "553"} -{"id": 4872, "token": "\u0120linear", "merges": "\u0120line ar", "raw_count": 106674, "count": 107433, "decode_str": " linear"} -{"id": 5009, "token": "atin", "merges": "at in", "raw_count": 68439, "count": 107441, "decode_str": "atin"} -{"id": 12958, "token": "\u0120guests", "merges": "\u0120gu ests", "raw_count": 107445, "count": 107445, "decode_str": " guests"} -{"id": 45055, "token": "Wu", "merges": "W u", "raw_count": 107451, "count": 107451, "decode_str": "Wu"} -{"id": 7788, "token": "\u0120continues", "merges": "\u0120contin ues", "raw_count": 107453, "count": 107453, "decode_str": " continues"} -{"id": 6797, "token": "\u0120deg", "merges": "\u0120de g", "raw_count": 31706, "count": 107468, "decode_str": " deg"} -{"id": 28578, "token": "Ell", "merges": "E ll", "raw_count": 107471, "count": 107471, "decode_str": "Ell"} -{"id": 3534, "token": "\u0120gave", "merges": "\u0120g ave", "raw_count": 107498, "count": 107498, "decode_str": " gave"} -{"id": 12384, "token": "rooms", "merges": "ro oms", "raw_count": 74651, "count": 107510, "decode_str": "rooms"} -{"id": 14161, "token": "cpp", "merges": "c pp", "raw_count": 107515, "count": 107515, "decode_str": "cpp"} -{"id": 5957, "token": "resents", "merges": "res ents", "raw_count": 14202, "count": 107517, "decode_str": "resents"} -{"id": 27861, "token": "rout", "merges": "r out", "raw_count": 107533, "count": 107533, "decode_str": "rout"} -{"id": 18459, "token": ":#", "merges": ": #", "raw_count": 107658, "count": 107658, "decode_str": ":#"} -{"id": 7939, "token": "\u0120linked", "merges": "\u0120link ed", "raw_count": 107662, "count": 107662, "decode_str": " linked"} -{"id": 11925, "token": "ryst", "merges": "ry st", "raw_count": 13564, "count": 107675, "decode_str": "ryst"} -{"id": 17546, "token": "\u0120islands", "merges": "\u0120is lands", "raw_count": 107705, "count": 107705, "decode_str": " islands"} -{"id": 4852, "token": "\u0120lives", "merges": "\u0120l ives", "raw_count": 107710, "count": 107710, "decode_str": " lives"} -{"id": 18008, "token": "ryption", "merges": "ry ption", "raw_count": 78471, "count": 107712, "decode_str": "ryption"} -{"id": 31962, "token": "Camera", "merges": "Cam era", "raw_count": 107714, "count": 107714, "decode_str": "Camera"} -{"id": 40616, "token": "Lady", "merges": "L ady", "raw_count": 107716, "count": 107716, "decode_str": "Lady"} -{"id": 27239, "token": "YOU", "merges": "Y OU", "raw_count": 107731, "count": 107731, "decode_str": "YOU"} -{"id": 3965, "token": "\u0120pretty", "merges": "\u0120pret ty", "raw_count": 107757, "count": 107757, "decode_str": " pretty"} -{"id": 9274, "token": "idents", "merges": "id ents", "raw_count": 31532, "count": 107765, "decode_str": "idents"} -{"id": 28253, "token": "Plot", "merges": "Pl ot", "raw_count": 107783, "count": 107783, "decode_str": "Plot"} -{"id": 8356, "token": "\u0120automatically", "merges": "\u0120autom atically", "raw_count": 107794, "count": 107794, "decode_str": " automatically"} -{"id": 5362, "token": "\u0120scen", "merges": "\u0120sc en", "raw_count": 2273, "count": 107794, "decode_str": " scen"} -{"id": 13725, "token": "\u0120dump", "merges": "\u0120d ump", "raw_count": 91158, "count": 107814, "decode_str": " dump"} -{"id": 6833, "token": "\u0120manufacture", "merges": "\u0120manufact ure", "raw_count": 31832, "count": 107825, "decode_str": " manufacture"} -{"id": 3560, "token": "\u0120followed", "merges": "\u0120follow ed", "raw_count": 107825, "count": 107825, "decode_str": " followed"} -{"id": 8613, "token": "mediate", "merges": "medi ate", "raw_count": 74864, "count": 107843, "decode_str": "mediate"} -{"id": 15505, "token": "minute", "merges": "min ute", "raw_count": 107849, "count": 107849, "decode_str": "minute"} -{"id": 34462, "token": "KI", "merges": "K I", "raw_count": 107882, "count": 107882, "decode_str": "KI"} -{"id": 42150, "token": "preview", "merges": "pre view", "raw_count": 107908, "count": 107908, "decode_str": "preview"} -{"id": 5611, "token": "\u0120introduced", "merges": "\u0120introdu ced", "raw_count": 107937, "count": 107937, "decode_str": " introduced"} -{"id": 45197, "token": "087", "merges": "0 87", "raw_count": 107956, "count": 107956, "decode_str": "087"} -{"id": 28288, "token": "icator", "merges": "ic ator", "raw_count": 108009, "count": 108009, "decode_str": "icator"} -{"id": 38212, "token": "wc", "merges": "w c", "raw_count": 108012, "count": 108012, "decode_str": "wc"} -{"id": 4144, "token": "psi", "merges": "ps i", "raw_count": 108035, "count": 108035, "decode_str": "psi"} -{"id": 19553, "token": "\u0120retrieve", "merges": "\u0120ret rieve", "raw_count": 108045, "count": 108045, "decode_str": " retrieve"} -{"id": 26801, "token": "\u0120charter", "merges": "\u0120char ter", "raw_count": 108089, "count": 108089, "decode_str": " charter"} -{"id": 48943, "token": "Blog", "merges": "B log", "raw_count": 108125, "count": 108125, "decode_str": "Blog"} -{"id": 36884, "token": "diss", "merges": "d iss", "raw_count": 108159, "count": 108159, "decode_str": "diss"} -{"id": 12586, "token": "enz", "merges": "en z", "raw_count": 84191, "count": 108172, "decode_str": "enz"} -{"id": 4665, "token": "\u0120interpret", "merges": "\u0120inter pret", "raw_count": 25109, "count": 108191, "decode_str": " interpret"} -{"id": 6699, "token": "\u0120finished", "merges": "\u0120fin ished", "raw_count": 108203, "count": 108203, "decode_str": " finished"} -{"id": 149, "token": "\u00d9", "merges": "NULL", "raw_count": 6757, "count": 108216, "decode_str": "\ufffd"} -{"id": 5167, "token": "\u0120susp", "merges": "\u0120sus p", "raw_count": 5705, "count": 108301, "decode_str": " susp"} -{"id": 40761, "token": "773", "merges": "77 3", "raw_count": 108311, "count": 108311, "decode_str": "773"} -{"id": 6109, "token": "\u0120mobile", "merges": "\u0120m obile", "raw_count": 108329, "count": 108329, "decode_str": " mobile"} -{"id": 45225, "token": "534", "merges": "5 34", "raw_count": 108350, "count": 108350, "decode_str": "534"} -{"id": 1413, "token": "Category", "merges": "C ategory", "raw_count": 108377, "count": 108377, "decode_str": "Category"} -{"id": 7272, "token": "amber", "merges": "am ber", "raw_count": 45948, "count": 108387, "decode_str": "amber"} -{"id": 4209, "token": "\u0120sufficient", "merges": "\u0120su fficient", "raw_count": 87323, "count": 108417, "decode_str": " sufficient"} -{"id": 5357, "token": "\u0120Net", "merges": "\u0120N et", "raw_count": 31488, "count": 108417, "decode_str": " Net"} -{"id": 19212, "token": "INGS", "merges": "ING S", "raw_count": 108459, "count": 108459, "decode_str": "INGS"} -{"id": 19774, "token": "Func", "merges": "F unc", "raw_count": 108473, "count": 108473, "decode_str": "Func"} -{"id": 26209, "token": "talk", "merges": "t alk", "raw_count": 108487, "count": 108487, "decode_str": "talk"} -{"id": 42532, "token": "pip", "merges": "p ip", "raw_count": 108540, "count": 108540, "decode_str": "pip"} -{"id": 35478, "token": "nf", "merges": "n f", "raw_count": 108578, "count": 108578, "decode_str": "nf"} -{"id": 22141, "token": "bx", "merges": "b x", "raw_count": 108595, "count": 108595, "decode_str": "bx"} -{"id": 35002, "token": "connections", "merges": "conne ctions", "raw_count": 108624, "count": 108624, "decode_str": "connections"} -{"id": 25050, "token": "disabled", "merges": "dis abled", "raw_count": 108633, "count": 108633, "decode_str": "disabled"} -{"id": 7894, "token": "arsh", "merges": "ars h", "raw_count": 32735, "count": 108643, "decode_str": "arsh"} -{"id": 9005, "token": "\u0120cloud", "merges": "\u0120cl oud", "raw_count": 108676, "count": 108676, "decode_str": " cloud"} -{"id": 6521, "token": "\u0120mouse", "merges": "\u0120m ouse", "raw_count": 108694, "count": 108694, "decode_str": " mouse"} -{"id": 29234, "token": ";_", "merges": "; _", "raw_count": 108703, "count": 108703, "decode_str": ";_"} -{"id": 6936, "token": "\u0120skills", "merges": "\u0120sk ills", "raw_count": 108712, "count": 108712, "decode_str": " skills"} -{"id": 4860, "token": "\u0120indicated", "merges": "\u0120indic ated", "raw_count": 108732, "count": 108732, "decode_str": " indicated"} -{"id": 2722, "token": "\u0120shows", "merges": "\u0120show s", "raw_count": 108752, "count": 108752, "decode_str": " shows"} -{"id": 7969, "token": "arks", "merges": "ar ks", "raw_count": 65568, "count": 108791, "decode_str": "arks"} -{"id": 12580, "token": "\u0120pi", "merges": "\u0120p i", "raw_count": 108122, "count": 108829, "decode_str": " pi"} -{"id": 5398, "token": "\u0120prem", "merges": "\u0120pre m", "raw_count": 9476, "count": 108839, "decode_str": " prem"} -{"id": 10484, "token": "\u012077", "merges": "\u01207 7", "raw_count": 108844, "count": 108844, "decode_str": " 77"} -{"id": 2529, "token": "\u0120described", "merges": "\u0120describ ed", "raw_count": 108874, "count": 108874, "decode_str": " described"} -{"id": 11289, "token": "\u012089", "merges": "\u01208 9", "raw_count": 108879, "count": 108879, "decode_str": " 89"} -{"id": 10097, "token": "\u0120documentation", "merges": "\u0120document ation", "raw_count": 108881, "count": 108881, "decode_str": " documentation"} -{"id": 21766, "token": "LOC", "merges": "L OC", "raw_count": 64209, "count": 108881, "decode_str": "LOC"} -{"id": 53027, "token": "\u00e7\u013f\u00a5", "merges": "\u00e7\u013f \u00a5", "raw_count": 108886, "count": 108886, "decode_str": "\u7765"} -{"id": 13116, "token": "effective", "merges": "effect ive", "raw_count": 101443, "count": 108915, "decode_str": "effective"} -{"id": 6084, "token": "cknow", "merges": "ck now", "raw_count": 2488, "count": 108929, "decode_str": "cknow"} -{"id": 15722, "token": "\u0120pipeline", "merges": "\u0120pip eline", "raw_count": 108940, "count": 108940, "decode_str": " pipeline"} -{"id": 43780, "token": "shut", "merges": "sh ut", "raw_count": 108962, "count": 108962, "decode_str": "shut"} -{"id": 10494, "token": "&&", "merges": "& &", "raw_count": 108985, "count": 108985, "decode_str": "&&"} -{"id": 53256, "token": "\u00e7\u00b1\u00bc", "merges": "\u00e7\u00b1 \u00bc", "raw_count": 108989, "count": 108989, "decode_str": "\u7c7c"} -{"id": 33914, "token": "Mesh", "merges": "M esh", "raw_count": 109003, "count": 109003, "decode_str": "Mesh"} -{"id": 5734, "token": "\u0120unless", "merges": "\u0120un less", "raw_count": 109012, "count": 109012, "decode_str": " unless"} -{"id": 21566, "token": "\u0120404", "merges": "\u01204 04", "raw_count": 109029, "count": 109029, "decode_str": " 404"} -{"id": 32031, "token": "Chen", "merges": "C hen", "raw_count": 109038, "count": 109038, "decode_str": "Chen"} -{"id": 1341, "token": "\u0120cells", "merges": "\u0120cell s", "raw_count": 109088, "count": 109088, "decode_str": " cells"} -{"id": 16978, "token": "Writer", "merges": "W riter", "raw_count": 109094, "count": 109094, "decode_str": "Writer"} -{"id": 10800, "token": "\u0120ongoing", "merges": "\u0120on going", "raw_count": 109146, "count": 109146, "decode_str": " ongoing"} -{"id": 7015, "token": "\u0120chief", "merges": "\u0120ch ief", "raw_count": 97697, "count": 109159, "decode_str": " chief"} -{"id": 2011, "token": "\u0120shown", "merges": "\u0120sh own", "raw_count": 109195, "count": 109195, "decode_str": " shown"} -{"id": 3274, "token": "ecause", "merges": "ec ause", "raw_count": 299, "count": 109221, "decode_str": "ecause"} -{"id": 16005, "token": "\u0120parliament", "merges": "\u0120par liament", "raw_count": 77963, "count": 109224, "decode_str": " parliament"} -{"id": 29627, "token": "Jun", "merges": "J un", "raw_count": 109228, "count": 109228, "decode_str": "Jun"} -{"id": 4211, "token": "\u0120sold", "merges": "\u0120s old", "raw_count": 48647, "count": 109284, "decode_str": " sold"} -{"id": 12241, "token": "REE", "merges": "RE E", "raw_count": 73888, "count": 109287, "decode_str": "REE"} -{"id": 53455, "token": "\u00e8\u0122\u00a8", "merges": "\u00e8\u0122 \u00a8", "raw_count": 109298, "count": 109298, "decode_str": "\u8028"} -{"id": 4891, "token": "\u0120solid", "merges": "\u0120sol id", "raw_count": 69151, "count": 109392, "decode_str": " solid"} -{"id": 7898, "token": "\u0120partial", "merges": "\u0120part ial", "raw_count": 109394, "count": 109394, "decode_str": " partial"} -{"id": 3798, "token": "\u0120usually", "merges": "\u0120us ually", "raw_count": 109416, "count": 109416, "decode_str": " usually"} -{"id": 19499, "token": "FLAGS", "merges": "FLAG S", "raw_count": 109448, "count": 109448, "decode_str": "FLAGS"} -{"id": 11138, "token": "\u0120improving", "merges": "\u0120impro ving", "raw_count": 109463, "count": 109463, "decode_str": " improving"} -{"id": 10393, "token": "\u0120usage", "merges": "\u0120us age", "raw_count": 109465, "count": 109465, "decode_str": " usage"} -{"id": 4850, "token": "\u0120gets", "merges": "\u0120get s", "raw_count": 109469, "count": 109469, "decode_str": " gets"} -{"id": 50880, "token": "\u00e5\u012f\u0141", "merges": "\u00e5\u012f \u0141", "raw_count": 109498, "count": 109498, "decode_str": "\u535f"} -{"id": 27295, "token": "\u01203000", "merges": "\u01203 000", "raw_count": 109500, "count": 109500, "decode_str": " 3000"} -{"id": 51658, "token": "\u00e5\u00be\u00b3", "merges": "\u00e5\u00be \u00b3", "raw_count": 109507, "count": 109507, "decode_str": "\u5fb3"} -{"id": 16526, "token": "wat", "merges": "w at", "raw_count": 91128, "count": 109511, "decode_str": "wat"} -{"id": 35410, "token": "993", "merges": "99 3", "raw_count": 109516, "count": 109516, "decode_str": "993"} -{"id": 4582, "token": "\u0120arriv", "merges": "\u0120ar riv", "raw_count": 6712, "count": 109566, "decode_str": " arriv"} -{"id": 16141, "token": "\u0120\u00ef", "merges": "\u0120 \u00ef", "raw_count": 109528, "count": 109571, "decode_str": " \ufffd"} -{"id": 3249, "token": "\u0120comes", "merges": "\u0120com es", "raw_count": 109574, "count": 109574, "decode_str": " comes"} -{"id": 32659, "token": "\u0120opts", "merges": "\u0120opt s", "raw_count": 109607, "count": 109607, "decode_str": " opts"} -{"id": 5111, "token": "\u0120um", "merges": "\u0120 um", "raw_count": 75478, "count": 109609, "decode_str": " um"} -{"id": 52338, "token": "\u00e6\u00a5\u013f", "merges": "\u00e6\u00a5 \u013f", "raw_count": 109612, "count": 109612, "decode_str": "\u695d"} -{"id": 35674, "token": "minimum", "merges": "min imum", "raw_count": 109687, "count": 109687, "decode_str": "minimum"} -{"id": 8657, "token": "ati", "merges": "at i", "raw_count": 105667, "count": 109724, "decode_str": "ati"} -{"id": 6909, "token": "\u0120destroy", "merges": "\u0120dest roy", "raw_count": 63232, "count": 109726, "decode_str": " destroy"} -{"id": 32316, "token": "\u0120commitments", "merges": "\u0120commit ments", "raw_count": 109757, "count": 109757, "decode_str": " commitments"} -{"id": 12419, "token": "\u0120boolean", "merges": "\u0120bo olean", "raw_count": 109827, "count": 109827, "decode_str": " boolean"} -{"id": 33113, "token": "locale", "merges": "loc ale", "raw_count": 109827, "count": 109827, "decode_str": "locale"} -{"id": 5304, "token": "\u0120visual", "merges": "\u0120vis ual", "raw_count": 62698, "count": 109830, "decode_str": " visual"} -{"id": 9214, "token": "\u0120permission", "merges": "\u0120per mission", "raw_count": 109856, "count": 109856, "decode_str": " permission"} -{"id": 20692, "token": "plicit", "merges": "plic it", "raw_count": 109858, "count": 109858, "decode_str": "plicit"} -{"id": 21297, "token": "abul", "merges": "ab ul", "raw_count": 13371, "count": 109869, "decode_str": "abul"} -{"id": 13886, "token": "pection", "merges": "pe ction", "raw_count": 37765, "count": 109879, "decode_str": "pection"} -{"id": 42325, "token": "geo", "merges": "ge o", "raw_count": 109888, "count": 109888, "decode_str": "geo"} -{"id": 10883, "token": "\u0120partition", "merges": "\u0120part ition", "raw_count": 105019, "count": 109930, "decode_str": " partition"} -{"id": 19447, "token": "Cast", "merges": "C ast", "raw_count": 109949, "count": 109949, "decode_str": "Cast"} -{"id": 38186, "token": "Girl", "merges": "G irl", "raw_count": 109957, "count": 109957, "decode_str": "Girl"} -{"id": 7607, "token": "\u0120accepted", "merges": "\u0120accept ed", "raw_count": 109998, "count": 109998, "decode_str": " accepted"} -{"id": 13323, "token": "odd", "merges": "od d", "raw_count": 109336, "count": 110010, "decode_str": "odd"} -{"id": 38368, "token": "Soft", "merges": "So ft", "raw_count": 110019, "count": 110019, "decode_str": "Soft"} -{"id": 44598, "token": "467", "merges": "4 67", "raw_count": 110039, "count": 110039, "decode_str": "467"} -{"id": 24422, "token": "EST", "merges": "E ST", "raw_count": 110053, "count": 110053, "decode_str": "EST"} -{"id": 19441, "token": "LEN", "merges": "L EN", "raw_count": 49051, "count": 110061, "decode_str": "LEN"} -{"id": 19769, "token": "\u0120ns", "merges": "\u0120n s", "raw_count": 110097, "count": 110097, "decode_str": " ns"} -{"id": 46607, "token": "?\",", "merges": "?\" ,", "raw_count": 110101, "count": 110101, "decode_str": "?\","} -{"id": 34384, "token": "879", "merges": "87 9", "raw_count": 110110, "count": 110110, "decode_str": "879"} -{"id": 33765, "token": "DG", "merges": "D G", "raw_count": 110118, "count": 110118, "decode_str": "DG"} -{"id": 45240, "token": "5555", "merges": "55 55", "raw_count": 110135, "count": 110135, "decode_str": "5555"} -{"id": 8634, "token": ".-", "merges": ". -", "raw_count": 110139, "count": 110139, "decode_str": ".-"} -{"id": 20678, "token": "Lar", "merges": "L ar", "raw_count": 88166, "count": 110168, "decode_str": "Lar"} -{"id": 21454, "token": "sections", "merges": "se ctions", "raw_count": 104028, "count": 110174, "decode_str": "sections"} -{"id": 17182, "token": "six", "merges": "s ix", "raw_count": 110174, "count": 110174, "decode_str": "six"} -{"id": 27837, "token": "Rh", "merges": "R h", "raw_count": 110289, "count": 110289, "decode_str": "Rh"} -{"id": 6552, "token": "\u0120excell", "merges": "\u0120exc ell", "raw_count": 31124, "count": 110316, "decode_str": " excell"} -{"id": 12863, "token": "arts", "merges": "art s", "raw_count": 94319, "count": 110338, "decode_str": "arts"} -{"id": 11846, "token": "\u0120Event", "merges": "\u0120E vent", "raw_count": 109327, "count": 110346, "decode_str": " Event"} -{"id": 16782, "token": "\u0120chairman", "merges": "\u0120chair man", "raw_count": 110366, "count": 110366, "decode_str": " chairman"} -{"id": 27413, "token": "YE", "merges": "Y E", "raw_count": 110369, "count": 110369, "decode_str": "YE"} -{"id": 10439, "token": "\u0120western", "merges": "\u0120w estern", "raw_count": 110385, "count": 110385, "decode_str": " western"} -{"id": 3122, "token": "/*", "merges": "/ *", "raw_count": 103498, "count": 110523, "decode_str": "/*"} -{"id": 29965, "token": "analy", "merges": "an aly", "raw_count": 110525, "count": 110525, "decode_str": "analy"} -{"id": 4754, "token": "\u0120yes", "merges": "\u0120y es", "raw_count": 76379, "count": 110530, "decode_str": " yes"} -{"id": 25000, "token": "Mary", "merges": "M ary", "raw_count": 110536, "count": 110536, "decode_str": "Mary"} -{"id": 42316, "token": "operations", "merges": "oper ations", "raw_count": 110559, "count": 110559, "decode_str": "operations"} -{"id": 33466, "token": "Cook", "merges": "C ook", "raw_count": 110565, "count": 110565, "decode_str": "Cook"} -{"id": 40010, "token": "871", "merges": "87 1", "raw_count": 110576, "count": 110576, "decode_str": "871"} -{"id": 30467, "token": "694", "merges": "69 4", "raw_count": 110579, "count": 110579, "decode_str": "694"} -{"id": 14381, "token": "ims", "merges": "im s", "raw_count": 110585, "count": 110585, "decode_str": "ims"} -{"id": 35179, "token": "752", "merges": "75 2", "raw_count": 110620, "count": 110620, "decode_str": "752"} -{"id": 6224, "token": "\u0120sales", "merges": "\u0120s ales", "raw_count": 110630, "count": 110630, "decode_str": " sales"} -{"id": 7051, "token": "\u0120electronic", "merges": "\u0120elect ronic", "raw_count": 110648, "count": 110648, "decode_str": " electronic"} -{"id": 15592, "token": "books", "merges": "book s", "raw_count": 103086, "count": 110672, "decode_str": "books"} -{"id": 14983, "token": "anal", "merges": "an al", "raw_count": 82874, "count": 110681, "decode_str": "anal"} -{"id": 21207, "token": "\u0120torture", "merges": "\u0120tort ure", "raw_count": 110688, "count": 110688, "decode_str": " torture"} -{"id": 17936, "token": "uke", "merges": "u ke", "raw_count": 80699, "count": 110693, "decode_str": "uke"} -{"id": 27890, "token": "Sar", "merges": "S ar", "raw_count": 46554, "count": 110714, "decode_str": "Sar"} -{"id": 21264, "token": "prises", "merges": "pr ises", "raw_count": 14398, "count": 110725, "decode_str": "prises"} -{"id": 12137, "token": "\u0120crimes", "merges": "\u0120cr imes", "raw_count": 110739, "count": 110739, "decode_str": " crimes"} -{"id": 19038, "token": "ANS", "merges": "AN S", "raw_count": 110742, "count": 110742, "decode_str": "ANS"} -{"id": 8461, "token": "\u0120poll", "merges": "\u0120pol l", "raw_count": 58140, "count": 110746, "decode_str": " poll"} -{"id": 4418, "token": "\u0120\u00d0\u00bd", "merges": "\u0120\u00d0 \u00bd", "raw_count": 45417, "count": 110774, "decode_str": " \u043d"} -{"id": 3361, "token": "\u0120presence", "merges": "\u0120pres ence", "raw_count": 110789, "count": 110789, "decode_str": " presence"} -{"id": 16022, "token": "\u0120exceptions", "merges": "\u0120except ions", "raw_count": 110815, "count": 110815, "decode_str": " exceptions"} -{"id": 14806, "token": "into", "merges": "int o", "raw_count": 110815, "count": 110815, "decode_str": "into"} -{"id": 29526, "token": "ALT", "merges": "AL T", "raw_count": 110828, "count": 110828, "decode_str": "ALT"} -{"id": 16642, "token": "ania", "merges": "an ia", "raw_count": 110779, "count": 110833, "decode_str": "ania"} -{"id": 25777, "token": "\u0120'#", "merges": "\u0120' #", "raw_count": 110839, "count": 110839, "decode_str": " '#"} -{"id": 41445, "token": "Regex", "merges": "Re gex", "raw_count": 110847, "count": 110847, "decode_str": "Regex"} -{"id": 15772, "token": "\u0120institutional", "merges": "\u0120institution al", "raw_count": 110866, "count": 110866, "decode_str": " institutional"} -{"id": 9187, "token": "\u0120cro", "merges": "\u0120c ro", "raw_count": 86429, "count": 110890, "decode_str": " cro"} -{"id": 9763, "token": "\u0120controller", "merges": "\u0120controll er", "raw_count": 110911, "count": 110911, "decode_str": " controller"} -{"id": 54161, "token": "\u00e9\u0124\u00b0", "merges": "\u00e9\u0124 \u00b0", "raw_count": 110914, "count": 110914, "decode_str": "\u90b0"} -{"id": 37339, "token": "Band", "merges": "B and", "raw_count": 110926, "count": 110926, "decode_str": "Band"} -{"id": 15680, "token": "impl", "merges": "im pl", "raw_count": 110937, "count": 110937, "decode_str": "impl"} -{"id": 42763, "token": "572", "merges": "57 2", "raw_count": 110976, "count": 110976, "decode_str": "572"} -{"id": 8234, "token": "inite", "merges": "in ite", "raw_count": 59471, "count": 110981, "decode_str": "inite"} -{"id": 33291, "token": "693", "merges": "69 3", "raw_count": 110996, "count": 110996, "decode_str": "693"} -{"id": 19240, "token": "INSERT", "merges": "INS ERT", "raw_count": 111054, "count": 111054, "decode_str": "INSERT"} -{"id": 48828, "token": "639", "merges": "6 39", "raw_count": 111065, "count": 111065, "decode_str": "639"} -{"id": 7308, "token": "\u010a\u0109\u0109\u0109\u0109\u0109", "merges": "\u010a\u0109\u0109\u0109\u0109 \u0109", "raw_count": 111071, "count": 111071, "decode_str": "\n\t\t\t\t\t"} -{"id": 13568, "token": "plane", "merges": "pl ane", "raw_count": 105226, "count": 111093, "decode_str": "plane"} -{"id": 36222, "token": "wrong", "merges": "wr ong", "raw_count": 111096, "count": 111096, "decode_str": "wrong"} -{"id": 46043, "token": "717", "merges": "7 17", "raw_count": 111110, "count": 111110, "decode_str": "717"} -{"id": 29016, "token": "anchor", "merges": "anch or", "raw_count": 111127, "count": 111127, "decode_str": "anchor"} -{"id": 21165, "token": "\u0120regex", "merges": "\u0120re gex", "raw_count": 111135, "count": 111135, "decode_str": " regex"} -{"id": 15208, "token": "iti", "merges": "it i", "raw_count": 106574, "count": 111171, "decode_str": "iti"} -{"id": 2785, "token": "\u0120||", "merges": "\u0120| |", "raw_count": 111194, "count": 111194, "decode_str": " ||"} -{"id": 4911, "token": "pective", "merges": "pect ive", "raw_count": 35623, "count": 111200, "decode_str": "pective"} -{"id": 5129, "token": "\u00d0\u00b4", "merges": "\u00d0 \u00b4", "raw_count": 64008, "count": 111200, "decode_str": "\u0434"} -{"id": 7281, "token": "\u0120cart", "merges": "\u0120c art", "raw_count": 99853, "count": 111220, "decode_str": " cart"} -{"id": 16469, "token": "udo", "merges": "ud o", "raw_count": 29508, "count": 111224, "decode_str": "udo"} -{"id": 3314, "token": "\u00c3\u00a7", "merges": "\u00c3 \u00a7", "raw_count": 20856, "count": 111233, "decode_str": "\u00e7"} -{"id": 4889, "token": "\u0120AND", "merges": "\u0120AN D", "raw_count": 111259, "count": 111259, "decode_str": " AND"} -{"id": 45475, "token": "477", "merges": "4 77", "raw_count": 111335, "count": 111335, "decode_str": "477"} -{"id": 48402, "token": "RQ", "merges": "R Q", "raw_count": 111373, "count": 111373, "decode_str": "RQ"} -{"id": 13083, "token": "verted", "merges": "vert ed", "raw_count": 97542, "count": 111378, "decode_str": "verted"} -{"id": 11135, "token": "isp", "merges": "is p", "raw_count": 83602, "count": 111396, "decode_str": "isp"} -{"id": 8945, "token": "\u0120emergency", "merges": "\u0120emerg ency", "raw_count": 111439, "count": 111439, "decode_str": " emergency"} -{"id": 5836, "token": "\u0120CON", "merges": "\u0120C ON", "raw_count": 65736, "count": 111452, "decode_str": " CON"} -{"id": 39894, "token": "stmt", "merges": "st mt", "raw_count": 111477, "count": 111477, "decode_str": "stmt"} -{"id": 16726, "token": "iam", "merges": "i am", "raw_count": 111473, "count": 111482, "decode_str": "iam"} -{"id": 18441, "token": "UTF", "merges": "UT F", "raw_count": 111518, "count": 111518, "decode_str": "UTF"} -{"id": 17775, "token": "\u0120Message", "merges": "\u0120M essage", "raw_count": 111533, "count": 111533, "decode_str": " Message"} -{"id": 6200, "token": "\u0120scene", "merges": "\u0120sc ene", "raw_count": 111551, "count": 111551, "decode_str": " scene"} -{"id": 53655, "token": "\u00e8\u012d\u00ab", "merges": "\u00e8\u012d \u00ab", "raw_count": 111565, "count": 111565, "decode_str": "\u82eb"} -{"id": 12379, "token": "\u0120judicial", "merges": "\u0120jud icial", "raw_count": 111582, "count": 111582, "decode_str": " judicial"} -{"id": 14731, "token": "\u0120currency", "merges": "\u0120cur rency", "raw_count": 111593, "count": 111593, "decode_str": " currency"} -{"id": 6499, "token": "jected", "merges": "ject ed", "raw_count": 57933, "count": 111597, "decode_str": "jected"} -{"id": 4606, "token": "\u0120reasons", "merges": "\u0120re asons", "raw_count": 111607, "count": 111607, "decode_str": " reasons"} -{"id": 3958, "token": "\u0120games", "merges": "\u0120g ames", "raw_count": 111621, "count": 111621, "decode_str": " games"} -{"id": 18566, "token": "does", "merges": "do es", "raw_count": 100468, "count": 111631, "decode_str": "does"} -{"id": 41149, "token": ")',", "merges": ") ',", "raw_count": 111665, "count": 111665, "decode_str": ")',"} -{"id": 46878, "token": "613", "merges": "6 13", "raw_count": 111671, "count": 111671, "decode_str": "613"} -{"id": 25889, "token": "Visual", "merges": "Vis ual", "raw_count": 111672, "count": 111672, "decode_str": "Visual"} -{"id": 11114, "token": "izz", "merges": "iz z", "raw_count": 94592, "count": 111676, "decode_str": "izz"} -{"id": 7535, "token": "\u0120advice", "merges": "\u0120adv ice", "raw_count": 111691, "count": 111691, "decode_str": " advice"} -{"id": 49475, "token": "988", "merges": "9 88", "raw_count": 111694, "count": 111694, "decode_str": "988"} -{"id": 53094, "token": "\u00e7\u00a2\u013d", "merges": "\u00e7\u00a2 \u013d", "raw_count": 111697, "count": 111697, "decode_str": "\u789b"} -{"id": 37681, "token": "APS", "merges": "AP S", "raw_count": 111699, "count": 111699, "decode_str": "APS"} -{"id": 2175, "token": "\u0120studies", "merges": "\u0120stud ies", "raw_count": 111708, "count": 111708, "decode_str": " studies"} -{"id": 5180, "token": "[^", "merges": "[ ^", "raw_count": 110438, "count": 111711, "decode_str": "[^"} -{"id": 16025, "token": "\u0120DB", "merges": "\u0120D B", "raw_count": 111727, "count": 111727, "decode_str": " DB"} -{"id": 8151, "token": "\u0120feat", "merges": "\u0120fe at", "raw_count": 78639, "count": 111758, "decode_str": " feat"} -{"id": 5210, "token": "nes", "merges": "n es", "raw_count": 80221, "count": 111802, "decode_str": "nes"} -{"id": 8658, "token": "scr", "merges": "sc r", "raw_count": 111736, "count": 111806, "decode_str": "scr"} -{"id": 10424, "token": "oli", "merges": "ol i", "raw_count": 109084, "count": 111825, "decode_str": "oli"} -{"id": 3785, "token": "\u0120pull", "merges": "\u0120p ull", "raw_count": 68384, "count": 111842, "decode_str": " pull"} -{"id": 52345, "token": "\u00e6\u00a5\u00b8", "merges": "\u00e6\u00a5 \u00b8", "raw_count": 111849, "count": 111849, "decode_str": "\u6978"} -{"id": 38464, "token": "753", "merges": "75 3", "raw_count": 111873, "count": 111873, "decode_str": "753"} -{"id": 10826, "token": "\u0120OK", "merges": "\u0120O K", "raw_count": 111875, "count": 111875, "decode_str": " OK"} -{"id": 5549, "token": "\u0120na", "merges": "\u0120n a", "raw_count": 94904, "count": 111902, "decode_str": " na"} -{"id": 45533, "token": "546", "merges": "5 46", "raw_count": 111916, "count": 111916, "decode_str": "546"} -{"id": 5901, "token": "\u0120Group", "merges": "\u0120Gr oup", "raw_count": 111921, "count": 111921, "decode_str": " Group"} -{"id": 19984, "token": "OUNT", "merges": "OU NT", "raw_count": 50140, "count": 111923, "decode_str": "OUNT"} -{"id": 44285, "token": "DELETE", "merges": "DE LETE", "raw_count": 111938, "count": 111938, "decode_str": "DELETE"} -{"id": 23857, "token": "Track", "merges": "Tr ack", "raw_count": 111965, "count": 111965, "decode_str": "Track"} -{"id": 25408, "token": "DEX", "merges": "DE X", "raw_count": 52580, "count": 111998, "decode_str": "DEX"} -{"id": 33024, "token": "truth", "merges": "tr uth", "raw_count": 112032, "count": 112032, "decode_str": "truth"} -{"id": 6754, "token": "\u00d0\u00b0\u00d0\u00bd", "merges": "\u00d0\u00b0 \u00d0\u00bd", "raw_count": 65490, "count": 112045, "decode_str": "\u0430\u043d"} -{"id": 49722, "token": "685", "merges": "6 85", "raw_count": 112057, "count": 112057, "decode_str": "685"} -{"id": 13425, "token": "General", "merges": "Gen eral", "raw_count": 112079, "count": 112079, "decode_str": "General"} -{"id": 34078, "token": "\u0120suffix", "merges": "\u0120suff ix", "raw_count": 112114, "count": 112114, "decode_str": " suffix"} -{"id": 7489, "token": "\u0120Open", "merges": "\u0120O pen", "raw_count": 112131, "count": 112131, "decode_str": " Open"} -{"id": 5637, "token": "\u0120electric", "merges": "\u0120elect ric", "raw_count": 74700, "count": 112218, "decode_str": " electric"} -{"id": 8152, "token": "irector", "merges": "ire ctor", "raw_count": 10410, "count": 112222, "decode_str": "irector"} -{"id": 8021, "token": "\u0120EX", "merges": "\u0120E X", "raw_count": 104113, "count": 112235, "decode_str": " EX"} -{"id": 35389, "token": "PY", "merges": "P Y", "raw_count": 112276, "count": 112276, "decode_str": "PY"} -{"id": 5087, "token": "\u0120paid", "merges": "\u0120pa id", "raw_count": 112324, "count": 112324, "decode_str": " paid"} -{"id": 54198, "token": "\u00e9\u0127\u00a9", "merges": "\u00e9\u0127 \u00a9", "raw_count": 112339, "count": 112339, "decode_str": "\u9169"} -{"id": 14033, "token": "ancial", "merges": "anc ial", "raw_count": 34376, "count": 112345, "decode_str": "ancial"} -{"id": 6142, "token": "\u0120reb", "merges": "\u0120re b", "raw_count": 25901, "count": 112347, "decode_str": " reb"} -{"id": 22600, "token": "Spring", "merges": "Sp ring", "raw_count": 98618, "count": 112367, "decode_str": "Spring"} -{"id": 7683, "token": "velopment", "merges": "velop ment", "raw_count": 6021, "count": 112368, "decode_str": "velopment"} -{"id": 23221, "token": "\u0120centres", "merges": "\u0120cent res", "raw_count": 112388, "count": 112388, "decode_str": " centres"} -{"id": 38057, "token": "hb", "merges": "h b", "raw_count": 112403, "count": 112403, "decode_str": "hb"} -{"id": 50833, "token": "\u00e5\u012d\u0138", "merges": "\u00e5\u012d \u0138", "raw_count": 112432, "count": 112432, "decode_str": "\u52d6"} -{"id": 22249, "token": "Screen", "merges": "S creen", "raw_count": 112452, "count": 112452, "decode_str": "Screen"} -{"id": 19559, "token": "got", "merges": "g ot", "raw_count": 112497, "count": 112497, "decode_str": "got"} -{"id": 25603, "token": "Driver", "merges": "D river", "raw_count": 112512, "count": 112512, "decode_str": "Driver"} -{"id": 24731, "token": "Land", "merges": "L and", "raw_count": 112545, "count": 112545, "decode_str": "Land"} -{"id": 7986, "token": "hether", "merges": "he ther", "raw_count": 187, "count": 112549, "decode_str": "hether"} -{"id": 21274, "token": "045", "merges": "0 45", "raw_count": 112559, "count": 112559, "decode_str": "045"} -{"id": 46702, "token": "832", "merges": "8 32", "raw_count": 112596, "count": 112596, "decode_str": "832"} -{"id": 9307, "token": "uma", "merges": "um a", "raw_count": 106045, "count": 112613, "decode_str": "uma"} -{"id": 6282, "token": "\u0120Out", "merges": "\u0120O ut", "raw_count": 39442, "count": 112617, "decode_str": " Out"} -{"id": 29594, "token": "Mail", "merges": "M ail", "raw_count": 112630, "count": 112630, "decode_str": "Mail"} -{"id": 11017, "token": "\u0120scan", "merges": "\u0120sc an", "raw_count": 112632, "count": 112632, "decode_str": " scan"} -{"id": 5269, "token": "\u0120tal", "merges": "\u0120t al", "raw_count": 32544, "count": 112712, "decode_str": " tal"} -{"id": 21630, "token": "cmp", "merges": "c mp", "raw_count": 112735, "count": 112735, "decode_str": "cmp"} -{"id": 31080, "token": "Bern", "merges": "B ern", "raw_count": 112750, "count": 112750, "decode_str": "Bern"} -{"id": 7910, "token": "Two", "merges": "T wo", "raw_count": 112764, "count": 112764, "decode_str": "Two"} -{"id": 6134, "token": "eless", "merges": "el ess", "raw_count": 73563, "count": 112773, "decode_str": "eless"} -{"id": 19529, "token": "\u0120submission", "merges": "\u0120sub mission", "raw_count": 112783, "count": 112783, "decode_str": " submission"} -{"id": 22482, "token": "Dest", "merges": "D est", "raw_count": 78310, "count": 112787, "decode_str": "Dest"} -{"id": 36310, "token": "0026", "merges": "00 26", "raw_count": 112815, "count": 112815, "decode_str": "0026"} -{"id": 10986, "token": "oi", "merges": "o i", "raw_count": 111752, "count": 112825, "decode_str": "oi"} -{"id": 48698, "token": "Shop", "merges": "Sh op", "raw_count": 112857, "count": 112857, "decode_str": "Shop"} -{"id": 5520, "token": "\u0120improved", "merges": "\u0120impro ved", "raw_count": 112918, "count": 112918, "decode_str": " improved"} -{"id": 11055, "token": "\u0120Conne", "merges": "\u0120Con ne", "raw_count": 15464, "count": 112932, "decode_str": " Conne"} -{"id": 47926, "token": "annotations", "merges": "annot ations", "raw_count": 112937, "count": 112937, "decode_str": "annotations"} -{"id": 8845, "token": "\u0120rent", "merges": "\u0120re nt", "raw_count": 43162, "count": 112950, "decode_str": " rent"} -{"id": 6406, "token": "\u0120street", "merges": "\u0120st reet", "raw_count": 112976, "count": 112976, "decode_str": " street"} -{"id": 33304, "token": "681", "merges": "68 1", "raw_count": 112977, "count": 112977, "decode_str": "681"} -{"id": 4998, "token": "oman", "merges": "om an", "raw_count": 48098, "count": 112978, "decode_str": "oman"} -{"id": 20990, "token": "Den", "merges": "D en", "raw_count": 113031, "count": 113031, "decode_str": "Den"} -{"id": 42389, "token": "514", "merges": "5 14", "raw_count": 113040, "count": 113040, "decode_str": "514"} -{"id": 29140, "token": "Young", "merges": "Y oung", "raw_count": 113042, "count": 113042, "decode_str": "Young"} -{"id": 9206, "token": "\u0120Object", "merges": "\u0120O bject", "raw_count": 100810, "count": 113055, "decode_str": " Object"} -{"id": 23955, "token": "another", "merges": "an other", "raw_count": 113061, "count": 113061, "decode_str": "another"} -{"id": 19505, "token": "beat", "merges": "be at", "raw_count": 101132, "count": 113102, "decode_str": "beat"} -{"id": 21052, "token": "derer", "merges": "de rer", "raw_count": 110462, "count": 113106, "decode_str": "derer"} -{"id": 19016, "token": "third", "merges": "th ird", "raw_count": 113124, "count": 113124, "decode_str": "third"} -{"id": 7412, "token": "\u0120AS", "merges": "\u0120A S", "raw_count": 113124, "count": 113124, "decode_str": " AS"} -{"id": 9381, "token": "\u0120rotation", "merges": "\u0120rot ation", "raw_count": 113129, "count": 113129, "decode_str": " rotation"} -{"id": 39264, "token": "circuit", "merges": "circ uit", "raw_count": 113161, "count": 113161, "decode_str": "circuit"} -{"id": 19008, "token": "Mad", "merges": "M ad", "raw_count": 113177, "count": 113177, "decode_str": "Mad"} -{"id": 10747, "token": "leton", "merges": "let on", "raw_count": 51062, "count": 113182, "decode_str": "leton"} -{"id": 12320, "token": "\u0120precision", "merges": "\u0120prec ision", "raw_count": 113190, "count": 113190, "decode_str": " precision"} -{"id": 17356, "token": "\u0120gamma", "merges": "\u0120g amma", "raw_count": 113204, "count": 113204, "decode_str": " gamma"} -{"id": 23537, "token": "rar", "merges": "r ar", "raw_count": 113262, "count": 113262, "decode_str": "rar"} -{"id": 16713, "token": "eto", "merges": "et o", "raw_count": 103291, "count": 113277, "decode_str": "eto"} -{"id": 31728, "token": "hc", "merges": "h c", "raw_count": 113285, "count": 113285, "decode_str": "hc"} -{"id": 22098, "token": "Ep", "merges": "E p", "raw_count": 113308, "count": 113308, "decode_str": "Ep"} -{"id": 4300, "token": "\u0120announ", "merges": "\u0120ann oun", "raw_count": 874, "count": 113357, "decode_str": " announ"} -{"id": 54117, "token": "\u00e9\u0122\u00b6", "merges": "\u00e9\u0122 \u00b6", "raw_count": 113371, "count": 113371, "decode_str": "\u9036"} -{"id": 16539, "token": "ICK", "merges": "IC K", "raw_count": 113381, "count": 113381, "decode_str": "ICK"} -{"id": 6396, "token": "\u0120jurisd", "merges": "\u0120jur isd", "raw_count": 46, "count": 113408, "decode_str": " jurisd"} -{"id": 22374, "token": "brand", "merges": "br and", "raw_count": 113433, "count": 113433, "decode_str": "brand"} -{"id": 4864, "token": "\u0120brief", "merges": "\u0120b rief", "raw_count": 68884, "count": 113488, "decode_str": " brief"} -{"id": 15065, "token": "\u0120finance", "merges": "\u0120fin ance", "raw_count": 113504, "count": 113504, "decode_str": " finance"} -{"id": 39273, "token": "883", "merges": "88 3", "raw_count": 113555, "count": 113555, "decode_str": "883"} -{"id": 35333, "token": "gd", "merges": "g d", "raw_count": 113566, "count": 113566, "decode_str": "gd"} -{"id": 17401, "token": "\u0120recommendation", "merges": "\u0120recommend ation", "raw_count": 113658, "count": 113658, "decode_str": " recommendation"} -{"id": 17745, "token": "Capt", "merges": "C apt", "raw_count": 38616, "count": 113664, "decode_str": "Capt"} -{"id": 48442, "token": "577", "merges": "5 77", "raw_count": 113673, "count": 113673, "decode_str": "577"} -{"id": 8888, "token": "\u0120mail", "merges": "\u0120m ail", "raw_count": 103276, "count": 113678, "decode_str": " mail"} -{"id": 7215, "token": "agger", "merges": "ag ger", "raw_count": 98213, "count": 113689, "decode_str": "agger"} -{"id": 32834, "token": "642", "merges": "64 2", "raw_count": 113689, "count": 113689, "decode_str": "642"} -{"id": 30890, "token": "vb", "merges": "v b", "raw_count": 113708, "count": 113708, "decode_str": "vb"} -{"id": 37862, "token": "ARP", "merges": "AR P", "raw_count": 113715, "count": 113715, "decode_str": "ARP"} -{"id": 20099, "token": "translation", "merges": "trans lation", "raw_count": 113723, "count": 113723, "decode_str": "translation"} -{"id": 22860, "token": "scroll", "merges": "sc roll", "raw_count": 113739, "count": 113739, "decode_str": "scroll"} -{"id": 51724, "token": "\u00e6\u0123\u00ab", "merges": "\u00e6\u0123 \u00ab", "raw_count": 113739, "count": 113739, "decode_str": "\u606b"} -{"id": 30957, "token": "population", "merges": "pop ulation", "raw_count": 113741, "count": 113741, "decode_str": "population"} -{"id": 27142, "token": "gap", "merges": "g ap", "raw_count": 113757, "count": 113757, "decode_str": "gap"} -{"id": 25353, "token": "Fre", "merges": "F re", "raw_count": 113770, "count": 113770, "decode_str": "Fre"} -{"id": 4600, "token": "\u0120sleep", "merges": "\u0120sle ep", "raw_count": 93775, "count": 113786, "decode_str": " sleep"} -{"id": 26198, "token": "\u0120ll", "merges": "\u0120l l", "raw_count": 113824, "count": 113824, "decode_str": " ll"} -{"id": 47740, "token": "RAW", "merges": "RA W", "raw_count": 113839, "count": 113839, "decode_str": "RAW"} -{"id": 17910, "token": "\u0120recurs", "merges": "\u0120rec urs", "raw_count": 28314, "count": 113845, "decode_str": " recurs"} -{"id": 20982, "token": "PLE", "merges": "P LE", "raw_count": 113865, "count": 113865, "decode_str": "PLE"} -{"id": 48944, "token": "buttons", "merges": "but tons", "raw_count": 113885, "count": 113885, "decode_str": "buttons"} -{"id": 24721, "token": "Ho", "merges": "H o", "raw_count": 113890, "count": 113890, "decode_str": "Ho"} -{"id": 3494, "token": "ospital", "merges": "osp ital", "raw_count": 29213, "count": 113899, "decode_str": "ospital"} -{"id": 7162, "token": "\u0120confidence", "merges": "\u0120conf idence", "raw_count": 113903, "count": 113903, "decode_str": " confidence"} -{"id": 7961, "token": "ante", "merges": "ant e", "raw_count": 112911, "count": 113909, "decode_str": "ante"} -{"id": 15847, "token": "qual", "merges": "qu al", "raw_count": 83084, "count": 113916, "decode_str": "qual"} -{"id": 3501, "token": "\u0120cry", "merges": "\u0120c ry", "raw_count": 25060, "count": 113930, "decode_str": " cry"} -{"id": 30851, "token": "HOME", "merges": "H OME", "raw_count": 113931, "count": 113931, "decode_str": "HOME"} -{"id": 54552, "token": "\u00e7\u0124\u013f", "merges": "\u00e7\u0124 \u013f", "raw_count": 113965, "count": 113965, "decode_str": "\u709d"} -{"id": 16409, "token": "rik", "merges": "ri k", "raw_count": 113719, "count": 114050, "decode_str": "rik"} -{"id": 15512, "token": "\u0120slice", "merges": "\u0120sl ice", "raw_count": 114073, "count": 114073, "decode_str": " slice"} -{"id": 5485, "token": "\u0120opened", "merges": "\u0120open ed", "raw_count": 114074, "count": 114074, "decode_str": " opened"} -{"id": 22227, "token": "TAG", "merges": "T AG", "raw_count": 114075, "count": 114075, "decode_str": "TAG"} -{"id": 17050, "token": "quired", "merges": "qu ired", "raw_count": 21139, "count": 114092, "decode_str": "quired"} -{"id": 16683, "token": "izza", "merges": "iz za", "raw_count": 99896, "count": 114132, "decode_str": "izza"} -{"id": 9614, "token": "aylor", "merges": "ay lor", "raw_count": 24933, "count": 114135, "decode_str": "aylor"} -{"id": 42140, "token": "592", "merges": "59 2", "raw_count": 114144, "count": 114144, "decode_str": "592"} -{"id": 4457, "token": "\u0120beyond", "merges": "\u0120be yond", "raw_count": 114145, "count": 114145, "decode_str": " beyond"} -{"id": 8582, "token": "\u0120Tem", "merges": "\u0120T em", "raw_count": 34498, "count": 114150, "decode_str": " Tem"} -{"id": 27475, "token": "inx", "merges": "in x", "raw_count": 114152, "count": 114152, "decode_str": "inx"} -{"id": 1777, "token": "\u0120Ph", "merges": "\u0120P h", "raw_count": 31074, "count": 114272, "decode_str": " Ph"} -{"id": 51788, "token": "\u00e6\u0126\u012f", "merges": "\u00e6\u0126 \u012f", "raw_count": 114280, "count": 114280, "decode_str": "\u610d"} -{"id": 4053, "token": "vention", "merges": "v ention", "raw_count": 56466, "count": 114284, "decode_str": "vention"} -{"id": 46780, "token": "Zoom", "merges": "Z oom", "raw_count": 114296, "count": 114296, "decode_str": "Zoom"} -{"id": 18406, "token": "\u0120collections", "merges": "\u0120colle ctions", "raw_count": 114297, "count": 114297, "decode_str": " collections"} -{"id": 42256, "token": "happy", "merges": "h appy", "raw_count": 114313, "count": 114313, "decode_str": "happy"} -{"id": 20643, "token": "Mil", "merges": "M il", "raw_count": 107354, "count": 114324, "decode_str": "Mil"} -{"id": 13552, "token": "priv", "merges": "p riv", "raw_count": 114325, "count": 114325, "decode_str": "priv"} -{"id": 30715, "token": "774", "merges": "77 4", "raw_count": 114345, "count": 114345, "decode_str": "774"} -{"id": 13047, "token": "endor", "merges": "end or", "raw_count": 32392, "count": 114354, "decode_str": "endor"} -{"id": 10473, "token": "\u0120enforcement", "merges": "\u0120enforce ment", "raw_count": 114373, "count": 114373, "decode_str": " enforcement"} -{"id": 11003, "token": "\u012088", "merges": "\u01208 8", "raw_count": 114381, "count": 114381, "decode_str": " 88"} -{"id": 53250, "token": "\u00e7\u00ae\u00b8", "merges": "\u00e7\u00ae \u00b8", "raw_count": 114469, "count": 114469, "decode_str": "\u7bb8"} -{"id": 8535, "token": "west", "merges": "w est", "raw_count": 98744, "count": 114491, "decode_str": "west"} -{"id": 24650, "token": "NEW", "merges": "NE W", "raw_count": 114499, "count": 114499, "decode_str": "NEW"} -{"id": 14326, "token": "lit", "merges": "l it", "raw_count": 45374, "count": 114510, "decode_str": "lit"} -{"id": 2183, "token": "\u0120told", "merges": "\u0120to ld", "raw_count": 114576, "count": 114576, "decode_str": " told"} -{"id": 8922, "token": "ishment", "merges": "ish ment", "raw_count": 38056, "count": 114591, "decode_str": "ishment"} -{"id": 50996, "token": "\u00e5\u0133\u0135", "merges": "\u00e5\u0133 \u0135", "raw_count": 114598, "count": 114598, "decode_str": "\u5453"} -{"id": 44941, "token": "715", "merges": "7 15", "raw_count": 114626, "count": 114626, "decode_str": "715"} -{"id": 24441, "token": "Law", "merges": "L aw", "raw_count": 114653, "count": 114653, "decode_str": "Law"} -{"id": 11084, "token": "\u0120130", "merges": "\u01201 30", "raw_count": 114676, "count": 114676, "decode_str": " 130"} -{"id": 34814, "token": "following", "merges": "f ollowing", "raw_count": 114702, "count": 114702, "decode_str": "following"} -{"id": 5014, "token": "\u0120participants", "merges": "\u0120particip ants", "raw_count": 114707, "count": 114707, "decode_str": " participants"} -{"id": 35394, "token": "Mix", "merges": "M ix", "raw_count": 114710, "count": 114710, "decode_str": "Mix"} -{"id": 21338, "token": "manif", "merges": "man if", "raw_count": 9409, "count": 114714, "decode_str": "manif"} -{"id": 15442, "token": "\u0120hex", "merges": "\u0120he x", "raw_count": 114715, "count": 114715, "decode_str": " hex"} -{"id": 26545, "token": "\u0120disabilities", "merges": "\u0120dis abilities", "raw_count": 114725, "count": 114725, "decode_str": " disabilities"} -{"id": 9800, "token": "\u0120compat", "merges": "\u0120comp at", "raw_count": 23381, "count": 114725, "decode_str": " compat"} -{"id": 31309, "token": "MF", "merges": "M F", "raw_count": 114746, "count": 114746, "decode_str": "MF"} -{"id": 19681, "token": "dynamic", "merges": "d ynamic", "raw_count": 114092, "count": 114749, "decode_str": "dynamic"} -{"id": 29871, "token": "pod", "merges": "p od", "raw_count": 114814, "count": 114814, "decode_str": "pod"} -{"id": 24582, "token": "ANN", "merges": "AN N", "raw_count": 71503, "count": 114831, "decode_str": "ANN"} -{"id": 4430, "token": "\u0120arm", "merges": "\u0120ar m", "raw_count": 93567, "count": 114887, "decode_str": " arm"} -{"id": 24282, "token": "IDTH", "merges": "ID TH", "raw_count": 14968, "count": 114910, "decode_str": "IDTH"} -{"id": 35432, "token": "876", "merges": "87 6", "raw_count": 114910, "count": 114910, "decode_str": "876"} -{"id": 48105, "token": "627", "merges": "6 27", "raw_count": 114917, "count": 114917, "decode_str": "627"} -{"id": 14844, "token": "bean", "merges": "be an", "raw_count": 112409, "count": 114932, "decode_str": "bean"} -{"id": 12864, "token": "Take", "merges": "T ake", "raw_count": 114944, "count": 114944, "decode_str": "Take"} -{"id": 41347, "token": "reload", "merges": "rel oad", "raw_count": 114952, "count": 114952, "decode_str": "reload"} -{"id": 31621, "token": "HOST", "merges": "H OST", "raw_count": 114971, "count": 114971, "decode_str": "HOST"} -{"id": 30994, "token": "Nodes", "merges": "N odes", "raw_count": 115036, "count": 115036, "decode_str": "Nodes"} -{"id": 36208, "token": "854", "merges": "85 4", "raw_count": 115042, "count": 115042, "decode_str": "854"} -{"id": 6161, "token": "\u0120coe", "merges": "\u0120co e", "raw_count": 40911, "count": 115050, "decode_str": " coe"} -{"id": 9901, "token": "\u012061", "merges": "\u01206 1", "raw_count": 115060, "count": 115060, "decode_str": " 61"} -{"id": 17374, "token": "\u0120foo", "merges": "\u0120f oo", "raw_count": 115065, "count": 115065, "decode_str": " foo"} -{"id": 46064, "token": ":\")", "merges": ": \")", "raw_count": 115079, "count": 115079, "decode_str": ":\")"} -{"id": 40461, "token": "Cookie", "merges": "C ookie", "raw_count": 115084, "count": 115084, "decode_str": "Cookie"} -{"id": 15689, "token": "Public", "merges": "P ublic", "raw_count": 115121, "count": 115121, "decode_str": "Public"} -{"id": 9771, "token": "\u0120alloc", "merges": "\u0120all oc", "raw_count": 36784, "count": 115182, "decode_str": " alloc"} -{"id": 3282, "token": "\u0120sense", "merges": "\u0120s ense", "raw_count": 115216, "count": 115216, "decode_str": " sense"} -{"id": 29825, "token": "(\".", "merges": "(\" .", "raw_count": 115221, "count": 115221, "decode_str": "(\"."} -{"id": 9963, "token": "\u012067", "merges": "\u01206 7", "raw_count": 115230, "count": 115230, "decode_str": " 67"} -{"id": 15528, "token": "DEV", "merges": "DE V", "raw_count": 75700, "count": 115239, "decode_str": "DEV"} -{"id": 31876, "token": "broad", "merges": "b road", "raw_count": 115259, "count": 115259, "decode_str": "broad"} -{"id": 8495, "token": "\u0120align", "merges": "\u0120al ign", "raw_count": 105803, "count": 115263, "decode_str": " align"} -{"id": 18881, "token": "\u0120220", "merges": "\u01202 20", "raw_count": 115268, "count": 115268, "decode_str": " 220"} -{"id": 39981, "token": "hub", "merges": "h ub", "raw_count": 115281, "count": 115281, "decode_str": "hub"} -{"id": 29033, "token": "Mag", "merges": "M ag", "raw_count": 115289, "count": 115289, "decode_str": "Mag"} -{"id": 40612, "token": "neo", "merges": "ne o", "raw_count": 115299, "count": 115299, "decode_str": "neo"} -{"id": 29456, "token": "Ka", "merges": "K a", "raw_count": 115302, "count": 115302, "decode_str": "Ka"} -{"id": 17491, "token": "Copy", "merges": "C opy", "raw_count": 115312, "count": 115312, "decode_str": "Copy"} -{"id": 43894, "token": "\u00e8\u00ab", "merges": "\u00e8 \u00ab", "raw_count": 115322, "count": 115322, "decode_str": "\ufffd"} -{"id": 33244, "token": "Harry", "merges": "Har ry", "raw_count": 115344, "count": 115344, "decode_str": "Harry"} -{"id": 2812, "token": "\u0120spect", "merges": "\u0120spe ct", "raw_count": 19973, "count": 115348, "decode_str": " spect"} -{"id": 35438, "token": "Lev", "merges": "L ev", "raw_count": 115350, "count": 115350, "decode_str": "Lev"} -{"id": 19871, "token": "ANK", "merges": "AN K", "raw_count": 115374, "count": 115374, "decode_str": "ANK"} -{"id": 13158, "token": "eed", "merges": "e ed", "raw_count": 67219, "count": 115415, "decode_str": "eed"} -{"id": 30799, "token": "means", "merges": "me ans", "raw_count": 115443, "count": 115443, "decode_str": "means"} -{"id": 11057, "token": "\u0120Number", "merges": "\u0120N umber", "raw_count": 115448, "count": 115448, "decode_str": " Number"} -{"id": 24115, "token": "Wall", "merges": "W all", "raw_count": 115471, "count": 115471, "decode_str": "Wall"} -{"id": 43490, "token": "466", "merges": "4 66", "raw_count": 115492, "count": 115492, "decode_str": "466"} -{"id": 3548, "token": "\u0120isn", "merges": "\u0120is n", "raw_count": 115498, "count": 115498, "decode_str": " isn"} -{"id": 8557, "token": "\u0120pairs", "merges": "\u0120p airs", "raw_count": 115527, "count": 115527, "decode_str": " pairs"} -{"id": 45467, "token": "ETS", "merges": "ET S", "raw_count": 115529, "count": 115529, "decode_str": "ETS"} -{"id": 31455, "token": "Cluster", "merges": "Cl uster", "raw_count": 115533, "count": 115533, "decode_str": "Cluster"} -{"id": 12202, "token": "ucky", "merges": "uck y", "raw_count": 114503, "count": 115577, "decode_str": "ucky"} -{"id": 5114, "token": "sis", "merges": "s is", "raw_count": 70318, "count": 115583, "decode_str": "sis"} -{"id": 7355, "token": "\u0120recovery", "merges": "\u0120rec overy", "raw_count": 115599, "count": 115599, "decode_str": " recovery"} -{"id": 5911, "token": "elled", "merges": "ell ed", "raw_count": 66136, "count": 115611, "decode_str": "elled"} -{"id": 14065, "token": "oker", "merges": "ok er", "raw_count": 107878, "count": 115627, "decode_str": "oker"} -{"id": 31048, "token": "\u0120pt", "merges": "\u0120p t", "raw_count": 115637, "count": 115637, "decode_str": " pt"} -{"id": 6070, "token": "\u0120extent", "merges": "\u0120ext ent", "raw_count": 115644, "count": 115644, "decode_str": " extent"} -{"id": 30682, "token": "RH", "merges": "R H", "raw_count": 115663, "count": 115663, "decode_str": "RH"} -{"id": 21610, "token": ":/", "merges": ": /", "raw_count": 115682, "count": 115682, "decode_str": ":/"} -{"id": 33597, "token": "461", "merges": "46 1", "raw_count": 115711, "count": 115711, "decode_str": "461"} -{"id": 42149, "token": "Lam", "merges": "L am", "raw_count": 115712, "count": 115712, "decode_str": "Lam"} -{"id": 11660, "token": "acon", "merges": "ac on", "raw_count": 99473, "count": 115727, "decode_str": "acon"} -{"id": 53476, "token": "\u00e8\u0124\u0126", "merges": "\u00e8\u0124 \u0126", "raw_count": 115730, "count": 115730, "decode_str": "\u8084"} -{"id": 7292, "token": "roke", "merges": "ro ke", "raw_count": 23169, "count": 115788, "decode_str": "roke"} -{"id": 6799, "token": "\u0120desired", "merges": "\u0120des ired", "raw_count": 115846, "count": 115846, "decode_str": " desired"} -{"id": 5580, "token": "\u0120sell", "merges": "\u0120s ell", "raw_count": 70153, "count": 115856, "decode_str": " sell"} -{"id": 44293, "token": "IMO", "merges": "IM O", "raw_count": 115864, "count": 115864, "decode_str": "IMO"} -{"id": 22893, "token": "Head", "merges": "He ad", "raw_count": 115902, "count": 115902, "decode_str": "Head"} -{"id": 23270, "token": "Bio", "merges": "B io", "raw_count": 115968, "count": 115968, "decode_str": "Bio"} -{"id": 11118, "token": "\u0120signature", "merges": "\u0120sign ature", "raw_count": 115972, "count": 115972, "decode_str": " signature"} -{"id": 50571, "token": "\u00e4\u00bd\u00bb", "merges": "\u00e4\u00bd \u00bb", "raw_count": 115974, "count": 115974, "decode_str": "\u4f7b"} -{"id": 26409, "token": "3333", "merges": "33 33", "raw_count": 116002, "count": 116002, "decode_str": "3333"} -{"id": 36451, "token": "templates", "merges": "tem plates", "raw_count": 116027, "count": 116027, "decode_str": "templates"} -{"id": 52722, "token": "\u00e7\u0124\u0123", "merges": "\u00e7\u0124 \u0123", "raw_count": 116035, "count": 116035, "decode_str": "\u7081"} -{"id": 25087, "token": "\u0120tile", "merges": "\u0120t ile", "raw_count": 116051, "count": 116051, "decode_str": " tile"} -{"id": 6964, "token": "duc", "merges": "du c", "raw_count": 8892, "count": 116073, "decode_str": "duc"} -{"id": 6498, "token": "\u0120operating", "merges": "\u0120oper ating", "raw_count": 116074, "count": 116074, "decode_str": " operating"} -{"id": 8792, "token": "omething", "merges": "om ething", "raw_count": 10093, "count": 116083, "decode_str": "omething"} -{"id": 34337, "token": "Rank", "merges": "R ank", "raw_count": 116104, "count": 116104, "decode_str": "Rank"} -{"id": 53570, "token": "\u00e8\u012a\u0124", "merges": "\u00e8\u012a \u0124", "raw_count": 116112, "count": 116112, "decode_str": "\u8202"} -{"id": 34108, "token": "Exit", "merges": "Ex it", "raw_count": 116143, "count": 116143, "decode_str": "Exit"} -{"id": 7038, "token": "\u0120leaders", "merges": "\u0120lead ers", "raw_count": 116188, "count": 116188, "decode_str": " leaders"} -{"id": 7453, "token": "\u0120restaur", "merges": "\u0120rest aur", "raw_count": 692, "count": 116214, "decode_str": " restaur"} -{"id": 38655, "token": "cum", "merges": "c um", "raw_count": 116237, "count": 116237, "decode_str": "cum"} -{"id": 4366, "token": "\u0120notice", "merges": "\u0120not ice", "raw_count": 111869, "count": 116247, "decode_str": " notice"} -{"id": 18581, "token": "Sem", "merges": "S em", "raw_count": 116248, "count": 116248, "decode_str": "Sem"} -{"id": 25978, "token": "\u0120governance", "merges": "\u0120govern ance", "raw_count": 116259, "count": 116259, "decode_str": " governance"} -{"id": 3865, "token": "\u0120anim", "merges": "\u0120an im", "raw_count": 18974, "count": 116289, "decode_str": " anim"} -{"id": 7752, "token": "sts", "merges": "st s", "raw_count": 58532, "count": 116290, "decode_str": "sts"} -{"id": 30475, "token": "Speed", "merges": "Spe ed", "raw_count": 116333, "count": 116333, "decode_str": "Speed"} -{"id": 12215, "token": "\u0120guarantee", "merges": "\u0120guarant ee", "raw_count": 116366, "count": 116366, "decode_str": " guarantee"} -{"id": 6398, "token": "\u0120Union", "merges": "\u0120Un ion", "raw_count": 116396, "count": 116396, "decode_str": " Union"} -{"id": 17171, "token": "ONT", "merges": "ON T", "raw_count": 67383, "count": 116418, "decode_str": "ONT"} -{"id": 9327, "token": "ski", "merges": "sk i", "raw_count": 67491, "count": 116430, "decode_str": "ski"} -{"id": 49967, "token": "Linked", "merges": "Link ed", "raw_count": 116456, "count": 116456, "decode_str": "Linked"} -{"id": 17520, "token": "HH", "merges": "H H", "raw_count": 116466, "count": 116466, "decode_str": "HH"} -{"id": 15456, "token": "margin", "merges": "m argin", "raw_count": 116488, "count": 116488, "decode_str": "margin"} -{"id": 31934, "token": "\u0120md", "merges": "\u0120m d", "raw_count": 116506, "count": 116506, "decode_str": " md"} -{"id": 14104, "token": "terminal", "merges": "term inal", "raw_count": 116508, "count": 116508, "decode_str": "terminal"} -{"id": 42082, "token": "536", "merges": "5 36", "raw_count": 116513, "count": 116513, "decode_str": "536"} -{"id": 20023, "token": "\u0120undertaken", "merges": "\u0120undert aken", "raw_count": 116528, "count": 116528, "decode_str": " undertaken"} -{"id": 8920, "token": "\u0120youth", "merges": "\u0120you th", "raw_count": 110802, "count": 116557, "decode_str": " youth"} -{"id": 22274, "token": "Socket", "merges": "S ocket", "raw_count": 116564, "count": 116564, "decode_str": "Socket"} -{"id": 3631, "token": "\u0120Comp", "merges": "\u0120Com p", "raw_count": 44764, "count": 116623, "decode_str": " Comp"} -{"id": 23600, "token": "squ", "merges": "s qu", "raw_count": 62231, "count": 116659, "decode_str": "squ"} -{"id": 37488, "token": "override", "merges": "over ride", "raw_count": 116702, "count": 116702, "decode_str": "override"} -{"id": 54511, "token": "\u00e9\u00aa\u00a7", "merges": "\u00e9\u00aa \u00a7", "raw_count": 116714, "count": 116714, "decode_str": "\u9aa7"} -{"id": 49002, "token": "765", "merges": "7 65", "raw_count": 116736, "count": 116736, "decode_str": "765"} -{"id": 2263, "token": "\u0120Cal", "merges": "\u0120C al", "raw_count": 45957, "count": 116755, "decode_str": " Cal"} -{"id": 13182, "token": "pur", "merges": "p ur", "raw_count": 86602, "count": 116760, "decode_str": "pur"} -{"id": 6262, "token": "\u0120esc", "merges": "\u0120es c", "raw_count": 31271, "count": 116767, "decode_str": " esc"} -{"id": 5031, "token": "\u00d1\u0123\u00d1\u0124", "merges": "\u00d1\u0123 \u00d1\u0124", "raw_count": 34497, "count": 116780, "decode_str": "\u0441\u0442"} -{"id": 10078, "token": "\u0120participate", "merges": "\u0120particip ate", "raw_count": 116799, "count": 116799, "decode_str": " participate"} -{"id": 7659, "token": "\u0120Dec", "merges": "\u0120D ec", "raw_count": 107105, "count": 116801, "decode_str": " Dec"} -{"id": 3368, "token": "\u0120experiment", "merges": "\u0120exper iment", "raw_count": 88969, "count": 116821, "decode_str": " experiment"} -{"id": 43015, "token": "431", "merges": "4 31", "raw_count": 116861, "count": 116861, "decode_str": "431"} -{"id": 32088, "token": "Company", "merges": "Comp any", "raw_count": 116866, "count": 116866, "decode_str": "Company"} -{"id": 18206, "token": "LI", "merges": "L I", "raw_count": 116877, "count": 116877, "decode_str": "LI"} -{"id": 5313, "token": "\u0120piece", "merges": "\u0120pie ce", "raw_count": 116953, "count": 116953, "decode_str": " piece"} -{"id": 2565, "token": "\u0120cou", "merges": "\u0120c ou", "raw_count": 23713, "count": 116966, "decode_str": " cou"} -{"id": 36639, "token": "VB", "merges": "V B", "raw_count": 116985, "count": 116985, "decode_str": "VB"} -{"id": 42641, "token": "pw", "merges": "p w", "raw_count": 116987, "count": 116987, "decode_str": "pw"} -{"id": 9779, "token": "reams", "merges": "re ams", "raw_count": 96392, "count": 117035, "decode_str": "reams"} -{"id": 23241, "token": "\u0120accommodation", "merges": "\u0120accommod ation", "raw_count": 117042, "count": 117042, "decode_str": " accommodation"} -{"id": 23820, "token": "\u0120credentials", "merges": "\u0120cred entials", "raw_count": 117105, "count": 117105, "decode_str": " credentials"} -{"id": 14984, "token": "Entity", "merges": "Ent ity", "raw_count": 117105, "count": 117105, "decode_str": "Entity"} -{"id": 42630, "token": "CDC", "merges": "CD C", "raw_count": 117110, "count": 117110, "decode_str": "CDC"} -{"id": 20865, "token": "Download", "merges": "Down load", "raw_count": 117124, "count": 117124, "decode_str": "Download"} -{"id": 18658, "token": "Review", "merges": "Rev iew", "raw_count": 111732, "count": 117160, "decode_str": "Review"} -{"id": 17908, "token": "\u0120io", "merges": "\u0120i o", "raw_count": 117228, "count": 117228, "decode_str": " io"} -{"id": 22574, "token": "STATUS", "merges": "STAT US", "raw_count": 117230, "count": 117230, "decode_str": "STATUS"} -{"id": 5293, "token": "\u0120none", "merges": "\u0120n one", "raw_count": 104738, "count": 117252, "decode_str": " none"} -{"id": 25207, "token": "Rot", "merges": "R ot", "raw_count": 81625, "count": 117261, "decode_str": "Rot"} -{"id": 25912, "token": "cale", "merges": "c ale", "raw_count": 115402, "count": 117283, "decode_str": "cale"} -{"id": 35248, "token": "DOWN", "merges": "D OWN", "raw_count": 117286, "count": 117286, "decode_str": "DOWN"} -{"id": 23666, "token": "Ber", "merges": "B er", "raw_count": 117297, "count": 117297, "decode_str": "Ber"} -{"id": 6215, "token": "\u0120ship", "merges": "\u0120sh ip", "raw_count": 108626, "count": 117326, "decode_str": " ship"} -{"id": 21005, "token": "runtime", "merges": "r untime", "raw_count": 117334, "count": 117334, "decode_str": "runtime"} -{"id": 42866, "token": "CBS", "merges": "C BS", "raw_count": 117345, "count": 117345, "decode_str": "CBS"} -{"id": 27903, "token": "Folder", "merges": "F older", "raw_count": 117347, "count": 117347, "decode_str": "Folder"} -{"id": 34407, "token": "REQUEST", "merges": "RE QUEST", "raw_count": 117484, "count": 117484, "decode_str": "REQUEST"} -{"id": 2860, "token": "\u0120hom", "merges": "\u0120h om", "raw_count": 31546, "count": 117496, "decode_str": " hom"} -{"id": 27157, "token": "Bon", "merges": "B on", "raw_count": 117503, "count": 117503, "decode_str": "Bon"} -{"id": 22990, "token": "need", "merges": "ne ed", "raw_count": 117518, "count": 117518, "decode_str": "need"} -{"id": 38601, "token": "Bin", "merges": "B in", "raw_count": 117527, "count": 117527, "decode_str": "Bin"} -{"id": 6786, "token": "\u0120achieved", "merges": "\u0120achie ved", "raw_count": 117535, "count": 117535, "decode_str": " achieved"} -{"id": 51717, "token": "\u00e6\u0123\u013c", "merges": "\u00e6\u0123 \u013c", "raw_count": 117565, "count": 117565, "decode_str": "\u605a"} -{"id": 27306, "token": "OWER", "merges": "OW ER", "raw_count": 117586, "count": 117586, "decode_str": "OWER"} -{"id": 7037, "token": "\u0120compens", "merges": "\u0120comp ens", "raw_count": 9289, "count": 117638, "decode_str": " compens"} -{"id": 53203, "token": "\u00e7\u00ab\u00bd", "merges": "\u00e7\u00ab \u00bd", "raw_count": 117642, "count": 117642, "decode_str": "\u7afd"} -{"id": 54558, "token": "\u00e8\u0130\u013e", "merges": "\u00e8\u0130 \u013e", "raw_count": 117649, "count": 117649, "decode_str": "\u839c"} -{"id": 14476, "token": "ASK", "merges": "AS K", "raw_count": 83109, "count": 117663, "decode_str": "ASK"} -{"id": 10508, "token": "\u012098", "merges": "\u01209 8", "raw_count": 117668, "count": 117668, "decode_str": " 98"} -{"id": 24450, "token": "GLE", "merges": "G LE", "raw_count": 53506, "count": 117719, "decode_str": "GLE"} -{"id": 20151, "token": "035", "merges": "0 35", "raw_count": 117747, "count": 117747, "decode_str": "035"} -{"id": 3911, "token": "\u0120opin", "merges": "\u0120op in", "raw_count": 932, "count": 117757, "decode_str": " opin"} -{"id": 10644, "token": "Buffer", "merges": "B uffer", "raw_count": 117759, "count": 117759, "decode_str": "Buffer"} -{"id": 14428, "token": "know", "merges": "k now", "raw_count": 76458, "count": 117774, "decode_str": "know"} -{"id": 10525, "token": "amond", "merges": "am ond", "raw_count": 44238, "count": 117796, "decode_str": "amond"} -{"id": 26454, "token": "management", "merges": "man agement", "raw_count": 117809, "count": 117809, "decode_str": "management"} -{"id": 12563, "token": "also", "merges": "al so", "raw_count": 117833, "count": 117833, "decode_str": "also"} -{"id": 5201, "token": "\u0120Dis", "merges": "\u0120D is", "raw_count": 67989, "count": 117838, "decode_str": " Dis"} -{"id": 5691, "token": "\u0120challenge", "merges": "\u0120chall enge", "raw_count": 117851, "count": 117851, "decode_str": " challenge"} -{"id": 4728, "token": "\u0120subsequ", "merges": "\u0120sub sequ", "raw_count": 5267, "count": 117856, "decode_str": " subsequ"} -{"id": 14767, "token": "_[", "merges": "_ [", "raw_count": 117887, "count": 117887, "decode_str": "_["} -{"id": 50767, "token": "\u00e5\u012a\u012a", "merges": "\u00e5\u012a \u012a", "raw_count": 117904, "count": 117904, "decode_str": "\u5208"} -{"id": 7200, "token": "\u0120accuracy", "merges": "\u0120accur acy", "raw_count": 117913, "count": 117913, "decode_str": " accuracy"} -{"id": 36435, "token": "digit", "merges": "dig it", "raw_count": 117919, "count": 117919, "decode_str": "digit"} -{"id": 9113, "token": "\u0120correctly", "merges": "\u0120correct ly", "raw_count": 117934, "count": 117934, "decode_str": " correctly"} -{"id": 9321, "token": "iva", "merges": "iv a", "raw_count": 108773, "count": 117946, "decode_str": "iva"} -{"id": 27453, "token": "TEM", "merges": "T EM", "raw_count": 117957, "count": 117957, "decode_str": "TEM"} -{"id": 7300, "token": "anta", "merges": "ant a", "raw_count": 70433, "count": 117967, "decode_str": "anta"} -{"id": 30713, "token": "touch", "merges": "t ouch", "raw_count": 118010, "count": 118010, "decode_str": "touch"} -{"id": 18373, "token": "\u0120obs", "merges": "\u0120ob s", "raw_count": 114931, "count": 118022, "decode_str": " obs"} -{"id": 36915, "token": "activate", "merges": "activ ate", "raw_count": 118069, "count": 118069, "decode_str": "activate"} -{"id": 26539, "token": "chrom", "merges": "ch rom", "raw_count": 118080, "count": 118080, "decode_str": "chrom"} -{"id": 5184, "token": "\u0120hop", "merges": "\u0120h op", "raw_count": 32648, "count": 118083, "decode_str": " hop"} -{"id": 19832, "token": "\u0120Input", "merges": "\u0120In put", "raw_count": 118093, "count": 118093, "decode_str": " Input"} -{"id": 40276, "token": "QA", "merges": "Q A", "raw_count": 118110, "count": 118110, "decode_str": "QA"} -{"id": 3563, "token": "\u0120late", "merges": "\u0120l ate", "raw_count": 100452, "count": 118140, "decode_str": " late"} -{"id": 25046, "token": "Camp", "merges": "C amp", "raw_count": 118142, "count": 118142, "decode_str": "Camp"} -{"id": 3685, "token": "\u00c3\u00a3o", "merges": "\u00c3\u00a3 o", "raw_count": 30372, "count": 118180, "decode_str": "\u00e3o"} -{"id": 8205, "token": "\u0120pursu", "merges": "\u0120pur su", "raw_count": 6739, "count": 118190, "decode_str": " pursu"} -{"id": 38032, "token": "557", "merges": "55 7", "raw_count": 118221, "count": 118221, "decode_str": "557"} -{"id": 8977, "token": "omatic", "merges": "om atic", "raw_count": 35015, "count": 118227, "decode_str": "omatic"} -{"id": 20842, "token": "Standard", "merges": "Stand ard", "raw_count": 118243, "count": 118243, "decode_str": "Standard"} -{"id": 16100, "token": "\u0120enterprise", "merges": "\u0120enter prise", "raw_count": 118247, "count": 118247, "decode_str": " enterprise"} -{"id": 36447, "token": "Stan", "merges": "St an", "raw_count": 118250, "count": 118250, "decode_str": "Stan"} -{"id": 43809, "token": "725", "merges": "7 25", "raw_count": 118251, "count": 118251, "decode_str": "725"} -{"id": 8468, "token": "\u0120sensor", "merges": "\u0120sens or", "raw_count": 118339, "count": 118339, "decode_str": " sensor"} -{"id": 10233, "token": "iture", "merges": "it ure", "raw_count": 24473, "count": 118342, "decode_str": "iture"} -{"id": 4633, "token": "\u0120popular", "merges": "\u0120pop ular", "raw_count": 105227, "count": 118343, "decode_str": " popular"} -{"id": 12275, "token": "\u0120pixel", "merges": "\u0120pix el", "raw_count": 118352, "count": 118352, "decode_str": " pixel"} -{"id": 8276, "token": "\u0120warn", "merges": "\u0120w arn", "raw_count": 36462, "count": 118378, "decode_str": " warn"} -{"id": 19162, "token": "\u0120pac", "merges": "\u0120p ac", "raw_count": 118431, "count": 118431, "decode_str": " pac"} -{"id": 15617, "token": "both", "merges": "b oth", "raw_count": 118436, "count": 118436, "decode_str": "both"} -{"id": 53159, "token": "\u00e7\u00a7\u0143", "merges": "\u00e7\u00a7 \u0143", "raw_count": 118437, "count": 118437, "decode_str": "\u79ed"} -{"id": 7000, "token": "\u0120detailed", "merges": "\u0120detail ed", "raw_count": 118485, "count": 118485, "decode_str": " detailed"} -{"id": 23520, "token": "offee", "merges": "of fee", "raw_count": 114500, "count": 118495, "decode_str": "offee"} -{"id": 6908, "token": "\u0120MA", "merges": "\u0120M A", "raw_count": 33307, "count": 118498, "decode_str": " MA"} -{"id": 11170, "token": "vy", "merges": "v y", "raw_count": 113599, "count": 118508, "decode_str": "vy"} -{"id": 3705, "token": "\u0120pict", "merges": "\u0120p ict", "raw_count": 6975, "count": 118618, "decode_str": " pict"} -{"id": 21136, "token": "\u0120pc", "merges": "\u0120p c", "raw_count": 118630, "count": 118630, "decode_str": " pc"} -{"id": 6629, "token": "\u0120schools", "merges": "\u0120school s", "raw_count": 118676, "count": 118676, "decode_str": " schools"} -{"id": 31352, "token": "Gar", "merges": "G ar", "raw_count": 118679, "count": 118679, "decode_str": "Gar"} -{"id": 3858, "token": "\u0120friends", "merges": "\u0120fri ends", "raw_count": 118698, "count": 118698, "decode_str": " friends"} -{"id": 35791, "token": "673", "merges": "67 3", "raw_count": 118698, "count": 118698, "decode_str": "673"} -{"id": 22309, "token": "why", "merges": "w hy", "raw_count": 118699, "count": 118699, "decode_str": "why"} -{"id": 42045, "token": "plots", "merges": "pl ots", "raw_count": 118725, "count": 118725, "decode_str": "plots"} -{"id": 16825, "token": "nik", "merges": "n ik", "raw_count": 113039, "count": 118733, "decode_str": "nik"} -{"id": 36936, "token": "772", "merges": "77 2", "raw_count": 118744, "count": 118744, "decode_str": "772"} -{"id": 47070, "token": "548", "merges": "5 48", "raw_count": 118747, "count": 118747, "decode_str": "548"} -{"id": 17443, "token": "jk", "merges": "j k", "raw_count": 118775, "count": 118775, "decode_str": "jk"} -{"id": 3667, "token": "\u0120Reg", "merges": "\u0120R eg", "raw_count": 35900, "count": 118810, "decode_str": " Reg"} -{"id": 6727, "token": "\u0120tro", "merges": "\u0120t ro", "raw_count": 26426, "count": 118821, "decode_str": " tro"} -{"id": 19128, "token": "\u0120Tree", "merges": "\u0120T ree", "raw_count": 118848, "count": 118848, "decode_str": " Tree"} -{"id": 48063, "token": "712", "merges": "7 12", "raw_count": 118853, "count": 118853, "decode_str": "712"} -{"id": 15782, "token": "IDS", "merges": "ID S", "raw_count": 93731, "count": 118858, "decode_str": "IDS"} -{"id": 42371, "token": "\u0120'*", "merges": "\u0120' *", "raw_count": 118860, "count": 118860, "decode_str": " '*"} -{"id": 12813, "token": "plex", "merges": "ple x", "raw_count": 50331, "count": 118867, "decode_str": "plex"} -{"id": 12615, "token": "fall", "merges": "f all", "raw_count": 118875, "count": 118875, "decode_str": "fall"} -{"id": 7041, "token": "claim", "merges": "cl aim", "raw_count": 60325, "count": 118883, "decode_str": "claim"} -{"id": 1954, "token": "\u00c3\u00b3", "merges": "\u00c3 \u00b3", "raw_count": 33364, "count": 118885, "decode_str": "\u00f3"} -{"id": 11858, "token": "\u0120140", "merges": "\u01201 40", "raw_count": 118891, "count": 118891, "decode_str": " 140"} -{"id": 43836, "token": "levels", "merges": "level s", "raw_count": 118898, "count": 118898, "decode_str": "levels"} -{"id": 34253, "token": "\u0120aids", "merges": "\u0120a ids", "raw_count": 118905, "count": 118905, "decode_str": " aids"} -{"id": 14934, "token": "heet", "merges": "he et", "raw_count": 103929, "count": 118906, "decode_str": "heet"} -{"id": 6558, "token": "\u0120maintain", "merges": "\u0120maint ain", "raw_count": 118919, "count": 118919, "decode_str": " maintain"} -{"id": 17525, "token": "sil", "merges": "s il", "raw_count": 118959, "count": 118959, "decode_str": "sil"} -{"id": 41237, "token": "Jason", "merges": "J ason", "raw_count": 118994, "count": 118994, "decode_str": "Jason"} -{"id": 35792, "token": "execution", "merges": "exec ution", "raw_count": 119022, "count": 119022, "decode_str": "execution"} -{"id": 5989, "token": "\u0120circumstances", "merges": "\u0120circum stances", "raw_count": 119027, "count": 119027, "decode_str": " circumstances"} -{"id": 53715, "token": "\u00e8\u00a1\u00be", "merges": "\u00e8\u00a1 \u00be", "raw_count": 119051, "count": 119051, "decode_str": "\u887e"} -{"id": 5160, "token": "\u00d0\u00bc", "merges": "\u00d0 \u00bc", "raw_count": 51985, "count": 119088, "decode_str": "\u043c"} -{"id": 13107, "token": "hn", "merges": "h n", "raw_count": 118869, "count": 119099, "decode_str": "hn"} -{"id": 10106, "token": "\u0120urban", "merges": "\u0120ur ban", "raw_count": 119109, "count": 119109, "decode_str": " urban"} -{"id": 4028, "token": "\u0120writing", "merges": "\u0120writ ing", "raw_count": 119118, "count": 119118, "decode_str": " writing"} -{"id": 4964, "token": "\u0120hour", "merges": "\u0120h our", "raw_count": 112581, "count": 119124, "decode_str": " hour"} -{"id": 6667, "token": "\u0120examples", "merges": "\u0120exam ples", "raw_count": 119128, "count": 119128, "decode_str": " examples"} -{"id": 6289, "token": "\u0120referred", "merges": "\u0120refer red", "raw_count": 119134, "count": 119134, "decode_str": " referred"} -{"id": 29404, "token": "acl", "merges": "ac l", "raw_count": 119151, "count": 119151, "decode_str": "acl"} -{"id": 5880, "token": "\u0120cycle", "merges": "\u0120cy cle", "raw_count": 119196, "count": 119196, "decode_str": " cycle"} -{"id": 21577, "token": "\u0120Magic", "merges": "\u0120Mag ic", "raw_count": 119202, "count": 119202, "decode_str": " Magic"} -{"id": 30658, "token": "Wat", "merges": "W at", "raw_count": 119240, "count": 119240, "decode_str": "Wat"} -{"id": 9352, "token": "illy", "merges": "il ly", "raw_count": 118546, "count": 119243, "decode_str": "illy"} -{"id": 46455, "token": "816", "merges": "8 16", "raw_count": 119244, "count": 119244, "decode_str": "816"} -{"id": 4261, "token": "iring", "merges": "ir ing", "raw_count": 41137, "count": 119285, "decode_str": "iring"} -{"id": 6040, "token": "subset", "merges": "sub set", "raw_count": 119269, "count": 119315, "decode_str": "subset"} -{"id": 9741, "token": "\u0120forest", "merges": "\u0120fore st", "raw_count": 119317, "count": 119317, "decode_str": " forest"} -{"id": 24905, "token": "parents", "merges": "parent s", "raw_count": 116475, "count": 119332, "decode_str": "parents"} -{"id": 6294, "token": "\u0120shut", "merges": "\u0120sh ut", "raw_count": 48390, "count": 119345, "decode_str": " shut"} -{"id": 40181, "token": "434", "merges": "4 34", "raw_count": 119347, "count": 119347, "decode_str": "434"} -{"id": 12114, "token": "\u0120\\\"", "merges": "\u0120\\ \"", "raw_count": 119352, "count": 119352, "decode_str": " \\\""} -{"id": 52919, "token": "\u00e7\u0138\u00b3", "merges": "\u00e7\u0138 \u00b3", "raw_count": 119371, "count": 119371, "decode_str": "\u75b3"} -{"id": 22897, "token": "ACS", "merges": "AC S", "raw_count": 119328, "count": 119378, "decode_str": "ACS"} -{"id": 2296, "token": "\u0120says", "merges": "\u0120s ays", "raw_count": 119397, "count": 119397, "decode_str": " says"} -{"id": 21107, "token": "working", "merges": "work ing", "raw_count": 119400, "count": 119400, "decode_str": "working"} -{"id": 21772, "token": "Struct", "merges": "St ruct", "raw_count": 119438, "count": 119438, "decode_str": "Struct"} -{"id": 45136, "token": "SOL", "merges": "S OL", "raw_count": 119446, "count": 119446, "decode_str": "SOL"} -{"id": 6733, "token": "\u0120efficiency", "merges": "\u0120effic iency", "raw_count": 119482, "count": 119482, "decode_str": " efficiency"} -{"id": 16030, "token": "\u0120inspect", "merges": "\u0120ins pect", "raw_count": 105420, "count": 119520, "decode_str": " inspect"} -{"id": 44439, "token": "825", "merges": "8 25", "raw_count": 119523, "count": 119523, "decode_str": "825"} -{"id": 4545, "token": "\u0120advant", "merges": "\u0120adv ant", "raw_count": 760, "count": 119533, "decode_str": " advant"} -{"id": 43020, "token": "finish", "merges": "fin ish", "raw_count": 119544, "count": 119544, "decode_str": "finish"} -{"id": 3738, "token": "\u0120although", "merges": "\u0120al though", "raw_count": 119582, "count": 119582, "decode_str": " although"} -{"id": 15828, "token": "\u0120passenger", "merges": "\u0120pass enger", "raw_count": 119591, "count": 119591, "decode_str": " passenger"} -{"id": 13509, "token": "elcome", "merges": "el come", "raw_count": 55202, "count": 119594, "decode_str": "elcome"} -{"id": 6703, "token": "\u0120inner", "merges": "\u0120in ner", "raw_count": 119602, "count": 119602, "decode_str": " inner"} -{"id": 9748, "token": "\u01201992", "merges": "\u0120199 2", "raw_count": 119629, "count": 119629, "decode_str": " 1992"} -{"id": 19578, "token": "DES", "merges": "D ES", "raw_count": 101735, "count": 119638, "decode_str": "DES"} -{"id": 20257, "token": "uni", "merges": "un i", "raw_count": 119651, "count": 119651, "decode_str": "uni"} -{"id": 4269, "token": "\u0120caused", "merges": "\u0120caus ed", "raw_count": 119665, "count": 119665, "decode_str": " caused"} -{"id": 39584, "token": "tit", "merges": "t it", "raw_count": 119671, "count": 119671, "decode_str": "tit"} -{"id": 4677, "token": "\u0120figure", "merges": "\u0120fig ure", "raw_count": 119675, "count": 119675, "decode_str": " figure"} -{"id": 15798, "token": "024", "merges": "0 24", "raw_count": 119692, "count": 119692, "decode_str": "024"} -{"id": 25906, "token": "Domain", "merges": "Dom ain", "raw_count": 119704, "count": 119704, "decode_str": "Domain"} -{"id": 35276, "token": "671", "merges": "67 1", "raw_count": 119714, "count": 119714, "decode_str": "671"} -{"id": 31189, "token": "Sound", "merges": "S ound", "raw_count": 119718, "count": 119718, "decode_str": "Sound"} -{"id": 53178, "token": "\u00e7\u00a8\u00b9", "merges": "\u00e7\u00a8 \u00b9", "raw_count": 119719, "count": 119719, "decode_str": "\u7a39"} -{"id": 9141, "token": "iser", "merges": "is er", "raw_count": 85713, "count": 119730, "decode_str": "iser"} -{"id": 4400, "token": "\u0120federal", "merges": "\u0120f ederal", "raw_count": 119740, "count": 119740, "decode_str": " federal"} -{"id": 32318, "token": "JC", "merges": "J C", "raw_count": 119745, "count": 119745, "decode_str": "JC"} -{"id": 21983, "token": "\u0120iv", "merges": "\u0120 iv", "raw_count": 119757, "count": 119757, "decode_str": " iv"} -{"id": 7413, "token": "ifferent", "merges": "if ferent", "raw_count": 6713, "count": 119769, "decode_str": "ifferent"} -{"id": 42926, "token": ",#", "merges": ", #", "raw_count": 119773, "count": 119773, "decode_str": ",#"} -{"id": 35933, "token": "swap", "merges": "sw ap", "raw_count": 119788, "count": 119788, "decode_str": "swap"} -{"id": 9557, "token": "\u0120nam", "merges": "\u0120n am", "raw_count": 64571, "count": 119808, "decode_str": " nam"} -{"id": 8069, "token": "\u0120effectively", "merges": "\u0120effect ively", "raw_count": 119864, "count": 119864, "decode_str": " effectively"} -{"id": 21888, "token": "recogn", "merges": "rec ogn", "raw_count": 79837, "count": 119915, "decode_str": "recogn"} -{"id": 7350, "token": "\u0120concerns", "merges": "\u0120concer ns", "raw_count": 119923, "count": 119923, "decode_str": " concerns"} -{"id": 8278, "token": "\u0120disput", "merges": "\u0120dis put", "raw_count": 1777, "count": 119927, "decode_str": " disput"} -{"id": 14430, "token": "\u0120quote", "merges": "\u0120qu ote", "raw_count": 119936, "count": 119936, "decode_str": " quote"} -{"id": 19093, "token": "TEXT", "merges": "T EXT", "raw_count": 102168, "count": 119971, "decode_str": "TEXT"} -{"id": 3912, "token": "\u0120tou", "merges": "\u0120t ou", "raw_count": 13867, "count": 119999, "decode_str": " tou"} -{"id": 22243, "token": "crypt", "merges": "c rypt", "raw_count": 66605, "count": 120006, "decode_str": "crypt"} -{"id": 13841, "token": "\u0120stake", "merges": "\u0120st ake", "raw_count": 20644, "count": 120012, "decode_str": " stake"} -{"id": 52798, "token": "\u00e7\u012c\u00b8", "merges": "\u00e7\u012c \u00b8", "raw_count": 120022, "count": 120022, "decode_str": "\u72b8"} -{"id": 22965, "token": "annotation", "merges": "annot ation", "raw_count": 120042, "count": 120042, "decode_str": "annotation"} -{"id": 8403, "token": "sup", "merges": "s up", "raw_count": 119981, "count": 120044, "decode_str": "sup"} -{"id": 16685, "token": "\u0120negotiations", "merges": "\u0120negot iations", "raw_count": 120065, "count": 120065, "decode_str": " negotiations"} -{"id": 11670, "token": "anz", "merges": "an z", "raw_count": 119141, "count": 120065, "decode_str": "anz"} -{"id": 4314, "token": "\u0120eight", "merges": "\u0120e ight", "raw_count": 77314, "count": 120068, "decode_str": " eight"} -{"id": 31484, "token": "Running", "merges": "R unning", "raw_count": 120069, "count": 120069, "decode_str": "Running"} -{"id": 32375, "token": "integration", "merges": "integr ation", "raw_count": 120113, "count": 120113, "decode_str": "integration"} -{"id": 3166, "token": "\u0120Do", "merges": "\u0120D o", "raw_count": 83934, "count": 120131, "decode_str": " Do"} -{"id": 43171, "token": "524", "merges": "5 24", "raw_count": 120152, "count": 120152, "decode_str": "524"} -{"id": 6394, "token": "{{", "merges": "{ {", "raw_count": 116488, "count": 120215, "decode_str": "{{"} -{"id": 26945, "token": "Generator", "merges": "Gener ator", "raw_count": 120229, "count": 120229, "decode_str": "Generator"} -{"id": 39232, "token": "ftp", "merges": "ft p", "raw_count": 120272, "count": 120272, "decode_str": "ftp"} -{"id": 49416, "token": "912", "merges": "9 12", "raw_count": 120308, "count": 120308, "decode_str": "912"} -{"id": 47901, "token": "Ops", "merges": "O ps", "raw_count": 120316, "count": 120316, "decode_str": "Ops"} -{"id": 36272, "token": "Clean", "merges": "Cle an", "raw_count": 120328, "count": 120328, "decode_str": "Clean"} -{"id": 4823, "token": "\u0120consequ", "merges": "\u0120con sequ", "raw_count": 6208, "count": 120331, "decode_str": " consequ"} -{"id": 32541, "token": "ensors", "merges": "ens ors", "raw_count": 120341, "count": 120341, "decode_str": "ensors"} -{"id": 18683, "token": "mel", "merges": "m el", "raw_count": 120343, "count": 120343, "decode_str": "mel"} -{"id": 41328, "token": "464", "merges": "4 64", "raw_count": 120355, "count": 120355, "decode_str": "464"} -{"id": 8553, "token": "\u0120accounts", "merges": "\u0120account s", "raw_count": 120357, "count": 120357, "decode_str": " accounts"} -{"id": 42877, "token": "suite", "merges": "su ite", "raw_count": 120373, "count": 120373, "decode_str": "suite"} -{"id": 3194, "token": "eks", "merges": "e ks", "raw_count": 20553, "count": 120375, "decode_str": "eks"} -{"id": 51383, "token": "\u00e5\u0143\u013d", "merges": "\u00e5\u0143 \u013d", "raw_count": 120380, "count": 120380, "decode_str": "\u5b5b"} -{"id": 27395, "token": "DOM", "merges": "D OM", "raw_count": 120412, "count": 120412, "decode_str": "DOM"} -{"id": 4955, "token": "\u0120org", "merges": "\u0120or g", "raw_count": 64866, "count": 120414, "decode_str": " org"} -{"id": 5083, "token": "\u0120truth", "merges": "\u0120tr uth", "raw_count": 115193, "count": 120428, "decode_str": " truth"} -{"id": 20989, "token": "built", "merges": "bu ilt", "raw_count": 120445, "count": 120445, "decode_str": "built"} -{"id": 22904, "token": "Transform", "merges": "Trans form", "raw_count": 120454, "count": 120454, "decode_str": "Transform"} -{"id": 5514, "token": "\u0120ded", "merges": "\u0120d ed", "raw_count": 27100, "count": 120465, "decode_str": " ded"} -{"id": 7654, "token": "\u0120strict", "merges": "\u0120st rict", "raw_count": 88512, "count": 120504, "decode_str": " strict"} -{"id": 36679, "token": "596", "merges": "59 6", "raw_count": 120507, "count": 120507, "decode_str": "596"} -{"id": 53896, "token": "\u00e8\u00b1\u0129", "merges": "\u00e8\u00b1 \u0129", "raw_count": 120520, "count": 120520, "decode_str": "\u8c47"} -{"id": 20405, "token": "Sir", "merges": "S ir", "raw_count": 120522, "count": 120522, "decode_str": "Sir"} -{"id": 12866, "token": "cases", "merges": "c ases", "raw_count": 120530, "count": 120530, "decode_str": "cases"} -{"id": 30104, "token": "ASC", "merges": "AS C", "raw_count": 120549, "count": 120549, "decode_str": "ASC"} -{"id": 4177, "token": "\u0120star", "merges": "\u0120st ar", "raw_count": 102803, "count": 120575, "decode_str": " star"} -{"id": 53767, "token": "\u00e8\u00a7\u00a5", "merges": "\u00e8\u00a7 \u00a5", "raw_count": 120616, "count": 120616, "decode_str": "\u89e5"} -{"id": 7909, "token": "oral", "merges": "or al", "raw_count": 51568, "count": 120635, "decode_str": "oral"} -{"id": 4483, "token": "\u0120allows", "merges": "\u0120allow s", "raw_count": 120638, "count": 120638, "decode_str": " allows"} -{"id": 5476, "token": "\u0120guess", "merges": "\u0120gu ess", "raw_count": 103173, "count": 120679, "decode_str": " guess"} -{"id": 39840, "token": "875", "merges": "8 75", "raw_count": 120725, "count": 120725, "decode_str": "875"} -{"id": 4617, "token": "\u0120impos", "merges": "\u0120im pos", "raw_count": 447, "count": 120792, "decode_str": " impos"} -{"id": 4293, "token": "\u0120imm", "merges": "\u0120im m", "raw_count": 32919, "count": 120815, "decode_str": " imm"} -{"id": 14908, "token": "gments", "merges": "g ments", "raw_count": 114002, "count": 120838, "decode_str": "gments"} -{"id": 6838, "token": "\u0120girls", "merges": "\u0120girl s", "raw_count": 120849, "count": 120849, "decode_str": " girls"} -{"id": 14453, "token": "phys", "merges": "ph ys", "raw_count": 63067, "count": 120857, "decode_str": "phys"} -{"id": 30520, "token": "lap", "merges": "l ap", "raw_count": 120872, "count": 120872, "decode_str": "lap"} -{"id": 22265, "token": "\u0120Assert", "merges": "\u0120Ass ert", "raw_count": 120905, "count": 120905, "decode_str": " Assert"} -{"id": 18587, "token": "TON", "merges": "T ON", "raw_count": 118138, "count": 120906, "decode_str": "TON"} -{"id": 14638, "token": "\u0120germ", "merges": "\u0120g erm", "raw_count": 120068, "count": 120926, "decode_str": " germ"} -{"id": 23474, "token": "Selection", "merges": "Se lection", "raw_count": 121006, "count": 121006, "decode_str": "Selection"} -{"id": 29619, "token": "scheme", "merges": "sche me", "raw_count": 121034, "count": 121034, "decode_str": "scheme"} -{"id": 54555, "token": "\u00e6\u012c\u00bb", "merges": "\u00e6\u012c \u00bb", "raw_count": 121071, "count": 121071, "decode_str": "\u62bb"} -{"id": 34960, "token": "Ken", "merges": "K en", "raw_count": 121076, "count": 121076, "decode_str": "Ken"} -{"id": 54550, "token": "\u00e6\u0139\u00af", "merges": "\u00e6\u0139 \u00af", "raw_count": 121082, "count": 121082, "decode_str": "\u65ef"} -{"id": 18204, "token": "Prim", "merges": "P rim", "raw_count": 76158, "count": 121090, "decode_str": "Prim"} -{"id": 50198, "token": "mw", "merges": "m w", "raw_count": 121092, "count": 121092, "decode_str": "mw"} -{"id": 48888, "token": "listener", "merges": "list ener", "raw_count": 121095, "count": 121095, "decode_str": "listener"} -{"id": 34189, "token": "escape", "merges": "esc ape", "raw_count": 121095, "count": 121095, "decode_str": "escape"} -{"id": 14535, "token": "ISH", "merges": "IS H", "raw_count": 80339, "count": 121114, "decode_str": "ISH"} -{"id": 43228, "token": "Loss", "merges": "L oss", "raw_count": 121115, "count": 121115, "decode_str": "Loss"} -{"id": 32304, "token": "tg", "merges": "t g", "raw_count": 121146, "count": 121146, "decode_str": "tg"} -{"id": 50431, "token": "\u00e4\u00b8\u00bc", "merges": "\u00e4\u00b8 \u00bc", "raw_count": 121156, "count": 121156, "decode_str": "\u4e3c"} -{"id": 17335, "token": "\u0120proxy", "merges": "\u0120pro xy", "raw_count": 121158, "count": 121158, "decode_str": " proxy"} -{"id": 4361, "token": "\u0120reading", "merges": "\u0120read ing", "raw_count": 121202, "count": 121202, "decode_str": " reading"} -{"id": 44072, "token": "<=", "merges": "< =", "raw_count": 121220, "count": 121220, "decode_str": "<="} -{"id": 4374, "token": "Yes", "merges": "Y es", "raw_count": 116558, "count": 121223, "decode_str": "Yes"} -{"id": 44168, "token": "TTPS", "merges": "TT PS", "raw_count": 121229, "count": 121229, "decode_str": "TTPS"} -{"id": 53354, "token": "\u00e7\u00bb\u00a1", "merges": "\u00e7\u00bb \u00a1", "raw_count": 121267, "count": 121267, "decode_str": "\u7ee1"} -{"id": 7936, "token": "\u0120fundamental", "merges": "\u0120fundament al", "raw_count": 121277, "count": 121277, "decode_str": " fundamental"} -{"id": 6273, "token": "\u0120vote", "merges": "\u0120v ote", "raw_count": 121319, "count": 121319, "decode_str": " vote"} -{"id": 5752, "token": "\u0120serve", "merges": "\u0120ser ve", "raw_count": 121364, "count": 121364, "decode_str": " serve"} -{"id": 7394, "token": "\u0120gate", "merges": "\u0120g ate", "raw_count": 85339, "count": 121371, "decode_str": " gate"} -{"id": 43208, "token": "emo", "merges": "em o", "raw_count": 121418, "count": 121418, "decode_str": "emo"} -{"id": 5663, "token": "\u0120belong", "merges": "\u0120bel ong", "raw_count": 35612, "count": 121429, "decode_str": " belong"} -{"id": 3064, "token": "\u0120difference", "merges": "\u0120diffe rence", "raw_count": 121472, "count": 121472, "decode_str": " difference"} -{"id": 7703, "token": "\u0120seek", "merges": "\u0120see k", "raw_count": 112548, "count": 121476, "decode_str": " seek"} -{"id": 30995, "token": "constraint", "merges": "const raint", "raw_count": 121483, "count": 121483, "decode_str": "constraint"} -{"id": 9830, "token": "\u0120colors", "merges": "\u0120col ors", "raw_count": 121507, "count": 121507, "decode_str": " colors"} -{"id": 33043, "token": "\u0120covenant", "merges": "\u0120cov enant", "raw_count": 121516, "count": 121516, "decode_str": " covenant"} -{"id": 3934, "token": "osure", "merges": "os ure", "raw_count": 7550, "count": 121528, "decode_str": "osure"} -{"id": 20356, "token": "Security", "merges": "Sec urity", "raw_count": 121533, "count": 121533, "decode_str": "Security"} -{"id": 52309, "token": "\u00e6\u00a1\u0142", "merges": "\u00e6\u00a1 \u0142", "raw_count": 121544, "count": 121544, "decode_str": "\u6860"} -{"id": 45256, "token": "\u00e5\u0122\u012d", "merges": "\u00e5\u0122 \u012d", "raw_count": 121557, "count": 121557, "decode_str": "\u500b"} -{"id": 27378, "token": "ployment", "merges": "ploy ment", "raw_count": 121581, "count": 121581, "decode_str": "ployment"} -{"id": 24226, "token": "Cas", "merges": "C as", "raw_count": 121629, "count": 121629, "decode_str": "Cas"} -{"id": 48856, "token": "ICC", "merges": "IC C", "raw_count": 121635, "count": 121635, "decode_str": "ICC"} -{"id": 8158, "token": "\u0120bath", "merges": "\u0120b ath", "raw_count": 31468, "count": 121645, "decode_str": " bath"} -{"id": 29916, "token": "Carl", "merges": "C arl", "raw_count": 121654, "count": 121654, "decode_str": "Carl"} -{"id": 10007, "token": "\u0120modify", "merges": "\u0120mod ify", "raw_count": 121686, "count": 121686, "decode_str": " modify"} -{"id": 18548, "token": "Summary", "merges": "Sum mary", "raw_count": 121688, "count": 121688, "decode_str": "Summary"} -{"id": 34309, "token": "visual", "merges": "vis ual", "raw_count": 121696, "count": 121696, "decode_str": "visual"} -{"id": 11235, "token": "rele", "merges": "re le", "raw_count": 22706, "count": 121701, "decode_str": "rele"} -{"id": 17037, "token": "VERSION", "merges": "VERS ION", "raw_count": 121708, "count": 121708, "decode_str": "VERSION"} -{"id": 28968, "token": "Volume", "merges": "Vol ume", "raw_count": 121712, "count": 121712, "decode_str": "Volume"} -{"id": 10276, "token": "\u0120compliance", "merges": "\u0120compl iance", "raw_count": 121713, "count": 121713, "decode_str": " compliance"} -{"id": 4179, "token": "\u0120charge", "merges": "\u0120char ge", "raw_count": 121727, "count": 121727, "decode_str": " charge"} -{"id": 30531, "token": "FU", "merges": "F U", "raw_count": 121740, "count": 121740, "decode_str": "FU"} -{"id": 12154, "token": "\u0120sessions", "merges": "\u0120s essions", "raw_count": 121751, "count": 121751, "decode_str": " sessions"} -{"id": 34240, "token": "958", "merges": "95 8", "raw_count": 121754, "count": 121754, "decode_str": "958"} -{"id": 11737, "token": "\u0120tu", "merges": "\u0120t u", "raw_count": 116422, "count": 121798, "decode_str": " tu"} -{"id": 20838, "token": "Schema", "merges": "Sche ma", "raw_count": 121801, "count": 121801, "decode_str": "Schema"} -{"id": 4568, "token": "\u0120Rec", "merges": "\u0120R ec", "raw_count": 70919, "count": 121877, "decode_str": " Rec"} -{"id": 44979, "token": "rotate", "merges": "rot ate", "raw_count": 121892, "count": 121892, "decode_str": "rotate"} -{"id": 19255, "token": "hero", "merges": "he ro", "raw_count": 120343, "count": 121904, "decode_str": "hero"} -{"id": 21341, "token": "chart", "merges": "ch art", "raw_count": 121931, "count": 121931, "decode_str": "chart"} -{"id": 7673, "token": "More", "merges": "M ore", "raw_count": 121349, "count": 121935, "decode_str": "More"} -{"id": 9734, "token": "\u0120warning", "merges": "\u0120war ning", "raw_count": 121939, "count": 121939, "decode_str": " warning"} -{"id": 27962, "token": "sound", "merges": "s ound", "raw_count": 121988, "count": 121988, "decode_str": "sound"} -{"id": 30319, "token": "rase", "merges": "r ase", "raw_count": 15262, "count": 121994, "decode_str": "rase"} -{"id": 31059, "token": "Rock", "merges": "R ock", "raw_count": 122048, "count": 122048, "decode_str": "Rock"} -{"id": 5358, "token": "ensure", "merges": "ens ure", "raw_count": 121983, "count": 122077, "decode_str": "ensure"} -{"id": 19366, "token": "UTH", "merges": "UT H", "raw_count": 29565, "count": 122138, "decode_str": "UTH"} -{"id": 19236, "token": "angles", "merges": "ang les", "raw_count": 110488, "count": 122140, "decode_str": "angles"} -{"id": 5674, "token": "\u0120nation", "merges": "\u0120n ation", "raw_count": 66600, "count": 122147, "decode_str": " nation"} -{"id": 18747, "token": "\u0120dx", "merges": "\u0120d x", "raw_count": 122199, "count": 122199, "decode_str": " dx"} -{"id": 53468, "token": "\u00e8\u0123\u0134", "merges": "\u00e8\u0123 \u0134", "raw_count": 122199, "count": 122199, "decode_str": "\u8052"} -{"id": 31019, "token": "Techn", "merges": "Te chn", "raw_count": 122202, "count": 122202, "decode_str": "Techn"} -{"id": 7763, "token": "\u0120applicable", "merges": "\u0120applic able", "raw_count": 122204, "count": 122204, "decode_str": " applicable"} -{"id": 23472, "token": "\u0120Client", "merges": "\u0120Cl ient", "raw_count": 122217, "count": 122217, "decode_str": " Client"} -{"id": 7680, "token": "\u0120contribution", "merges": "\u0120cont ribution", "raw_count": 122222, "count": 122222, "decode_str": " contribution"} -{"id": 15852, "token": "Parent", "merges": "P arent", "raw_count": 122233, "count": 122233, "decode_str": "Parent"} -{"id": 50669, "token": "\u00e5\u0125\u00ae", "merges": "\u00e5\u0125 \u00ae", "raw_count": 122273, "count": 122273, "decode_str": "\u50ee"} -{"id": 5193, "token": "\u0120vill", "merges": "\u0120v ill", "raw_count": 12522, "count": 122291, "decode_str": " vill"} -{"id": 53214, "token": "\u00e7\u00ac\u0140", "merges": "\u00e7\u00ac \u0140", "raw_count": 122311, "count": 122311, "decode_str": "\u7b1e"} -{"id": 41830, "token": "617", "merges": "6 17", "raw_count": 122371, "count": 122371, "decode_str": "617"} -{"id": 16801, "token": "Empty", "merges": "E mpty", "raw_count": 104072, "count": 122372, "decode_str": "Empty"} -{"id": 6789, "token": "\u0120calling", "merges": "\u0120call ing", "raw_count": 122388, "count": 122388, "decode_str": " calling"} -{"id": 2215, "token": "\u0120dise", "merges": "\u0120dis e", "raw_count": 906, "count": 122409, "decode_str": " dise"} -{"id": 1916, "token": "\u0120To", "merges": "\u0120T o", "raw_count": 114613, "count": 122468, "decode_str": " To"} -{"id": 26839, "token": "Tele", "merges": "Te le", "raw_count": 116928, "count": 122515, "decode_str": "Tele"} -{"id": 20679, "token": "=\"\"", "merges": "=\" \"", "raw_count": 122519, "count": 122519, "decode_str": "=\"\""} -{"id": 18293, "token": "ordinate", "merges": "ord inate", "raw_count": 44426, "count": 122549, "decode_str": "ordinate"} -{"id": 36341, "token": "-{", "merges": "- {", "raw_count": 122581, "count": 122581, "decode_str": "-{"} -{"id": 22147, "token": "Password", "merges": "Pass word", "raw_count": 122634, "count": 122634, "decode_str": "Password"} -{"id": 44286, "token": "CONF", "merges": "CON F", "raw_count": 122643, "count": 122643, "decode_str": "CONF"} -{"id": 14780, "token": "ONG", "merges": "ON G", "raw_count": 90553, "count": 122689, "decode_str": "ONG"} -{"id": 10169, "token": "\u0120markets", "merges": "\u0120mark ets", "raw_count": 122726, "count": 122726, "decode_str": " markets"} -{"id": 30697, "token": "CY", "merges": "C Y", "raw_count": 122734, "count": 122734, "decode_str": "CY"} -{"id": 17693, "token": "ifference", "merges": "if ference", "raw_count": 30533, "count": 122745, "decode_str": "ifference"} -{"id": 37950, "token": "751", "merges": "75 1", "raw_count": 122752, "count": 122752, "decode_str": "751"} -{"id": 28221, "token": "qt", "merges": "q t", "raw_count": 122771, "count": 122771, "decode_str": "qt"} -{"id": 4182, "token": "omy", "merges": "om y", "raw_count": 33524, "count": 122807, "decode_str": "omy"} -{"id": 9171, "token": "\u0120scal", "merges": "\u0120sc al", "raw_count": 36257, "count": 122814, "decode_str": " scal"} -{"id": 44322, "token": ",~", "merges": ", ~", "raw_count": 122827, "count": 122827, "decode_str": ",~"} -{"id": 45555, "token": "527", "merges": "5 27", "raw_count": 122846, "count": 122846, "decode_str": "527"} -{"id": 52884, "token": "\u00e7\u0137\u0122", "merges": "\u00e7\u0137 \u0122", "raw_count": 122848, "count": 122848, "decode_str": "\u7540"} -{"id": 17992, "token": "idation", "merges": "id ation", "raw_count": 23546, "count": 122859, "decode_str": "idation"} -{"id": 4344, "token": "\u0120fair", "merges": "\u0120f air", "raw_count": 90268, "count": 122879, "decode_str": " fair"} -{"id": 52932, "token": "\u00e7\u0139\u012f", "merges": "\u00e7\u0139 \u012f", "raw_count": 122906, "count": 122906, "decode_str": "\u75cd"} -{"id": 46796, "token": "\u0120sess", "merges": "\u0120s ess", "raw_count": 122909, "count": 122909, "decode_str": " sess"} -{"id": 45615, "token": "Road", "merges": "R oad", "raw_count": 122923, "count": 122923, "decode_str": "Road"} -{"id": 32006, "token": "472", "merges": "47 2", "raw_count": 122923, "count": 122923, "decode_str": "472"} -{"id": 19907, "token": "Send", "merges": "S end", "raw_count": 122952, "count": 122952, "decode_str": "Send"} -{"id": 32941, "token": "539", "merges": "5 39", "raw_count": 122961, "count": 122961, "decode_str": "539"} -{"id": 6243, "token": "appe", "merges": "ap pe", "raw_count": 49622, "count": 122973, "decode_str": "appe"} -{"id": 15768, "token": "Given", "merges": "G iven", "raw_count": 123025, "count": 123025, "decode_str": "Given"} -{"id": 10157, "token": "itan", "merges": "it an", "raw_count": 104375, "count": 123050, "decode_str": "itan"} -{"id": 29327, "token": "674", "merges": "67 4", "raw_count": 123079, "count": 123079, "decode_str": "674"} -{"id": 11038, "token": "\u0120matching", "merges": "\u0120match ing", "raw_count": 123118, "count": 123118, "decode_str": " matching"} -{"id": 21821, "token": "plicate", "merges": "plic ate", "raw_count": 122934, "count": 123127, "decode_str": "plicate"} -{"id": 54557, "token": "\u00e9\u00a6\u0132", "merges": "\u00e9\u00a6 \u0132", "raw_count": 123158, "count": 123158, "decode_str": "\u9990"} -{"id": 9419, "token": "\u0120prohib", "merges": "\u0120pro hib", "raw_count": 8993, "count": 123184, "decode_str": " prohib"} -{"id": 8336, "token": "\u0120blocks", "merges": "\u0120bl ocks", "raw_count": 123197, "count": 123197, "decode_str": " blocks"} -{"id": 5828, "token": "\u0120vel", "merges": "\u0120v el", "raw_count": 36769, "count": 123219, "decode_str": " vel"} -{"id": 36592, "token": "xia", "merges": "x ia", "raw_count": 123221, "count": 123221, "decode_str": "xia"} -{"id": 12905, "token": "Reference", "merges": "Re ference", "raw_count": 123332, "count": 123332, "decode_str": "Reference"} -{"id": 53154, "token": "\u00e7\u00a7\u00a3", "merges": "\u00e7\u00a7 \u00a3", "raw_count": 123355, "count": 123355, "decode_str": "\u79e3"} -{"id": 52452, "token": "\u00e6\u00b0\u00a1", "merges": "\u00e6\u00b0 \u00a1", "raw_count": 123366, "count": 123366, "decode_str": "\u6c21"} -{"id": 34938, "token": "846", "merges": "84 6", "raw_count": 123369, "count": 123369, "decode_str": "846"} -{"id": 19650, "token": "izontal", "merges": "iz ontal", "raw_count": 313, "count": 123403, "decode_str": "izontal"} -{"id": 33976, "token": "641", "merges": "64 1", "raw_count": 123460, "count": 123460, "decode_str": "641"} -{"id": 32097, "token": "\u0120institute", "merges": "\u0120instit ute", "raw_count": 123512, "count": 123512, "decode_str": " institute"} -{"id": 18377, "token": "\u0120soup", "merges": "\u0120s oup", "raw_count": 123512, "count": 123512, "decode_str": " soup"} -{"id": 28047, "token": "apps", "merges": "app s", "raw_count": 123524, "count": 123524, "decode_str": "apps"} -{"id": 8596, "token": "\u0120aid", "merges": "\u0120a id", "raw_count": 123535, "count": 123535, "decode_str": " aid"} -{"id": 40418, "token": "viv", "merges": "v iv", "raw_count": 123568, "count": 123568, "decode_str": "viv"} -{"id": 30724, "token": "Future", "merges": "F uture", "raw_count": 123634, "count": 123634, "decode_str": "Future"} -{"id": 1457, "token": "\u0120New", "merges": "\u0120N ew", "raw_count": 99461, "count": 123637, "decode_str": " New"} -{"id": 2820, "token": "\u0120trying", "merges": "\u0120try ing", "raw_count": 123663, "count": 123663, "decode_str": " trying"} -{"id": 6136, "token": "isted", "merges": "ist ed", "raw_count": 54113, "count": 123668, "decode_str": "isted"} -{"id": 10070, "token": "\u0120vulner", "merges": "\u0120vul ner", "raw_count": 336, "count": 123689, "decode_str": " vulner"} -{"id": 7503, "token": "\u0120virtual", "merges": "\u0120virt ual", "raw_count": 123720, "count": 123720, "decode_str": " virtual"} -{"id": 35757, "token": "exchange", "merges": "ex change", "raw_count": 123752, "count": 123752, "decode_str": "exchange"} -{"id": 24093, "token": "Journal", "merges": "J ournal", "raw_count": 123773, "count": 123773, "decode_str": "Journal"} -{"id": 10554, "token": "\u0120prediction", "merges": "\u0120pred iction", "raw_count": 123797, "count": 123797, "decode_str": " prediction"} -{"id": 24393, "token": "Begin", "merges": "B egin", "raw_count": 123805, "count": 123805, "decode_str": "Begin"} -{"id": 4176, "token": "\u0120suit", "merges": "\u0120su it", "raw_count": 42957, "count": 123879, "decode_str": " suit"} -{"id": 54025, "token": "\u00e8\u00bd\u0143", "merges": "\u00e8\u00bd \u0143", "raw_count": 123916, "count": 123916, "decode_str": "\u8f6d"} -{"id": 4701, "token": "ruary", "merges": "ru ary", "raw_count": 117071, "count": 123924, "decode_str": "ruary"} -{"id": 9874, "token": "avascript", "merges": "avas cript", "raw_count": 46109, "count": 123936, "decode_str": "avascript"} -{"id": 29067, "token": "\u01205000", "merges": "\u01205 000", "raw_count": 123939, "count": 123939, "decode_str": " 5000"} -{"id": 20043, "token": "verter", "merges": "ver ter", "raw_count": 85856, "count": 123946, "decode_str": "verter"} -{"id": 4210, "token": "hors", "merges": "h ors", "raw_count": 7595, "count": 123973, "decode_str": "hors"} -{"id": 34632, "token": "staff", "merges": "st aff", "raw_count": 124011, "count": 124011, "decode_str": "staff"} -{"id": 25076, "token": "Keys", "merges": "Ke ys", "raw_count": 124023, "count": 124023, "decode_str": "Keys"} -{"id": 17784, "token": "Care", "merges": "C are", "raw_count": 108608, "count": 124085, "decode_str": "Care"} -{"id": 52552, "token": "\u00e6\u00b4\u0126", "merges": "\u00e6\u00b4 \u0126", "raw_count": 124086, "count": 124086, "decode_str": "\u6d04"} -{"id": 16721, "token": "Bytes", "merges": "B ytes", "raw_count": 124096, "count": 124096, "decode_str": "Bytes"} -{"id": 5555, "token": "osing", "merges": "os ing", "raw_count": 47020, "count": 124098, "decode_str": "osing"} -{"id": 3047, "token": "\u0120saw", "merges": "\u0120sa w", "raw_count": 124100, "count": 124100, "decode_str": " saw"} -{"id": 10447, "token": "\u012069", "merges": "\u01206 9", "raw_count": 124105, "count": 124105, "decode_str": " 69"} -{"id": 3261, "token": "\u0120looked", "merges": "\u0120look ed", "raw_count": 124145, "count": 124145, "decode_str": " looked"} -{"id": 12783, "token": "\u0120boxes", "merges": "\u0120box es", "raw_count": 124164, "count": 124164, "decode_str": " boxes"} -{"id": 26928, "token": "dead", "merges": "de ad", "raw_count": 124173, "count": 124173, "decode_str": "dead"} -{"id": 28845, "token": "\u0120commissioner", "merges": "\u0120commission er", "raw_count": 124210, "count": 124210, "decode_str": " commissioner"} -{"id": 34133, "token": "tcp", "merges": "t cp", "raw_count": 124248, "count": 124248, "decode_str": "tcp"} -{"id": 49025, "token": "589", "merges": "5 89", "raw_count": 124265, "count": 124265, "decode_str": "589"} -{"id": 11806, "token": "door", "merges": "d oor", "raw_count": 81921, "count": 124285, "decode_str": "door"} -{"id": 50798, "token": "\u00e5\u012b\u013e", "merges": "\u00e5\u012b \u013e", "raw_count": 124287, "count": 124287, "decode_str": "\u525c"} -{"id": 13816, "token": "hw", "merges": "h w", "raw_count": 124301, "count": 124301, "decode_str": "hw"} -{"id": 53868, "token": "\u00e8\u00b0\u0136", "merges": "\u00e8\u00b0 \u0136", "raw_count": 124312, "count": 124312, "decode_str": "\u8c14"} -{"id": 46027, "token": "554", "merges": "55 4", "raw_count": 124327, "count": 124327, "decode_str": "554"} -{"id": 47059, "token": "626", "merges": "6 26", "raw_count": 124333, "count": 124333, "decode_str": "626"} -{"id": 36602, "token": "DAT", "merges": "D AT", "raw_count": 124337, "count": 124337, "decode_str": "DAT"} -{"id": 26125, "token": "san", "merges": "s an", "raw_count": 124338, "count": 124338, "decode_str": "san"} -{"id": 8782, "token": "liament", "merges": "li ament", "raw_count": 14583, "count": 124342, "decode_str": "liament"} -{"id": 5749, "token": "\u0120\"[", "merges": "\u0120\" [", "raw_count": 124391, "count": 124391, "decode_str": " \"["} -{"id": 27109, "token": "nas", "merges": "n as", "raw_count": 124472, "count": 124472, "decode_str": "nas"} -{"id": 45759, "token": "611", "merges": "6 11", "raw_count": 124474, "count": 124474, "decode_str": "611"} -{"id": 13635, "token": "DER", "merges": "D ER", "raw_count": 95738, "count": 124491, "decode_str": "DER"} -{"id": 11919, "token": "usr", "merges": "us r", "raw_count": 124492, "count": 124492, "decode_str": "usr"} -{"id": 2970, "token": "\u0120getting", "merges": "\u0120get ting", "raw_count": 124510, "count": 124510, "decode_str": " getting"} -{"id": 2837, "token": "\u0120demonstr", "merges": "\u0120demon str", "raw_count": 6945, "count": 124526, "decode_str": " demonstr"} -{"id": 15289, "token": "OUND", "merges": "OU ND", "raw_count": 106355, "count": 124552, "decode_str": "OUND"} -{"id": 7890, "token": "\u0120Use", "merges": "\u0120U se", "raw_count": 124564, "count": 124564, "decode_str": " Use"} -{"id": 22906, "token": "\u0120refresh", "merges": "\u0120ref resh", "raw_count": 124591, "count": 124591, "decode_str": " refresh"} -{"id": 48204, "token": "665", "merges": "6 65", "raw_count": 124619, "count": 124619, "decode_str": "665"} -{"id": 26158, "token": "temperature", "merges": "tem perature", "raw_count": 124622, "count": 124622, "decode_str": "temperature"} -{"id": 12966, "token": "\u0120cub", "merges": "\u0120c ub", "raw_count": 105346, "count": 124653, "decode_str": " cub"} -{"id": 10441, "token": "uj", "merges": "u j", "raw_count": 120711, "count": 124664, "decode_str": "uj"} -{"id": 24177, "token": "\u00e2\u0138\u012a", "merges": "\u00e2\u0138 \u012a", "raw_count": 18690, "count": 124690, "decode_str": "\u2588"} -{"id": 20294, "token": "Commun", "merges": "Com mun", "raw_count": 90852, "count": 124730, "decode_str": "Commun"} -{"id": 22259, "token": "virtual", "merges": "v irtual", "raw_count": 124733, "count": 124733, "decode_str": "virtual"} -{"id": 36042, "token": "requires", "merges": "requ ires", "raw_count": 124734, "count": 124734, "decode_str": "requires"} -{"id": 34063, "token": "0023", "merges": "00 23", "raw_count": 124753, "count": 124753, "decode_str": "0023"} -{"id": 1876, "token": "\u0120All", "merges": "\u0120A ll", "raw_count": 101377, "count": 124773, "decode_str": " All"} -{"id": 6489, "token": "\u0120identity", "merges": "\u0120ident ity", "raw_count": 124782, "count": 124782, "decode_str": " identity"} -{"id": 19013, "token": "Coll", "merges": "C oll", "raw_count": 93565, "count": 124788, "decode_str": "Coll"} -{"id": 3108, "token": "\u0120influ", "merges": "\u0120infl u", "raw_count": 2461, "count": 124813, "decode_str": " influ"} -{"id": 5060, "token": "enses", "merges": "ens es", "raw_count": 33268, "count": 124822, "decode_str": "enses"} -{"id": 2761, "token": "\u0120almost", "merges": "\u0120al most", "raw_count": 124823, "count": 124823, "decode_str": " almost"} -{"id": 44105, "token": "receive", "merges": "re ceive", "raw_count": 124835, "count": 124835, "decode_str": "receive"} -{"id": 11164, "token": "ARY", "merges": "AR Y", "raw_count": 81015, "count": 124836, "decode_str": "ARY"} -{"id": 23074, "token": "Proxy", "merges": "Pro xy", "raw_count": 124838, "count": 124838, "decode_str": "Proxy"} -{"id": 12463, "token": "estyle", "merges": "est yle", "raw_count": 112816, "count": 124847, "decode_str": "estyle"} -{"id": 25078, "token": "pointer", "merges": "po inter", "raw_count": 124849, "count": 124849, "decode_str": "pointer"} -{"id": 46956, "token": "ISP", "merges": "IS P", "raw_count": 124858, "count": 124858, "decode_str": "ISP"} -{"id": 48926, "token": "cash", "merges": "c ash", "raw_count": 124890, "count": 124890, "decode_str": "cash"} -{"id": 5196, "token": "\u0120conducted", "merges": "\u0120conduct ed", "raw_count": 124921, "count": 124921, "decode_str": " conducted"} -{"id": 25736, "token": "national", "merges": "n ational", "raw_count": 124933, "count": 124933, "decode_str": "national"} -{"id": 31477, "token": "exist", "merges": "ex ist", "raw_count": 124963, "count": 124963, "decode_str": "exist"} -{"id": 19154, "token": "Quant", "merges": "Qu ant", "raw_count": 40316, "count": 124968, "decode_str": "Quant"} -{"id": 11149, "token": "\u0120Point", "merges": "\u0120P oint", "raw_count": 113907, "count": 124995, "decode_str": " Point"} -{"id": 30731, "token": "Emb", "merges": "E mb", "raw_count": 31429, "count": 125000, "decode_str": "Emb"} -{"id": 35461, "token": "959", "merges": "95 9", "raw_count": 125001, "count": 125001, "decode_str": "959"} -{"id": 4618, "token": "\u0120wide", "merges": "\u0120w ide", "raw_count": 125032, "count": 125032, "decode_str": " wide"} -{"id": 26764, "token": "0101", "merges": "01 01", "raw_count": 125035, "count": 125035, "decode_str": "0101"} -{"id": 30358, "token": "\u0120decode", "merges": "\u0120dec ode", "raw_count": 125093, "count": 125093, "decode_str": " decode"} -{"id": 12954, "token": "\u0120worker", "merges": "\u0120work er", "raw_count": 125110, "count": 125110, "decode_str": " worker"} -{"id": 42734, "token": "Pix", "merges": "P ix", "raw_count": 125113, "count": 125113, "decode_str": "Pix"} -{"id": 7375, "token": "\u0120jobs", "merges": "\u0120job s", "raw_count": 125152, "count": 125152, "decode_str": " jobs"} -{"id": 31254, "token": "754", "merges": "75 4", "raw_count": 125172, "count": 125172, "decode_str": "754"} -{"id": 27754, "token": "\u0120cpu", "merges": "\u0120c pu", "raw_count": 125174, "count": 125174, "decode_str": " cpu"} -{"id": 11716, "token": "\u0120provider", "merges": "\u0120prov ider", "raw_count": 125195, "count": 125195, "decode_str": " provider"} -{"id": 9008, "token": "\u0120preparation", "merges": "\u0120prepar ation", "raw_count": 125203, "count": 125203, "decode_str": " preparation"} -{"id": 5493, "token": "ston", "merges": "st on", "raw_count": 97121, "count": 125221, "decode_str": "ston"} -{"id": 6664, "token": "orthern", "merges": "ort hern", "raw_count": 4197, "count": 125227, "decode_str": "orthern"} -{"id": 20749, "token": "catal", "merges": "c atal", "raw_count": 22663, "count": 125293, "decode_str": "catal"} -{"id": 7895, "token": "\u0120secure", "merges": "\u0120sec ure", "raw_count": 101917, "count": 125296, "decode_str": " secure"} -{"id": 16768, "token": "UES", "merges": "U ES", "raw_count": 53452, "count": 125316, "decode_str": "UES"} -{"id": 40416, "token": "1101", "merges": "11 01", "raw_count": 125320, "count": 125320, "decode_str": "1101"} -{"id": 40280, "token": "\u0120expr", "merges": "\u0120exp r", "raw_count": 125329, "count": 125329, "decode_str": " expr"} -{"id": 27207, "token": "dash", "merges": "d ash", "raw_count": 125346, "count": 125346, "decode_str": "dash"} -{"id": 36630, "token": "661", "merges": "66 1", "raw_count": 125350, "count": 125350, "decode_str": "661"} -{"id": 29764, "token": "Pet", "merges": "P et", "raw_count": 125364, "count": 125364, "decode_str": "Pet"} -{"id": 32473, "token": "Food", "merges": "F ood", "raw_count": 125368, "count": 125368, "decode_str": "Food"} -{"id": 31327, "token": "resolve", "merges": "res olve", "raw_count": 125394, "count": 125394, "decode_str": "resolve"} -{"id": 10633, "token": "nie", "merges": "n ie", "raw_count": 125333, "count": 125421, "decode_str": "nie"} -{"id": 23821, "token": "apon", "merges": "ap on", "raw_count": 125468, "count": 125468, "decode_str": "apon"} -{"id": 23088, "token": "Basic", "merges": "Bas ic", "raw_count": 125506, "count": 125506, "decode_str": "Basic"} -{"id": 23513, "token": "Perm", "merges": "P erm", "raw_count": 73047, "count": 125512, "decode_str": "Perm"} -{"id": 22963, "token": "SIG", "merges": "S IG", "raw_count": 125531, "count": 125531, "decode_str": "SIG"} -{"id": 9050, "token": "\u0120categories", "merges": "\u0120categ ories", "raw_count": 125553, "count": 125553, "decode_str": " categories"} -{"id": 31061, "token": "Wang", "merges": "W ang", "raw_count": 125591, "count": 125591, "decode_str": "Wang"} -{"id": 37473, "token": "capacity", "merges": "cap acity", "raw_count": 125593, "count": 125593, "decode_str": "capacity"} -{"id": 21948, "token": "\u0120summit", "merges": "\u0120sum mit", "raw_count": 125597, "count": 125597, "decode_str": " summit"} -{"id": 8765, "token": "aks", "merges": "ak s", "raw_count": 120984, "count": 125606, "decode_str": "aks"} -{"id": 21428, "token": "dog", "merges": "d og", "raw_count": 125622, "count": 125622, "decode_str": "dog"} -{"id": 42992, "token": "Street", "merges": "St reet", "raw_count": 125627, "count": 125627, "decode_str": "Street"} -{"id": 24234, "token": "Far", "merges": "F ar", "raw_count": 125630, "count": 125630, "decode_str": "Far"} -{"id": 9594, "token": "ibilities", "merges": "ib ilities", "raw_count": 17657, "count": 125663, "decode_str": "ibilities"} -{"id": 53645, "token": "\u00e8\u012d\u0137", "merges": "\u00e8\u012d \u0137", "raw_count": 125671, "count": 125671, "decode_str": "\u82d5"} -{"id": 31356, "token": "ymbols", "merges": "ymb ols", "raw_count": 125695, "count": 125695, "decode_str": "ymbols"} -{"id": 29099, "token": "Ren", "merges": "R en", "raw_count": 125726, "count": 125726, "decode_str": "Ren"} -{"id": 32971, "token": "demo", "merges": "dem o", "raw_count": 125729, "count": 125729, "decode_str": "demo"} -{"id": 17547, "token": "Operation", "merges": "Oper ation", "raw_count": 125791, "count": 125791, "decode_str": "Operation"} -{"id": 42039, "token": "Yu", "merges": "Y u", "raw_count": 125805, "count": 125805, "decode_str": "Yu"} -{"id": 8329, "token": "umer", "merges": "um er", "raw_count": 36595, "count": 125806, "decode_str": "umer"} -{"id": 29011, "token": "Accept", "merges": "Ac cept", "raw_count": 125822, "count": 125822, "decode_str": "Accept"} -{"id": 7594, "token": "never", "merges": "ne ver", "raw_count": 88008, "count": 125836, "decode_str": "never"} -{"id": 24167, "token": "|_", "merges": "| _", "raw_count": 125881, "count": 125881, "decode_str": "|_"} -{"id": 9637, "token": "ventions", "merges": "vent ions", "raw_count": 14536, "count": 125887, "decode_str": "ventions"} -{"id": 6383, "token": "\u0120customers", "merges": "\u0120custom ers", "raw_count": 125890, "count": 125890, "decode_str": " customers"} -{"id": 4352, "token": "\u0120hit", "merges": "\u0120h it", "raw_count": 125938, "count": 125938, "decode_str": " hit"} -{"id": 17166, "token": "spot", "merges": "sp ot", "raw_count": 114677, "count": 125944, "decode_str": "spot"} -{"id": 31644, "token": "adapter", "merges": "ad apter", "raw_count": 125954, "count": 125954, "decode_str": "adapter"} -{"id": 6252, "token": "\u0120teac", "merges": "\u0120te ac", "raw_count": 461, "count": 125960, "decode_str": " teac"} -{"id": 8621, "token": "hab", "merges": "h ab", "raw_count": 94116, "count": 125964, "decode_str": "hab"} -{"id": 1874, "token": "();", "merges": "( );", "raw_count": 125747, "count": 126005, "decode_str": "();"} -{"id": 38705, "token": "snap", "merges": "sn ap", "raw_count": 126049, "count": 126049, "decode_str": "snap"} -{"id": 3759, "token": "\u0120Sim", "merges": "\u0120S im", "raw_count": 49384, "count": 126111, "decode_str": " Sim"} -{"id": 11287, "token": "\u0120temporary", "merges": "\u0120tempor ary", "raw_count": 126119, "count": 126119, "decode_str": " temporary"} -{"id": 8269, "token": "\u0120legisl", "merges": "\u0120legis l", "raw_count": 8866, "count": 126126, "decode_str": " legisl"} -{"id": 10318, "token": "\u0120Text", "merges": "\u0120T ext", "raw_count": 126163, "count": 126163, "decode_str": " Text"} -{"id": 7603, "token": "aven", "merges": "av en", "raw_count": 99345, "count": 126180, "decode_str": "aven"} -{"id": 16651, "token": "focus", "merges": "f ocus", "raw_count": 109799, "count": 126182, "decode_str": "focus"} -{"id": 10599, "token": "\u0120adequate", "merges": "\u0120adequ ate", "raw_count": 126199, "count": 126199, "decode_str": " adequate"} -{"id": 36561, "token": "\"/", "merges": "\" /", "raw_count": 126199, "count": 126199, "decode_str": "\"/"} -{"id": 44060, "token": "586", "merges": "5 86", "raw_count": 126243, "count": 126243, "decode_str": "586"} -{"id": 52121, "token": "\u00e6\u0139\u00ae", "merges": "\u00e6\u0139 \u00ae", "raw_count": 126270, "count": 126270, "decode_str": "\u65ee"} -{"id": 17001, "token": "mir", "merges": "m ir", "raw_count": 126214, "count": 126284, "decode_str": "mir"} -{"id": 3286, "token": "\u0120district", "merges": "\u0120dist rict", "raw_count": 104712, "count": 126332, "decode_str": " district"} -{"id": 8191, "token": "\u0120informed", "merges": "\u0120inform ed", "raw_count": 126334, "count": 126334, "decode_str": " informed"} -{"id": 31783, "token": "diag", "merges": "di ag", "raw_count": 126340, "count": 126340, "decode_str": "diag"} -{"id": 36116, "token": "maximum", "merges": "max imum", "raw_count": 126353, "count": 126353, "decode_str": "maximum"} -{"id": 8165, "token": "ollowing", "merges": "ollow ing", "raw_count": 820, "count": 126391, "decode_str": "ollowing"} -{"id": 8807, "token": "ila", "merges": "il a", "raw_count": 124581, "count": 126425, "decode_str": "ila"} -{"id": 6264, "token": "\u0120commercial", "merges": "\u0120commerc ial", "raw_count": 125031, "count": 126443, "decode_str": " commercial"} -{"id": 34974, "token": "questions", "merges": "quest ions", "raw_count": 126450, "count": 126450, "decode_str": "questions"} -{"id": 9525, "token": "ruption", "merges": "ru ption", "raw_count": 29173, "count": 126451, "decode_str": "ruption"} -{"id": 52101, "token": "\u00e6\u0138\u00ab", "merges": "\u00e6\u0138 \u00ab", "raw_count": 126466, "count": 126466, "decode_str": "\u65ab"} -{"id": 11028, "token": "iry", "merges": "ir y", "raw_count": 90367, "count": 126537, "decode_str": "iry"} -{"id": 10636, "token": "\u0120execution", "merges": "\u0120exec ution", "raw_count": 126588, "count": 126588, "decode_str": " execution"} -{"id": 52188, "token": "\u00e6\u013e\u0132", "merges": "\u00e6\u013e \u0132", "raw_count": 126591, "count": 126591, "decode_str": "\u6710"} -{"id": 8036, "token": "bling", "merges": "bl ing", "raw_count": 103821, "count": 126599, "decode_str": "bling"} -{"id": 31408, "token": "473", "merges": "47 3", "raw_count": 126613, "count": 126613, "decode_str": "473"} -{"id": 21595, "token": "Simple", "merges": "Sim ple", "raw_count": 126620, "count": 126620, "decode_str": "Simple"} -{"id": 6707, "token": "\u0120Read", "merges": "\u0120R ead", "raw_count": 100799, "count": 126626, "decode_str": " Read"} -{"id": 12844, "token": "acher", "merges": "ac her", "raw_count": 117639, "count": 126629, "decode_str": "acher"} -{"id": 35360, "token": "distribution", "merges": "dist ribution", "raw_count": 126643, "count": 126643, "decode_str": "distribution"} -{"id": 19635, "token": "0007", "merges": "000 7", "raw_count": 126655, "count": 126655, "decode_str": "0007"} -{"id": 3395, "token": "\u0120became", "merges": "\u0120bec ame", "raw_count": 126686, "count": 126686, "decode_str": " became"} -{"id": 39258, "token": "\"[", "merges": "\" [", "raw_count": 126702, "count": 126702, "decode_str": "\"["} -{"id": 5754, "token": "\u0120prison", "merges": "\u0120pr ison", "raw_count": 72827, "count": 126734, "decode_str": " prison"} -{"id": 4853, "token": "\u0120define", "merges": "\u0120def ine", "raw_count": 126767, "count": 126767, "decode_str": " define"} -{"id": 9744, "token": "NU", "merges": "N U", "raw_count": 94653, "count": 126768, "decode_str": "NU"} -{"id": 42942, "token": "notification", "merges": "not ification", "raw_count": 126799, "count": 126799, "decode_str": "notification"} -{"id": 16669, "token": "\u0120arrangements", "merges": "\u0120arrang ements", "raw_count": 126805, "count": 126805, "decode_str": " arrangements"} -{"id": 7338, "token": "sect", "merges": "se ct", "raw_count": 73786, "count": 126825, "decode_str": "sect"} -{"id": 34766, "token": "Talk", "merges": "T alk", "raw_count": 126825, "count": 126825, "decode_str": "Talk"} -{"id": 3916, "token": "\u0120claims", "merges": "\u0120claim s", "raw_count": 126871, "count": 126871, "decode_str": " claims"} -{"id": 10247, "token": "positive", "merges": "pos itive", "raw_count": 126887, "count": 126887, "decode_str": "positive"} -{"id": 10981, "token": "stra", "merges": "st ra", "raw_count": 117842, "count": 126897, "decode_str": "stra"} -{"id": 8162, "token": "\u0120contribute", "merges": "\u0120cont ribute", "raw_count": 126903, "count": 126903, "decode_str": " contribute"} -{"id": 22205, "token": "\u0120bucket", "merges": "\u0120buck et", "raw_count": 126923, "count": 126923, "decode_str": " bucket"} -{"id": 49904, "token": "Train", "merges": "T rain", "raw_count": 126970, "count": 126970, "decode_str": "Train"} -{"id": 10574, "token": "formed", "merges": "form ed", "raw_count": 62582, "count": 126974, "decode_str": "formed"} -{"id": 32065, "token": "mmol", "merges": "mm ol", "raw_count": 127002, "count": 127002, "decode_str": "mmol"} -{"id": 37541, "token": "Stephen", "merges": "Ste phen", "raw_count": 127034, "count": 127034, "decode_str": "Stephen"} -{"id": 5312, "token": "\u0120daily", "merges": "\u0120d aily", "raw_count": 127042, "count": 127042, "decode_str": " daily"} -{"id": 44985, "token": "522", "merges": "5 22", "raw_count": 127047, "count": 127047, "decode_str": "522"} -{"id": 54573, "token": "\u00e8\u00bd\u00b1", "merges": "\u00e8\u00bd \u00b1", "raw_count": 127087, "count": 127087, "decode_str": "\u8f71"} -{"id": 28605, "token": "HY", "merges": "H Y", "raw_count": 127087, "count": 127087, "decode_str": "HY"} -{"id": 20480, "token": "Scal", "merges": "S cal", "raw_count": 93954, "count": 127089, "decode_str": "Scal"} -{"id": 33847, "token": "662", "merges": "66 2", "raw_count": 127090, "count": 127090, "decode_str": "662"} -{"id": 41909, "token": "Cannot", "merges": "C annot", "raw_count": 127091, "count": 127091, "decode_str": "Cannot"} -{"id": 39988, "token": "Arguments", "merges": "Arg uments", "raw_count": 127119, "count": 127119, "decode_str": "Arguments"} -{"id": 8220, "token": "??", "merges": "? ?", "raw_count": 83973, "count": 127134, "decode_str": "??"} -{"id": 13736, "token": "Offset", "merges": "Off set", "raw_count": 127148, "count": 127148, "decode_str": "Offset"} -{"id": 4847, "token": "\u0120absol", "merges": "\u0120abs ol", "raw_count": 4701, "count": 127167, "decode_str": " absol"} -{"id": 37058, "token": "WIND", "merges": "W IND", "raw_count": 127172, "count": 127172, "decode_str": "WIND"} -{"id": 8263, "token": "uled", "merges": "ul ed", "raw_count": 64953, "count": 127191, "decode_str": "uled"} -{"id": 37282, "token": "\u0120timed", "merges": "\u0120tim ed", "raw_count": 127202, "count": 127202, "decode_str": " timed"} -{"id": 8938, "token": "foot", "merges": "f oot", "raw_count": 69477, "count": 127238, "decode_str": "foot"} -{"id": 22842, "token": "relations", "merges": "rel ations", "raw_count": 80889, "count": 127242, "decode_str": "relations"} -{"id": 35337, "token": "493", "merges": "49 3", "raw_count": 127261, "count": 127261, "decode_str": "493"} -{"id": 32067, "token": "mf", "merges": "m f", "raw_count": 127269, "count": 127269, "decode_str": "mf"} -{"id": 23335, "token": "BASE", "merges": "B ASE", "raw_count": 127298, "count": 127298, "decode_str": "BASE"} -{"id": 15231, "token": "\u0120asset", "merges": "\u0120ass et", "raw_count": 127351, "count": 127351, "decode_str": " asset"} -{"id": 2779, "token": "\u0120likely", "merges": "\u0120lik ely", "raw_count": 127359, "count": 127359, "decode_str": " likely"} -{"id": 7878, "token": "American", "merges": "Americ an", "raw_count": 127368, "count": 127368, "decode_str": "American"} -{"id": 11757, "token": "\u0120combat", "merges": "\u0120comb at", "raw_count": 127391, "count": 127391, "decode_str": " combat"} -{"id": 30626, "token": "497", "merges": "49 7", "raw_count": 127401, "count": 127401, "decode_str": "497"} -{"id": 31332, "token": "verts", "merges": "ver ts", "raw_count": 127413, "count": 127413, "decode_str": "verts"} -{"id": 47650, "token": "TES", "merges": "T ES", "raw_count": 127435, "count": 127435, "decode_str": "TES"} -{"id": 12769, "token": "irth", "merges": "ir th", "raw_count": 35928, "count": 127455, "decode_str": "irth"} -{"id": 8756, "token": "\u0120recon", "merges": "\u0120re con", "raw_count": 32682, "count": 127486, "decode_str": " recon"} -{"id": 4795, "token": "\u0120resulting", "merges": "\u0120result ing", "raw_count": 127493, "count": 127493, "decode_str": " resulting"} -{"id": 34383, "token": "vectors", "merges": "ve ctors", "raw_count": 120416, "count": 127539, "decode_str": "vectors"} -{"id": 28935, "token": "peer", "merges": "pe er", "raw_count": 127542, "count": 127542, "decode_str": "peer"} -{"id": 52904, "token": "\u00e7\u0138\u0138", "merges": "\u00e7\u0138 \u0138", "raw_count": 127596, "count": 127596, "decode_str": "\u7596"} -{"id": 10511, "token": "athan", "merges": "ath an", "raw_count": 59969, "count": 127702, "decode_str": "athan"} -{"id": 32590, "token": "pag", "merges": "p ag", "raw_count": 127711, "count": 127711, "decode_str": "pag"} -{"id": 2927, "token": "\u0120eyes", "merges": "\u0120ey es", "raw_count": 127718, "count": 127718, "decode_str": " eyes"} -{"id": 52130, "token": "\u00e6\u013a\u012b", "merges": "\u00e6\u013a \u012b", "raw_count": 127776, "count": 127776, "decode_str": "\u6609"} -{"id": 45660, "token": "\u0120millennium", "merges": "\u0120millenn ium", "raw_count": 127809, "count": 127809, "decode_str": " millennium"} -{"id": 12038, "token": "Builder", "merges": "Bu ilder", "raw_count": 127214, "count": 127828, "decode_str": "Builder"} -{"id": 17031, "token": "Mask", "merges": "M ask", "raw_count": 127868, "count": 127868, "decode_str": "Mask"} -{"id": 31666, "token": "Feed", "merges": "Fe ed", "raw_count": 127880, "count": 127880, "decode_str": "Feed"} -{"id": 50770, "token": "\u00e5\u012a\u0130", "merges": "\u00e5\u012a \u0130", "raw_count": 127886, "count": 127886, "decode_str": "\u520e"} -{"id": 15933, "token": ",\u00e2\u0122\u013b", "merges": ", \u00e2\u0122\u013b", "raw_count": 127956, "count": 127956, "decode_str": ",\u2019"} -{"id": 9340, "token": "Results", "merges": "Res ults", "raw_count": 127971, "count": 127971, "decode_str": "Results"} -{"id": 7337, "token": "oster", "merges": "ost er", "raw_count": 85569, "count": 127978, "decode_str": "oster"} -{"id": 41325, "token": "881", "merges": "88 1", "raw_count": 128010, "count": 128010, "decode_str": "881"} -{"id": 17014, "token": "addle", "merges": "add le", "raw_count": 72999, "count": 128034, "decode_str": "addle"} -{"id": 6735, "token": "\u0120debt", "merges": "\u0120de bt", "raw_count": 111324, "count": 128046, "decode_str": " debt"} -{"id": 16467, "token": "Integer", "merges": "Inte ger", "raw_count": 128067, "count": 128067, "decode_str": "Integer"} -{"id": 9810, "token": "\u0120tort", "merges": "\u0120t ort", "raw_count": 9782, "count": 128072, "decode_str": " tort"} -{"id": 21667, "token": "OTO", "merges": "OT O", "raw_count": 116336, "count": 128094, "decode_str": "OTO"} -{"id": 31510, "token": "docker", "merges": "d ocker", "raw_count": 128095, "count": 128095, "decode_str": "docker"} -{"id": 51165, "token": "\u00e5\u013d\u00ab", "merges": "\u00e5\u013d \u00ab", "raw_count": 128152, "count": 128152, "decode_str": "\u56eb"} -{"id": 17828, "token": "iterator", "merges": "iter ator", "raw_count": 128161, "count": 128161, "decode_str": "iterator"} -{"id": 47503, "token": "CAS", "merges": "C AS", "raw_count": 128168, "count": 128168, "decode_str": "CAS"} -{"id": 7183, "token": "\u00e1\u0122", "merges": "\u00e1 \u0122", "raw_count": 88926, "count": 128169, "decode_str": "\ufffd"} -{"id": 22610, "token": "@@", "merges": "@ @", "raw_count": 128172, "count": 128172, "decode_str": "@@"} -{"id": 17457, "token": "oda", "merges": "od a", "raw_count": 128203, "count": 128203, "decode_str": "oda"} -{"id": 25695, "token": "HM", "merges": "H M", "raw_count": 128239, "count": 128239, "decode_str": "HM"} -{"id": 5899, "token": "\u0120traditional", "merges": "\u0120tradition al", "raw_count": 128240, "count": 128240, "decode_str": " traditional"} -{"id": 9363, "token": "\u0120maintenance", "merges": "\u0120maint enance", "raw_count": 128285, "count": 128285, "decode_str": " maintenance"} -{"id": 11769, "token": "sto", "merges": "st o", "raw_count": 127824, "count": 128286, "decode_str": "sto"} -{"id": 10651, "token": "\u0120icon", "merges": "\u0120 icon", "raw_count": 126696, "count": 128320, "decode_str": " icon"} -{"id": 15258, "token": "ORY", "merges": "OR Y", "raw_count": 128244, "count": 128321, "decode_str": "ORY"} -{"id": 25209, "token": "pipe", "merges": "pi pe", "raw_count": 128337, "count": 128337, "decode_str": "pipe"} -{"id": 15611, "token": "Great", "merges": "G reat", "raw_count": 128349, "count": 128349, "decode_str": "Great"} -{"id": 4394, "token": "\u0120ones", "merges": "\u0120on es", "raw_count": 121388, "count": 128421, "decode_str": " ones"} -{"id": 9707, "token": "THE", "merges": "T HE", "raw_count": 128435, "count": 128435, "decode_str": "THE"} -{"id": 39639, "token": "aaa", "merges": "aa a", "raw_count": 128445, "count": 128445, "decode_str": "aaa"} -{"id": 12252, "token": "\u0120reply", "merges": "\u0120rep ly", "raw_count": 128471, "count": 128471, "decode_str": " reply"} -{"id": 30925, "token": "KL", "merges": "K L", "raw_count": 128479, "count": 128479, "decode_str": "KL"} -{"id": 45270, "token": "pv", "merges": "p v", "raw_count": 128513, "count": 128513, "decode_str": "pv"} -{"id": 34830, "token": "Louis", "merges": "Lou is", "raw_count": 128516, "count": 128516, "decode_str": "Louis"} -{"id": 50570, "token": "\u00e4\u00bd\u00b6", "merges": "\u00e4\u00bd \u00b6", "raw_count": 128581, "count": 128581, "decode_str": "\u4f76"} -{"id": 3860, "token": "\u0120href", "merges": "\u0120h ref", "raw_count": 128607, "count": 128607, "decode_str": " href"} -{"id": 10629, "token": "sch", "merges": "s ch", "raw_count": 127643, "count": 128611, "decode_str": "sch"} -{"id": 8145, "token": "!--", "merges": "! --", "raw_count": 113632, "count": 128618, "decode_str": "!--"} -{"id": 22070, "token": "ceiver", "merges": "ce iver", "raw_count": 112427, "count": 128632, "decode_str": "ceiver"} -{"id": 4544, "token": "\u0120campaign", "merges": "\u0120camp aign", "raw_count": 87847, "count": 128686, "decode_str": " campaign"} -{"id": 27169, "token": "terms", "merges": "ter ms", "raw_count": 128747, "count": 128747, "decode_str": "terms"} -{"id": 24330, "token": "major", "merges": "ma jor", "raw_count": 128749, "count": 128749, "decode_str": "major"} -{"id": 20857, "token": "gene", "merges": "gen e", "raw_count": 128697, "count": 128761, "decode_str": "gene"} -{"id": 36665, "token": "idea", "merges": "ide a", "raw_count": 128766, "count": 128766, "decode_str": "idea"} -{"id": 21749, "token": "Elect", "merges": "E lect", "raw_count": 83220, "count": 128793, "decode_str": "Elect"} -{"id": 12978, "token": "Will", "merges": "W ill", "raw_count": 128794, "count": 128794, "decode_str": "Will"} -{"id": 12608, "token": "ghan", "merges": "g han", "raw_count": 128619, "count": 128821, "decode_str": "ghan"} -{"id": 11322, "token": "\u0120resolve", "merges": "\u0120res olve", "raw_count": 128843, "count": 128843, "decode_str": " resolve"} -{"id": 48480, "token": ",+", "merges": ", +", "raw_count": 128878, "count": 128878, "decode_str": ",+"} -{"id": 24095, "token": "Hol", "merges": "H ol", "raw_count": 128914, "count": 128914, "decode_str": "Hol"} -{"id": 40219, "token": ".',", "merges": ". ',", "raw_count": 128923, "count": 128923, "decode_str": ".',"} -{"id": 4797, "token": "\u0120blue", "merges": "\u0120bl ue", "raw_count": 128960, "count": 128960, "decode_str": " blue"} -{"id": 9743, "token": "\u012062", "merges": "\u01206 2", "raw_count": 128993, "count": 128993, "decode_str": " 62"} -{"id": 6231, "token": "iant", "merges": "i ant", "raw_count": 96941, "count": 129014, "decode_str": "iant"} -{"id": 49758, "token": "628", "merges": "6 28", "raw_count": 129020, "count": 129020, "decode_str": "628"} -{"id": 35340, "token": "482", "merges": "48 2", "raw_count": 129038, "count": 129038, "decode_str": "482"} -{"id": 14496, "token": "\u0120snap", "merges": "\u0120sn ap", "raw_count": 45244, "count": 129043, "decode_str": " snap"} -{"id": 2604, "token": "\u0120Pr", "merges": "\u0120P r", "raw_count": 21013, "count": 129049, "decode_str": " Pr"} -{"id": 14014, "token": "interest", "merges": "in terest", "raw_count": 107467, "count": 129052, "decode_str": "interest"} -{"id": 3663, "token": "\u0120lost", "merges": "\u0120l ost", "raw_count": 129071, "count": 129071, "decode_str": " lost"} -{"id": 6563, "token": "\u0120nav", "merges": "\u0120n av", "raw_count": 31083, "count": 129081, "decode_str": " nav"} -{"id": 6868, "token": "\u0120sin", "merges": "\u0120s in", "raw_count": 123140, "count": 129099, "decode_str": " sin"} -{"id": 31638, "token": "album", "merges": "al bum", "raw_count": 129103, "count": 129103, "decode_str": "album"} -{"id": 27277, "token": "\u01201024", "merges": "\u012010 24", "raw_count": 129108, "count": 129108, "decode_str": " 1024"} -{"id": 4632, "token": "\u0120vs", "merges": "\u0120v s", "raw_count": 129154, "count": 129154, "decode_str": " vs"} -{"id": 6121, "token": "burg", "merges": "b urg", "raw_count": 89625, "count": 129160, "decode_str": "burg"} -{"id": 44164, "token": "zoom", "merges": "z oom", "raw_count": 129178, "count": 129178, "decode_str": "zoom"} -{"id": 8879, "token": "aze", "merges": "az e", "raw_count": 95971, "count": 129183, "decode_str": "aze"} -{"id": 51935, "token": "\u00e6\u012e\u012a", "merges": "\u00e6\u012e \u012a", "raw_count": 129183, "count": 129183, "decode_str": "\u6308"} -{"id": 10898, "token": "\u0120universal", "merges": "\u0120univers al", "raw_count": 129199, "count": 129199, "decode_str": " universal"} -{"id": 2433, "token": "osis", "merges": "os is", "raw_count": 77328, "count": 129205, "decode_str": "osis"} -{"id": 19546, "token": "LF", "merges": "L F", "raw_count": 129229, "count": 129229, "decode_str": "LF"} -{"id": 11938, "token": "aki", "merges": "ak i", "raw_count": 113967, "count": 129280, "decode_str": "aki"} -{"id": 32302, "token": "SG", "merges": "S G", "raw_count": 129298, "count": 129298, "decode_str": "SG"} -{"id": 22089, "token": "heads", "merges": "head s", "raw_count": 129333, "count": 129333, "decode_str": "heads"} -{"id": 17749, "token": "\u0120ensuring", "merges": "\u0120ens uring", "raw_count": 129337, "count": 129337, "decode_str": " ensuring"} -{"id": 4407, "token": "\u0120\u00d0\u00b2", "merges": "\u0120\u00d0 \u00b2", "raw_count": 98766, "count": 129429, "decode_str": " \u0432"} -{"id": 12301, "token": "formance", "merges": "form ance", "raw_count": 7663, "count": 129467, "decode_str": "formance"} -{"id": 4858, "token": "\u0120separate", "merges": "\u0120separ ate", "raw_count": 129470, "count": 129470, "decode_str": " separate"} -{"id": 5462, "token": "sey", "merges": "se y", "raw_count": 118314, "count": 129486, "decode_str": "sey"} -{"id": 31591, "token": "bench", "merges": "ben ch", "raw_count": 129528, "count": 129528, "decode_str": "bench"} -{"id": 7290, "token": "venue", "merges": "ven ue", "raw_count": 74618, "count": 129538, "decode_str": "venue"} -{"id": 16886, "token": "isse", "merges": "is se", "raw_count": 129592, "count": 129592, "decode_str": "isse"} -{"id": 42164, "token": "565", "merges": "5 65", "raw_count": 129599, "count": 129599, "decode_str": "565"} -{"id": 33451, "token": "Almost", "merges": "Al most", "raw_count": 129618, "count": 129618, "decode_str": "Almost"} -{"id": 33356, "token": "curve", "merges": "cur ve", "raw_count": 129666, "count": 129666, "decode_str": "curve"} -{"id": 18800, "token": "DEF", "merges": "DE F", "raw_count": 78308, "count": 129670, "decode_str": "DEF"} -{"id": 41227, "token": "551", "merges": "55 1", "raw_count": 129678, "count": 129678, "decode_str": "551"} -{"id": 9999, "token": "\u0120representing", "merges": "\u0120represent ing", "raw_count": 129692, "count": 129692, "decode_str": " representing"} -{"id": 40838, "token": "SEE", "merges": "SE E", "raw_count": 129702, "count": 129702, "decode_str": "SEE"} -{"id": 33023, "token": "LETE", "merges": "LE TE", "raw_count": 17775, "count": 129713, "decode_str": "LETE"} -{"id": 44991, "token": "locations", "merges": "loc ations", "raw_count": 129854, "count": 129854, "decode_str": "locations"} -{"id": 6583, "token": "\u0120confirm", "merges": "\u0120conf irm", "raw_count": 71461, "count": 129857, "decode_str": " confirm"} -{"id": 16364, "token": "criptor", "merges": "cript or", "raw_count": 4828, "count": 129886, "decode_str": "criptor"} -{"id": 18105, "token": "fre", "merges": "f re", "raw_count": 126715, "count": 129940, "decode_str": "fre"} -{"id": 6214, "token": "etes", "merges": "et es", "raw_count": 9589, "count": 130013, "decode_str": "etes"} -{"id": 22444, "token": "Api", "merges": "A pi", "raw_count": 130020, "count": 130020, "decode_str": "Api"} -{"id": 3874, "token": "\u0120town", "merges": "\u0120to wn", "raw_count": 102874, "count": 130021, "decode_str": " town"} -{"id": 11205, "token": "\u0120aimed", "merges": "\u0120aim ed", "raw_count": 130040, "count": 130040, "decode_str": " aimed"} -{"id": 16722, "token": "Handle", "merges": "Hand le", "raw_count": 130046, "count": 130046, "decode_str": "Handle"} -{"id": 28951, "token": "\u0120tx", "merges": "\u0120t x", "raw_count": 130061, "count": 130061, "decode_str": " tx"} -{"id": 23422, "token": "LIST", "merges": "L IST", "raw_count": 130095, "count": 130095, "decode_str": "LIST"} -{"id": 22532, "token": "Flag", "merges": "Fl ag", "raw_count": 130124, "count": 130124, "decode_str": "Flag"} -{"id": 25385, "token": "Cy", "merges": "C y", "raw_count": 130173, "count": 130173, "decode_str": "Cy"} -{"id": 24204, "token": "gre", "merges": "g re", "raw_count": 130204, "count": 130204, "decode_str": "gre"} -{"id": 39120, "token": "dimension", "merges": "dim ension", "raw_count": 130233, "count": 130233, "decode_str": "dimension"} -{"id": 45235, "token": "\u0120consultations", "merges": "\u0120consult ations", "raw_count": 130246, "count": 130246, "decode_str": " consultations"} -{"id": 36446, "token": "versions", "merges": "vers ions", "raw_count": 130279, "count": 130279, "decode_str": "versions"} -{"id": 49909, "token": "718", "merges": "7 18", "raw_count": 130283, "count": 130283, "decode_str": "718"} -{"id": 52815, "token": "\u00e7\u0130\u00b3", "merges": "\u00e7\u0130 \u00b3", "raw_count": 130302, "count": 130302, "decode_str": "\u73b3"} -{"id": 5725, "token": "orrow", "merges": "or row", "raw_count": 42886, "count": 130307, "decode_str": "orrow"} -{"id": 6882, "token": "\u0120cond", "merges": "\u0120con d", "raw_count": 72717, "count": 130326, "decode_str": " cond"} -{"id": 11747, "token": "dam", "merges": "d am", "raw_count": 107544, "count": 130335, "decode_str": "dam"} -{"id": 33355, "token": "Bot", "merges": "B ot", "raw_count": 130339, "count": 130339, "decode_str": "Bot"} -{"id": 9785, "token": "IES", "merges": "I ES", "raw_count": 130261, "count": 130345, "decode_str": "IES"} -{"id": 24933, "token": "\u0120millenn", "merges": "\u0120mill enn", "raw_count": 2547, "count": 130356, "decode_str": " millenn"} -{"id": 51029, "token": "\u00e5\u0134\u013a", "merges": "\u00e5\u0134 \u013a", "raw_count": 130365, "count": 130365, "decode_str": "\u5498"} -{"id": 2332, "token": "\u0120trial", "merges": "\u0120tri al", "raw_count": 130366, "count": 130366, "decode_str": " trial"} -{"id": 4313, "token": "\u0120ratio", "merges": "\u0120rat io", "raw_count": 130377, "count": 130377, "decode_str": " ratio"} -{"id": 17929, "token": "\u0120headquarters", "merges": "\u0120head quarters", "raw_count": 130397, "count": 130397, "decode_str": " headquarters"} -{"id": 24055, "token": "Lear", "merges": "L ear", "raw_count": 20662, "count": 130423, "decode_str": "Lear"} -{"id": 16559, "token": "cas", "merges": "c as", "raw_count": 124442, "count": 130446, "decode_str": "cas"} -{"id": 30838, "token": "yu", "merges": "y u", "raw_count": 130461, "count": 130461, "decode_str": "yu"} -{"id": 6859, "token": "osa", "merges": "os a", "raw_count": 96576, "count": 130479, "decode_str": "osa"} -{"id": 18157, "token": "Dim", "merges": "D im", "raw_count": 130490, "count": 130490, "decode_str": "Dim"} -{"id": 21563, "token": "Database", "merges": "Dat abase", "raw_count": 130509, "count": 130509, "decode_str": "Database"} -{"id": 26697, "token": "vn", "merges": "v n", "raw_count": 130523, "count": 130523, "decode_str": "vn"} -{"id": 17176, "token": "xd", "merges": "x d", "raw_count": 130537, "count": 130537, "decode_str": "xd"} -{"id": 9170, "token": "\u0120Mult", "merges": "\u0120M ult", "raw_count": 52062, "count": 130539, "decode_str": " Mult"} -{"id": 22202, "token": "similar", "merges": "sim ilar", "raw_count": 127660, "count": 130552, "decode_str": "similar"} -{"id": 53055, "token": "\u00e7\u0142\u0134", "merges": "\u00e7\u0142 \u0134", "raw_count": 130621, "count": 130621, "decode_str": "\u7812"} -{"id": 8415, "token": "\u0120solve", "merges": "\u0120sol ve", "raw_count": 130627, "count": 130627, "decode_str": " solve"} -{"id": 2450, "token": "\u0120inj", "merges": "\u0120in j", "raw_count": 11219, "count": 130632, "decode_str": " inj"} -{"id": 38508, "token": "IEEE", "merges": "I EEE", "raw_count": 130674, "count": 130674, "decode_str": "IEEE"} -{"id": 23954, "token": "Area", "merges": "Are a", "raw_count": 130678, "count": 130678, "decode_str": "Area"} -{"id": 18853, "token": "Ha", "merges": "H a", "raw_count": 130691, "count": 130691, "decode_str": "Ha"} -{"id": 30209, "token": "poll", "merges": "p oll", "raw_count": 130716, "count": 130716, "decode_str": "poll"} -{"id": 4294, "token": "\u0120frequency", "merges": "\u0120frequ ency", "raw_count": 130722, "count": 130722, "decode_str": " frequency"} -{"id": 25684, "token": "LEV", "merges": "LE V", "raw_count": 61540, "count": 130762, "decode_str": "LEV"} -{"id": 5838, "token": "\u0120Note", "merges": "\u0120N ote", "raw_count": 130787, "count": 130787, "decode_str": " Note"} -{"id": 5974, "token": "\u0120student", "merges": "\u0120stud ent", "raw_count": 130796, "count": 130796, "decode_str": " student"} -{"id": 10296, "token": "\u0120technologies", "merges": "\u0120techn ologies", "raw_count": 130805, "count": 130805, "decode_str": " technologies"} -{"id": 9654, "token": "\u012063", "merges": "\u01206 3", "raw_count": 130812, "count": 130812, "decode_str": " 63"} -{"id": 37325, "token": "ygon", "merges": "yg on", "raw_count": 130826, "count": 130826, "decode_str": "ygon"} -{"id": 28192, "token": "selector", "merges": "select or", "raw_count": 130833, "count": 130833, "decode_str": "selector"} -{"id": 17259, "token": "unny", "merges": "unn y", "raw_count": 123678, "count": 130880, "decode_str": "unny"} -{"id": 51679, "token": "\u00e5\u00bf\u00aa", "merges": "\u00e5\u00bf \u00aa", "raw_count": 130893, "count": 130893, "decode_str": "\u5fea"} -{"id": 14801, "token": "\u0120append", "merges": "\u0120app end", "raw_count": 130902, "count": 130902, "decode_str": " append"} -{"id": 33965, "token": "pending", "merges": "p ending", "raw_count": 130914, "count": 130914, "decode_str": "pending"} -{"id": 4619, "token": "\u0120critical", "merges": "\u0120crit ical", "raw_count": 130926, "count": 130926, "decode_str": " critical"} -{"id": 12721, "token": "'_", "merges": "' _", "raw_count": 130939, "count": 130939, "decode_str": "'_"} -{"id": 19457, "token": "\u0120lang", "merges": "\u0120l ang", "raw_count": 130951, "count": 130951, "decode_str": " lang"} -{"id": 15187, "token": "Div", "merges": "D iv", "raw_count": 121703, "count": 130952, "decode_str": "Div"} -{"id": 2916, "token": "\u0120contr", "merges": "\u0120cont r", "raw_count": 9993, "count": 130970, "decode_str": " contr"} -{"id": 19515, "token": "Keep", "merges": "Ke ep", "raw_count": 130971, "count": 130971, "decode_str": "Keep"} -{"id": 15226, "token": "Container", "merges": "Cont ainer", "raw_count": 131003, "count": 131003, "decode_str": "Container"} -{"id": 7146, "token": "Click", "merges": "C lick", "raw_count": 127601, "count": 131049, "decode_str": "Click"} -{"id": 40106, "token": "velocity", "merges": "vel ocity", "raw_count": 131070, "count": 131070, "decode_str": "velocity"} -{"id": 17713, "token": "\u0120dy", "merges": "\u0120d y", "raw_count": 131109, "count": 131109, "decode_str": " dy"} -{"id": 23414, "token": "\u0120512", "merges": "\u01205 12", "raw_count": 131127, "count": 131127, "decode_str": " 512"} -{"id": 13524, "token": "three", "merges": "th ree", "raw_count": 131130, "count": 131130, "decode_str": "three"} -{"id": 19389, "token": "named", "merges": "n amed", "raw_count": 127456, "count": 131170, "decode_str": "named"} -{"id": 8929, "token": "Controller", "merges": "Cont roller", "raw_count": 128257, "count": 131227, "decode_str": "Controller"} -{"id": 8959, "token": "\u0120prompt", "merges": "\u0120prom pt", "raw_count": 82548, "count": 131235, "decode_str": " prompt"} -{"id": 26342, "token": "leaf", "merges": "le af", "raw_count": 131267, "count": 131267, "decode_str": "leaf"} -{"id": 2725, "token": "\u0120demon", "merges": "\u0120dem on", "raw_count": 6759, "count": 131285, "decode_str": " demon"} -{"id": 48279, "token": "Choice", "merges": "Cho ice", "raw_count": 131310, "count": 131310, "decode_str": "Choice"} -{"id": 12036, "token": "\u0120160", "merges": "\u01201 60", "raw_count": 131313, "count": 131313, "decode_str": " 160"} -{"id": 46601, "token": "aggreg", "merges": "ag greg", "raw_count": 131384, "count": 131384, "decode_str": "aggreg"} -{"id": 16676, "token": "\u0120Load", "merges": "\u0120L oad", "raw_count": 121065, "count": 131409, "decode_str": " Load"} -{"id": 47608, "token": "711", "merges": "7 11", "raw_count": 131445, "count": 131445, "decode_str": "711"} -{"id": 54545, "token": "\u00e7\u013b\u0122", "merges": "\u00e7\u013b \u0122", "raw_count": 131465, "count": 131465, "decode_str": "\u7640"} -{"id": 4446, "token": "\u0120drive", "merges": "\u0120dri ve", "raw_count": 128087, "count": 131497, "decode_str": " drive"} -{"id": 16247, "token": "fly", "merges": "f ly", "raw_count": 126130, "count": 131509, "decode_str": "fly"} -{"id": 28821, "token": "given", "merges": "g iven", "raw_count": 131566, "count": 131566, "decode_str": "given"} -{"id": 30920, "token": "906", "merges": "90 6", "raw_count": 131574, "count": 131574, "decode_str": "906"} -{"id": 33727, "token": "779", "merges": "77 9", "raw_count": 131593, "count": 131593, "decode_str": "779"} -{"id": 25194, "token": "ighbor", "merges": "igh bor", "raw_count": 105470, "count": 131602, "decode_str": "ighbor"} -{"id": 9119, "token": "\u0120mob", "merges": "\u0120m ob", "raw_count": 30951, "count": 131610, "decode_str": " mob"} -{"id": 20792, "token": "termin", "merges": "ter min", "raw_count": 109830, "count": 131648, "decode_str": "termin"} -{"id": 35304, "token": "797", "merges": "79 7", "raw_count": 131680, "count": 131680, "decode_str": "797"} -{"id": 5592, "token": "\u0120commerc", "merges": "\u0120comm erc", "raw_count": 155, "count": 131692, "decode_str": " commerc"} -{"id": 6152, "token": "\u0120credit", "merges": "\u0120cred it", "raw_count": 131692, "count": 131692, "decode_str": " credit"} -{"id": 50142, "token": "622", "merges": "6 22", "raw_count": 131726, "count": 131726, "decode_str": "622"} -{"id": 15177, "token": "quality", "merges": "qu ality", "raw_count": 131759, "count": 131759, "decode_str": "quality"} -{"id": 6821, "token": "\u0120spl", "merges": "\u0120s pl", "raw_count": 71543, "count": 131770, "decode_str": " spl"} -{"id": 6780, "token": "\u0120highlight", "merges": "\u0120high light", "raw_count": 45603, "count": 131779, "decode_str": " highlight"} -{"id": 26646, "token": "RB", "merges": "R B", "raw_count": 131788, "count": 131788, "decode_str": "RB"} -{"id": 19698, "token": "\u0120IO", "merges": "\u0120I O", "raw_count": 131526, "count": 131790, "decode_str": " IO"} -{"id": 7012, "token": "\u0120approved", "merges": "\u0120appro ved", "raw_count": 131827, "count": 131827, "decode_str": " approved"} -{"id": 34305, "token": "884", "merges": "88 4", "raw_count": 131902, "count": 131902, "decode_str": "884"} -{"id": 12806, "token": "\u0120layout", "merges": "\u0120lay out", "raw_count": 131907, "count": 131907, "decode_str": " layout"} -{"id": 20812, "token": "050", "merges": "0 50", "raw_count": 131910, "count": 131910, "decode_str": "050"} -{"id": 23118, "token": "circle", "merges": "circ le", "raw_count": 131914, "count": 131914, "decode_str": "circle"} -{"id": 18595, "token": "\u0120proposals", "merges": "\u0120propos als", "raw_count": 131917, "count": 131917, "decode_str": " proposals"} -{"id": 5919, "token": "\u0120efficient", "merges": "\u0120e fficient", "raw_count": 106700, "count": 131963, "decode_str": " efficient"} -{"id": 34802, "token": "878", "merges": "87 8", "raw_count": 131972, "count": 131972, "decode_str": "878"} -{"id": 18904, "token": "OPT", "merges": "OP T", "raw_count": 131973, "count": 131973, "decode_str": "OPT"} -{"id": 35726, "token": "653", "merges": "65 3", "raw_count": 131981, "count": 131981, "decode_str": "653"} -{"id": 26692, "token": "Protocol", "merges": "Pro tocol", "raw_count": 132007, "count": 132007, "decode_str": "Protocol"} -{"id": 18181, "token": "spect", "merges": "s pect", "raw_count": 86543, "count": 132036, "decode_str": "spect"} -{"id": 7592, "token": "\u0120disk", "merges": "\u0120dis k", "raw_count": 132082, "count": 132082, "decode_str": " disk"} -{"id": 15758, "token": "ifact", "merges": "if act", "raw_count": 29905, "count": 132085, "decode_str": "ifact"} -{"id": 3407, "token": "\u0120began", "merges": "\u0120be gan", "raw_count": 132107, "count": 132107, "decode_str": " began"} -{"id": 16389, "token": "middle", "merges": "m iddle", "raw_count": 132117, "count": 132117, "decode_str": "middle"} -{"id": 15566, "token": "Convert", "merges": "Con vert", "raw_count": 132118, "count": 132118, "decode_str": "Convert"} -{"id": 30183, "token": "Points", "merges": "Point s", "raw_count": 132160, "count": 132160, "decode_str": "Points"} -{"id": 11171, "token": "hol", "merges": "h ol", "raw_count": 92488, "count": 132183, "decode_str": "hol"} -{"id": 27225, "token": "FIX", "merges": "FI X", "raw_count": 65465, "count": 132192, "decode_str": "FIX"} -{"id": 6662, "token": "\u0120fundament", "merges": "\u0120fund ament", "raw_count": 4915, "count": 132254, "decode_str": " fundament"} -{"id": 6813, "token": "\u0120Mag", "merges": "\u0120M ag", "raw_count": 9704, "count": 132292, "decode_str": " Mag"} -{"id": 32604, "token": "AZ", "merges": "A Z", "raw_count": 132299, "count": 132299, "decode_str": "AZ"} -{"id": 39228, "token": "CCC", "merges": "CC C", "raw_count": 132307, "count": 132307, "decode_str": "CCC"} -{"id": 26352, "token": "\u0120yo", "merges": "\u0120y o", "raw_count": 132307, "count": 132307, "decode_str": " yo"} -{"id": 7907, "token": "\u0120depart", "merges": "\u0120dep art", "raw_count": 19485, "count": 132316, "decode_str": " depart"} -{"id": 21440, "token": "\u0120hotels", "merges": "\u0120hot els", "raw_count": 132354, "count": 132354, "decode_str": " hotels"} -{"id": 44295, "token": "further", "merges": "f urther", "raw_count": 132377, "count": 132377, "decode_str": "further"} -{"id": 6704, "token": "\u0120signed", "merges": "\u0120sign ed", "raw_count": 132423, "count": 132423, "decode_str": " signed"} -{"id": 31685, "token": "BMI", "merges": "B MI", "raw_count": 132425, "count": 132425, "decode_str": "BMI"} -{"id": 36077, "token": "finished", "merges": "fin ished", "raw_count": 132428, "count": 132428, "decode_str": "finished"} -{"id": 5790, "token": "\u00d0\u00be\u00d0\u00b2", "merges": "\u00d0\u00be\u00d0 \u00b2", "raw_count": 104189, "count": 132441, "decode_str": "\u043e\u0432"} -{"id": 32763, "token": "planes", "merges": "pl anes", "raw_count": 132465, "count": 132465, "decode_str": "planes"} -{"id": 6251, "token": "\u0120officers", "merges": "\u0120offic ers", "raw_count": 132493, "count": 132493, "decode_str": " officers"} -{"id": 30172, "token": "methods", "merges": "method s", "raw_count": 132528, "count": 132528, "decode_str": "methods"} -{"id": 5955, "token": "\u0120discussion", "merges": "\u0120discuss ion", "raw_count": 132564, "count": 132564, "decode_str": " discussion"} -{"id": 7794, "token": "\u0120aspects", "merges": "\u0120aspect s", "raw_count": 132580, "count": 132580, "decode_str": " aspects"} -{"id": 11987, "token": "eras", "merges": "er as", "raw_count": 113476, "count": 132583, "decode_str": "eras"} -{"id": 42772, "token": "545", "merges": "5 45", "raw_count": 132603, "count": 132603, "decode_str": "545"} -{"id": 1982, "token": "\u0120US", "merges": "\u0120U S", "raw_count": 64070, "count": 132617, "decode_str": " US"} -{"id": 9382, "token": "avas", "merges": "av as", "raw_count": 8694, "count": 132630, "decode_str": "avas"} -{"id": 6454, "token": "\u0120outcome", "merges": "\u0120out come", "raw_count": 132666, "count": 132666, "decode_str": " outcome"} -{"id": 7642, "token": "\u0120suppl", "merges": "\u0120supp l", "raw_count": 1707, "count": 132680, "decode_str": " suppl"} -{"id": 15537, "token": "VER", "merges": "V ER", "raw_count": 123289, "count": 132681, "decode_str": "VER"} -{"id": 21375, "token": "-[", "merges": "- [", "raw_count": 132711, "count": 132711, "decode_str": "-["} -{"id": 10489, "token": "through", "merges": "th rough", "raw_count": 111500, "count": 132750, "decode_str": "through"} -{"id": 25855, "token": "almost", "merges": "al most", "raw_count": 132751, "count": 132751, "decode_str": "almost"} -{"id": 6429, "token": "\u0120ma", "merges": "\u0120m a", "raw_count": 119271, "count": 132761, "decode_str": " ma"} -{"id": 21061, "token": "resolution", "merges": "res olution", "raw_count": 132767, "count": 132767, "decode_str": "resolution"} -{"id": 17164, "token": "FUN", "merges": "F UN", "raw_count": 92425, "count": 132802, "decode_str": "FUN"} -{"id": 23781, "token": "...]", "merges": "... ]", "raw_count": 127356, "count": 132843, "decode_str": "...]"} -{"id": 17884, "token": "040", "merges": "0 40", "raw_count": 132873, "count": 132873, "decode_str": "040"} -{"id": 39697, "token": "567", "merges": "5 67", "raw_count": 132876, "count": 132876, "decode_str": "567"} -{"id": 29790, "token": "697", "merges": "69 7", "raw_count": 132915, "count": 132915, "decode_str": "697"} -{"id": 13689, "token": "Wait", "merges": "W ait", "raw_count": 132924, "count": 132924, "decode_str": "Wait"} -{"id": 40512, "token": "resid", "merges": "res id", "raw_count": 132938, "count": 132938, "decode_str": "resid"} -{"id": 54566, "token": "\u00e9\u0136\u0139", "merges": "\u00e9\u0136 \u0139", "raw_count": 132941, "count": 132941, "decode_str": "\u9517"} -{"id": 16501, "token": "Cre", "merges": "C re", "raw_count": 44270, "count": 132953, "decode_str": "Cre"} -{"id": 50554, "token": "\u00e4\u00bd\u013a", "merges": "\u00e4\u00bd \u013a", "raw_count": 133049, "count": 133049, "decode_str": "\u4f58"} -{"id": 4593, "token": "\u0120effic", "merges": "\u0120e ffic", "raw_count": 1282, "count": 133088, "decode_str": " effic"} -{"id": 19570, "token": "Helper", "merges": "Hel per", "raw_count": 133105, "count": 133105, "decode_str": "Helper"} -{"id": 8249, "token": "\u0120scientific", "merges": "\u0120scient ific", "raw_count": 133117, "count": 133117, "decode_str": " scientific"} -{"id": 17338, "token": "transfer", "merges": "trans fer", "raw_count": 132286, "count": 133117, "decode_str": "transfer"} -{"id": 4259, "token": "epsilon", "merges": "eps ilon", "raw_count": 133150, "count": 133150, "decode_str": "epsilon"} -{"id": 19268, "token": "cribe", "merges": "crib e", "raw_count": 66035, "count": 133151, "decode_str": "cribe"} -{"id": 5649, "token": "\u0120benefit", "merges": "\u0120benef it", "raw_count": 133154, "count": 133154, "decode_str": " benefit"} -{"id": 5385, "token": "\u0120cru", "merges": "\u0120c ru", "raw_count": 14689, "count": 133155, "decode_str": " cru"} -{"id": 40851, "token": "ADA", "merges": "AD A", "raw_count": 133163, "count": 133163, "decode_str": "ADA"} -{"id": 30413, "token": "474", "merges": "47 4", "raw_count": 133173, "count": 133173, "decode_str": "474"} -{"id": 19417, "token": "design", "merges": "des ign", "raw_count": 133187, "count": 133187, "decode_str": "design"} -{"id": 10103, "token": "\u0120dimensions", "merges": "\u0120dim ensions", "raw_count": 133206, "count": 133206, "decode_str": " dimensions"} -{"id": 36751, "token": "Jean", "merges": "J ean", "raw_count": 133290, "count": 133290, "decode_str": "Jean"} -{"id": 27436, "token": "\u0120wrapper", "merges": "\u0120wra pper", "raw_count": 133299, "count": 133299, "decode_str": " wrapper"} -{"id": 32186, "token": ")--", "merges": ") --", "raw_count": 133305, "count": 133305, "decode_str": ")--"} -{"id": 2616, "token": "\u0120factors", "merges": "\u0120fact ors", "raw_count": 133318, "count": 133318, "decode_str": " factors"} -{"id": 30430, "token": "Online", "merges": "On line", "raw_count": 133318, "count": 133318, "decode_str": "Online"} -{"id": 4044, "token": "\u0120obtain", "merges": "\u0120obt ain", "raw_count": 133333, "count": 133333, "decode_str": " obtain"} -{"id": 26102, "token": "Sequence", "merges": "Sequ ence", "raw_count": 133347, "count": 133347, "decode_str": "Sequence"} -{"id": 6547, "token": "cluding", "merges": "clud ing", "raw_count": 15478, "count": 133350, "decode_str": "cluding"} -{"id": 5123, "token": "uses", "merges": "us es", "raw_count": 81788, "count": 133358, "decode_str": "uses"} -{"id": 25009, "token": "nom", "merges": "n om", "raw_count": 133360, "count": 133360, "decode_str": "nom"} -{"id": 7790, "token": "ifies", "merges": "if ies", "raw_count": 85552, "count": 133412, "decode_str": "ifies"} -{"id": 15511, "token": "VERS", "merges": "V ERS", "raw_count": 11713, "count": 133421, "decode_str": "VERS"} -{"id": 24301, "token": "adv", "merges": "ad v", "raw_count": 91864, "count": 133500, "decode_str": "adv"} -{"id": 24912, "token": "ogo", "merges": "og o", "raw_count": 133500, "count": 133500, "decode_str": "ogo"} -{"id": 4048, "token": "orph", "merges": "or ph", "raw_count": 80518, "count": 133505, "decode_str": "orph"} -{"id": 8420, "token": "mann", "merges": "m ann", "raw_count": 128314, "count": 133525, "decode_str": "mann"} -{"id": 21611, "token": "Msg", "merges": "M sg", "raw_count": 133531, "count": 133531, "decode_str": "Msg"} -{"id": 4745, "token": "\u0120immediately", "merges": "\u0120immedi ately", "raw_count": 133575, "count": 133575, "decode_str": " immediately"} -{"id": 11891, "token": "\u0120awareness", "merges": "\u0120aw areness", "raw_count": 133580, "count": 133580, "decode_str": " awareness"} -{"id": 35139, "token": "Pub", "merges": "P ub", "raw_count": 133584, "count": 133584, "decode_str": "Pub"} -{"id": 43357, "token": "Party", "merges": "Part y", "raw_count": 133622, "count": 133622, "decode_str": "Party"} -{"id": 50563, "token": "\u00e4\u00bd\u00a4", "merges": "\u00e4\u00bd \u00a4", "raw_count": 133684, "count": 133684, "decode_str": "\u4f64"} -{"id": 7096, "token": "xe", "merges": "x e", "raw_count": 133691, "count": 133691, "decode_str": "xe"} -{"id": 28949, "token": "0100", "merges": "01 00", "raw_count": 133705, "count": 133705, "decode_str": "0100"} -{"id": 17977, "token": "~-", "merges": "~ -", "raw_count": 133709, "count": 133709, "decode_str": "~-"} -{"id": 23611, "token": "imi", "merges": "im i", "raw_count": 133720, "count": 133720, "decode_str": "imi"} -{"id": 6395, "token": "(&", "merges": "( &", "raw_count": 133723, "count": 133723, "decode_str": "(&"} -{"id": 50057, "token": ".?", "merges": ". ?", "raw_count": 133777, "count": 133777, "decode_str": ".?"} -{"id": 27916, "token": "Rub", "merges": "R ub", "raw_count": 77509, "count": 133859, "decode_str": "Rub"} -{"id": 20282, "token": "vt", "merges": "v t", "raw_count": 133876, "count": 133876, "decode_str": "vt"} -{"id": 14749, "token": "Nav", "merges": "N av", "raw_count": 120028, "count": 133915, "decode_str": "Nav"} -{"id": 28440, "token": "Joe", "merges": "J oe", "raw_count": 133949, "count": 133949, "decode_str": "Joe"} -{"id": 21617, "token": "istration", "merges": "ist ration", "raw_count": 2386, "count": 133954, "decode_str": "istration"} -{"id": 38518, "token": "683", "merges": "68 3", "raw_count": 133955, "count": 133955, "decode_str": "683"} -{"id": 34651, "token": "597", "merges": "59 7", "raw_count": 133986, "count": 133986, "decode_str": "597"} -{"id": 26008, "token": "Pen", "merges": "P en", "raw_count": 134049, "count": 134049, "decode_str": "Pen"} -{"id": 27381, "token": "online", "merges": "on line", "raw_count": 134053, "count": 134053, "decode_str": "online"} -{"id": 47616, "token": "538", "merges": "5 38", "raw_count": 134072, "count": 134072, "decode_str": "538"} -{"id": 9797, "token": "\u0120audio", "merges": "\u0120aud io", "raw_count": 134078, "count": 134078, "decode_str": " audio"} -{"id": 28883, "token": "684", "merges": "68 4", "raw_count": 134127, "count": 134127, "decode_str": "684"} -{"id": 45698, "token": "705", "merges": "7 05", "raw_count": 134136, "count": 134136, "decode_str": "705"} -{"id": 28348, "token": "CAC", "merges": "C AC", "raw_count": 82074, "count": 134146, "decode_str": "CAC"} -{"id": 40844, "token": "prior", "merges": "pri or", "raw_count": 134172, "count": 134172, "decode_str": "prior"} -{"id": 40629, "token": "762", "merges": "76 2", "raw_count": 134180, "count": 134180, "decode_str": "762"} -{"id": 26241, "token": "hdr", "merges": "h dr", "raw_count": 134189, "count": 134189, "decode_str": "hdr"} -{"id": 53511, "token": "\u00e8\u0125\u012f", "merges": "\u00e8\u0125 \u012f", "raw_count": 134191, "count": 134191, "decode_str": "\u80cd"} -{"id": 35488, "token": "682", "merges": "68 2", "raw_count": 134228, "count": 134228, "decode_str": "682"} -{"id": 13456, "token": "sky", "merges": "sk y", "raw_count": 124838, "count": 134238, "decode_str": "sky"} -{"id": 20752, "token": "mag", "merges": "m ag", "raw_count": 134258, "count": 134258, "decode_str": "mag"} -{"id": 32012, "token": "nail", "merges": "n ail", "raw_count": 134317, "count": 134317, "decode_str": "nail"} -{"id": 54567, "token": "\u00e7\u0136\u0133", "merges": "\u00e7\u0136 \u0133", "raw_count": 134327, "count": 134327, "decode_str": "\u7511"} -{"id": 27944, "token": "ytics", "merges": "yt ics", "raw_count": 129123, "count": 134338, "decode_str": "ytics"} -{"id": 4585, "token": "\u0120highest", "merges": "\u0120hig hest", "raw_count": 134382, "count": 134382, "decode_str": " highest"} -{"id": 13020, "token": "scribe", "merges": "scrib e", "raw_count": 12860, "count": 134435, "decode_str": "scribe"} -{"id": 7855, "token": "iary", "merges": "i ary", "raw_count": 22449, "count": 134438, "decode_str": "iary"} -{"id": 4426, "token": "\u0120qual", "merges": "\u0120qu al", "raw_count": 21967, "count": 134446, "decode_str": " qual"} -{"id": 10795, "token": "Does", "merges": "Do es", "raw_count": 134454, "count": 134454, "decode_str": "Does"} -{"id": 43554, "token": "Tuple", "merges": "T uple", "raw_count": 134479, "count": 134479, "decode_str": "Tuple"} -{"id": 3748, "token": "\u0120mention", "merges": "\u0120m ention", "raw_count": 42567, "count": 134481, "decode_str": " mention"} -{"id": 54329, "token": "\u00e9\u013b\u0141", "merges": "\u00e9\u013b \u0141", "raw_count": 134505, "count": 134505, "decode_str": "\u965f"} -{"id": 23475, "token": "Cat", "merges": "C at", "raw_count": 134522, "count": 134522, "decode_str": "Cat"} -{"id": 22384, "token": "Scott", "merges": "Sc ott", "raw_count": 134545, "count": 134545, "decode_str": "Scott"} -{"id": 29576, "token": "vl", "merges": "v l", "raw_count": 134625, "count": 134625, "decode_str": "vl"} -{"id": 4155, "token": "\u0120System", "merges": "\u0120S ystem", "raw_count": 126566, "count": 134629, "decode_str": " System"} -{"id": 12554, "token": "represent", "merges": "rep resent", "raw_count": 50073, "count": 134646, "decode_str": "represent"} -{"id": 24474, "token": "Hor", "merges": "H or", "raw_count": 97175, "count": 134670, "decode_str": "Hor"} -{"id": 23713, "token": "nh", "merges": "n h", "raw_count": 134688, "count": 134688, "decode_str": "nh"} -{"id": 4298, "token": "\u0120experien", "merges": "\u0120exper ien", "raw_count": 394, "count": 134690, "decode_str": " experien"} -{"id": 11441, "token": "amps", "merges": "am ps", "raw_count": 114716, "count": 134705, "decode_str": "amps"} -{"id": 13249, "token": "\u0120coordinate", "merges": "\u0120coord inate", "raw_count": 134707, "count": 134707, "decode_str": " coordinate"} -{"id": 6472, "token": "aming", "merges": "am ing", "raw_count": 99519, "count": 134711, "decode_str": "aming"} -{"id": 5975, "token": "\u0120conver", "merges": "\u0120con ver", "raw_count": 18337, "count": 134738, "decode_str": " conver"} -{"id": 27555, "token": "Times", "merges": "T imes", "raw_count": 134887, "count": 134887, "decode_str": "Times"} -{"id": 1108, "token": "\u0120\u00e2\u0122\u0135", "merges": "\u0120\u00e2\u0122 \u0135", "raw_count": 134874, "count": 134897, "decode_str": " \u2013"} -{"id": 18591, "token": "UG", "merges": "U G", "raw_count": 134901, "count": 134901, "decode_str": "UG"} -{"id": 5999, "token": "\u0120situ", "merges": "\u0120sit u", "raw_count": 7224, "count": 134904, "decode_str": " situ"} -{"id": 11581, "token": "\u0120duplic", "merges": "\u0120du plic", "raw_count": 6944, "count": 134922, "decode_str": " duplic"} -{"id": 37315, "token": "Sel", "merges": "S el", "raw_count": 135015, "count": 135015, "decode_str": "Sel"} -{"id": 50578, "token": "\u00e4\u00be\u0133", "merges": "\u00e4\u00be \u0133", "raw_count": 135030, "count": 135030, "decode_str": "\u4f91"} -{"id": 32279, "token": "future", "merges": "f uture", "raw_count": 135055, "count": 135055, "decode_str": "future"} -{"id": 13929, "token": "\u0120repos", "merges": "\u0120re pos", "raw_count": 17093, "count": 135069, "decode_str": " repos"} -{"id": 42383, "token": "421", "merges": "4 21", "raw_count": 135087, "count": 135087, "decode_str": "421"} -{"id": 16563, "token": "imit", "merges": "im it", "raw_count": 46383, "count": 135094, "decode_str": "imit"} -{"id": 7815, "token": "\u0120citizens", "merges": "\u0120citiz ens", "raw_count": 107244, "count": 135105, "decode_str": " citizens"} -{"id": 4158, "token": "\u0120designed", "merges": "\u0120des igned", "raw_count": 135108, "count": 135108, "decode_str": " designed"} -{"id": 3270, "token": "\u0120anti", "merges": "\u0120ant i", "raw_count": 135114, "count": 135114, "decode_str": " anti"} -{"id": 3294, "token": "\u0120compar", "merges": "\u0120comp ar", "raw_count": 7911, "count": 135158, "decode_str": " compar"} -{"id": 38686, "token": "427", "merges": "4 27", "raw_count": 135165, "count": 135165, "decode_str": "427"} -{"id": 4335, "token": "\u0120prime", "merges": "\u0120pr ime", "raw_count": 135200, "count": 135200, "decode_str": " prime"} -{"id": 33120, "token": "856", "merges": "85 6", "raw_count": 135211, "count": 135211, "decode_str": "856"} -{"id": 9072, "token": "strong", "merges": "str ong", "raw_count": 134188, "count": 135231, "decode_str": "strong"} -{"id": 3369, "token": "\u0120door", "merges": "\u0120do or", "raw_count": 131569, "count": 135267, "decode_str": " door"} -{"id": 6051, "token": "iable", "merges": "i able", "raw_count": 38245, "count": 135268, "decode_str": "iable"} -{"id": 53713, "token": "\u00e8\u00a1\u00b2", "merges": "\u00e8\u00a1 \u00b2", "raw_count": 135284, "count": 135284, "decode_str": "\u8872"} -{"id": 51123, "token": "\u00e5\u0138\u0141", "merges": "\u00e5\u0138 \u0141", "raw_count": 135297, "count": 135297, "decode_str": "\u559f"} -{"id": 36356, "token": "424", "merges": "4 24", "raw_count": 135298, "count": 135298, "decode_str": "424"} -{"id": 3636, "token": "\u0120identified", "merges": "\u0120ident ified", "raw_count": 135341, "count": 135341, "decode_str": " identified"} -{"id": 29003, "token": "FIN", "merges": "F IN", "raw_count": 135394, "count": 135394, "decode_str": "FIN"} -{"id": 30910, "token": "487", "merges": "48 7", "raw_count": 135470, "count": 135470, "decode_str": "487"} -{"id": 16705, "token": "twitter", "merges": "tw itter", "raw_count": 135485, "count": 135485, "decode_str": "twitter"} -{"id": 21950, "token": "Works", "merges": "W orks", "raw_count": 135502, "count": 135502, "decode_str": "Works"} -{"id": 14394, "token": "\u00eb\u012d", "merges": "\u00eb \u012d", "raw_count": 26061, "count": 135524, "decode_str": "\ufffd"} -{"id": 10312, "token": "\u0120guid", "merges": "\u0120gu id", "raw_count": 19679, "count": 135593, "decode_str": " guid"} -{"id": 2167, "token": "\u0120though", "merges": "\u0120th ough", "raw_count": 135598, "count": 135598, "decode_str": " though"} -{"id": 7277, "token": "\u0120compare", "merges": "\u0120comp are", "raw_count": 135607, "count": 135607, "decode_str": " compare"} -{"id": 10434, "token": "\u0120assets", "merges": "\u0120ass ets", "raw_count": 135607, "count": 135607, "decode_str": " assets"} -{"id": 54396, "token": "\u00e9\u013e\u00b0", "merges": "\u00e9\u013e \u00b0", "raw_count": 135623, "count": 135623, "decode_str": "\u9730"} -{"id": 4023, "token": "\u0120ball", "merges": "\u0120b all", "raw_count": 91417, "count": 135677, "decode_str": " ball"} -{"id": 31224, "token": "projects", "merges": "project s", "raw_count": 135704, "count": 135704, "decode_str": "projects"} -{"id": 4990, "token": "material", "merges": "m aterial", "raw_count": 103790, "count": 135709, "decode_str": "material"} -{"id": 5223, "token": "\u0120adapt", "merges": "\u0120ad apt", "raw_count": 47037, "count": 135716, "decode_str": " adapt"} -{"id": 53604, "token": "\u00e8\u012b\u00b9", "merges": "\u00e8\u012b \u00b9", "raw_count": 135758, "count": 135758, "decode_str": "\u8279"} -{"id": 10771, "token": "\u0120km", "merges": "\u0120k m", "raw_count": 135774, "count": 135774, "decode_str": " km"} -{"id": 3473, "token": "\u0120pressure", "merges": "\u0120press ure", "raw_count": 135795, "count": 135795, "decode_str": " pressure"} -{"id": 48173, "token": "940", "merges": "9 40", "raw_count": 135796, "count": 135796, "decode_str": "940"} -{"id": 4248, "token": "\u0120degree", "merges": "\u0120de gree", "raw_count": 135800, "count": 135800, "decode_str": " degree"} -{"id": 5271, "token": "\u0120Aut", "merges": "\u0120A ut", "raw_count": 43944, "count": 135809, "decode_str": " Aut"} -{"id": 3174, "token": "\u0120foot", "merges": "\u0120f oot", "raw_count": 54375, "count": 135820, "decode_str": " foot"} -{"id": 21996, "token": "HF", "merges": "H F", "raw_count": 135898, "count": 135898, "decode_str": "HF"} -{"id": 11909, "token": "Configuration", "merges": "Config uration", "raw_count": 135911, "count": 135911, "decode_str": "Configuration"} -{"id": 3559, "token": "\u0120presented", "merges": "\u0120present ed", "raw_count": 135992, "count": 135992, "decode_str": " presented"} -{"id": 7116, "token": "itable", "merges": "it able", "raw_count": 73547, "count": 136001, "decode_str": "itable"} -{"id": 35941, "token": "JB", "merges": "J B", "raw_count": 136025, "count": 136025, "decode_str": "JB"} -{"id": 13587, "token": "READ", "merges": "RE AD", "raw_count": 118199, "count": 136039, "decode_str": "READ"} -{"id": 7385, "token": "enth", "merges": "ent h", "raw_count": 29293, "count": 136048, "decode_str": "enth"} -{"id": 28946, "token": "rp", "merges": "r p", "raw_count": 136049, "count": 136049, "decode_str": "rp"} -{"id": 10202, "token": "elihood", "merges": "eli hood", "raw_count": 79203, "count": 136059, "decode_str": "elihood"} -{"id": 33317, "token": "wang", "merges": "w ang", "raw_count": 136065, "count": 136065, "decode_str": "wang"} -{"id": 5947, "token": "\u0120cir", "merges": "\u0120c ir", "raw_count": 69614, "count": 136078, "decode_str": " cir"} -{"id": 47952, "token": "erp", "merges": "er p", "raw_count": 136118, "count": 136118, "decode_str": "erp"} -{"id": 5326, "token": "\u0120remov", "merges": "\u0120rem ov", "raw_count": 8742, "count": 136125, "decode_str": " remov"} -{"id": 33953, "token": "471", "merges": "47 1", "raw_count": 136130, "count": 136130, "decode_str": "471"} -{"id": 39108, "token": ",&", "merges": ", &", "raw_count": 136131, "count": 136131, "decode_str": ",&"} -{"id": 25593, "token": "**:", "merges": "** :", "raw_count": 136185, "count": 136185, "decode_str": "**:"} -{"id": 35861, "token": "according", "merges": "acc ording", "raw_count": 136193, "count": 136193, "decode_str": "according"} -{"id": 21605, "token": "Remove", "merges": "Rem ove", "raw_count": 136196, "count": 136196, "decode_str": "Remove"} -{"id": 7547, "token": "\"})", "merges": "\"} )", "raw_count": 136202, "count": 136202, "decode_str": "\"})"} -{"id": 16008, "token": "Donald", "merges": "D onald", "raw_count": 135718, "count": 136236, "decode_str": "Donald"} -{"id": 49017, "token": "corp", "merges": "cor p", "raw_count": 136319, "count": 136319, "decode_str": "corp"} -{"id": 7448, "token": "/-", "merges": "/ -", "raw_count": 100757, "count": 136349, "decode_str": "/-"} -{"id": 4191, "token": "\u0120beaut", "merges": "\u0120be aut", "raw_count": 4528, "count": 136353, "decode_str": " beaut"} -{"id": 24133, "token": "0009", "merges": "000 9", "raw_count": 136377, "count": 136377, "decode_str": "0009"} -{"id": 13544, "token": ">\\", "merges": "> \\", "raw_count": 136416, "count": 136416, "decode_str": ">\\"} -{"id": 19506, "token": "say", "merges": "s ay", "raw_count": 136183, "count": 136464, "decode_str": "say"} -{"id": 48699, "token": "568", "merges": "5 68", "raw_count": 136469, "count": 136469, "decode_str": "568"} -{"id": 51052, "token": "\u00e5\u0135\u0124", "merges": "\u00e5\u0135 \u0124", "raw_count": 136471, "count": 136471, "decode_str": "\u54c2"} -{"id": 28700, "token": "bee", "merges": "be e", "raw_count": 136488, "count": 136488, "decode_str": "bee"} -{"id": 6284, "token": "\u0120interests", "merges": "\u0120interest s", "raw_count": 136523, "count": 136523, "decode_str": " interests"} -{"id": 13859, "token": "IAL", "merges": "I AL", "raw_count": 66803, "count": 136541, "decode_str": "IAL"} -{"id": 32731, "token": "veh", "merges": "ve h", "raw_count": 41852, "count": 136563, "decode_str": "veh"} -{"id": 4147, "token": "\u0120purch", "merges": "\u0120pur ch", "raw_count": 1908, "count": 136586, "decode_str": " purch"} -{"id": 28692, "token": "definition", "merges": "def inition", "raw_count": 136627, "count": 136627, "decode_str": "definition"} -{"id": 6785, "token": "imb", "merges": "im b", "raw_count": 63376, "count": 136630, "decode_str": "imb"} -{"id": 38043, "token": "423", "merges": "4 23", "raw_count": 136658, "count": 136658, "decode_str": "423"} -{"id": 39405, "token": "991", "merges": "99 1", "raw_count": 136664, "count": 136664, "decode_str": "991"} -{"id": 3784, "token": "pite", "merges": "p ite", "raw_count": 49664, "count": 136676, "decode_str": "pite"} -{"id": 38286, "token": "confirm", "merges": "conf irm", "raw_count": 136702, "count": 136702, "decode_str": "confirm"} -{"id": 9725, "token": "\u01201993", "merges": "\u0120199 3", "raw_count": 136720, "count": 136720, "decode_str": " 1993"} -{"id": 31703, "token": "Serializer", "merges": "Serial izer", "raw_count": 136751, "count": 136751, "decode_str": "Serializer"} -{"id": 8103, "token": "\u0120objective", "merges": "\u0120object ive", "raw_count": 136755, "count": 136755, "decode_str": " objective"} -{"id": 36458, "token": "491", "merges": "49 1", "raw_count": 136761, "count": 136761, "decode_str": "491"} -{"id": 20525, "token": "START", "merges": "ST ART", "raw_count": 136771, "count": 136771, "decode_str": "START"} -{"id": 41924, "token": ":{", "merges": ": {", "raw_count": 136784, "count": 136784, "decode_str": ":{"} -{"id": 46905, "token": "monitor", "merges": "mon itor", "raw_count": 136787, "count": 136787, "decode_str": "monitor"} -{"id": 3982, "token": "\u0120brought", "merges": "\u0120br ought", "raw_count": 136790, "count": 136790, "decode_str": " brought"} -{"id": 35515, "token": "Energy", "merges": "E nergy", "raw_count": 136791, "count": 136791, "decode_str": "Energy"} -{"id": 11983, "token": "aza", "merges": "az a", "raw_count": 135313, "count": 136796, "decode_str": "aza"} -{"id": 27250, "token": "gray", "merges": "gr ay", "raw_count": 136803, "count": 136803, "decode_str": "gray"} -{"id": 7523, "token": "war", "merges": "w ar", "raw_count": 111051, "count": 136882, "decode_str": "war"} -{"id": 33447, "token": "Ult", "merges": "U lt", "raw_count": 136886, "count": 136886, "decode_str": "Ult"} -{"id": 34101, "token": "ROOT", "merges": "RO OT", "raw_count": 136895, "count": 136895, "decode_str": "ROOT"} -{"id": 19350, "token": "formula", "merges": "form ula", "raw_count": 136914, "count": 136914, "decode_str": "formula"} -{"id": 7935, "token": "\u0120instrument", "merges": "\u0120instr ument", "raw_count": 121924, "count": 136920, "decode_str": " instrument"} -{"id": 23832, "token": "products", "merges": "product s", "raw_count": 136920, "count": 136920, "decode_str": "products"} -{"id": 5053, "token": "\u0120places", "merges": "\u0120pl aces", "raw_count": 136944, "count": 136944, "decode_str": " places"} -{"id": 48997, "token": "quit", "merges": "qu it", "raw_count": 137029, "count": 137029, "decode_str": "quit"} -{"id": 21008, "token": "Match", "merges": "M atch", "raw_count": 137048, "count": 137048, "decode_str": "Match"} -{"id": 21724, "token": "ycle", "merges": "y cle", "raw_count": 85164, "count": 137065, "decode_str": "ycle"} -{"id": 6808, "token": "\u0120issued", "merges": "\u0120iss ued", "raw_count": 137085, "count": 137085, "decode_str": " issued"} -{"id": 8143, "token": "\u0120perm", "merges": "\u0120per m", "raw_count": 69974, "count": 137109, "decode_str": " perm"} -{"id": 26077, "token": ";<", "merges": "; <", "raw_count": 137127, "count": 137127, "decode_str": ";<"} -{"id": 42262, "token": "legend", "merges": "leg end", "raw_count": 137142, "count": 137142, "decode_str": "legend"} -{"id": 5497, "token": "\u0120mo", "merges": "\u0120m o", "raw_count": 116906, "count": 137153, "decode_str": " mo"} -{"id": 7847, "token": "%%", "merges": "% %", "raw_count": 113723, "count": 137183, "decode_str": "%%"} -{"id": 18845, "token": "porter", "merges": "por ter", "raw_count": 136054, "count": 137194, "decode_str": "porter"} -{"id": 10944, "token": "iations", "merges": "i ations", "raw_count": 10465, "count": 137211, "decode_str": "iations"} -{"id": 30726, "token": "INA", "merges": "IN A", "raw_count": 137234, "count": 137234, "decode_str": "INA"} -{"id": 53697, "token": "\u00e8\u00a1\u0126", "merges": "\u00e8\u00a1 \u0126", "raw_count": 137243, "count": 137243, "decode_str": "\u8844"} -{"id": 6983, "token": "\u0120recall", "merges": "\u0120rec all", "raw_count": 62176, "count": 137303, "decode_str": " recall"} -{"id": 18449, "token": "HER", "merges": "H ER", "raw_count": 113528, "count": 137355, "decode_str": "HER"} -{"id": 30476, "token": "EU", "merges": "E U", "raw_count": 137373, "count": 137373, "decode_str": "EU"} -{"id": 13881, "token": "Height", "merges": "He ight", "raw_count": 137387, "count": 137387, "decode_str": "Height"} -{"id": 11109, "token": "conomic", "merges": "conom ic", "raw_count": 42894, "count": 137403, "decode_str": "conomic"} -{"id": 6507, "token": "\u0120flat", "merges": "\u0120fl at", "raw_count": 137441, "count": 137441, "decode_str": " flat"} -{"id": 16548, "token": "\u0120Returns", "merges": "\u0120Ret urns", "raw_count": 137451, "count": 137451, "decode_str": " Returns"} -{"id": 7901, "token": "\u01201990", "merges": "\u0120199 0", "raw_count": 137453, "count": 137453, "decode_str": " 1990"} -{"id": 6373, "token": "\u0120apprec", "merges": "\u0120app rec", "raw_count": 13794, "count": 137476, "decode_str": " apprec"} -{"id": 18193, "token": "\u0120Default", "merges": "\u0120Def ault", "raw_count": 137483, "count": 137483, "decode_str": " Default"} -{"id": 8349, "token": "outs", "merges": "out s", "raw_count": 122592, "count": 137508, "decode_str": "outs"} -{"id": 53446, "token": "\u00e8\u0122\u012d", "merges": "\u00e8\u0122 \u012d", "raw_count": 137556, "count": 137556, "decode_str": "\u800b"} -{"id": 18115, "token": "recated", "merges": "rec ated", "raw_count": 54270, "count": 137567, "decode_str": "recated"} -{"id": 10257, "token": "\u0120250", "merges": "\u01202 50", "raw_count": 137575, "count": 137575, "decode_str": " 250"} -{"id": 25321, "token": "tom", "merges": "t om", "raw_count": 137630, "count": 137630, "decode_str": "tom"} -{"id": 5870, "token": "\u0120families", "merges": "\u0120fam ilies", "raw_count": 137652, "count": 137652, "decode_str": " families"} -{"id": 44968, "token": "585", "merges": "5 85", "raw_count": 137655, "count": 137655, "decode_str": "585"} -{"id": 34474, "token": "481", "merges": "48 1", "raw_count": 137679, "count": 137679, "decode_str": "481"} -{"id": 40896, "token": "437", "merges": "4 37", "raw_count": 137711, "count": 137711, "decode_str": "437"} -{"id": 6058, "token": "gin", "merges": "g in", "raw_count": 41124, "count": 137787, "decode_str": "gin"} -{"id": 3756, "token": "ography", "merges": "ograph y", "raw_count": 96710, "count": 137816, "decode_str": "ography"} -{"id": 51180, "token": "\u00e5\u013e\u013e", "merges": "\u00e5\u013e \u013e", "raw_count": 137819, "count": 137819, "decode_str": "\u571c"} -{"id": 41223, "token": "\u0120tribunal", "merges": "\u0120trib unal", "raw_count": 137832, "count": 137832, "decode_str": " tribunal"} -{"id": 39338, "token": "552", "merges": "55 2", "raw_count": 137849, "count": 137849, "decode_str": "552"} -{"id": 22225, "token": "HEAD", "merges": "HE AD", "raw_count": 85322, "count": 137876, "decode_str": "HEAD"} -{"id": 4573, "token": "untu", "merges": "unt u", "raw_count": 3913, "count": 137908, "decode_str": "untu"} -{"id": 24722, "token": "(%", "merges": "( %", "raw_count": 137914, "count": 137914, "decode_str": "(%"} -{"id": 5254, "token": "\u0120floor", "merges": "\u0120fl oor", "raw_count": 137926, "count": 137926, "decode_str": " floor"} -{"id": 44159, "token": "595", "merges": "5 95", "raw_count": 137939, "count": 137939, "decode_str": "595"} -{"id": 27038, "token": "relative", "merges": "rel ative", "raw_count": 137940, "count": 137940, "decode_str": "relative"} -{"id": 24166, "token": "packages", "merges": "pack ages", "raw_count": 137986, "count": 137986, "decode_str": "packages"} -{"id": 10940, "token": "hav", "merges": "h av", "raw_count": 47054, "count": 138039, "decode_str": "hav"} -{"id": 23779, "token": "Success", "merges": "Su ccess", "raw_count": 138087, "count": 138087, "decode_str": "Success"} -{"id": 37719, "token": "trade", "merges": "tr ade", "raw_count": 138102, "count": 138102, "decode_str": "trade"} -{"id": 5005, "token": "cles", "merges": "cl es", "raw_count": 44448, "count": 138136, "decode_str": "cles"} -{"id": 6924, "token": "standing", "merges": "stand ing", "raw_count": 53545, "count": 138185, "decode_str": "standing"} -{"id": 21892, "token": "Wil", "merges": "W il", "raw_count": 73568, "count": 138229, "decode_str": "Wil"} -{"id": 50787, "token": "\u00e5\u012a\u00bd", "merges": "\u00e5\u012a \u00bd", "raw_count": 138240, "count": 138240, "decode_str": "\u523d"} -{"id": 13395, "token": "apsed", "merges": "aps ed", "raw_count": 90411, "count": 138257, "decode_str": "apsed"} -{"id": 32364, "token": "AUT", "merges": "A UT", "raw_count": 138258, "count": 138258, "decode_str": "AUT"} -{"id": 23536, "token": "Role", "merges": "R ole", "raw_count": 138296, "count": 138296, "decode_str": "Role"} -{"id": 7707, "token": "eller", "merges": "ell er", "raw_count": 135717, "count": 138300, "decode_str": "eller"} -{"id": 42487, "token": "\u0120uk", "merges": "\u0120u k", "raw_count": 138329, "count": 138329, "decode_str": " uk"} -{"id": 6046, "token": "\u0120noise", "merges": "\u0120no ise", "raw_count": 138330, "count": 138330, "decode_str": " noise"} -{"id": 11393, "token": "\u0120rural", "merges": "\u0120r ural", "raw_count": 138341, "count": 138341, "decode_str": " rural"} -{"id": 5554, "token": "?'", "merges": "? '", "raw_count": 138363, "count": 138363, "decode_str": "?'"} -{"id": 27421, "token": "dg", "merges": "d g", "raw_count": 138396, "count": 138396, "decode_str": "dg"} -{"id": 19382, "token": "\u0120refugees", "merges": "\u0120refuge es", "raw_count": 138405, "count": 138405, "decode_str": " refugees"} -{"id": 23226, "token": "maps", "merges": "m aps", "raw_count": 138445, "count": 138445, "decode_str": "maps"} -{"id": 6170, "token": "night", "merges": "n ight", "raw_count": 115654, "count": 138489, "decode_str": "night"} -{"id": 39116, "token": "\u0120theta", "merges": "\u0120the ta", "raw_count": 138500, "count": 138500, "decode_str": " theta"} -{"id": 6568, "token": "\u0120camera", "merges": "\u0120cam era", "raw_count": 138526, "count": 138526, "decode_str": " camera"} -{"id": 4229, "token": "\u0120fixed", "merges": "\u0120f ixed", "raw_count": 138537, "count": 138537, "decode_str": " fixed"} -{"id": 4291, "token": "inct", "merges": "in ct", "raw_count": 72421, "count": 138551, "decode_str": "inct"} -{"id": 35216, "token": "663", "merges": "66 3", "raw_count": 138560, "count": 138560, "decode_str": "663"} -{"id": 14105, "token": "quarters", "merges": "qu arters", "raw_count": 8231, "count": 138628, "decode_str": "quarters"} -{"id": 16468, "token": "acker", "merges": "ack er", "raw_count": 90636, "count": 138648, "decode_str": "acker"} -{"id": 42215, "token": "537", "merges": "5 37", "raw_count": 138649, "count": 138649, "decode_str": "537"} -{"id": 3970, "token": "\u0120dynam", "merges": "\u0120d ynam", "raw_count": 14564, "count": 138675, "decode_str": " dynam"} -{"id": 29844, "token": "gradient", "merges": "grad ient", "raw_count": 138703, "count": 138703, "decode_str": "gradient"} -{"id": 53483, "token": "\u00e8\u0124\u0135", "merges": "\u00e8\u0124 \u0135", "raw_count": 138709, "count": 138709, "decode_str": "\u8093"} -{"id": 35495, "token": "!=", "merges": "! =", "raw_count": 138716, "count": 138716, "decode_str": "!="} -{"id": 4095, "token": "\u0120devices", "merges": "\u0120dev ices", "raw_count": 138721, "count": 138721, "decode_str": " devices"} -{"id": 36421, "token": "saved", "merges": "s aved", "raw_count": 138728, "count": 138728, "decode_str": "saved"} -{"id": 20328, "token": "ebook", "merges": "eb ook", "raw_count": 104716, "count": 138729, "decode_str": "ebook"} -{"id": 14577, "token": "degree", "merges": "de gree", "raw_count": 138739, "count": 138739, "decode_str": "degree"} -{"id": 14312, "token": "\u0120promoting", "merges": "\u0120prom oting", "raw_count": 138742, "count": 138742, "decode_str": " promoting"} -{"id": 5109, "token": "itors", "merges": "it ors", "raw_count": 83424, "count": 138743, "decode_str": "itors"} -{"id": 27127, "token": "STM", "merges": "ST M", "raw_count": 138776, "count": 138776, "decode_str": "STM"} -{"id": 12454, "token": "\u0120facilitate", "merges": "\u0120facilit ate", "raw_count": 138779, "count": 138779, "decode_str": " facilitate"} -{"id": 19977, "token": "recip", "merges": "rec ip", "raw_count": 138490, "count": 138815, "decode_str": "recip"} -{"id": 6160, "token": "specific", "merges": "spec ific", "raw_count": 138832, "count": 138832, "decode_str": "specific"} -{"id": 11991, "token": "REG", "merges": "RE G", "raw_count": 138901, "count": 138901, "decode_str": "REG"} -{"id": 35236, "token": "\u0120({", "merges": "\u0120( {", "raw_count": 138911, "count": 138911, "decode_str": " ({"} -{"id": 37256, "token": "851", "merges": "85 1", "raw_count": 138925, "count": 138925, "decode_str": "851"} -{"id": 19252, "token": "OVE", "merges": "OV E", "raw_count": 132960, "count": 138931, "decode_str": "OVE"} -{"id": 13952, "token": "\u0120airport", "merges": "\u0120air port", "raw_count": 138937, "count": 138937, "decode_str": " airport"} -{"id": 34988, "token": "IU", "merges": "I U", "raw_count": 138954, "count": 138954, "decode_str": "IU"} -{"id": 7706, "token": "wing", "merges": "w ing", "raw_count": 67197, "count": 138960, "decode_str": "wing"} -{"id": 20592, "token": "iko", "merges": "ik o", "raw_count": 138983, "count": 138983, "decode_str": "iko"} -{"id": 14674, "token": "half", "merges": "h alf", "raw_count": 138992, "count": 138992, "decode_str": "half"} -{"id": 27716, "token": "gold", "merges": "g old", "raw_count": 139036, "count": 139036, "decode_str": "gold"} -{"id": 52342, "token": "\u00e6\u00a5\u00ab", "merges": "\u00e6\u00a5 \u00ab", "raw_count": 139072, "count": 139072, "decode_str": "\u696b"} -{"id": 26181, "token": "\u0120addr", "merges": "\u0120add r", "raw_count": 139093, "count": 139093, "decode_str": " addr"} -{"id": 4283, "token": "\u0120leading", "merges": "\u0120lead ing", "raw_count": 139152, "count": 139152, "decode_str": " leading"} -{"id": 45316, "token": "529", "merges": "5 29", "raw_count": 139168, "count": 139168, "decode_str": "529"} -{"id": 3242, "token": "\u0120exact", "merges": "\u0120ex act", "raw_count": 67265, "count": 139197, "decode_str": " exact"} -{"id": 3532, "token": "\u0120Ne", "merges": "\u0120N e", "raw_count": 42577, "count": 139224, "decode_str": " Ne"} -{"id": 30285, "token": "\u0120resolutions", "merges": "\u0120res olutions", "raw_count": 139248, "count": 139248, "decode_str": " resolutions"} -{"id": 17082, "token": "\u0120metrics", "merges": "\u0120metric s", "raw_count": 139300, "count": 139300, "decode_str": " metrics"} -{"id": 15653, "token": ".\"\"", "merges": ".\" \"", "raw_count": 139300, "count": 139300, "decode_str": ".\"\""} -{"id": 3520, "token": "\u0120physical", "merges": "\u0120phys ical", "raw_count": 139322, "count": 139322, "decode_str": " physical"} -{"id": 5068, "token": "\u0120beginning", "merges": "\u0120begin ning", "raw_count": 139328, "count": 139328, "decode_str": " beginning"} -{"id": 3362, "token": "quad", "merges": "qu ad", "raw_count": 121981, "count": 139361, "decode_str": "quad"} -{"id": 4435, "token": "\u00d1\u0129", "merges": "\u00d1 \u0129", "raw_count": 41078, "count": 139370, "decode_str": "\u0447"} -{"id": 15188, "token": "jor", "merges": "j or", "raw_count": 9154, "count": 139400, "decode_str": "jor"} -{"id": 26268, "token": "Chain", "merges": "Ch ain", "raw_count": 139444, "count": 139444, "decode_str": "Chain"} -{"id": 10892, "token": "acking", "merges": "ack ing", "raw_count": 69958, "count": 139447, "decode_str": "acking"} -{"id": 24212, "token": "kill", "merges": "k ill", "raw_count": 139472, "count": 139472, "decode_str": "kill"} -{"id": 10634, "token": "MENT", "merges": "M ENT", "raw_count": 122303, "count": 139496, "decode_str": "MENT"} -{"id": 9181, "token": "umes", "merges": "um es", "raw_count": 104816, "count": 139540, "decode_str": "umes"} -{"id": 14156, "token": "\u0120generator", "merges": "\u0120gener ator", "raw_count": 139555, "count": 139555, "decode_str": " generator"} -{"id": 53623, "token": "\u00e8\u012c\u00ab", "merges": "\u00e8\u012c \u00ab", "raw_count": 139576, "count": 139576, "decode_str": "\u82ab"} -{"id": 53576, "token": "\u00e8\u012a\u0132", "merges": "\u00e8\u012a \u0132", "raw_count": 139584, "count": 139584, "decode_str": "\u8210"} -{"id": 10222, "token": "ultural", "merges": "ult ural", "raw_count": 21426, "count": 139589, "decode_str": "ultural"} -{"id": 16566, "token": "\u0120objectives", "merges": "\u0120object ives", "raw_count": 139609, "count": 139609, "decode_str": " objectives"} -{"id": 45857, "token": "Bug", "merges": "B ug", "raw_count": 139661, "count": 139661, "decode_str": "Bug"} -{"id": 17034, "token": "bye", "merges": "by e", "raw_count": 127028, "count": 139699, "decode_str": "bye"} -{"id": 42678, "token": "!),", "merges": "! ),", "raw_count": 139712, "count": 139712, "decode_str": "!),"} -{"id": 5933, "token": "\u0120algorithm", "merges": "\u0120algorith m", "raw_count": 139798, "count": 139798, "decode_str": " algorithm"} -{"id": 2000, "token": "}_", "merges": "} _", "raw_count": 137961, "count": 139804, "decode_str": "}_"} -{"id": 15051, "token": "BER", "merges": "B ER", "raw_count": 93988, "count": 139805, "decode_str": "BER"} -{"id": 27483, "token": "))))", "merges": ")) ))", "raw_count": 139822, "count": 139822, "decode_str": "))))"} -{"id": 30381, "token": "Invest", "merges": "In vest", "raw_count": 139834, "count": 139834, "decode_str": "Invest"} -{"id": 25902, "token": "disable", "merges": "dis able", "raw_count": 139860, "count": 139860, "decode_str": "disable"} -{"id": 23479, "token": "isure", "merges": "is ure", "raw_count": 112546, "count": 139868, "decode_str": "isure"} -{"id": 7318, "token": "\u0120ca", "merges": "\u0120c a", "raw_count": 101698, "count": 139871, "decode_str": " ca"} -{"id": 7228, "token": "uls", "merges": "ul s", "raw_count": 76156, "count": 139909, "decode_str": "uls"} -{"id": 3176, "token": "\u0120appear", "merges": "\u0120appe ar", "raw_count": 98535, "count": 139954, "decode_str": " appear"} -{"id": 17185, "token": "White", "merges": "Wh ite", "raw_count": 139966, "count": 139966, "decode_str": "White"} -{"id": 31774, "token": "441", "merges": "44 1", "raw_count": 139994, "count": 139994, "decode_str": "441"} -{"id": 4481, "token": "\u0120phone", "merges": "\u0120ph one", "raw_count": 140007, "count": 140007, "decode_str": " phone"} -{"id": 32674, "token": "during", "merges": "d uring", "raw_count": 140008, "count": 140008, "decode_str": "during"} -{"id": 51375, "token": "\u00e5\u0143\u0122", "merges": "\u00e5\u0143 \u0122", "raw_count": 140012, "count": 140012, "decode_str": "\u5b40"} -{"id": 1904, "token": "\u0120didn", "merges": "\u0120did n", "raw_count": 134610, "count": 140068, "decode_str": " didn"} -{"id": 11185, "token": "Description", "merges": "Des cription", "raw_count": 140073, "count": 140073, "decode_str": "Description"} -{"id": 7299, "token": "bid", "merges": "b id", "raw_count": 127469, "count": 140132, "decode_str": "bid"} -{"id": 10419, "token": "\u0120proposal", "merges": "\u0120propos al", "raw_count": 140158, "count": 140158, "decode_str": " proposal"} -{"id": 15032, "token": "Doc", "merges": "D oc", "raw_count": 116406, "count": 140255, "decode_str": "Doc"} -{"id": 4651, "token": "\u0120parents", "merges": "\u0120parent s", "raw_count": 140289, "count": 140289, "decode_str": " parents"} -{"id": 24221, "token": "Jul", "merges": "J ul", "raw_count": 140291, "count": 140291, "decode_str": "Jul"} -{"id": 7232, "token": "kins", "merges": "k ins", "raw_count": 113602, "count": 140302, "decode_str": "kins"} -{"id": 3846, "token": "\u0120dead", "merges": "\u0120de ad", "raw_count": 94311, "count": 140338, "decode_str": " dead"} -{"id": 42198, "token": "436", "merges": "4 36", "raw_count": 140360, "count": 140360, "decode_str": "436"} -{"id": 44199, "token": "XS", "merges": "X S", "raw_count": 140365, "count": 140365, "decode_str": "XS"} -{"id": 5133, "token": "\u0120manner", "merges": "\u0120man ner", "raw_count": 140375, "count": 140375, "decode_str": " manner"} -{"id": 44681, "token": "\u0120wifi", "merges": "\u0120w ifi", "raw_count": 140392, "count": 140392, "decode_str": " wifi"} -{"id": 39227, "token": "amd", "merges": "am d", "raw_count": 140420, "count": 140420, "decode_str": "amd"} -{"id": 3746, "token": "\u0120themselves", "merges": "\u0120them selves", "raw_count": 140440, "count": 140440, "decode_str": " themselves"} -{"id": 7240, "token": "adow", "merges": "ad ow", "raw_count": 11083, "count": 140451, "decode_str": "adow"} -{"id": 3654, "token": "\u0120alleg", "merges": "\u0120al leg", "raw_count": 1922, "count": 140453, "decode_str": " alleg"} -{"id": 24827, "token": "mysql", "merges": "mys ql", "raw_count": 140472, "count": 140472, "decode_str": "mysql"} -{"id": 5043, "token": "\u0120plus", "merges": "\u0120pl us", "raw_count": 140475, "count": 140475, "decode_str": " plus"} -{"id": 33524, "token": "andidate", "merges": "andid ate", "raw_count": 140480, "count": 140480, "decode_str": "andidate"} -{"id": 3253, "token": "\u0120everything", "merges": "\u0120every thing", "raw_count": 140503, "count": 140503, "decode_str": " everything"} -{"id": 30978, "token": "eye", "merges": "ey e", "raw_count": 140514, "count": 140514, "decode_str": "eye"} -{"id": 12804, "token": "Util", "merges": "U til", "raw_count": 73927, "count": 140532, "decode_str": "Util"} -{"id": 38729, "token": "attach", "merges": "att ach", "raw_count": 140563, "count": 140563, "decode_str": "attach"} -{"id": 21691, "token": "Details", "merges": "Det ails", "raw_count": 140566, "count": 140566, "decode_str": "Details"} -{"id": 11548, "token": "imp", "merges": "im p", "raw_count": 102907, "count": 140586, "decode_str": "imp"} -{"id": 40105, "token": "Hyper", "merges": "Hy per", "raw_count": 140659, "count": 140659, "decode_str": "Hyper"} -{"id": 11410, "token": "\u0120enabled", "merges": "\u0120en abled", "raw_count": 140687, "count": 140687, "decode_str": " enabled"} -{"id": 5837, "token": "isation", "merges": "is ation", "raw_count": 107843, "count": 140688, "decode_str": "isation"} -{"id": 21674, "token": "\u0120identifier", "merges": "\u0120ident ifier", "raw_count": 140709, "count": 140709, "decode_str": " identifier"} -{"id": 20684, "token": "Report", "merges": "Rep ort", "raw_count": 140760, "count": 140760, "decode_str": "Report"} -{"id": 7622, "token": "\u0120route", "merges": "\u0120r oute", "raw_count": 140795, "count": 140795, "decode_str": " route"} -{"id": 38965, "token": "geometry", "merges": "ge ometry", "raw_count": 140852, "count": 140852, "decode_str": "geometry"} -{"id": 3350, "token": "\u0120bir", "merges": "\u0120b ir", "raw_count": 11596, "count": 140879, "decode_str": " bir"} -{"id": 32332, "token": "776", "merges": "77 6", "raw_count": 140901, "count": 140901, "decode_str": "776"} -{"id": 5099, "token": "\u0120jur", "merges": "\u0120j ur", "raw_count": 26299, "count": 140956, "decode_str": " jur"} -{"id": 8895, "token": "ema", "merges": "em a", "raw_count": 124727, "count": 140988, "decode_str": "ema"} -{"id": 12520, "token": "![](", "merges": "![ ](", "raw_count": 141029, "count": 141029, "decode_str": "![]("} -{"id": 4493, "token": "\u0120circum", "merges": "\u0120circ um", "raw_count": 7003, "count": 141032, "decode_str": " circum"} -{"id": 15163, "token": "Body", "merges": "B ody", "raw_count": 141095, "count": 141095, "decode_str": "Body"} -{"id": 37564, "token": "router", "merges": "r outer", "raw_count": 141183, "count": 141183, "decode_str": "router"} -{"id": 12496, "token": "four", "merges": "f our", "raw_count": 87596, "count": 141211, "decode_str": "four"} -{"id": 129, "token": "\u00c5", "merges": "NULL", "raw_count": 9734, "count": 141215, "decode_str": "\ufffd"} -{"id": 33492, "token": "detect", "merges": "det ect", "raw_count": 141241, "count": 141241, "decode_str": "detect"} -{"id": 36681, "token": "652", "merges": "65 2", "raw_count": 141242, "count": 141242, "decode_str": "652"} -{"id": 4375, "token": "\u0120sites", "merges": "\u0120sit es", "raw_count": 141301, "count": 141301, "decode_str": " sites"} -{"id": 45153, "token": "533", "merges": "5 33", "raw_count": 141305, "count": 141305, "decode_str": "533"} -{"id": 28448, "token": "Martin", "merges": "Mart in", "raw_count": 141308, "count": 141308, "decode_str": "Martin"} -{"id": 18919, "token": "Term", "merges": "T erm", "raw_count": 141323, "count": 141323, "decode_str": "Term"} -{"id": 18041, "token": "ENS", "merges": "EN S", "raw_count": 141365, "count": 141365, "decode_str": "ENS"} -{"id": 40819, "token": "\u0120rand", "merges": "\u0120r and", "raw_count": 141369, "count": 141369, "decode_str": " rand"} -{"id": 37365, "token": "mq", "merges": "m q", "raw_count": 141370, "count": 141370, "decode_str": "mq"} -{"id": 3221, "token": "\u0120false", "merges": "\u0120f alse", "raw_count": 141411, "count": 141411, "decode_str": " false"} -{"id": 22599, "token": "\u0120financing", "merges": "\u0120financ ing", "raw_count": 141417, "count": 141417, "decode_str": " financing"} -{"id": 7393, "token": "\u0120rac", "merges": "\u0120r ac", "raw_count": 12217, "count": 141473, "decode_str": " rac"} -{"id": 18130, "token": "Trump", "merges": "Tr ump", "raw_count": 141480, "count": 141480, "decode_str": "Trump"} -{"id": 16212, "token": "Bre", "merges": "B re", "raw_count": 84615, "count": 141486, "decode_str": "Bre"} -{"id": 9788, "token": "\u0120sig", "merges": "\u0120s ig", "raw_count": 138035, "count": 141538, "decode_str": " sig"} -{"id": 38062, "token": "\u0120elem", "merges": "\u0120ele m", "raw_count": 141540, "count": 141540, "decode_str": " elem"} -{"id": 27260, "token": "Feature", "merges": "Fe ature", "raw_count": 141553, "count": 141553, "decode_str": "Feature"} -{"id": 23134, "token": "enant", "merges": "en ant", "raw_count": 20051, "count": 141567, "decode_str": "enant"} -{"id": 16806, "token": "separ", "merges": "se par", "raw_count": 52696, "count": 141586, "decode_str": "separ"} -{"id": 10607, "token": "\u0120loaded", "merges": "\u0120load ed", "raw_count": 141640, "count": 141640, "decode_str": " loaded"} -{"id": 5234, "token": "\u0120switch", "merges": "\u0120sw itch", "raw_count": 127038, "count": 141645, "decode_str": " switch"} -{"id": 3440, "token": "\u0120music", "merges": "\u0120mus ic", "raw_count": 133675, "count": 141646, "decode_str": " music"} -{"id": 54553, "token": "\u00e9\u00a6\u012c", "merges": "\u00e9\u00a6 \u012c", "raw_count": 141656, "count": 141656, "decode_str": "\u998a"} -{"id": 14705, "token": "piece", "merges": "pie ce", "raw_count": 136265, "count": 141665, "decode_str": "piece"} -{"id": 49268, "token": "632", "merges": "6 32", "raw_count": 141685, "count": 141685, "decode_str": "632"} -{"id": 25435, "token": "HB", "merges": "H B", "raw_count": 141726, "count": 141726, "decode_str": "HB"} -{"id": 3278, "token": "icense", "merges": "ic ense", "raw_count": 1432, "count": 141734, "decode_str": "icense"} -{"id": 6837, "token": "cup", "merges": "c up", "raw_count": 83013, "count": 141749, "decode_str": "cup"} -{"id": 5793, "token": "\u0120chemical", "merges": "\u0120chem ical", "raw_count": 90647, "count": 141785, "decode_str": " chemical"} -{"id": 47487, "token": "tick", "merges": "t ick", "raw_count": 141788, "count": 141788, "decode_str": "tick"} -{"id": 5780, "token": "\u0120remaining", "merges": "\u0120rem aining", "raw_count": 141795, "count": 141795, "decode_str": " remaining"} -{"id": 9724, "token": "alty", "merges": "al ty", "raw_count": 64444, "count": 141798, "decode_str": "alty"} -{"id": 7363, "token": "\u0120scores", "merges": "\u0120sc ores", "raw_count": 141805, "count": 141805, "decode_str": " scores"} -{"id": 42640, "token": "513", "merges": "5 13", "raw_count": 141806, "count": 141806, "decode_str": "513"} -{"id": 13138, "token": "\u0120packet", "merges": "\u0120pack et", "raw_count": 141824, "count": 141824, "decode_str": " packet"} -{"id": 30516, "token": "FET", "merges": "F ET", "raw_count": 141888, "count": 141888, "decode_str": "FET"} -{"id": 15082, "token": "wen", "merges": "w en", "raw_count": 141145, "count": 141932, "decode_str": "wen"} -{"id": 36947, "token": "AJ", "merges": "A J", "raw_count": 141934, "count": 141934, "decode_str": "AJ"} -{"id": 4767, "token": "\u0120stated", "merges": "\u0120st ated", "raw_count": 141939, "count": 141939, "decode_str": " stated"} -{"id": 33296, "token": "culus", "merges": "cul us", "raw_count": 141953, "count": 141953, "decode_str": "culus"} -{"id": 3537, "token": "\u0120analy", "merges": "\u0120anal y", "raw_count": 9508, "count": 141961, "decode_str": " analy"} -{"id": 22823, "token": "AIL", "merges": "A IL", "raw_count": 141961, "count": 141961, "decode_str": "AIL"} -{"id": 50564, "token": "\u00e4\u00bd\u00a5", "merges": "\u00e4\u00bd \u00a5", "raw_count": 141969, "count": 141969, "decode_str": "\u4f65"} -{"id": 44472, "token": "django", "merges": "d jango", "raw_count": 141975, "count": 141975, "decode_str": "django"} -{"id": 49309, "token": "exclude", "merges": "ex clude", "raw_count": 142021, "count": 142021, "decode_str": "exclude"} -{"id": 4925, "token": "\u0120reached", "merges": "\u0120re ached", "raw_count": 142027, "count": 142027, "decode_str": " reached"} -{"id": 7093, "token": "Your", "merges": "Y our", "raw_count": 142032, "count": 142032, "decode_str": "Your"} -{"id": 4178, "token": "\u0120resid", "merges": "\u0120res id", "raw_count": 10323, "count": 142059, "decode_str": " resid"} -{"id": 20067, "token": "Inf", "merges": "In f", "raw_count": 142075, "count": 142075, "decode_str": "Inf"} -{"id": 4974, "token": "\u0120Sub", "merges": "\u0120S ub", "raw_count": 129571, "count": 142140, "decode_str": " Sub"} -{"id": 8753, "token": "\u0120seg", "merges": "\u0120se g", "raw_count": 79717, "count": 142141, "decode_str": " seg"} -{"id": 15952, "token": "\u0120initiative", "merges": "\u0120initi ative", "raw_count": 142157, "count": 142157, "decode_str": " initiative"} -{"id": 11388, "token": "!'", "merges": "! '", "raw_count": 142160, "count": 142160, "decode_str": "!'"} -{"id": 36516, "token": "Digital", "merges": "Dig ital", "raw_count": 142173, "count": 142173, "decode_str": "Digital"} -{"id": 21229, "token": "\u0120endpoint", "merges": "\u0120end point", "raw_count": 142186, "count": 142186, "decode_str": " endpoint"} -{"id": 43200, "token": "dense", "merges": "d ense", "raw_count": 142206, "count": 142206, "decode_str": "dense"} -{"id": 18828, "token": "DEBUG", "merges": "DE BUG", "raw_count": 142230, "count": 142230, "decode_str": "DEBUG"} -{"id": 14044, "token": "Conf", "merges": "Con f", "raw_count": 95548, "count": 142245, "decode_str": "Conf"} -{"id": 4727, "token": "Supp", "merges": "S upp", "raw_count": 70026, "count": 142247, "decode_str": "Supp"} -{"id": 52791, "token": "\u00e7\u012c\u0126", "merges": "\u00e7\u012c \u0126", "raw_count": 142284, "count": 142284, "decode_str": "\u7284"} -{"id": 54260, "token": "\u00e9\u0137\u013d", "merges": "\u00e9\u0137 \u013d", "raw_count": 142306, "count": 142306, "decode_str": "\u955b"} -{"id": 37257, "token": "NBC", "merges": "N BC", "raw_count": 142331, "count": 142331, "decode_str": "NBC"} -{"id": 11482, "token": "\u0120decor", "merges": "\u0120dec or", "raw_count": 94773, "count": 142336, "decode_str": " decor"} -{"id": 7478, "token": "\u0120recognized", "merges": "\u0120recogn ized", "raw_count": 142350, "count": 142350, "decode_str": " recognized"} -{"id": 41312, "token": "Mind", "merges": "M ind", "raw_count": 142390, "count": 142390, "decode_str": "Mind"} -{"id": 38478, "token": "Shift", "merges": "Sh ift", "raw_count": 142429, "count": 142429, "decode_str": "Shift"} -{"id": 6575, "token": "ando", "merges": "and o", "raw_count": 138022, "count": 142433, "decode_str": "ando"} -{"id": 33699, "token": "failure", "merges": "f ailure", "raw_count": 142461, "count": 142461, "decode_str": "failure"} -{"id": 53785, "token": "\u00e8\u00ae\u00a7", "merges": "\u00e8\u00ae \u00a7", "raw_count": 142592, "count": 142592, "decode_str": "\u8ba7"} -{"id": 51155, "token": "\u00e5\u013d\u0139", "merges": "\u00e5\u013d \u0139", "raw_count": 142644, "count": 142644, "decode_str": "\u56d7"} -{"id": 3073, "token": "> ", "merges": "? >", "raw_count": 149289, "count": 149289, "decode_str": "?>"} -{"id": 5859, "token": "\u0120science", "merges": "\u0120sc ience", "raw_count": 149497, "count": 149497, "decode_str": " science"} -{"id": 52352, "token": "\u00e6\u00a7\u0130", "merges": "\u00e6\u00a7 \u0130", "raw_count": 149514, "count": 149514, "decode_str": "\u69ce"} -{"id": 18570, "token": "adjust", "merges": "ad just", "raw_count": 126473, "count": 149571, "decode_str": "adjust"} -{"id": 10813, "token": "\u0120Init", "merges": "\u0120In it", "raw_count": 30082, "count": 149586, "decode_str": " Init"} -{"id": 20330, "token": "Directory", "merges": "D irectory", "raw_count": 149641, "count": 149641, "decode_str": "Directory"} -{"id": 26366, "token": "Wal", "merges": "W al", "raw_count": 149674, "count": 149674, "decode_str": "Wal"} -{"id": 5944, "token": "\u0120corpor", "merges": "\u0120cor por", "raw_count": 15357, "count": 149704, "decode_str": " corpor"} -{"id": 50618, "token": "\u00e5\u0122\u012e", "merges": "\u00e5\u0122 \u012e", "raw_count": 149807, "count": 149807, "decode_str": "\u500c"} -{"id": 6335, "token": "\u0120library", "merges": "\u0120l ibrary", "raw_count": 149811, "count": 149811, "decode_str": " library"} -{"id": 4723, "token": "\u0120damage", "merges": "\u0120dam age", "raw_count": 149858, "count": 149858, "decode_str": " damage"} -{"id": 13250, "token": "\u0120factory", "merges": "\u0120fact ory", "raw_count": 149896, "count": 149896, "decode_str": " factory"} -{"id": 8063, "token": "\u0120principle", "merges": "\u0120princ iple", "raw_count": 149906, "count": 149906, "decode_str": " principle"} -{"id": 30769, "token": "Andrew", "merges": "And rew", "raw_count": 149933, "count": 149933, "decode_str": "Andrew"} -{"id": 6368, "token": "edy", "merges": "ed y", "raw_count": 97505, "count": 149935, "decode_str": "edy"} -{"id": 33333, "token": "576", "merges": "57 6", "raw_count": 149938, "count": 149938, "decode_str": "576"} -{"id": 52419, "token": "\u00e6\u00ae\u0135", "merges": "\u00e6\u00ae \u0135", "raw_count": 149950, "count": 149950, "decode_str": "\u6b93"} -{"id": 30608, "token": "yz", "merges": "y z", "raw_count": 150020, "count": 150020, "decode_str": "yz"} -{"id": 5652, "token": "ferent", "merges": "fe rent", "raw_count": 9650, "count": 150033, "decode_str": "ferent"} -{"id": 8292, "token": "pert", "merges": "per t", "raw_count": 120404, "count": 150056, "decode_str": "pert"} -{"id": 24143, "token": "Mir", "merges": "M ir", "raw_count": 113695, "count": 150144, "decode_str": "Mir"} -{"id": 8213, "token": "\u0120matters", "merges": "\u0120mat ters", "raw_count": 150155, "count": 150155, "decode_str": " matters"} -{"id": 31436, "token": "672", "merges": "67 2", "raw_count": 150161, "count": 150161, "decode_str": "672"} -{"id": 52793, "token": "\u00e7\u012c\u012f", "merges": "\u00e7\u012c \u012f", "raw_count": 150165, "count": 150165, "decode_str": "\u728d"} -{"id": 7774, "token": "\u0120articles", "merges": "\u0120art icles", "raw_count": 150222, "count": 150222, "decode_str": " articles"} -{"id": 20814, "token": "rypted", "merges": "rypt ed", "raw_count": 112687, "count": 150279, "decode_str": "rypted"} -{"id": 41042, "token": "threads", "merges": "thread s", "raw_count": 150295, "count": 150295, "decode_str": "threads"} -{"id": 9354, "token": "\u01201994", "merges": "\u0120199 4", "raw_count": 150300, "count": 150300, "decode_str": " 1994"} -{"id": 5557, "token": "\u0120rout", "merges": "\u0120r out", "raw_count": 3212, "count": 150301, "decode_str": " rout"} -{"id": 30905, "token": "\u0120repo", "merges": "\u0120rep o", "raw_count": 150318, "count": 150318, "decode_str": " repo"} -{"id": 18113, "token": "loat", "merges": "lo at", "raw_count": 2903, "count": 150324, "decode_str": "loat"} -{"id": 18848, "token": "rob", "merges": "ro b", "raw_count": 150357, "count": 150357, "decode_str": "rob"} -{"id": 43301, "token": "615", "merges": "6 15", "raw_count": 150374, "count": 150374, "decode_str": "615"} -{"id": 6654, "token": "\u0120balance", "merges": "\u0120bal ance", "raw_count": 150386, "count": 150386, "decode_str": " balance"} -{"id": 25238, "token": "646", "merges": "64 6", "raw_count": 150406, "count": 150406, "decode_str": "646"} -{"id": 42491, "token": "\"+", "merges": "\" +", "raw_count": 150422, "count": 150422, "decode_str": "\"+"} -{"id": 19391, "token": "supported", "merges": "supp orted", "raw_count": 132581, "count": 150441, "decode_str": "supported"} -{"id": 12900, "token": "FLAG", "merges": "FL AG", "raw_count": 41035, "count": 150483, "decode_str": "FLAG"} -{"id": 2494, "token": "\u0120micro", "merges": "\u0120m icro", "raw_count": 123291, "count": 150520, "decode_str": " micro"} -{"id": 3698, "token": "\u0120watch", "merges": "\u0120w atch", "raw_count": 122454, "count": 150546, "decode_str": " watch"} -{"id": 18782, "token": "onda", "merges": "ond a", "raw_count": 150048, "count": 150555, "decode_str": "onda"} -{"id": 9934, "token": "\u012068", "merges": "\u01206 8", "raw_count": 150558, "count": 150558, "decode_str": " 68"} -{"id": 8130, "token": "\u0120strategies", "merges": "\u0120strateg ies", "raw_count": 150582, "count": 150582, "decode_str": " strategies"} -{"id": 5482, "token": "\u0120solutions", "merges": "\u0120sol utions", "raw_count": 150588, "count": 150588, "decode_str": " solutions"} -{"id": 21528, "token": "take", "merges": "t ake", "raw_count": 150603, "count": 150603, "decode_str": "take"} -{"id": 4166, "token": "\u0120oil", "merges": "\u0120o il", "raw_count": 150604, "count": 150604, "decode_str": " oil"} -{"id": 20900, "token": "Storage", "merges": "St orage", "raw_count": 150619, "count": 150619, "decode_str": "Storage"} -{"id": 39649, "token": "612", "merges": "6 12", "raw_count": 150784, "count": 150784, "decode_str": "612"} -{"id": 30072, "token": "391", "merges": "39 1", "raw_count": 150819, "count": 150819, "decode_str": "391"} -{"id": 3745, "token": "\u0120ability", "merges": "\u0120ab ility", "raw_count": 150861, "count": 150861, "decode_str": " ability"} -{"id": 5152, "token": "\u0120bul", "merges": "\u0120b ul", "raw_count": 42607, "count": 150861, "decode_str": " bul"} -{"id": 9199, "token": "\u0120110", "merges": "\u01201 10", "raw_count": 150882, "count": 150882, "decode_str": " 110"} -{"id": 2538, "token": "\u0120effects", "merges": "\u0120effect s", "raw_count": 150885, "count": 150885, "decode_str": " effects"} -{"id": 4581, "token": "\u0120closed", "merges": "\u0120cl osed", "raw_count": 150919, "count": 150919, "decode_str": " closed"} -{"id": 18743, "token": "integer", "merges": "inte ger", "raw_count": 150976, "count": 150976, "decode_str": "integer"} -{"id": 26403, "token": "Shape", "merges": "Sh ape", "raw_count": 150983, "count": 150983, "decode_str": "Shape"} -{"id": 26236, "token": "0025", "merges": "00 25", "raw_count": 151002, "count": 151002, "decode_str": "0025"} -{"id": 7581, "token": "\u0120conven", "merges": "\u0120con ven", "raw_count": 72220, "count": 151006, "decode_str": " conven"} -{"id": 10759, "token": "Her", "merges": "H er", "raw_count": 151084, "count": 151084, "decode_str": "Her"} -{"id": 5401, "token": "arth", "merges": "ar th", "raw_count": 58981, "count": 151095, "decode_str": "arth"} -{"id": 16850, "token": "Hash", "merges": "H ash", "raw_count": 151104, "count": 151104, "decode_str": "Hash"} -{"id": 33290, "token": "permission", "merges": "per mission", "raw_count": 151119, "count": 151119, "decode_str": "permission"} -{"id": 4504, "token": "irmed", "merges": "ir med", "raw_count": 40010, "count": 151119, "decode_str": "irmed"} -{"id": 13784, "token": "closed", "merges": "cl osed", "raw_count": 141157, "count": 151139, "decode_str": "closed"} -{"id": 8362, "token": "\u0120funding", "merges": "\u0120fund ing", "raw_count": 151140, "count": 151140, "decode_str": " funding"} -{"id": 17865, "token": "\u00e2\u0137", "merges": "\u00e2 \u0137", "raw_count": 34693, "count": 151174, "decode_str": "\ufffd"} -{"id": 26561, "token": "Zero", "merges": "Z ero", "raw_count": 151186, "count": 151186, "decode_str": "Zero"} -{"id": 34263, "token": "multiple", "merges": "mult iple", "raw_count": 151219, "count": 151219, "decode_str": "multiple"} -{"id": 7025, "token": "icted", "merges": "ict ed", "raw_count": 123253, "count": 151232, "decode_str": "icted"} -{"id": 26641, "token": "\u0120initialize", "merges": "\u0120initial ize", "raw_count": 151243, "count": 151243, "decode_str": " initialize"} -{"id": 40540, "token": "precision", "merges": "prec ision", "raw_count": 151249, "count": 151249, "decode_str": "precision"} -{"id": 25843, "token": "Music", "merges": "Mus ic", "raw_count": 151285, "count": 151285, "decode_str": "Music"} -{"id": 15916, "token": "ardo", "merges": "ard o", "raw_count": 151285, "count": 151285, "decode_str": "ardo"} -{"id": 10835, "token": "alloc", "merges": "all oc", "raw_count": 98235, "count": 151296, "decode_str": "alloc"} -{"id": 33491, "token": "sources", "merges": "s ources", "raw_count": 151300, "count": 151300, "decode_str": "sources"} -{"id": 16285, "token": "mount", "merges": "m ount", "raw_count": 138296, "count": 151330, "decode_str": "mount"} -{"id": 53061, "token": "\u00e7\u0142\u00a3", "merges": "\u00e7\u0142 \u00a3", "raw_count": 151356, "count": 151356, "decode_str": "\u7823"} -{"id": 4704, "token": "\u0120ready", "merges": "\u0120read y", "raw_count": 151362, "count": 151362, "decode_str": " ready"} -{"id": 4988, "token": "amin", "merges": "am in", "raw_count": 85418, "count": 151377, "decode_str": "amin"} -{"id": 7173, "token": "iot", "merges": "i ot", "raw_count": 142104, "count": 151386, "decode_str": "iot"} -{"id": 11735, "token": "Deb", "merges": "D eb", "raw_count": 75333, "count": 151428, "decode_str": "Deb"} -{"id": 16956, "token": "Option", "merges": "O ption", "raw_count": 151431, "count": 151431, "decode_str": "Option"} -{"id": 24334, "token": "\u0120dst", "merges": "\u0120d st", "raw_count": 151450, "count": 151450, "decode_str": " dst"} -{"id": 24902, "token": "possible", "merges": "pos sible", "raw_count": 151463, "count": 151463, "decode_str": "possible"} -{"id": 1941, "token": "\u0120evidence", "merges": "\u0120ev idence", "raw_count": 151521, "count": 151521, "decode_str": " evidence"} -{"id": 22568, "token": "Loader", "merges": "Load er", "raw_count": 151559, "count": 151559, "decode_str": "Loader"} -{"id": 30262, "token": "FTA", "merges": "FT A", "raw_count": 151426, "count": 151611, "decode_str": "FTA"} -{"id": 11592, "token": "Non", "merges": "N on", "raw_count": 151643, "count": 151643, "decode_str": "Non"} -{"id": 49700, "token": "\u0120\"--", "merges": "\u0120\" --", "raw_count": 151656, "count": 151656, "decode_str": " \"--"} -{"id": 54300, "token": "\u00e9\u013a\u0137", "merges": "\u00e9\u013a \u0137", "raw_count": 151660, "count": 151660, "decode_str": "\u9615"} -{"id": 44103, "token": "initialize", "merges": "init ialize", "raw_count": 151661, "count": 151661, "decode_str": "initialize"} -{"id": 11244, "token": "Use", "merges": "U se", "raw_count": 151677, "count": 151677, "decode_str": "Use"} -{"id": 10031, "token": "\u0120Model", "merges": "\u0120Mod el", "raw_count": 151754, "count": 151754, "decode_str": " Model"} -{"id": 26910, "token": "()).", "merges": "() ).", "raw_count": 151786, "count": 151786, "decode_str": "())."} -{"id": 754, "token": "\u0120He", "merges": "\u0120H e", "raw_count": 33161, "count": 151791, "decode_str": " He"} -{"id": 7036, "token": "\u0120conc", "merges": "\u0120con c", "raw_count": 56570, "count": 151814, "decode_str": " conc"} -{"id": 2004, "token": "though", "merges": "th ough", "raw_count": 28438, "count": 151815, "decode_str": "though"} -{"id": 22947, "token": "oct", "merges": "o ct", "raw_count": 151854, "count": 151854, "decode_str": "oct"} -{"id": 5170, "token": "\u0120upper", "merges": "\u0120upp er", "raw_count": 151876, "count": 151876, "decode_str": " upper"} -{"id": 13088, "token": "echo", "merges": "e cho", "raw_count": 151890, "count": 151890, "decode_str": "echo"} -{"id": 33297, "token": "651", "merges": "65 1", "raw_count": 151914, "count": 151914, "decode_str": "651"} -{"id": 13720, "token": "Serv", "merges": "S erv", "raw_count": 48501, "count": 151935, "decode_str": "Serv"} -{"id": 15170, "token": "ikipedia", "merges": "ikip edia", "raw_count": 108328, "count": 151936, "decode_str": "ikipedia"} -{"id": 45978, "token": "backup", "merges": "back up", "raw_count": 151942, "count": 151942, "decode_str": "backup"} -{"id": 23660, "token": "girl", "merges": "g irl", "raw_count": 151949, "count": 151949, "decode_str": "girl"} -{"id": 10338, "token": "\u0120Make", "merges": "\u0120M ake", "raw_count": 151954, "count": 151954, "decode_str": " Make"} -{"id": 3960, "token": "\u0120altern", "merges": "\u0120al tern", "raw_count": 7271, "count": 151960, "decode_str": " altern"} -{"id": 6153, "token": "\u0120creating", "merges": "\u0120creat ing", "raw_count": 151976, "count": 151976, "decode_str": " creating"} -{"id": 27901, "token": "VL", "merges": "V L", "raw_count": 151999, "count": 151999, "decode_str": "VL"} -{"id": 15668, "token": "Types", "merges": "Typ es", "raw_count": 152007, "count": 152007, "decode_str": "Types"} -{"id": 5369, "token": "\u0120unf", "merges": "\u0120un f", "raw_count": 100036, "count": 152034, "decode_str": " unf"} -{"id": 6191, "token": "\u0120mes", "merges": "\u0120m es", "raw_count": 44555, "count": 152058, "decode_str": " mes"} -{"id": 4635, "token": "chi", "merges": "ch i", "raw_count": 152073, "count": 152073, "decode_str": "chi"} -{"id": 54259, "token": "\u00e9\u0137\u0139", "merges": "\u00e9\u0137 \u0139", "raw_count": 152084, "count": 152084, "decode_str": "\u9557"} -{"id": 17556, "token": "tech", "merges": "te ch", "raw_count": 152128, "count": 152128, "decode_str": "tech"} -{"id": 11825, "token": "ika", "merges": "ik a", "raw_count": 152142, "count": 152142, "decode_str": "ika"} -{"id": 45774, "token": "636", "merges": "6 36", "raw_count": 152148, "count": 152148, "decode_str": "636"} -{"id": 8930, "token": "\u0120island", "merges": "\u0120is land", "raw_count": 152195, "count": 152195, "decode_str": " island"} -{"id": 10193, "token": "arters", "merges": "ar ters", "raw_count": 2236, "count": 152223, "decode_str": "arters"} -{"id": 15684, "token": "require", "merges": "requ ire", "raw_count": 152271, "count": 152271, "decode_str": "require"} -{"id": 51273, "token": "\u00e5\u00a3\u0128", "merges": "\u00e5\u00a3 \u0128", "raw_count": 152283, "count": 152283, "decode_str": "\u58c6"} -{"id": 20357, "token": "Low", "merges": "L ow", "raw_count": 152319, "count": 152319, "decode_str": "Low"} -{"id": 22708, "token": "Cross", "merges": "C ross", "raw_count": 152343, "count": 152343, "decode_str": "Cross"} -{"id": 20505, "token": "\u0120ds", "merges": "\u0120d s", "raw_count": 152349, "count": 152349, "decode_str": " ds"} -{"id": 5763, "token": "\u0120exercise", "merges": "\u0120exerc ise", "raw_count": 152354, "count": 152354, "decode_str": " exercise"} -{"id": 5373, "token": "\u0120benefits", "merges": "\u0120benef its", "raw_count": 152506, "count": 152506, "decode_str": " benefits"} -{"id": 17074, "token": "awn", "merges": "a wn", "raw_count": 118561, "count": 152576, "decode_str": "awn"} -{"id": 17796, "token": "\u012006", "merges": "\u01200 6", "raw_count": 152589, "count": 152589, "decode_str": " 06"} -{"id": 3112, "token": "\u0120assum", "merges": "\u0120ass um", "raw_count": 568, "count": 152592, "decode_str": " assum"} -{"id": 17667, "token": "Close", "merges": "Cl ose", "raw_count": 152607, "count": 152607, "decode_str": "Close"} -{"id": 6378, "token": "\u0120purposes", "merges": "\u0120pur poses", "raw_count": 152615, "count": 152615, "decode_str": " purposes"} -{"id": 9661, "token": "acer", "merges": "ac er", "raw_count": 118005, "count": 152619, "decode_str": "acer"} -{"id": 14981, "token": "PF", "merges": "P F", "raw_count": 152626, "count": 152626, "decode_str": "PF"} -{"id": 32994, "token": "Board", "merges": "Bo ard", "raw_count": 152628, "count": 152628, "decode_str": "Board"} -{"id": 6253, "token": "\u0120largest", "merges": "\u0120lar gest", "raw_count": 152736, "count": 152736, "decode_str": " largest"} -{"id": 4583, "token": "\u0120overall", "merges": "\u0120over all", "raw_count": 152751, "count": 152751, "decode_str": " overall"} -{"id": 2819, "token": "\u0120looking", "merges": "\u0120look ing", "raw_count": 152764, "count": 152764, "decode_str": " looking"} -{"id": 19017, "token": "complex", "merges": "comple x", "raw_count": 152785, "count": 152785, "decode_str": "complex"} -{"id": 17921, "token": "library", "merges": "l ibrary", "raw_count": 152796, "count": 152796, "decode_str": "library"} -{"id": 21315, "token": "icket", "merges": "ick et", "raw_count": 46860, "count": 152840, "decode_str": "icket"} -{"id": 3517, "token": "\u0120soon", "merges": "\u0120so on", "raw_count": 144153, "count": 152847, "decode_str": " soon"} -{"id": 24348, "token": "Ba", "merges": "B a", "raw_count": 152860, "count": 152860, "decode_str": "Ba"} -{"id": 4885, "token": "arest", "merges": "are st", "raw_count": 101833, "count": 152874, "decode_str": "arest"} -{"id": 14417, "token": "ariance", "merges": "ari ance", "raw_count": 124083, "count": 152896, "decode_str": "ariance"} -{"id": 5701, "token": "\u0120comments", "merges": "\u0120com ments", "raw_count": 152909, "count": 152909, "decode_str": " comments"} -{"id": 25404, "token": "\u0120\u00c3\u00a2", "merges": "\u0120\u00c3 \u00a2", "raw_count": 152924, "count": 152924, "decode_str": " \u00e2"} -{"id": 8201, "token": "ipping", "merges": "i pping", "raw_count": 85482, "count": 152941, "decode_str": "ipping"} -{"id": 27524, "token": "Ly", "merges": "L y", "raw_count": 153016, "count": 153016, "decode_str": "Ly"} -{"id": 37376, "token": "Eric", "merges": "E ric", "raw_count": 153019, "count": 153019, "decode_str": "Eric"} -{"id": 10383, "token": "about", "merges": "ab out", "raw_count": 153027, "count": 153027, "decode_str": "about"} -{"id": 6168, "token": "het", "merges": "he t", "raw_count": 111806, "count": 153041, "decode_str": "het"} -{"id": 4070, "token": "\u0120hon", "merges": "\u0120h on", "raw_count": 22673, "count": 153100, "decode_str": " hon"} -{"id": 18711, "token": "direct", "merges": "d irect", "raw_count": 153155, "count": 153155, "decode_str": "direct"} -{"id": 19158, "token": "Syn", "merges": "S yn", "raw_count": 110139, "count": 153189, "decode_str": "Syn"} -{"id": 32282, "token": "483", "merges": "48 3", "raw_count": 153204, "count": 153204, "decode_str": "483"} -{"id": 54413, "token": "\u00e9\u013f\u00bc", "merges": "\u00e9\u013f \u00bc", "raw_count": 153227, "count": 153227, "decode_str": "\u977c"} -{"id": 45141, "token": "evaluate", "merges": "eval uate", "raw_count": 153250, "count": 153250, "decode_str": "evaluate"} -{"id": 25837, "token": "fw", "merges": "f w", "raw_count": 153251, "count": 153251, "decode_str": "fw"} -{"id": 9840, "token": "\u0120beta", "merges": "\u0120bet a", "raw_count": 153270, "count": 153270, "decode_str": " beta"} -{"id": 20790, "token": "paper", "merges": "pa per", "raw_count": 153283, "count": 153283, "decode_str": "paper"} -{"id": 8891, "token": "\u0120crisis", "merges": "\u0120cris is", "raw_count": 153301, "count": 153301, "decode_str": " crisis"} -{"id": 5004, "token": "\u0120bottom", "merges": "\u0120bott om", "raw_count": 153303, "count": 153303, "decode_str": " bottom"} -{"id": 25016, "token": "modified", "merges": "mod ified", "raw_count": 153305, "count": 153305, "decode_str": "modified"} -{"id": 15007, "token": "wave", "merges": "w ave", "raw_count": 153329, "count": 153329, "decode_str": "wave"} -{"id": 23684, "token": "William", "merges": "Willi am", "raw_count": 153334, "count": 153334, "decode_str": "William"} -{"id": 14931, "token": "\u00f0\u0141", "merges": "\u00f0 \u0141", "raw_count": 132321, "count": 153374, "decode_str": "\ufffd"} -{"id": 21462, "token": "raints", "merges": "raint s", "raw_count": 139152, "count": 153396, "decode_str": "raints"} -{"id": 6477, "token": "ructions", "merges": "ru ctions", "raw_count": 77800, "count": 153406, "decode_str": "ructions"} -{"id": 19227, "token": "\u0120terrorism", "merges": "\u0120terror ism", "raw_count": 153412, "count": 153412, "decode_str": " terrorism"} -{"id": 8693, "token": "Last", "merges": "L ast", "raw_count": 153247, "count": 153429, "decode_str": "Last"} -{"id": 29483, "token": "addition", "merges": "ad dition", "raw_count": 46190, "count": 153506, "decode_str": "addition"} -{"id": 7472, "token": "\u0120evaluate", "merges": "\u0120evalu ate", "raw_count": 153530, "count": 153530, "decode_str": " evaluate"} -{"id": 18794, "token": "\u0120kingdom", "merges": "\u0120king dom", "raw_count": 153533, "count": 153533, "decode_str": " kingdom"} -{"id": 10442, "token": "aba", "merges": "ab a", "raw_count": 113220, "count": 153540, "decode_str": "aba"} -{"id": 18229, "token": "Callback", "merges": "Call back", "raw_count": 153590, "count": 153590, "decode_str": "Callback"} -{"id": 4824, "token": "\u0120carried", "merges": "\u0120car ried", "raw_count": 153618, "count": 153618, "decode_str": " carried"} -{"id": 3101, "token": "\u0120mother", "merges": "\u0120m other", "raw_count": 130429, "count": 153628, "decode_str": " mother"} -{"id": 10709, "token": "\u0120tur", "merges": "\u0120t ur", "raw_count": 78530, "count": 153632, "decode_str": " tur"} -{"id": 5101, "token": "\u0120sun", "merges": "\u0120s un", "raw_count": 127174, "count": 153652, "decode_str": " sun"} -{"id": 12846, "token": "regular", "merges": "reg ular", "raw_count": 132694, "count": 153654, "decode_str": "regular"} -{"id": 23473, "token": "\u0120keyword", "merges": "\u0120key word", "raw_count": 153717, "count": 153717, "decode_str": " keyword"} -{"id": 7983, "token": "onym", "merges": "on ym", "raw_count": 44636, "count": 153721, "decode_str": "onym"} -{"id": 2553, "token": "\u0120surface", "merges": "\u0120sur face", "raw_count": 153741, "count": 153741, "decode_str": " surface"} -{"id": 8935, "token": "\u0120west", "merges": "\u0120w est", "raw_count": 153741, "count": 153741, "decode_str": " west"} -{"id": 31213, "token": "453", "merges": "45 3", "raw_count": 153813, "count": 153813, "decode_str": "453"} -{"id": 29317, "token": "LAB", "merges": "L AB", "raw_count": 153828, "count": 153828, "decode_str": "LAB"} -{"id": 7181, "token": "\u0120obser", "merges": "\u0120ob ser", "raw_count": 247, "count": 153848, "decode_str": " obser"} -{"id": 39754, "token": "marker", "merges": "mark er", "raw_count": 153916, "count": 153916, "decode_str": "marker"} -{"id": 10368, "token": "porary", "merges": "por ary", "raw_count": 110763, "count": 153923, "decode_str": "porary"} -{"id": 4542, "token": "asm", "merges": "as m", "raw_count": 115934, "count": 153944, "decode_str": "asm"} -{"id": 22477, "token": "archive", "merges": "arch ive", "raw_count": 153953, "count": 153953, "decode_str": "archive"} -{"id": 26234, "token": "\u0120indent", "merges": "\u0120ind ent", "raw_count": 153997, "count": 153997, "decode_str": " indent"} -{"id": 7494, "token": "\u0120displ", "merges": "\u0120dis pl", "raw_count": 6461, "count": 154026, "decode_str": " displ"} -{"id": 43274, "token": "prompt", "merges": "prom pt", "raw_count": 154079, "count": 154079, "decode_str": "prompt"} -{"id": 52944, "token": "\u00e7\u0139\u00a8", "merges": "\u00e7\u0139 \u00a8", "raw_count": 154094, "count": 154094, "decode_str": "\u75e8"} -{"id": 16471, "token": "wp", "merges": "w p", "raw_count": 154132, "count": 154132, "decode_str": "wp"} -{"id": 5845, "token": "uing", "merges": "u ing", "raw_count": 27201, "count": 154177, "decode_str": "uing"} -{"id": 24227, "token": "CAT", "merges": "C AT", "raw_count": 154214, "count": 154214, "decode_str": "CAT"} -{"id": 47558, "token": "keywords", "merges": "key words", "raw_count": 154237, "count": 154237, "decode_str": "keywords"} -{"id": 4190, "token": "reme", "merges": "re me", "raw_count": 56800, "count": 154331, "decode_str": "reme"} -{"id": 4189, "token": "\u0120\u00d1\u0123", "merges": "\u0120 \u00d1\u0123", "raw_count": 76265, "count": 154336, "decode_str": " \u0441"} -{"id": 12270, "token": "backs", "merges": "back s", "raw_count": 152671, "count": 154403, "decode_str": "backs"} -{"id": 29167, "token": "proj", "merges": "pro j", "raw_count": 154426, "count": 154426, "decode_str": "proj"} -{"id": 31780, "token": "Validation", "merges": "Valid ation", "raw_count": 154439, "count": 154439, "decode_str": "Validation"} -{"id": 52837, "token": "\u00e7\u0131\u00ae", "merges": "\u00e7\u0131 \u00ae", "raw_count": 154468, "count": 154468, "decode_str": "\u73ee"} -{"id": 24787, "token": "tons", "merges": "t ons", "raw_count": 40586, "count": 154471, "decode_str": "tons"} -{"id": 8194, "token": "\u0120sched", "merges": "\u0120sc hed", "raw_count": 65721, "count": 154486, "decode_str": " sched"} -{"id": 12451, "token": "aya", "merges": "ay a", "raw_count": 154552, "count": 154552, "decode_str": "aya"} -{"id": 12892, "token": "oro", "merges": "or o", "raw_count": 152831, "count": 154553, "decode_str": "oro"} -{"id": 40107, "token": "ARA", "merges": "AR A", "raw_count": 154561, "count": 154561, "decode_str": "ARA"} -{"id": 16658, "token": "tocol", "merges": "t ocol", "raw_count": 507, "count": 154584, "decode_str": "tocol"} -{"id": 18529, "token": "EEE", "merges": "EE E", "raw_count": 19319, "count": 154609, "decode_str": "EEE"} -{"id": 34194, "token": ";&#", "merges": "; &#", "raw_count": 154613, "count": 154613, "decode_str": ";&#"} -{"id": 24649, "token": "ority", "merges": "or ity", "raw_count": 8054, "count": 154660, "decode_str": "ority"} -{"id": 9039, "token": "\u0120calc", "merges": "\u0120cal c", "raw_count": 147559, "count": 154705, "decode_str": " calc"} -{"id": 7888, "token": "\u0120communities", "merges": "\u0120commun ities", "raw_count": 154740, "count": 154740, "decode_str": " communities"} -{"id": 21676, "token": "optional", "merges": "opt ional", "raw_count": 154745, "count": 154745, "decode_str": "optional"} -{"id": 32631, "token": "414", "merges": "4 14", "raw_count": 154746, "count": 154746, "decode_str": "414"} -{"id": 20987, "token": "contract", "merges": "cont ract", "raw_count": 145487, "count": 154763, "decode_str": "contract"} -{"id": 5876, "token": "\u0120affected", "merges": "\u0120affect ed", "raw_count": 154774, "count": 154774, "decode_str": " affected"} -{"id": 38100, "token": "=='", "merges": "== '", "raw_count": 154781, "count": 154781, "decode_str": "=='"} -{"id": 32162, "token": "GU", "merges": "G U", "raw_count": 154802, "count": 154802, "decode_str": "GU"} -{"id": 7846, "token": "\u0120ast", "merges": "\u0120a st", "raw_count": 150020, "count": 154914, "decode_str": " ast"} -{"id": 48219, "token": "521", "merges": "5 21", "raw_count": 154921, "count": 154921, "decode_str": "521"} -{"id": 9330, "token": "\u012085", "merges": "\u01208 5", "raw_count": 154931, "count": 154931, "decode_str": " 85"} -{"id": 14253, "token": "RR", "merges": "R R", "raw_count": 154950, "count": 154950, "decode_str": "RR"} -{"id": 53373, "token": "\u00e7\u00bb\u00bb", "merges": "\u00e7\u00bb \u00bb", "raw_count": 154952, "count": 154952, "decode_str": "\u7efb"} -{"id": 8298, "token": "bridge", "merges": "br idge", "raw_count": 111103, "count": 154981, "decode_str": "bridge"} -{"id": 16123, "token": "wiki", "merges": "w iki", "raw_count": 155004, "count": 155004, "decode_str": "wiki"} -{"id": 14279, "token": "DW", "merges": "D W", "raw_count": 155022, "count": 155022, "decode_str": "DW"} -{"id": 42996, "token": "authentic", "merges": "aut hentic", "raw_count": 155023, "count": 155023, "decode_str": "authentic"} -{"id": 4021, "token": "\u0120double", "merges": "\u0120dou ble", "raw_count": 155058, "count": 155058, "decode_str": " double"} -{"id": 51084, "token": "\u00e5\u0137\u012b", "merges": "\u00e5\u0137 \u012b", "raw_count": 155109, "count": 155109, "decode_str": "\u5549"} -{"id": 21678, "token": "processing", "merges": "process ing", "raw_count": 155132, "count": 155132, "decode_str": "processing"} -{"id": 11430, "token": "eh", "merges": "e h", "raw_count": 145052, "count": 155274, "decode_str": "eh"} -{"id": 15100, "token": "avor", "merges": "av or", "raw_count": 115074, "count": 155281, "decode_str": "avor"} -{"id": 16462, "token": "EF", "merges": "E F", "raw_count": 155311, "count": 155311, "decode_str": "EF"} -{"id": 38603, "token": "Nature", "merges": "N ature", "raw_count": 155312, "count": 155312, "decode_str": "Nature"} -{"id": 19480, "token": "food", "merges": "f ood", "raw_count": 144595, "count": 155317, "decode_str": "food"} -{"id": 38819, "token": "852", "merges": "85 2", "raw_count": 155357, "count": 155357, "decode_str": "852"} -{"id": 12289, "token": "redit", "merges": "red it", "raw_count": 7872, "count": 155384, "decode_str": "redit"} -{"id": 7778, "token": "charge", "merges": "char ge", "raw_count": 121914, "count": 155436, "decode_str": "charge"} -{"id": 23877, "token": "tot", "merges": "t ot", "raw_count": 155441, "count": 155441, "decode_str": "tot"} -{"id": 43272, "token": "flip", "merges": "fl ip", "raw_count": 155443, "count": 155443, "decode_str": "flip"} -{"id": 18968, "token": "Mor", "merges": "M or", "raw_count": 155545, "count": 155545, "decode_str": "Mor"} -{"id": 6484, "token": "antic", "merges": "ant ic", "raw_count": 120799, "count": 155623, "decode_str": "antic"} -{"id": 36814, "token": "903", "merges": "90 3", "raw_count": 155624, "count": 155624, "decode_str": "903"} -{"id": 6742, "token": "\u0120delivery", "merges": "\u0120del ivery", "raw_count": 155654, "count": 155654, "decode_str": " delivery"} -{"id": 4270, "token": "\u0120built", "merges": "\u0120bu ilt", "raw_count": 155673, "count": 155673, "decode_str": " built"} -{"id": 12433, "token": "\u0120buck", "merges": "\u0120bu ck", "raw_count": 10205, "count": 155719, "decode_str": " buck"} -{"id": 47704, "token": "quantity", "merges": "quant ity", "raw_count": 155722, "count": 155722, "decode_str": "quantity"} -{"id": 28927, "token": "804", "merges": "80 4", "raw_count": 155723, "count": 155723, "decode_str": "804"} -{"id": 15927, "token": "\u0120violations", "merges": "\u0120viol ations", "raw_count": 155727, "count": 155727, "decode_str": " violations"} -{"id": 43628, "token": "517", "merges": "5 17", "raw_count": 155766, "count": 155766, "decode_str": "517"} -{"id": 26521, "token": "Hold", "merges": "H old", "raw_count": 155768, "count": 155768, "decode_str": "Hold"} -{"id": 5667, "token": "\u0120essential", "merges": "\u0120ess ential", "raw_count": 155776, "count": 155776, "decode_str": " essential"} -{"id": 17853, "token": "Cond", "merges": "C ond", "raw_count": 82764, "count": 155780, "decode_str": "Cond"} -{"id": 4685, "token": "\u0120understanding", "merges": "\u0120understand ing", "raw_count": 155810, "count": 155810, "decode_str": " understanding"} -{"id": 5411, "token": "ifying", "merges": "ify ing", "raw_count": 87100, "count": 155819, "decode_str": "ifying"} -{"id": 21468, "token": "\u0120missions", "merges": "\u0120miss ions", "raw_count": 155896, "count": 155896, "decode_str": " missions"} -{"id": 40848, "token": "438", "merges": "4 38", "raw_count": 155897, "count": 155897, "decode_str": "438"} -{"id": 8902, "token": "abb", "merges": "ab b", "raw_count": 136170, "count": 155900, "decode_str": "abb"} -{"id": 7141, "token": "\u0120stored", "merges": "\u0120st ored", "raw_count": 155915, "count": 155915, "decode_str": " stored"} -{"id": 15486, "token": "\u0120agreements", "merges": "\u0120agre ements", "raw_count": 155936, "count": 155936, "decode_str": " agreements"} -{"id": 36584, "token": "TW", "merges": "T W", "raw_count": 155943, "count": 155943, "decode_str": "TW"} -{"id": 11875, "token": "Left", "merges": "Le ft", "raw_count": 155967, "count": 155967, "decode_str": "Left"} -{"id": 17505, "token": "gorithm", "merges": "gorith m", "raw_count": 1208, "count": 156011, "decode_str": "gorithm"} -{"id": 26756, "token": "GN", "merges": "G N", "raw_count": 156024, "count": 156024, "decode_str": "GN"} -{"id": 17964, "token": "Save", "merges": "S ave", "raw_count": 156054, "count": 156054, "decode_str": "Save"} -{"id": 11136, "token": "\u0120behalf", "merges": "\u0120beh alf", "raw_count": 156071, "count": 156071, "decode_str": " behalf"} -{"id": 25908, "token": "ollo", "merges": "oll o", "raw_count": 155255, "count": 156071, "decode_str": "ollo"} -{"id": 19104, "token": "plain", "merges": "pl ain", "raw_count": 156200, "count": 156200, "decode_str": "plain"} -{"id": 8950, "token": "ald", "merges": "al d", "raw_count": 125561, "count": 156218, "decode_str": "ald"} -{"id": 6349, "token": "\u0120importance", "merges": "\u0120import ance", "raw_count": 156269, "count": 156269, "decode_str": " importance"} -{"id": 54405, "token": "\u00e9\u013f\u013d", "merges": "\u00e9\u013f \u013d", "raw_count": 156310, "count": 156310, "decode_str": "\u975b"} -{"id": 8636, "token": "zo", "merges": "z o", "raw_count": 146249, "count": 156322, "decode_str": "zo"} -{"id": 12820, "token": "\u0120validation", "merges": "\u0120valid ation", "raw_count": 156367, "count": 156367, "decode_str": " validation"} -{"id": 6021, "token": "\u0120income", "merges": "\u0120inc ome", "raw_count": 156385, "count": 156385, "decode_str": " income"} -{"id": 14145, "token": "\u0120offices", "merges": "\u0120off ices", "raw_count": 156390, "count": 156390, "decode_str": " offices"} -{"id": 28723, "token": "MET", "merges": "M ET", "raw_count": 156433, "count": 156433, "decode_str": "MET"} -{"id": 6757, "token": "\u0120agency", "merges": "\u0120ag ency", "raw_count": 156483, "count": 156483, "decode_str": " agency"} -{"id": 8471, "token": "friend", "merges": "f riend", "raw_count": 86997, "count": 156491, "decode_str": "friend"} -{"id": 5702, "token": "\u0120professional", "merges": "\u0120profess ional", "raw_count": 156527, "count": 156527, "decode_str": " professional"} -{"id": 8038, "token": "\u0120installed", "merges": "\u0120install ed", "raw_count": 156588, "count": 156588, "decode_str": " installed"} -{"id": 16564, "token": "seen", "merges": "se en", "raw_count": 150881, "count": 156603, "decode_str": "seen"} -{"id": 10925, "token": "................", "merges": "........ ........", "raw_count": 66118, "count": 156634, "decode_str": "................"} -{"id": 10228, "token": "stone", "merges": "st one", "raw_count": 156679, "count": 156679, "decode_str": "stone"} -{"id": 9821, "token": "una", "merges": "un a", "raw_count": 155525, "count": 156745, "decode_str": "una"} -{"id": 35242, "token": "(+)", "merges": "( +)", "raw_count": 156796, "count": 156796, "decode_str": "(+)"} -{"id": 22473, "token": "blank", "merges": "bl ank", "raw_count": 156816, "count": 156816, "decode_str": "blank"} -{"id": 9554, "token": "\u0120integration", "merges": "\u0120integr ation", "raw_count": 156821, "count": 156821, "decode_str": " integration"} -{"id": 11699, "token": "ulator", "merges": "ul ator", "raw_count": 137128, "count": 156827, "decode_str": "ulator"} -{"id": 51394, "token": "\u00e5\u0143\u00b1", "merges": "\u00e5\u0143 \u00b1", "raw_count": 156840, "count": 156840, "decode_str": "\u5b71"} -{"id": 27396, "token": "#,", "merges": "# ,", "raw_count": 156841, "count": 156841, "decode_str": "#,"} -{"id": 4656, "token": "\u0120restrict", "merges": "\u0120rest rict", "raw_count": 25617, "count": 156843, "decode_str": " restrict"} -{"id": 5107, "token": "\u0120opportunity", "merges": "\u0120opportun ity", "raw_count": 156844, "count": 156844, "decode_str": " opportunity"} -{"id": 16687, "token": "Collection", "merges": "Col lection", "raw_count": 156855, "count": 156855, "decode_str": "Collection"} -{"id": 23237, "token": "nick", "merges": "n ick", "raw_count": 156859, "count": 156859, "decode_str": "nick"} -{"id": 14573, "token": "cu", "merges": "c u", "raw_count": 155989, "count": 156873, "decode_str": "cu"} -{"id": 5953, "token": "inity", "merges": "in ity", "raw_count": 89465, "count": 156876, "decode_str": "inity"} -{"id": 29249, "token": "907", "merges": "90 7", "raw_count": 156924, "count": 156924, "decode_str": "907"} -{"id": 37267, "token": "bins", "merges": "b ins", "raw_count": 156958, "count": 156958, "decode_str": "bins"} -{"id": 7686, "token": "idelines", "merges": "idel ines", "raw_count": 12464, "count": 157022, "decode_str": "idelines"} -{"id": 4103, "token": "\u0120relative", "merges": "\u0120rel ative", "raw_count": 157062, "count": 157062, "decode_str": " relative"} -{"id": 6444, "token": "\u0120arbit", "merges": "\u0120ar bit", "raw_count": 20091, "count": 157067, "decode_str": " arbit"} -{"id": 11305, "token": "oving", "merges": "ov ing", "raw_count": 61418, "count": 157096, "decode_str": "oving"} -{"id": 16375, "token": "\u0120\"<", "merges": "\u0120\" <", "raw_count": 157119, "count": 157119, "decode_str": " \"<"} -{"id": 8047, "token": "iger", "merges": "ig er", "raw_count": 121747, "count": 157199, "decode_str": "iger"} -{"id": 13961, "token": "human", "merges": "h uman", "raw_count": 157220, "count": 157220, "decode_str": "human"} -{"id": 51955, "token": "\u00e6\u012e\u00b2", "merges": "\u00e6\u012e \u00b2", "raw_count": 157221, "count": 157221, "decode_str": "\u6332"} -{"id": 7825, "token": "\u0120adequ", "merges": "\u0120ad equ", "raw_count": 254, "count": 157273, "decode_str": " adequ"} -{"id": 6533, "token": "agen", "merges": "ag en", "raw_count": 123864, "count": 157277, "decode_str": "agen"} -{"id": 13273, "token": "clock", "merges": "cl ock", "raw_count": 157306, "count": 157306, "decode_str": "clock"} -{"id": 8988, "token": "\u012057", "merges": "\u01205 7", "raw_count": 157360, "count": 157360, "decode_str": " 57"} -{"id": 11564, "token": "Only", "merges": "On ly", "raw_count": 157372, "count": 157372, "decode_str": "Only"} -{"id": 52978, "token": "\u00e7\u013c\u00b4", "merges": "\u00e7\u013c \u00b4", "raw_count": 157408, "count": 157408, "decode_str": "\u76b4"} -{"id": 46080, "token": "orea", "merges": "ore a", "raw_count": 157442, "count": 157442, "decode_str": "orea"} -{"id": 44118, "token": "\u0120jan", "merges": "\u0120j an", "raw_count": 157460, "count": 157460, "decode_str": " jan"} -{"id": 13930, "token": "0005", "merges": "000 5", "raw_count": 157499, "count": 157499, "decode_str": "0005"} -{"id": 1757, "token": "\u00c3\u00a1", "merges": "\u00c3 \u00a1", "raw_count": 62038, "count": 157500, "decode_str": "\u00e1"} -{"id": 2712, "token": "\u0120anything", "merges": "\u0120any thing", "raw_count": 157553, "count": 157553, "decode_str": " anything"} -{"id": 51140, "token": "\u00e5\u013b\u013b", "merges": "\u00e5\u013b \u013b", "raw_count": 157559, "count": 157559, "decode_str": "\u5659"} -{"id": 14460, "token": "izers", "merges": "iz ers", "raw_count": 152249, "count": 157655, "decode_str": "izers"} -{"id": 22589, "token": "iang", "merges": "i ang", "raw_count": 156742, "count": 157666, "decode_str": "iang"} -{"id": 9319, "token": "\u0120posts", "merges": "\u0120post s", "raw_count": 157676, "count": 157676, "decode_str": " posts"} -{"id": 43547, "token": "901", "merges": "9 01", "raw_count": 157714, "count": 157714, "decode_str": "901"} -{"id": 16737, "token": "\u0120deleted", "merges": "\u0120delet ed", "raw_count": 157718, "count": 157718, "decode_str": " deleted"} -{"id": 2257, "token": "\u0120lot", "merges": "\u0120l ot", "raw_count": 151208, "count": 157720, "decode_str": " lot"} -{"id": 4987, "token": "\u0120hous", "merges": "\u0120h ous", "raw_count": 2277, "count": 157729, "decode_str": " hous"} -{"id": 4226, "token": "00000000", "merges": "0000 0000", "raw_count": 111689, "count": 157744, "decode_str": "00000000"} -{"id": 4088, "token": "\u0120ways", "merges": "\u0120w ays", "raw_count": 157753, "count": 157753, "decode_str": " ways"} -{"id": 54483, "token": "\u00e9\u00a6\u0136", "merges": "\u00e9\u00a6 \u0136", "raw_count": 157792, "count": 157792, "decode_str": "\u9994"} -{"id": 6292, "token": "nam", "merges": "n am", "raw_count": 132958, "count": 157842, "decode_str": "nam"} -{"id": 21423, "token": "primary", "merges": "prim ary", "raw_count": 157846, "count": 157846, "decode_str": "primary"} -{"id": 5480, "token": "\u0120prepared", "merges": "\u0120prep ared", "raw_count": 157854, "count": 157854, "decode_str": " prepared"} -{"id": 21377, "token": "notes", "merges": "not es", "raw_count": 157931, "count": 157931, "decode_str": "notes"} -{"id": 14956, "token": "ikip", "merges": "ik ip", "raw_count": 6030, "count": 157966, "decode_str": "ikip"} -{"id": 39805, "token": "Fit", "merges": "F it", "raw_count": 158001, "count": 158001, "decode_str": "Fit"} -{"id": 54262, "token": "\u00e9\u0137\u00a3", "merges": "\u00e9\u0137 \u00a3", "raw_count": 158046, "count": 158046, "decode_str": "\u9563"} -{"id": 10314, "token": "Pi", "merges": "P i", "raw_count": 158063, "count": 158063, "decode_str": "Pi"} -{"id": 19880, "token": "cod", "merges": "c od", "raw_count": 158072, "count": 158072, "decode_str": "cod"} -{"id": 6816, "token": "ancing", "merges": "anc ing", "raw_count": 56139, "count": 158128, "decode_str": "ancing"} -{"id": 5030, "token": "\u0120pow", "merges": "\u0120p ow", "raw_count": 57825, "count": 158148, "decode_str": " pow"} -{"id": 16429, "token": "relation", "merges": "rel ation", "raw_count": 120563, "count": 158152, "decode_str": "relation"} -{"id": 22354, "token": "sat", "merges": "s at", "raw_count": 143946, "count": 158173, "decode_str": "sat"} -{"id": 5586, "token": "\u0120para", "merges": "\u0120par a", "raw_count": 158221, "count": 158221, "decode_str": " para"} -{"id": 15801, "token": "bone", "merges": "b one", "raw_count": 134996, "count": 158222, "decode_str": "bone"} -{"id": 30206, "token": "Gi", "merges": "G i", "raw_count": 158226, "count": 158226, "decode_str": "Gi"} -{"id": 8521, "token": "\u0120recommended", "merges": "\u0120recomm ended", "raw_count": 158270, "count": 158270, "decode_str": " recommended"} -{"id": 24494, "token": "Bad", "merges": "B ad", "raw_count": 158288, "count": 158288, "decode_str": "Bad"} -{"id": 27094, "token": "bud", "merges": "b ud", "raw_count": 158312, "count": 158312, "decode_str": "bud"} -{"id": 21592, "token": "cop", "merges": "c op", "raw_count": 158367, "count": 158367, "decode_str": "cop"} -{"id": 52162, "token": "\u00e6\u013b\u0140", "merges": "\u00e6\u013b \u0140", "raw_count": 158388, "count": 158388, "decode_str": "\u665e"} -{"id": 22452, "token": "console", "merges": "con sole", "raw_count": 158397, "count": 158397, "decode_str": "console"} -{"id": 4142, "token": "\u0120rates", "merges": "\u0120r ates", "raw_count": 158455, "count": 158455, "decode_str": " rates"} -{"id": 29941, "token": "689", "merges": "68 9", "raw_count": 158464, "count": 158464, "decode_str": "689"} -{"id": 28315, "token": "997", "merges": "99 7", "raw_count": 158479, "count": 158479, "decode_str": "997"} -{"id": 24442, "token": "photo", "merges": "ph oto", "raw_count": 158480, "count": 158480, "decode_str": "photo"} -{"id": 2933, "token": "\u0120AN", "merges": "\u0120A N", "raw_count": 31614, "count": 158539, "decode_str": " AN"} -{"id": 28184, "token": "Mic", "merges": "M ic", "raw_count": 67754, "count": 158550, "decode_str": "Mic"} -{"id": 50665, "token": "\u00e5\u0125\u0138", "merges": "\u00e5\u0125 \u0138", "raw_count": 158560, "count": 158560, "decode_str": "\u50d6"} -{"id": 5328, "token": "\u0120gold", "merges": "\u0120g old", "raw_count": 125485, "count": 158571, "decode_str": " gold"} -{"id": 8536, "token": "ensus", "merges": "ens us", "raw_count": 42255, "count": 158616, "decode_str": "ensus"} -{"id": 39849, "token": "511", "merges": "5 11", "raw_count": 158699, "count": 158699, "decode_str": "511"} -{"id": 54453, "token": "\u00e9\u00a2\u013d", "merges": "\u00e9\u00a2 \u013d", "raw_count": 158714, "count": 158714, "decode_str": "\u989b"} -{"id": 8187, "token": "\u012072", "merges": "\u01207 2", "raw_count": 158740, "count": 158740, "decode_str": " 72"} -{"id": 13146, "token": "^)", "merges": "^ )", "raw_count": 158762, "count": 158762, "decode_str": "^)"} -{"id": 10132, "token": "\u0120regulations", "merges": "\u0120reg ulations", "raw_count": 158789, "count": 158789, "decode_str": " regulations"} -{"id": 9091, "token": "\u0120opportunities", "merges": "\u0120opportun ities", "raw_count": 158800, "count": 158800, "decode_str": " opportunities"} -{"id": 10120, "token": "yd", "merges": "y d", "raw_count": 132614, "count": 158821, "decode_str": "yd"} -{"id": 13004, "token": "erred", "merges": "er red", "raw_count": 127946, "count": 158834, "decode_str": "erred"} -{"id": 6993, "token": "\u0120acts", "merges": "\u0120act s", "raw_count": 158843, "count": 158843, "decode_str": " acts"} -{"id": 3468, "token": "\u0120slow", "merges": "\u0120s low", "raw_count": 102169, "count": 158849, "decode_str": " slow"} -{"id": 5426, "token": "\u0120definition", "merges": "\u0120defin ition", "raw_count": 158889, "count": 158889, "decode_str": " definition"} -{"id": 43104, "token": "Fly", "merges": "F ly", "raw_count": 158970, "count": 158970, "decode_str": "Fly"} -{"id": 10038, "token": "\u0120ec", "merges": "\u0120e c", "raw_count": 136540, "count": 159001, "decode_str": " ec"} -{"id": 30592, "token": "451", "merges": "45 1", "raw_count": 159004, "count": 159004, "decode_str": "451"} -{"id": 7068, "token": "iner", "merges": "in er", "raw_count": 146544, "count": 159011, "decode_str": "iner"} -{"id": 18758, "token": "wal", "merges": "w al", "raw_count": 150340, "count": 159093, "decode_str": "wal"} -{"id": 16945, "token": "-)", "merges": "- )", "raw_count": 156409, "count": 159140, "decode_str": "-)"} -{"id": 5239, "token": "\u0120sets", "merges": "\u0120set s", "raw_count": 159148, "count": 159148, "decode_str": " sets"} -{"id": 4893, "token": "\u0120applications", "merges": "\u0120applic ations", "raw_count": 159156, "count": 159156, "decode_str": " applications"} -{"id": 25697, "token": "TN", "merges": "T N", "raw_count": 159184, "count": 159184, "decode_str": "TN"} -{"id": 3224, "token": "ederal", "merges": "ed eral", "raw_count": 471, "count": 159229, "decode_str": "ederal"} -{"id": 40009, "token": "\u0120sigma", "merges": "\u0120s igma", "raw_count": 159240, "count": 159240, "decode_str": " sigma"} -{"id": 15942, "token": "\u0120operational", "merges": "\u0120oper ational", "raw_count": 159333, "count": 159333, "decode_str": " operational"} -{"id": 2455, "token": "\u0120ever", "merges": "\u0120e ver", "raw_count": 159333, "count": 159333, "decode_str": " ever"} -{"id": 32745, "token": "052", "merges": "05 2", "raw_count": 159389, "count": 159389, "decode_str": "052"} -{"id": 8455, "token": "Right", "merges": "R ight", "raw_count": 159218, "count": 159390, "decode_str": "Right"} -{"id": 29064, "token": "Score", "merges": "Sc ore", "raw_count": 159390, "count": 159390, "decode_str": "Score"} -{"id": 22097, "token": "Tor", "merges": "T or", "raw_count": 159402, "count": 159402, "decode_str": "Tor"} -{"id": 5810, "token": "\u0120characters", "merges": "\u0120char acters", "raw_count": 159437, "count": 159437, "decode_str": " characters"} -{"id": 45407, "token": "filtered", "merges": "fil tered", "raw_count": 159455, "count": 159455, "decode_str": "filtered"} -{"id": 5798, "token": "\u0120cat", "merges": "\u0120c at", "raw_count": 131960, "count": 159482, "decode_str": " cat"} -{"id": 48808, "token": "wf", "merges": "w f", "raw_count": 159501, "count": 159501, "decode_str": "wf"} -{"id": 54543, "token": "\u00e7\u00a1\u012e", "merges": "\u00e7\u00a1 \u012e", "raw_count": 159564, "count": 159564, "decode_str": "\u784c"} -{"id": 22930, "token": "Hen", "merges": "H en", "raw_count": 68849, "count": 159579, "decode_str": "Hen"} -{"id": 27390, "token": "until", "merges": "un til", "raw_count": 159597, "count": 159597, "decode_str": "until"} -{"id": 8676, "token": "\u012053", "merges": "\u01205 3", "raw_count": 159601, "count": 159601, "decode_str": " 53"} -{"id": 45635, "token": "('<", "merges": "(' <", "raw_count": 159602, "count": 159602, "decode_str": "('<"} -{"id": 3347, "token": "\u0120son", "merges": "\u0120s on", "raw_count": 158041, "count": 159638, "decode_str": " son"} -{"id": 4183, "token": "\u00d0\u00b2", "merges": "\u00d0 \u00b2", "raw_count": 87354, "count": 159674, "decode_str": "\u0432"} -{"id": 54518, "token": "\u00e9\u00ab\u0124", "merges": "\u00e9\u00ab \u0124", "raw_count": 159675, "count": 159675, "decode_str": "\u9ac2"} -{"id": 10073, "token": "\u0120assist", "merges": "\u0120ass ist", "raw_count": 147578, "count": 159770, "decode_str": " assist"} -{"id": 4125, "token": "Now", "merges": "N ow", "raw_count": 159781, "count": 159781, "decode_str": "Now"} -{"id": 4980, "token": "\u0120modern", "merges": "\u0120mod ern", "raw_count": 159783, "count": 159783, "decode_str": " modern"} -{"id": 13101, "token": "cells", "merges": "cell s", "raw_count": 159791, "count": 159791, "decode_str": "cells"} -{"id": 2724, "token": "\u0120behav", "merges": "\u0120beh av", "raw_count": 719, "count": 159889, "decode_str": " behav"} -{"id": 3438, "token": "\u0120former", "merges": "\u0120form er", "raw_count": 150768, "count": 159890, "decode_str": " former"} -{"id": 53007, "token": "\u00e7\u013e\u013b", "merges": "\u00e7\u013e \u013b", "raw_count": 159906, "count": 159906, "decode_str": "\u7719"} -{"id": 43676, "token": "419", "merges": "4 19", "raw_count": 159914, "count": 159914, "decode_str": "419"} -{"id": 2325, "token": "\u0120Be", "merges": "\u0120B e", "raw_count": 48852, "count": 159928, "decode_str": " Be"} -{"id": 49582, "token": "519", "merges": "5 19", "raw_count": 159936, "count": 159936, "decode_str": "519"} -{"id": 31263, "token": "allowed", "merges": "allow ed", "raw_count": 159977, "count": 159977, "decode_str": "allowed"} -{"id": 7550, "token": "\u0120cris", "merges": "\u0120cr is", "raw_count": 3719, "count": 159993, "decode_str": " cris"} -{"id": 32179, "token": "seek", "merges": "se ek", "raw_count": 160045, "count": 160045, "decode_str": "seek"} -{"id": 6732, "token": "nbsp", "merges": "nb sp", "raw_count": 160109, "count": 160109, "decode_str": "nbsp"} -{"id": 24391, "token": "Random", "merges": "R andom", "raw_count": 160162, "count": 160162, "decode_str": "Random"} -{"id": 8878, "token": "\u01201995", "merges": "\u0120199 5", "raw_count": 160197, "count": 160197, "decode_str": " 1995"} -{"id": 16912, "token": "\u0120Import", "merges": "\u0120Im port", "raw_count": 157466, "count": 160239, "decode_str": " Import"} -{"id": 10349, "token": "\u0120victims", "merges": "\u0120victim s", "raw_count": 160242, "count": 160242, "decode_str": " victims"} -{"id": 16461, "token": "curs", "merges": "cur s", "raw_count": 34806, "count": 160267, "decode_str": "curs"} -{"id": 23092, "token": "Plan", "merges": "Pl an", "raw_count": 160297, "count": 160297, "decode_str": "Plan"} -{"id": 12255, "token": "\u0120checks", "merges": "\u0120che cks", "raw_count": 160337, "count": 160337, "decode_str": " checks"} -{"id": 17932, "token": "character", "merges": "char acter", "raw_count": 160379, "count": 160379, "decode_str": "character"} -{"id": 52445, "token": "\u00e6\u00b0\u0132", "merges": "\u00e6\u00b0 \u0132", "raw_count": 160385, "count": 160385, "decode_str": "\u6c10"} -{"id": 4653, "token": "\u0120PR", "merges": "\u0120P R", "raw_count": 92958, "count": 160405, "decode_str": " PR"} -{"id": 21082, "token": "War", "merges": "W ar", "raw_count": 160434, "count": 160434, "decode_str": "War"} -{"id": 33919, "token": "Gate", "merges": "G ate", "raw_count": 160444, "count": 160444, "decode_str": "Gate"} -{"id": 22940, "token": "dit", "merges": "d it", "raw_count": 157428, "count": 160452, "decode_str": "dit"} -{"id": 35899, "token": "cancel", "merges": "c ancel", "raw_count": 160456, "count": 160456, "decode_str": "cancel"} -{"id": 15719, "token": "ean", "merges": "e an", "raw_count": 25526, "count": 160470, "decode_str": "ean"} -{"id": 14074, "token": "Unit", "merges": "Un it", "raw_count": 160514, "count": 160514, "decode_str": "Unit"} -{"id": 3573, "token": "\u0120heav", "merges": "\u0120he av", "raw_count": 3834, "count": 160522, "decode_str": " heav"} -{"id": 13511, "token": "oj", "merges": "o j", "raw_count": 160525, "count": 160525, "decode_str": "oj"} -{"id": 41849, "token": "Tony", "merges": "T ony", "raw_count": 160548, "count": 160548, "decode_str": "Tony"} -{"id": 26544, "token": "alert", "merges": "al ert", "raw_count": 160565, "count": 160565, "decode_str": "alert"} -{"id": 20612, "token": "consum", "merges": "con sum", "raw_count": 53420, "count": 160603, "decode_str": "consum"} -{"id": 31203, "token": "757", "merges": "75 7", "raw_count": 160607, "count": 160607, "decode_str": "757"} -{"id": 3214, "token": "partial", "merges": "part ial", "raw_count": 160633, "count": 160633, "decode_str": "partial"} -{"id": 29577, "token": "usters", "merges": "ust ers", "raw_count": 160637, "count": 160637, "decode_str": "usters"} -{"id": 5126, "token": "\u00d0\u00b5\u00d0\u00bd", "merges": "\u00d0\u00b5 \u00d0\u00bd", "raw_count": 66133, "count": 160687, "decode_str": "\u0435\u043d"} -{"id": 17557, "token": "Mal", "merges": "M al", "raw_count": 160699, "count": 160699, "decode_str": "Mal"} -{"id": 10894, "token": "\u0120lists", "merges": "\u0120l ists", "raw_count": 160701, "count": 160701, "decode_str": " lists"} -{"id": 7726, "token": "\u0120interval", "merges": "\u0120inter val", "raw_count": 160705, "count": 160705, "decode_str": " interval"} -{"id": 51656, "token": "\u00e5\u00be\u00ac", "merges": "\u00e5\u00be \u00ac", "raw_count": 160738, "count": 160738, "decode_str": "\u5fac"} -{"id": 17188, "token": "erver", "merges": "er ver", "raw_count": 119023, "count": 160772, "decode_str": "erver"} -{"id": 7767, "token": "\u0120enforce", "merges": "\u0120en force", "raw_count": 40638, "count": 160777, "decode_str": " enforce"} -{"id": 21333, "token": "Price", "merges": "Pr ice", "raw_count": 160804, "count": 160804, "decode_str": "Price"} -{"id": 21823, "token": "\u0120initiatives", "merges": "\u0120initi atives", "raw_count": 160807, "count": 160807, "decode_str": " initiatives"} -{"id": 22550, "token": "IK", "merges": "I K", "raw_count": 160867, "count": 160867, "decode_str": "IK"} -{"id": 42420, "token": "516", "merges": "5 16", "raw_count": 160893, "count": 160893, "decode_str": "516"} -{"id": 51459, "token": "\u00e5\u00b0\u0137", "merges": "\u00e5\u00b0 \u0137", "raw_count": 160903, "count": 160903, "decode_str": "\u5c15"} -{"id": 17144, "token": "marks", "merges": "mar ks", "raw_count": 122615, "count": 160906, "decode_str": "marks"} -{"id": 20279, "token": "\u0120fetch", "merges": "\u0120fet ch", "raw_count": 160940, "count": 160940, "decode_str": " fetch"} -{"id": 11509, "token": "Prov", "merges": "Pro v", "raw_count": 71748, "count": 160943, "decode_str": "Prov"} -{"id": 33775, "token": "411", "merges": "4 11", "raw_count": 160945, "count": 160945, "decode_str": "411"} -{"id": 26617, "token": "love", "merges": "l ove", "raw_count": 160996, "count": 160996, "decode_str": "love"} -{"id": 32314, "token": "sid", "merges": "s id", "raw_count": 161021, "count": 161021, "decode_str": "sid"} -{"id": 13432, "token": "DH", "merges": "D H", "raw_count": 160541, "count": 161022, "decode_str": "DH"} -{"id": 4994, "token": "erved", "merges": "erv ed", "raw_count": 43209, "count": 161080, "decode_str": "erved"} -{"id": 15888, "token": "Values", "merges": "Val ues", "raw_count": 161126, "count": 161126, "decode_str": "Values"} -{"id": 8317, "token": "\u0120collabor", "merges": "\u0120coll abor", "raw_count": 14451, "count": 161137, "decode_str": " collabor"} -{"id": 12119, "token": "\u0120upload", "merges": "\u0120u pload", "raw_count": 120640, "count": 161173, "decode_str": " upload"} -{"id": 14379, "token": "enum", "merges": "en um", "raw_count": 161174, "count": 161174, "decode_str": "enum"} -{"id": 40948, "token": "445", "merges": "4 45", "raw_count": 161208, "count": 161208, "decode_str": "445"} -{"id": 26233, "token": "679", "merges": "67 9", "raw_count": 161260, "count": 161260, "decode_str": "679"} -{"id": 27803, "token": "clone", "merges": "cl one", "raw_count": 161261, "count": 161261, "decode_str": "clone"} -{"id": 17310, "token": "\u0120merge", "merges": "\u0120mer ge", "raw_count": 161266, "count": 161266, "decode_str": " merge"} -{"id": 11215, "token": "aver", "merges": "a ver", "raw_count": 156730, "count": 161267, "decode_str": "aver"} -{"id": 52263, "token": "\u00e6\u0141\u0140", "merges": "\u00e6\u0141 \u0140", "raw_count": 161284, "count": 161284, "decode_str": "\u67de"} -{"id": 18378, "token": "Len", "merges": "L en", "raw_count": 161298, "count": 161298, "decode_str": "Len"} -{"id": 40760, "token": "465", "merges": "4 65", "raw_count": 161359, "count": 161359, "decode_str": "465"} -{"id": 4533, "token": "\u0120roll", "merges": "\u0120ro ll", "raw_count": 97870, "count": 161397, "decode_str": " roll"} -{"id": 25377, "token": "wrapper", "merges": "w rapper", "raw_count": 161398, "count": 161398, "decode_str": "wrapper"} -{"id": 16253, "token": "\u0120adoption", "merges": "\u0120adopt ion", "raw_count": 161428, "count": 161428, "decode_str": " adoption"} -{"id": 48172, "token": "790", "merges": "7 90", "raw_count": 161444, "count": 161444, "decode_str": "790"} -{"id": 52640, "token": "\u00e6\u00b7\u00a6", "merges": "\u00e6\u00b7 \u00a6", "raw_count": 161458, "count": 161458, "decode_str": "\u6de6"} -{"id": 6010, "token": "\u0120summary", "merges": "\u0120sum mary", "raw_count": 161467, "count": 161467, "decode_str": " summary"} -{"id": 45060, "token": "Sky", "merges": "S ky", "raw_count": 161488, "count": 161488, "decode_str": "Sky"} -{"id": 14506, "token": "xf", "merges": "x f", "raw_count": 161593, "count": 161593, "decode_str": "xf"} -{"id": 51359, "token": "\u00e5\u00a7\u0134", "merges": "\u00e5\u00a7 \u0134", "raw_count": 161628, "count": 161628, "decode_str": "\u59d2"} -{"id": 10455, "token": "unning", "merges": "un ning", "raw_count": 8988, "count": 161671, "decode_str": "unning"} -{"id": 31730, "token": "643", "merges": "64 3", "raw_count": 161671, "count": 161671, "decode_str": "643"} -{"id": 19284, "token": "Files", "merges": "F iles", "raw_count": 161720, "count": 161720, "decode_str": "Files"} -{"id": 53892, "token": "\u00e8\u00b0\u00b6", "merges": "\u00e8\u00b0 \u00b6", "raw_count": 161721, "count": 161721, "decode_str": "\u8c36"} -{"id": 15223, "token": "\u0120fake", "merges": "\u0120f ake", "raw_count": 161731, "count": 161731, "decode_str": " fake"} -{"id": 14740, "token": "mpty", "merges": "mpt y", "raw_count": 785, "count": 161766, "decode_str": "mpty"} -{"id": 13766, "token": "PORT", "merges": "P ORT", "raw_count": 147093, "count": 161794, "decode_str": "PORT"} -{"id": 5730, "token": "\u0120wish", "merges": "\u0120w ish", "raw_count": 161816, "count": 161816, "decode_str": " wish"} -{"id": 39069, "token": "417", "merges": "4 17", "raw_count": 161862, "count": 161862, "decode_str": "417"} -{"id": 3937, "token": "mega", "merges": "m ega", "raw_count": 17627, "count": 161867, "decode_str": "mega"} -{"id": 28584, "token": "ventory", "merges": "vent ory", "raw_count": 149967, "count": 161899, "decode_str": "ventory"} -{"id": 14410, "token": "Draw", "merges": "D raw", "raw_count": 140909, "count": 161949, "decode_str": "Draw"} -{"id": 7467, "token": "\u0120duration", "merges": "\u0120d uration", "raw_count": 161953, "count": 161953, "decode_str": " duration"} -{"id": 14172, "token": "\u0120march", "merges": "\u0120m arch", "raw_count": 159519, "count": 162016, "decode_str": " march"} -{"id": 17607, "token": "\u0120HTTP", "merges": "\u0120H TTP", "raw_count": 162029, "count": 162029, "decode_str": " HTTP"} -{"id": 14323, "token": "disp", "merges": "dis p", "raw_count": 82176, "count": 162035, "decode_str": "disp"} -{"id": 8527, "token": "\u0120integrated", "merges": "\u0120integr ated", "raw_count": 162063, "count": 162063, "decode_str": " integrated"} -{"id": 51347, "token": "\u00e5\u00a6\u00aa", "merges": "\u00e5\u00a6 \u00aa", "raw_count": 162065, "count": 162065, "decode_str": "\u59aa"} -{"id": 6375, "token": "rog", "merges": "ro g", "raw_count": 116140, "count": 162068, "decode_str": "rog"} -{"id": 5372, "token": "atically", "merges": "at ically", "raw_count": 25701, "count": 162084, "decode_str": "atically"} -{"id": 16604, "token": "027", "merges": "0 27", "raw_count": 162114, "count": 162114, "decode_str": "027"} -{"id": 4215, "token": "iated", "merges": "i ated", "raw_count": 55475, "count": 162123, "decode_str": "iated"} -{"id": 8002, "token": "nav", "merges": "n av", "raw_count": 133374, "count": 162137, "decode_str": "nav"} -{"id": 3638, "token": "\u0120constant", "merges": "\u0120const ant", "raw_count": 133761, "count": 162186, "decode_str": " constant"} -{"id": 9021, "token": "\u0120contributions", "merges": "\u0120contribut ions", "raw_count": 162187, "count": 162187, "decode_str": " contributions"} -{"id": 28202, "token": "995", "merges": "99 5", "raw_count": 162188, "count": 162188, "decode_str": "995"} -{"id": 3743, "token": "asons", "merges": "as ons", "raw_count": 36474, "count": 162213, "decode_str": "asons"} -{"id": 11759, "token": "\u0120Error", "merges": "\u0120Err or", "raw_count": 162222, "count": 162222, "decode_str": " Error"} -{"id": 22468, "token": "phot", "merges": "ph ot", "raw_count": 123237, "count": 162274, "decode_str": "phot"} -{"id": 15285, "token": "\u0120strategic", "merges": "\u0120strateg ic", "raw_count": 162291, "count": 162291, "decode_str": " strategic"} -{"id": 26845, "token": "Bob", "merges": "B ob", "raw_count": 162302, "count": 162302, "decode_str": "Bob"} -{"id": 50818, "token": "\u00e5\u012c\u0143", "merges": "\u00e5\u012c \u0143", "raw_count": 162345, "count": 162345, "decode_str": "\u52ad"} -{"id": 41133, "token": "Prime", "merges": "Pr ime", "raw_count": 162364, "count": 162364, "decode_str": "Prime"} -{"id": 19975, "token": "ovo", "merges": "ov o", "raw_count": 162297, "count": 162369, "decode_str": "ovo"} -{"id": 3590, "token": "\u0120sound", "merges": "\u0120s ound", "raw_count": 152150, "count": 162425, "decode_str": " sound"} -{"id": 23187, "token": "hin", "merges": "h in", "raw_count": 162446, "count": 162446, "decode_str": "hin"} -{"id": 44662, "token": ":&", "merges": ": &", "raw_count": 162508, "count": 162508, "decode_str": ":&"} -{"id": 33234, "token": "\u0120dp", "merges": "\u0120d p", "raw_count": 162526, "count": 162526, "decode_str": " dp"} -{"id": 30651, "token": "696", "merges": "69 6", "raw_count": 162554, "count": 162554, "decode_str": "696"} -{"id": 16140, "token": "\u0120Return", "merges": "\u0120Ret urn", "raw_count": 162563, "count": 162563, "decode_str": " Return"} -{"id": 9212, "token": "\u0120assign", "merges": "\u0120ass ign", "raw_count": 119564, "count": 162604, "decode_str": " assign"} -{"id": 4811, "token": "\u0120regions", "merges": "\u0120reg ions", "raw_count": 162610, "count": 162610, "decode_str": " regions"} -{"id": 6410, "token": "ariant", "merges": "ari ant", "raw_count": 16173, "count": 162612, "decode_str": "ariant"} -{"id": 52010, "token": "\u00e6\u0131\u0126", "merges": "\u00e6\u0131 \u0126", "raw_count": 162620, "count": 162620, "decode_str": "\u63c4"} -{"id": 16379, "token": "Items", "merges": "It ems", "raw_count": 162706, "count": 162706, "decode_str": "Items"} -{"id": 10102, "token": "\u0120rom", "merges": "\u0120 rom", "raw_count": 140677, "count": 162719, "decode_str": " rom"} -{"id": 28936, "token": "machine", "merges": "m achine", "raw_count": 162729, "count": 162729, "decode_str": "machine"} -{"id": 45837, "token": "mmHg", "merges": "mm Hg", "raw_count": 162749, "count": 162749, "decode_str": "mmHg"} -{"id": 3168, "token": "\u0120white", "merges": "\u0120wh ite", "raw_count": 162763, "count": 162763, "decode_str": " white"} -{"id": 51677, "token": "\u00e5\u00bf\u00a4", "merges": "\u00e5\u00bf \u00a4", "raw_count": 162776, "count": 162776, "decode_str": "\u5fe4"} -{"id": 24111, "token": "plugins", "merges": "plug ins", "raw_count": 162837, "count": 162837, "decode_str": "plugins"} -{"id": 6339, "token": "stein", "merges": "ste in", "raw_count": 122889, "count": 162913, "decode_str": "stein"} -{"id": 19000, "token": "RD", "merges": "R D", "raw_count": 162927, "count": 162927, "decode_str": "RD"} -{"id": 4171, "token": "\u0120acqu", "merges": "\u0120ac qu", "raw_count": 10383, "count": 162931, "decode_str": " acqu"} -{"id": 15068, "token": "present", "merges": "p resent", "raw_count": 132448, "count": 163033, "decode_str": "present"} -{"id": 54187, "token": "\u00e9\u0127\u012c", "merges": "\u00e9\u0127 \u012c", "raw_count": 163041, "count": 163041, "decode_str": "\u914a"} -{"id": 8232, "token": "\u0120zone", "merges": "\u0120z one", "raw_count": 163051, "count": 163051, "decode_str": " zone"} -{"id": 7013, "token": "\u0120emph", "merges": "\u0120em ph", "raw_count": 3091, "count": 163060, "decode_str": " emph"} -{"id": 13749, "token": "icker", "merges": "ick er", "raw_count": 133990, "count": 163084, "decode_str": "icker"} -{"id": 4649, "token": "\u0120algorith", "merges": "\u0120al gorith", "raw_count": 423, "count": 163119, "decode_str": " algorith"} -{"id": 23912, "token": "Profile", "merges": "Pro file", "raw_count": 163139, "count": 163139, "decode_str": "Profile"} -{"id": 52411, "token": "\u00e6\u00ae\u0123", "merges": "\u00e6\u00ae \u0123", "raw_count": 163189, "count": 163189, "decode_str": "\u6b81"} -{"id": 19052, "token": "loaded", "merges": "load ed", "raw_count": 163249, "count": 163249, "decode_str": "loaded"} -{"id": 5157, "token": "stitute", "merges": "stit ute", "raw_count": 128526, "count": 163312, "decode_str": "stitute"} -{"id": 4866, "token": "\u0120movement", "merges": "\u0120move ment", "raw_count": 163319, "count": 163319, "decode_str": " movement"} -{"id": 15954, "token": "\u00e9\u0138", "merges": "\u00e9 \u0138", "raw_count": 67261, "count": 163373, "decode_str": "\ufffd"} -{"id": 6312, "token": "\u0120completed", "merges": "\u0120complet ed", "raw_count": 163376, "count": 163376, "decode_str": " completed"} -{"id": 12599, "token": "Local", "merges": "L ocal", "raw_count": 163405, "count": 163405, "decode_str": "Local"} -{"id": 50490, "token": "\u00e4\u00bb\u0125", "merges": "\u00e4\u00bb \u0125", "raw_count": 163444, "count": 163444, "decode_str": "\u4ec3"} -{"id": 54369, "token": "\u00e9\u013d\u0134", "merges": "\u00e9\u013d \u0134", "raw_count": 163491, "count": 163491, "decode_str": "\u96d2"} -{"id": 19877, "token": "Icon", "merges": "I con", "raw_count": 163540, "count": 163540, "decode_str": "Icon"} -{"id": 5884, "token": "\u0120minor", "merges": "\u0120min or", "raw_count": 56847, "count": 163552, "decode_str": " minor"} -{"id": 6278, "token": "\u0120square", "merges": "\u0120squ are", "raw_count": 161831, "count": 163609, "decode_str": " square"} -{"id": 19225, "token": "\u0120traff", "merges": "\u0120tra ff", "raw_count": 14445, "count": 163624, "decode_str": " traff"} -{"id": 19157, "token": "Enabled", "merges": "En abled", "raw_count": 163663, "count": 163663, "decode_str": "Enabled"} -{"id": 13700, "token": "ceive", "merges": "ce ive", "raw_count": 8996, "count": 163697, "decode_str": "ceive"} -{"id": 7730, "token": "\u0120committed", "merges": "\u0120comm itted", "raw_count": 163710, "count": 163710, "decode_str": " committed"} -{"id": 28908, "token": "ssl", "merges": "ss l", "raw_count": 163830, "count": 163830, "decode_str": "ssl"} -{"id": 13508, "token": "utable", "merges": "ut able", "raw_count": 120184, "count": 163861, "decode_str": "utable"} -{"id": 22719, "token": ")\",", "merges": ") \",", "raw_count": 163866, "count": 163866, "decode_str": ")\","} -{"id": 25981, "token": "WORD", "merges": "W ORD", "raw_count": 163944, "count": 163944, "decode_str": "WORD"} -{"id": 6211, "token": "\u0120citiz", "merges": "\u0120cit iz", "raw_count": 132, "count": 163977, "decode_str": " citiz"} -{"id": 31699, "token": "476", "merges": "47 6", "raw_count": 163980, "count": 163980, "decode_str": "476"} -{"id": 29462, "token": "676", "merges": "67 6", "raw_count": 163990, "count": 163990, "decode_str": "676"} -{"id": 22009, "token": "mil", "merges": "m il", "raw_count": 149420, "count": 164036, "decode_str": "mil"} -{"id": 3477, "token": "\u0120easy", "merges": "\u0120eas y", "raw_count": 164048, "count": 164048, "decode_str": " easy"} -{"id": 26122, "token": "comments", "merges": "com ments", "raw_count": 164072, "count": 164072, "decode_str": "comments"} -{"id": 15956, "token": "\u0120\u00e2\u0122\u013b", "merges": "\u0120 \u00e2\u0122\u013b", "raw_count": 164114, "count": 164114, "decode_str": " \u2019"} -{"id": 7151, "token": "ket", "merges": "k et", "raw_count": 68076, "count": 164127, "decode_str": "ket"} -{"id": 28418, "token": "422", "merges": "4 22", "raw_count": 164133, "count": 164133, "decode_str": "422"} -{"id": 50627, "token": "\u00e5\u0122\u013e", "merges": "\u00e5\u0122 \u013e", "raw_count": 164146, "count": 164146, "decode_str": "\u501c"} -{"id": 3653, "token": "\u0120determine", "merges": "\u0120determ ine", "raw_count": 164149, "count": 164149, "decode_str": " determine"} -{"id": 8437, "token": "\u0120101", "merges": "\u01201 01", "raw_count": 164149, "count": 164149, "decode_str": " 101"} -{"id": 29631, "token": "075", "merges": "0 75", "raw_count": 164152, "count": 164152, "decode_str": "075"} -{"id": 3499, "token": "\u0120hor", "merges": "\u0120h or", "raw_count": 30828, "count": 164194, "decode_str": " hor"} -{"id": 5348, "token": "ilies", "merges": "il ies", "raw_count": 5479, "count": 164196, "decode_str": "ilies"} -{"id": 8443, "token": "\u0120arrang", "merges": "\u0120arr ang", "raw_count": 235, "count": 164243, "decode_str": " arrang"} -{"id": 42023, "token": "solution", "merges": "s olution", "raw_count": 164302, "count": 164302, "decode_str": "solution"} -{"id": 5419, "token": "\u0120pun", "merges": "\u0120p un", "raw_count": 16476, "count": 164306, "decode_str": " pun"} -{"id": 50943, "token": "\u00e5\u0131\u00b5", "merges": "\u00e5\u0131 \u00b5", "raw_count": 164312, "count": 164312, "decode_str": "\u53f5"} -{"id": 10229, "token": "\u0120goods", "merges": "\u0120good s", "raw_count": 164316, "count": 164316, "decode_str": " goods"} -{"id": 46450, "token": "Spot", "merges": "Sp ot", "raw_count": 164403, "count": 164403, "decode_str": "Spot"} -{"id": 30452, "token": "489", "merges": "48 9", "raw_count": 164419, "count": 164419, "decode_str": "489"} -{"id": 14889, "token": "boy", "merges": "b oy", "raw_count": 164470, "count": 164470, "decode_str": "boy"} -{"id": 27763, "token": "%=", "merges": "% =", "raw_count": 164433, "count": 164473, "decode_str": "%="} -{"id": 2868, "token": "\u0120believe", "merges": "\u0120belie ve", "raw_count": 164498, "count": 164498, "decode_str": " believe"} -{"id": 4085, "token": "eful", "merges": "ef ul", "raw_count": 16204, "count": 164503, "decode_str": "eful"} -{"id": 42576, "token": "Travel", "merges": "Tra vel", "raw_count": 164593, "count": 164593, "decode_str": "Travel"} -{"id": 5692, "token": "rient", "merges": "ri ent", "raw_count": 27264, "count": 164663, "decode_str": "rient"} -{"id": 33788, "token": "transport", "merges": "trans port", "raw_count": 164673, "count": 164673, "decode_str": "transport"} -{"id": 11799, "token": "evin", "merges": "ev in", "raw_count": 13653, "count": 164697, "decode_str": "evin"} -{"id": 17277, "token": "Best", "merges": "B est", "raw_count": 164707, "count": 164707, "decode_str": "Best"} -{"id": 18188, "token": "\u012007", "merges": "\u01200 7", "raw_count": 164733, "count": 164733, "decode_str": " 07"} -{"id": 50993, "token": "\u00e5\u0133\u012d", "merges": "\u00e5\u0133 \u012d", "raw_count": 164759, "count": 164759, "decode_str": "\u544b"} -{"id": 43874, "token": "elist", "merges": "el ist", "raw_count": 164762, "count": 164762, "decode_str": "elist"} -{"id": 8440, "token": "ona", "merges": "on a", "raw_count": 155162, "count": 164766, "decode_str": "ona"} -{"id": 52952, "token": "\u00e7\u0139\u00bc", "merges": "\u00e7\u0139 \u00bc", "raw_count": 164783, "count": 164783, "decode_str": "\u75fc"} -{"id": 22284, "token": "Ang", "merges": "An g", "raw_count": 164784, "count": 164784, "decode_str": "Ang"} -{"id": 6823, "token": "ashion", "merges": "ash ion", "raw_count": 64269, "count": 164801, "decode_str": "ashion"} -{"id": 54384, "token": "\u00e9\u013e\u012a", "merges": "\u00e9\u013e \u012a", "raw_count": 164836, "count": 164836, "decode_str": "\u9708"} -{"id": 53358, "token": "\u00e7\u00bb\u00a6", "merges": "\u00e7\u00bb \u00a6", "raw_count": 164845, "count": 164845, "decode_str": "\u7ee6"} -{"id": 35356, "token": "691", "merges": "69 1", "raw_count": 164921, "count": 164921, "decode_str": "691"} -{"id": 53635, "token": "\u00e8\u012d\u0123", "merges": "\u00e8\u012d \u0123", "raw_count": 164982, "count": 164982, "decode_str": "\u82c1"} -{"id": 5960, "token": "}-", "merges": "} -", "raw_count": 165124, "count": 165129, "decode_str": "}-"} -{"id": 5333, "token": "\u0120shift", "merges": "\u0120sh ift", "raw_count": 144056, "count": 165130, "decode_str": " shift"} -{"id": 5302, "token": "using", "merges": "us ing", "raw_count": 148084, "count": 165191, "decode_str": "using"} -{"id": 29706, "token": "money", "merges": "m oney", "raw_count": 165204, "count": 165204, "decode_str": "money"} -{"id": 20894, "token": "proto", "merges": "pro to", "raw_count": 165215, "count": 165215, "decode_str": "proto"} -{"id": 16857, "token": "\u0120\u00ea", "merges": "\u0120 \u00ea", "raw_count": 66318, "count": 165228, "decode_str": " \ufffd"} -{"id": 21400, "token": "idas", "merges": "id as", "raw_count": 165232, "count": 165232, "decode_str": "idas"} -{"id": 148, "token": "\u00d8", "merges": "NULL", "raw_count": 2286, "count": 165233, "decode_str": "\ufffd"} -{"id": 17656, "token": "ilateral", "merges": "il ateral", "raw_count": 138203, "count": 165236, "decode_str": "ilateral"} -{"id": 18586, "token": "\u0120\"\",", "merges": "\u0120\" \",", "raw_count": 165267, "count": 165267, "decode_str": " \"\","} -{"id": 38070, "token": "558", "merges": "55 8", "raw_count": 165275, "count": 165275, "decode_str": "558"} -{"id": 52381, "token": "\u00e6\u00a9\u00b9", "merges": "\u00e6\u00a9 \u00b9", "raw_count": 165296, "count": 165296, "decode_str": "\u6a79"} -{"id": 45438, "token": "cached", "merges": "c ached", "raw_count": 165321, "count": 165321, "decode_str": "cached"} -{"id": 10208, "token": "\u0120fed", "merges": "\u0120f ed", "raw_count": 159036, "count": 165327, "decode_str": " fed"} -{"id": 17414, "token": "\u0120dialogue", "merges": "\u0120dialog ue", "raw_count": 165335, "count": 165335, "decode_str": " dialogue"} -{"id": 28703, "token": "756", "merges": "75 6", "raw_count": 165341, "count": 165341, "decode_str": "756"} -{"id": 5680, "token": "\u0120border", "merges": "\u0120b order", "raw_count": 164412, "count": 165411, "decode_str": " border"} -{"id": 10921, "token": "\u0120reward", "merges": "\u0120re ward", "raw_count": 157689, "count": 165417, "decode_str": " reward"} -{"id": 6186, "token": "\u0120supply", "merges": "\u0120supp ly", "raw_count": 165424, "count": 165424, "decode_str": " supply"} -{"id": 9846, "token": "will", "merges": "w ill", "raw_count": 165460, "count": 165460, "decode_str": "will"} -{"id": 13174, "token": "people", "merges": "pe ople", "raw_count": 165523, "count": 165524, "decode_str": "people"} -{"id": 19346, "token": "San", "merges": "S an", "raw_count": 165540, "count": 165540, "decode_str": "San"} -{"id": 26942, "token": "704", "merges": "70 4", "raw_count": 165582, "count": 165582, "decode_str": "704"} -{"id": 4034, "token": "omen", "merges": "om en", "raw_count": 32179, "count": 165603, "decode_str": "omen"} -{"id": 30311, "token": "677", "merges": "67 7", "raw_count": 165689, "count": 165689, "decode_str": "677"} -{"id": 5951, "token": "\u0120trig", "merges": "\u0120tr ig", "raw_count": 13126, "count": 165707, "decode_str": " trig"} -{"id": 33546, "token": "889", "merges": "88 9", "raw_count": 165735, "count": 165735, "decode_str": "889"} -{"id": 12505, "token": "tan", "merges": "t an", "raw_count": 134320, "count": 165869, "decode_str": "tan"} -{"id": 7843, "token": "oration", "merges": "or ation", "raw_count": 75420, "count": 165968, "decode_str": "oration"} -{"id": 20750, "token": "Ga", "merges": "G a", "raw_count": 166129, "count": 166129, "decode_str": "Ga"} -{"id": 34277, "token": "442", "merges": "44 2", "raw_count": 166184, "count": 166184, "decode_str": "442"} -{"id": 6111, "token": "irty", "merges": "ir ty", "raw_count": 33190, "count": 166200, "decode_str": "irty"} -{"id": 13046, "token": "agg", "merges": "ag g", "raw_count": 156855, "count": 166204, "decode_str": "agg"} -{"id": 27329, "token": "strings", "merges": "str ings", "raw_count": 166215, "count": 166215, "decode_str": "strings"} -{"id": 8319, "token": "\u012051", "merges": "\u01205 1", "raw_count": 166253, "count": 166253, "decode_str": " 51"} -{"id": 22108, "token": "external", "merges": "ex ternal", "raw_count": 166275, "count": 166275, "decode_str": "external"} -{"id": 28339, "token": "657", "merges": "65 7", "raw_count": 166283, "count": 166283, "decode_str": "657"} -{"id": 5924, "token": "itled", "merges": "it led", "raw_count": 14005, "count": 166308, "decode_str": "itled"} -{"id": 4091, "token": "yond", "merges": "y ond", "raw_count": 1312, "count": 166328, "decode_str": "yond"} -{"id": 35811, "token": "Mg", "merges": "M g", "raw_count": 166381, "count": 166381, "decode_str": "Mg"} -{"id": 5538, "token": "igation", "merges": "ig ation", "raw_count": 24543, "count": 166429, "decode_str": "igation"} -{"id": 32429, "token": "song", "merges": "s ong", "raw_count": 166491, "count": 166491, "decode_str": "song"} -{"id": 15542, "token": "Stand", "merges": "St and", "raw_count": 48296, "count": 166539, "decode_str": "Stand"} -{"id": 5248, "token": "\u0120cast", "merges": "\u0120c ast", "raw_count": 122003, "count": 166553, "decode_str": " cast"} -{"id": 12690, "token": "fact", "merges": "f act", "raw_count": 91332, "count": 166561, "decode_str": "fact"} -{"id": 4441, "token": "\u0120located", "merges": "\u0120loc ated", "raw_count": 166619, "count": 166619, "decode_str": " located"} -{"id": 26607, "token": "\u0120(%", "merges": "\u0120( %", "raw_count": 166654, "count": 166654, "decode_str": " (%"} -{"id": 5827, "token": "\u0120plans", "merges": "\u0120pl ans", "raw_count": 166680, "count": 166680, "decode_str": " plans"} -{"id": 35837, "token": "prepare", "merges": "prep are", "raw_count": 166685, "count": 166685, "decode_str": "prepare"} -{"id": 6626, "token": "iller", "merges": "ill er", "raw_count": 98319, "count": 166809, "decode_str": "iller"} -{"id": 20198, "token": "JP", "merges": "J P", "raw_count": 166796, "count": 166810, "decode_str": "JP"} -{"id": 14892, "token": "\u0120promotion", "merges": "\u0120prom otion", "raw_count": 166869, "count": 166869, "decode_str": " promotion"} -{"id": 4094, "token": "estern", "merges": "es tern", "raw_count": 468, "count": 166886, "decode_str": "estern"} -{"id": 17857, "token": "\u0120ic", "merges": "\u0120 ic", "raw_count": 146494, "count": 166902, "decode_str": " ic"} -{"id": 50740, "token": "\u00e5\u0129\u0129", "merges": "\u00e5\u0129 \u0129", "raw_count": 166946, "count": 166946, "decode_str": "\u51c7"} -{"id": 29343, "token": "learn", "merges": "le arn", "raw_count": 166948, "count": 166948, "decode_str": "learn"} -{"id": 2884, "token": "\u0120Fl", "merges": "\u0120F l", "raw_count": 83067, "count": 166968, "decode_str": " Fl"} -{"id": 34457, "token": "notify", "merges": "not ify", "raw_count": 166985, "count": 166985, "decode_str": "notify"} -{"id": 6594, "token": "ads", "merges": "ad s", "raw_count": 140676, "count": 167015, "decode_str": "ads"} -{"id": 12975, "token": "holders", "merges": "hold ers", "raw_count": 50662, "count": 167058, "decode_str": "holders"} -{"id": 7658, "token": "\u0120constraint", "merges": "\u0120const raint", "raw_count": 82135, "count": 167059, "decode_str": " constraint"} -{"id": 8869, "token": "\u0120creation", "merges": "\u0120cre ation", "raw_count": 167122, "count": 167122, "decode_str": " creation"} -{"id": 54582, "token": "\u00e8\u00aa\u012c", "merges": "\u00e8\u00aa \u012c", "raw_count": 167172, "count": 167172, "decode_str": "\u8a8a"} -{"id": 42980, "token": "535", "merges": "5 35", "raw_count": 167180, "count": 167180, "decode_str": "535"} -{"id": 4983, "token": "\u0120starting", "merges": "\u0120start ing", "raw_count": 167197, "count": 167197, "decode_str": " starting"} -{"id": 19924, "token": "asa", "merges": "as a", "raw_count": 167234, "count": 167234, "decode_str": "asa"} -{"id": 3392, "token": "\u0120father", "merges": "\u0120f ather", "raw_count": 149260, "count": 167243, "decode_str": " father"} -{"id": 28898, "token": "371", "merges": "37 1", "raw_count": 167259, "count": 167259, "decode_str": "371"} -{"id": 21179, "token": "hide", "merges": "h ide", "raw_count": 167294, "count": 167294, "decode_str": "hide"} -{"id": 13371, "token": "\u0120glob", "merges": "\u0120gl ob", "raw_count": 141742, "count": 167332, "decode_str": " glob"} -{"id": 10614, "token": "enny", "merges": "enn y", "raw_count": 161485, "count": 167345, "decode_str": "enny"} -{"id": 33713, "token": "0024", "merges": "00 24", "raw_count": 167361, "count": 167361, "decode_str": "0024"} -{"id": 44095, "token": "hosts", "merges": "host s", "raw_count": 167367, "count": 167367, "decode_str": "hosts"} -{"id": 8518, "token": "ication", "merges": "ic ation", "raw_count": 104266, "count": 167475, "decode_str": "ication"} -{"id": 8125, "token": "aria", "merges": "ar ia", "raw_count": 76640, "count": 167616, "decode_str": "aria"} -{"id": 6235, "token": "\u0120Rem", "merges": "\u0120R em", "raw_count": 36071, "count": 167634, "decode_str": " Rem"} -{"id": 34191, "token": "Science", "merges": "Sc ience", "raw_count": 167678, "count": 167678, "decode_str": "Science"} -{"id": 36615, "token": "OY", "merges": "O Y", "raw_count": 167697, "count": 167697, "decode_str": "OY"} -{"id": 16324, "token": "Record", "merges": "Rec ord", "raw_count": 167741, "count": 167741, "decode_str": "Record"} -{"id": 31879, "token": "Alt", "merges": "Al t", "raw_count": 167743, "count": 167743, "decode_str": "Alt"} -{"id": 53278, "token": "\u00e7\u00b2\u00bf", "merges": "\u00e7\u00b2 \u00bf", "raw_count": 167820, "count": 167820, "decode_str": "\u7cbf"} -{"id": 29827, "token": "392", "merges": "39 2", "raw_count": 167848, "count": 167848, "decode_str": "392"} -{"id": 5765, "token": "\u0120vert", "merges": "\u0120 vert", "raw_count": 27608, "count": 167873, "decode_str": " vert"} -{"id": 52265, "token": "\u00e6\u0141\u00a2", "merges": "\u00e6\u0141 \u00a2", "raw_count": 167922, "count": 167922, "decode_str": "\u67e2"} -{"id": 7089, "token": "\u0120decisions", "merges": "\u0120dec isions", "raw_count": 167954, "count": 167954, "decode_str": " decisions"} -{"id": 22922, "token": "localhost", "merges": "local host", "raw_count": 168044, "count": 168044, "decode_str": "localhost"} -{"id": 4473, "token": "\u0120concept", "merges": "\u0120con cept", "raw_count": 119696, "count": 168093, "decode_str": " concept"} -{"id": 8379, "token": "\u0120successfully", "merges": "\u0120success fully", "raw_count": 168097, "count": 168097, "decode_str": " successfully"} -{"id": 6185, "token": "mic", "merges": "m ic", "raw_count": 149971, "count": 168144, "decode_str": "mic"} -{"id": 4627, "token": "\u0120upp", "merges": "\u0120 upp", "raw_count": 16290, "count": 168166, "decode_str": " upp"} -{"id": 3134, "token": "ensive", "merges": "ens ive", "raw_count": 21457, "count": 168167, "decode_str": "ensive"} -{"id": 48087, "token": "\u0120english", "merges": "\u0120eng lish", "raw_count": 168170, "count": 168170, "decode_str": " english"} -{"id": 4199, "token": "ondon", "merges": "ond on", "raw_count": 87192, "count": 168198, "decode_str": "ondon"} -{"id": 23337, "token": "Love", "merges": "L ove", "raw_count": 168204, "count": 168204, "decode_str": "Love"} -{"id": 31873, "token": "slot", "merges": "sl ot", "raw_count": 168208, "count": 168208, "decode_str": "slot"} -{"id": 14918, "token": "Pop", "merges": "P op", "raw_count": 148443, "count": 168210, "decode_str": "Pop"} -{"id": 45827, "token": "910", "merges": "9 10", "raw_count": 168217, "count": 168217, "decode_str": "910"} -{"id": 16621, "token": "Bi", "merges": "B i", "raw_count": 167260, "count": 168217, "decode_str": "Bi"} -{"id": 3624, "token": "rief", "merges": "ri ef", "raw_count": 14947, "count": 168222, "decode_str": "rief"} -{"id": 20137, "token": "existing", "merges": "ex isting", "raw_count": 168248, "count": 168248, "decode_str": "existing"} -{"id": 50658, "token": "\u00e5\u0124\u00a5", "merges": "\u00e5\u0124 \u00a5", "raw_count": 168291, "count": 168291, "decode_str": "\u50a5"} -{"id": 13325, "token": "Make", "merges": "M ake", "raw_count": 168308, "count": 168308, "decode_str": "Make"} -{"id": 15994, "token": "respons", "merges": "resp ons", "raw_count": 144498, "count": 168327, "decode_str": "respons"} -{"id": 9990, "token": "\u0120statistics", "merges": "\u0120stat istics", "raw_count": 168331, "count": 168331, "decode_str": " statistics"} -{"id": 5050, "token": "\u0120incor", "merges": "\u0120inc or", "raw_count": 2514, "count": 168341, "decode_str": " incor"} -{"id": 25079, "token": "WIN", "merges": "W IN", "raw_count": 168348, "count": 168348, "decode_str": "WIN"} -{"id": 23802, "token": "GI", "merges": "G I", "raw_count": 168353, "count": 168353, "decode_str": "GI"} -{"id": 31280, "token": "Anal", "merges": "An al", "raw_count": 168361, "count": 168361, "decode_str": "Anal"} -{"id": 24859, "token": "VO", "merges": "V O", "raw_count": 168379, "count": 168379, "decode_str": "VO"} -{"id": 10976, "token": "Options", "merges": "O ptions", "raw_count": 168406, "count": 168406, "decode_str": "Options"} -{"id": 19089, "token": "sy", "merges": "s y", "raw_count": 168421, "count": 168421, "decode_str": "sy"} -{"id": 39701, "token": "Studio", "merges": "Stud io", "raw_count": 168424, "count": 168424, "decode_str": "Studio"} -{"id": 47526, "token": "\u0120'+", "merges": "\u0120' +", "raw_count": 168441, "count": 168441, "decode_str": " '+"} -{"id": 4114, "token": "\u0120background", "merges": "\u0120back ground", "raw_count": 168511, "count": 168511, "decode_str": " background"} -{"id": 40918, "token": "salt", "merges": "s alt", "raw_count": 168525, "count": 168525, "decode_str": "salt"} -{"id": 17251, "token": "\u0120Update", "merges": "\u0120Up date", "raw_count": 168543, "count": 168543, "decode_str": " Update"} -{"id": 23562, "token": "FIL", "merges": "F IL", "raw_count": 77224, "count": 168595, "decode_str": "FIL"} -{"id": 21390, "token": "props", "merges": "pro ps", "raw_count": 168604, "count": 168604, "decode_str": "props"} -{"id": 3441, "token": "arily", "merges": "ar ily", "raw_count": 24725, "count": 168617, "decode_str": "arily"} -{"id": 41529, "token": "\u0120Tensor", "merges": "\u0120T ensor", "raw_count": 168618, "count": 168618, "decode_str": " Tensor"} -{"id": 6149, "token": "\u0120earth", "merges": "\u0120ear th", "raw_count": 139806, "count": 168621, "decode_str": " earth"} -{"id": 7970, "token": "\u0120annual", "merges": "\u0120ann ual", "raw_count": 168808, "count": 168808, "decode_str": " annual"} -{"id": 19968, "token": "Bro", "merges": "B ro", "raw_count": 134883, "count": 168823, "decode_str": "Bro"} -{"id": 8790, "token": "\u0120subs", "merges": "\u0120sub s", "raw_count": 76452, "count": 168824, "decode_str": " subs"} -{"id": 7745, "token": "Look", "merges": "L ook", "raw_count": 109552, "count": 168883, "decode_str": "Look"} -{"id": 46103, "token": "sensor", "merges": "sens or", "raw_count": 168887, "count": 168887, "decode_str": "sensor"} -{"id": 25469, "token": "549", "merges": "5 49", "raw_count": 168906, "count": 168906, "decode_str": "549"} -{"id": 8300, "token": "acket", "merges": "ack et", "raw_count": 27418, "count": 168912, "decode_str": "acket"} -{"id": 44734, "token": "hk", "merges": "h k", "raw_count": 168933, "count": 168933, "decode_str": "hk"} -{"id": 10321, "token": "anguages", "merges": "angu ages", "raw_count": 61952, "count": 168986, "decode_str": "anguages"} -{"id": 38941, "token": "PCI", "merges": "PC I", "raw_count": 168989, "count": 168989, "decode_str": "PCI"} -{"id": 15283, "token": "Reader", "merges": "Read er", "raw_count": 169000, "count": 169000, "decode_str": "Reader"} -{"id": 26433, "token": "Lin", "merges": "L in", "raw_count": 169012, "count": 169012, "decode_str": "Lin"} -{"id": 13783, "token": "ifiers", "merges": "if iers", "raw_count": 141416, "count": 169067, "decode_str": "ifiers"} -{"id": 13821, "token": "support", "merges": "supp ort", "raw_count": 169082, "count": 169082, "decode_str": "support"} -{"id": 3206, "token": "\u0120involved", "merges": "\u0120invol ved", "raw_count": 169116, "count": 169116, "decode_str": " involved"} -{"id": 5657, "token": "\u0120tools", "merges": "\u0120to ols", "raw_count": 169145, "count": 169145, "decode_str": " tools"} -{"id": 27682, "token": "Kim", "merges": "K im", "raw_count": 169153, "count": 169153, "decode_str": "Kim"} -{"id": 18348, "token": "029", "merges": "0 29", "raw_count": 169165, "count": 169165, "decode_str": "029"} -{"id": 19882, "token": "chr", "merges": "ch r", "raw_count": 168160, "count": 169174, "decode_str": "chr"} -{"id": 4859, "token": "\u0120links", "merges": "\u0120l inks", "raw_count": 169175, "count": 169175, "decode_str": " links"} -{"id": 51519, "token": "\u00e5\u00b7\u00bf", "merges": "\u00e5\u00b7 \u00bf", "raw_count": 169184, "count": 169184, "decode_str": "\u5dff"} -{"id": 53721, "token": "\u00e8\u00a2\u012a", "merges": "\u00e8\u00a2 \u012a", "raw_count": 169198, "count": 169198, "decode_str": "\u8888"} -{"id": 6323, "token": "\u0120latest", "merges": "\u0120lat est", "raw_count": 169213, "count": 169213, "decode_str": " latest"} -{"id": 3776, "token": "\u0120\u00d0\u00bf", "merges": "\u0120\u00d0 \u00bf", "raw_count": 44868, "count": 169227, "decode_str": " \u043f"} -{"id": 18989, "token": "sol", "merges": "s ol", "raw_count": 168723, "count": 169230, "decode_str": "sol"} -{"id": 24780, "token": "lb", "merges": "l b", "raw_count": 169251, "count": 169251, "decode_str": "lb"} -{"id": 14429, "token": "\u0120entities", "merges": "\u0120ent ities", "raw_count": 169277, "count": 169277, "decode_str": " entities"} -{"id": 15857, "token": "DIS", "merges": "D IS", "raw_count": 168998, "count": 169280, "decode_str": "DIS"} -{"id": 28777, "token": "Hu", "merges": "H u", "raw_count": 169333, "count": 169333, "decode_str": "Hu"} -{"id": 9196, "token": "\u0120pip", "merges": "\u0120p ip", "raw_count": 37765, "count": 169341, "decode_str": " pip"} -{"id": 2546, "token": "\u0120asked", "merges": "\u0120ask ed", "raw_count": 169351, "count": 169351, "decode_str": " asked"} -{"id": 27538, "token": "486", "merges": "48 6", "raw_count": 169371, "count": 169371, "decode_str": "486"} -{"id": 19586, "token": "special", "merges": "spec ial", "raw_count": 169438, "count": 169438, "decode_str": "special"} -{"id": 6853, "token": "etric", "merges": "et ric", "raw_count": 25334, "count": 169444, "decode_str": "etric"} -{"id": 5291, "token": "\u0120<<", "merges": "\u0120< <", "raw_count": 169495, "count": 169495, "decode_str": " <<"} -{"id": 2581, "token": "\u0120rather", "merges": "\u0120r ather", "raw_count": 169532, "count": 169532, "decode_str": " rather"} -{"id": 12618, "token": "Header", "merges": "He ader", "raw_count": 169550, "count": 169550, "decode_str": "Header"} -{"id": 12785, "token": "\u0120territory", "merges": "\u0120territ ory", "raw_count": 169568, "count": 169568, "decode_str": " territory"} -{"id": 14059, "token": "iy", "merges": "i y", "raw_count": 169607, "count": 169607, "decode_str": "iy"} -{"id": 30968, "token": "codes", "merges": "c odes", "raw_count": 169613, "count": 169613, "decode_str": "codes"} -{"id": 34087, "token": "468", "merges": "4 68", "raw_count": 169669, "count": 169669, "decode_str": "468"} -{"id": 23055, "token": "\u0120tv", "merges": "\u0120t v", "raw_count": 169697, "count": 169697, "decode_str": " tv"} -{"id": 4238, "token": "was", "merges": "w as", "raw_count": 167934, "count": 169734, "decode_str": "was"} -{"id": 3727, "token": "\u0120release", "merges": "\u0120rele ase", "raw_count": 169813, "count": 169813, "decode_str": " release"} -{"id": 4705, "token": "iday", "merges": "id ay", "raw_count": 96002, "count": 169822, "decode_str": "iday"} -{"id": 3023, "token": "nu", "merges": "n u", "raw_count": 156127, "count": 169844, "decode_str": "nu"} -{"id": 5521, "token": "orter", "merges": "or ter", "raw_count": 120430, "count": 169867, "decode_str": "orter"} -{"id": 41733, "token": "BOX", "merges": "BO X", "raw_count": 169870, "count": 169870, "decode_str": "BOX"} -{"id": 27827, "token": "lc", "merges": "l c", "raw_count": 169873, "count": 169873, "decode_str": "lc"} -{"id": 6096, "token": "\u0120shared", "merges": "\u0120sh ared", "raw_count": 169879, "count": 169879, "decode_str": " shared"} -{"id": 18458, "token": "perature", "merges": "per ature", "raw_count": 33972, "count": 169902, "decode_str": "perature"} -{"id": 12095, "token": "\u0120destination", "merges": "\u0120dest ination", "raw_count": 169924, "count": 169924, "decode_str": " destination"} -{"id": 45362, "token": "CMS", "merges": "C MS", "raw_count": 169947, "count": 169947, "decode_str": "CMS"} -{"id": 23538, "token": "isco", "merges": "is co", "raw_count": 166551, "count": 169960, "decode_str": "isco"} -{"id": 47477, "token": "Sport", "merges": "S port", "raw_count": 169975, "count": 169975, "decode_str": "Sport"} -{"id": 54430, "token": "\u00e9\u00a1\u00bc", "merges": "\u00e9\u00a1 \u00bc", "raw_count": 169991, "count": 169991, "decode_str": "\u987c"} -{"id": 3304, "token": "\u0120inside", "merges": "\u0120ins ide", "raw_count": 170013, "count": 170013, "decode_str": " inside"} -{"id": 20188, "token": "fixed", "merges": "f ixed", "raw_count": 170023, "count": 170023, "decode_str": "fixed"} -{"id": 19720, "token": "panel", "merges": "pan el", "raw_count": 170073, "count": 170073, "decode_str": "panel"} -{"id": 42583, "token": "stride", "merges": "str ide", "raw_count": 170137, "count": 170137, "decode_str": "stride"} -{"id": 34164, "token": "ssh", "merges": "ss h", "raw_count": 170142, "count": 170142, "decode_str": "ssh"} -{"id": 4609, "token": "which", "merges": "wh ich", "raw_count": 170147, "count": 170147, "decode_str": "which"} -{"id": 44219, "token": "523", "merges": "5 23", "raw_count": 170180, "count": 170180, "decode_str": "523"} -{"id": 24322, "token": "ods", "merges": "od s", "raw_count": 170186, "count": 170186, "decode_str": "ods"} -{"id": 24581, "token": "080", "merges": "0 80", "raw_count": 170189, "count": 170189, "decode_str": "080"} -{"id": 5442, "token": "anned", "merges": "ann ed", "raw_count": 46819, "count": 170197, "decode_str": "anned"} -{"id": 3554, "token": "\u0120chem", "merges": "\u0120che m", "raw_count": 10080, "count": 170233, "decode_str": " chem"} -{"id": 18213, "token": "\u0120labour", "merges": "\u0120lab our", "raw_count": 170274, "count": 170274, "decode_str": " labour"} -{"id": 53902, "token": "\u00e8\u00b1\u00a2", "merges": "\u00e8\u00b1 \u00a2", "raw_count": 170292, "count": 170292, "decode_str": "\u8c62"} -{"id": 4382, "token": "\u0120computer", "merges": "\u0120comput er", "raw_count": 166079, "count": 170303, "decode_str": " computer"} -{"id": 30579, "token": "Force", "merges": "For ce", "raw_count": 170324, "count": 170324, "decode_str": "Force"} -{"id": 3692, "token": "\u0120whose", "merges": "\u0120wh ose", "raw_count": 170357, "count": 170357, "decode_str": " whose"} -{"id": 4732, "token": "\u0120virt", "merges": "\u0120vir t", "raw_count": 12990, "count": 170359, "decode_str": " virt"} -{"id": 23813, "token": "compare", "merges": "comp are", "raw_count": 170547, "count": 170547, "decode_str": "compare"} -{"id": 36838, "token": "\u0120parsed", "merges": "\u0120pars ed", "raw_count": 170547, "count": 170547, "decode_str": " parsed"} -{"id": 51738, "token": "\u00e6\u0124\u012e", "merges": "\u00e6\u0124 \u012e", "raw_count": 170551, "count": 170551, "decode_str": "\u608c"} -{"id": 3668, "token": "\u0120news", "merges": "\u0120new s", "raw_count": 155645, "count": 170657, "decode_str": " news"} -{"id": 8410, "token": "\u0120employment", "merges": "\u0120employ ment", "raw_count": 170666, "count": 170666, "decode_str": " employment"} -{"id": 4480, "token": "\u0120Trans", "merges": "\u0120Tr ans", "raw_count": 55200, "count": 170681, "decode_str": " Trans"} -{"id": 29543, "token": "656", "merges": "65 6", "raw_count": 170697, "count": 170697, "decode_str": "656"} -{"id": 10860, "token": "URE", "merges": "U RE", "raw_count": 121220, "count": 170762, "decode_str": "URE"} -{"id": 7769, "token": "defined", "merges": "def ined", "raw_count": 98110, "count": 170763, "decode_str": "defined"} -{"id": 11345, "token": "aws", "merges": "aw s", "raw_count": 163994, "count": 170765, "decode_str": "aws"} -{"id": 25606, "token": "ATP", "merges": "AT P", "raw_count": 170856, "count": 170856, "decode_str": "ATP"} -{"id": 23262, "token": "Ray", "merges": "R ay", "raw_count": 170916, "count": 170916, "decode_str": "Ray"} -{"id": 8135, "token": "\u0120shell", "merges": "\u0120she ll", "raw_count": 163017, "count": 170956, "decode_str": " shell"} -{"id": 22118, "token": "\u0120stats", "merges": "\u0120stat s", "raw_count": 171013, "count": 171013, "decode_str": " stats"} -{"id": 54604, "token": "\u00ef\u00bc\u0127", "merges": "\u00ef\u00bc \u0127", "raw_count": 171052, "count": 171052, "decode_str": "\uff05"} -{"id": 10932, "token": "\u0120organized", "merges": "\u0120organ ized", "raw_count": 171057, "count": 171057, "decode_str": " organized"} -{"id": 6748, "token": "ading", "merges": "ad ing", "raw_count": 127423, "count": 171073, "decode_str": "ading"} -{"id": 36273, "token": "Pixel", "merges": "P ixel", "raw_count": 171108, "count": 171108, "decode_str": "Pixel"} -{"id": 51234, "token": "\u00e5\u0141\u0137", "merges": "\u00e5\u0141 \u0137", "raw_count": 171130, "count": 171130, "decode_str": "\u57d5"} -{"id": 52539, "token": "\u00e6\u00b3\u00ae", "merges": "\u00e6\u00b3 \u00ae", "raw_count": 171150, "count": 171150, "decode_str": "\u6cee"} -{"id": 8255, "token": "\u012054", "merges": "\u01205 4", "raw_count": 171198, "count": 171198, "decode_str": " 54"} -{"id": 19822, "token": "atted", "merges": "att ed", "raw_count": 104638, "count": 171206, "decode_str": "atted"} -{"id": 43488, "token": "checks", "merges": "che cks", "raw_count": 171238, "count": 171238, "decode_str": "checks"} -{"id": 28872, "token": "problem", "merges": "pro blem", "raw_count": 171249, "count": 171249, "decode_str": "problem"} -{"id": 21760, "token": ">\"", "merges": "> \"", "raw_count": 171252, "count": 171252, "decode_str": ">\""} -{"id": 18667, "token": "~~~~~~~~", "merges": "~~~~ ~~~~", "raw_count": 80547, "count": 171255, "decode_str": "~~~~~~~~"} -{"id": 6751, "token": "\u0120prosec", "merges": "\u0120pro sec", "raw_count": 14919, "count": 171305, "decode_str": " prosec"} -{"id": 7278, "token": "\u0120enhance", "merges": "\u0120enh ance", "raw_count": 142058, "count": 171338, "decode_str": " enhance"} -{"id": 5387, "token": "\u0120dut", "merges": "\u0120d ut", "raw_count": 31543, "count": 171361, "decode_str": " dut"} -{"id": 17439, "token": "construct", "merges": "con struct", "raw_count": 108903, "count": 171375, "decode_str": "construct"} -{"id": 26541, "token": "695", "merges": "69 5", "raw_count": 171377, "count": 171377, "decode_str": "695"} -{"id": 3053, "token": "\u0120started", "merges": "\u0120start ed", "raw_count": 171388, "count": 171388, "decode_str": " started"} -{"id": 11540, "token": "Ident", "merges": "Id ent", "raw_count": 43373, "count": 171398, "decode_str": "Ident"} -{"id": 11580, "token": "\u0120visited", "merges": "\u0120vis ited", "raw_count": 171434, "count": 171434, "decode_str": " visited"} -{"id": 16951, "token": "\u0120360", "merges": "\u01203 60", "raw_count": 171444, "count": 171444, "decode_str": " 360"} -{"id": 10129, "token": "\u0120matches", "merges": "\u0120mat ches", "raw_count": 171515, "count": 171515, "decode_str": " matches"} -{"id": 23108, "token": "George", "merges": "Ge orge", "raw_count": 171515, "count": 171515, "decode_str": "George"} -{"id": 25322, "token": "statement", "merges": "stat ement", "raw_count": 171518, "count": 171518, "decode_str": "statement"} -{"id": 29203, "token": "shop", "merges": "sh op", "raw_count": 171548, "count": 171548, "decode_str": "shop"} -{"id": 19618, "token": "mouse", "merges": "m ouse", "raw_count": 171571, "count": 171571, "decode_str": "mouse"} -{"id": 1869, "token": "\u0120thought", "merges": "\u0120th ought", "raw_count": 142056, "count": 171688, "decode_str": " thought"} -{"id": 8941, "token": "achment", "merges": "ach ment", "raw_count": 31564, "count": 171703, "decode_str": "achment"} -{"id": 12840, "token": "berry", "merges": "ber ry", "raw_count": 154911, "count": 171755, "decode_str": "berry"} -{"id": 5643, "token": "tre", "merges": "t re", "raw_count": 86494, "count": 171766, "decode_str": "tre"} -{"id": 14224, "token": "border", "merges": "b order", "raw_count": 171805, "count": 171805, "decode_str": "border"} -{"id": 24526, "token": "Daniel", "merges": "Dan iel", "raw_count": 171808, "count": 171808, "decode_str": "Daniel"} -{"id": 37170, "token": "428", "merges": "4 28", "raw_count": 171810, "count": 171810, "decode_str": "428"} -{"id": 18971, "token": "NM", "merges": "N M", "raw_count": 171855, "count": 171855, "decode_str": "NM"} -{"id": 11577, "token": "internal", "merges": "in ternal", "raw_count": 171863, "count": 171863, "decode_str": "internal"} -{"id": 45607, "token": "Market", "merges": "Mark et", "raw_count": 171880, "count": 171880, "decode_str": "Market"} -{"id": 53096, "token": "\u00e7\u00a2\u00a3", "merges": "\u00e7\u00a2 \u00a3", "raw_count": 171893, "count": 171893, "decode_str": "\u78a3"} -{"id": 35800, "token": "bounds", "merges": "b ounds", "raw_count": 171896, "count": 171896, "decode_str": "bounds"} -{"id": 1009, "token": ")$", "merges": ") $", "raw_count": 147019, "count": 171907, "decode_str": ")$"} -{"id": 5240, "token": "omin", "merges": "om in", "raw_count": 117887, "count": 171925, "decode_str": "omin"} -{"id": 23716, "token": "ocity", "merges": "oc ity", "raw_count": 40862, "count": 171932, "decode_str": "ocity"} -{"id": 53670, "token": "\u00e8\u0130\u00aa", "merges": "\u00e8\u0130 \u00aa", "raw_count": 171956, "count": 171956, "decode_str": "\u83aa"} -{"id": 52235, "token": "\u00e6\u0140\u012d", "merges": "\u00e6\u0140 \u012d", "raw_count": 171982, "count": 171982, "decode_str": "\u678b"} -{"id": 4831, "token": "\u0120demand", "merges": "\u0120dem and", "raw_count": 144588, "count": 172030, "decode_str": " demand"} -{"id": 30965, "token": "412", "merges": "4 12", "raw_count": 172040, "count": 172040, "decode_str": "412"} -{"id": 31845, "token": "\u0120strengthening", "merges": "\u0120streng thening", "raw_count": 172163, "count": 172163, "decode_str": " strengthening"} -{"id": 36034, "token": "encoded", "merges": "enc oded", "raw_count": 172168, "count": 172168, "decode_str": "encoded"} -{"id": 52388, "token": "\u00e6\u00ac\u00b8", "merges": "\u00e6\u00ac \u00b8", "raw_count": 172270, "count": 172270, "decode_str": "\u6b38"} -{"id": 6509, "token": "\u0120categ", "merges": "\u0120c ateg", "raw_count": 3235, "count": 172297, "decode_str": " categ"} -{"id": 40555, "token": "CAN", "merges": "C AN", "raw_count": 172297, "count": 172297, "decode_str": "CAN"} -{"id": 44296, "token": "\u0120fp", "merges": "\u0120f p", "raw_count": 172317, "count": 172317, "decode_str": " fp"} -{"id": 25314, "token": "ZZ", "merges": "Z Z", "raw_count": 172323, "count": 172323, "decode_str": "ZZ"} -{"id": 36677, "token": "435", "merges": "4 35", "raw_count": 172327, "count": 172327, "decode_str": "435"} -{"id": 15160, "token": "every", "merges": "e very", "raw_count": 139739, "count": 172371, "decode_str": "every"} -{"id": 5931, "token": "\u0120chain", "merges": "\u0120ch ain", "raw_count": 172382, "count": 172382, "decode_str": " chain"} -{"id": 7806, "token": "phen", "merges": "p hen", "raw_count": 41464, "count": 172390, "decode_str": "phen"} -{"id": 4205, "token": "\u0120mount", "merges": "\u0120m ount", "raw_count": 58729, "count": 172391, "decode_str": " mount"} -{"id": 26826, "token": "uo", "merges": "u o", "raw_count": 172430, "count": 172430, "decode_str": "uo"} -{"id": 25310, "token": "Bill", "merges": "B ill", "raw_count": 172436, "count": 172436, "decode_str": "Bill"} -{"id": 25020, "token": "648", "merges": "64 8", "raw_count": 172455, "count": 172455, "decode_str": "648"} -{"id": 52209, "token": "\u00e6\u013f\u012a", "merges": "\u00e6\u013f \u012a", "raw_count": 172513, "count": 172513, "decode_str": "\u6748"} -{"id": 8328, "token": "isters", "merges": "is ters", "raw_count": 63985, "count": 172554, "decode_str": "isters"} -{"id": 40506, "token": "1001", "merges": "100 1", "raw_count": 172559, "count": 172559, "decode_str": "1001"} -{"id": 50597, "token": "\u00e4\u00bf\u0130", "merges": "\u00e4\u00bf \u0130", "raw_count": 172562, "count": 172562, "decode_str": "\u4fce"} -{"id": 6544, "token": "\u0120appoint", "merges": "\u0120app oint", "raw_count": 27098, "count": 172585, "decode_str": " appoint"} -{"id": 9432, "token": "har", "merges": "h ar", "raw_count": 162862, "count": 172629, "decode_str": "har"} -{"id": 5994, "token": "prime", "merges": "pr ime", "raw_count": 172644, "count": 172644, "decode_str": "prime"} -{"id": 9787, "token": "\u0120industrial", "merges": "\u0120indust rial", "raw_count": 172670, "count": 172670, "decode_str": " industrial"} -{"id": 9996, "token": "\u0120transaction", "merges": "\u0120trans action", "raw_count": 172675, "count": 172675, "decode_str": " transaction"} -{"id": 15426, "token": "Sal", "merges": "S al", "raw_count": 171963, "count": 172732, "decode_str": "Sal"} -{"id": 7697, "token": "enance", "merges": "en ance", "raw_count": 7739, "count": 172753, "decode_str": "enance"} -{"id": 29195, "token": "654", "merges": "65 4", "raw_count": 172777, "count": 172777, "decode_str": "654"} -{"id": 39540, "token": "JJ", "merges": "J J", "raw_count": 172802, "count": 172802, "decode_str": "JJ"} -{"id": 4169, "token": "\u00d1\u012e", "merges": "\u00d1 \u012e", "raw_count": 49571, "count": 172872, "decode_str": "\u044c"} -{"id": 5140, "token": "\u0120construction", "merges": "\u0120const ruction", "raw_count": 172877, "count": 172877, "decode_str": " construction"} -{"id": 13774, "token": "aid", "merges": "a id", "raw_count": 172886, "count": 172886, "decode_str": "aid"} -{"id": 14897, "token": "Author", "merges": "Aut hor", "raw_count": 172914, "count": 172914, "decode_str": "Author"} -{"id": 2181, "token": "\u0120thing", "merges": "\u0120th ing", "raw_count": 172922, "count": 172922, "decode_str": " thing"} -{"id": 15328, "token": "lay", "merges": "l ay", "raw_count": 124886, "count": 172924, "decode_str": "lay"} -{"id": 6702, "token": "arden", "merges": "ard en", "raw_count": 93076, "count": 172931, "decode_str": "arden"} -{"id": 7789, "token": "\u0120branch", "merges": "\u0120br anch", "raw_count": 169496, "count": 172935, "decode_str": " branch"} -{"id": 18675, "token": "Cu", "merges": "C u", "raw_count": 172936, "count": 172936, "decode_str": "Cu"} -{"id": 3402, "token": "\u0120wall", "merges": "\u0120w all", "raw_count": 136207, "count": 172939, "decode_str": " wall"} -{"id": 10711, "token": "\u0120trace", "merges": "\u0120tr ace", "raw_count": 172944, "count": 172944, "decode_str": " trace"} -{"id": 20502, "token": "station", "merges": "st ation", "raw_count": 172960, "count": 172960, "decode_str": "station"} -{"id": 30349, "token": "703", "merges": "70 3", "raw_count": 172962, "count": 172962, "decode_str": "703"} -{"id": 16319, "token": "ACH", "merges": "AC H", "raw_count": 172962, "count": 172962, "decode_str": "ACH"} -{"id": 11929, "token": "\u0120submit", "merges": "\u0120sub mit", "raw_count": 172965, "count": 172965, "decode_str": " submit"} -{"id": 33281, "token": "Management", "merges": "Man agement", "raw_count": 173025, "count": 173025, "decode_str": "Management"} -{"id": 5567, "token": "istant", "merges": "ist ant", "raw_count": 94109, "count": 173034, "decode_str": "istant"} -{"id": 8441, "token": "\u01201996", "merges": "\u0120199 6", "raw_count": 173142, "count": 173142, "decode_str": " 1996"} -{"id": 8223, "token": "\u0120segment", "merges": "\u0120se gment", "raw_count": 145834, "count": 173160, "decode_str": " segment"} -{"id": 4973, "token": "\u0120sources", "merges": "\u0120s ources", "raw_count": 173174, "count": 173174, "decode_str": " sources"} -{"id": 15697, "token": "issue", "merges": "iss ue", "raw_count": 172690, "count": 173262, "decode_str": "issue"} -{"id": 3578, "token": "\u0120ten", "merges": "\u0120t en", "raw_count": 101276, "count": 173298, "decode_str": " ten"} -{"id": 35824, "token": ",...", "merges": ", ...", "raw_count": 173312, "count": 173312, "decode_str": ",..."} -{"id": 35808, "token": "902", "merges": "90 2", "raw_count": 173329, "count": 173329, "decode_str": "902"} -{"id": 9802, "token": "have", "merges": "h ave", "raw_count": 173358, "count": 173358, "decode_str": "have"} -{"id": 5778, "token": "\u0120delay", "merges": "\u0120del ay", "raw_count": 139424, "count": 173394, "decode_str": " delay"} -{"id": 8978, "token": "\u012059", "merges": "\u01205 9", "raw_count": 173397, "count": 173397, "decode_str": " 59"} -{"id": 29469, "token": "unknown", "merges": "un known", "raw_count": 173401, "count": 173401, "decode_str": "unknown"} -{"id": 51372, "token": "\u00e5\u00a7\u00b9", "merges": "\u00e5\u00a7 \u00b9", "raw_count": 173411, "count": 173411, "decode_str": "\u59f9"} -{"id": 15960, "token": "030", "merges": "0 30", "raw_count": 173472, "count": 173472, "decode_str": "030"} -{"id": 23838, "token": "nr", "merges": "n r", "raw_count": 173522, "count": 173522, "decode_str": "nr"} -{"id": 16331, "token": "\u012008", "merges": "\u01200 8", "raw_count": 173572, "count": 173572, "decode_str": " 08"} -{"id": 18480, "token": "information", "merges": "in formation", "raw_count": 173682, "count": 173682, "decode_str": "information"} -{"id": 3986, "token": "\u0120reach", "merges": "\u0120re ach", "raw_count": 138868, "count": 173691, "decode_str": " reach"} -{"id": 4982, "token": "\"},", "merges": "\"} ,", "raw_count": 173716, "count": 173716, "decode_str": "\"},"} -{"id": 11847, "token": "\u0120commitment", "merges": "\u0120commit ment", "raw_count": 173729, "count": 173729, "decode_str": " commitment"} -{"id": 16295, "token": "Rule", "merges": "R ule", "raw_count": 173856, "count": 173856, "decode_str": "Rule"} -{"id": 23295, "token": "keyword", "merges": "key word", "raw_count": 173916, "count": 173916, "decode_str": "keyword"} -{"id": 8848, "token": "\u0120institution", "merges": "\u0120instit ution", "raw_count": 63176, "count": 174042, "decode_str": " institution"} -{"id": 9439, "token": "00000", "merges": "00 000", "raw_count": 174057, "count": 174057, "decode_str": "00000"} -{"id": 3021, "token": "\u0120thus", "merges": "\u0120th us", "raw_count": 174058, "count": 174058, "decode_str": " thus"} -{"id": 22495, "token": "Multi", "merges": "Mult i", "raw_count": 174075, "count": 174075, "decode_str": "Multi"} -{"id": 53739, "token": "\u00e8\u00a3\u0141", "merges": "\u00e8\u00a3 \u0141", "raw_count": 174121, "count": 174121, "decode_str": "\u88df"} -{"id": 4907, "token": "\u0120named", "merges": "\u0120n amed", "raw_count": 174167, "count": 174167, "decode_str": " named"} -{"id": 53444, "token": "\u00e8\u0122\u0126", "merges": "\u00e8\u0122 \u0126", "raw_count": 174222, "count": 174222, "decode_str": "\u8004"} -{"id": 9818, "token": "ARE", "merges": "AR E", "raw_count": 142462, "count": 174234, "decode_str": "ARE"} -{"id": 13186, "token": "Const", "merges": "Con st", "raw_count": 42587, "count": 174274, "decode_str": "Const"} -{"id": 12135, "token": "activity", "merges": "act ivity", "raw_count": 174400, "count": 174402, "decode_str": "activity"} -{"id": 9343, "token": "PCR", "merges": "P CR", "raw_count": 170767, "count": 174407, "decode_str": "PCR"} -{"id": 31560, "token": "vertex", "merges": "ver tex", "raw_count": 174419, "count": 174419, "decode_str": "vertex"} -{"id": 13818, "token": "\u0120ms", "merges": "\u0120m s", "raw_count": 174424, "count": 174424, "decode_str": " ms"} -{"id": 9368, "token": "\u0120Call", "merges": "\u0120C all", "raw_count": 157742, "count": 174432, "decode_str": " Call"} -{"id": 12064, "token": "aussian", "merges": "auss ian", "raw_count": 92581, "count": 174462, "decode_str": "aussian"} -{"id": 8090, "token": "\u0120layers", "merges": "\u0120lay ers", "raw_count": 174494, "count": 174494, "decode_str": " layers"} -{"id": 4648, "token": "\u0120uses", "merges": "\u0120us es", "raw_count": 174499, "count": 174499, "decode_str": " uses"} -{"id": 12209, "token": "\u0120forum", "merges": "\u0120for um", "raw_count": 174570, "count": 174570, "decode_str": " forum"} -{"id": 19766, "token": "fu", "merges": "f u", "raw_count": 174570, "count": 174570, "decode_str": "fu"} -{"id": 13269, "token": "023", "merges": "0 23", "raw_count": 174579, "count": 174579, "decode_str": "023"} -{"id": 13917, "token": "via", "merges": "v ia", "raw_count": 174590, "count": 174590, "decode_str": "via"} -{"id": 20072, "token": "LT", "merges": "L T", "raw_count": 174612, "count": 174612, "decode_str": "LT"} -{"id": 23098, "token": "AIN", "merges": "A IN", "raw_count": 174636, "count": 174636, "decode_str": "AIN"} -{"id": 6849, "token": "\u0120views", "merges": "\u0120view s", "raw_count": 174665, "count": 174665, "decode_str": " views"} -{"id": 8707, "token": "orts", "merges": "ort s", "raw_count": 161291, "count": 174670, "decode_str": "orts"} -{"id": 2789, "token": "\u0120makes", "merges": "\u0120m akes", "raw_count": 174719, "count": 174719, "decode_str": " makes"} -{"id": 4768, "token": "\u0120throughout", "merges": "\u0120through out", "raw_count": 174720, "count": 174720, "decode_str": " throughout"} -{"id": 47984, "token": "heap", "merges": "he ap", "raw_count": 174763, "count": 174763, "decode_str": "heap"} -{"id": 5162, "token": "\u0120processing", "merges": "\u0120process ing", "raw_count": 174765, "count": 174765, "decode_str": " processing"} -{"id": 9956, "token": "\u0120rooms", "merges": "\u0120room s", "raw_count": 174771, "count": 174771, "decode_str": " rooms"} -{"id": 15130, "token": "INK", "merges": "IN K", "raw_count": 91436, "count": 174779, "decode_str": "INK"} -{"id": 13814, "token": "\u0120Python", "merges": "\u0120Py thon", "raw_count": 174835, "count": 174835, "decode_str": " Python"} -{"id": 42999, "token": "\u0120aust", "merges": "\u0120a ust", "raw_count": 174846, "count": 174846, "decode_str": " aust"} -{"id": 3702, "token": "uary", "merges": "u ary", "raw_count": 158339, "count": 174863, "decode_str": "uary"} -{"id": 24712, "token": "repeat", "merges": "re peat", "raw_count": 174887, "count": 174887, "decode_str": "repeat"} -{"id": 22132, "token": "\u0120peoples", "merges": "\u0120pe oples", "raw_count": 174895, "count": 174895, "decode_str": " peoples"} -{"id": 21459, "token": "PEG", "merges": "PE G", "raw_count": 174982, "count": 174982, "decode_str": "PEG"} -{"id": 34923, "token": "inian", "merges": "in ian", "raw_count": 175016, "count": 175016, "decode_str": "inian"} -{"id": 8705, "token": "cean", "merges": "ce an", "raw_count": 100504, "count": 175031, "decode_str": "cean"} -{"id": 4099, "token": "rench", "merges": "ren ch", "raw_count": 143608, "count": 175044, "decode_str": "rench"} -{"id": 11208, "token": "ordan", "merges": "ord an", "raw_count": 68360, "count": 175086, "decode_str": "ordan"} -{"id": 5182, "token": "ria", "merges": "ri a", "raw_count": 170555, "count": 175119, "decode_str": "ria"} -{"id": 3155, "token": "ych", "merges": "y ch", "raw_count": 38757, "count": 175188, "decode_str": "ych"} -{"id": 5861, "token": "\u0120records", "merges": "\u0120record s", "raw_count": 175197, "count": 175197, "decode_str": " records"} -{"id": 14543, "token": "tn", "merges": "t n", "raw_count": 102768, "count": 175254, "decode_str": "tn"} -{"id": 7731, "token": "\u0120customer", "merges": "\u0120custom er", "raw_count": 175269, "count": 175269, "decode_str": " customer"} -{"id": 8026, "token": "\u012056", "merges": "\u01205 6", "raw_count": 175297, "count": 175297, "decode_str": " 56"} -{"id": 30763, "token": "Deep", "merges": "De ep", "raw_count": 175300, "count": 175300, "decode_str": "Deep"} -{"id": 3691, "token": "oma", "merges": "om a", "raw_count": 159959, "count": 175321, "decode_str": "oma"} -{"id": 23062, "token": "Meta", "merges": "M eta", "raw_count": 175323, "count": 175323, "decode_str": "Meta"} -{"id": 10085, "token": "\u0120accommod", "merges": "\u0120accom mod", "raw_count": 8375, "count": 175339, "decode_str": " accommod"} -{"id": 26824, "token": "hit", "merges": "h it", "raw_count": 175346, "count": 175346, "decode_str": "hit"} -{"id": 36066, "token": "IPE", "merges": "IP E", "raw_count": 175357, "count": 175357, "decode_str": "IPE"} -{"id": 3553, "token": "\u0120leave", "merges": "\u0120le ave", "raw_count": 175374, "count": 175374, "decode_str": " leave"} -{"id": 22772, "token": "visible", "merges": "vis ible", "raw_count": 175408, "count": 175408, "decode_str": "visible"} -{"id": 38349, "token": "hua", "merges": "h ua", "raw_count": 175427, "count": 175427, "decode_str": "hua"} -{"id": 16760, "token": "National", "merges": "N ational", "raw_count": 175504, "count": 175504, "decode_str": "National"} -{"id": 16532, "token": "market", "merges": "mark et", "raw_count": 170018, "count": 175549, "decode_str": "market"} -{"id": 42949, "token": "528", "merges": "5 28", "raw_count": 175583, "count": 175583, "decode_str": "528"} -{"id": 22307, "token": "RP", "merges": "R P", "raw_count": 175599, "count": 175599, "decode_str": "RP"} -{"id": 4295, "token": "\u0120components", "merges": "\u0120compon ents", "raw_count": 175622, "count": 175622, "decode_str": " components"} -{"id": 17708, "token": "covery", "merges": "co very", "raw_count": 122497, "count": 175633, "decode_str": "covery"} -{"id": 25595, "token": "CAR", "merges": "C AR", "raw_count": 175681, "count": 175681, "decode_str": "CAR"} -{"id": 54257, "token": "\u00e9\u0137\u0137", "merges": "\u00e9\u0137 \u0137", "raw_count": 175727, "count": 175727, "decode_str": "\u9555"} -{"id": 9717, "token": "\u0120Err", "merges": "\u0120E rr", "raw_count": 13528, "count": 175750, "decode_str": " Err"} -{"id": 12953, "token": "\u0120namespace", "merges": "\u0120names pace", "raw_count": 175784, "count": 175784, "decode_str": " namespace"} -{"id": 18004, "token": "ARK", "merges": "AR K", "raw_count": 106766, "count": 175788, "decode_str": "ARK"} -{"id": 2847, "token": "\u0120cause", "merges": "\u0120c ause", "raw_count": 175803, "count": 175803, "decode_str": " cause"} -{"id": 33868, "token": "898", "merges": "89 8", "raw_count": 175804, "count": 175804, "decode_str": "898"} -{"id": 3841, "token": "oles", "merges": "ol es", "raw_count": 95455, "count": 175829, "decode_str": "oles"} -{"id": 11865, "token": "\u0120paths", "merges": "\u0120path s", "raw_count": 175856, "count": 175856, "decode_str": " paths"} -{"id": 53831, "token": "\u00e8\u00af\u00a4", "merges": "\u00e8\u00af \u00a4", "raw_count": 175874, "count": 175874, "decode_str": "\u8be4"} -{"id": 9928, "token": "\u0120permanent", "merges": "\u0120perman ent", "raw_count": 175920, "count": 175920, "decode_str": " permanent"} -{"id": 19118, "token": "INTER", "merges": "IN TER", "raw_count": 175923, "count": 175923, "decode_str": "INTER"} -{"id": 35817, "token": "cards", "merges": "c ards", "raw_count": 175955, "count": 175955, "decode_str": "cards"} -{"id": 11350, "token": "\u0120agric", "merges": "\u0120ag ric", "raw_count": 2054, "count": 175961, "decode_str": " agric"} -{"id": 4740, "token": "aste", "merges": "as te", "raw_count": 73895, "count": 175987, "decode_str": "aste"} -{"id": 5250, "token": "aching", "merges": "ach ing", "raw_count": 62871, "count": 176039, "decode_str": "aching"} -{"id": 50202, "token": "mkdir", "merges": "mk dir", "raw_count": 176045, "count": 176045, "decode_str": "mkdir"} -{"id": 3764, "token": "vere", "merges": "ve re", "raw_count": 16510, "count": 176045, "decode_str": "vere"} -{"id": 12201, "token": "\u0120flags", "merges": "\u0120fl ags", "raw_count": 176100, "count": 176100, "decode_str": " flags"} -{"id": 4848, "token": "\u0120rob", "merges": "\u0120ro b", "raw_count": 25025, "count": 176104, "decode_str": " rob"} -{"id": 3850, "token": "fered", "merges": "fe red", "raw_count": 28675, "count": 176113, "decode_str": "fered"} -{"id": 6237, "token": "\u0120suff", "merges": "\u0120su ff", "raw_count": 9137, "count": 176226, "decode_str": " suff"} -{"id": 3794, "token": "\u0120respond", "merges": "\u0120resp ond", "raw_count": 88091, "count": 176284, "decode_str": " respond"} -{"id": 4363, "token": "wide", "merges": "w ide", "raw_count": 97143, "count": 176336, "decode_str": "wide"} -{"id": 25804, "token": "Team", "merges": "Te am", "raw_count": 176338, "count": 176338, "decode_str": "Team"} -{"id": 9410, "token": "\u0120contents", "merges": "\u0120cont ents", "raw_count": 176339, "count": 176339, "decode_str": " contents"} -{"id": 16754, "token": "Active", "merges": "Act ive", "raw_count": 176371, "count": 176371, "decode_str": "Active"} -{"id": 7952, "token": "\u0120climate", "merges": "\u0120cl imate", "raw_count": 176408, "count": 176408, "decode_str": " climate"} -{"id": 5897, "token": "\u0120tempor", "merges": "\u0120tem por", "raw_count": 4699, "count": 176430, "decode_str": " tempor"} -{"id": 3002, "token": "dro", "merges": "d ro", "raw_count": 61322, "count": 176467, "decode_str": "dro"} -{"id": 26316, "token": "destroy", "merges": "dest roy", "raw_count": 176492, "count": 176492, "decode_str": "destroy"} -{"id": 51261, "token": "\u00e5\u00a2\u012b", "merges": "\u00e5\u00a2 \u012b", "raw_count": 176518, "count": 176518, "decode_str": "\u5889"} -{"id": 9388, "token": "lar", "merges": "l ar", "raw_count": 69399, "count": 176660, "decode_str": "lar"} -{"id": 17973, "token": "\u0120obligations", "merges": "\u0120oblig ations", "raw_count": 176683, "count": 176683, "decode_str": " obligations"} -{"id": 53971, "token": "\u00e8\u00b5\u0143", "merges": "\u00e8\u00b5 \u0143", "raw_count": 176709, "count": 176709, "decode_str": "\u8d6d"} -{"id": 38693, "token": "433", "merges": "4 33", "raw_count": 176732, "count": 176732, "decode_str": "433"} -{"id": 6254, "token": "\u0120driver", "merges": "\u0120dri ver", "raw_count": 176737, "count": 176737, "decode_str": " driver"} -{"id": 31007, "token": "registry", "merges": "reg istry", "raw_count": 176758, "count": 176758, "decode_str": "registry"} -{"id": 24979, "token": "Warning", "merges": "W arning", "raw_count": 176865, "count": 176865, "decode_str": "Warning"} -{"id": 2883, "token": "\u0120fav", "merges": "\u0120f av", "raw_count": 12282, "count": 176940, "decode_str": " fav"} -{"id": 5569, "token": "\u0120lock", "merges": "\u0120l ock", "raw_count": 127810, "count": 176994, "decode_str": " lock"} -{"id": 6887, "token": "\u0120positions", "merges": "\u0120position s", "raw_count": 177015, "count": 177015, "decode_str": " positions"} -{"id": 46829, "token": "movie", "merges": "mov ie", "raw_count": 177048, "count": 177048, "decode_str": "movie"} -{"id": 29805, "token": "885", "merges": "88 5", "raw_count": 177074, "count": 177074, "decode_str": "885"} -{"id": 34637, "token": "429", "merges": "4 29", "raw_count": 177099, "count": 177099, "decode_str": "429"} -{"id": 19687, "token": "incre", "merges": "in cre", "raw_count": 158412, "count": 177102, "decode_str": "incre"} -{"id": 15897, "token": "esh", "merges": "es h", "raw_count": 68166, "count": 177169, "decode_str": "esh"} -{"id": 21966, "token": ")>", "merges": ") >", "raw_count": 177203, "count": 177203, "decode_str": ")>"} -{"id": 4098, "token": "\u0120grant", "merges": "\u0120gr ant", "raw_count": 82177, "count": 177231, "decode_str": " grant"} -{"id": 17994, "token": "\u0120bot", "merges": "\u0120b ot", "raw_count": 173316, "count": 177255, "decode_str": " bot"} -{"id": 4543, "token": "\u0120nor", "merges": "\u0120n or", "raw_count": 177267, "count": 177267, "decode_str": " nor"} -{"id": 37498, "token": "repository", "merges": "repos itory", "raw_count": 177352, "count": 177352, "decode_str": "repository"} -{"id": 18246, "token": "Params", "merges": "Par ams", "raw_count": 177449, "count": 177449, "decode_str": "Params"} -{"id": 28386, "token": "wm", "merges": "w m", "raw_count": 177494, "count": 177494, "decode_str": "wm"} -{"id": 5209, "token": "gar", "merges": "g ar", "raw_count": 146665, "count": 177504, "decode_str": "gar"} -{"id": 18851, "token": "Channel", "merges": "Ch annel", "raw_count": 177519, "count": 177519, "decode_str": "Channel"} -{"id": 34286, "token": "categories", "merges": "c ategories", "raw_count": 177526, "count": 177526, "decode_str": "categories"} -{"id": 10002, "token": "who", "merges": "w ho", "raw_count": 177594, "count": 177594, "decode_str": "who"} -{"id": 6677, "token": "ln", "merges": "l n", "raw_count": 170706, "count": 177628, "decode_str": "ln"} -{"id": 27004, "token": "COP", "merges": "C OP", "raw_count": 156016, "count": 177647, "decode_str": "COP"} -{"id": 11627, "token": "\u0120coordinates", "merges": "\u0120coord inates", "raw_count": 177664, "count": 177664, "decode_str": " coordinates"} -{"id": 9809, "token": "\u0120saved", "merges": "\u0120sav ed", "raw_count": 177719, "count": 177719, "decode_str": " saved"} -{"id": 54232, "token": "\u00e9\u0136\u0141", "merges": "\u00e9\u0136 \u0141", "raw_count": 177791, "count": 177791, "decode_str": "\u951f"} -{"id": 34590, "token": "customer", "merges": "custom er", "raw_count": 177813, "count": 177813, "decode_str": "customer"} -{"id": 29330, "token": "Touch", "merges": "T ouch", "raw_count": 177873, "count": 177873, "decode_str": "Touch"} -{"id": 4970, "token": "\u0120scient", "merges": "\u0120sc ient", "raw_count": 1463, "count": 177875, "decode_str": " scient"} -{"id": 27270, "token": "Business", "merges": "B usiness", "raw_count": 177930, "count": 177930, "decode_str": "Business"} -{"id": 4660, "token": "\u0120station", "merges": "\u0120st ation", "raw_count": 166333, "count": 177958, "decode_str": " station"} -{"id": 10603, "token": "\u0120mapping", "merges": "\u0120m apping", "raw_count": 177969, "count": 177969, "decode_str": " mapping"} -{"id": 3356, "token": "\u0120longer", "merges": "\u0120long er", "raw_count": 178066, "count": 178066, "decode_str": " longer"} -{"id": 49534, "token": "digest", "merges": "dig est", "raw_count": 178066, "count": 178066, "decode_str": "digest"} -{"id": 4231, "token": "\u0120mag", "merges": "\u0120m ag", "raw_count": 66951, "count": 178128, "decode_str": " mag"} -{"id": 24894, "token": "leted", "merges": "let ed", "raw_count": 178169, "count": 178169, "decode_str": "leted"} -{"id": 7640, "token": "ums", "merges": "um s", "raw_count": 125123, "count": 178231, "decode_str": "ums"} -{"id": 52444, "token": "\u00e6\u00af\u00bd", "merges": "\u00e6\u00af \u00bd", "raw_count": 178241, "count": 178241, "decode_str": "\u6bfd"} -{"id": 5199, "token": "\u0120procedure", "merges": "\u0120proced ure", "raw_count": 178311, "count": 178311, "decode_str": " procedure"} -{"id": 53101, "token": "\u00e7\u00a2\u00b4", "merges": "\u00e7\u00a2 \u00b4", "raw_count": 178355, "count": 178355, "decode_str": "\u78b4"} -{"id": 2660, "token": "\u0120temper", "merges": "\u0120tem per", "raw_count": 11431, "count": 178356, "decode_str": " temper"} -{"id": 3739, "token": "\u0120medical", "merges": "\u0120med ical", "raw_count": 178368, "count": 178368, "decode_str": " medical"} -{"id": 11510, "token": "prod", "merges": "pro d", "raw_count": 178434, "count": 178434, "decode_str": "prod"} -{"id": 52996, "token": "\u00e7\u013d\u00a5", "merges": "\u00e7\u013d \u00a5", "raw_count": 178451, "count": 178451, "decode_str": "\u76e5"} -{"id": 2909, "token": "\u0120minutes", "merges": "\u0120min utes", "raw_count": 178456, "count": 178456, "decode_str": " minutes"} -{"id": 27590, "token": "446", "merges": "44 6", "raw_count": 178504, "count": 178504, "decode_str": "446"} -{"id": 2501, "token": "arrow", "merges": "ar row", "raw_count": 125949, "count": 178523, "decode_str": "arrow"} -{"id": 10181, "token": "frastructure", "merges": "frast ructure", "raw_count": 29840, "count": 178590, "decode_str": "frastructure"} -{"id": 4759, "token": "\u0120green", "merges": "\u0120g reen", "raw_count": 156277, "count": 178603, "decode_str": " green"} -{"id": 9401, "token": "iro", "merges": "i ro", "raw_count": 177271, "count": 178657, "decode_str": "iro"} -{"id": 9751, "token": "nergy", "merges": "ner gy", "raw_count": 29909, "count": 178668, "decode_str": "nergy"} -{"id": 26719, "token": "workers", "merges": "work ers", "raw_count": 178684, "count": 178684, "decode_str": "workers"} -{"id": 15157, "token": "MAN", "merges": "M AN", "raw_count": 178696, "count": 178696, "decode_str": "MAN"} -{"id": 28921, "token": "\u0120timestamp", "merges": "\u0120tim estamp", "raw_count": 178711, "count": 178711, "decode_str": " timestamp"} -{"id": 8073, "token": "\u012052", "merges": "\u01205 2", "raw_count": 178737, "count": 178737, "decode_str": " 52"} -{"id": 35895, "token": "PLAY", "merges": "PL AY", "raw_count": 178824, "count": 178824, "decode_str": "PLAY"} -{"id": 54408, "token": "\u00e9\u013f\u00a5", "merges": "\u00e9\u013f \u00a5", "raw_count": 178857, "count": 178857, "decode_str": "\u9765"} -{"id": 6131, "token": "\u0120offers", "merges": "\u0120off ers", "raw_count": 178883, "count": 178883, "decode_str": " offers"} -{"id": 31973, "token": "changes", "merges": "ch anges", "raw_count": 178886, "count": 178886, "decode_str": "changes"} -{"id": 54040, "token": "\u00e8\u00be\u0129", "merges": "\u00e8\u00be \u0129", "raw_count": 178915, "count": 178915, "decode_str": "\u8f87"} -{"id": 8123, "token": "\u0120channels", "merges": "\u0120ch annels", "raw_count": 178955, "count": 178955, "decode_str": " channels"} -{"id": 36961, "token": "gui", "merges": "g ui", "raw_count": 179007, "count": 179007, "decode_str": "gui"} -{"id": 22151, "token": "isode", "merges": "is ode", "raw_count": 172639, "count": 179012, "decode_str": "isode"} -{"id": 2564, "token": "\u0120mind", "merges": "\u0120m ind", "raw_count": 154067, "count": 179024, "decode_str": " mind"} -{"id": 34291, "token": "intel", "merges": "int el", "raw_count": 179058, "count": 179058, "decode_str": "intel"} -{"id": 9336, "token": "]\"", "merges": "] \"", "raw_count": 179118, "count": 179118, "decode_str": "]\""} -{"id": 34649, "token": "%);", "merges": "% );", "raw_count": 179130, "count": 179130, "decode_str": "%);"} -{"id": 21704, "token": "ril", "merges": "r il", "raw_count": 179160, "count": 179160, "decode_str": "ril"} -{"id": 26946, "token": "Mike", "merges": "M ike", "raw_count": 179240, "count": 179240, "decode_str": "Mike"} -{"id": 5176, "token": "\u0120removed", "merges": "\u0120rem oved", "raw_count": 179250, "count": 179250, "decode_str": " removed"} -{"id": 4195, "token": "\u0120fa", "merges": "\u0120f a", "raw_count": 86703, "count": 179255, "decode_str": " fa"} -{"id": 7845, "token": "Please", "merges": "P lease", "raw_count": 179258, "count": 179258, "decode_str": "Please"} -{"id": 12175, "token": "Width", "merges": "W idth", "raw_count": 179337, "count": 179337, "decode_str": "Width"} -{"id": 22688, "token": "\u0120sept", "merges": "\u0120se pt", "raw_count": 179347, "count": 179347, "decode_str": " sept"} -{"id": 3842, "token": "\u0120repe", "merges": "\u0120re pe", "raw_count": 6261, "count": 179371, "decode_str": " repe"} -{"id": 13641, "token": "Dem", "merges": "D em", "raw_count": 114478, "count": 179409, "decode_str": "Dem"} -{"id": 18049, "token": "vid", "merges": "v id", "raw_count": 104190, "count": 179427, "decode_str": "vid"} -{"id": 8592, "token": "erman", "merges": "erm an", "raw_count": 155198, "count": 179450, "decode_str": "erman"} -{"id": 45939, "token": "!!!!!!!!", "merges": "!!!! !!!!", "raw_count": 179477, "count": 179477, "decode_str": "!!!!!!!!"} -{"id": 6173, "token": "terest", "merges": "te rest", "raw_count": 13023, "count": 179508, "decode_str": "terest"} -{"id": 8573, "token": "\u0120internet", "merges": "\u0120inter net", "raw_count": 179512, "count": 179512, "decode_str": " internet"} -{"id": 10984, "token": "hard", "merges": "h ard", "raw_count": 166242, "count": 179538, "decode_str": "hard"} -{"id": 26706, "token": "\u0120widget", "merges": "\u0120wid get", "raw_count": 179543, "count": 179543, "decode_str": " widget"} -{"id": 53716, "token": "\u00e8\u00a1\u00bf", "merges": "\u00e8\u00a1 \u00bf", "raw_count": 179547, "count": 179547, "decode_str": "\u887f"} -{"id": 52604, "token": "\u00e6\u00b6\u0136", "merges": "\u00e6\u00b6 \u0136", "raw_count": 179568, "count": 179568, "decode_str": "\u6d94"} -{"id": 53272, "token": "\u00e7\u00b2\u00b2", "merges": "\u00e7\u00b2 \u00b2", "raw_count": 179569, "count": 179569, "decode_str": "\u7cb2"} -{"id": 27463, "token": "394", "merges": "39 4", "raw_count": 179582, "count": 179582, "decode_str": "394"} -{"id": 21889, "token": "659", "merges": "65 9", "raw_count": 179638, "count": 179638, "decode_str": "659"} -{"id": 6681, "token": "mas", "merges": "m as", "raw_count": 176851, "count": 179649, "decode_str": "mas"} -{"id": 4433, "token": "\u0120failure", "merges": "\u0120fail ure", "raw_count": 179663, "count": 179663, "decode_str": " failure"} -{"id": 5440, "token": "\u0120cop", "merges": "\u0120c op", "raw_count": 90174, "count": 179777, "decode_str": " cop"} -{"id": 23487, "token": "cart", "merges": "c art", "raw_count": 179805, "count": 179805, "decode_str": "cart"} -{"id": 43612, "token": "Git", "merges": "G it", "raw_count": 179830, "count": 179830, "decode_str": "Git"} -{"id": 6174, "token": "\u0120arms", "merges": "\u0120ar ms", "raw_count": 179841, "count": 179841, "decode_str": " arms"} -{"id": 9025, "token": "\u0120division", "merges": "\u0120div ision", "raw_count": 179876, "count": 179876, "decode_str": " division"} -{"id": 3484, "token": "\u0120students", "merges": "\u0120stud ents", "raw_count": 179906, "count": 179906, "decode_str": " students"} -{"id": 20515, "token": "0020", "merges": "00 20", "raw_count": 180006, "count": 180006, "decode_str": "0020"} -{"id": 28057, "token": "686", "merges": "68 6", "raw_count": 180017, "count": 180017, "decode_str": "686"} -{"id": 18179, "token": "Could", "merges": "C ould", "raw_count": 180051, "count": 180051, "decode_str": "Could"} -{"id": 52266, "token": "\u00e6\u0141\u00a9", "merges": "\u00e6\u0141 \u00a9", "raw_count": 180069, "count": 180069, "decode_str": "\u67e9"} -{"id": 14017, "token": "Sing", "merges": "S ing", "raw_count": 93457, "count": 180077, "decode_str": "Sing"} -{"id": 14920, "token": "without", "merges": "with out", "raw_count": 180081, "count": 180081, "decode_str": "without"} -{"id": 50668, "token": "\u00e5\u0125\u0143", "merges": "\u00e5\u0125 \u0143", "raw_count": 180096, "count": 180096, "decode_str": "\u50ed"} -{"id": 4520, "token": "\u0120numer", "merges": "\u0120num er", "raw_count": 28599, "count": 180130, "decode_str": " numer"} -{"id": 4425, "token": "\u0120decided", "merges": "\u0120dec ided", "raw_count": 179015, "count": 180225, "decode_str": " decided"} -{"id": 5439, "token": "\u0120raised", "merges": "\u0120ra ised", "raw_count": 180235, "count": 180235, "decode_str": " raised"} -{"id": 3797, "token": "\u0120includes", "merges": "\u0120includ es", "raw_count": 180252, "count": 180252, "decode_str": " includes"} -{"id": 20227, "token": "fan", "merges": "f an", "raw_count": 176238, "count": 180287, "decode_str": "fan"} -{"id": 42161, "token": "defaults", "merges": "default s", "raw_count": 180314, "count": 180314, "decode_str": "defaults"} -{"id": 54459, "token": "\u00e9\u00a2\u00a2", "merges": "\u00e9\u00a2 \u00a2", "raw_count": 180316, "count": 180316, "decode_str": "\u98a2"} -{"id": 11930, "token": "Location", "merges": "L ocation", "raw_count": 180354, "count": 180354, "decode_str": "Location"} -{"id": 35999, "token": "emit", "merges": "em it", "raw_count": 180366, "count": 180366, "decode_str": "emit"} -{"id": 6540, "token": "onald", "merges": "onal d", "raw_count": 42756, "count": 180375, "decode_str": "onald"} -{"id": 49155, "token": "oyo", "merges": "oy o", "raw_count": 180382, "count": 180382, "decode_str": "oyo"} -{"id": 24634, "token": "contains", "merges": "cont ains", "raw_count": 180388, "count": 180388, "decode_str": "contains"} -{"id": 13510, "token": "Custom", "merges": "C ustom", "raw_count": 120227, "count": 180397, "decode_str": "Custom"} -{"id": 3732, "token": "\u0120applied", "merges": "\u0120appl ied", "raw_count": 180454, "count": 180454, "decode_str": " applied"} -{"id": 11559, "token": "\u0120strings", "merges": "\u0120str ings", "raw_count": 180454, "count": 180454, "decode_str": " strings"} -{"id": 52998, "token": "\u00e7\u013d\u00b1", "merges": "\u00e7\u013d \u00b1", "raw_count": 180454, "count": 180454, "decode_str": "\u76f1"} -{"id": 15099, "token": "Grid", "merges": "Gr id", "raw_count": 175199, "count": 180464, "decode_str": "Grid"} -{"id": 18372, "token": "poly", "merges": "pol y", "raw_count": 170909, "count": 180494, "decode_str": "poly"} -{"id": 4459, "token": "\u0120carry", "merges": "\u0120car ry", "raw_count": 126632, "count": 180497, "decode_str": " carry"} -{"id": 8032, "token": "ima", "merges": "im a", "raw_count": 170522, "count": 180515, "decode_str": "ima"} -{"id": 14611, "token": "mass", "merges": "m ass", "raw_count": 180535, "count": 180535, "decode_str": "mass"} -{"id": 26943, "token": "Tests", "merges": "Test s", "raw_count": 180558, "count": 180558, "decode_str": "Tests"} -{"id": 3158, "token": "\u0120quick", "merges": "\u0120qu ick", "raw_count": 86824, "count": 180598, "decode_str": " quick"} -{"id": 5969, "token": "rich", "merges": "r ich", "raw_count": 154315, "count": 180604, "decode_str": "rich"} -{"id": 8192, "token": "\u0120Log", "merges": "\u0120L og", "raw_count": 120882, "count": 180698, "decode_str": " Log"} -{"id": 7426, "token": "clusive", "merges": "clus ive", "raw_count": 74560, "count": 180719, "decode_str": "clusive"} -{"id": 24711, "token": "Mi", "merges": "M i", "raw_count": 180725, "count": 180725, "decode_str": "Mi"} -{"id": 20540, "token": "\u0120chunk", "merges": "\u0120ch unk", "raw_count": 180740, "count": 180740, "decode_str": " chunk"} -{"id": 7205, "token": "\u0120manager", "merges": "\u0120manag er", "raw_count": 180774, "count": 180774, "decode_str": " manager"} -{"id": 3331, "token": "\u0120friend", "merges": "\u0120fri end", "raw_count": 91584, "count": 180849, "decode_str": " friend"} -{"id": 18317, "token": "structure", "merges": "struct ure", "raw_count": 180890, "count": 180890, "decode_str": "structure"} -{"id": 13981, "token": "orient", "merges": "or ient", "raw_count": 41311, "count": 180891, "decode_str": "orient"} -{"id": 49197, "token": "serialize", "merges": "ser ialize", "raw_count": 180931, "count": 180931, "decode_str": "serialize"} -{"id": 49242, "token": "devices", "merges": "dev ices", "raw_count": 180962, "count": 180962, "decode_str": "devices"} -{"id": 13420, "token": "cha", "merges": "ch a", "raw_count": 181011, "count": 181011, "decode_str": "cha"} -{"id": 25953, "token": "647", "merges": "64 7", "raw_count": 181021, "count": 181021, "decode_str": "647"} -{"id": 29976, "token": "gf", "merges": "g f", "raw_count": 181028, "count": 181028, "decode_str": "gf"} -{"id": 10752, "token": "reason", "merges": "re ason", "raw_count": 165101, "count": 181033, "decode_str": "reason"} -{"id": 19475, "token": "mom", "merges": "m om", "raw_count": 86873, "count": 181050, "decode_str": "mom"} -{"id": 5035, "token": "See", "merges": "S ee", "raw_count": 181077, "count": 181077, "decode_str": "See"} -{"id": 7543, "token": "\u012047", "merges": "\u01204 7", "raw_count": 181086, "count": 181086, "decode_str": " 47"} -{"id": 3383, "token": "\u0120(-", "merges": "\u0120( -", "raw_count": 181095, "count": 181095, "decode_str": " (-"} -{"id": 16853, "token": "tu", "merges": "t u", "raw_count": 181097, "count": 181097, "decode_str": "tu"} -{"id": 12550, "token": "your", "merges": "y our", "raw_count": 181108, "count": 181108, "decode_str": "your"} -{"id": 51063, "token": "\u00e5\u0135\u0132", "merges": "\u00e5\u0135 \u0132", "raw_count": 181119, "count": 181119, "decode_str": "\u54d0"} -{"id": 19878, "token": "Queue", "merges": "Que ue", "raw_count": 181120, "count": 181120, "decode_str": "Queue"} -{"id": 23833, "token": "Richard", "merges": "Rich ard", "raw_count": 181138, "count": 181138, "decode_str": "Richard"} -{"id": 28124, "token": "WP", "merges": "W P", "raw_count": 181160, "count": 181160, "decode_str": "WP"} -{"id": 5600, "token": "\u0120transl", "merges": "\u0120trans l", "raw_count": 13567, "count": 181211, "decode_str": " transl"} -{"id": 5163, "token": "orry", "merges": "or ry", "raw_count": 78380, "count": 181223, "decode_str": "orry"} -{"id": 32029, "token": "currency", "merges": "cur rency", "raw_count": 181350, "count": 181350, "decode_str": "currency"} -{"id": 50519, "token": "\u00e4\u00bc\u012b", "merges": "\u00e4\u00bc \u012b", "raw_count": 181407, "count": 181407, "decode_str": "\u4f09"} -{"id": 9358, "token": "ester", "merges": "es ter", "raw_count": 154103, "count": 181420, "decode_str": "ester"} -{"id": 2774, "token": "\u0120moment", "merges": "\u0120mom ent", "raw_count": 121343, "count": 181506, "decode_str": " moment"} -{"id": 42011, "token": "\u0120'''", "merges": "\u0120' ''", "raw_count": 181565, "count": 181565, "decode_str": " '''"} -{"id": 20872, "token": "NUM", "merges": "N UM", "raw_count": 135766, "count": 181583, "decode_str": "NUM"} -{"id": 5336, "token": "olved", "merges": "ol ved", "raw_count": 50878, "count": 181621, "decode_str": "olved"} -{"id": 5547, "token": "\u0120successful", "merges": "\u0120success ful", "raw_count": 181622, "count": 181622, "decode_str": " successful"} -{"id": 20932, "token": "sz", "merges": "s z", "raw_count": 181652, "count": 181652, "decode_str": "sz"} -{"id": 25227, "token": "KN", "merges": "K N", "raw_count": 122476, "count": 181664, "decode_str": "KN"} -{"id": 13003, "token": "IGN", "merges": "IG N", "raw_count": 168381, "count": 181733, "decode_str": "IGN"} -{"id": 34237, "token": "452", "merges": "45 2", "raw_count": 181781, "count": 181781, "decode_str": "452"} -{"id": 6688, "token": "istent", "merges": "ist ent", "raw_count": 79177, "count": 181793, "decode_str": "istent"} -{"id": 29360, "token": "393", "merges": "39 3", "raw_count": 181819, "count": 181819, "decode_str": "393"} -{"id": 8226, "token": "ontal", "merges": "ont al", "raw_count": 6561, "count": 181848, "decode_str": "ontal"} -{"id": 20472, "token": "sheet", "merges": "she et", "raw_count": 172547, "count": 181878, "decode_str": "sheet"} -{"id": 8211, "token": "eting", "merges": "et ing", "raw_count": 174318, "count": 181916, "decode_str": "eting"} -{"id": 30424, "token": "KY", "merges": "K Y", "raw_count": 181950, "count": 181950, "decode_str": "KY"} -{"id": 17407, "token": "pler", "merges": "pl er", "raw_count": 180568, "count": 181966, "decode_str": "pler"} -{"id": 50506, "token": "\u00e4\u00bb\u013f", "merges": "\u00e4\u00bb \u013f", "raw_count": 181991, "count": 181991, "decode_str": "\u4edd"} -{"id": 41011, "token": "destination", "merges": "dest ination", "raw_count": 182095, "count": 182095, "decode_str": "destination"} -{"id": 53562, "token": "\u00e8\u0129\u00ac", "merges": "\u00e8\u0129 \u00ac", "raw_count": 182124, "count": 182124, "decode_str": "\u81ec"} -{"id": 53687, "token": "\u00e8\u013b\u00a2", "merges": "\u00e8\u013b \u00a2", "raw_count": 182140, "count": 182140, "decode_str": "\u8662"} -{"id": 20402, "token": "dh", "merges": "d h", "raw_count": 182174, "count": 182174, "decode_str": "dh"} -{"id": 31219, "token": "OTT", "merges": "OT T", "raw_count": 182178, "count": 182178, "decode_str": "OTT"} -{"id": 23763, "token": "sal", "merges": "s al", "raw_count": 182196, "count": 182196, "decode_str": "sal"} -{"id": 6300, "token": "Just", "merges": "J ust", "raw_count": 167113, "count": 182206, "decode_str": "Just"} -{"id": 2217, "token": "\u0120enough", "merges": "\u0120en ough", "raw_count": 182229, "count": 182229, "decode_str": " enough"} -{"id": 28591, "token": "\u0120[-", "merges": "\u0120[ -", "raw_count": 182231, "count": 182231, "decode_str": " [-"} -{"id": 8279, "token": "riev", "merges": "ri ev", "raw_count": 60129, "count": 182243, "decode_str": "riev"} -{"id": 3297, "token": "\u0120stay", "merges": "\u0120st ay", "raw_count": 149680, "count": 182274, "decode_str": " stay"} -{"id": 10779, "token": "anim", "merges": "an im", "raw_count": 88007, "count": 182299, "decode_str": "anim"} -{"id": 2360, "token": "\u0120night", "merges": "\u0120n ight", "raw_count": 166623, "count": 182363, "decode_str": " night"} -{"id": 15930, "token": "OLD", "merges": "OL D", "raw_count": 180620, "count": 182380, "decode_str": "OLD"} -{"id": 33928, "token": "mh", "merges": "m h", "raw_count": 182480, "count": 182480, "decode_str": "mh"} -{"id": 54366, "token": "\u00e9\u013d\u0130", "merges": "\u00e9\u013d \u0130", "raw_count": 182546, "count": 182546, "decode_str": "\u96ce"} -{"id": 8910, "token": "\u0120menu", "merges": "\u0120men u", "raw_count": 182563, "count": 182563, "decode_str": " menu"} -{"id": 33440, "token": "\u0120[{", "merges": "\u0120[ {", "raw_count": 182596, "count": 182596, "decode_str": " [{"} -{"id": 6753, "token": "\u0120auto", "merges": "\u0120aut o", "raw_count": 182263, "count": 182672, "decode_str": " auto"} -{"id": 2806, "token": "\u0120black", "merges": "\u0120bl ack", "raw_count": 179145, "count": 182729, "decode_str": " black"} -{"id": 40297, "token": "426", "merges": "4 26", "raw_count": 182751, "count": 182751, "decode_str": "426"} -{"id": 16704, "token": "Settings", "merges": "S ettings", "raw_count": 182799, "count": 182799, "decode_str": "Settings"} -{"id": 16484, "token": "cover", "merges": "c over", "raw_count": 181252, "count": 182831, "decode_str": "cover"} -{"id": 29412, "token": "372", "merges": "37 2", "raw_count": 182848, "count": 182848, "decode_str": "372"} -{"id": 54551, "token": "\u00e6\u0140\u0140", "merges": "\u00e6\u0140 \u0140", "raw_count": 182849, "count": 182849, "decode_str": "\u679e"} -{"id": 5280, "token": "abil", "merges": "ab il", "raw_count": 43952, "count": 182956, "decode_str": "abil"} -{"id": 53434, "token": "\u00e7\u00be\u00a7", "merges": "\u00e7\u00be \u00a7", "raw_count": 182974, "count": 182974, "decode_str": "\u7fa7"} -{"id": 1035, "token": "(\\", "merges": "( \\", "raw_count": 157491, "count": 183004, "decode_str": "(\\"} -{"id": 24900, "token": "Du", "merges": "D u", "raw_count": 183062, "count": 183062, "decode_str": "Du"} -{"id": 17148, "token": "Print", "merges": "Pr int", "raw_count": 183066, "count": 183066, "decode_str": "Print"} -{"id": 7779, "token": "water", "merges": "w ater", "raw_count": 153137, "count": 183194, "decode_str": "water"} -{"id": 5572, "token": "\u0120operator", "merges": "\u0120oper ator", "raw_count": 183210, "count": 183210, "decode_str": " operator"} -{"id": 14609, "token": "BIT", "merges": "B IT", "raw_count": 170829, "count": 183236, "decode_str": "BIT"} -{"id": 35261, "token": "latest", "merges": "lat est", "raw_count": 183254, "count": 183254, "decode_str": "latest"} -{"id": 17213, "token": "Video", "merges": "V ideo", "raw_count": 183344, "count": 183344, "decode_str": "Video"} -{"id": 10221, "token": "employ", "merges": "em ploy", "raw_count": 32415, "count": 183375, "decode_str": "employ"} -{"id": 33568, "token": "signature", "merges": "sign ature", "raw_count": 183378, "count": 183378, "decode_str": "signature"} -{"id": 7410, "token": "\u0120constitution", "merges": "\u0120constit ution", "raw_count": 115943, "count": 183441, "decode_str": " constitution"} -{"id": 21962, "token": "Parse", "merges": "Par se", "raw_count": 183490, "count": 183490, "decode_str": "Parse"} -{"id": 5206, "token": "\u0120choose", "merges": "\u0120cho ose", "raw_count": 183513, "count": 183513, "decode_str": " choose"} -{"id": 9045, "token": "anna", "merges": "ann a", "raw_count": 173577, "count": 183564, "decode_str": "anna"} -{"id": 38538, "token": "tables", "merges": "t ables", "raw_count": 183566, "count": 183566, "decode_str": "tables"} -{"id": 23030, "token": "Mer", "merges": "M er", "raw_count": 183575, "count": 183575, "decode_str": "Mer"} -{"id": 20511, "token": "editor", "merges": "ed itor", "raw_count": 183600, "count": 183600, "decode_str": "editor"} -{"id": 52011, "token": "\u00e6\u0131\u0128", "merges": "\u00e6\u0131 \u0128", "raw_count": 183611, "count": 183611, "decode_str": "\u63c6"} -{"id": 3984, "token": "\u0120speak", "merges": "\u0120spe ak", "raw_count": 84908, "count": 183660, "decode_str": " speak"} -{"id": 6880, "token": "\u0120extension", "merges": "\u0120ext ension", "raw_count": 183757, "count": 183757, "decode_str": " extension"} -{"id": 9135, "token": "\u012058", "merges": "\u01205 8", "raw_count": 183870, "count": 183870, "decode_str": " 58"} -{"id": 17109, "token": "\u0120oct", "merges": "\u0120o ct", "raw_count": 183874, "count": 183874, "decode_str": " oct"} -{"id": 53660, "token": "\u00e8\u012d\u00bb", "merges": "\u00e8\u012d \u00bb", "raw_count": 183884, "count": 183884, "decode_str": "\u82fb"} -{"id": 51033, "token": "\u00e5\u0134\u00a3", "merges": "\u00e5\u0134 \u00a3", "raw_count": 183913, "count": 183913, "decode_str": "\u54a3"} -{"id": 12935, "token": "ogram", "merges": "og ram", "raw_count": 147110, "count": 183928, "decode_str": "ogram"} -{"id": 128, "token": "\u00c4", "merges": "NULL", "raw_count": 12939, "count": 183988, "decode_str": "\ufffd"} -{"id": 50947, "token": "\u00e5\u0131\u00bb", "merges": "\u00e5\u0131 \u00bb", "raw_count": 184055, "count": 184055, "decode_str": "\u53fb"} -{"id": 18808, "token": "Kind", "merges": "K ind", "raw_count": 184065, "count": 184065, "decode_str": "Kind"} -{"id": 3266, "token": "xim", "merges": "x im", "raw_count": 77366, "count": 184065, "decode_str": "xim"} -{"id": 27898, "token": "\"'", "merges": "\" '", "raw_count": 184101, "count": 184101, "decode_str": "\"'"} -{"id": 4016, "token": "\u0120negative", "merges": "\u0120neg ative", "raw_count": 184109, "count": 184109, "decode_str": " negative"} -{"id": 4271, "token": "\u0120identify", "merges": "\u0120ident ify", "raw_count": 134705, "count": 184186, "decode_str": " identify"} -{"id": 53996, "token": "\u00e8\u00b7\u0138", "merges": "\u00e8\u00b7 \u0138", "raw_count": 184218, "count": 184218, "decode_str": "\u8dd6"} -{"id": 20181, "token": "\u0120000", "merges": "\u0120 000", "raw_count": 184238, "count": 184238, "decode_str": " 000"} -{"id": 42940, "token": "701", "merges": "7 01", "raw_count": 184250, "count": 184250, "decode_str": "701"} -{"id": 5120, "token": "onic", "merges": "on ic", "raw_count": 157879, "count": 184293, "decode_str": "onic"} -{"id": 10124, "token": "endar", "merges": "end ar", "raw_count": 12227, "count": 184313, "decode_str": "endar"} -{"id": 5603, "token": "\u0120park", "merges": "\u0120p ark", "raw_count": 125062, "count": 184313, "decode_str": " park"} -{"id": 43402, "token": "Club", "merges": "Cl ub", "raw_count": 184342, "count": 184342, "decode_str": "Club"} -{"id": 50603, "token": "\u00e4\u00bf\u013c", "merges": "\u00e4\u00bf \u013c", "raw_count": 184359, "count": 184359, "decode_str": "\u4fda"} -{"id": 36043, "token": "463", "merges": "46 3", "raw_count": 184401, "count": 184401, "decode_str": "463"} -{"id": 7897, "token": "\u0120ans", "merges": "\u0120an s", "raw_count": 152159, "count": 184404, "decode_str": " ans"} -{"id": 54130, "token": "\u00e9\u0123\u0134", "merges": "\u00e9\u0123 \u0134", "raw_count": 184421, "count": 184421, "decode_str": "\u9052"} -{"id": 6150, "token": "\u0120sea", "merges": "\u0120se a", "raw_count": 184445, "count": 184445, "decode_str": " sea"} -{"id": 19452, "token": "activ", "merges": "act iv", "raw_count": 66409, "count": 184478, "decode_str": "activ"} -{"id": 12600, "token": "\u0120relating", "merges": "\u0120rel ating", "raw_count": 184501, "count": 184501, "decode_str": " relating"} -{"id": 6559, "token": "crib", "merges": "c rib", "raw_count": 12792, "count": 184519, "decode_str": "crib"} -{"id": 6147, "token": "yr", "merges": "y r", "raw_count": 159919, "count": 184525, "decode_str": "yr"} -{"id": 28950, "token": "807", "merges": "80 7", "raw_count": 184542, "count": 184542, "decode_str": "807"} -{"id": 54153, "token": "\u00e9\u0124\u013f", "merges": "\u00e9\u0124 \u013f", "raw_count": 184559, "count": 184559, "decode_str": "\u909d"} -{"id": 52761, "token": "\u00e7\u012a\u00b0", "merges": "\u00e7\u012a \u00b0", "raw_count": 184577, "count": 184577, "decode_str": "\u7230"} -{"id": 2157, "token": "\u0120infl", "merges": "\u0120in fl", "raw_count": 9671, "count": 184695, "decode_str": " infl"} -{"id": 8324, "token": "Property", "merges": "Pro perty", "raw_count": 183441, "count": 184707, "decode_str": "Property"} -{"id": 15074, "token": "\u00ed\u0137", "merges": "\u00ed \u0137", "raw_count": 56670, "count": 184715, "decode_str": "\ufffd"} -{"id": 21448, "token": "fx", "merges": "f x", "raw_count": 184718, "count": 184718, "decode_str": "fx"} -{"id": 2830, "token": "\u0120sil", "merges": "\u0120s il", "raw_count": 27247, "count": 184728, "decode_str": " sil"} -{"id": 2607, "token": "\u0120months", "merges": "\u0120month s", "raw_count": 184735, "count": 184735, "decode_str": " months"} -{"id": 53947, "token": "\u00e8\u00b5\u0127", "merges": "\u00e8\u00b5 \u0127", "raw_count": 184742, "count": 184742, "decode_str": "\u8d45"} -{"id": 41956, "token": "\u0120\"\")", "merges": "\u0120\" \")", "raw_count": 184766, "count": 184766, "decode_str": " \"\")"} -{"id": 23213, "token": "Db", "merges": "D b", "raw_count": 184804, "count": 184804, "decode_str": "Db"} -{"id": 10366, "token": "\u0120xml", "merges": "\u0120x ml", "raw_count": 167634, "count": 184805, "decode_str": " xml"} -{"id": 26881, "token": "055", "merges": "05 5", "raw_count": 184832, "count": 184832, "decode_str": "055"} -{"id": 54170, "token": "\u00e9\u0125\u0127", "merges": "\u00e9\u0125 \u0127", "raw_count": 184837, "count": 184837, "decode_str": "\u90c5"} -{"id": 8664, "token": "\u0120concerning", "merges": "\u0120concer ning", "raw_count": 184858, "count": 184858, "decode_str": " concerning"} -{"id": 20449, "token": "gz", "merges": "g z", "raw_count": 172123, "count": 184858, "decode_str": "gz"} -{"id": 4946, "token": "bra", "merges": "b ra", "raw_count": 130166, "count": 184920, "decode_str": "bra"} -{"id": 11571, "token": "\u0120voc", "merges": "\u0120v oc", "raw_count": 110989, "count": 184929, "decode_str": " voc"} -{"id": 5958, "token": "\u0120rank", "merges": "\u0120r ank", "raw_count": 138886, "count": 184936, "decode_str": " rank"} -{"id": 6024, "token": "\u0120external", "merges": "\u0120ex ternal", "raw_count": 184950, "count": 184950, "decode_str": " external"} -{"id": 30169, "token": "381", "merges": "38 1", "raw_count": 184957, "count": 184957, "decode_str": "381"} -{"id": 4204, "token": "\u0120da", "merges": "\u0120d a", "raw_count": 169606, "count": 185060, "decode_str": " da"} -{"id": 4225, "token": "oted", "merges": "ot ed", "raw_count": 67924, "count": 185095, "decode_str": "oted"} -{"id": 6787, "token": "ifications", "merges": "ific ations", "raw_count": 109773, "count": 185112, "decode_str": "ifications"} -{"id": 16926, "token": "hai", "merges": "h ai", "raw_count": 183349, "count": 185124, "decode_str": "hai"} -{"id": 5660, "token": "icial", "merges": "ic ial", "raw_count": 30341, "count": 185130, "decode_str": "icial"} -{"id": 9983, "token": ">,", "merges": "> ,", "raw_count": 185140, "count": 185140, "decode_str": ">,"} -{"id": 33648, "token": "908", "merges": "90 8", "raw_count": 185151, "count": 185151, "decode_str": "908"} -{"id": 14558, "token": "OX", "merges": "O X", "raw_count": 184337, "count": 185206, "decode_str": "OX"} -{"id": 8054, "token": "undle", "merges": "und le", "raw_count": 3310, "count": 185211, "decode_str": "undle"} -{"id": 14455, "token": "depend", "merges": "d epend", "raw_count": 20230, "count": 185228, "decode_str": "depend"} -{"id": 9004, "token": "\u0120rect", "merges": "\u0120re ct", "raw_count": 131745, "count": 185234, "decode_str": " rect"} -{"id": 53281, "token": "\u00e7\u00b3\u012f", "merges": "\u00e7\u00b3 \u012f", "raw_count": 185271, "count": 185271, "decode_str": "\u7ccd"} -{"id": 19216, "token": "omo", "merges": "om o", "raw_count": 185347, "count": 185347, "decode_str": "omo"} -{"id": 11714, "token": "pot", "merges": "p ot", "raw_count": 124146, "count": 185370, "decode_str": "pot"} -{"id": 52320, "token": "\u00e6\u00a3\u0124", "merges": "\u00e6\u00a3 \u0124", "raw_count": 185468, "count": 185468, "decode_str": "\u68c2"} -{"id": 4525, "token": "uted", "merges": "ut ed", "raw_count": 63917, "count": 185478, "decode_str": "uted"} -{"id": 21399, "token": "submit", "merges": "sub mit", "raw_count": 185520, "count": 185520, "decode_str": "submit"} -{"id": 4062, "token": "\u0120tradition", "merges": "\u0120trad ition", "raw_count": 25633, "count": 185528, "decode_str": " tradition"} -{"id": 28953, "token": "803", "merges": "80 3", "raw_count": 185677, "count": 185677, "decode_str": "803"} -{"id": 51392, "token": "\u00e5\u0143\u00ac", "merges": "\u00e5\u0143 \u00ac", "raw_count": 185720, "count": 185720, "decode_str": "\u5b6c"} -{"id": 12408, "token": "hl", "merges": "h l", "raw_count": 185589, "count": 185786, "decode_str": "hl"} -{"id": 24259, "token": "ADE", "merges": "AD E", "raw_count": 185812, "count": 185812, "decode_str": "ADE"} -{"id": 51225, "token": "\u00e5\u0140\u00a9", "merges": "\u00e5\u0140 \u00a9", "raw_count": 185924, "count": 185924, "decode_str": "\u57a9"} -{"id": 18787, "token": "QR", "merges": "Q R", "raw_count": 184067, "count": 185930, "decode_str": "QR"} -{"id": 22096, "token": "Fun", "merges": "F un", "raw_count": 154516, "count": 185992, "decode_str": "Fun"} -{"id": 34753, "token": "gm", "merges": "g m", "raw_count": 186096, "count": 186096, "decode_str": "gm"} -{"id": 5237, "token": "\u0120harm", "merges": "\u0120h arm", "raw_count": 39059, "count": 186283, "decode_str": " harm"} -{"id": 3430, "token": "\u0120wrong", "merges": "\u0120wr ong", "raw_count": 169920, "count": 186296, "decode_str": " wrong"} -{"id": 26807, "token": "DV", "merges": "D V", "raw_count": 186328, "count": 186328, "decode_str": "DV"} -{"id": 25230, "token": "thening", "merges": "the ning", "raw_count": 14211, "count": 186374, "decode_str": "thening"} -{"id": 50058, "token": "\u0120unicode", "merges": "\u0120un icode", "raw_count": 186405, "count": 186405, "decode_str": " unicode"} -{"id": 29557, "token": "\u0120annex", "merges": "\u0120an nex", "raw_count": 186460, "count": 186460, "decode_str": " annex"} -{"id": 8210, "token": "\u01201997", "merges": "\u0120199 7", "raw_count": 186483, "count": 186483, "decode_str": " 1997"} -{"id": 21239, "token": "tz", "merges": "t z", "raw_count": 186524, "count": 186524, "decode_str": "tz"} -{"id": 52845, "token": "\u00e7\u0132\u012f", "merges": "\u00e7\u0132 \u012f", "raw_count": 186526, "count": 186526, "decode_str": "\u740d"} -{"id": 53581, "token": "\u00e8\u012a\u013d", "merges": "\u00e8\u012a \u013d", "raw_count": 186555, "count": 186555, "decode_str": "\u821b"} -{"id": 4917, "token": "\u0120yield", "merges": "\u0120y ield", "raw_count": 146622, "count": 186562, "decode_str": " yield"} -{"id": 11807, "token": "family", "merges": "f amily", "raw_count": 186590, "count": 186590, "decode_str": "family"} -{"id": 20826, "token": "037", "merges": "0 37", "raw_count": 186617, "count": 186617, "decode_str": "037"} -{"id": 25654, "token": "645", "merges": "64 5", "raw_count": 186621, "count": 186621, "decode_str": "645"} -{"id": 16380, "token": "BF", "merges": "B F", "raw_count": 186632, "count": 186632, "decode_str": "BF"} -{"id": 14364, "token": "PRE", "merges": "P RE", "raw_count": 119993, "count": 186720, "decode_str": "PRE"} -{"id": 6297, "token": "\u0120mechanisms", "merges": "\u0120mechan isms", "raw_count": 186756, "count": 186756, "decode_str": " mechanisms"} -{"id": 5511, "token": "\u0120communication", "merges": "\u0120communic ation", "raw_count": 186762, "count": 186762, "decode_str": " communication"} -{"id": 11862, "token": "OUR", "merges": "OU R", "raw_count": 101822, "count": 186828, "decode_str": "OUR"} -{"id": 53593, "token": "\u00e8\u012a\u00b8", "merges": "\u00e8\u012a \u00b8", "raw_count": 186878, "count": 186878, "decode_str": "\u8238"} -{"id": 53608, "token": "\u00e8\u012c\u0125", "merges": "\u00e8\u012c \u0125", "raw_count": 186898, "count": 186898, "decode_str": "\u8283"} -{"id": 28822, "token": "\u0120logger", "merges": "\u0120log ger", "raw_count": 186901, "count": 186901, "decode_str": " logger"} -{"id": 7685, "token": "legal", "merges": "leg al", "raw_count": 87637, "count": 186982, "decode_str": "legal"} -{"id": 24080, "token": "Thomas", "merges": "Th omas", "raw_count": 187028, "count": 187028, "decode_str": "Thomas"} -{"id": 4517, "token": "\u0120trust", "merges": "\u0120tr ust", "raw_count": 137945, "count": 187050, "decode_str": " trust"} -{"id": 40515, "token": "\u0120nd", "merges": "\u0120n d", "raw_count": 187071, "count": 187071, "decode_str": " nd"} -{"id": 5927, "token": "\u0120minimum", "merges": "\u0120min imum", "raw_count": 187081, "count": 187081, "decode_str": " minimum"} -{"id": 39095, "token": "student", "merges": "stud ent", "raw_count": 187123, "count": 187123, "decode_str": "student"} -{"id": 5527, "token": "ruit", "merges": "ru it", "raw_count": 30417, "count": 187236, "decode_str": "ruit"} -{"id": 6978, "token": "\u0120univers", "merges": "\u0120un ivers", "raw_count": 8269, "count": 187254, "decode_str": " univers"} -{"id": 3066, "token": "\u0120via", "merges": "\u0120v ia", "raw_count": 187269, "count": 187269, "decode_str": " via"} -{"id": 40666, "token": "515", "merges": "5 15", "raw_count": 187304, "count": 187304, "decode_str": "515"} -{"id": 18046, "token": "olute", "merges": "ol ute", "raw_count": 9526, "count": 187309, "decode_str": "olute"} -{"id": 23037, "token": "oft", "merges": "o ft", "raw_count": 183202, "count": 187404, "decode_str": "oft"} -{"id": 3721, "token": "\u00d0\u00ba", "merges": "\u00d0 \u00ba", "raw_count": 65118, "count": 187414, "decode_str": "\u043a"} -{"id": 4715, "token": "\u0120learning", "merges": "\u0120le arning", "raw_count": 187517, "count": 187517, "decode_str": " learning"} -{"id": 3857, "token": "\u0120&&", "merges": "\u0120& &", "raw_count": 187532, "count": 187532, "decode_str": " &&"} -{"id": 10632, "token": "\\\"", "merges": "\\ \"", "raw_count": 187581, "count": 187581, "decode_str": "\\\""} -{"id": 23865, "token": "collect", "merges": "col lect", "raw_count": 187585, "count": 187585, "decode_str": "collect"} -{"id": 30528, "token": "383", "merges": "38 3", "raw_count": 187593, "count": 187593, "decode_str": "383"} -{"id": 54156, "token": "\u00e9\u0124\u00a8", "merges": "\u00e9\u0124 \u00a8", "raw_count": 187619, "count": 187619, "decode_str": "\u90a8"} -{"id": 16976, "token": "Font", "merges": "F ont", "raw_count": 187654, "count": 187654, "decode_str": "Font"} -{"id": 9323, "token": "Cons", "merges": "C ons", "raw_count": 133521, "count": 187668, "decode_str": "Cons"} -{"id": 3376, "token": "\u0120pie", "merges": "\u0120p ie", "raw_count": 14662, "count": 187679, "decode_str": " pie"} -{"id": 51690, "token": "\u00e6\u0122\u0128", "merges": "\u00e6\u0122 \u0128", "raw_count": 187680, "count": 187680, "decode_str": "\u6006"} -{"id": 16854, "token": "TG", "merges": "T G", "raw_count": 187711, "count": 187711, "decode_str": "TG"} -{"id": 18898, "token": "oples", "merges": "op les", "raw_count": 12851, "count": 187746, "decode_str": "oples"} -{"id": 20042, "token": "IH", "merges": "I H", "raw_count": 187271, "count": 187770, "decode_str": "IH"} -{"id": 26123, "token": "Lee", "merges": "L ee", "raw_count": 187823, "count": 187823, "decode_str": "Lee"} -{"id": 24210, "token": "extension", "merges": "ext ension", "raw_count": 187874, "count": 187874, "decode_str": "extension"} -{"id": 4851, "token": "\u0120cit", "merges": "\u0120c it", "raw_count": 15559, "count": 187884, "decode_str": " cit"} -{"id": 38505, "token": "COLOR", "merges": "COL OR", "raw_count": 187948, "count": 187948, "decode_str": "COLOR"} -{"id": 29546, "token": "373", "merges": "37 3", "raw_count": 188121, "count": 188121, "decode_str": "373"} -{"id": 11584, "token": "BT", "merges": "B T", "raw_count": 188285, "count": 188285, "decode_str": "BT"} -{"id": 3049, "token": "selves", "merges": "sel ves", "raw_count": 2309, "count": 188334, "decode_str": "selves"} -{"id": 4628, "token": "urance", "merges": "ur ance", "raw_count": 53543, "count": 188345, "decode_str": "urance"} -{"id": 5303, "token": "\u0120sen", "merges": "\u0120s en", "raw_count": 79307, "count": 188422, "decode_str": " sen"} -{"id": 1702, "token": "================", "merges": "======== ========", "raw_count": 10951, "count": 188475, "decode_str": "================"} -{"id": 11890, "token": "################", "merges": "######## ########", "raw_count": 42143, "count": 188487, "decode_str": "################"} -{"id": 5122, "token": "\u0120mechanism", "merges": "\u0120mechan ism", "raw_count": 188509, "count": 188509, "decode_str": " mechanism"} -{"id": 2817, "token": "\u0120sus", "merges": "\u0120s us", "raw_count": 12774, "count": 188530, "decode_str": " sus"} -{"id": 53083, "token": "\u00e7\u00a2\u0123", "merges": "\u00e7\u00a2 \u0123", "raw_count": 188597, "count": 188597, "decode_str": "\u7881"} -{"id": 32045, "token": "examples", "merges": "ex amples", "raw_count": 188601, "count": 188601, "decode_str": "examples"} -{"id": 38884, "token": "lv", "merges": "l v", "raw_count": 188619, "count": 188619, "decode_str": "lv"} -{"id": 5438, "token": "\u0120selection", "merges": "\u0120se lection", "raw_count": 188622, "count": 188622, "decode_str": " selection"} -{"id": 28615, "token": "362", "merges": "36 2", "raw_count": 188632, "count": 188632, "decode_str": "362"} -{"id": 5971, "token": "\u0120classes", "merges": "\u0120class es", "raw_count": 188635, "count": 188635, "decode_str": " classes"} -{"id": 6803, "token": "\u0120assessment", "merges": "\u0120assess ment", "raw_count": 188701, "count": 188701, "decode_str": " assessment"} -{"id": 28166, "token": "706", "merges": "70 6", "raw_count": 188760, "count": 188760, "decode_str": "706"} -{"id": 2071, "token": "\u0120Bl", "merges": "\u0120B l", "raw_count": 49356, "count": 188766, "decode_str": " Bl"} -{"id": 8243, "token": "sen", "merges": "s en", "raw_count": 147649, "count": 188795, "decode_str": "sen"} -{"id": 5744, "token": "raz", "merges": "ra z", "raw_count": 95370, "count": 188913, "decode_str": "raz"} -{"id": 3969, "token": "\u0120corresponding", "merges": "\u0120correspond ing", "raw_count": 187159, "count": 188968, "decode_str": " corresponding"} -{"id": 26933, "token": "397", "merges": "39 7", "raw_count": 188975, "count": 188975, "decode_str": "397"} -{"id": 30238, "token": "measure", "merges": "me asure", "raw_count": 188976, "count": 188976, "decode_str": "measure"} -{"id": 32897, "token": "please", "merges": "ple ase", "raw_count": 189064, "count": 189064, "decode_str": "please"} -{"id": 28303, "token": "POR", "merges": "P OR", "raw_count": 189167, "count": 189167, "decode_str": "POR"} -{"id": 42856, "token": "100000", "merges": "100 000", "raw_count": 189314, "count": 189314, "decode_str": "100000"} -{"id": 8727, "token": "ista", "merges": "ist a", "raw_count": 176852, "count": 189340, "decode_str": "ista"} -{"id": 35265, "token": "886", "merges": "88 6", "raw_count": 189495, "count": 189495, "decode_str": "886"} -{"id": 35833, "token": "418", "merges": "4 18", "raw_count": 189512, "count": 189512, "decode_str": "418"} -{"id": 18469, "token": "HI", "merges": "H I", "raw_count": 189551, "count": 189551, "decode_str": "HI"} -{"id": 52636, "token": "\u00e6\u00b7\u013b", "merges": "\u00e6\u00b7 \u013b", "raw_count": 189598, "count": 189598, "decode_str": "\u6dd9"} -{"id": 8357, "token": "\u0120seed", "merges": "\u0120se ed", "raw_count": 186007, "count": 189619, "decode_str": " seed"} -{"id": 32718, "token": "ESP", "merges": "ES P", "raw_count": 189646, "count": 189646, "decode_str": "ESP"} -{"id": 40170, "token": "Ki", "merges": "K i", "raw_count": 189668, "count": 189668, "decode_str": "Ki"} -{"id": 6982, "token": "\u0120economy", "merges": "\u0120econom y", "raw_count": 189672, "count": 189672, "decode_str": " economy"} -{"id": 11458, "token": "\u00e2\u0136\u0122", "merges": "\u00e2\u0136 \u0122", "raw_count": 28984, "count": 189682, "decode_str": "\u2500"} -{"id": 3408, "token": "\u0120phase", "merges": "\u0120ph ase", "raw_count": 189687, "count": 189687, "decode_str": " phase"} -{"id": 4621, "token": "irit", "merges": "ir it", "raw_count": 28992, "count": 189688, "decode_str": "irit"} -{"id": 20851, "token": "\u0120Config", "merges": "\u0120Con fig", "raw_count": 145853, "count": 189693, "decode_str": " Config"} -{"id": 3722, "token": "\u0120bed", "merges": "\u0120b ed", "raw_count": 127344, "count": 189695, "decode_str": " bed"} -{"id": 16560, "token": "Root", "merges": "R oot", "raw_count": 189770, "count": 189770, "decode_str": "Root"} -{"id": 25770, "token": "448", "merges": "44 8", "raw_count": 189790, "count": 189790, "decode_str": "448"} -{"id": 9298, "token": "\u0120reserv", "merges": "\u0120res erv", "raw_count": 6629, "count": 189825, "decode_str": " reserv"} -{"id": 34948, "token": "POL", "merges": "P OL", "raw_count": 189877, "count": 189877, "decode_str": "POL"} -{"id": 18576, "token": "WD", "merges": "W D", "raw_count": 189882, "count": 189882, "decode_str": "WD"} -{"id": 27503, "token": "Chris", "merges": "Ch ris", "raw_count": 189891, "count": 189891, "decode_str": "Chris"} -{"id": 24525, "token": "Lou", "merges": "L ou", "raw_count": 61404, "count": 189920, "decode_str": "Lou"} -{"id": 20722, "token": "UB", "merges": "U B", "raw_count": 189928, "count": 189928, "decode_str": "UB"} -{"id": 7887, "token": "\u0120threshold", "merges": "\u0120th reshold", "raw_count": 189976, "count": 189976, "decode_str": " threshold"} -{"id": 27506, "token": ":*", "merges": ": *", "raw_count": 190037, "count": 190037, "decode_str": ":*"} -{"id": 24343, "token": "lp", "merges": "l p", "raw_count": 190054, "count": 190054, "decode_str": "lp"} -{"id": 17480, "token": "since", "merges": "s ince", "raw_count": 190056, "count": 190056, "decode_str": "since"} -{"id": 38354, "token": "Pow", "merges": "P ow", "raw_count": 190099, "count": 190099, "decode_str": "Pow"} -{"id": 51692, "token": "\u00e6\u0122\u0131", "merges": "\u00e6\u0122 \u0131", "raw_count": 190108, "count": 190108, "decode_str": "\u600f"} -{"id": 20132, "token": "creat", "merges": "c reat", "raw_count": 190157, "count": 190157, "decode_str": "creat"} -{"id": 52807, "token": "\u00e7\u0130\u0141", "merges": "\u00e7\u0130 \u0141", "raw_count": 190202, "count": 190202, "decode_str": "\u739f"} -{"id": 6423, "token": "\u0120director", "merges": "\u0120direct or", "raw_count": 190206, "count": 190206, "decode_str": " director"} -{"id": 50660, "token": "\u00e5\u0124\u00a9", "merges": "\u00e5\u0124 \u00a9", "raw_count": 190211, "count": 190211, "decode_str": "\u50a9"} -{"id": 28744, "token": "457", "merges": "45 7", "raw_count": 190249, "count": 190249, "decode_str": "457"} -{"id": 51709, "token": "\u00e6\u0123\u0123", "merges": "\u00e6\u0123 \u0123", "raw_count": 190270, "count": 190270, "decode_str": "\u6041"} -{"id": 13922, "token": "\u0120JSON", "merges": "\u0120J SON", "raw_count": 190280, "count": 190280, "decode_str": " JSON"} -{"id": 10639, "token": "Write", "merges": "W rite", "raw_count": 189087, "count": 190305, "decode_str": "Write"} -{"id": 5458, "token": "osen", "merges": "os en", "raw_count": 105934, "count": 190334, "decode_str": "osen"} -{"id": 2862, "token": "\u0120entire", "merges": "\u0120ent ire", "raw_count": 145649, "count": 190351, "decode_str": " entire"} -{"id": 21556, "token": "Phil", "merges": "Ph il", "raw_count": 105233, "count": 190363, "decode_str": "Phil"} -{"id": 12109, "token": "hang", "merges": "h ang", "raw_count": 125158, "count": 190412, "decode_str": "hang"} -{"id": 7877, "token": "\u0120dimension", "merges": "\u0120dim ension", "raw_count": 186922, "count": 190444, "decode_str": " dimension"} -{"id": 9400, "token": "\u0120topic", "merges": "\u0120top ic", "raw_count": 190448, "count": 190448, "decode_str": " topic"} -{"id": 42644, "token": "\u0120sf", "merges": "\u0120s f", "raw_count": 190454, "count": 190454, "decode_str": " sf"} -{"id": 51760, "token": "\u00e6\u0125\u0129", "merges": "\u00e6\u0125 \u0129", "raw_count": 190464, "count": 190464, "decode_str": "\u60c7"} -{"id": 36673, "token": "\"...", "merges": "\" ...", "raw_count": 190510, "count": 190510, "decode_str": "\"..."} -{"id": 28246, "token": "Fed", "merges": "F ed", "raw_count": 190670, "count": 190670, "decode_str": "Fed"} -{"id": 7276, "token": "gers", "merges": "g ers", "raw_count": 112611, "count": 190751, "decode_str": "gers"} -{"id": 23200, "token": "gif", "merges": "g if", "raw_count": 190802, "count": 190802, "decode_str": "gif"} -{"id": 18095, "token": "]}", "merges": "] }", "raw_count": 190838, "count": 190838, "decode_str": "]}"} -{"id": 26937, "token": "649", "merges": "64 9", "raw_count": 190863, "count": 190863, "decode_str": "649"} -{"id": 15379, "token": "igm", "merges": "ig m", "raw_count": 183443, "count": 190894, "decode_str": "igm"} -{"id": 20454, "token": "\u0120ministry", "merges": "\u0120min istry", "raw_count": 190962, "count": 190962, "decode_str": " ministry"} -{"id": 9627, "token": "frast", "merges": "fr ast", "raw_count": 12448, "count": 191038, "decode_str": "frast"} -{"id": 7584, "token": "\u012049", "merges": "\u01204 9", "raw_count": 191045, "count": 191045, "decode_str": " 49"} -{"id": 15575, "token": "YP", "merges": "Y P", "raw_count": 190556, "count": 191049, "decode_str": "YP"} -{"id": 8209, "token": "FIG", "merges": "F IG", "raw_count": 20313, "count": 191056, "decode_str": "FIG"} -{"id": 22833, "token": "\u0120....", "merges": "\u0120 ....", "raw_count": 191066, "count": 191066, "decode_str": " ...."} -{"id": 3844, "token": "aches", "merges": "ac hes", "raw_count": 68810, "count": 191152, "decode_str": "aches"} -{"id": 12117, "token": "Typ", "merges": "T yp", "raw_count": 39162, "count": 191169, "decode_str": "Typ"} -{"id": 13086, "token": "Change", "merges": "Ch ange", "raw_count": 191173, "count": 191173, "decode_str": "Change"} -{"id": 50559, "token": "\u00e4\u00bd\u0140", "merges": "\u00e4\u00bd \u0140", "raw_count": 191173, "count": 191173, "decode_str": "\u4f5e"} -{"id": 10071, "token": "\u0120experts", "merges": "\u0120exper ts", "raw_count": 191217, "count": 191217, "decode_str": " experts"} -{"id": 4262, "token": "\u0120proceed", "merges": "\u0120pro ceed", "raw_count": 42176, "count": 191245, "decode_str": " proceed"} -{"id": 42959, "token": "attention", "merges": "att ention", "raw_count": 191254, "count": 191254, "decode_str": "attention"} -{"id": 13193, "token": "\u0120Index", "merges": "\u0120In dex", "raw_count": 191261, "count": 191261, "decode_str": " Index"} -{"id": 25131, "token": "Ali", "merges": "A li", "raw_count": 158102, "count": 191300, "decode_str": "Ali"} -{"id": 4753, "token": "\u0120materials", "merges": "\u0120material s", "raw_count": 191490, "count": 191490, "decode_str": " materials"} -{"id": 25616, "token": "607", "merges": "60 7", "raw_count": 191493, "count": 191493, "decode_str": "607"} -{"id": 43563, "token": "vx", "merges": "v x", "raw_count": 191559, "count": 191559, "decode_str": "vx"} -{"id": 29525, "token": "configure", "merges": "config ure", "raw_count": 191613, "count": 191613, "decode_str": "configure"} -{"id": 4052, "token": "aling", "merges": "al ing", "raw_count": 48564, "count": 191644, "decode_str": "aling"} -{"id": 22047, "token": "LM", "merges": "L M", "raw_count": 191689, "count": 191689, "decode_str": "LM"} -{"id": 22829, "token": "flat", "merges": "fl at", "raw_count": 191762, "count": 191762, "decode_str": "flat"} -{"id": 27787, "token": "\u0120advisory", "merges": "\u0120advis ory", "raw_count": 191779, "count": 191779, "decode_str": " advisory"} -{"id": 19815, "token": "Move", "merges": "M ove", "raw_count": 191798, "count": 191798, "decode_str": "Move"} -{"id": 15613, "token": "\u0120proc", "merges": "\u0120pro c", "raw_count": 89063, "count": 191822, "decode_str": " proc"} -{"id": 25325, "token": "\u0120rapport", "merges": "\u0120rapp ort", "raw_count": 191903, "count": 191903, "decode_str": " rapport"} -{"id": 53648, "token": "\u00e8\u012d\u013e", "merges": "\u00e8\u012d \u013e", "raw_count": 191933, "count": 191933, "decode_str": "\u82dc"} -{"id": 25997, "token": "Cost", "merges": "C ost", "raw_count": 191942, "count": 191942, "decode_str": "Cost"} -{"id": 6653, "token": "aper", "merges": "a per", "raw_count": 62771, "count": 192086, "decode_str": "aper"} -{"id": 37622, "token": "\u0120christ", "merges": "\u0120ch rist", "raw_count": 192193, "count": 192193, "decode_str": " christ"} -{"id": 10297, "token": "Tab", "merges": "T ab", "raw_count": 192254, "count": 192254, "decode_str": "Tab"} -{"id": 3345, "token": "\u0120outside", "merges": "\u0120out side", "raw_count": 192324, "count": 192324, "decode_str": " outside"} -{"id": 12891, "token": "\u0120600", "merges": "\u01206 00", "raw_count": 192393, "count": 192393, "decode_str": " 600"} -{"id": 3924, "token": "\u0120stage", "merges": "\u0120st age", "raw_count": 192407, "count": 192407, "decode_str": " stage"} -{"id": 10269, "token": "\u0120bin", "merges": "\u0120b in", "raw_count": 180615, "count": 192416, "decode_str": " bin"} -{"id": 4991, "token": "rant", "merges": "r ant", "raw_count": 68702, "count": 192484, "decode_str": "rant"} -{"id": 37799, "token": "visit", "merges": "vis it", "raw_count": 192497, "count": 192497, "decode_str": "visit"} -{"id": 53284, "token": "\u00e7\u00b3\u0139", "merges": "\u00e7\u00b3 \u0139", "raw_count": 192497, "count": 192497, "decode_str": "\u7cd7"} -{"id": 5881, "token": "edom", "merges": "ed om", "raw_count": 43745, "count": 192508, "decode_str": "edom"} -{"id": 16987, "token": "\u012005", "merges": "\u01200 5", "raw_count": 192564, "count": 192564, "decode_str": " 05"} -{"id": 17004, "token": "Dom", "merges": "D om", "raw_count": 72870, "count": 192574, "decode_str": "Dom"} -{"id": 9154, "token": "even", "merges": "ev en", "raw_count": 153887, "count": 192610, "decode_str": "even"} -{"id": 51956, "token": "\u00e6\u012e\u00b9", "merges": "\u00e6\u012e \u00b9", "raw_count": 192777, "count": 192777, "decode_str": "\u6339"} -{"id": 17759, "token": "expression", "merges": "exp ression", "raw_count": 192840, "count": 192840, "decode_str": "expression"} -{"id": 18074, "token": "Sil", "merges": "S il", "raw_count": 129894, "count": 192864, "decode_str": "Sil"} -{"id": 52609, "token": "\u00e6\u00b6\u0140", "merges": "\u00e6\u00b6 \u0140", "raw_count": 192877, "count": 192877, "decode_str": "\u6d9e"} -{"id": 24483, "token": "usage", "merges": "us age", "raw_count": 191141, "count": 192887, "decode_str": "usage"} -{"id": 2578, "token": "\u0120tre", "merges": "\u0120t re", "raw_count": 49392, "count": 192943, "decode_str": " tre"} -{"id": 21787, "token": "\u0120mandate", "merges": "\u0120mand ate", "raw_count": 193008, "count": 193008, "decode_str": " mandate"} -{"id": 8235, "token": "oung", "merges": "oun g", "raw_count": 31193, "count": 193013, "decode_str": "oung"} -{"id": 2588, "token": "\u0120Gen", "merges": "\u0120G en", "raw_count": 37224, "count": 193048, "decode_str": " Gen"} -{"id": 48049, "token": "2222", "merges": "22 22", "raw_count": 193078, "count": 193078, "decode_str": "2222"} -{"id": 33731, "token": "Chat", "merges": "C hat", "raw_count": 193098, "count": 193098, "decode_str": "Chat"} -{"id": 34508, "token": "CAM", "merges": "C AM", "raw_count": 193129, "count": 193129, "decode_str": "CAM"} -{"id": 16408, "token": "AU", "merges": "A U", "raw_count": 158747, "count": 193136, "decode_str": "AU"} -{"id": 2326, "token": "\u0120seen", "merges": "\u0120se en", "raw_count": 193146, "count": 193146, "decode_str": " seen"} -{"id": 20519, "token": "Hg", "merges": "H g", "raw_count": 29022, "count": 193168, "decode_str": "Hg"} -{"id": 10069, "token": "Format", "merges": "Form at", "raw_count": 193220, "count": 193220, "decode_str": "Format"} -{"id": 53320, "token": "\u00e7\u00ba\u00b0", "merges": "\u00e7\u00ba \u00b0", "raw_count": 193369, "count": 193369, "decode_str": "\u7eb0"} -{"id": 20034, "token": "environment", "merges": "en vironment", "raw_count": 193226, "count": 193385, "decode_str": "environment"} -{"id": 6391, "token": "\u0120buffer", "merges": "\u0120bu ffer", "raw_count": 193407, "count": 193407, "decode_str": " buffer"} -{"id": 22045, "token": "contact", "merges": "cont act", "raw_count": 193418, "count": 193418, "decode_str": "contact"} -{"id": 12727, "token": "aga", "merges": "ag a", "raw_count": 189482, "count": 193459, "decode_str": "aga"} -{"id": 12328, "token": "ynamic", "merges": "ynam ic", "raw_count": 5431, "count": 193479, "decode_str": "ynamic"} -{"id": 13436, "token": "plates", "merges": "pl ates", "raw_count": 34489, "count": 193485, "decode_str": "plates"} -{"id": 38510, "token": "801", "merges": "8 01", "raw_count": 193501, "count": 193501, "decode_str": "801"} -{"id": 20602, "token": "fmt", "merges": "f mt", "raw_count": 193550, "count": 193550, "decode_str": "fmt"} -{"id": 12654, "token": "\u0120verify", "merges": "\u0120ver ify", "raw_count": 193557, "count": 193557, "decode_str": " verify"} -{"id": 2425, "token": "\u0120activity", "merges": "\u0120activ ity", "raw_count": 193574, "count": 193574, "decode_str": " activity"} -{"id": 30010, "token": "Mn", "merges": "M n", "raw_count": 193590, "count": 193590, "decode_str": "Mn"} -{"id": 19895, "token": "Health", "merges": "He alth", "raw_count": 193637, "count": 193637, "decode_str": "Health"} -{"id": 2028, "token": "\u0120tell", "merges": "\u0120t ell", "raw_count": 148134, "count": 193753, "decode_str": " tell"} -{"id": 6907, "token": "\u0120angle", "merges": "\u0120ang le", "raw_count": 193769, "count": 193769, "decode_str": " angle"} -{"id": 14132, "token": "Da", "merges": "D a", "raw_count": 189430, "count": 193804, "decode_str": "Da"} -{"id": 32803, "token": "432", "merges": "4 32", "raw_count": 193818, "count": 193818, "decode_str": "432"} -{"id": 12211, "token": "iii", "merges": "ii i", "raw_count": 193841, "count": 193841, "decode_str": "iii"} -{"id": 15554, "token": "Cache", "merges": "C ache", "raw_count": 193883, "count": 193883, "decode_str": "Cache"} -{"id": 6604, "token": "\u0120join", "merges": "\u0120jo in", "raw_count": 193890, "count": 193890, "decode_str": " join"} -{"id": 10347, "token": "\u0120prepare", "merges": "\u0120prep are", "raw_count": 193892, "count": 193892, "decode_str": " prepare"} -{"id": 48052, "token": "prog", "merges": "pro g", "raw_count": 193983, "count": 193983, "decode_str": "prog"} -{"id": 52571, "token": "\u00e6\u00b5\u0125", "merges": "\u00e6\u00b5 \u0125", "raw_count": 194075, "count": 194075, "decode_str": "\u6d43"} -{"id": 8892, "token": "\u0120tasks", "merges": "\u0120t asks", "raw_count": 194142, "count": 194142, "decode_str": " tasks"} -{"id": 4413, "token": "\u0120companies", "merges": "\u0120compan ies", "raw_count": 194150, "count": 194150, "decode_str": " companies"} -{"id": 25745, "token": "387", "merges": "38 7", "raw_count": 194262, "count": 194262, "decode_str": "387"} -{"id": 37011, "token": ")\u00e2\u0122\u0136", "merges": ") \u00e2\u0122\u0136", "raw_count": 194394, "count": 194394, "decode_str": ")\u2014"} -{"id": 18166, "token": "activation", "merges": "act ivation", "raw_count": 194124, "count": 194410, "decode_str": "activation"} -{"id": 3600, "token": "\u0120bur", "merges": "\u0120b ur", "raw_count": 96956, "count": 194447, "decode_str": " bur"} -{"id": 9424, "token": "\u0120Name", "merges": "\u0120N ame", "raw_count": 194448, "count": 194448, "decode_str": " Name"} -{"id": 43975, "token": "logs", "merges": "log s", "raw_count": 194485, "count": 194485, "decode_str": "logs"} -{"id": 33032, "token": "sep", "merges": "se p", "raw_count": 194493, "count": 194493, "decode_str": "sep"} -{"id": 4607, "token": "\u0120relig", "merges": "\u0120rel ig", "raw_count": 643, "count": 194547, "decode_str": " relig"} -{"id": 23723, "token": "blob", "merges": "bl ob", "raw_count": 194554, "count": 194554, "decode_str": "blob"} -{"id": 6736, "token": "ena", "merges": "en a", "raw_count": 192923, "count": 194662, "decode_str": "ena"} -{"id": 28704, "token": "assign", "merges": "ass ign", "raw_count": 194714, "count": 194714, "decode_str": "assign"} -{"id": 28120, "token": ">'", "merges": "> '", "raw_count": 194744, "count": 194744, "decode_str": ">'"} -{"id": 26448, "token": "House", "merges": "H ouse", "raw_count": 194866, "count": 194866, "decode_str": "House"} -{"id": 52019, "token": "\u00e6\u0131\u00a9", "merges": "\u00e6\u0131 \u00a9", "raw_count": 194894, "count": 194894, "decode_str": "\u63e9"} -{"id": 18737, "token": "\u0120rapp", "merges": "\u0120ra pp", "raw_count": 2998, "count": 194901, "decode_str": " rapp"} -{"id": 49629, "token": "\u0120618", "merges": "\u01206 18", "raw_count": 194973, "count": 194973, "decode_str": " 618"} -{"id": 7904, "token": "\u012046", "merges": "\u01204 6", "raw_count": 195036, "count": 195036, "decode_str": " 46"} -{"id": 14650, "token": "ping", "merges": "p ing", "raw_count": 195056, "count": 195056, "decode_str": "ping"} -{"id": 21922, "token": "services", "merges": "serv ices", "raw_count": 195129, "count": 195129, "decode_str": "services"} -{"id": 4809, "token": "\u0120aspect", "merges": "\u0120as pect", "raw_count": 62555, "count": 195135, "decode_str": " aspect"} -{"id": 4096, "token": "\u0120purpose", "merges": "\u0120pur pose", "raw_count": 195140, "count": 195140, "decode_str": " purpose"} -{"id": 10463, "token": "\u0120exit", "merges": "\u0120ex it", "raw_count": 195210, "count": 195210, "decode_str": " exit"} -{"id": 3533, "token": "\u0120questions", "merges": "\u0120quest ions", "raw_count": 195236, "count": 195236, "decode_str": " questions"} -{"id": 45007, "token": "SDK", "merges": "SD K", "raw_count": 195314, "count": 195314, "decode_str": "SDK"} -{"id": 3607, "token": "\u0120properties", "merges": "\u0120proper ties", "raw_count": 195320, "count": 195320, "decode_str": " properties"} -{"id": 8153, "token": "\u0120IP", "merges": "\u0120I P", "raw_count": 162872, "count": 195396, "decode_str": " IP"} -{"id": 17242, "token": "\u0120WHERE", "merges": "\u0120WH ERE", "raw_count": 195403, "count": 195403, "decode_str": " WHERE"} -{"id": 32296, "token": "495", "merges": "4 95", "raw_count": 195427, "count": 195427, "decode_str": "495"} -{"id": 38825, "token": "\u0120*=", "merges": "\u0120* =", "raw_count": 195447, "count": 195447, "decode_str": " *="} -{"id": 17089, "token": "mys", "merges": "m ys", "raw_count": 54985, "count": 195457, "decode_str": "mys"} -{"id": 4364, "token": "iency", "merges": "i ency", "raw_count": 13574, "count": 195523, "decode_str": "iency"} -{"id": 22410, "token": "MRI", "merges": "M RI", "raw_count": 194787, "count": 195544, "decode_str": "MRI"} -{"id": 49407, "token": "\"--", "merges": "\" --", "raw_count": 195548, "count": 195548, "decode_str": "\"--"} -{"id": 28201, "token": "Vo", "merges": "V o", "raw_count": 134957, "count": 195582, "decode_str": "Vo"} -{"id": 17261, "token": "dk", "merges": "d k", "raw_count": 195582, "count": 195582, "decode_str": "dk"} -{"id": 5175, "token": "\u0120testing", "merges": "\u0120test ing", "raw_count": 195639, "count": 195639, "decode_str": " testing"} -{"id": 14115, "token": "energy", "merges": "en ergy", "raw_count": 195669, "count": 195669, "decode_str": "energy"} -{"id": 6374, "token": "\u0120elim", "merges": "\u0120el im", "raw_count": 10246, "count": 195698, "decode_str": " elim"} -{"id": 39869, "token": "asset", "merges": "ass et", "raw_count": 195708, "count": 195708, "decode_str": "asset"} -{"id": 4063, "token": "urb", "merges": "ur b", "raw_count": 71057, "count": 195774, "decode_str": "urb"} -{"id": 10843, "token": "\u0120legislation", "merges": "\u0120legis lation", "raw_count": 195811, "count": 195811, "decode_str": " legislation"} -{"id": 35609, "token": "xyz", "merges": "xy z", "raw_count": 195891, "count": 195891, "decode_str": "xyz"} -{"id": 19495, "token": "\u0120disable", "merges": "\u0120dis able", "raw_count": 195932, "count": 195932, "decode_str": " disable"} -{"id": 2940, "token": "\u0120walk", "merges": "\u0120w alk", "raw_count": 126120, "count": 195939, "decode_str": " walk"} -{"id": 17049, "token": "\u0120skip", "merges": "\u0120sk ip", "raw_count": 195955, "count": 195955, "decode_str": " skip"} -{"id": 25370, "token": "STEM", "merges": "ST EM", "raw_count": 156063, "count": 195963, "decode_str": "STEM"} -{"id": 24349, "token": "Jim", "merges": "J im", "raw_count": 196005, "count": 196005, "decode_str": "Jim"} -{"id": 7867, "token": "\u0120perman", "merges": "\u0120per man", "raw_count": 3010, "count": 196038, "decode_str": " perman"} -{"id": 16615, "token": "INFO", "merges": "IN FO", "raw_count": 196064, "count": 196064, "decode_str": "INFO"} -{"id": 2139, "token": "\u0120why", "merges": "\u0120wh y", "raw_count": 196143, "count": 196143, "decode_str": " why"} -{"id": 4479, "token": "\\'", "merges": "\\ '", "raw_count": 196330, "count": 196330, "decode_str": "\\'"} -{"id": 4605, "token": "\u0120String", "merges": "\u0120St ring", "raw_count": 195805, "count": 196419, "decode_str": " String"} -{"id": 48759, "token": "decoder", "merges": "dec oder", "raw_count": 196476, "count": 196476, "decode_str": "decoder"} -{"id": 2954, "token": "\u0120relationship", "merges": "\u0120relations hip", "raw_count": 148690, "count": 196479, "decode_str": " relationship"} -{"id": 39029, "token": "\u0120Runtime", "merges": "\u0120R untime", "raw_count": 196505, "count": 196505, "decode_str": " Runtime"} -{"id": 18545, "token": "\u0120democratic", "merges": "\u0120democr atic", "raw_count": 196508, "count": 196508, "decode_str": " democratic"} -{"id": 19108, "token": "ongo", "merges": "ong o", "raw_count": 171134, "count": 196576, "decode_str": "ongo"} -{"id": 12742, "token": "ytes", "merges": "yt es", "raw_count": 72598, "count": 196694, "decode_str": "ytes"} -{"id": 4686, "token": "cluded", "merges": "clud ed", "raw_count": 44758, "count": 196722, "decode_str": "cluded"} -{"id": 27337, "token": "failed", "merges": "f ailed", "raw_count": 196762, "count": 196762, "decode_str": "failed"} -{"id": 26522, "token": "707", "merges": "70 7", "raw_count": 196774, "count": 196774, "decode_str": "707"} -{"id": 37717, "token": "partition", "merges": "part ition", "raw_count": 196775, "count": 196775, "decode_str": "partition"} -{"id": 14382, "token": "each", "merges": "e ach", "raw_count": 196803, "count": 196803, "decode_str": "each"} -{"id": 52854, "token": "\u00e7\u0132\u00ac", "merges": "\u00e7\u0132 \u00ac", "raw_count": 196812, "count": 196812, "decode_str": "\u742c"} -{"id": 27222, "token": "342", "merges": "34 2", "raw_count": 196844, "count": 196844, "decode_str": "342"} -{"id": 53093, "token": "\u00e7\u00a2\u013c", "merges": "\u00e7\u00a2 \u013c", "raw_count": 196884, "count": 196884, "decode_str": "\u789a"} -{"id": 52310, "token": "\u00e6\u00a1\u00a1", "merges": "\u00e6\u00a1 \u00a1", "raw_count": 196908, "count": 196908, "decode_str": "\u6861"} -{"id": 3502, "token": "olds", "merges": "old s", "raw_count": 93892, "count": 196932, "decode_str": "olds"} -{"id": 28757, "token": "479", "merges": "47 9", "raw_count": 196997, "count": 196997, "decode_str": "479"} -{"id": 53994, "token": "\u00e8\u00b7\u0130", "merges": "\u00e8\u00b7 \u0130", "raw_count": 197007, "count": 197007, "decode_str": "\u8dce"} -{"id": 5739, "token": "\u0120stock", "merges": "\u0120st ock", "raw_count": 197021, "count": 197021, "decode_str": " stock"} -{"id": 24984, "token": "\u0120indigenous", "merges": "\u0120ind igenous", "raw_count": 197037, "count": 197037, "decode_str": " indigenous"} -{"id": 6013, "token": "poses", "merges": "pos es", "raw_count": 44439, "count": 197054, "decode_str": "poses"} -{"id": 3966, "token": "\u0120etc", "merges": "\u0120et c", "raw_count": 197060, "count": 197060, "decode_str": " etc"} -{"id": 3542, "token": "\u0120written", "merges": "\u0120wr itten", "raw_count": 197096, "count": 197096, "decode_str": " written"} -{"id": 3694, "token": "\u0120software", "merges": "\u0120soft ware", "raw_count": 197108, "count": 197108, "decode_str": " software"} -{"id": 13183, "token": "andy", "merges": "and y", "raw_count": 196919, "count": 197136, "decode_str": "andy"} -{"id": 3907, "token": "\u0120independent", "merges": "\u0120ind ependent", "raw_count": 197247, "count": 197247, "decode_str": " independent"} -{"id": 6772, "token": "appro", "merges": "app ro", "raw_count": 83010, "count": 197270, "decode_str": "appro"} -{"id": 4401, "token": "\u0120manufact", "merges": "\u0120man ufact", "raw_count": 4791, "count": 197466, "decode_str": " manufact"} -{"id": 52883, "token": "\u00e7\u0136\u00be", "merges": "\u00e7\u0136 \u00be", "raw_count": 197500, "count": 197500, "decode_str": "\u753e"} -{"id": 29519, "token": "cook", "merges": "c ook", "raw_count": 197551, "count": 197551, "decode_str": "cook"} -{"id": 52728, "token": "\u00e7\u0124\u0136", "merges": "\u00e7\u0124 \u0136", "raw_count": 197599, "count": 197599, "decode_str": "\u7094"} -{"id": 31671, "token": "698", "merges": "69 8", "raw_count": 197618, "count": 197618, "decode_str": "698"} -{"id": 17894, "token": "otor", "merges": "ot or", "raw_count": 104230, "count": 197628, "decode_str": "otor"} -{"id": 5627, "token": "*)", "merges": "* )", "raw_count": 197664, "count": 197664, "decode_str": "*)"} -{"id": 8382, "token": "bel", "merges": "b el", "raw_count": 113949, "count": 197796, "decode_str": "bel"} -{"id": 8333, "token": "\u0120practices", "merges": "\u0120pract ices", "raw_count": 197816, "count": 197816, "decode_str": " practices"} -{"id": 14233, "token": "ceptions", "merges": "cept ions", "raw_count": 191670, "count": 197889, "decode_str": "ceptions"} -{"id": 9108, "token": "bro", "merges": "b ro", "raw_count": 117189, "count": 197933, "decode_str": "bro"} -{"id": 15044, "token": "square", "merges": "s quare", "raw_count": 197963, "count": 197963, "decode_str": "square"} -{"id": 8781, "token": "\u0120container", "merges": "\u0120contain er", "raw_count": 198002, "count": 198002, "decode_str": " container"} -{"id": 35450, "token": "'},", "merges": "' },", "raw_count": 198041, "count": 198041, "decode_str": "'},"} -{"id": 44563, "token": "588", "merges": "5 88", "raw_count": 198146, "count": 198146, "decode_str": "588"} -{"id": 6458, "token": "lif", "merges": "l if", "raw_count": 166491, "count": 198233, "decode_str": "lif"} -{"id": 5590, "token": "hal", "merges": "h al", "raw_count": 143392, "count": 198233, "decode_str": "hal"} -{"id": 6779, "token": "\u0120representation", "merges": "\u0120represent ation", "raw_count": 198267, "count": 198267, "decode_str": " representation"} -{"id": 41488, "token": "MQ", "merges": "M Q", "raw_count": 198268, "count": 198268, "decode_str": "MQ"} -{"id": 29206, "token": "pixel", "merges": "p ixel", "raw_count": 198317, "count": 198317, "decode_str": "pixel"} -{"id": 40956, "token": "MU", "merges": "M U", "raw_count": 198333, "count": 198333, "decode_str": "MU"} -{"id": 48180, "token": "930", "merges": "9 30", "raw_count": 198339, "count": 198339, "decode_str": "930"} -{"id": 26116, "token": "Sa", "merges": "S a", "raw_count": 198387, "count": 198387, "decode_str": "Sa"} -{"id": 6597, "token": "anes", "merges": "an es", "raw_count": 52228, "count": 198388, "decode_str": "anes"} -{"id": 2439, "token": "\u0120across", "merges": "\u0120ac ross", "raw_count": 198454, "count": 198454, "decode_str": " across"} -{"id": 18091, "token": "Account", "merges": "Acc ount", "raw_count": 198568, "count": 198568, "decode_str": "Account"} -{"id": 14193, "token": "<<", "merges": "< <", "raw_count": 198579, "count": 198579, "decode_str": "<<"} -{"id": 7211, "token": "\u0120notes", "merges": "\u0120not es", "raw_count": 198601, "count": 198601, "decode_str": " notes"} -{"id": 41290, "token": "\u0120americ", "merges": "\u0120am eric", "raw_count": 198604, "count": 198604, "decode_str": " americ"} -{"id": 12360, "token": "\u0120armed", "merges": "\u0120ar med", "raw_count": 198666, "count": 198666, "decode_str": " armed"} -{"id": 26428, "token": "Logger", "merges": "Log ger", "raw_count": 198667, "count": 198667, "decode_str": "Logger"} -{"id": 5001, "token": "\u0120regarding", "merges": "\u0120regard ing", "raw_count": 198702, "count": 198702, "decode_str": " regarding"} -{"id": 23667, "token": "rv", "merges": "r v", "raw_count": 198717, "count": 198717, "decode_str": "rv"} -{"id": 6723, "token": "Are", "merges": "A re", "raw_count": 68063, "count": 198741, "decode_str": "Are"} -{"id": 51087, "token": "\u00e5\u0137\u0138", "merges": "\u00e5\u0137 \u0138", "raw_count": 198762, "count": 198762, "decode_str": "\u5556"} -{"id": 11976, "token": "`,", "merges": "` ,", "raw_count": 194318, "count": 198792, "decode_str": "`,"} -{"id": 6693, "token": "Any", "merges": "An y", "raw_count": 174949, "count": 198796, "decode_str": "Any"} -{"id": 6609, "token": "orders", "merges": "ord ers", "raw_count": 146401, "count": 198800, "decode_str": "orders"} -{"id": 3661, "token": "\u0120controll", "merges": "\u0120cont roll", "raw_count": 3566, "count": 198810, "decode_str": " controll"} -{"id": 21761, "token": "\u0120tokens", "merges": "\u0120tok ens", "raw_count": 198823, "count": 198823, "decode_str": " tokens"} -{"id": 2558, "token": "\u0120percent", "merges": "\u0120per cent", "raw_count": 98632, "count": 198827, "decode_str": " percent"} -{"id": 39297, "token": "kv", "merges": "k v", "raw_count": 198922, "count": 198922, "decode_str": "kv"} -{"id": 28617, "token": "setting", "merges": "set ting", "raw_count": 198927, "count": 198927, "decode_str": "setting"} -{"id": 3915, "token": "\u0120ST", "merges": "\u0120S T", "raw_count": 121945, "count": 198957, "decode_str": " ST"} -{"id": 19238, "token": "Delete", "merges": "De lete", "raw_count": 199035, "count": 199035, "decode_str": "Delete"} -{"id": 8985, "token": "\u0120binary", "merges": "\u0120b inary", "raw_count": 199036, "count": 199036, "decode_str": " binary"} -{"id": 30830, "token": "chars", "merges": "ch ars", "raw_count": 149605, "count": 199064, "decode_str": "chars"} -{"id": 19598, "token": "sets", "merges": "set s", "raw_count": 199065, "count": 199065, "decode_str": "sets"} -{"id": 24562, "token": "374", "merges": "37 4", "raw_count": 199067, "count": 199067, "decode_str": "374"} -{"id": 26431, "token": "XY", "merges": "X Y", "raw_count": 199077, "count": 199077, "decode_str": "XY"} -{"id": 44449, "token": "740", "merges": "7 40", "raw_count": 199084, "count": 199084, "decode_str": "740"} -{"id": 8171, "token": "\u0120replace", "merges": "\u0120repl ace", "raw_count": 199092, "count": 199092, "decode_str": " replace"} -{"id": 48207, "token": "Chan", "merges": "Ch an", "raw_count": 199125, "count": 199125, "decode_str": "Chan"} -{"id": 5823, "token": "\u0120mm", "merges": "\u0120m m", "raw_count": 195215, "count": 199171, "decode_str": " mm"} -{"id": 21784, "token": "Bur", "merges": "B ur", "raw_count": 199176, "count": 199176, "decode_str": "Bur"} -{"id": 5498, "token": "Don", "merges": "D on", "raw_count": 193527, "count": 199206, "decode_str": "Don"} -{"id": 14688, "token": "\u0120aug", "merges": "\u0120a ug", "raw_count": 151298, "count": 199210, "decode_str": " aug"} -{"id": 12427, "token": "icking", "merges": "ick ing", "raw_count": 50135, "count": 199314, "decode_str": "icking"} -{"id": 2717, "token": "\u0120nothing", "merges": "\u0120not hing", "raw_count": 199335, "count": 199335, "decode_str": " nothing"} -{"id": 28333, "token": "459", "merges": "45 9", "raw_count": 199435, "count": 199435, "decode_str": "459"} -{"id": 6795, "token": "small", "merges": "sm all", "raw_count": 199306, "count": 199449, "decode_str": "small"} -{"id": 52483, "token": "\u00e6\u00b1\u00a8", "merges": "\u00e6\u00b1 \u00a8", "raw_count": 199461, "count": 199461, "decode_str": "\u6c68"} -{"id": 46376, "token": "recv", "merges": "rec v", "raw_count": 199492, "count": 199492, "decode_str": "recv"} -{"id": 2912, "token": "------------", "merges": "-------- ----", "raw_count": 41221, "count": 199508, "decode_str": "------------"} -{"id": 16339, "token": "Bet", "merges": "B et", "raw_count": 136612, "count": 199546, "decode_str": "Bet"} -{"id": 15083, "token": "expl", "merges": "ex pl", "raw_count": 191192, "count": 199631, "decode_str": "expl"} -{"id": 22288, "token": "ategories", "merges": "ateg ories", "raw_count": 3653, "count": 199651, "decode_str": "ategories"} -{"id": 13494, "token": "requency", "merges": "requ ency", "raw_count": 711, "count": 199657, "decode_str": "requency"} -{"id": 4763, "token": "\u0120receive", "merges": "\u0120rece ive", "raw_count": 199704, "count": 199704, "decode_str": " receive"} -{"id": 4206, "token": "iled", "merges": "il ed", "raw_count": 69854, "count": 199721, "decode_str": "iled"} -{"id": 5370, "token": "\u0120panel", "merges": "\u0120pan el", "raw_count": 199730, "count": 199730, "decode_str": " panel"} -{"id": 1663, "token": "\u0120really", "merges": "\u0120re ally", "raw_count": 199757, "count": 199757, "decode_str": " really"} -{"id": 2570, "token": "\u0120complex", "merges": "\u0120comp lex", "raw_count": 166990, "count": 199809, "decode_str": " complex"} -{"id": 18867, "token": "shared", "merges": "sh ared", "raw_count": 199858, "count": 199858, "decode_str": "shared"} -{"id": 53449, "token": "\u00e8\u0122\u0134", "merges": "\u00e8\u0122 \u0134", "raw_count": 199887, "count": 199887, "decode_str": "\u8012"} -{"id": 3184, "token": "ying", "merges": "y ing", "raw_count": 97698, "count": 199901, "decode_str": "ying"} -{"id": 29913, "token": "alias", "merges": "al ias", "raw_count": 199943, "count": 199943, "decode_str": "alias"} -{"id": 53120, "token": "\u00e7\u00a5\u013e", "merges": "\u00e7\u00a5 \u013e", "raw_count": 199982, "count": 199982, "decode_str": "\u795c"} -{"id": 8745, "token": "\u0120deploy", "merges": "\u0120de ploy", "raw_count": 52508, "count": 200018, "decode_str": " deploy"} -{"id": 6221, "token": "\u0120contained", "merges": "\u0120cont ained", "raw_count": 200074, "count": 200074, "decode_str": " contained"} -{"id": 14054, "token": "atom", "merges": "at om", "raw_count": 198359, "count": 200095, "decode_str": "atom"} -{"id": 18958, "token": "+(", "merges": "+ (", "raw_count": 200152, "count": 200152, "decode_str": "+("} -{"id": 5820, "token": "\u0120workers", "merges": "\u0120work ers", "raw_count": 200174, "count": 200174, "decode_str": " workers"} -{"id": 21329, "token": "dan", "merges": "d an", "raw_count": 200188, "count": 200188, "decode_str": "dan"} -{"id": 20347, "token": "lm", "merges": "l m", "raw_count": 200238, "count": 200238, "decode_str": "lm"} -{"id": 23985, "token": "dw", "merges": "d w", "raw_count": 200278, "count": 200278, "decode_str": "dw"} -{"id": 28256, "token": "lists", "merges": "l ists", "raw_count": 200293, "count": 200293, "decode_str": "lists"} -{"id": 4469, "token": "\u0120expressed", "merges": "\u0120exp ressed", "raw_count": 200349, "count": 200349, "decode_str": " expressed"} -{"id": 23807, "token": "Variable", "merges": "V ariable", "raw_count": 200352, "count": 200352, "decode_str": "Variable"} -{"id": 20167, "token": "Normal", "merges": "N ormal", "raw_count": 200355, "count": 200355, "decode_str": "Normal"} -{"id": 30977, "token": "415", "merges": "4 15", "raw_count": 200465, "count": 200465, "decode_str": "415"} -{"id": 15191, "token": "\u0120plugin", "merges": "\u0120pl ugin", "raw_count": 200471, "count": 200471, "decode_str": " plugin"} -{"id": 15973, "token": "igo", "merges": "ig o", "raw_count": 200499, "count": 200499, "decode_str": "igo"} -{"id": 52739, "token": "\u00e7\u0124\u00b7", "merges": "\u00e7\u0124 \u00b7", "raw_count": 200748, "count": 200748, "decode_str": "\u70b7"} -{"id": 3611, "token": "ague", "merges": "ag ue", "raw_count": 52312, "count": 200754, "decode_str": "ague"} -{"id": 3216, "token": "\u0120ground", "merges": "\u0120gr ound", "raw_count": 189579, "count": 200762, "decode_str": " ground"} -{"id": 12212, "token": "\u0120prevention", "merges": "\u0120prev ention", "raw_count": 200800, "count": 200800, "decode_str": " prevention"} -{"id": 17733, "token": "XML", "merges": "X ML", "raw_count": 200832, "count": 200832, "decode_str": "XML"} -{"id": 6197, "token": "\u0120sentence", "merges": "\u0120sent ence", "raw_count": 200892, "count": 200892, "decode_str": " sentence"} -{"id": 2872, "token": "\u0120young", "merges": "\u0120you ng", "raw_count": 193937, "count": 200976, "decode_str": " young"} -{"id": 9484, "token": "\u0120symbol", "merges": "\u0120symb ol", "raw_count": 201060, "count": 201060, "decode_str": " symbol"} -{"id": 54180, "token": "\u00e9\u0125\u00a7", "merges": "\u00e9\u0125 \u00a7", "raw_count": 201074, "count": 201074, "decode_str": "\u90e7"} -{"id": 6148, "token": "van", "merges": "v an", "raw_count": 182571, "count": 201111, "decode_str": "van"} -{"id": 8064, "token": "\u0120funds", "merges": "\u0120fun ds", "raw_count": 201135, "count": 201135, "decode_str": " funds"} -{"id": 33980, "token": "qi", "merges": "q i", "raw_count": 201213, "count": 201213, "decode_str": "qi"} -{"id": 11570, "token": "\u0120personnel", "merges": "\u0120person nel", "raw_count": 201233, "count": 201233, "decode_str": " personnel"} -{"id": 9546, "token": "\u0120trib", "merges": "\u0120t rib", "raw_count": 32706, "count": 201395, "decode_str": " trib"} -{"id": 24447, "token": "444", "merges": "44 4", "raw_count": 201412, "count": 201412, "decode_str": "444"} -{"id": 12582, "token": "022", "merges": "0 22", "raw_count": 201433, "count": 201433, "decode_str": "022"} -{"id": 12237, "token": "double", "merges": "d ouble", "raw_count": 201459, "count": 201459, "decode_str": "double"} -{"id": 53241, "token": "\u00e7\u00ae\u0132", "merges": "\u00e7\u00ae \u0132", "raw_count": 201520, "count": 201520, "decode_str": "\u7b90"} -{"id": 9335, "token": "nic", "merges": "n ic", "raw_count": 123431, "count": 201637, "decode_str": "nic"} -{"id": 36981, "token": "processed", "merges": "process ed", "raw_count": 201801, "count": 201801, "decode_str": "processed"} -{"id": 1928, "token": "\u0120feel", "merges": "\u0120fe el", "raw_count": 133882, "count": 201832, "decode_str": " feel"} -{"id": 42090, "token": "\u0120Attribute", "merges": "\u0120Att ribute", "raw_count": 201877, "count": 201877, "decode_str": " Attribute"} -{"id": 26555, "token": "surface", "merges": "sur face", "raw_count": 201972, "count": 201972, "decode_str": "surface"} -{"id": 15548, "token": "\u0120python", "merges": "\u0120py thon", "raw_count": 201994, "count": 201994, "decode_str": " python"} -{"id": 41794, "token": "redirect", "merges": "red irect", "raw_count": 202039, "count": 202039, "decode_str": "redirect"} -{"id": 21255, "token": "\u0120ii", "merges": "\u0120i i", "raw_count": 202170, "count": 202170, "decode_str": " ii"} -{"id": 3464, "token": "\u0120remain", "merges": "\u0120rem ain", "raw_count": 166140, "count": 202174, "decode_str": " remain"} -{"id": 5813, "token": "\u0120fif", "merges": "\u0120f if", "raw_count": 21601, "count": 202175, "decode_str": " fif"} -{"id": 4870, "token": "\u0120processes", "merges": "\u0120process es", "raw_count": 202337, "count": 202337, "decode_str": " processes"} -{"id": 5803, "token": "\u0120NOT", "merges": "\u0120N OT", "raw_count": 135903, "count": 202417, "decode_str": " NOT"} -{"id": 3038, "token": "\u0120hours", "merges": "\u0120h ours", "raw_count": 202436, "count": 202436, "decode_str": " hours"} -{"id": 19107, "token": "\u0120Request", "merges": "\u0120Re quest", "raw_count": 202487, "count": 202487, "decode_str": " Request"} -{"id": 13443, "token": "Product", "merges": "Pro duct", "raw_count": 173755, "count": 202511, "decode_str": "Product"} -{"id": 10207, "token": "uer", "merges": "u er", "raw_count": 200793, "count": 202525, "decode_str": "uer"} -{"id": 53138, "token": "\u00e7\u00a6\u013d", "merges": "\u00e7\u00a6 \u013d", "raw_count": 202549, "count": 202549, "decode_str": "\u799b"} -{"id": 6510, "token": "\u0120origin", "merges": "\u0120orig in", "raw_count": 190171, "count": 202568, "decode_str": " origin"} -{"id": 17643, "token": "AST", "merges": "A ST", "raw_count": 202587, "count": 202587, "decode_str": "AST"} -{"id": 51731, "token": "\u00e6\u0123\u00b8", "merges": "\u00e6\u0123 \u00b8", "raw_count": 202638, "count": 202638, "decode_str": "\u6078"} -{"id": 4164, "token": "\u0120il", "merges": "\u0120 il", "raw_count": 91292, "count": 202665, "decode_str": " il"} -{"id": 11710, "token": "ERV", "merges": "ER V", "raw_count": 37779, "count": 202679, "decode_str": "ERV"} -{"id": 4141, "token": "\u00d1\u012d", "merges": "\u00d1 \u012d", "raw_count": 90348, "count": 202684, "decode_str": "\u044b"} -{"id": 5194, "token": "\u0120agree", "merges": "\u0120ag ree", "raw_count": 193952, "count": 202695, "decode_str": " agree"} -{"id": 36294, "token": "sender", "merges": "s ender", "raw_count": 202741, "count": 202741, "decode_str": "sender"} -{"id": 49926, "token": "TOD", "merges": "T OD", "raw_count": 202838, "count": 202838, "decode_str": "TOD"} -{"id": 34459, "token": "flush", "merges": "fl ush", "raw_count": 202983, "count": 202983, "decode_str": "flush"} -{"id": 2427, "token": "\u0120went", "merges": "\u0120w ent", "raw_count": 203053, "count": 203053, "decode_str": " went"} -{"id": 3289, "token": "\u0120fire", "merges": "\u0120f ire", "raw_count": 141640, "count": 203093, "decode_str": " fire"} -{"id": 14063, "token": "connected", "merges": "conne cted", "raw_count": 181983, "count": 203124, "decode_str": "connected"} -{"id": 2716, "token": "\u0120half", "merges": "\u0120h alf", "raw_count": 198628, "count": 203158, "decode_str": " half"} -{"id": 5286, "token": "\u0120administration", "merges": "\u0120administ ration", "raw_count": 203166, "count": 203166, "decode_str": " administration"} -{"id": 20439, "token": "Policy", "merges": "Pol icy", "raw_count": 203167, "count": 203167, "decode_str": "Policy"} -{"id": 6202, "token": "\u0120DE", "merges": "\u0120D E", "raw_count": 70679, "count": 203185, "decode_str": " DE"} -{"id": 3936, "token": "\u0120takes", "merges": "\u0120t akes", "raw_count": 203209, "count": 203209, "decode_str": " takes"} -{"id": 21505, "token": "pages", "merges": "p ages", "raw_count": 203281, "count": 203281, "decode_str": "pages"} -{"id": 37279, "token": "Switch", "merges": "Sw itch", "raw_count": 203338, "count": 203338, "decode_str": "Switch"} -{"id": 14750, "token": "kk", "merges": "k k", "raw_count": 203339, "count": 203339, "decode_str": "kk"} -{"id": 34115, "token": "NotFound", "merges": "Not Found", "raw_count": 203414, "count": 203414, "decode_str": "NotFound"} -{"id": 21288, "token": "'\"", "merges": "' \"", "raw_count": 203430, "count": 203430, "decode_str": "'\""} -{"id": 33309, "token": "perm", "merges": "per m", "raw_count": 203439, "count": 203439, "decode_str": "perm"} -{"id": 19020, "token": "eva", "merges": "ev a", "raw_count": 203203, "count": 203455, "decode_str": "eva"} -{"id": 3835, "token": "\u0120cover", "merges": "\u0120co ver", "raw_count": 162211, "count": 203503, "decode_str": " cover"} -{"id": 22388, "token": "Argument", "merges": "Arg ument", "raw_count": 199636, "count": 203504, "decode_str": "Argument"} -{"id": 6894, "token": "ipher", "merges": "ip her", "raw_count": 37561, "count": 203522, "decode_str": "ipher"} -{"id": 7609, "token": "\u012041", "merges": "\u01204 1", "raw_count": 203543, "count": 203543, "decode_str": " 41"} -{"id": 26205, "token": "VAR", "merges": "V AR", "raw_count": 203576, "count": 203576, "decode_str": "VAR"} -{"id": 3530, "token": "\u0120samples", "merges": "\u0120sam ples", "raw_count": 203671, "count": 203671, "decode_str": " samples"} -{"id": 22052, "token": "Ro", "merges": "R o", "raw_count": 203740, "count": 203740, "decode_str": "Ro"} -{"id": 3300, "token": "\u0120sem", "merges": "\u0120s em", "raw_count": 47756, "count": 203741, "decode_str": " sem"} -{"id": 21049, "token": "quote", "merges": "qu ote", "raw_count": 203768, "count": 203768, "decode_str": "quote"} -{"id": 8623, "token": "align", "merges": "al ign", "raw_count": 203877, "count": 203877, "decode_str": "align"} -{"id": 8620, "token": "Good", "merges": "G ood", "raw_count": 203885, "count": 203885, "decode_str": "Good"} -{"id": 22492, "token": "jj", "merges": "j j", "raw_count": 203886, "count": 203886, "decode_str": "jj"} -{"id": 11708, "token": "STAT", "merges": "ST AT", "raw_count": 68728, "count": 203935, "decode_str": "STAT"} -{"id": 4586, "token": "rier", "merges": "ri er", "raw_count": 82292, "count": 203967, "decode_str": "rier"} -{"id": 15491, "token": "West", "merges": "W est", "raw_count": 204020, "count": 204020, "decode_str": "West"} -{"id": 34940, "token": "ROM", "merges": "R OM", "raw_count": 204054, "count": 204054, "decode_str": "ROM"} -{"id": 29676, "token": "cg", "merges": "c g", "raw_count": 204128, "count": 204128, "decode_str": "cg"} -{"id": 40957, "token": "numbers", "merges": "num bers", "raw_count": 204266, "count": 204266, "decode_str": "numbers"} -{"id": 4613, "token": "\u0120candid", "merges": "\u0120cand id", "raw_count": 10994, "count": 204300, "decode_str": " candid"} -{"id": 3867, "token": "illing", "merges": "ill ing", "raw_count": 84088, "count": 204326, "decode_str": "illing"} -{"id": 25261, "token": "ICS", "merges": "IC S", "raw_count": 204365, "count": 204365, "decode_str": "ICS"} -{"id": 49959, "token": "suffix", "merges": "s uffix", "raw_count": 204447, "count": 204447, "decode_str": "suffix"} -{"id": 19807, "token": "668", "merges": "6 68", "raw_count": 204447, "count": 204447, "decode_str": "668"} -{"id": 32965, "token": "identity", "merges": "ident ity", "raw_count": 204513, "count": 204513, "decode_str": "identity"} -{"id": 1849, "token": "'ve", "merges": "' ve", "raw_count": 204539, "count": 204539, "decode_str": "'ve"} -{"id": 31969, "token": "Steve", "merges": "Ste ve", "raw_count": 204603, "count": 204603, "decode_str": "Steve"} -{"id": 16662, "token": "joint", "merges": "j oint", "raw_count": 189363, "count": 204614, "decode_str": "joint"} -{"id": 4246, "token": "cember", "merges": "ce mber", "raw_count": 196981, "count": 204620, "decode_str": "cember"} -{"id": 4322, "token": "\u0120threat", "merges": "\u0120th reat", "raw_count": 91787, "count": 204623, "decode_str": " threat"} -{"id": 10787, "token": "lers", "merges": "l ers", "raw_count": 157108, "count": 204722, "decode_str": "lers"} -{"id": 7675, "token": "lu", "merges": "l u", "raw_count": 182632, "count": 204769, "decode_str": "lu"} -{"id": 33098, "token": "\u00e2\u0122\u0136\u00e2\u0122\u0136\u00e2\u0122\u0136\u00e2\u0122\u0136\u00e2\u0122\u0136\u00e2\u0122\u0136\u00e2\u0122\u0136\u00e2\u0122\u0136", "merges": "\u00e2\u0122\u0136\u00e2\u0122\u0136\u00e2\u0122\u0136\u00e2\u0122\u0136 \u00e2\u0122\u0136\u00e2\u0122\u0136\u00e2\u0122\u0136\u00e2\u0122\u0136", "raw_count": 204878, "count": 204878, "decode_str": "\u2014\u2014\u2014\u2014\u2014\u2014\u2014\u2014"} -{"id": 20027, "token": "CAP", "merges": "C AP", "raw_count": 204881, "count": 204881, "decode_str": "CAP"} -{"id": 5141, "token": "\u0120reduction", "merges": "\u0120redu ction", "raw_count": 204940, "count": 204940, "decode_str": " reduction"} -{"id": 53010, "token": "\u00e7\u013e\u00a6", "merges": "\u00e7\u013e \u00a6", "raw_count": 204940, "count": 204940, "decode_str": "\u7726"} -{"id": 25610, "token": "company", "merges": "comp any", "raw_count": 204951, "count": 204951, "decode_str": "company"} -{"id": 5502, "token": "\u0120transition", "merges": "\u0120trans ition", "raw_count": 159329, "count": 204954, "decode_str": " transition"} -{"id": 53708, "token": "\u00e8\u00a1\u00a9", "merges": "\u00e8\u00a1 \u00a9", "raw_count": 204966, "count": 204966, "decode_str": "\u8869"} -{"id": 13029, "token": "pow", "merges": "p ow", "raw_count": 153944, "count": 204978, "decode_str": "pow"} -{"id": 13820, "token": "MAP", "merges": "M AP", "raw_count": 204981, "count": 204981, "decode_str": "MAP"} -{"id": 6968, "token": "uh", "merges": "u h", "raw_count": 197942, "count": 204983, "decode_str": "uh"} -{"id": 13585, "token": "wrap", "merges": "w rap", "raw_count": 205036, "count": 205036, "decode_str": "wrap"} -{"id": 7881, "token": "\u0120challenges", "merges": "\u0120challeng es", "raw_count": 205065, "count": 205065, "decode_str": " challenges"} -{"id": 16388, "token": "peat", "merges": "pe at", "raw_count": 23020, "count": 205102, "decode_str": "peat"} -{"id": 28766, "token": "909", "merges": "90 9", "raw_count": 205169, "count": 205169, "decode_str": "909"} -{"id": 8432, "token": "ira", "merges": "ir a", "raw_count": 199401, "count": 205289, "decode_str": "ira"} -{"id": 3625, "token": "\u0120primary", "merges": "\u0120prim ary", "raw_count": 205333, "count": 205333, "decode_str": " primary"} -{"id": 27003, "token": "),(", "merges": "), (", "raw_count": 205370, "count": 205370, "decode_str": "),("} -{"id": 25629, "token": "average", "merges": "a verage", "raw_count": 205398, "count": 205398, "decode_str": "average"} -{"id": 3946, "token": "\u0120practice", "merges": "\u0120pract ice", "raw_count": 205414, "count": 205414, "decode_str": " practice"} -{"id": 26274, "token": "343", "merges": "34 3", "raw_count": 205486, "count": 205486, "decode_str": "343"} -{"id": 6303, "token": "\u0120master", "merges": "\u0120m aster", "raw_count": 200025, "count": 205506, "decode_str": " master"} -{"id": 5323, "token": "\u0120laws", "merges": "\u0120law s", "raw_count": 200915, "count": 205534, "decode_str": " laws"} -{"id": 5308, "token": "wood", "merges": "wo od", "raw_count": 180526, "count": 205540, "decode_str": "wood"} -{"id": 4634, "token": "overy", "merges": "o very", "raw_count": 42649, "count": 205651, "decode_str": "overy"} -{"id": 19467, "token": "Lib", "merges": "L ib", "raw_count": 205689, "count": 205689, "decode_str": "Lib"} -{"id": 7876, "token": "eli", "merges": "el i", "raw_count": 69654, "count": 205713, "decode_str": "eli"} -{"id": 5673, "token": "\u0120interface", "merges": "\u0120inter face", "raw_count": 205720, "count": 205720, "decode_str": " interface"} -{"id": 13217, "token": "linux", "merges": "lin ux", "raw_count": 205827, "count": 205827, "decode_str": "linux"} -{"id": 14135, "token": "TL", "merges": "T L", "raw_count": 205751, "count": 205868, "decode_str": "TL"} -{"id": 44128, "token": "schedule", "merges": "sche dule", "raw_count": 205886, "count": 205886, "decode_str": "schedule"} -{"id": 25217, "token": "Ig", "merges": "I g", "raw_count": 205903, "count": 205903, "decode_str": "Ig"} -{"id": 15356, "token": "health", "merges": "he alth", "raw_count": 181967, "count": 205904, "decode_str": "health"} -{"id": 6731, "token": "iler", "merges": "il er", "raw_count": 68497, "count": 205997, "decode_str": "iler"} -{"id": 17431, "token": "igenous", "merges": "igen ous", "raw_count": 8938, "count": 206024, "decode_str": "igenous"} -{"id": 4224, "token": "mpt", "merges": "m pt", "raw_count": 16244, "count": 206055, "decode_str": "mpt"} -{"id": 9710, "token": "Stat", "merges": "St at", "raw_count": 85810, "count": 206081, "decode_str": "Stat"} -{"id": 54495, "token": "\u00e9\u00aa\u012a", "merges": "\u00e9\u00aa \u012a", "raw_count": 206123, "count": 206123, "decode_str": "\u9a88"} -{"id": 5327, "token": "ellig", "merges": "ell ig", "raw_count": 9447, "count": 206146, "decode_str": "ellig"} -{"id": 10471, "token": "\u0120partners", "merges": "\u0120part ners", "raw_count": 206155, "count": 206155, "decode_str": " partners"} -{"id": 53344, "token": "\u00e7\u00bb\u0136", "merges": "\u00e7\u00bb \u0136", "raw_count": 206160, "count": 206160, "decode_str": "\u7ed4"} -{"id": 9652, "token": "apes", "merges": "ap es", "raw_count": 144140, "count": 206171, "decode_str": "apes"} -{"id": 24845, "token": "ctrl", "merges": "ct rl", "raw_count": 206239, "count": 206239, "decode_str": "ctrl"} -{"id": 52838, "token": "\u00e7\u0131\u00b2", "merges": "\u00e7\u0131 \u00b2", "raw_count": 206302, "count": 206302, "decode_str": "\u73f2"} -{"id": 2210, "token": "\u0120came", "merges": "\u0120c ame", "raw_count": 206318, "count": 206318, "decode_str": " came"} -{"id": 28971, "token": "runner", "merges": "run ner", "raw_count": 206334, "count": 206334, "decode_str": "runner"} -{"id": 47977, "token": "__.", "merges": "__ .", "raw_count": 206359, "count": 206359, "decode_str": "__."} -{"id": 34331, "token": "HIV", "merges": "H IV", "raw_count": 206389, "count": 206389, "decode_str": "HIV"} -{"id": 28197, "token": "browser", "merges": "b rowser", "raw_count": 206407, "count": 206407, "decode_str": "browser"} -{"id": 22552, "token": "Arm", "merges": "A rm", "raw_count": 206459, "count": 206459, "decode_str": "Arm"} -{"id": 6850, "token": "isher", "merges": "is her", "raw_count": 88672, "count": 206483, "decode_str": "isher"} -{"id": 2822, "token": "\u0120near", "merges": "\u0120ne ar", "raw_count": 175972, "count": 206487, "decode_str": " near"} -{"id": 17229, "token": "Rect", "merges": "R ect", "raw_count": 206524, "count": 206524, "decode_str": "Rect"} -{"id": 4773, "token": "ptr", "merges": "pt r", "raw_count": 205746, "count": 206524, "decode_str": "ptr"} -{"id": 3485, "token": "elling", "merges": "ell ing", "raw_count": 72906, "count": 206528, "decode_str": "elling"} -{"id": 14271, "token": "\u0120html", "merges": "\u0120h tml", "raw_count": 206585, "count": 206585, "decode_str": " html"} -{"id": 156, "token": "\u00e0", "merges": "NULL", "raw_count": 5159, "count": 206603, "decode_str": "\ufffd"} -{"id": 43323, "token": "\u0120uid", "merges": "\u0120u id", "raw_count": 206626, "count": 206626, "decode_str": " uid"} -{"id": 1623, "token": "\u0120On", "merges": "\u0120O n", "raw_count": 111671, "count": 206628, "decode_str": " On"} -{"id": 33505, "token": "778", "merges": "77 8", "raw_count": 206631, "count": 206631, "decode_str": "778"} -{"id": 5105, "token": "\u0120eth", "merges": "\u0120 eth", "raw_count": 71879, "count": 206666, "decode_str": " eth"} -{"id": 4513, "token": "iate", "merges": "i ate", "raw_count": 114028, "count": 206728, "decode_str": "iate"} -{"id": 26931, "token": "seg", "merges": "se g", "raw_count": 206864, "count": 206864, "decode_str": "seg"} -{"id": 27656, "token": "Jeff", "merges": "J eff", "raw_count": 206870, "count": 206870, "decode_str": "Jeff"} -{"id": 36469, "token": "Lim", "merges": "L im", "raw_count": 206905, "count": 206905, "decode_str": "Lim"} -{"id": 28459, "token": "341", "merges": "34 1", "raw_count": 206906, "count": 206906, "decode_str": "341"} -{"id": 25039, "token": "354", "merges": "35 4", "raw_count": 206931, "count": 206931, "decode_str": "354"} -{"id": 47295, "token": "ighb", "merges": "igh b", "raw_count": 206969, "count": 206969, "decode_str": "ighb"} -{"id": 23654, "token": "gc", "merges": "g c", "raw_count": 207055, "count": 207055, "decode_str": "gc"} -{"id": 27616, "token": "href", "merges": "h ref", "raw_count": 207083, "count": 207083, "decode_str": "href"} -{"id": 9587, "token": "erry", "merges": "er ry", "raw_count": 165792, "count": 207163, "decode_str": "erry"} -{"id": 4944, "token": "\u0120fit", "merges": "\u0120f it", "raw_count": 207206, "count": 207206, "decode_str": " fit"} -{"id": 3947, "token": "\u0120compet", "merges": "\u0120comp et", "raw_count": 39586, "count": 207326, "decode_str": " compet"} -{"id": 3139, "token": "\u0120itself", "merges": "\u0120its elf", "raw_count": 207376, "count": 207376, "decode_str": " itself"} -{"id": 46668, "token": "cci", "merges": "cc i", "raw_count": 207394, "count": 207394, "decode_str": "cci"} -{"id": 7259, "token": "\u0120procedures", "merges": "\u0120proced ures", "raw_count": 207481, "count": 207481, "decode_str": " procedures"} -{"id": 6496, "token": "Americ", "merges": "A meric", "raw_count": 9307, "count": 207481, "decode_str": "Americ"} -{"id": 7177, "token": "\u0120documents", "merges": "\u0120doc uments", "raw_count": 207576, "count": 207576, "decode_str": " documents"} -{"id": 43640, "token": "MIX", "merges": "MI X", "raw_count": 207656, "count": 207656, "decode_str": "MIX"} -{"id": 16668, "token": "wind", "merges": "w ind", "raw_count": 207692, "count": 207692, "decode_str": "wind"} -{"id": 17945, "token": "tl", "merges": "t l", "raw_count": 207710, "count": 207710, "decode_str": "tl"} -{"id": 12481, "token": "Total", "merges": "T otal", "raw_count": 207716, "count": 207716, "decode_str": "Total"} -{"id": 7127, "token": "\u012044", "merges": "\u01204 4", "raw_count": 207864, "count": 207864, "decode_str": " 44"} -{"id": 20824, "token": "\u0120schema", "merges": "\u0120sche ma", "raw_count": 207868, "count": 207868, "decode_str": " schema"} -{"id": 54537, "token": "\u00e9\u00bb\u0142", "merges": "\u00e9\u00bb \u0142", "raw_count": 207884, "count": 207884, "decode_str": "\u9ee0"} -{"id": 53652, "token": "\u00e8\u012d\u00a3", "merges": "\u00e8\u012d \u00a3", "raw_count": 207897, "count": 207897, "decode_str": "\u82e3"} -{"id": 26461, "token": "JO", "merges": "J O", "raw_count": 207923, "count": 207923, "decode_str": "JO"} -{"id": 13316, "token": "Bas", "merges": "B as", "raw_count": 70042, "count": 207969, "decode_str": "Bas"} -{"id": 25335, "token": "intern", "merges": "in tern", "raw_count": 129843, "count": 207981, "decode_str": "intern"} -{"id": 12100, "token": "\u0120refuge", "merges": "\u0120ref uge", "raw_count": 8981, "count": 208067, "decode_str": " refuge"} -{"id": 53906, "token": "\u00e8\u00b1\u00ba", "merges": "\u00e8\u00b1 \u00ba", "raw_count": 208081, "count": 208081, "decode_str": "\u8c7a"} -{"id": 11419, "token": "\u0120meta", "merges": "\u0120met a", "raw_count": 208103, "count": 208103, "decode_str": " meta"} -{"id": 18941, "token": "same", "merges": "s ame", "raw_count": 208104, "count": 208104, "decode_str": "same"} -{"id": 8928, "token": "\u0120cultural", "merges": "\u0120cult ural", "raw_count": 208159, "count": 208159, "decode_str": " cultural"} -{"id": 26338, "token": "363", "merges": "36 3", "raw_count": 208165, "count": 208165, "decode_str": "363"} -{"id": 32350, "token": "__)", "merges": "__ )", "raw_count": 208263, "count": 208263, "decode_str": "__)"} -{"id": 2798, "token": "\u0120heart", "merges": "\u0120he art", "raw_count": 175585, "count": 208380, "decode_str": " heart"} -{"id": 2169, "token": "\u0120higher", "merges": "\u0120hig her", "raw_count": 208439, "count": 208439, "decode_str": " higher"} -{"id": 8659, "token": "ted", "merges": "t ed", "raw_count": 65699, "count": 208565, "decode_str": "ted"} -{"id": 25409, "token": "DEFAULT", "merges": "DE FAULT", "raw_count": 208577, "count": 208577, "decode_str": "DEFAULT"} -{"id": 12354, "token": "oa", "merges": "o a", "raw_count": 203167, "count": 208604, "decode_str": "oa"} -{"id": 3730, "token": "\u0120refer", "merges": "\u0120ref er", "raw_count": 68573, "count": 208618, "decode_str": " refer"} -{"id": 4180, "token": "\u0120profess", "merges": "\u0120prof ess", "raw_count": 4743, "count": 208664, "decode_str": " profess"} -{"id": 4506, "token": "\u0120exerc", "merges": "\u0120ex erc", "raw_count": 1693, "count": 208770, "decode_str": " exerc"} -{"id": 12519, "token": "Range", "merges": "R ange", "raw_count": 208849, "count": 208849, "decode_str": "Range"} -{"id": 4561, "token": "\u0120generated", "merges": "\u0120gener ated", "raw_count": 208862, "count": 208862, "decode_str": " generated"} -{"id": 6265, "token": "\u0120authority", "merges": "\u0120author ity", "raw_count": 208863, "count": 208863, "decode_str": " authority"} -{"id": 12437, "token": "AMP", "merges": "AM P", "raw_count": 150264, "count": 208865, "decode_str": "AMP"} -{"id": 38586, "token": "840", "merges": "8 40", "raw_count": 208890, "count": 208890, "decode_str": "840"} -{"id": 43979, "token": "bob", "merges": "b ob", "raw_count": 208953, "count": 208953, "decode_str": "bob"} -{"id": 5671, "token": "itect", "merges": "ite ct", "raw_count": 33259, "count": 209102, "decode_str": "itect"} -{"id": 43756, "token": "IQ", "merges": "I Q", "raw_count": 209217, "count": 209217, "decode_str": "IQ"} -{"id": 7390, "token": "bour", "merges": "b our", "raw_count": 64414, "count": 209219, "decode_str": "bour"} -{"id": 4880, "token": ".\\", "merges": ". \\", "raw_count": 197116, "count": 209253, "decode_str": ".\\"} -{"id": 17703, "token": "bank", "merges": "b ank", "raw_count": 209354, "count": 209354, "decode_str": "bank"} -{"id": 26068, "token": "Think", "merges": "Th ink", "raw_count": 209383, "count": 209383, "decode_str": "Think"} -{"id": 21083, "token": "\u0120'<", "merges": "\u0120' <", "raw_count": 209388, "count": 209388, "decode_str": " '<"} -{"id": 10587, "token": "xc", "merges": "x c", "raw_count": 209405, "count": 209405, "decode_str": "xc"} -{"id": 11081, "token": "\u0120discrimination", "merges": "\u0120discrim ination", "raw_count": 209411, "count": 209411, "decode_str": " discrimination"} -{"id": 43557, "token": "920", "merges": "9 20", "raw_count": 209434, "count": 209434, "decode_str": "920"} -{"id": 2078, "token": "\u0120lik", "merges": "\u0120li k", "raw_count": 9659, "count": 209457, "decode_str": " lik"} -{"id": 4092, "token": "\u0120serious", "merges": "\u0120ser ious", "raw_count": 166380, "count": 209459, "decode_str": " serious"} -{"id": 20459, "token": "Job", "merges": "J ob", "raw_count": 209470, "count": 209470, "decode_str": "Job"} -{"id": 50913, "token": "\u00e5\u0130\u00a9", "merges": "\u00e5\u0130 \u00a9", "raw_count": 209510, "count": 209510, "decode_str": "\u53a9"} -{"id": 15630, "token": "\u012009", "merges": "\u01200 9", "raw_count": 209546, "count": 209546, "decode_str": " 09"} -{"id": 13307, "token": "nl", "merges": "n l", "raw_count": 206096, "count": 209577, "decode_str": "nl"} -{"id": 14451, "token": "hou", "merges": "h ou", "raw_count": 109730, "count": 209587, "decode_str": "hou"} -{"id": 7710, "token": "Mr", "merges": "M r", "raw_count": 209634, "count": 209634, "decode_str": "Mr"} -{"id": 28836, "token": "658", "merges": "65 8", "raw_count": 209743, "count": 209743, "decode_str": "658"} -{"id": 3795, "token": "\u0120compan", "merges": "\u0120comp an", "raw_count": 1425, "count": 209774, "decode_str": " compan"} -{"id": 1907, "token": "\u0120having", "merges": "\u0120ha ving", "raw_count": 209783, "count": 209783, "decode_str": " having"} -{"id": 23568, "token": "347", "merges": "34 7", "raw_count": 209902, "count": 209902, "decode_str": "347"} -{"id": 20922, "token": "291", "merges": "29 1", "raw_count": 209910, "count": 209910, "decode_str": "291"} -{"id": 35507, "token": "positions", "merges": "position s", "raw_count": 209914, "count": 209914, "decode_str": "positions"} -{"id": 11696, "token": "\u0120partnership", "merges": "\u0120part nership", "raw_count": 131154, "count": 210085, "decode_str": " partnership"} -{"id": 7750, "token": "false", "merges": "f alse", "raw_count": 210085, "count": 210085, "decode_str": "false"} -{"id": 11774, "token": "hm", "merges": "h m", "raw_count": 193594, "count": 210113, "decode_str": "hm"} -{"id": 17447, "token": "tar", "merges": "t ar", "raw_count": 210123, "count": 210123, "decode_str": "tar"} -{"id": 35630, "token": "416", "merges": "4 16", "raw_count": 210126, "count": 210126, "decode_str": "416"} -{"id": 18092, "token": "033", "merges": "0 33", "raw_count": 210173, "count": 210173, "decode_str": "033"} -{"id": 17299, "token": "Serial", "merges": "Ser ial", "raw_count": 73436, "count": 210187, "decode_str": "Serial"} -{"id": 13021, "token": "Rad", "merges": "R ad", "raw_count": 91763, "count": 210274, "decode_str": "Rad"} -{"id": 2930, "token": "etition", "merges": "et ition", "raw_count": 55939, "count": 210381, "decode_str": "etition"} -{"id": 12243, "token": "\u0120byte", "merges": "\u0120by te", "raw_count": 210404, "count": 210404, "decode_str": " byte"} -{"id": 4892, "token": "\u0120tour", "merges": "\u0120t our", "raw_count": 78391, "count": 210538, "decode_str": " tour"} -{"id": 5852, "token": "iders", "merges": "id ers", "raw_count": 92960, "count": 210589, "decode_str": "iders"} -{"id": 16046, "token": "igger", "merges": "ig ger", "raw_count": 18277, "count": 210645, "decode_str": "igger"} -{"id": 13980, "token": "security", "merges": "sec urity", "raw_count": 192005, "count": 210666, "decode_str": "security"} -{"id": 26980, "token": "MOD", "merges": "M OD", "raw_count": 210697, "count": 210697, "decode_str": "MOD"} -{"id": 2471, "token": "\u0120death", "merges": "\u0120de ath", "raw_count": 179611, "count": 210755, "decode_str": " death"} -{"id": 44224, "token": "dummy", "merges": "d ummy", "raw_count": 210769, "count": 210769, "decode_str": "dummy"} -{"id": 3933, "token": "\u0120accur", "merges": "\u0120acc ur", "raw_count": 4443, "count": 210842, "decode_str": " accur"} -{"id": 12327, "token": "riter", "merges": "rit er", "raw_count": 12691, "count": 210875, "decode_str": "riter"} -{"id": 44077, "token": "\u0120ids", "merges": "\u0120 ids", "raw_count": 210911, "count": 210911, "decode_str": " ids"} -{"id": 5145, "token": "\u0120machine", "merges": "\u0120mach ine", "raw_count": 210940, "count": 210940, "decode_str": " machine"} -{"id": 3480, "token": "\u0120lack", "merges": "\u0120l ack", "raw_count": 178370, "count": 210945, "decode_str": " lack"} -{"id": 23131, "token": "USER", "merges": "US ER", "raw_count": 210953, "count": 210953, "decode_str": "USER"} -{"id": 32557, "token": "calc", "merges": "cal c", "raw_count": 211084, "count": 211084, "decode_str": "calc"} -{"id": 14212, "token": "\u0120800", "merges": "\u01208 00", "raw_count": 211089, "count": 211089, "decode_str": " 800"} -{"id": 31983, "token": "VV", "merges": "V V", "raw_count": 211210, "count": 211210, "decode_str": "VV"} -{"id": 43670, "token": "770", "merges": "7 70", "raw_count": 211228, "count": 211228, "decode_str": "770"} -{"id": 23015, "token": "SEM", "merges": "SE M", "raw_count": 211300, "count": 211300, "decode_str": "SEM"} -{"id": 27158, "token": "708", "merges": "70 8", "raw_count": 211375, "count": 211375, "decode_str": "708"} -{"id": 5252, "token": "\u0120safety", "merges": "\u0120saf ety", "raw_count": 211379, "count": 211379, "decode_str": " safety"} -{"id": 17991, "token": "\u0120lord", "merges": "\u0120l ord", "raw_count": 211427, "count": 211427, "decode_str": " lord"} -{"id": 54560, "token": "\u00e9\u0137\u012c", "merges": "\u00e9\u0137 \u012c", "raw_count": 211427, "count": 211427, "decode_str": "\u954a"} -{"id": 2150, "token": "\u0120phys", "merges": "\u0120ph ys", "raw_count": 7767, "count": 211435, "decode_str": " phys"} -{"id": 6316, "token": "stract", "merges": "st ract", "raw_count": 5189, "count": 211438, "decode_str": "stract"} -{"id": 7400, "token": "ITY", "merges": "IT Y", "raw_count": 192698, "count": 211451, "decode_str": "ITY"} -{"id": 2280, "token": "\u0120mass", "merges": "\u0120m ass", "raw_count": 136329, "count": 211481, "decode_str": " mass"} -{"id": 34438, "token": "Park", "merges": "P ark", "raw_count": 211632, "count": 211632, "decode_str": "Park"} -{"id": 47346, "token": "!.", "merges": "! .", "raw_count": 211632, "count": 211632, "decode_str": "!."} -{"id": 15139, "token": "letter", "merges": "let ter", "raw_count": 200661, "count": 211669, "decode_str": "letter"} -{"id": 24946, "token": "noise", "merges": "no ise", "raw_count": 211683, "count": 211683, "decode_str": "noise"} -{"id": 32035, "token": "Way", "merges": "W ay", "raw_count": 211710, "count": 211710, "decode_str": "Way"} -{"id": 2907, "token": "ulated", "merges": "ul ated", "raw_count": 65173, "count": 211718, "decode_str": "ulated"} -{"id": 47499, "token": "':'", "merges": "': '", "raw_count": 211728, "count": 211728, "decode_str": "':'"} -{"id": 51143, "token": "\u00e5\u013b\u00a4", "merges": "\u00e5\u013b \u00a4", "raw_count": 211731, "count": 211731, "decode_str": "\u5664"} -{"id": 4379, "token": "ford", "merges": "f ord", "raw_count": 176871, "count": 211753, "decode_str": "ford"} -{"id": 26981, "token": "wei", "merges": "we i", "raw_count": 211805, "count": 211805, "decode_str": "wei"} -{"id": 7264, "token": "\u0120guarant", "merges": "\u0120gu arant", "raw_count": 5071, "count": 211806, "decode_str": " guarant"} -{"id": 5681, "token": "going", "merges": "go ing", "raw_count": 66979, "count": 211851, "decode_str": "going"} -{"id": 2442, "token": "\u0120potential", "merges": "\u0120pot ential", "raw_count": 206246, "count": 212063, "decode_str": " potential"} -{"id": 26178, "token": "lookup", "merges": "look up", "raw_count": 212117, "count": 212117, "decode_str": "lookup"} -{"id": 14081, "token": "AME", "merges": "AM E", "raw_count": 150037, "count": 212123, "decode_str": "AME"} -{"id": 24896, "token": "\u0120auth", "merges": "\u0120aut h", "raw_count": 210841, "count": 212276, "decode_str": " auth"} -{"id": 20039, "token": "esc", "merges": "es c", "raw_count": 91181, "count": 212276, "decode_str": "esc"} -{"id": 4869, "token": "\u0120maximum", "merges": "\u0120max imum", "raw_count": 212308, "count": 212308, "decode_str": " maximum"} -{"id": 29599, "token": "validation", "merges": "valid ation", "raw_count": 212309, "count": 212309, "decode_str": "validation"} -{"id": 46717, "token": "dictionary", "merges": "d ictionary", "raw_count": 212430, "count": 212430, "decode_str": "dictionary"} -{"id": 44144, "token": "jobs", "merges": "j obs", "raw_count": 212440, "count": 212440, "decode_str": "jobs"} -{"id": 54177, "token": "\u00e9\u0125\u00a2", "merges": "\u00e9\u0125 \u00a2", "raw_count": 212456, "count": 212456, "decode_str": "\u90e2"} -{"id": 2359, "token": "\u0120phot", "merges": "\u0120ph ot", "raw_count": 20293, "count": 212462, "decode_str": " phot"} -{"id": 28172, "token": "Agent", "merges": "A gent", "raw_count": 212515, "count": 212515, "decode_str": "Agent"} -{"id": 9038, "token": "icate", "merges": "ic ate", "raw_count": 167226, "count": 212568, "decode_str": "icate"} -{"id": 8169, "token": "\u0120messages", "merges": "\u0120mess ages", "raw_count": 212590, "count": 212590, "decode_str": " messages"} -{"id": 53851, "token": "\u00e8\u00b0\u0122", "merges": "\u00e8\u00b0 \u0122", "raw_count": 212609, "count": 212609, "decode_str": "\u8c00"} -{"id": 5743, "token": "\u0120activation", "merges": "\u0120activ ation", "raw_count": 212620, "count": 212620, "decode_str": " activation"} -{"id": 3673, "token": "\u0120bott", "merges": "\u0120b ott", "raw_count": 25748, "count": 212672, "decode_str": " bott"} -{"id": 14213, "token": "phase", "merges": "ph ase", "raw_count": 212719, "count": 212719, "decode_str": "phase"} -{"id": 15628, "token": "Iter", "merges": "I ter", "raw_count": 165793, "count": 212826, "decode_str": "Iter"} -{"id": 3366, "token": "\u0120Def", "merges": "\u0120D ef", "raw_count": 30862, "count": 212871, "decode_str": " Def"} -{"id": 3324, "token": "\u0120bring", "merges": "\u0120b ring", "raw_count": 168321, "count": 212881, "decode_str": " bring"} -{"id": 33321, "token": "DX", "merges": "D X", "raw_count": 212912, "count": 212912, "decode_str": "DX"} -{"id": 24475, "token": "Drop", "merges": "D rop", "raw_count": 212931, "count": 212931, "decode_str": "Drop"} -{"id": 28212, "token": "yi", "merges": "y i", "raw_count": 212970, "count": 212970, "decode_str": "yi"} -{"id": 30744, "token": "\u0120{},", "merges": "\u0120{ },", "raw_count": 213209, "count": 213209, "decode_str": " {},"} -{"id": 6390, "token": "ipped", "merges": "i pped", "raw_count": 100566, "count": 213248, "decode_str": "ipped"} -{"id": 4165, "token": "\u0120Ser", "merges": "\u0120S er", "raw_count": 17378, "count": 213304, "decode_str": " Ser"} -{"id": 17168, "token": "}:", "merges": "} :", "raw_count": 213336, "count": 213336, "decode_str": "}:"} -{"id": 13896, "token": "\u0120commands", "merges": "\u0120comm ands", "raw_count": 213387, "count": 213387, "decode_str": " commands"} -{"id": 2347, "token": "How", "merges": "H ow", "raw_count": 204145, "count": 213396, "decode_str": "How"} -{"id": 17758, "token": "028", "merges": "0 28", "raw_count": 213432, "count": 213432, "decode_str": "028"} -{"id": 47698, "token": "Joy", "merges": "J oy", "raw_count": 213495, "count": 213495, "decode_str": "Joy"} -{"id": 33833, "token": "\u0120Mock", "merges": "\u0120M ock", "raw_count": 213517, "count": 213517, "decode_str": " Mock"} -{"id": 45306, "token": "FIF", "merges": "F IF", "raw_count": 213519, "count": 213519, "decode_str": "FIF"} -{"id": 2048, "token": "\u0120expression", "merges": "\u0120exp ression", "raw_count": 213677, "count": 213677, "decode_str": " expression"} -{"id": 53064, "token": "\u00e7\u0142\u0143", "merges": "\u00e7\u0142 \u0143", "raw_count": 213809, "count": 213809, "decode_str": "\u782d"} -{"id": 17831, "token": "Media", "merges": "M edia", "raw_count": 213871, "count": 213871, "decode_str": "Media"} -{"id": 18100, "token": "QUE", "merges": "Q UE", "raw_count": 69194, "count": 213910, "decode_str": "QUE"} -{"id": 10772, "token": "Cell", "merges": "C ell", "raw_count": 213953, "count": 213953, "decode_str": "Cell"} -{"id": 3626, "token": "\u0120natural", "merges": "\u0120nat ural", "raw_count": 213992, "count": 213992, "decode_str": " natural"} -{"id": 3177, "token": "\u0120attempt", "merges": "\u0120att empt", "raw_count": 108927, "count": 214057, "decode_str": " attempt"} -{"id": 21156, "token": "SSL", "merges": "SS L", "raw_count": 214073, "count": 214073, "decode_str": "SSL"} -{"id": 12081, "token": "wall", "merges": "w all", "raw_count": 196535, "count": 214110, "decode_str": "wall"} -{"id": 4631, "token": "ais", "merges": "a is", "raw_count": 164091, "count": 214114, "decode_str": "ais"} -{"id": 3957, "token": "hest", "merges": "he st", "raw_count": 32472, "count": 214133, "decode_str": "hest"} -{"id": 18516, "token": "sb", "merges": "s b", "raw_count": 214133, "count": 214133, "decode_str": "sb"} -{"id": 4014, "token": "\u0120tele", "merges": "\u0120te le", "raw_count": 76977, "count": 214218, "decode_str": " tele"} -{"id": 2826, "token": "\u0120occur", "merges": "\u0120occ ur", "raw_count": 69189, "count": 214275, "decode_str": " occur"} -{"id": 17381, "token": "plug", "merges": "pl ug", "raw_count": 51455, "count": 214292, "decode_str": "plug"} -{"id": 8206, "token": "life", "merges": "l ife", "raw_count": 202169, "count": 214313, "decode_str": "life"} -{"id": 11396, "token": "\u0120>>", "merges": "\u0120> >", "raw_count": 214403, "count": 214403, "decode_str": " >>"} -{"id": 18318, "token": "TIME", "merges": "T IME", "raw_count": 214410, "count": 214410, "decode_str": "TIME"} -{"id": 16459, "token": "\u0120Node", "merges": "\u0120N ode", "raw_count": 214470, "count": 214470, "decode_str": " Node"} -{"id": 4667, "token": "\u0120pair", "merges": "\u0120p air", "raw_count": 191710, "count": 214534, "decode_str": " pair"} -{"id": 6902, "token": "riend", "merges": "ri end", "raw_count": 6710, "count": 214594, "decode_str": "riend"} -{"id": 18942, "token": "Green", "merges": "G reen", "raw_count": 214624, "count": 214624, "decode_str": "Green"} -{"id": 3311, "token": "\u0120estim", "merges": "\u0120est im", "raw_count": 3381, "count": 214679, "decode_str": " estim"} -{"id": 14124, "token": "unes", "merges": "un es", "raw_count": 208709, "count": 214779, "decode_str": "unes"} -{"id": 4846, "token": ")**", "merges": ") **", "raw_count": 194822, "count": 214779, "decode_str": ")**"} -{"id": 5477, "token": "ago", "merges": "ag o", "raw_count": 157431, "count": 214873, "decode_str": "ago"} -{"id": 9649, "token": "ECT", "merges": "E CT", "raw_count": 70718, "count": 214912, "decode_str": "ECT"} -{"id": 47082, "token": "970", "merges": "9 70", "raw_count": 214945, "count": 214945, "decode_str": "970"} -{"id": 35400, "token": "830", "merges": "8 30", "raw_count": 215011, "count": 215011, "decode_str": "830"} -{"id": 54524, "token": "\u00e9\u00ab\u00af", "merges": "\u00e9\u00ab \u00af", "raw_count": 215028, "count": 215028, "decode_str": "\u9aef"} -{"id": 4766, "token": "\u0120middle", "merges": "\u0120m iddle", "raw_count": 215073, "count": 215073, "decode_str": " middle"} -{"id": 4126, "token": "aign", "merges": "a ign", "raw_count": 32805, "count": 215088, "decode_str": "aign"} -{"id": 18357, "token": "unks", "merges": "un ks", "raw_count": 146622, "count": 215116, "decode_str": "unks"} -{"id": 15982, "token": "Device", "merges": "Dev ice", "raw_count": 215162, "count": 215162, "decode_str": "Device"} -{"id": 6151, "token": "rees", "merges": "re es", "raw_count": 140735, "count": 215192, "decode_str": "rees"} -{"id": 3670, "token": "\u0120immedi", "merges": "\u0120im medi", "raw_count": 1013, "count": 215207, "decode_str": " immedi"} -{"id": 27236, "token": "disk", "merges": "d isk", "raw_count": 215213, "count": 215213, "decode_str": "disk"} -{"id": 53634, "token": "\u00e8\u012c\u00be", "merges": "\u00e8\u012c \u00be", "raw_count": 215231, "count": 215231, "decode_str": "\u82be"} -{"id": 29185, "token": "449", "merges": "44 9", "raw_count": 215240, "count": 215240, "decode_str": "449"} -{"id": 4470, "token": "\u0120inn", "merges": "\u0120in n", "raw_count": 40521, "count": 215253, "decode_str": " inn"} -{"id": 6713, "token": "crete", "merges": "cre te", "raw_count": 107373, "count": 215339, "decode_str": "crete"} -{"id": 18619, "token": ")'", "merges": ") '", "raw_count": 215345, "count": 215345, "decode_str": ")'"} -{"id": 9268, "token": "\u0120east", "merges": "\u0120e ast", "raw_count": 215351, "count": 215351, "decode_str": " east"} -{"id": 9383, "token": "\u0120cov", "merges": "\u0120c ov", "raw_count": 62611, "count": 215369, "decode_str": " cov"} -{"id": 2129, "token": "\u0120week", "merges": "\u0120we ek", "raw_count": 166634, "count": 215373, "decode_str": " week"} -{"id": 6991, "token": "ceived", "merges": "ce ived", "raw_count": 17892, "count": 215413, "decode_str": "ceived"} -{"id": 21279, "token": "BG", "merges": "B G", "raw_count": 215413, "count": 215413, "decode_str": "BG"} -{"id": 3076, "token": "\u0120bad", "merges": "\u0120b ad", "raw_count": 188964, "count": 215421, "decode_str": " bad"} -{"id": 7652, "token": "\u012043", "merges": "\u01204 3", "raw_count": 215466, "count": 215466, "decode_str": " 43"} -{"id": 2986, "token": "\u0120camp", "merges": "\u0120c amp", "raw_count": 61787, "count": 215511, "decode_str": " camp"} -{"id": 32149, "token": "625", "merges": "6 25", "raw_count": 215524, "count": 215524, "decode_str": "625"} -{"id": 31035, "token": "hao", "merges": "ha o", "raw_count": 214773, "count": 215559, "decode_str": "hao"} -{"id": 30967, "token": "702", "merges": "70 2", "raw_count": 215561, "count": 215561, "decode_str": "702"} -{"id": 2733, "token": "gamma", "merges": "g amma", "raw_count": 215564, "count": 215564, "decode_str": "gamma"} -{"id": 25977, "token": "Rate", "merges": "R ate", "raw_count": 215613, "count": 215613, "decode_str": "Rate"} -{"id": 21486, "token": "\u0120fn", "merges": "\u0120f n", "raw_count": 215620, "count": 215620, "decode_str": " fn"} -{"id": 7103, "token": "\u0120evaluation", "merges": "\u0120eval uation", "raw_count": 215645, "count": 215645, "decode_str": " evaluation"} -{"id": 32499, "token": "camera", "merges": "cam era", "raw_count": 215707, "count": 215707, "decode_str": "camera"} -{"id": 2361, "token": "\u0120reported", "merges": "\u0120report ed", "raw_count": 192766, "count": 215763, "decode_str": " reported"} -{"id": 8264, "token": "\u0120fet", "merges": "\u0120f et", "raw_count": 51368, "count": 215763, "decode_str": " fet"} -{"id": 29288, "token": "806", "merges": "80 6", "raw_count": 215773, "count": 215773, "decode_str": "806"} -{"id": 17558, "token": "\u0120256", "merges": "\u012025 6", "raw_count": 215793, "count": 215793, "decode_str": " 256"} -{"id": 3267, "token": "\u0120Cont", "merges": "\u0120C ont", "raw_count": 35294, "count": 215827, "decode_str": " Cont"} -{"id": 3265, "token": "\u0120ess", "merges": "\u0120 ess", "raw_count": 9151, "count": 215828, "decode_str": " ess"} -{"id": 11707, "token": "green", "merges": "g reen", "raw_count": 215845, "count": 215845, "decode_str": "green"} -{"id": 21972, "token": "Center", "merges": "C enter", "raw_count": 215868, "count": 215868, "decode_str": "Center"} -{"id": 8571, "token": "\u0120targets", "merges": "\u0120target s", "raw_count": 215873, "count": 215873, "decode_str": " targets"} -{"id": 10690, "token": "WR", "merges": "W R", "raw_count": 184143, "count": 216075, "decode_str": "WR"} -{"id": 52866, "token": "\u00e7\u0136\u013b", "merges": "\u00e7\u0136 \u013b", "raw_count": 216159, "count": 216159, "decode_str": "\u7519"} -{"id": 52835, "token": "\u00e7\u0131\u00aa", "merges": "\u00e7\u0131 \u00aa", "raw_count": 216166, "count": 216166, "decode_str": "\u73ea"} -{"id": 4331, "token": "\u0120pen", "merges": "\u0120p en", "raw_count": 58686, "count": 216239, "decode_str": " pen"} -{"id": 9590, "token": "essions", "merges": "ess ions", "raw_count": 93025, "count": 216241, "decode_str": "essions"} -{"id": 4736, "token": "\u0120goal", "merges": "\u0120go al", "raw_count": 216291, "count": 216291, "decode_str": " goal"} -{"id": 17071, "token": "mol", "merges": "m ol", "raw_count": 216296, "count": 216296, "decode_str": "mol"} -{"id": 3444, "token": "clusion", "merges": "cl usion", "raw_count": 47990, "count": 216307, "decode_str": "clusion"} -{"id": 33060, "token": "cx", "merges": "c x", "raw_count": 216387, "count": 216387, "decode_str": "cx"} -{"id": 22421, "token": "kb", "merges": "k b", "raw_count": 216395, "count": 216395, "decode_str": "kb"} -{"id": 22351, "token": "Az", "merges": "A z", "raw_count": 70226, "count": 216457, "decode_str": "Az"} -{"id": 6791, "token": "May", "merges": "M ay", "raw_count": 203728, "count": 216559, "decode_str": "May"} -{"id": 41881, "token": "goal", "merges": "go al", "raw_count": 216600, "count": 216600, "decode_str": "goal"} -{"id": 13311, "token": "stage", "merges": "st age", "raw_count": 216641, "count": 216641, "decode_str": "stage"} -{"id": 2677, "token": "\u0120quant", "merges": "\u0120qu ant", "raw_count": 54858, "count": 216733, "decode_str": " quant"} -{"id": 3931, "token": "isms", "merges": "is ms", "raw_count": 11647, "count": 216835, "decode_str": "isms"} -{"id": 2647, "token": "\u0120matter", "merges": "\u0120mat ter", "raw_count": 216866, "count": 216866, "decode_str": " matter"} -{"id": 3504, "token": "\u00d1\u0131", "merges": "\u00d1 \u0131", "raw_count": 58437, "count": 216905, "decode_str": "\u044f"} -{"id": 14557, "token": "mus", "merges": "m us", "raw_count": 68808, "count": 216938, "decode_str": "mus"} -{"id": 1971, "token": "\u0120treatment", "merges": "\u0120treat ment", "raw_count": 216956, "count": 216956, "decode_str": " treatment"} -{"id": 9301, "token": "Next", "merges": "N ext", "raw_count": 216967, "count": 216967, "decode_str": "Next"} -{"id": 53117, "token": "\u00e7\u00a5\u0139", "merges": "\u00e7\u00a5 \u0139", "raw_count": 216985, "count": 216985, "decode_str": "\u7957"} -{"id": 26890, "token": "604", "merges": "60 4", "raw_count": 217011, "count": 217011, "decode_str": "604"} -{"id": 18027, "token": "chnology", "merges": "chn ology", "raw_count": 130776, "count": 217014, "decode_str": "chnology"} -{"id": 17118, "token": "wt", "merges": "w t", "raw_count": 217018, "count": 217018, "decode_str": "wt"} -{"id": 5487, "token": "\u0120victim", "merges": "\u0120vict im", "raw_count": 56800, "count": 217042, "decode_str": " victim"} -{"id": 7588, "token": "ami", "merges": "am i", "raw_count": 204841, "count": 217080, "decode_str": "ami"} -{"id": 21705, "token": "basic", "merges": "bas ic", "raw_count": 217119, "count": 217119, "decode_str": "basic"} -{"id": 6485, "token": "\u0120expert", "merges": "\u0120exper t", "raw_count": 140904, "count": 217130, "decode_str": " expert"} -{"id": 9165, "token": "\u0120executive", "merges": "\u0120exec utive", "raw_count": 217154, "count": 217154, "decode_str": " executive"} -{"id": 35065, "token": "previous", "merges": "pre vious", "raw_count": 217240, "count": 217240, "decode_str": "previous"} -{"id": 39780, "token": "Drive", "merges": "D rive", "raw_count": 217242, "count": 217242, "decode_str": "Drive"} -{"id": 13636, "token": "Url", "merges": "U rl", "raw_count": 217253, "count": 217253, "decode_str": "Url"} -{"id": 5216, "token": "\u0120tests", "merges": "\u0120test s", "raw_count": 217297, "count": 217297, "decode_str": " tests"} -{"id": 22158, "token": "-->", "merges": "-- >", "raw_count": 217334, "count": 217334, "decode_str": "-->"} -{"id": 22526, "token": "Gold", "merges": "G old", "raw_count": 217360, "count": 217360, "decode_str": "Gold"} -{"id": 13229, "token": "\u0120pad", "merges": "\u0120p ad", "raw_count": 217498, "count": 217498, "decode_str": " pad"} -{"id": 12084, "token": "}]", "merges": "} ]", "raw_count": 217506, "count": 217506, "decode_str": "}]"} -{"id": 12332, "token": "Application", "merges": "App lication", "raw_count": 217511, "count": 217511, "decode_str": "Application"} -{"id": 24338, "token": "KA", "merges": "K A", "raw_count": 217513, "count": 217513, "decode_str": "KA"} -{"id": 3226, "token": "\u0120girl", "merges": "\u0120g irl", "raw_count": 88982, "count": 217576, "decode_str": " girl"} -{"id": 20203, "token": "balance", "merges": "bal ance", "raw_count": 209967, "count": 217582, "decode_str": "balance"} -{"id": 16697, "token": "emb", "merges": "em b", "raw_count": 217584, "count": 217584, "decode_str": "emb"} -{"id": 17642, "token": "Real", "merges": "Re al", "raw_count": 217657, "count": 217657, "decode_str": "Real"} -{"id": 53689, "token": "\u00e8\u013b\u00ac", "merges": "\u00e8\u013b \u00ac", "raw_count": 217685, "count": 217685, "decode_str": "\u866c"} -{"id": 3635, "token": "\u0120null", "merges": "\u0120n ull", "raw_count": 216976, "count": 217695, "decode_str": " null"} -{"id": 8492, "token": "\u0120bias", "merges": "\u0120bi as", "raw_count": 217790, "count": 217790, "decode_str": " bias"} -{"id": 19095, "token": "odo", "merges": "od o", "raw_count": 217864, "count": 217864, "decode_str": "odo"} -{"id": 15662, "token": "fb", "merges": "f b", "raw_count": 218037, "count": 218037, "decode_str": "fb"} -{"id": 36386, "token": "mv", "merges": "m v", "raw_count": 218084, "count": 218084, "decode_str": "mv"} -{"id": 11300, "token": "white", "merges": "wh ite", "raw_count": 218159, "count": 218159, "decode_str": "white"} -{"id": 53961, "token": "\u00e8\u00b5\u013f", "merges": "\u00e8\u00b5 \u013f", "raw_count": 218343, "count": 218343, "decode_str": "\u8d5d"} -{"id": 54485, "token": "\u00e9\u00a6\u0139", "merges": "\u00e9\u00a6 \u0139", "raw_count": 218415, "count": 218415, "decode_str": "\u9997"} -{"id": 39328, "token": "892", "merges": "89 2", "raw_count": 218551, "count": 218551, "decode_str": "892"} -{"id": 3043, "token": "../", "merges": ".. /", "raw_count": 101916, "count": 218593, "decode_str": "../"} -{"id": 2882, "token": "\u0120consist", "merges": "\u0120cons ist", "raw_count": 22094, "count": 218617, "decode_str": " consist"} -{"id": 54507, "token": "\u00e9\u00aa\u0142", "merges": "\u00e9\u00aa \u0142", "raw_count": 218618, "count": 218618, "decode_str": "\u9aa0"} -{"id": 3779, "token": "\u0120sal", "merges": "\u0120s al", "raw_count": 81735, "count": 218698, "decode_str": " sal"} -{"id": 3971, "token": "\u0120road", "merges": "\u0120ro ad", "raw_count": 186569, "count": 218732, "decode_str": " road"} -{"id": 36554, "token": "578", "merges": "57 8", "raw_count": 218792, "count": 218792, "decode_str": "578"} -{"id": 53458, "token": "\u00e8\u0122\u00b7", "merges": "\u00e8\u0122 \u00b7", "raw_count": 218816, "count": 218816, "decode_str": "\u8037"} -{"id": 11756, "token": "Attribute", "merges": "Att ribute", "raw_count": 218847, "count": 218847, "decode_str": "Attribute"} -{"id": 5325, "token": "\u012095", "merges": "\u01209 5", "raw_count": 218938, "count": 218938, "decode_str": " 95"} -{"id": 9903, "token": "don", "merges": "d on", "raw_count": 219115, "count": 219115, "decode_str": "don"} -{"id": 11247, "token": "Case", "merges": "C ase", "raw_count": 143789, "count": 219145, "decode_str": "Case"} -{"id": 12988, "token": "ISA", "merges": "IS A", "raw_count": 218649, "count": 219180, "decode_str": "ISA"} -{"id": 12775, "token": "ETH", "merges": "ET H", "raw_count": 164646, "count": 219188, "decode_str": "ETH"} -{"id": 5347, "token": "\u0120capital", "merges": "\u0120cap ital", "raw_count": 207263, "count": 219277, "decode_str": " capital"} -{"id": 14077, "token": "turn", "merges": "t urn", "raw_count": 210869, "count": 219291, "decode_str": "turn"} -{"id": 20415, "token": "many", "merges": "m any", "raw_count": 219485, "count": 219485, "decode_str": "many"} -{"id": 53168, "token": "\u00e7\u00a8\u0136", "merges": "\u00e7\u00a8 \u0136", "raw_count": 219509, "count": 219509, "decode_str": "\u7a14"} -{"id": 12486, "token": "Long", "merges": "L ong", "raw_count": 219511, "count": 219511, "decode_str": "Long"} -{"id": 11177, "token": "ele", "merges": "e le", "raw_count": 217985, "count": 219517, "decode_str": "ele"} -{"id": 3469, "token": "\u0120depend", "merges": "\u0120dep end", "raw_count": 59038, "count": 219523, "decode_str": " depend"} -{"id": 13248, "token": "Var", "merges": "V ar", "raw_count": 217641, "count": 219608, "decode_str": "Var"} -{"id": 2065, "token": "\u0120Col", "merges": "\u0120C ol", "raw_count": 38532, "count": 219609, "decode_str": " Col"} -{"id": 32078, "token": "332", "merges": "3 32", "raw_count": 219662, "count": 219662, "decode_str": "332"} -{"id": 5104, "token": "iny", "merges": "in y", "raw_count": 137172, "count": 219693, "decode_str": "iny"} -{"id": 4264, "token": "\u0120enjoy", "merges": "\u0120en joy", "raw_count": 131334, "count": 219719, "decode_str": " enjoy"} -{"id": 29000, "token": "delay", "merges": "del ay", "raw_count": 219756, "count": 219756, "decode_str": "delay"} -{"id": 9367, "token": "aved", "merges": "av ed", "raw_count": 73763, "count": 219795, "decode_str": "aved"} -{"id": 15310, "token": "Host", "merges": "H ost", "raw_count": 219819, "count": 219819, "decode_str": "Host"} -{"id": 16822, "token": "Bank", "merges": "B ank", "raw_count": 219979, "count": 219999, "decode_str": "Bank"} -{"id": 9843, "token": "\u0120minister", "merges": "\u0120min ister", "raw_count": 220014, "count": 220014, "decode_str": " minister"} -{"id": 14694, "token": "tail", "merges": "t ail", "raw_count": 214958, "count": 220017, "decode_str": "tail"} -{"id": 4138, "token": "\u0120assert", "merges": "\u0120ass ert", "raw_count": 168192, "count": 220039, "decode_str": " assert"} -{"id": 12677, "token": "GH", "merges": "G H", "raw_count": 208901, "count": 220119, "decode_str": "GH"} -{"id": 53890, "token": "\u00e8\u00b0\u00b2", "merges": "\u00e8\u00b0 \u00b2", "raw_count": 220129, "count": 220129, "decode_str": "\u8c32"} -{"id": 14194, "token": "ASH", "merges": "AS H", "raw_count": 219809, "count": 220261, "decode_str": "ASH"} -{"id": 20482, "token": "\u0120cursor", "merges": "\u0120cur sor", "raw_count": 220265, "count": 220265, "decode_str": " cursor"} -{"id": 7219, "token": "\u0120planning", "merges": "\u0120plan ning", "raw_count": 220275, "count": 220275, "decode_str": " planning"} -{"id": 11156, "token": "ORE", "merges": "OR E", "raw_count": 159342, "count": 220288, "decode_str": "ORE"} -{"id": 51377, "token": "\u00e5\u0143\u0133", "merges": "\u00e5\u0143 \u0133", "raw_count": 220310, "count": 220310, "decode_str": "\u5b51"} -{"id": 51132, "token": "\u00e5\u0138\u00b9", "merges": "\u00e5\u0138 \u00b9", "raw_count": 220316, "count": 220316, "decode_str": "\u55b9"} -{"id": 23272, "token": "WL", "merges": "W L", "raw_count": 220347, "count": 220347, "decode_str": "WL"} -{"id": 30550, "token": "fh", "merges": "f h", "raw_count": 220455, "count": 220455, "decode_str": "fh"} -{"id": 53888, "token": "\u00e8\u00b0\u00af", "merges": "\u00e8\u00b0 \u00af", "raw_count": 220579, "count": 220579, "decode_str": "\u8c2f"} -{"id": 18142, "token": "Aud", "merges": "A ud", "raw_count": 132768, "count": 220594, "decode_str": "Aud"} -{"id": 1999, "token": "etic", "merges": "et ic", "raw_count": 68663, "count": 220636, "decode_str": "etic"} -{"id": 9705, "token": "bul", "merges": "b ul", "raw_count": 155363, "count": 220690, "decode_str": "bul"} -{"id": 3045, "token": "\u0120performance", "merges": "\u0120perform ance", "raw_count": 220693, "count": 220693, "decode_str": " performance"} -{"id": 5499, "token": "\u0120mill", "merges": "\u0120m ill", "raw_count": 37680, "count": 220727, "decode_str": " mill"} -{"id": 1784, "token": "\u0120der", "merges": "\u0120d er", "raw_count": 53992, "count": 220742, "decode_str": " der"} -{"id": 9241, "token": "\u0120principles", "merges": "\u0120princ iples", "raw_count": 220802, "count": 220802, "decode_str": " principles"} -{"id": 5965, "token": "\u0120hol", "merges": "\u0120h ol", "raw_count": 67578, "count": 220802, "decode_str": " hol"} -{"id": 19090, "token": "EQ", "merges": "E Q", "raw_count": 220867, "count": 220867, "decode_str": "EQ"} -{"id": 9610, "token": "\u0120reporting", "merges": "\u0120report ing", "raw_count": 220868, "count": 220868, "decode_str": " reporting"} -{"id": 5033, "token": "icit", "merges": "ic it", "raw_count": 20218, "count": 220885, "decode_str": "icit"} -{"id": 4417, "token": "\u0120cook", "merges": "\u0120c ook", "raw_count": 29118, "count": 220943, "decode_str": " cook"} -{"id": 3811, "token": "\u0120living", "merges": "\u0120l iving", "raw_count": 220998, "count": 220998, "decode_str": " living"} -{"id": 10991, "token": "inition", "merges": "in ition", "raw_count": 2901, "count": 221019, "decode_str": "inition"} -{"id": 3215, "token": "\u0120pret", "merges": "\u0120pre t", "raw_count": 86298, "count": 221032, "decode_str": " pret"} -{"id": 8617, "token": "ictor", "merges": "ict or", "raw_count": 120521, "count": 221043, "decode_str": "ictor"} -{"id": 6992, "token": "rid", "merges": "r id", "raw_count": 174098, "count": 221043, "decode_str": "rid"} -{"id": 19217, "token": "Engine", "merges": "Eng ine", "raw_count": 221280, "count": 221280, "decode_str": "Engine"} -{"id": 3901, "token": "inated", "merges": "in ated", "raw_count": 61040, "count": 221305, "decode_str": "inated"} -{"id": 3640, "token": "\u0120knowledge", "merges": "\u0120know ledge", "raw_count": 218038, "count": 221361, "decode_str": " knowledge"} -{"id": 49800, "token": "688", "merges": "6 88", "raw_count": 221376, "count": 221376, "decode_str": "688"} -{"id": 25588, "token": "UA", "merges": "U A", "raw_count": 221383, "count": 221383, "decode_str": "UA"} -{"id": 20963, "token": "exe", "merges": "ex e", "raw_count": 221387, "count": 221387, "decode_str": "exe"} -{"id": 10719, "token": "acts", "merges": "act s", "raw_count": 103493, "count": 221388, "decode_str": "acts"} -{"id": 13701, "token": "\u0120establishment", "merges": "\u0120establish ment", "raw_count": 221434, "count": 221434, "decode_str": " establishment"} -{"id": 5841, "token": "\u0120calls", "merges": "\u0120call s", "raw_count": 221484, "count": 221484, "decode_str": " calls"} -{"id": 3037, "token": "\u0120learn", "merges": "\u0120le arn", "raw_count": 128477, "count": 221638, "decode_str": " learn"} -{"id": 8425, "token": "scrib", "merges": "sc rib", "raw_count": 31625, "count": 221666, "decode_str": "scrib"} -{"id": 7253, "token": "\u0120seconds", "merges": "\u0120second s", "raw_count": 221806, "count": 221806, "decode_str": " seconds"} -{"id": 10004, "token": "Select", "merges": "Se lect", "raw_count": 177843, "count": 221811, "decode_str": "Select"} -{"id": 9262, "token": "\u0120submitted", "merges": "\u0120sub mitted", "raw_count": 221865, "count": 221865, "decode_str": " submitted"} -{"id": 8089, "token": "fold", "merges": "f old", "raw_count": 221915, "count": 221915, "decode_str": "fold"} -{"id": 16703, "token": "\u012004", "merges": "\u01200 4", "raw_count": 221966, "count": 221966, "decode_str": " 04"} -{"id": 41317, "token": "qs", "merges": "q s", "raw_count": 221995, "count": 221995, "decode_str": "qs"} -{"id": 4391, "token": "\u0120changed", "merges": "\u0120chang ed", "raw_count": 222014, "count": 222014, "decode_str": " changed"} -{"id": 45089, "token": "Gui", "merges": "G ui", "raw_count": 222045, "count": 222045, "decode_str": "Gui"} -{"id": 20671, "token": "Flow", "merges": "F low", "raw_count": 222069, "count": 222069, "decode_str": "Flow"} -{"id": 44054, "token": "unicode", "merges": "un icode", "raw_count": 222087, "count": 222087, "decode_str": "unicode"} -{"id": 26935, "token": "dings", "merges": "d ings", "raw_count": 173507, "count": 222134, "decode_str": "dings"} -{"id": 12857, "token": "Sche", "merges": "S che", "raw_count": 31334, "count": 222144, "decode_str": "Sche"} -{"id": 2074, "token": "\u0120similar", "merges": "\u0120sim ilar", "raw_count": 174314, "count": 222186, "decode_str": " similar"} -{"id": 36531, "token": "matches", "merges": "mat ches", "raw_count": 222206, "count": 222206, "decode_str": "matches"} -{"id": 5735, "token": "idel", "merges": "id el", "raw_count": 30939, "count": 222224, "decode_str": "idel"} -{"id": 31668, "token": "identifier", "merges": "ident ifier", "raw_count": 222267, "count": 222267, "decode_str": "identifier"} -{"id": 31117, "token": "858", "merges": "85 8", "raw_count": 222332, "count": 222332, "decode_str": "858"} -{"id": 15237, "token": "\u0120advis", "merges": "\u0120adv is", "raw_count": 8152, "count": 222368, "decode_str": " advis"} -{"id": 16164, "token": "\u0120login", "merges": "\u0120log in", "raw_count": 222380, "count": 222380, "decode_str": " login"} -{"id": 27307, "token": "_)", "merges": "_ )", "raw_count": 222528, "count": 222528, "decode_str": "_)"} -{"id": 2803, "token": "\u0120factor", "merges": "\u0120fact or", "raw_count": 218832, "count": 222548, "decode_str": " factor"} -{"id": 51086, "token": "\u00e5\u0137\u0137", "merges": "\u00e5\u0137 \u0137", "raw_count": 222603, "count": 222603, "decode_str": "\u5555"} -{"id": 53870, "token": "\u00e8\u00b0\u0139", "merges": "\u00e8\u00b0 \u0139", "raw_count": 222646, "count": 222646, "decode_str": "\u8c17"} -{"id": 13220, "token": "DO", "merges": "D O", "raw_count": 213346, "count": 222767, "decode_str": "DO"} -{"id": 8905, "token": "\u0120remote", "merges": "\u0120rem ote", "raw_count": 222842, "count": 222842, "decode_str": " remote"} -{"id": 11159, "token": "may", "merges": "m ay", "raw_count": 136902, "count": 222896, "decode_str": "may"} -{"id": 3809, "token": "\u0120fast", "merges": "\u0120f ast", "raw_count": 206059, "count": 222903, "decode_str": " fast"} -{"id": 5532, "token": "\u0120click", "merges": "\u0120cl ick", "raw_count": 178886, "count": 222910, "decode_str": " click"} -{"id": 23824, "token": "expect", "merges": "ex pect", "raw_count": 223007, "count": 223007, "decode_str": "expect"} -{"id": 48656, "token": "\u0120verbose", "merges": "\u0120verb ose", "raw_count": 223024, "count": 223024, "decode_str": " verbose"} -{"id": 42565, "token": "jt", "merges": "j t", "raw_count": 223064, "count": 223064, "decode_str": "jt"} -{"id": 53586, "token": "\u00e8\u012a\u00ab", "merges": "\u00e8\u012a \u00ab", "raw_count": 223074, "count": 223074, "decode_str": "\u822b"} -{"id": 37123, "token": "sock", "merges": "s ock", "raw_count": 223099, "count": 223099, "decode_str": "sock"} -{"id": 6407, "token": "First", "merges": "F irst", "raw_count": 223181, "count": 223181, "decode_str": "First"} -{"id": 31823, "token": "XL", "merges": "X L", "raw_count": 223195, "count": 223195, "decode_str": "XL"} -{"id": 30146, "token": "publ", "merges": "p ubl", "raw_count": 74249, "count": 223242, "decode_str": "publ"} -{"id": 13363, "token": "WA", "merges": "W A", "raw_count": 180387, "count": 223256, "decode_str": "WA"} -{"id": 2956, "token": "\u0120Par", "merges": "\u0120P ar", "raw_count": 66209, "count": 223293, "decode_str": " Par"} -{"id": 24564, "token": "AW", "merges": "A W", "raw_count": 223303, "count": 223303, "decode_str": "AW"} -{"id": 20409, "token": "sha", "merges": "sh a", "raw_count": 223330, "count": 223330, "decode_str": "sha"} -{"id": 29435, "token": "458", "merges": "45 8", "raw_count": 223334, "count": 223334, "decode_str": "458"} -{"id": 15669, "token": "ailure", "merges": "ail ure", "raw_count": 1386, "count": 223380, "decode_str": "ailure"} -{"id": 21309, "token": "Robert", "merges": "Rober t", "raw_count": 223492, "count": 223492, "decode_str": "Robert"} -{"id": 5058, "token": "\u0120zero", "merges": "\u0120z ero", "raw_count": 223522, "count": 223522, "decode_str": " zero"} -{"id": 54083, "token": "\u00e8\u00bf\u00a4", "merges": "\u00e8\u00bf \u00a4", "raw_count": 223573, "count": 223573, "decode_str": "\u8fe4"} -{"id": 5161, "token": "\u0120core", "merges": "\u0120c ore", "raw_count": 223600, "count": 223600, "decode_str": " core"} -{"id": 11674, "token": "\u0120priority", "merges": "\u0120prior ity", "raw_count": 223625, "count": 223625, "decode_str": " priority"} -{"id": 5315, "token": "\u0120mac", "merges": "\u0120m ac", "raw_count": 159976, "count": 223631, "decode_str": " mac"} -{"id": 1800, "token": "\u0120describ", "merges": "\u0120desc rib", "raw_count": 331, "count": 223663, "decode_str": " describ"} -{"id": 10492, "token": "bottom", "merges": "b ottom", "raw_count": 223692, "count": 223692, "decode_str": "bottom"} -{"id": 3629, "token": "\u0120increasing", "merges": "\u0120incre asing", "raw_count": 151687, "count": 223809, "decode_str": " increasing"} -{"id": 6938, "token": "\u0120environmental", "merges": "\u0120environment al", "raw_count": 223817, "count": 223817, "decode_str": " environmental"} -{"id": 21466, "token": "UX", "merges": "U X", "raw_count": 223857, "count": 223857, "decode_str": "UX"} -{"id": 22653, "token": "Lu", "merges": "L u", "raw_count": 223878, "count": 223878, "decode_str": "Lu"} -{"id": 8517, "token": "prote", "merges": "pro te", "raw_count": 19213, "count": 223905, "decode_str": "prote"} -{"id": 5656, "token": "ANT", "merges": "AN T", "raw_count": 218498, "count": 224104, "decode_str": "ANT"} -{"id": 52449, "token": "\u00e6\u00b0\u013b", "merges": "\u00e6\u00b0 \u013b", "raw_count": 224130, "count": 224130, "decode_str": "\u6c19"} -{"id": 53305, "token": "\u00e7\u00b6\u00a6", "merges": "\u00e7\u00b6 \u00a6", "raw_count": 224215, "count": 224215, "decode_str": "\u7da6"} -{"id": 14344, "token": "Free", "merges": "F ree", "raw_count": 224216, "count": 224216, "decode_str": "Free"} -{"id": 14507, "token": "\u00e2\u0124\u00ac", "merges": "\u00e2 \u0124\u00ac", "raw_count": 224123, "count": 224216, "decode_str": "\u20ac"} -{"id": 6146, "token": "\u0120north", "merges": "\u0120n orth", "raw_count": 215935, "count": 224246, "decode_str": " north"} -{"id": 1646, "token": "\u0120seem", "merges": "\u0120se em", "raw_count": 67437, "count": 224248, "decode_str": " seem"} -{"id": 30176, "token": "475", "merges": "4 75", "raw_count": 224291, "count": 224291, "decode_str": "475"} -{"id": 1912, "token": "\u0120won", "merges": "\u0120w on", "raw_count": 147179, "count": 224315, "decode_str": " won"} -{"id": 1219, "token": "\u0120Al", "merges": "\u0120A l", "raw_count": 70582, "count": 224416, "decode_str": " Al"} -{"id": 4198, "token": "\u0120prop", "merges": "\u0120pro p", "raw_count": 136999, "count": 224502, "decode_str": " prop"} -{"id": 18914, "token": "_-", "merges": "_ -", "raw_count": 224544, "count": 224544, "decode_str": "_-"} -{"id": 18640, "token": "lon", "merges": "l on", "raw_count": 224588, "count": 224588, "decode_str": "lon"} -{"id": 24698, "token": "396", "merges": "39 6", "raw_count": 224602, "count": 224602, "decode_str": "396"} -{"id": 2965, "token": "\u0120fall", "merges": "\u0120f all", "raw_count": 138538, "count": 224606, "decode_str": " fall"} -{"id": 3256, "token": "aled", "merges": "al ed", "raw_count": 124232, "count": 224632, "decode_str": "aled"} -{"id": 14519, "token": "OME", "merges": "OM E", "raw_count": 103545, "count": 224701, "decode_str": "OME"} -{"id": 19921, "token": "RC", "merges": "R C", "raw_count": 224742, "count": 224742, "decode_str": "RC"} -{"id": 19630, "token": "293", "merges": "29 3", "raw_count": 224826, "count": 224826, "decode_str": "293"} -{"id": 15400, "token": "IDE", "merges": "ID E", "raw_count": 197054, "count": 224890, "decode_str": "IDE"} -{"id": 10851, "token": "Dep", "merges": "D ep", "raw_count": 109551, "count": 224918, "decode_str": "Dep"} -{"id": 50451, "token": "\u00e4\u00b9\u013e", "merges": "\u00e4\u00b9 \u013e", "raw_count": 224935, "count": 224935, "decode_str": "\u4e5c"} -{"id": 3521, "token": "\u0120stri", "merges": "\u0120st ri", "raw_count": 10454, "count": 224952, "decode_str": " stri"} -{"id": 6228, "token": "inder", "merges": "in der", "raw_count": 123920, "count": 225005, "decode_str": "inder"} -{"id": 31028, "token": "\u0120\"+", "merges": "\u0120\" +", "raw_count": 225103, "count": 225103, "decode_str": " \"+"} -{"id": 12560, "token": "Exec", "merges": "Ex ec", "raw_count": 81744, "count": 225183, "decode_str": "Exec"} -{"id": 16885, "token": "tools", "merges": "to ols", "raw_count": 225206, "count": 225206, "decode_str": "tools"} -{"id": 10344, "token": "prise", "merges": "pr ise", "raw_count": 100903, "count": 225219, "decode_str": "prise"} -{"id": 5987, "token": "\u0120https", "merges": "\u0120htt ps", "raw_count": 225236, "count": 225236, "decode_str": " https"} -{"id": 11088, "token": "\u0120comprehensive", "merges": "\u0120comprehens ive", "raw_count": 225238, "count": 225238, "decode_str": " comprehensive"} -{"id": 12168, "token": "Target", "merges": "T arget", "raw_count": 225262, "count": 225262, "decode_str": "Target"} -{"id": 3587, "token": "\u0120directly", "merges": "\u0120direct ly", "raw_count": 225302, "count": 225302, "decode_str": " directly"} -{"id": 10757, "token": "acity", "merges": "ac ity", "raw_count": 35775, "count": 225317, "decode_str": "acity"} -{"id": 10830, "token": "Length", "merges": "L ength", "raw_count": 225376, "count": 225376, "decode_str": "Length"} -{"id": 18036, "token": "OFF", "merges": "O FF", "raw_count": 201338, "count": 225670, "decode_str": "OFF"} -{"id": 38860, "token": "MIT", "merges": "M IT", "raw_count": 225679, "count": 225679, "decode_str": "MIT"} -{"id": 6431, "token": "\u0120exchange", "merges": "\u0120ex change", "raw_count": 225810, "count": 225810, "decode_str": " exchange"} -{"id": 26324, "token": "protocol", "merges": "prot ocol", "raw_count": 225830, "count": 225830, "decode_str": "protocol"} -{"id": 3422, "token": "olic", "merges": "ol ic", "raw_count": 184867, "count": 225973, "decode_str": "olic"} -{"id": 38348, "token": "ADC", "merges": "AD C", "raw_count": 225973, "count": 225973, "decode_str": "ADC"} -{"id": 18012, "token": "\u0120outputs", "merges": "\u0120output s", "raw_count": 225975, "count": 225975, "decode_str": " outputs"} -{"id": 10189, "token": "NR", "merges": "N R", "raw_count": 223648, "count": 226019, "decode_str": "NR"} -{"id": 14968, "token": "Template", "merges": "Tem plate", "raw_count": 226096, "count": 226096, "decode_str": "Template"} -{"id": 14178, "token": "Dist", "merges": "D ist", "raw_count": 161326, "count": 226119, "decode_str": "Dist"} -{"id": 9836, "token": "\u0120domestic", "merges": "\u0120dom estic", "raw_count": 226209, "count": 226209, "decode_str": " domestic"} -{"id": 28269, "token": "learning", "merges": "le arning", "raw_count": 226286, "count": 226286, "decode_str": "learning"} -{"id": 1572, "token": ")\\", "merges": ") \\", "raw_count": 193751, "count": 226289, "decode_str": ")\\"} -{"id": 51625, "token": "\u00e5\u00bd\u00a7", "merges": "\u00e5\u00bd \u00a7", "raw_count": 226467, "count": 226467, "decode_str": "\u5f67"} -{"id": 15219, "token": "Vector", "merges": "V ector", "raw_count": 226497, "count": 226497, "decode_str": "Vector"} -{"id": 2625, "token": "\u0120signal", "merges": "\u0120sign al", "raw_count": 221385, "count": 226543, "decode_str": " signal"} -{"id": 16454, "token": "\u0120handler", "merges": "\u0120hand ler", "raw_count": 226551, "count": 226551, "decode_str": " handler"} -{"id": 4655, "token": "lick", "merges": "lic k", "raw_count": 27458, "count": 226570, "decode_str": "lick"} -{"id": 54179, "token": "\u00e9\u0125\u00a6", "merges": "\u00e9\u0125 \u00a6", "raw_count": 226570, "count": 226570, "decode_str": "\u90e6"} -{"id": 13830, "token": "\u0120_,", "merges": "\u0120_ ,", "raw_count": 226665, "count": 226665, "decode_str": " _,"} -{"id": 13844, "token": "\u0120debug", "merges": "\u0120deb ug", "raw_count": 196891, "count": 226726, "decode_str": " debug"} -{"id": 5179, "token": "arter", "merges": "ar ter", "raw_count": 68138, "count": 226766, "decode_str": "arter"} -{"id": 12018, "token": "Ev", "merges": "E v", "raw_count": 138751, "count": 226783, "decode_str": "Ev"} -{"id": 18362, "token": "country", "merges": "count ry", "raw_count": 226826, "count": 226826, "decode_str": "country"} -{"id": 13152, "token": "BV", "merges": "B V", "raw_count": 225969, "count": 226828, "decode_str": "BV"} -{"id": 49087, "token": "870", "merges": "8 70", "raw_count": 226855, "count": 226855, "decode_str": "870"} -{"id": 2873, "token": "\u0120mut", "merges": "\u0120m ut", "raw_count": 74772, "count": 226869, "decode_str": " mut"} -{"id": 26385, "token": "Ta", "merges": "T a", "raw_count": 226888, "count": 226888, "decode_str": "Ta"} -{"id": 27571, "token": "281", "merges": "28 1", "raw_count": 226920, "count": 226920, "decode_str": "281"} -{"id": 4523, "token": "ULL", "merges": "U LL", "raw_count": 30154, "count": 226954, "decode_str": "ULL"} -{"id": 9869, "token": "las", "merges": "l as", "raw_count": 225677, "count": 226975, "decode_str": "las"} -{"id": 8093, "token": "Stream", "merges": "St ream", "raw_count": 220363, "count": 227034, "decode_str": "Stream"} -{"id": 13449, "token": "boot", "merges": "b oot", "raw_count": 175270, "count": 227052, "decode_str": "boot"} -{"id": 51848, "token": "\u00e6\u012b\u00aa", "merges": "\u00e6\u012b \u00aa", "raw_count": 227057, "count": 227057, "decode_str": "\u626a"} -{"id": 3192, "token": "\u0120taking", "merges": "\u0120t aking", "raw_count": 227211, "count": 227211, "decode_str": " taking"} -{"id": 11133, "token": "Resource", "merges": "Res ource", "raw_count": 227273, "count": 227273, "decode_str": "Resource"} -{"id": 13285, "token": "Tool", "merges": "T ool", "raw_count": 164323, "count": 227319, "decode_str": "Tool"} -{"id": 28575, "token": "packet", "merges": "pack et", "raw_count": 227333, "count": 227333, "decode_str": "packet"} -{"id": 2929, "token": "\u0120paper", "merges": "\u0120pa per", "raw_count": 225096, "count": 227357, "decode_str": " paper"} -{"id": 8294, "token": "\u0120responsibility", "merges": "\u0120respons ibility", "raw_count": 227366, "count": 227366, "decode_str": " responsibility"} -{"id": 4914, "token": "asis", "merges": "as is", "raw_count": 69120, "count": 227400, "decode_str": "asis"} -{"id": 4968, "token": "\u0120tool", "merges": "\u0120to ol", "raw_count": 212373, "count": 227406, "decode_str": " tool"} -{"id": 26140, "token": "346", "merges": "34 6", "raw_count": 227412, "count": 227412, "decode_str": "346"} -{"id": 9155, "token": "ipt", "merges": "i pt", "raw_count": 115807, "count": 227476, "decode_str": "ipt"} -{"id": 4575, "token": "\u0120adjust", "merges": "\u0120adj ust", "raw_count": 102427, "count": 227499, "decode_str": " adjust"} -{"id": 37231, "token": "RAM", "merges": "R AM", "raw_count": 227507, "count": 227507, "decode_str": "RAM"} -{"id": 7896, "token": "ela", "merges": "el a", "raw_count": 213085, "count": 227509, "decode_str": "ela"} -{"id": 5816, "token": "\u0120missing", "merges": "\u0120miss ing", "raw_count": 227532, "count": 227532, "decode_str": " missing"} -{"id": 1621, "token": "\u0120No", "merges": "\u0120N o", "raw_count": 225747, "count": 227588, "decode_str": " No"} -{"id": 22127, "token": "components", "merges": "comp onents", "raw_count": 227737, "count": 227737, "decode_str": "components"} -{"id": 3792, "token": "lege", "merges": "le ge", "raw_count": 27496, "count": 227738, "decode_str": "lege"} -{"id": 13502, "token": "Enc", "merges": "En c", "raw_count": 81387, "count": 227775, "decode_str": "Enc"} -{"id": 52279, "token": "\u00e6\u0142\u012b", "merges": "\u00e6\u0142 \u012b", "raw_count": 227785, "count": 227785, "decode_str": "\u6809"} -{"id": 28899, "token": "282", "merges": "28 2", "raw_count": 227795, "count": 227795, "decode_str": "282"} -{"id": 18316, "token": "share", "merges": "sh are", "raw_count": 227809, "count": 227809, "decode_str": "share"} -{"id": 22817, "token": "International", "merges": "Intern ational", "raw_count": 227844, "count": 227844, "decode_str": "International"} -{"id": 8046, "token": "\u0120enable", "merges": "\u0120en able", "raw_count": 227849, "count": 227849, "decode_str": " enable"} -{"id": 25739, "token": "follow", "merges": "f ollow", "raw_count": 227883, "count": 227883, "decode_str": "follow"} -{"id": 1198, "token": "\u0120For", "merges": "\u0120F or", "raw_count": 181259, "count": 227890, "decode_str": " For"} -{"id": 26889, "token": "RM", "merges": "R M", "raw_count": 228008, "count": 228008, "decode_str": "RM"} -{"id": 14056, "token": "quer", "merges": "qu er", "raw_count": 222767, "count": 228100, "decode_str": "quer"} -{"id": 11501, "token": "Access", "merges": "A ccess", "raw_count": 219578, "count": 228108, "decode_str": "Access"} -{"id": 14090, "token": "Names", "merges": "N ames", "raw_count": 174889, "count": 228189, "decode_str": "Names"} -{"id": 52958, "token": "\u00e7\u013b\u0140", "merges": "\u00e7\u013b \u0140", "raw_count": 228202, "count": 228202, "decode_str": "\u765e"} -{"id": 4940, "token": "inger", "merges": "ing er", "raw_count": 108197, "count": 228258, "decode_str": "inger"} -{"id": 33412, "token": "Surface", "merges": "Sur face", "raw_count": 228264, "count": 228264, "decode_str": "Surface"} -{"id": 18921, "token": "accur", "merges": "ac cur", "raw_count": 202167, "count": 228330, "decode_str": "accur"} -{"id": 5342, "token": "jection", "merges": "j ection", "raw_count": 125586, "count": 228347, "decode_str": "jection"} -{"id": 4747, "token": "\u0120challeng", "merges": "\u0120chall eng", "raw_count": 548, "count": 228413, "decode_str": " challeng"} -{"id": 54190, "token": "\u00e9\u0127\u0132", "merges": "\u00e9\u0127 \u0132", "raw_count": 228465, "count": 228465, "decode_str": "\u9150"} -{"id": 2583, "token": "\u0120money", "merges": "\u0120m oney", "raw_count": 228473, "count": 228473, "decode_str": " money"} -{"id": 31819, "token": "478", "merges": "47 8", "raw_count": 228479, "count": 228479, "decode_str": "478"} -{"id": 4419, "token": "\u0120requires", "merges": "\u0120requ ires", "raw_count": 228534, "count": 228534, "decode_str": " requires"} -{"id": 5821, "token": "\u0120agreed", "merges": "\u0120agre ed", "raw_count": 228538, "count": 228538, "decode_str": " agreed"} -{"id": 53763, "token": "\u00e8\u00a7\u0132", "merges": "\u00e8\u00a7 \u0132", "raw_count": 228559, "count": 228559, "decode_str": "\u89d0"} -{"id": 2736, "token": "\u0120detect", "merges": "\u0120det ect", "raw_count": 89561, "count": 228578, "decode_str": " detect"} -{"id": 1446, "token": "meric", "merges": "mer ic", "raw_count": 4052, "count": 228706, "decode_str": "meric"} -{"id": 2046, "token": "\u0120ey", "merges": "\u0120e y", "raw_count": 15815, "count": 228764, "decode_str": " ey"} -{"id": 22543, "token": "344", "merges": "34 4", "raw_count": 228772, "count": 228772, "decode_str": "344"} -{"id": 2559, "token": "\u0120increased", "merges": "\u0120incre ased", "raw_count": 228833, "count": 228833, "decode_str": " increased"} -{"id": 54013, "token": "\u00e8\u00ba\u0131", "merges": "\u00e8\u00ba \u0131", "raw_count": 228851, "count": 228851, "decode_str": "\u8e8f"} -{"id": 138, "token": "\u00ce", "merges": "NULL", "raw_count": 40286, "count": 228929, "decode_str": "\ufffd"} -{"id": 3709, "token": "include", "merges": "in clude", "raw_count": 229043, "count": 229043, "decode_str": "include"} -{"id": 19292, "token": "\u0120\"_", "merges": "\u0120\" _", "raw_count": 229047, "count": 229047, "decode_str": " \"_"} -{"id": 41211, "token": "575", "merges": "5 75", "raw_count": 229147, "count": 229147, "decode_str": "575"} -{"id": 14452, "token": "\u0120indices", "merges": "\u0120ind ices", "raw_count": 229186, "count": 229186, "decode_str": " indices"} -{"id": 20062, "token": "Hub", "merges": "H ub", "raw_count": 215731, "count": 229219, "decode_str": "Hub"} -{"id": 53172, "token": "\u00e7\u00a8\u0140", "merges": "\u00e7\u00a8 \u0140", "raw_count": 229289, "count": 229289, "decode_str": "\u7a1e"} -{"id": 8498, "token": "vin", "merges": "v in", "raw_count": 223560, "count": 229457, "decode_str": "vin"} -{"id": 54163, "token": "\u00e9\u0124\u00b3", "merges": "\u00e9\u0124 \u00b3", "raw_count": 229575, "count": 229575, "decode_str": "\u90b3"} -{"id": 8408, "token": "\u0120negot", "merges": "\u0120neg ot", "raw_count": 10163, "count": 229625, "decode_str": " negot"} -{"id": 31110, "token": "382", "merges": "38 2", "raw_count": 229738, "count": 229738, "decode_str": "382"} -{"id": 5621, "token": "\u0120forces", "merges": "\u0120for ces", "raw_count": 229791, "count": 229791, "decode_str": " forces"} -{"id": 13206, "token": "figure", "merges": "fig ure", "raw_count": 229795, "count": 229795, "decode_str": "figure"} -{"id": 3111, "token": "overed", "merges": "ove red", "raw_count": 46248, "count": 229810, "decode_str": "overed"} -{"id": 6372, "token": "ptions", "merges": "pt ions", "raw_count": 14884, "count": 229893, "decode_str": "ptions"} -{"id": 3403, "token": "\u0120capt", "merges": "\u0120c apt", "raw_count": 37024, "count": 229914, "decode_str": " capt"} -{"id": 52892, "token": "\u00e7\u0137\u00a6", "merges": "\u00e7\u0137 \u00a6", "raw_count": 229939, "count": 229939, "decode_str": "\u7566"} -{"id": 10990, "token": "Row", "merges": "R ow", "raw_count": 229995, "count": 229995, "decode_str": "Row"} -{"id": 8202, "token": "yan", "merges": "y an", "raw_count": 134432, "count": 230046, "decode_str": "yan"} -{"id": 3922, "token": "urg", "merges": "ur g", "raw_count": 81340, "count": 230055, "decode_str": "urg"} -{"id": 7971, "token": "\u0120facilit", "merges": "\u0120fac ilit", "raw_count": 13168, "count": 230078, "decode_str": " facilit"} -{"id": 3153, "token": "\u0120live", "merges": "\u0120l ive", "raw_count": 230079, "count": 230079, "decode_str": " live"} -{"id": 26371, "token": "709", "merges": "70 9", "raw_count": 230311, "count": 230311, "decode_str": "709"} -{"id": 18687, "token": "\u0120delta", "merges": "\u0120del ta", "raw_count": 230361, "count": 230361, "decode_str": " delta"} -{"id": 3977, "token": "\u0120led", "merges": "\u0120l ed", "raw_count": 230376, "count": 230376, "decode_str": " led"} -{"id": 51545, "token": "\u00e5\u00b9\u0126", "merges": "\u00e5\u00b9 \u0126", "raw_count": 230396, "count": 230396, "decode_str": "\u5e44"} -{"id": 19910, "token": "pkg", "merges": "p kg", "raw_count": 230409, "count": 230409, "decode_str": "pkg"} -{"id": 2112, "token": "\u0120along", "merges": "\u0120al ong", "raw_count": 214976, "count": 230449, "decode_str": " along"} -{"id": 4938, "token": "asp", "merges": "as p", "raw_count": 186500, "count": 230521, "decode_str": "asp"} -{"id": 2549, "token": "\u0120frequ", "merges": "\u0120f requ", "raw_count": 4014, "count": 230547, "decode_str": " frequ"} -{"id": 26652, "token": "mx", "merges": "m x", "raw_count": 230572, "count": 230572, "decode_str": "mx"} -{"id": 46622, "token": "records", "merges": "rec ords", "raw_count": 230581, "count": 230581, "decode_str": "records"} -{"id": 27059, "token": "609", "merges": "60 9", "raw_count": 230743, "count": 230743, "decode_str": "609"} -{"id": 27573, "token": "Van", "merges": "V an", "raw_count": 230810, "count": 230810, "decode_str": "Van"} -{"id": 5468, "token": "acters", "merges": "act ers", "raw_count": 71391, "count": 230828, "decode_str": "acters"} -{"id": 24774, "token": "Bal", "merges": "B al", "raw_count": 230834, "count": 230834, "decode_str": "Bal"} -{"id": 7513, "token": "lik", "merges": "li k", "raw_count": 161244, "count": 230840, "decode_str": "lik"} -{"id": 26320, "token": "timer", "merges": "t imer", "raw_count": 230860, "count": 230860, "decode_str": "timer"} -{"id": 5945, "token": "ander", "merges": "and er", "raw_count": 138432, "count": 230893, "decode_str": "ander"} -{"id": 22768, "token": "safe", "merges": "sa fe", "raw_count": 230949, "count": 230949, "decode_str": "safe"} -{"id": 19384, "token": "irs", "merges": "ir s", "raw_count": 228693, "count": 230955, "decode_str": "irs"} -{"id": 10449, "token": "ARD", "merges": "AR D", "raw_count": 199771, "count": 230999, "decode_str": "ARD"} -{"id": 26383, "token": "Failed", "merges": "F ailed", "raw_count": 231098, "count": 231098, "decode_str": "Failed"} -{"id": 3896, "token": "\u0120squ", "merges": "\u0120s qu", "raw_count": 17716, "count": 231133, "decode_str": " squ"} -{"id": 21831, "token": "Disc", "merges": "D isc", "raw_count": 231158, "count": 231158, "decode_str": "Disc"} -{"id": 54514, "token": "\u00e9\u00aa\u00b6", "merges": "\u00e9\u00aa \u00b6", "raw_count": 231209, "count": 231209, "decode_str": "\u9ab6"} -{"id": 44670, "token": "/'", "merges": "/ '", "raw_count": 231219, "count": 231219, "decode_str": "/'"} -{"id": 17009, "token": "olutions", "merges": "ol utions", "raw_count": 91991, "count": 231239, "decode_str": "olutions"} -{"id": 13257, "token": "TX", "merges": "T X", "raw_count": 231245, "count": 231245, "decode_str": "TX"} -{"id": 31941, "token": "uffix", "merges": "uff ix", "raw_count": 26840, "count": 231287, "decode_str": "uffix"} -{"id": 3710, "token": "\u0120limited", "merges": "\u0120lim ited", "raw_count": 231313, "count": 231313, "decode_str": " limited"} -{"id": 13678, "token": "walk", "merges": "w alk", "raw_count": 199540, "count": 231562, "decode_str": "walk"} -{"id": 51567, "token": "\u00e5\u00ba\u0138", "merges": "\u00e5\u00ba \u0138", "raw_count": 231583, "count": 231583, "decode_str": "\u5e96"} -{"id": 13904, "token": "Edit", "merges": "Ed it", "raw_count": 231614, "count": 231614, "decode_str": "Edit"} -{"id": 15402, "token": "Parameter", "merges": "Par ameter", "raw_count": 231676, "count": 231676, "decode_str": "Parameter"} -{"id": 18094, "token": "CU", "merges": "C U", "raw_count": 229882, "count": 231691, "decode_str": "CU"} -{"id": 5863, "token": "\u0120Up", "merges": "\u0120U p", "raw_count": 52832, "count": 231740, "decode_str": " Up"} -{"id": 51160, "token": "\u00e5\u013d\u00a1", "merges": "\u00e5\u013d \u00a1", "raw_count": 231788, "count": 231788, "decode_str": "\u56e1"} -{"id": 37687, "token": "598", "merges": "59 8", "raw_count": 231830, "count": 231830, "decode_str": "598"} -{"id": 52855, "token": "\u00e7\u0132\u00ae", "merges": "\u00e7\u0132 \u00ae", "raw_count": 231882, "count": 231882, "decode_str": "\u742e"} -{"id": 6879, "token": "\u012075", "merges": "\u01207 5", "raw_count": 231904, "count": 231904, "decode_str": " 75"} -{"id": 51102, "token": "\u00e5\u0137\u00b6", "merges": "\u00e5\u0137 \u00b6", "raw_count": 231925, "count": 231925, "decode_str": "\u5576"} -{"id": 2958, "token": "\u0120publ", "merges": "\u0120p ubl", "raw_count": 7577, "count": 231951, "decode_str": " publ"} -{"id": 7112, "token": "ido", "merges": "id o", "raw_count": 228903, "count": 231954, "decode_str": "ido"} -{"id": 50769, "token": "\u00e5\u012a\u012f", "merges": "\u00e5\u012a \u012f", "raw_count": 232063, "count": 232063, "decode_str": "\u520d"} -{"id": 4796, "token": "\u0120reduce", "merges": "\u0120redu ce", "raw_count": 232124, "count": 232124, "decode_str": " reduce"} -{"id": 25679, "token": "dialog", "merges": "d ialog", "raw_count": 232133, "count": 232133, "decode_str": "dialog"} -{"id": 51395, "token": "\u00e5\u0143\u00b3", "merges": "\u00e5\u0143 \u00b3", "raw_count": 232203, "count": 232203, "decode_str": "\u5b73"} -{"id": 4556, "token": "*.", "merges": "* .", "raw_count": 209232, "count": 232207, "decode_str": "*."} -{"id": 9342, "token": "\u0120wra", "merges": "\u0120w ra", "raw_count": 10542, "count": 232289, "decode_str": " wra"} -{"id": 18721, "token": "ancel", "merges": "anc el", "raw_count": 17950, "count": 232300, "decode_str": "ancel"} -{"id": 2389, "token": "\u0120love", "merges": "\u0120l ove", "raw_count": 232300, "count": 232300, "decode_str": " love"} -{"id": 32280, "token": "scene", "merges": "sc ene", "raw_count": 232342, "count": 232342, "decode_str": "scene"} -{"id": 4402, "token": "operator", "merges": "oper ator", "raw_count": 231260, "count": 232344, "decode_str": "operator"} -{"id": 22619, "token": "voice", "merges": "vo ice", "raw_count": 217737, "count": 232353, "decode_str": "voice"} -{"id": 53000, "token": "\u00e7\u013d\u00b9", "merges": "\u00e7\u013d \u00b9", "raw_count": 232380, "count": 232380, "decode_str": "\u76f9"} -{"id": 2854, "token": "\u0120drug", "merges": "\u0120d rug", "raw_count": 140096, "count": 232435, "decode_str": " drug"} -{"id": 8701, "token": "his", "merges": "h is", "raw_count": 232456, "count": 232456, "decode_str": "his"} -{"id": 42787, "token": "jpeg", "merges": "j peg", "raw_count": 232540, "count": 232540, "decode_str": "jpeg"} -{"id": 5341, "token": "oting", "merges": "ot ing", "raw_count": 48247, "count": 232559, "decode_str": "oting"} -{"id": 17214, "token": "Display", "merges": "Dis play", "raw_count": 232581, "count": 232581, "decode_str": "Display"} -{"id": 31010, "token": "cli", "merges": "cl i", "raw_count": 232619, "count": 232619, "decode_str": "cli"} -{"id": 3398, "token": "hers", "merges": "her s", "raw_count": 40775, "count": 232653, "decode_str": "hers"} -{"id": 7342, "token": "\u0120goals", "merges": "\u0120go als", "raw_count": 232700, "count": 232700, "decode_str": " goals"} -{"id": 19641, "token": "\u0120dt", "merges": "\u0120d t", "raw_count": 232714, "count": 232714, "decode_str": " dt"} -{"id": 38664, "token": "refresh", "merges": "ref resh", "raw_count": 232777, "count": 232777, "decode_str": "refresh"} -{"id": 52500, "token": "\u00e6\u00b2\u0131", "merges": "\u00e6\u00b2 \u0131", "raw_count": 232870, "count": 232870, "decode_str": "\u6c8f"} -{"id": 53438, "token": "\u00e7\u00be\u00b8", "merges": "\u00e7\u00be \u00b8", "raw_count": 233009, "count": 233009, "decode_str": "\u7fb8"} -{"id": 39610, "token": "QS", "merges": "Q S", "raw_count": 233046, "count": 233046, "decode_str": "QS"} -{"id": 29860, "token": "ascii", "merges": "asc ii", "raw_count": 233082, "count": 233082, "decode_str": "ascii"} -{"id": 9112, "token": "Rel", "merges": "R el", "raw_count": 156343, "count": 233102, "decode_str": "Rel"} -{"id": 45276, "token": "pts", "merges": "pt s", "raw_count": 233149, "count": 233149, "decode_str": "pts"} -{"id": 19642, "token": "UK", "merges": "U K", "raw_count": 233178, "count": 233178, "decode_str": "UK"} -{"id": 3793, "token": "\u0120veh", "merges": "\u0120ve h", "raw_count": 11531, "count": 233192, "decode_str": " veh"} -{"id": 3063, "token": "\u0120today", "merges": "\u0120to day", "raw_count": 233339, "count": 233339, "decode_str": " today"} -{"id": 12782, "token": "Inte", "merges": "In te", "raw_count": 17443, "count": 233343, "decode_str": "Inte"} -{"id": 13897, "token": "integr", "merges": "inte gr", "raw_count": 66447, "count": 233360, "decode_str": "integr"} -{"id": 8066, "token": "\u0120pix", "merges": "\u0120p ix", "raw_count": 38044, "count": 233386, "decode_str": " pix"} -{"id": 16204, "token": "\u0120declaration", "merges": "\u0120decl aration", "raw_count": 233403, "count": 233403, "decode_str": " declaration"} -{"id": 11297, "token": "ictions", "merges": "ict ions", "raw_count": 209507, "count": 233469, "decode_str": "ictions"} -{"id": 10605, "token": "Current", "merges": "C urrent", "raw_count": 217488, "count": 233553, "decode_str": "Current"} -{"id": 37369, "token": "rror", "merges": "rr or", "raw_count": 233556, "count": 233556, "decode_str": "rror"} -{"id": 17901, "token": "shell", "merges": "she ll", "raw_count": 233601, "count": 233601, "decode_str": "shell"} -{"id": 13808, "token": "edu", "merges": "ed u", "raw_count": 233720, "count": 233720, "decode_str": "edu"} -{"id": 2403, "token": "\u0120making", "merges": "\u0120m aking", "raw_count": 233796, "count": 233796, "decode_str": " making"} -{"id": 29137, "token": "353", "merges": "35 3", "raw_count": 233844, "count": 233844, "decode_str": "353"} -{"id": 18497, "token": "Card", "merges": "C ard", "raw_count": 233910, "count": 233910, "decode_str": "Card"} -{"id": 12660, "token": "\u0120180", "merges": "\u012018 0", "raw_count": 234052, "count": 234052, "decode_str": " 180"} -{"id": 4758, "token": "\u0120setting", "merges": "\u0120set ting", "raw_count": 234137, "count": 234137, "decode_str": " setting"} -{"id": 6628, "token": "ses", "merges": "s es", "raw_count": 130339, "count": 234137, "decode_str": "ses"} -{"id": 1804, "token": "\u0120suggest", "merges": "\u0120sugg est", "raw_count": 39681, "count": 234205, "decode_str": " suggest"} -{"id": 52007, "token": "\u00e6\u0130\u00b8", "merges": "\u00e6\u0130 \u00b8", "raw_count": 234287, "count": 234287, "decode_str": "\u63b8"} -{"id": 11554, "token": "kit", "merges": "k it", "raw_count": 180359, "count": 234327, "decode_str": "kit"} -{"id": 39525, "token": "(+", "merges": "( +", "raw_count": 234444, "count": 234444, "decode_str": "(+"} -{"id": 3885, "token": "\u0120speed", "merges": "\u0120spe ed", "raw_count": 209384, "count": 234453, "decode_str": " speed"} -{"id": 9300, "token": "\u0120updated", "merges": "\u0120upd ated", "raw_count": 234459, "count": 234459, "decode_str": " updated"} -{"id": 7245, "token": "\u0120WH", "merges": "\u0120W H", "raw_count": 25459, "count": 234474, "decode_str": " WH"} -{"id": 11904, "token": "yo", "merges": "y o", "raw_count": 233362, "count": 234490, "decode_str": "yo"} -{"id": 2835, "token": "itting", "merges": "itt ing", "raw_count": 63925, "count": 234514, "decode_str": "itting"} -{"id": 52301, "token": "\u00e6\u00a1\u012b", "merges": "\u00e6\u00a1 \u012b", "raw_count": 234527, "count": 234527, "decode_str": "\u6849"} -{"id": 19820, "token": "Ax", "merges": "A x", "raw_count": 160656, "count": 234554, "decode_str": "Ax"} -{"id": 5573, "token": "\u0120occup", "merges": "\u0120occ up", "raw_count": 2508, "count": 234581, "decode_str": " occup"} -{"id": 3989, "token": "\u0120construct", "merges": "\u0120const ruct", "raw_count": 107531, "count": 234606, "decode_str": " construct"} -{"id": 6617, "token": "\u0120crime", "merges": "\u0120cr ime", "raw_count": 234695, "count": 234695, "decode_str": " crime"} -{"id": 3541, "token": "\u0120memory", "merges": "\u0120mem ory", "raw_count": 234730, "count": 234730, "decode_str": " memory"} -{"id": 18760, "token": "Cent", "merges": "C ent", "raw_count": 153152, "count": 234736, "decode_str": "Cent"} -{"id": 27216, "token": "async", "merges": "as ync", "raw_count": 234996, "count": 234996, "decode_str": "async"} -{"id": 21093, "token": "City", "merges": "C ity", "raw_count": 235029, "count": 235029, "decode_str": "City"} -{"id": 18038, "token": "tc", "merges": "t c", "raw_count": 235053, "count": 235053, "decode_str": "tc"} -{"id": 39618, "token": "'/", "merges": "' /", "raw_count": 235071, "count": 235071, "decode_str": "'/"} -{"id": 25011, "token": "members", "merges": "mem bers", "raw_count": 235107, "count": 235107, "decode_str": "members"} -{"id": 14324, "token": "Menu", "merges": "M enu", "raw_count": 214176, "count": 235190, "decode_str": "Menu"} -{"id": 51823, "token": "\u00e6\u012a\u00ac", "merges": "\u00e6\u012a \u00ac", "raw_count": 235249, "count": 235249, "decode_str": "\u622c"} -{"id": 3443, "token": "\u0120du", "merges": "\u0120d u", "raw_count": 84505, "count": 235342, "decode_str": " du"} -{"id": 4981, "token": "\u0120util", "merges": "\u0120ut il", "raw_count": 140409, "count": 235438, "decode_str": " util"} -{"id": 5551, "token": "produ", "merges": "pro du", "raw_count": 95322, "count": 235468, "decode_str": "produ"} -{"id": 2903, "token": "\u0120Ass", "merges": "\u0120A ss", "raw_count": 47120, "count": 235553, "decode_str": " Ass"} -{"id": 14192, "token": "\u0120poverty", "merges": "\u0120p overty", "raw_count": 235575, "count": 235575, "decode_str": " poverty"} -{"id": 1803, "token": "\u0120sugg", "merges": "\u0120su gg", "raw_count": 1378, "count": 235583, "decode_str": " sugg"} -{"id": 13144, "token": "013", "merges": "01 3", "raw_count": 235651, "count": 235651, "decode_str": "013"} -{"id": 15581, "token": "btn", "merges": "bt n", "raw_count": 235682, "count": 235682, "decode_str": "btn"} -{"id": 15572, "token": "\u0120representatives", "merges": "\u0120represent atives", "raw_count": 235689, "count": 235689, "decode_str": " representatives"} -{"id": 44291, "token": "commands", "merges": "comm ands", "raw_count": 235860, "count": 235860, "decode_str": "commands"} -{"id": 35878, "token": "reduce", "merges": "red uce", "raw_count": 235870, "count": 235870, "decode_str": "reduce"} -{"id": 18858, "token": "sq", "merges": "s q", "raw_count": 234600, "count": 235877, "decode_str": "sq"} -{"id": 12923, "token": "Spe", "merges": "S pe", "raw_count": 114390, "count": 235952, "decode_str": "Spe"} -{"id": 2162, "token": "phi", "merges": "ph i", "raw_count": 234240, "count": 235973, "decode_str": "phi"} -{"id": 1325, "token": "\u0120\u00c3", "merges": "\u0120 \u00c3", "raw_count": 6723, "count": 235988, "decode_str": " \ufffd"} -{"id": 24333, "token": "504", "merges": "50 4", "raw_count": 236051, "count": 236051, "decode_str": "504"} -{"id": 4351, "token": "king", "merges": "k ing", "raw_count": 165894, "count": 236055, "decode_str": "king"} -{"id": 27122, "token": "292", "merges": "29 2", "raw_count": 236195, "count": 236195, "decode_str": "292"} -{"id": 8149, "token": "\u0120investment", "merges": "\u0120invest ment", "raw_count": 236258, "count": 236258, "decode_str": " investment"} -{"id": 31896, "token": "\u0120delegation", "merges": "\u0120deleg ation", "raw_count": 236287, "count": 236287, "decode_str": " delegation"} -{"id": 47928, "token": "(?", "merges": "( ?", "raw_count": 236297, "count": 236297, "decode_str": "(?"} -{"id": 16192, "token": "mn", "merges": "m n", "raw_count": 236302, "count": 236302, "decode_str": "mn"} -{"id": 10735, "token": "ificate", "merges": "ific ate", "raw_count": 88877, "count": 236348, "decode_str": "ificate"} -{"id": 26399, "token": "MK", "merges": "M K", "raw_count": 236464, "count": 236464, "decode_str": "MK"} -{"id": 8908, "token": "ABLE", "merges": "AB LE", "raw_count": 98044, "count": 236508, "decode_str": "ABLE"} -{"id": 24264, "token": "409", "merges": "40 9", "raw_count": 236564, "count": 236564, "decode_str": "409"} -{"id": 18769, "token": "IZ", "merges": "I Z", "raw_count": 236587, "count": 236587, "decode_str": "IZ"} -{"id": 52948, "token": "\u00e7\u0139\u00b1", "merges": "\u00e7\u0139 \u00b1", "raw_count": 236622, "count": 236622, "decode_str": "\u75f1"} -{"id": 6230, "token": "ras", "merges": "r as", "raw_count": 207639, "count": 236660, "decode_str": "ras"} -{"id": 3388, "token": "\u0120average", "merges": "\u0120a verage", "raw_count": 236672, "count": 236672, "decode_str": " average"} -{"id": 2914, "token": "\u0120front", "merges": "\u0120fr ont", "raw_count": 211236, "count": 236714, "decode_str": " front"} -{"id": 44480, "token": "Baby", "merges": "B aby", "raw_count": 236722, "count": 236722, "decode_str": "Baby"} -{"id": 4788, "token": "adem", "merges": "ad em", "raw_count": 61097, "count": 236755, "decode_str": "adem"} -{"id": 5506, "token": "\u0120responsible", "merges": "\u0120respons ible", "raw_count": 236880, "count": 236880, "decode_str": " responsible"} -{"id": 24769, "token": "407", "merges": "40 7", "raw_count": 236903, "count": 236903, "decode_str": "407"} -{"id": 52545, "token": "\u00e6\u00b3\u00b7", "merges": "\u00e6\u00b3 \u00b7", "raw_count": 236973, "count": 236973, "decode_str": "\u6cf7"} -{"id": 23699, "token": "ools", "merges": "ool s", "raw_count": 236981, "count": 236981, "decode_str": "ools"} -{"id": 8914, "token": "\u0120weapons", "merges": "\u0120weap ons", "raw_count": 236984, "count": 236984, "decode_str": " weapons"} -{"id": 33511, "token": "elem", "merges": "e lem", "raw_count": 236996, "count": 236996, "decode_str": "elem"} -{"id": 24706, "token": "mix", "merges": "m ix", "raw_count": 237063, "count": 237063, "decode_str": "mix"} -{"id": 5811, "token": "ows", "merges": "ow s", "raw_count": 129499, "count": 237112, "decode_str": "ows"} -{"id": 37348, "token": "798", "merges": "79 8", "raw_count": 237125, "count": 237125, "decode_str": "798"} -{"id": 3087, "token": "inding", "merges": "ind ing", "raw_count": 12009, "count": 237129, "decode_str": "inding"} -{"id": 52749, "token": "\u00e7\u0126\u013a", "merges": "\u00e7\u0126 \u013a", "raw_count": 237148, "count": 237148, "decode_str": "\u7118"} -{"id": 10192, "token": "pres", "merges": "p res", "raw_count": 175893, "count": 237180, "decode_str": "pres"} -{"id": 26359, "token": ",**", "merges": ", **", "raw_count": 237236, "count": 237236, "decode_str": ",**"} -{"id": 23911, "token": "/\"", "merges": "/ \"", "raw_count": 237279, "count": 237279, "decode_str": "/\""} -{"id": 16808, "token": "ISS", "merges": "IS S", "raw_count": 180080, "count": 237293, "decode_str": "ISS"} -{"id": 13707, "token": "eur", "merges": "e ur", "raw_count": 236220, "count": 237364, "decode_str": "eur"} -{"id": 48054, "token": "925", "merges": "9 25", "raw_count": 237482, "count": 237482, "decode_str": "925"} -{"id": 27267, "token": "352", "merges": "35 2", "raw_count": 237484, "count": 237484, "decode_str": "352"} -{"id": 25592, "token": "389", "merges": "38 9", "raw_count": 237502, "count": 237502, "decode_str": "389"} -{"id": 21958, "token": "King", "merges": "K ing", "raw_count": 237605, "count": 237605, "decode_str": "King"} -{"id": 24534, "token": "Ni", "merges": "N i", "raw_count": 237688, "count": 237688, "decode_str": "Ni"} -{"id": 4552, "token": "iful", "merges": "if ul", "raw_count": 10167, "count": 237739, "decode_str": "iful"} -{"id": 6222, "token": "\u0120profile", "merges": "\u0120prof ile", "raw_count": 237841, "count": 237841, "decode_str": " profile"} -{"id": 2243, "token": "\u0120mom", "merges": "\u0120m om", "raw_count": 35389, "count": 237885, "decode_str": " mom"} -{"id": 7911, "token": "\u0120prices", "merges": "\u0120p rices", "raw_count": 237947, "count": 237947, "decode_str": " prices"} -{"id": 51050, "token": "\u00e5\u0134\u00bf", "merges": "\u00e5\u0134 \u00bf", "raw_count": 237980, "count": 237980, "decode_str": "\u54bf"} -{"id": 30301, "token": "Series", "merges": "Ser ies", "raw_count": 238004, "count": 238004, "decode_str": "Series"} -{"id": 18527, "token": "Obj", "merges": "Ob j", "raw_count": 238098, "count": 238098, "decode_str": "Obj"} -{"id": 9835, "token": "\u0120university", "merges": "\u0120un iversity", "raw_count": 238125, "count": 238125, "decode_str": " university"} -{"id": 24880, "token": "379", "merges": "37 9", "raw_count": 238204, "count": 238204, "decode_str": "379"} -{"id": 12155, "token": "hh", "merges": "h h", "raw_count": 165886, "count": 238210, "decode_str": "hh"} -{"id": 28933, "token": "283", "merges": "28 3", "raw_count": 238299, "count": 238299, "decode_str": "283"} -{"id": 43153, "token": "\u0120csv", "merges": "\u0120c sv", "raw_count": 238395, "count": 238395, "decode_str": " csv"} -{"id": 33553, "token": "adj", "merges": "ad j", "raw_count": 238411, "count": 238411, "decode_str": "adj"} -{"id": 1929, "token": "\u0120known", "merges": "\u0120kn own", "raw_count": 238598, "count": 238598, "decode_str": " known"} -{"id": 14760, "token": "enable", "merges": "en able", "raw_count": 237368, "count": 238632, "decode_str": "enable"} -{"id": 3687, "token": "\u0120greater", "merges": "\u0120great er", "raw_count": 238655, "count": 238655, "decode_str": " greater"} -{"id": 7280, "token": "github", "merges": "g ithub", "raw_count": 238668, "count": 238668, "decode_str": "github"} -{"id": 9562, "token": "enger", "merges": "en ger", "raw_count": 106176, "count": 238684, "decode_str": "enger"} -{"id": 3751, "token": "anger", "merges": "ang er", "raw_count": 117642, "count": 238840, "decode_str": "anger"} -{"id": 10832, "token": "\u0120undert", "merges": "\u0120under t", "raw_count": 16047, "count": 238845, "decode_str": " undert"} -{"id": 29582, "token": "Edge", "merges": "Ed ge", "raw_count": 238891, "count": 238891, "decode_str": "Edge"} -{"id": 8490, "token": "\u0120File", "merges": "\u0120F ile", "raw_count": 238918, "count": 238918, "decode_str": " File"} -{"id": 54456, "token": "\u00e9\u00a2\u0140", "merges": "\u00e9\u00a2 \u0140", "raw_count": 239103, "count": 239103, "decode_str": "\u989e"} -{"id": 12695, "token": "VE", "merges": "V E", "raw_count": 217126, "count": 239152, "decode_str": "VE"} -{"id": 24606, "token": "scal", "merges": "sc al", "raw_count": 92966, "count": 239187, "decode_str": "scal"} -{"id": 6352, "token": "olf", "merges": "ol f", "raw_count": 117043, "count": 239312, "decode_str": "olf"} -{"id": 2393, "token": "\u0120early", "merges": "\u0120e arly", "raw_count": 239345, "count": 239345, "decode_str": " early"} -{"id": 11494, "token": "014", "merges": "01 4", "raw_count": 239410, "count": 239410, "decode_str": "014"} -{"id": 4787, "token": "otes", "merges": "ot es", "raw_count": 149400, "count": 239474, "decode_str": "otes"} -{"id": 18677, "token": "rx", "merges": "r x", "raw_count": 239474, "count": 239474, "decode_str": "rx"} -{"id": 27018, "token": "351", "merges": "35 1", "raw_count": 239499, "count": 239499, "decode_str": "351"} -{"id": 3384, "token": "\u0120\u00e2", "merges": "\u0120 \u00e2", "raw_count": 156891, "count": 239545, "decode_str": " \ufffd"} -{"id": 14641, "token": "coll", "merges": "col l", "raw_count": 222087, "count": 239596, "decode_str": "coll"} -{"id": 6638, "token": "xture", "merges": "xt ure", "raw_count": 174630, "count": 239618, "decode_str": "xture"} -{"id": 1810, "token": "\u0120Sc", "merges": "\u0120S c", "raw_count": 69576, "count": 239629, "decode_str": " Sc"} -{"id": 8812, "token": "\u0120delet", "merges": "\u0120de let", "raw_count": 17684, "count": 239631, "decode_str": " delet"} -{"id": 24502, "token": "sig", "merges": "s ig", "raw_count": 239636, "count": 239636, "decode_str": "sig"} -{"id": 4406, "token": "\u0120emerg", "merges": "\u0120em erg", "raw_count": 364, "count": 239719, "decode_str": " emerg"} -{"id": 18244, "token": "UID", "merges": "U ID", "raw_count": 239741, "count": 239741, "decode_str": "UID"} -{"id": 54303, "token": "\u00e9\u013a\u013c", "merges": "\u00e9\u013a \u013c", "raw_count": 239742, "count": 239742, "decode_str": "\u961a"} -{"id": 3604, "token": "ega", "merges": "eg a", "raw_count": 76299, "count": 239777, "decode_str": "ega"} -{"id": 6056, "token": "lands", "merges": "land s", "raw_count": 129367, "count": 239806, "decode_str": "lands"} -{"id": 6001, "token": "\u0120script", "merges": "\u0120sc ript", "raw_count": 212168, "count": 239882, "decode_str": " script"} -{"id": 2943, "token": "lying", "merges": "ly ing", "raw_count": 76988, "count": 240052, "decode_str": "lying"} -{"id": 24335, "token": "sync", "merges": "s ync", "raw_count": 240098, "count": 240098, "decode_str": "sync"} -{"id": 7070, "token": "ipl", "merges": "i pl", "raw_count": 148757, "count": 240114, "decode_str": "ipl"} -{"id": 3462, "token": "ronic", "merges": "ron ic", "raw_count": 53466, "count": 240158, "decode_str": "ronic"} -{"id": 6409, "token": "\u0120button", "merges": "\u0120but ton", "raw_count": 240179, "count": 240179, "decode_str": " button"} -{"id": 2762, "token": "\u0120positive", "merges": "\u0120pos itive", "raw_count": 240206, "count": 240206, "decode_str": " positive"} -{"id": 45038, "token": "\u00e2\u0122\u013f\u00e2\u0122\u0136", "merges": "\u00e2\u0122\u013f \u00e2\u0122\u0136", "raw_count": 240293, "count": 240293, "decode_str": "\u201d\u2014"} -{"id": 27133, "token": "507", "merges": "50 7", "raw_count": 240442, "count": 240442, "decode_str": "507"} -{"id": 8065, "token": "\u01201998", "merges": "\u0120199 8", "raw_count": 240478, "count": 240478, "decode_str": " 1998"} -{"id": 3787, "token": "rupt", "merges": "ru pt", "raw_count": 99177, "count": 240494, "decode_str": "rupt"} -{"id": 3277, "token": "\u0120Qu", "merges": "\u0120Q u", "raw_count": 53720, "count": 240509, "decode_str": " Qu"} -{"id": 15770, "token": "-,", "merges": "- ,", "raw_count": 240531, "count": 240531, "decode_str": "-,"} -{"id": 5169, "token": "eria", "merges": "er ia", "raw_count": 123591, "count": 240545, "decode_str": "eria"} -{"id": 3082, "token": "\u0120methods", "merges": "\u0120method s", "raw_count": 240569, "count": 240569, "decode_str": " methods"} -{"id": 10026, "token": "nership", "merges": "n ership", "raw_count": 29601, "count": 240689, "decode_str": "nership"} -{"id": 4603, "token": "bum", "merges": "b um", "raw_count": 11760, "count": 240690, "decode_str": "bum"} -{"id": 16569, "token": "OOK", "merges": "OO K", "raw_count": 240692, "count": 240692, "decode_str": "OOK"} -{"id": 5756, "token": "chen", "merges": "c hen", "raw_count": 165659, "count": 240706, "decode_str": "chen"} -{"id": 11342, "token": "fire", "merges": "f ire", "raw_count": 240722, "count": 240722, "decode_str": "fire"} -{"id": 25140, "token": "367", "merges": "36 7", "raw_count": 240725, "count": 240725, "decode_str": "367"} -{"id": 5797, "token": "eds", "merges": "ed s", "raw_count": 151367, "count": 240780, "decode_str": "eds"} -{"id": 14985, "token": "pic", "merges": "p ic", "raw_count": 238152, "count": 240819, "decode_str": "pic"} -{"id": 17020, "token": "DATA", "merges": "D ATA", "raw_count": 240828, "count": 240828, "decode_str": "DATA"} -{"id": 44647, "token": "670", "merges": "6 70", "raw_count": 240893, "count": 240893, "decode_str": "670"} -{"id": 46056, "token": "ppm", "merges": "pp m", "raw_count": 240935, "count": 240935, "decode_str": "ppm"} -{"id": 7465, "token": "\u0120standards", "merges": "\u0120stand ards", "raw_count": 240947, "count": 240947, "decode_str": " standards"} -{"id": 21512, "token": "\u0120sql", "merges": "\u0120s ql", "raw_count": 149318, "count": 240973, "decode_str": " sql"} -{"id": 7892, "token": "\u0120cm", "merges": "\u0120c m", "raw_count": 241080, "count": 241080, "decode_str": " cm"} -{"id": 27087, "token": "454", "merges": "45 4", "raw_count": 241086, "count": 241086, "decode_str": "454"} -{"id": 4703, "token": "enge", "merges": "en ge", "raw_count": 13487, "count": 241091, "decode_str": "enge"} -{"id": 27494, "token": "slice", "merges": "sl ice", "raw_count": 241118, "count": 241118, "decode_str": "slice"} -{"id": 4644, "token": "\u0120volume", "merges": "\u0120vol ume", "raw_count": 241151, "count": 241151, "decode_str": " volume"} -{"id": 12236, "token": "Address", "merges": "Add ress", "raw_count": 241199, "count": 241199, "decode_str": "Address"} -{"id": 12508, "token": "irtual", "merges": "irt ual", "raw_count": 1682, "count": 241278, "decode_str": "irtual"} -{"id": 16792, "token": "Willi", "merges": "W illi", "raw_count": 2398, "count": 241280, "decode_str": "Willi"} -{"id": 22174, "token": "constant", "merges": "con stant", "raw_count": 241525, "count": 241525, "decode_str": "constant"} -{"id": 23492, "token": "keeping", "merges": "ke eping", "raw_count": 241540, "count": 241540, "decode_str": "keeping"} -{"id": 3651, "token": "\u0120consum", "merges": "\u0120cons um", "raw_count": 12877, "count": 241605, "decode_str": " consum"} -{"id": 2969, "token": "\u0120simple", "merges": "\u0120sim ple", "raw_count": 235821, "count": 241628, "decode_str": " simple"} -{"id": 37219, "token": "525", "merges": "5 25", "raw_count": 241634, "count": 241634, "decode_str": "525"} -{"id": 51405, "token": "\u00e5\u00ae\u0135", "merges": "\u00e5\u00ae \u0135", "raw_count": 241648, "count": 241648, "decode_str": "\u5b93"} -{"id": 52281, "token": "\u00e6\u0142\u0130", "merges": "\u00e6\u0142 \u0130", "raw_count": 241657, "count": 241657, "decode_str": "\u680e"} -{"id": 11713, "token": "commun", "merges": "com mun", "raw_count": 95063, "count": 241763, "decode_str": "commun"} -{"id": 9483, "token": "\u0120comprehens", "merges": "\u0120comp rehens", "raw_count": 8630, "count": 241777, "decode_str": " comprehens"} -{"id": 2644, "token": "\u0120whole", "merges": "\u0120who le", "raw_count": 241861, "count": 241861, "decode_str": " whole"} -{"id": 3415, "token": "\u00d0\u00bb", "merges": "\u00d0 \u00bb", "raw_count": 71565, "count": 241946, "decode_str": "\u043b"} -{"id": 5306, "token": "\u0120cert", "merges": "\u0120c ert", "raw_count": 69517, "count": 241963, "decode_str": " cert"} -{"id": 51117, "token": "\u00e5\u0138\u0131", "merges": "\u00e5\u0138 \u0131", "raw_count": 241973, "count": 241973, "decode_str": "\u558f"} -{"id": 39397, "token": "tile", "merges": "t ile", "raw_count": 242254, "count": 242254, "decode_str": "tile"} -{"id": 50558, "token": "\u00e4\u00bd\u013f", "merges": "\u00e4\u00bd \u013f", "raw_count": 242265, "count": 242265, "decode_str": "\u4f5d"} -{"id": 29667, "token": "317", "merges": "3 17", "raw_count": 242274, "count": 242274, "decode_str": "317"} -{"id": 25848, "token": "376", "merges": "37 6", "raw_count": 242297, "count": 242297, "decode_str": "376"} -{"id": 52373, "token": "\u00e6\u00a8\u00be", "merges": "\u00e6\u00a8 \u00be", "raw_count": 242299, "count": 242299, "decode_str": "\u6a3e"} -{"id": 10173, "token": "\u0120calculate", "merges": "\u0120calcul ate", "raw_count": 242325, "count": 242325, "decode_str": " calculate"} -{"id": 4445, "token": "\u0120component", "merges": "\u0120compon ent", "raw_count": 242331, "count": 242331, "decode_str": " component"} -{"id": 2443, "token": "\u0120dou", "merges": "\u0120d ou", "raw_count": 7388, "count": 242419, "decode_str": " dou"} -{"id": 27760, "token": "apshot", "merges": "ap shot", "raw_count": 203648, "count": 242447, "decode_str": "apshot"} -{"id": 12950, "token": "ettings", "merges": "ett ings", "raw_count": 16842, "count": 242469, "decode_str": "ettings"} -{"id": 11446, "token": "Style", "merges": "S tyle", "raw_count": 242548, "count": 242548, "decode_str": "Style"} -{"id": 21795, "token": ",%", "merges": ", %", "raw_count": 242559, "count": 242559, "decode_str": ",%"} -{"id": 26498, "token": "KB", "merges": "K B", "raw_count": 242611, "count": 242611, "decode_str": "KB"} -{"id": 6045, "token": "ror", "merges": "r or", "raw_count": 93432, "count": 242631, "decode_str": "ror"} -{"id": 5570, "token": "\u0120agent", "merges": "\u0120ag ent", "raw_count": 242638, "count": 242638, "decode_str": " agent"} -{"id": 50734, "token": "\u00e5\u0128\u00bc", "merges": "\u00e5\u0128 \u00bc", "raw_count": 242742, "count": 242742, "decode_str": "\u51bc"} -{"id": 2299, "token": "\u0120however", "merges": "\u0120how ever", "raw_count": 242910, "count": 242910, "decode_str": " however"} -{"id": 4319, "token": "argin", "merges": "arg in", "raw_count": 65889, "count": 242943, "decode_str": "argin"} -{"id": 2557, "token": "\u0120measure", "merges": "\u0120meas ure", "raw_count": 130095, "count": 242961, "decode_str": " measure"} -{"id": 24098, "token": "\u0120payload", "merges": "\u0120pay load", "raw_count": 242992, "count": 242992, "decode_str": " payload"} -{"id": 44729, "token": "590", "merges": "5 90", "raw_count": 243059, "count": 243059, "decode_str": "590"} -{"id": 1633, "token": "\u0120something", "merges": "\u0120som ething", "raw_count": 243136, "count": 243136, "decode_str": " something"} -{"id": 16887, "token": "deg", "merges": "de g", "raw_count": 243150, "count": 243150, "decode_str": "deg"} -{"id": 1997, "token": "\u0120Gr", "merges": "\u0120G r", "raw_count": 29068, "count": 243180, "decode_str": " Gr"} -{"id": 12535, "token": "Op", "merges": "O p", "raw_count": 243201, "count": 243201, "decode_str": "Op"} -{"id": 31922, "token": "XT", "merges": "X T", "raw_count": 243238, "count": 243238, "decode_str": "XT"} -{"id": 11550, "token": "yg", "merges": "y g", "raw_count": 112097, "count": 243260, "decode_str": "yg"} -{"id": 30382, "token": "smart", "merges": "sm art", "raw_count": 243262, "count": 243262, "decode_str": "smart"} -{"id": 8720, "token": "LR", "merges": "L R", "raw_count": 242907, "count": 243346, "decode_str": "LR"} -{"id": 4837, "token": "iling", "merges": "il ing", "raw_count": 105293, "count": 243370, "decode_str": "iling"} -{"id": 4172, "token": "\u0120ri", "merges": "\u0120 ri", "raw_count": 106145, "count": 243511, "decode_str": " ri"} -{"id": 29278, "token": "\u0120'',", "merges": "\u0120' ',", "raw_count": 243525, "count": 243525, "decode_str": " '',"} -{"id": 2983, "token": "\u0120attack", "merges": "\u0120att ack", "raw_count": 116285, "count": 243575, "decode_str": " attack"} -{"id": 8248, "token": "\u0120bodies", "merges": "\u0120b odies", "raw_count": 243600, "count": 243600, "decode_str": " bodies"} -{"id": 5984, "token": "allel", "merges": "alle l", "raw_count": 55015, "count": 243619, "decode_str": "allel"} -{"id": 17890, "token": "comb", "merges": "com b", "raw_count": 243626, "count": 243626, "decode_str": "comb"} -{"id": 2853, "token": "\u0120ill", "merges": "\u0120 ill", "raw_count": 80649, "count": 243765, "decode_str": " ill"} -{"id": 4948, "token": "\u0120forms", "merges": "\u0120form s", "raw_count": 243771, "count": 243771, "decode_str": " forms"} -{"id": 13925, "token": "011", "merges": "01 1", "raw_count": 243881, "count": 243881, "decode_str": "011"} -{"id": 23185, "token": "297", "merges": "29 7", "raw_count": 244005, "count": 244005, "decode_str": "297"} -{"id": 23848, "token": "\u0120treaty", "merges": "\u0120treat y", "raw_count": 244057, "count": 244057, "decode_str": " treaty"} -{"id": 14866, "token": "Miss", "merges": "M iss", "raw_count": 157309, "count": 244076, "decode_str": "Miss"} -{"id": 3913, "token": "acement", "merges": "ac ement", "raw_count": 20186, "count": 244084, "decode_str": "acement"} -{"id": 11497, "token": "\u0120participation", "merges": "\u0120particip ation", "raw_count": 244123, "count": 244123, "decode_str": " participation"} -{"id": 22798, "token": "scan", "merges": "sc an", "raw_count": 244140, "count": 244140, "decode_str": "scan"} -{"id": 14521, "token": "025", "merges": "0 25", "raw_count": 244193, "count": 244193, "decode_str": "025"} -{"id": 50510, "token": "\u00e4\u00bb\u00a8", "merges": "\u00e4\u00bb \u00a8", "raw_count": 244234, "count": 244234, "decode_str": "\u4ee8"} -{"id": 31358, "token": "498", "merges": "49 8", "raw_count": 244328, "count": 244328, "decode_str": "498"} -{"id": 14007, "token": "KS", "merges": "K S", "raw_count": 244392, "count": 244392, "decode_str": "KS"} -{"id": 4906, "token": "pling", "merges": "pl ing", "raw_count": 67622, "count": 244408, "decode_str": "pling"} -{"id": 30128, "token": "Images", "merges": "Im ages", "raw_count": 244630, "count": 244630, "decode_str": "Images"} -{"id": 7251, "token": "\u012065", "merges": "\u01206 5", "raw_count": 244635, "count": 244635, "decode_str": " 65"} -{"id": 49777, "token": ":\",", "merges": ": \",", "raw_count": 244645, "count": 244645, "decode_str": ":\","} -{"id": 5282, "token": "zen", "merges": "z en", "raw_count": 208721, "count": 244651, "decode_str": "zen"} -{"id": 13909, "token": "\u0120affairs", "merges": "\u0120aff airs", "raw_count": 244732, "count": 244732, "decode_str": " affairs"} -{"id": 17835, "token": "Email", "merges": "E mail", "raw_count": 244774, "count": 244774, "decode_str": "Email"} -{"id": 6106, "token": "ivery", "merges": "i very", "raw_count": 85081, "count": 244788, "decode_str": "ivery"} -{"id": 50863, "token": "\u00e5\u012f\u0127", "merges": "\u00e5\u012f \u0127", "raw_count": 244846, "count": 244846, "decode_str": "\u5345"} -{"id": 1833, "token": "'ll", "merges": "' ll", "raw_count": 244929, "count": 244929, "decode_str": "'ll"} -{"id": 11009, "token": "\u0120agencies", "merges": "\u0120ag encies", "raw_count": 244938, "count": 244938, "decode_str": " agencies"} -{"id": 2330, "token": "\u0120associated", "merges": "\u0120associ ated", "raw_count": 245265, "count": 245265, "decode_str": " associated"} -{"id": 22365, "token": "\u0120wx", "merges": "\u0120w x", "raw_count": 245277, "count": 245277, "decode_str": " wx"} -{"id": 4857, "token": "\u0120letter", "merges": "\u0120let ter", "raw_count": 245340, "count": 245340, "decode_str": " letter"} -{"id": 18772, "token": "]=", "merges": "] =", "raw_count": 245399, "count": 245399, "decode_str": "]="} -{"id": 41256, "token": ")],", "merges": ") ],", "raw_count": 245405, "count": 245405, "decode_str": ")],"} -{"id": 3340, "token": "\u0120especially", "merges": "\u0120es pecially", "raw_count": 245589, "count": 245589, "decode_str": " especially"} -{"id": 6062, "token": "olar", "merges": "ol ar", "raw_count": 221385, "count": 245602, "decode_str": "olar"} -{"id": 46906, "token": "datas", "merges": "dat as", "raw_count": 245688, "count": 245688, "decode_str": "datas"} -{"id": 45983, "token": "requests", "merges": "requ ests", "raw_count": 245713, "count": 245713, "decode_str": "requests"} -{"id": 11151, "token": "week", "merges": "we ek", "raw_count": 245725, "count": 245725, "decode_str": "week"} -{"id": 13880, "token": "docs", "merges": "doc s", "raw_count": 245794, "count": 245794, "decode_str": "docs"} -{"id": 51017, "token": "\u00e5\u0134\u0124", "merges": "\u00e5\u0134 \u0124", "raw_count": 245810, "count": 245810, "decode_str": "\u5482"} -{"id": 23100, "token": "364", "merges": "3 64", "raw_count": 245910, "count": 245910, "decode_str": "364"} -{"id": 7311, "token": "gi", "merges": "g i", "raw_count": 200375, "count": 245925, "decode_str": "gi"} -{"id": 27136, "token": "builder", "merges": "bu ilder", "raw_count": 246060, "count": 246060, "decode_str": "builder"} -{"id": 4017, "token": "\u0120protect", "merges": "\u0120prote ct", "raw_count": 173191, "count": 246130, "decode_str": " protect"} -{"id": 7522, "token": "\u0120fill", "merges": "\u0120f ill", "raw_count": 246223, "count": 246223, "decode_str": " fill"} -{"id": 8180, "token": "\u0120consideration", "merges": "\u0120consider ation", "raw_count": 246354, "count": 246354, "decode_str": " consideration"} -{"id": 13030, "token": "Main", "merges": "M ain", "raw_count": 246431, "count": 246431, "decode_str": "Main"} -{"id": 4306, "token": "ancy", "merges": "an cy", "raw_count": 166418, "count": 246482, "decode_str": "ancy"} -{"id": 49168, "token": "\u00e2\u0122\u00a6..", "merges": "\u00e2\u0122\u00a6 ..", "raw_count": 246496, "count": 246496, "decode_str": "\u2026.."} -{"id": 3029, "token": "\u0120defin", "merges": "\u0120def in", "raw_count": 8808, "count": 246552, "decode_str": " defin"} -{"id": 15510, "token": "Mart", "merges": "M art", "raw_count": 105340, "count": 246648, "decode_str": "Mart"} -{"id": 53550, "token": "\u00e8\u0126\u00b2", "merges": "\u00e8\u0126 \u00b2", "raw_count": 246685, "count": 246685, "decode_str": "\u8132"} -{"id": 5645, "token": "\u0120expand", "merges": "\u0120exp and", "raw_count": 142536, "count": 246750, "decode_str": " expand"} -{"id": 13117, "token": "Jo", "merges": "J o", "raw_count": 208705, "count": 246775, "decode_str": "Jo"} -{"id": 3035, "token": "\u0120En", "merges": "\u0120E n", "raw_count": 87132, "count": 246807, "decode_str": " En"} -{"id": 1841, "token": "\u0120things", "merges": "\u0120th ings", "raw_count": 246823, "count": 246823, "decode_str": " things"} -{"id": 52678, "token": "\u00e6\u00ba\u0131", "merges": "\u00e6\u00ba \u0131", "raw_count": 246829, "count": 246829, "decode_str": "\u6e8f"} -{"id": 12809, "token": "overty", "merges": "over ty", "raw_count": 11278, "count": 246853, "decode_str": "overty"} -{"id": 35858, "token": "entries", "merges": "ent ries", "raw_count": 246857, "count": 246857, "decode_str": "entries"} -{"id": 19915, "token": "\u0120coordination", "merges": "\u0120coord ination", "raw_count": 246859, "count": 246859, "decode_str": " coordination"} -{"id": 11863, "token": "blue", "merges": "bl ue", "raw_count": 246889, "count": 246889, "decode_str": "blue"} -{"id": 4110, "token": "\u0120IS", "merges": "\u0120I S", "raw_count": 200987, "count": 246902, "decode_str": " IS"} -{"id": 16321, "token": "xxxx", "merges": "xx xx", "raw_count": 209920, "count": 246998, "decode_str": "xxxx"} -{"id": 28316, "token": "helper", "merges": "hel per", "raw_count": 247016, "count": 247016, "decode_str": "helper"} -{"id": 8473, "token": "\u0120embed", "merges": "\u0120em bed", "raw_count": 74593, "count": 247385, "decode_str": " embed"} -{"id": 19397, "token": "fat", "merges": "f at", "raw_count": 247423, "count": 247423, "decode_str": "fat"} -{"id": 3567, "token": "ributed", "merges": "ribut ed", "raw_count": 50602, "count": 247431, "decode_str": "ributed"} -{"id": 23045, "token": "Design", "merges": "Des ign", "raw_count": 247475, "count": 247475, "decode_str": "Design"} -{"id": 12242, "token": "hop", "merges": "h op", "raw_count": 166508, "count": 247486, "decode_str": "hop"} -{"id": 18583, "token": "(__", "merges": "( __", "raw_count": 247501, "count": 247501, "decode_str": "(__"} -{"id": 2571, "token": "\u0120others", "merges": "\u0120other s", "raw_count": 247556, "count": 247556, "decode_str": " others"} -{"id": 12474, "token": "\u0120attributes", "merges": "\u0120att ributes", "raw_count": 247692, "count": 247692, "decode_str": " attributes"} -{"id": 12395, "token": "eries", "merges": "er ies", "raw_count": 178046, "count": 247778, "decode_str": "eries"} -{"id": 51101, "token": "\u00e5\u0137\u00b5", "merges": "\u00e5\u0137 \u00b5", "raw_count": 247781, "count": 247781, "decode_str": "\u5575"} -{"id": 5970, "token": "ologies", "merges": "olog ies", "raw_count": 93076, "count": 247796, "decode_str": "ologies"} -{"id": 52303, "token": "\u00e6\u00a1\u0130", "merges": "\u00e6\u00a1 \u0130", "raw_count": 247937, "count": 247937, "decode_str": "\u684e"} -{"id": 48294, "token": "860", "merges": "8 60", "raw_count": 247959, "count": 247959, "decode_str": "860"} -{"id": 3766, "token": "hern", "merges": "her n", "raw_count": 18310, "count": 248043, "decode_str": "hern"} -{"id": 44832, "token": "axes", "merges": "ax es", "raw_count": 248070, "count": 248070, "decode_str": "axes"} -{"id": 36617, "token": "cookie", "merges": "c ookie", "raw_count": 248110, "count": 248110, "decode_str": "cookie"} -{"id": 12842, "token": "\u0120128", "merges": "\u012012 8", "raw_count": 248137, "count": 248137, "decode_str": " 128"} -{"id": 20216, "token": "395", "merges": "39 5", "raw_count": 248146, "count": 248146, "decode_str": "395"} -{"id": 4815, "token": "\u0120costs", "merges": "\u0120cost s", "raw_count": 248201, "count": 248201, "decode_str": " costs"} -{"id": 8688, "token": "\u012099", "merges": "\u01209 9", "raw_count": 248207, "count": 248207, "decode_str": " 99"} -{"id": 13474, "token": "\u0120export", "merges": "\u0120ex port", "raw_count": 248274, "count": 248274, "decode_str": " export"} -{"id": 3693, "token": "\u0120avoid", "merges": "\u0120av oid", "raw_count": 199856, "count": 248473, "decode_str": " avoid"} -{"id": 4903, "token": "\u0120variables", "merges": "\u0120vari ables", "raw_count": 248574, "count": 248574, "decode_str": " variables"} -{"id": 3509, "token": "\u0120prec", "merges": "\u0120pre c", "raw_count": 48100, "count": 248586, "decode_str": " prec"} -{"id": 3041, "token": "\u0120million", "merges": "\u0120m illion", "raw_count": 248720, "count": 248720, "decode_str": " million"} -{"id": 28847, "token": "regex", "merges": "re gex", "raw_count": 248730, "count": 248730, "decode_str": "regex"} -{"id": 51697, "token": "\u00e6\u0122\u013b", "merges": "\u00e6\u0122 \u013b", "raw_count": 248847, "count": 248847, "decode_str": "\u6019"} -{"id": 4691, "token": "\u0120mal", "merges": "\u0120m al", "raw_count": 194306, "count": 248853, "decode_str": " mal"} -{"id": 49088, "token": "\u0120cfg", "merges": "\u0120c fg", "raw_count": 248881, "count": 248881, "decode_str": " cfg"} -{"id": 53949, "token": "\u00e8\u00b5\u012c", "merges": "\u00e8\u00b5 \u012c", "raw_count": 248978, "count": 248978, "decode_str": "\u8d4a"} -{"id": 27423, "token": "selection", "merges": "se lection", "raw_count": 248979, "count": 248979, "decode_str": "selection"} -{"id": 15642, "token": "atar", "merges": "at ar", "raw_count": 223226, "count": 249052, "decode_str": "atar"} -{"id": 3103, "token": "\u0120therefore", "merges": "\u0120there fore", "raw_count": 249155, "count": 249155, "decode_str": " therefore"} -{"id": 4405, "token": "urt", "merges": "ur t", "raw_count": 111544, "count": 249169, "decode_str": "urt"} -{"id": 2620, "token": "\u0120five", "merges": "\u0120f ive", "raw_count": 249179, "count": 249179, "decode_str": " five"} -{"id": 24656, "token": "phabet", "merges": "phab et", "raw_count": 205245, "count": 249180, "decode_str": "phabet"} -{"id": 3217, "token": "comes", "merges": "com es", "raw_count": 109024, "count": 249191, "decode_str": "comes"} -{"id": 53515, "token": "\u00e8\u0125\u013d", "merges": "\u00e8\u0125 \u013d", "raw_count": 249237, "count": 249237, "decode_str": "\u80db"} -{"id": 4136, "token": "\u0120allowed", "merges": "\u0120allow ed", "raw_count": 249287, "count": 249287, "decode_str": " allowed"} -{"id": 12723, "token": ";;", "merges": "; ;", "raw_count": 185637, "count": 249337, "decode_str": ";;"} -{"id": 5363, "token": "ship", "merges": "sh ip", "raw_count": 174787, "count": 249388, "decode_str": "ship"} -{"id": 4263, "token": "oring", "merges": "or ing", "raw_count": 149646, "count": 249471, "decode_str": "oring"} -{"id": 5916, "token": "arp", "merges": "ar p", "raw_count": 166053, "count": 249544, "decode_str": "arp"} -{"id": 2870, "token": "\u0120ste", "merges": "\u0120st e", "raw_count": 36077, "count": 249562, "decode_str": " ste"} -{"id": 1977, "token": "\u0120away", "merges": "\u0120a way", "raw_count": 249569, "count": 249569, "decode_str": " away"} -{"id": 24117, "token": "287", "merges": "28 7", "raw_count": 249585, "count": 249585, "decode_str": "287"} -{"id": 28626, "token": "glob", "merges": "gl ob", "raw_count": 249586, "count": 249586, "decode_str": "glob"} -{"id": 3890, "token": "\u0120express", "merges": "\u0120exp ress", "raw_count": 127781, "count": 249634, "decode_str": " express"} -{"id": 52397, "token": "\u00e6\u0143\u013b", "merges": "\u00e6\u0143 \u013b", "raw_count": 249680, "count": 249680, "decode_str": "\u6b59"} -{"id": 10582, "token": "gle", "merges": "g le", "raw_count": 75161, "count": 249738, "decode_str": "gle"} -{"id": 25358, "token": "606", "merges": "60 6", "raw_count": 249794, "count": 249794, "decode_str": "606"} -{"id": 3944, "token": "\u0120http", "merges": "\u0120htt p", "raw_count": 250011, "count": 250011, "decode_str": " http"} -{"id": 4921, "token": "omas", "merges": "om as", "raw_count": 57756, "count": 250023, "decode_str": "omas"} -{"id": 3116, "token": "\u0120growth", "merges": "\u0120grow th", "raw_count": 250059, "count": 250059, "decode_str": " growth"} -{"id": 45142, "token": "GIS", "merges": "G IS", "raw_count": 250099, "count": 250099, "decode_str": "GIS"} -{"id": 51095, "token": "\u00e5\u0137\u00ab", "merges": "\u00e5\u0137 \u00ab", "raw_count": 250178, "count": 250178, "decode_str": "\u556b"} -{"id": 13569, "token": "Del", "merges": "D el", "raw_count": 214235, "count": 250242, "decode_str": "Del"} -{"id": 4404, "token": "\u0120towards", "merges": "\u0120toward s", "raw_count": 250251, "count": 250251, "decode_str": " towards"} -{"id": 5926, "token": "\u0120drop", "merges": "\u0120d rop", "raw_count": 243793, "count": 250283, "decode_str": " drop"} -{"id": 13921, "token": "Order", "merges": "Or der", "raw_count": 250384, "count": 250384, "decode_str": "Order"} -{"id": 17995, "token": "prec", "merges": "p rec", "raw_count": 99178, "count": 250427, "decode_str": "prec"} -{"id": 20604, "token": "NY", "merges": "N Y", "raw_count": 250483, "count": 250483, "decode_str": "NY"} -{"id": 15718, "token": "CRE", "merges": "CR E", "raw_count": 159594, "count": 250554, "decode_str": "CRE"} -{"id": 4491, "token": "\u0120industry", "merges": "\u0120indust ry", "raw_count": 250581, "count": 250581, "decode_str": " industry"} -{"id": 5277, "token": "\u0120providing", "merges": "\u0120prov iding", "raw_count": 250582, "count": 250582, "decode_str": " providing"} -{"id": 5027, "token": "\u0120contribut", "merges": "\u0120cont ribut", "raw_count": 2504, "count": 250637, "decode_str": " contribut"} -{"id": 14774, "token": "sym", "merges": "s ym", "raw_count": 227222, "count": 250727, "decode_str": "sym"} -{"id": 7399, "token": "istan", "merges": "ist an", "raw_count": 250382, "count": 250800, "decode_str": "istan"} -{"id": 4327, "token": "\u0120choice", "merges": "\u0120cho ice", "raw_count": 250818, "count": 250818, "decode_str": " choice"} -{"id": 5147, "token": "\u0120platform", "merges": "\u0120pl atform", "raw_count": 213663, "count": 250898, "decode_str": " platform"} -{"id": 29429, "token": "segment", "merges": "se gment", "raw_count": 250949, "count": 250949, "decode_str": "segment"} -{"id": 4671, "token": "icip", "merges": "ic ip", "raw_count": 14542, "count": 250960, "decode_str": "icip"} -{"id": 14610, "token": "\u0120tags", "merges": "\u0120t ags", "raw_count": 250983, "count": 250983, "decode_str": " tags"} -{"id": 3959, "token": "\u0120offer", "merges": "\u0120off er", "raw_count": 234985, "count": 251052, "decode_str": " offer"} -{"id": 9683, "token": "Layout", "merges": "L ayout", "raw_count": 250341, "count": 251237, "decode_str": "Layout"} -{"id": 733, "token": "\u0120It", "merges": "\u0120I t", "raw_count": 152865, "count": 251239, "decode_str": " It"} -{"id": 3008, "token": "iqu", "merges": "i qu", "raw_count": 124095, "count": 251312, "decode_str": "iqu"} -{"id": 49737, "token": "verbose", "merges": "verb ose", "raw_count": 251344, "count": 251344, "decode_str": "verbose"} -{"id": 19731, "token": "radius", "merges": "rad ius", "raw_count": 251386, "count": 251386, "decode_str": "radius"} -{"id": 23657, "token": "\u0120epoch", "merges": "\u0120ep och", "raw_count": 195537, "count": 251463, "decode_str": " epoch"} -{"id": 4652, "token": "orge", "merges": "or ge", "raw_count": 67896, "count": 251645, "decode_str": "orge"} -{"id": 4278, "token": "\u0120details", "merges": "\u0120detail s", "raw_count": 251683, "count": 251683, "decode_str": " details"} -{"id": 4389, "token": "\u0120saf", "merges": "\u0120sa f", "raw_count": 19398, "count": 251699, "decode_str": " saf"} -{"id": 8885, "token": "ori", "merges": "or i", "raw_count": 248904, "count": 251752, "decode_str": "ori"} -{"id": 10267, "token": "Mem", "merges": "M em", "raw_count": 112793, "count": 251800, "decode_str": "Mem"} -{"id": 35238, "token": "transaction", "merges": "trans action", "raw_count": 251813, "count": 251813, "decode_str": "transaction"} -{"id": 19552, "token": "...)", "merges": "... )", "raw_count": 251813, "count": 251813, "decode_str": "...)"} -{"id": 2968, "token": "\u0120deal", "merges": "\u0120de al", "raw_count": 151192, "count": 251868, "decode_str": " deal"} -{"id": 18227, "token": "micro", "merges": "m icro", "raw_count": 251766, "count": 251957, "decode_str": "micro"} -{"id": 12752, "token": "ITE", "merges": "IT E", "raw_count": 220055, "count": 251987, "decode_str": "ITE"} -{"id": 32658, "token": "OE", "merges": "O E", "raw_count": 252162, "count": 252162, "decode_str": "OE"} -{"id": 22401, "token": "fm", "merges": "f m", "raw_count": 252196, "count": 252196, "decode_str": "fm"} -{"id": 2962, "token": "\u0120series", "merges": "\u0120ser ies", "raw_count": 252210, "count": 252210, "decode_str": " series"} -{"id": 17295, "token": ".\",", "merges": ".\" ,", "raw_count": 252234, "count": 252234, "decode_str": ".\","} -{"id": 4414, "token": "_.", "merges": "_ .", "raw_count": 252236, "count": 252236, "decode_str": "_."} -{"id": 2223, "token": "\u0120often", "merges": "\u0120of ten", "raw_count": 252254, "count": 252254, "decode_str": " often"} -{"id": 4003, "token": "erve", "merges": "er ve", "raw_count": 97173, "count": 252301, "decode_str": "erve"} -{"id": 6025, "token": "alysis", "merges": "al ysis", "raw_count": 7195, "count": 252311, "decode_str": "alysis"} -{"id": 3909, "token": "\u0120online", "merges": "\u0120on line", "raw_count": 252463, "count": 252463, "decode_str": " online"} -{"id": 14085, "token": "Entry", "merges": "Ent ry", "raw_count": 252464, "count": 252464, "decode_str": "Entry"} -{"id": 19834, "token": "outube", "merges": "out ube", "raw_count": 142815, "count": 252480, "decode_str": "outube"} -{"id": 3997, "token": "\u0120feed", "merges": "\u0120fe ed", "raw_count": 158496, "count": 252597, "decode_str": " feed"} -{"id": 5279, "token": "Over", "merges": "O ver", "raw_count": 173216, "count": 252620, "decode_str": "Over"} -{"id": 27814, "token": "merge", "merges": "mer ge", "raw_count": 252672, "count": 252672, "decode_str": "merge"} -{"id": 54535, "token": "\u00e9\u00bb\u013e", "merges": "\u00e9\u00bb \u013e", "raw_count": 252683, "count": 252683, "decode_str": "\u9edc"} -{"id": 5085, "token": "\u0120units", "merges": "\u0120un its", "raw_count": 252701, "count": 252701, "decode_str": " units"} -{"id": 8286, "token": "CTION", "merges": "CT ION", "raw_count": 129248, "count": 252719, "decode_str": "CTION"} -{"id": 32666, "token": "]/", "merges": "] /", "raw_count": 252721, "count": 252721, "decode_str": "]/"} -{"id": 17126, "token": "Ben", "merges": "B en", "raw_count": 252768, "count": 252768, "decode_str": "Ben"} -{"id": 3904, "token": "\u0120numbers", "merges": "\u0120num bers", "raw_count": 252774, "count": 252774, "decode_str": " numbers"} -{"id": 18129, "token": "MODE", "merges": "MO DE", "raw_count": 252810, "count": 252810, "decode_str": "MODE"} -{"id": 3268, "token": "\u0120distribution", "merges": "\u0120dist ribution", "raw_count": 252936, "count": 252936, "decode_str": " distribution"} -{"id": 9020, "token": "isting", "merges": "ist ing", "raw_count": 42020, "count": 252964, "decode_str": "isting"} -{"id": 31126, "token": "arguments", "merges": "arg uments", "raw_count": 253014, "count": 253014, "decode_str": "arguments"} -{"id": 4011, "token": "ran", "merges": "r an", "raw_count": 185174, "count": 253027, "decode_str": "ran"} -{"id": 157, "token": "\u00e1", "merges": "NULL", "raw_count": 48056, "count": 253039, "decode_str": "\ufffd"} -{"id": 18697, "token": "Cho", "merges": "C ho", "raw_count": 87111, "count": 253209, "decode_str": "Cho"} -{"id": 35621, "token": "resize", "merges": "res ize", "raw_count": 253210, "count": 253210, "decode_str": "resize"} -{"id": 4659, "token": "static", "merges": "st atic", "raw_count": 251380, "count": 253304, "decode_str": "static"} -{"id": 12899, "token": "\u0120Path", "merges": "\u0120P ath", "raw_count": 253353, "count": 253353, "decode_str": " Path"} -{"id": 3987, "token": "ming", "merges": "m ing", "raw_count": 116261, "count": 253465, "decode_str": "ming"} -{"id": 31601, "token": "mul", "merges": "m ul", "raw_count": 253512, "count": 253512, "decode_str": "mul"} -{"id": 53789, "token": "\u00e8\u00ae\u00ab", "merges": "\u00e8\u00ae \u00ab", "raw_count": 253593, "count": 253593, "decode_str": "\u8bab"} -{"id": 46288, "token": "PID", "merges": "P ID", "raw_count": 253734, "count": 253734, "decode_str": "PID"} -{"id": 2524, "token": "ilon", "merges": "il on", "raw_count": 21220, "count": 253767, "decode_str": "ilon"} -{"id": 5914, "token": "kin", "merges": "k in", "raw_count": 242853, "count": 253819, "decode_str": "kin"} -{"id": 12312, "token": "gov", "merges": "g ov", "raw_count": 253895, "count": 253895, "decode_str": "gov"} -{"id": 54129, "token": "\u00e9\u0123\u0133", "merges": "\u00e9\u0123 \u0133", "raw_count": 253939, "count": 253939, "decode_str": "\u9051"} -{"id": 18734, "token": "\u0120tok", "merges": "\u0120to k", "raw_count": 55158, "count": 253981, "decode_str": " tok"} -{"id": 34561, "token": "Batch", "merges": "B atch", "raw_count": 254126, "count": 254126, "decode_str": "Batch"} -{"id": 3862, "token": "\u0120broad", "merges": "\u0120bro ad", "raw_count": 106789, "count": 254164, "decode_str": " broad"} -{"id": 27820, "token": "809", "merges": "80 9", "raw_count": 254166, "count": 254166, "decode_str": "809"} -{"id": 3092, "token": "\u0120introdu", "merges": "\u0120int rodu", "raw_count": 3257, "count": 254210, "decode_str": " introdu"} -{"id": 20373, "token": "386", "merges": "38 6", "raw_count": 254219, "count": 254219, "decode_str": "386"} -{"id": 20893, "token": "\u0120logging", "merges": "\u0120log ging", "raw_count": 254250, "count": 254250, "decode_str": " logging"} -{"id": 23714, "token": "uniform", "merges": "un iform", "raw_count": 254261, "count": 254261, "decode_str": "uniform"} -{"id": 15383, "token": "Black", "merges": "Bl ack", "raw_count": 254283, "count": 254283, "decode_str": "Black"} -{"id": 51227, "token": "\u00e5\u0140\u0143", "merges": "\u00e5\u0140 \u0143", "raw_count": 254286, "count": 254286, "decode_str": "\u57ad"} -{"id": 47916, "token": "']))", "merges": "'] ))", "raw_count": 254315, "count": 254315, "decode_str": "']))"} -{"id": 4317, "token": "ees", "merges": "e es", "raw_count": 72653, "count": 254330, "decode_str": "ees"} -{"id": 2834, "token": "\u0120difficult", "merges": "\u0120diff icult", "raw_count": 143165, "count": 254383, "decode_str": " difficult"} -{"id": 7368, "token": "\u0120cluster", "merges": "\u0120clust er", "raw_count": 254434, "count": 254434, "decode_str": " cluster"} -{"id": 15353, "token": "gate", "merges": "g ate", "raw_count": 254442, "count": 254442, "decode_str": "gate"} -{"id": 15311, "token": "rieve", "merges": "rie ve", "raw_count": 146671, "count": 254716, "decode_str": "rieve"} -{"id": 7818, "token": "ructure", "merges": "ruct ure", "raw_count": 10550, "count": 254839, "decode_str": "ructure"} -{"id": 19998, "token": "Player", "merges": "Pl ayer", "raw_count": 254900, "count": 254900, "decode_str": "Player"} -{"id": 11964, "token": "hour", "merges": "h our", "raw_count": 254931, "count": 254931, "decode_str": "hour"} -{"id": 2999, "token": "\u0120appl", "merges": "\u0120app l", "raw_count": 2001, "count": 255108, "decode_str": " appl"} -{"id": 2043, "token": "begin", "merges": "b egin", "raw_count": 255122, "count": 255122, "decode_str": "begin"} -{"id": 53885, "token": "\u00e8\u00b0\u00aa", "merges": "\u00e8\u00b0 \u00aa", "raw_count": 255187, "count": 255187, "decode_str": "\u8c2a"} -{"id": 3807, "token": "\u0120und", "merges": "\u0120un d", "raw_count": 194985, "count": 255245, "decode_str": " und"} -{"id": 1850, "token": "\u0120den", "merges": "\u0120d en", "raw_count": 124230, "count": 255280, "decode_str": " den"} -{"id": 11212, "token": "Sign", "merges": "S ign", "raw_count": 111348, "count": 255372, "decode_str": "Sign"} -{"id": 28209, "token": "271", "merges": "27 1", "raw_count": 255405, "count": 255405, "decode_str": "271"} -{"id": 51007, "token": "\u00e5\u0133\u00b2", "merges": "\u00e5\u0133 \u00b2", "raw_count": 255407, "count": 255407, "decode_str": "\u5472"} -{"id": 51174, "token": "\u00e5\u013d\u00bf", "merges": "\u00e5\u013d \u00bf", "raw_count": 255434, "count": 255434, "decode_str": "\u56ff"} -{"id": 2432, "token": "\u0120vir", "merges": "\u0120v ir", "raw_count": 15620, "count": 255521, "decode_str": " vir"} -{"id": 4371, "token": "fort", "merges": "f ort", "raw_count": 133964, "count": 255577, "decode_str": "fort"} -{"id": 7217, "token": "\u0120violence", "merges": "\u0120viol ence", "raw_count": 255686, "count": 255686, "decode_str": " violence"} -{"id": 9189, "token": "\u0120facilities", "merges": "\u0120fac ilities", "raw_count": 255694, "count": 255694, "decode_str": " facilities"} -{"id": 5021, "token": "ella", "merges": "ell a", "raw_count": 229515, "count": 255695, "decode_str": "ella"} -{"id": 3237, "token": "\u0120problems", "merges": "\u0120proble ms", "raw_count": 255774, "count": 255774, "decode_str": " problems"} -{"id": 36817, "token": "sentence", "merges": "sent ence", "raw_count": 255788, "count": 255788, "decode_str": "sentence"} -{"id": 9486, "token": "private", "merges": "p rivate", "raw_count": 255791, "count": 255791, "decode_str": "private"} -{"id": 10064, "token": "auss", "merges": "aus s", "raw_count": 75354, "count": 255999, "decode_str": "auss"} -{"id": 2624, "token": "\u0120cut", "merges": "\u0120c ut", "raw_count": 153049, "count": 256031, "decode_str": " cut"} -{"id": 7288, "token": "\u012055", "merges": "\u01205 5", "raw_count": 256049, "count": 256049, "decode_str": " 55"} -{"id": 2988, "token": "uly", "merges": "u ly", "raw_count": 185019, "count": 256161, "decode_str": "uly"} -{"id": 2334, "token": "\u0120caus", "merges": "\u0120c aus", "raw_count": 1993, "count": 256187, "decode_str": " caus"} -{"id": 22621, "token": "live", "merges": "l ive", "raw_count": 256189, "count": 256189, "decode_str": "live"} -{"id": 24176, "token": "heng", "merges": "hen g", "raw_count": 256233, "count": 256233, "decode_str": "heng"} -{"id": 3676, "token": "\u0120deep", "merges": "\u0120de ep", "raw_count": 213755, "count": 256299, "decode_str": " deep"} -{"id": 51262, "token": "\u00e5\u00a2\u0134", "merges": "\u00e5\u00a2 \u0134", "raw_count": 256357, "count": 256357, "decode_str": "\u5892"} -{"id": 12078, "token": "\u0120invalid", "merges": "\u0120inval id", "raw_count": 256470, "count": 256470, "decode_str": " invalid"} -{"id": 5745, "token": "\u0120sav", "merges": "\u0120s av", "raw_count": 30401, "count": 256501, "decode_str": " sav"} -{"id": 19428, "token": "prep", "merges": "pre p", "raw_count": 63338, "count": 256501, "decode_str": "prep"} -{"id": 2709, "token": "\u0120multiple", "merges": "\u0120mult iple", "raw_count": 256506, "count": 256506, "decode_str": " multiple"} -{"id": 27208, "token": "FX", "merges": "F X", "raw_count": 256538, "count": 256538, "decode_str": "FX"} -{"id": 7540, "token": "iples", "merges": "i ples", "raw_count": 17014, "count": 256632, "decode_str": "iples"} -{"id": 10656, "token": "\u0120administrative", "merges": "\u0120administr ative", "raw_count": 256670, "count": 256670, "decode_str": " administrative"} -{"id": 6286, "token": "sible", "merges": "s ible", "raw_count": 58725, "count": 256676, "decode_str": "sible"} -{"id": 6951, "token": "\u0120chair", "merges": "\u0120ch air", "raw_count": 146366, "count": 256732, "decode_str": " chair"} -{"id": 4081, "token": "\u0120proposed", "merges": "\u0120propos ed", "raw_count": 256772, "count": 256772, "decode_str": " proposed"} -{"id": 52029, "token": "\u00e6\u0134\u0127", "merges": "\u00e6\u0134 \u0127", "raw_count": 256796, "count": 256796, "decode_str": "\u6485"} -{"id": 13194, "token": "\u0120execute", "merges": "\u0120exec ute", "raw_count": 256887, "count": 256887, "decode_str": " execute"} -{"id": 6840, "token": "aked", "merges": "ak ed", "raw_count": 234441, "count": 256915, "decode_str": "aked"} -{"id": 12944, "token": "SV", "merges": "S V", "raw_count": 250942, "count": 256926, "decode_str": "SV"} -{"id": 12404, "token": "blem", "merges": "ble m", "raw_count": 12202, "count": 256933, "decode_str": "blem"} -{"id": 16856, "token": "oco", "merges": "oc o", "raw_count": 256081, "count": 256979, "decode_str": "oco"} -{"id": 5519, "token": "icks", "merges": "ic ks", "raw_count": 195259, "count": 257042, "decode_str": "icks"} -{"id": 23939, "token": "multi", "merges": "mult i", "raw_count": 257066, "count": 257066, "decode_str": "multi"} -{"id": 25966, "token": "route", "merges": "r oute", "raw_count": 257113, "count": 257113, "decode_str": "route"} -{"id": 8200, "token": "**,", "merges": "** ,", "raw_count": 254877, "count": 257221, "decode_str": "**,"} -{"id": 16599, "token": "cross", "merges": "c ross", "raw_count": 248281, "count": 257299, "decode_str": "cross"} -{"id": 52562, "token": "\u00e6\u00b4\u00ae", "merges": "\u00e6\u00b4 \u00ae", "raw_count": 257299, "count": 257299, "decode_str": "\u6d2e"} -{"id": 52042, "token": "\u00e6\u0134\u00b5", "merges": "\u00e6\u0134 \u00b5", "raw_count": 257309, "count": 257309, "decode_str": "\u64b5"} -{"id": 19512, "token": "Layer", "merges": "L ayer", "raw_count": 257362, "count": 257362, "decode_str": "Layer"} -{"id": 32785, "token": "aq", "merges": "a q", "raw_count": 257385, "count": 257385, "decode_str": "aq"} -{"id": 33522, "token": "yaml", "merges": "y aml", "raw_count": 257394, "count": 257394, "decode_str": "yaml"} -{"id": 54505, "token": "\u00e9\u00aa\u013e", "merges": "\u00e9\u00aa \u013e", "raw_count": 257401, "count": 257401, "decode_str": "\u9a9c"} -{"id": 6340, "token": "uate", "merges": "u ate", "raw_count": 40436, "count": 257505, "decode_str": "uate"} -{"id": 14305, "token": "SY", "merges": "S Y", "raw_count": 209820, "count": 257572, "decode_str": "SY"} -{"id": 2687, "token": "\u0120dam", "merges": "\u0120d am", "raw_count": 34328, "count": 257597, "decode_str": " dam"} -{"id": 24693, "token": "configuration", "merges": "config uration", "raw_count": 257724, "count": 257724, "decode_str": "configuration"} -{"id": 9671, "token": "Default", "merges": "Def ault", "raw_count": 221702, "count": 257781, "decode_str": "Default"} -{"id": 10175, "token": "\u0120rows", "merges": "\u0120row s", "raw_count": 257816, "count": 257816, "decode_str": " rows"} -{"id": 14107, "token": "syn", "merges": "s yn", "raw_count": 210092, "count": 257847, "decode_str": "syn"} -{"id": 3940, "token": "\u0120cand", "merges": "\u0120c and", "raw_count": 24583, "count": 257895, "decode_str": " cand"} -{"id": 48937, "token": "ftime", "merges": "ft ime", "raw_count": 258006, "count": 258006, "decode_str": "ftime"} -{"id": 2335, "token": "\u0120took", "merges": "\u0120to ok", "raw_count": 258014, "count": 258014, "decode_str": " took"} -{"id": 53029, "token": "\u00e7\u013f\u00a8", "merges": "\u00e7\u013f \u00a8", "raw_count": 258106, "count": 258106, "decode_str": "\u7768"} -{"id": 21497, "token": "andid", "merges": "and id", "raw_count": 11138, "count": 258117, "decode_str": "andid"} -{"id": 50508, "token": "\u00e4\u00bb\u0141", "merges": "\u00e4\u00bb \u0141", "raw_count": 258118, "count": 258118, "decode_str": "\u4edf"} -{"id": 25139, "token": "378", "merges": "37 8", "raw_count": 258125, "count": 258125, "decode_str": "378"} -{"id": 51136, "token": "\u00e5\u013b\u012e", "merges": "\u00e5\u013b \u012e", "raw_count": 258163, "count": 258163, "decode_str": "\u564c"} -{"id": 15122, "token": "OWN", "merges": "OW N", "raw_count": 64764, "count": 258222, "decode_str": "OWN"} -{"id": 31090, "token": "Face", "merges": "F ace", "raw_count": 258226, "count": 258226, "decode_str": "Face"} -{"id": 22412, "token": "deep", "merges": "de ep", "raw_count": 258227, "count": 258227, "decode_str": "deep"} -{"id": 29960, "token": "worker", "merges": "work er", "raw_count": 258318, "count": 258318, "decode_str": "worker"} -{"id": 33722, "token": "missing", "merges": "miss ing", "raw_count": 258335, "count": 258335, "decode_str": "missing"} -{"id": 3894, "token": "\u0120share", "merges": "\u0120sh are", "raw_count": 235666, "count": 258395, "decode_str": " share"} -{"id": 7990, "token": "\u0120scope", "merges": "\u0120sc ope", "raw_count": 258491, "count": 258491, "decode_str": " scope"} -{"id": 8893, "token": "Version", "merges": "V ersion", "raw_count": 258605, "count": 258605, "decode_str": "Version"} -{"id": 52147, "token": "\u00e6\u013a\u00b6", "merges": "\u00e6\u013a \u00b6", "raw_count": 258743, "count": 258743, "decode_str": "\u6636"} -{"id": 4288, "token": "\u0120travel", "merges": "\u0120tra vel", "raw_count": 201834, "count": 258779, "decode_str": " travel"} -{"id": 12361, "token": "namespace", "merges": "names pace", "raw_count": 258876, "count": 258876, "decode_str": "namespace"} -{"id": 39055, "token": "updated", "merges": "up dated", "raw_count": 258924, "count": 258924, "decode_str": "updated"} -{"id": 53245, "token": "\u00e7\u00ae\u00a9", "merges": "\u00e7\u00ae \u00a9", "raw_count": 259142, "count": 259142, "decode_str": "\u7ba9"} -{"id": 20133, "token": "Master", "merges": "M aster", "raw_count": 259151, "count": 259151, "decode_str": "Master"} -{"id": 10448, "token": "pie", "merges": "p ie", "raw_count": 50209, "count": 259160, "decode_str": "pie"} -{"id": 6133, "token": "ilit", "merges": "il it", "raw_count": 27685, "count": 259203, "decode_str": "ilit"} -{"id": 10756, "token": "\u0120dialog", "merges": "\u0120d ialog", "raw_count": 93870, "count": 259205, "decode_str": " dialog"} -{"id": 19287, "token": "Pool", "merges": "P ool", "raw_count": 259210, "count": 259210, "decode_str": "Pool"} -{"id": 13998, "token": "sun", "merges": "s un", "raw_count": 247351, "count": 259269, "decode_str": "sun"} -{"id": 27174, "token": "('.", "merges": "(' .", "raw_count": 259450, "count": 259450, "decode_str": "('."} -{"id": 3258, "token": "astic", "merges": "ast ic", "raw_count": 95827, "count": 259496, "decode_str": "astic"} -{"id": 7134, "token": "\u0120discrim", "merges": "\u0120disc rim", "raw_count": 27640, "count": 259503, "decode_str": " discrim"} -{"id": 18507, "token": "Matrix", "merges": "Mat rix", "raw_count": 259524, "count": 259524, "decode_str": "Matrix"} -{"id": 4002, "token": "ille", "merges": "il le", "raw_count": 145115, "count": 259537, "decode_str": "ille"} -{"id": 53854, "token": "\u00e8\u00b0\u0126", "merges": "\u00e8\u00b0 \u0126", "raw_count": 259588, "count": 259588, "decode_str": "\u8c04"} -{"id": 4706, "token": "\u0120sec", "merges": "\u0120se c", "raw_count": 90828, "count": 259729, "decode_str": " sec"} -{"id": 7381, "token": "ko", "merges": "k o", "raw_count": 249451, "count": 259801, "decode_str": "ko"} -{"id": 8391, "token": "rehens", "merges": "rehen s", "raw_count": 14322, "count": 259805, "decode_str": "rehens"} -{"id": 2892, "token": "\u0120history", "merges": "\u0120hist ory", "raw_count": 259826, "count": 259826, "decode_str": " history"} -{"id": 3707, "token": "\u0120except", "merges": "\u0120ex cept", "raw_count": 125024, "count": 259945, "decode_str": " except"} -{"id": 19479, "token": "\u0120\"-", "merges": "\u0120\" -", "raw_count": 259970, "count": 259970, "decode_str": " \"-"} -{"id": 13408, "token": "Title", "merges": "T itle", "raw_count": 259976, "count": 259976, "decode_str": "Title"} -{"id": 15736, "token": "fox", "merges": "f ox", "raw_count": 241891, "count": 259980, "decode_str": "fox"} -{"id": 5746, "token": "arant", "merges": "ar ant", "raw_count": 36769, "count": 259982, "decode_str": "arant"} -{"id": 17084, "token": "\u0120strengthen", "merges": "\u0120streng then", "raw_count": 197566, "count": 260073, "decode_str": " strengthen"} -{"id": 3332, "token": "\u0120recent", "merges": "\u0120rec ent", "raw_count": 260111, "count": 260111, "decode_str": " recent"} -{"id": 2708, "token": "\u0120below", "merges": "\u0120bel ow", "raw_count": 260203, "count": 260203, "decode_str": " below"} -{"id": 16490, "token": "Ma", "merges": "M a", "raw_count": 260205, "count": 260205, "decode_str": "Ma"} -{"id": 16712, "token": "pub", "merges": "p ub", "raw_count": 260225, "count": 260225, "decode_str": "pub"} -{"id": 3941, "token": "oul", "merges": "ou l", "raw_count": 189051, "count": 260264, "decode_str": "oul"} -{"id": 8952, "token": "ali", "merges": "al i", "raw_count": 258735, "count": 260310, "decode_str": "ali"} -{"id": 4611, "token": "ato", "merges": "at o", "raw_count": 244864, "count": 260313, "decode_str": "ato"} -{"id": 3827, "token": "ellow", "merges": "ell ow", "raw_count": 70562, "count": 260314, "decode_str": "ellow"} -{"id": 19224, "token": "Dig", "merges": "D ig", "raw_count": 118142, "count": 260315, "decode_str": "Dig"} -{"id": 12412, "token": "High", "merges": "H igh", "raw_count": 245389, "count": 260318, "decode_str": "High"} -{"id": 1996, "token": "\u0120later", "merges": "\u0120l ater", "raw_count": 251967, "count": 260335, "decode_str": " later"} -{"id": 47557, "token": "governmental", "merges": "government al", "raw_count": 260378, "count": 260378, "decode_str": "governmental"} -{"id": 54461, "token": "\u00e9\u00a2\u00a6", "merges": "\u00e9\u00a2 \u00a6", "raw_count": 260417, "count": 260417, "decode_str": "\u98a6"} -{"id": 4616, "token": "\u0120transport", "merges": "\u0120trans port", "raw_count": 185430, "count": 260455, "decode_str": " transport"} -{"id": 8175, "token": "ottom", "merges": "ott om", "raw_count": 1510, "count": 260534, "decode_str": "ottom"} -{"id": 12225, "token": "\u0120meetings", "merges": "\u0120meet ings", "raw_count": 260603, "count": 260603, "decode_str": " meetings"} -{"id": 4821, "token": "\u0120continued", "merges": "\u0120contin ued", "raw_count": 260621, "count": 260621, "decode_str": " continued"} -{"id": 52295, "token": "\u00e6\u00a1\u0123", "merges": "\u00e6\u00a1 \u0123", "raw_count": 260678, "count": 260678, "decode_str": "\u6841"} -{"id": 1276, "token": "What", "merges": "W hat", "raw_count": 260702, "count": 260702, "decode_str": "What"} -{"id": 1733, "token": "\u0120mot", "merges": "\u0120m ot", "raw_count": 25507, "count": 260711, "decode_str": " mot"} -{"id": 2416, "token": "\u0120writ", "merges": "\u0120w rit", "raw_count": 20663, "count": 260808, "decode_str": " writ"} -{"id": 19161, "token": "platform", "merges": "pl atform", "raw_count": 260840, "count": 260840, "decode_str": "platform"} -{"id": 6500, "token": "\u0120equipment", "merges": "\u0120equ ipment", "raw_count": 260846, "count": 260846, "decode_str": " equipment"} -{"id": 53651, "token": "\u00e8\u012d\u00a1", "merges": "\u00e8\u012d \u00a1", "raw_count": 260852, "count": 260852, "decode_str": "\u82e1"} -{"id": 30606, "token": "\u0120conn", "merges": "\u0120con n", "raw_count": 260855, "count": 260855, "decode_str": " conn"} -{"id": 4390, "token": "\u0120currently", "merges": "\u0120current ly", "raw_count": 260925, "count": 260925, "decode_str": " currently"} -{"id": 4422, "token": "\u0120website", "merges": "\u0120webs ite", "raw_count": 260926, "count": 260926, "decode_str": " website"} -{"id": 14930, "token": "olver", "merges": "ol ver", "raw_count": 239507, "count": 261025, "decode_str": "olver"} -{"id": 8101, "token": "nel", "merges": "n el", "raw_count": 55540, "count": 261061, "decode_str": "nel"} -{"id": 2963, "token": "\u0120po", "merges": "\u0120p o", "raw_count": 98951, "count": 261072, "decode_str": " po"} -{"id": 2592, "token": "sigma", "merges": "s igma", "raw_count": 261080, "count": 261080, "decode_str": "sigma"} -{"id": 22566, "token": "added", "merges": "add ed", "raw_count": 261090, "count": 261090, "decode_str": "added"} -{"id": 26560, "token": "261", "merges": "26 1", "raw_count": 261093, "count": 261093, "decode_str": "261"} -{"id": 14576, "token": "ea", "merges": "e a", "raw_count": 261112, "count": 261112, "decode_str": "ea"} -{"id": 17589, "token": "MEM", "merges": "M EM", "raw_count": 261152, "count": 261152, "decode_str": "MEM"} -{"id": 7344, "token": "\u0120conflict", "merges": "\u0120conf lict", "raw_count": 261153, "count": 261153, "decode_str": " conflict"} -{"id": 15268, "token": "Stack", "merges": "St ack", "raw_count": 259473, "count": 261172, "decode_str": "Stack"} -{"id": 25671, "token": "273", "merges": "27 3", "raw_count": 261263, "count": 261263, "decode_str": "273"} -{"id": 1469, "token": "\u0120going", "merges": "\u0120go ing", "raw_count": 261276, "count": 261276, "decode_str": " going"} -{"id": 11814, "token": "background", "merges": "back ground", "raw_count": 261304, "count": 261304, "decode_str": "background"} -{"id": 1652, "token": "\u0120little", "merges": "\u0120l ittle", "raw_count": 261316, "count": 261316, "decode_str": " little"} -{"id": 4471, "token": "\u0120multi", "merges": "\u0120mult i", "raw_count": 184619, "count": 261354, "decode_str": " multi"} -{"id": 14836, "token": "bd", "merges": "b d", "raw_count": 261392, "count": 261392, "decode_str": "bd"} -{"id": 5464, "token": "ette", "merges": "et te", "raw_count": 209507, "count": 261425, "decode_str": "ette"} -{"id": 2998, "token": "pecially", "merges": "pec ially", "raw_count": 2316, "count": 261436, "decode_str": "pecially"} -{"id": 16217, "token": "exper", "merges": "ex per", "raw_count": 188893, "count": 261466, "decode_str": "exper"} -{"id": 7164, "token": "\u0120raise", "merges": "\u0120ra ise", "raw_count": 261499, "count": 261499, "decode_str": " raise"} -{"id": 52565, "token": "\u00e6\u00b4\u00b5", "merges": "\u00e6\u00b4 \u00b5", "raw_count": 261651, "count": 261651, "decode_str": "\u6d35"} -{"id": 17813, "token": "\u0120validate", "merges": "\u0120valid ate", "raw_count": 261660, "count": 261660, "decode_str": " validate"} -{"id": 22426, "token": ":'", "merges": ": '", "raw_count": 261662, "count": 261662, "decode_str": ":'"} -{"id": 5669, "token": "\u0120insert", "merges": "\u0120ins ert", "raw_count": 184196, "count": 261663, "decode_str": " insert"} -{"id": 7514, "token": "\u0120concerned", "merges": "\u0120concern ed", "raw_count": 261760, "count": 261760, "decode_str": " concerned"} -{"id": 51006, "token": "\u00e5\u0133\u00b1", "merges": "\u00e5\u0133 \u00b1", "raw_count": 261813, "count": 261813, "decode_str": "\u5471"} -{"id": 8749, "token": "\u0120register", "merges": "\u0120reg ister", "raw_count": 248648, "count": 261817, "decode_str": " register"} -{"id": 6287, "token": "\u0120loop", "merges": "\u0120lo op", "raw_count": 261830, "count": 261830, "decode_str": " loop"} -{"id": 25676, "token": "284", "merges": "28 4", "raw_count": 261965, "count": 261965, "decode_str": "284"} -{"id": 16082, "token": "Jack", "merges": "J ack", "raw_count": 197614, "count": 262009, "decode_str": "Jack"} -{"id": 10788, "token": "arse", "merges": "ar se", "raw_count": 175654, "count": 262017, "decode_str": "arse"} -{"id": 10413, "token": "eping", "merges": "ep ing", "raw_count": 10048, "count": 262092, "decode_str": "eping"} -{"id": 27391, "token": "branch", "merges": "br anch", "raw_count": 262131, "count": 262131, "decode_str": "branch"} -{"id": 33008, "token": "provider", "merges": "prov ider", "raw_count": 262145, "count": 262145, "decode_str": "provider"} -{"id": 4381, "token": "\u0120neigh", "merges": "\u0120ne igh", "raw_count": 9812, "count": 262180, "decode_str": " neigh"} -{"id": 9009, "token": "\u0120implemented", "merges": "\u0120implement ed", "raw_count": 262349, "count": 262349, "decode_str": " implemented"} -{"id": 30612, "token": "JD", "merges": "J D", "raw_count": 262372, "count": 262372, "decode_str": "JD"} -{"id": 4046, "token": "attle", "merges": "att le", "raw_count": 184150, "count": 262422, "decode_str": "attle"} -{"id": 31485, "token": "cov", "merges": "c ov", "raw_count": 262444, "count": 262444, "decode_str": "cov"} -{"id": 12097, "token": "\u0120patch", "merges": "\u0120pat ch", "raw_count": 262445, "count": 262445, "decode_str": " patch"} -{"id": 2689, "token": "oph", "merges": "op h", "raw_count": 147664, "count": 262588, "decode_str": "oph"} -{"id": 1780, "token": "\u0120Ar", "merges": "\u0120A r", "raw_count": 76644, "count": 262636, "decode_str": " Ar"} -{"id": 8337, "token": "pet", "merges": "p et", "raw_count": 181133, "count": 262657, "decode_str": "pet"} -{"id": 4662, "token": "rick", "merges": "ric k", "raw_count": 153301, "count": 262660, "decode_str": "rick"} -{"id": 19258, "token": "Light", "merges": "L ight", "raw_count": 262710, "count": 262710, "decode_str": "Light"} -{"id": 31062, "token": "sched", "merges": "sc hed", "raw_count": 262731, "count": 262731, "decode_str": "sched"} -{"id": 37691, "token": "MH", "merges": "M H", "raw_count": 262773, "count": 262773, "decode_str": "MH"} -{"id": 4822, "token": "\u0120collect", "merges": "\u0120col lect", "raw_count": 129760, "count": 262832, "decode_str": " collect"} -{"id": 15125, "token": "emon", "merges": "em on", "raw_count": 257658, "count": 262853, "decode_str": "emon"} -{"id": 6451, "token": "ani", "merges": "an i", "raw_count": 256205, "count": 262865, "decode_str": "ani"} -{"id": 28486, "token": "repos", "merges": "re pos", "raw_count": 85573, "count": 262925, "decode_str": "repos"} -{"id": 53998, "token": "\u00e8\u00b7\u013d", "merges": "\u00e8\u00b7 \u013d", "raw_count": 262942, "count": 262942, "decode_str": "\u8ddb"} -{"id": 14932, "token": "\u0120reset", "merges": "\u0120res et", "raw_count": 262946, "count": 262946, "decode_str": " reset"} -{"id": 8667, "token": "\u0120monitoring", "merges": "\u0120monitor ing", "raw_count": 262970, "count": 262970, "decode_str": " monitoring"} -{"id": 1605, "token": "\u0120De", "merges": "\u0120D e", "raw_count": 118528, "count": 262992, "decode_str": " De"} -{"id": 7589, "token": "ju", "merges": "j u", "raw_count": 259822, "count": 263036, "decode_str": "ju"} -{"id": 9492, "token": "rh", "merges": "r h", "raw_count": 255430, "count": 263075, "decode_str": "rh"} -{"id": 18346, "token": "?:", "merges": "? :", "raw_count": 249477, "count": 263190, "decode_str": "?:"} -{"id": 2996, "token": "iting", "merges": "it ing", "raw_count": 124964, "count": 263233, "decode_str": "iting"} -{"id": 21164, "token": "Creat", "merges": "C reat", "raw_count": 214353, "count": 263281, "decode_str": "Creat"} -{"id": 4559, "token": "\u0120Mod", "merges": "\u0120M od", "raw_count": 53380, "count": 263308, "decode_str": " Mod"} -{"id": 4879, "token": "\u0120noted", "merges": "\u0120not ed", "raw_count": 263388, "count": 263388, "decode_str": " noted"} -{"id": 7389, "token": "estic", "merges": "est ic", "raw_count": 25085, "count": 263411, "decode_str": "estic"} -{"id": 29681, "token": "DN", "merges": "D N", "raw_count": 263430, "count": 263430, "decode_str": "DN"} -{"id": 16282, "token": "Session", "merges": "S ession", "raw_count": 263514, "count": 263514, "decode_str": "Session"} -{"id": 9061, "token": "\u0120authorities", "merges": "\u0120author ities", "raw_count": 263531, "count": 263531, "decode_str": " authorities"} -{"id": 54133, "token": "\u00e9\u0123\u00a2", "merges": "\u00e9\u0123 \u00a2", "raw_count": 263564, "count": 263564, "decode_str": "\u9062"} -{"id": 4894, "token": "omb", "merges": "om b", "raw_count": 209320, "count": 263584, "decode_str": "omb"} -{"id": 9152, "token": "android", "merges": "and roid", "raw_count": 263615, "count": 263615, "decode_str": "android"} -{"id": 11625, "token": "oves", "merges": "ov es", "raw_count": 257708, "count": 263876, "decode_str": "oves"} -{"id": 25250, "token": "percent", "merges": "per cent", "raw_count": 263926, "count": 263926, "decode_str": "percent"} -{"id": 27385, "token": "331", "merges": "33 1", "raw_count": 263993, "count": 263993, "decode_str": "331"} -{"id": 8460, "token": "\u0120reform", "merges": "\u0120re form", "raw_count": 207108, "count": 264024, "decode_str": " reform"} -{"id": 4849, "token": "\u0120collection", "merges": "\u0120col lection", "raw_count": 264048, "count": 264048, "decode_str": " collection"} -{"id": 2740, "token": "\u0120break", "merges": "\u0120bre ak", "raw_count": 159702, "count": 264054, "decode_str": " break"} -{"id": 7305, "token": "acks", "merges": "ack s", "raw_count": 146884, "count": 264153, "decode_str": "acks"} -{"id": 8754, "token": "wa", "merges": "w a", "raw_count": 251916, "count": 264369, "decode_str": "wa"} -{"id": 19583, "token": "simple", "merges": "sim ple", "raw_count": 264379, "count": 264379, "decode_str": "simple"} -{"id": 24854, "token": "406", "merges": "40 6", "raw_count": 264500, "count": 264500, "decode_str": "406"} -{"id": 3201, "token": "urch", "merges": "ur ch", "raw_count": 40806, "count": 264571, "decode_str": "urch"} -{"id": 17764, "token": "stock", "merges": "st ock", "raw_count": 264656, "count": 264656, "decode_str": "stock"} -{"id": 2495, "token": "\u0120risk", "merges": "\u0120r isk", "raw_count": 258851, "count": 264698, "decode_str": " risk"} -{"id": 6864, "token": "\u0120depth", "merges": "\u0120dep th", "raw_count": 252869, "count": 264739, "decode_str": " depth"} -{"id": 7391, "token": "olt", "merges": "ol t", "raw_count": 101299, "count": 264777, "decode_str": "olt"} -{"id": 2964, "token": "\u00d1\u0125", "merges": "\u00d1 \u0125", "raw_count": 85454, "count": 264800, "decode_str": "\u0443"} -{"id": 53279, "token": "\u00e7\u00b3\u0127", "merges": "\u00e7\u00b3 \u0127", "raw_count": 264881, "count": 264881, "decode_str": "\u7cc5"} -{"id": 8551, "token": "000000", "merges": "0000 00", "raw_count": 222639, "count": 264892, "decode_str": "000000"} -{"id": 5718, "token": "\u0120storage", "merges": "\u0120st orage", "raw_count": 264979, "count": 264979, "decode_str": " storage"} -{"id": 3772, "token": "\u0120autom", "merges": "\u0120aut om", "raw_count": 22720, "count": 265210, "decode_str": " autom"} -{"id": 10611, "token": "\u0120URL", "merges": "\u0120U RL", "raw_count": 242486, "count": 265242, "decode_str": " URL"} -{"id": 4538, "token": "Sec", "merges": "S ec", "raw_count": 143798, "count": 265331, "decode_str": "Sec"} -{"id": 3601, "token": "\u0120screen", "merges": "\u0120sc reen", "raw_count": 246084, "count": 265337, "decode_str": " screen"} -{"id": 9799, "token": "\u00e2\u0136", "merges": "\u00e2 \u0136", "raw_count": 25695, "count": 265343, "decode_str": "\ufffd"} -{"id": 54500, "token": "\u00e9\u00aa\u0132", "merges": "\u00e9\u00aa \u0132", "raw_count": 265447, "count": 265447, "decode_str": "\u9a90"} -{"id": 24257, "token": "334", "merges": "33 4", "raw_count": 265507, "count": 265507, "decode_str": "334"} -{"id": 13780, "token": "OVID", "merges": "OV ID", "raw_count": 260416, "count": 265622, "decode_str": "OVID"} -{"id": 2051, "token": "\u0120App", "merges": "\u0120A pp", "raw_count": 119018, "count": 265633, "decode_str": " App"} -{"id": 2746, "token": "\u0120approach", "merges": "\u0120appro ach", "raw_count": 256022, "count": 265688, "decode_str": " approach"} -{"id": 5851, "token": "AV", "merges": "A V", "raw_count": 211705, "count": 265739, "decode_str": "AV"} -{"id": 7676, "token": "Ref", "merges": "R ef", "raw_count": 215887, "count": 265919, "decode_str": "Ref"} -{"id": 27422, "token": "origin", "merges": "or igin", "raw_count": 266013, "count": 266013, "decode_str": "origin"} -{"id": 22036, "token": "Blue", "merges": "Bl ue", "raw_count": 266049, "count": 266049, "decode_str": "Blue"} -{"id": 54147, "token": "\u00e9\u0124\u012a", "merges": "\u00e9\u0124 \u012a", "raw_count": 266085, "count": 266085, "decode_str": "\u9088"} -{"id": 2891, "token": "\u0120tax", "merges": "\u0120t ax", "raw_count": 168774, "count": 266098, "decode_str": " tax"} -{"id": 3400, "token": "\u0120provides", "merges": "\u0120prov ides", "raw_count": 266188, "count": 266188, "decode_str": " provides"} -{"id": 23953, "token": "\u0120Http", "merges": "\u0120H ttp", "raw_count": 266249, "count": 266249, "decode_str": " Http"} -{"id": 11534, "token": "\u0120folder", "merges": "\u0120f older", "raw_count": 266448, "count": 266448, "decode_str": " folder"} -{"id": 3647, "token": "ishing", "merges": "ish ing", "raw_count": 74978, "count": 266557, "decode_str": "ishing"} -{"id": 13001, "token": "\u0120governments", "merges": "\u0120govern ments", "raw_count": 266610, "count": 266610, "decode_str": " governments"} -{"id": 3367, "token": "\u0120personal", "merges": "\u0120person al", "raw_count": 260461, "count": 266675, "decode_str": " personal"} -{"id": 26906, "token": "503", "merges": "50 3", "raw_count": 266825, "count": 266825, "decode_str": "503"} -{"id": 10987, "token": "Build", "merges": "B uild", "raw_count": 213006, "count": 266918, "decode_str": "Build"} -{"id": 5154, "token": "agon", "merges": "ag on", "raw_count": 233929, "count": 266945, "decode_str": "agon"} -{"id": 3782, "token": "\u0120particularly", "merges": "\u0120particular ly", "raw_count": 267039, "count": 267039, "decode_str": " particularly"} -{"id": 14803, "token": "DF", "merges": "D F", "raw_count": 267080, "count": 267080, "decode_str": "DF"} -{"id": 2080, "token": "\u0120far", "merges": "\u0120f ar", "raw_count": 245217, "count": 267248, "decode_str": " far"} -{"id": 54152, "token": "\u00e9\u0124\u013d", "merges": "\u00e9\u0124 \u013d", "raw_count": 267403, "count": 267403, "decode_str": "\u909b"} -{"id": 1823, "token": "\u0120obt", "merges": "\u0120ob t", "raw_count": 13220, "count": 267410, "decode_str": " obt"} -{"id": 28743, "token": "Research", "merges": "Res earch", "raw_count": 267547, "count": 267547, "decode_str": "Research"} -{"id": 5044, "token": "\u0120basic", "merges": "\u0120bas ic", "raw_count": 267577, "count": 267577, "decode_str": " basic"} -{"id": 53558, "token": "\u00e8\u0129\u012c", "merges": "\u00e8\u0129 \u012c", "raw_count": 267587, "count": 267587, "decode_str": "\u81ca"} -{"id": 14594, "token": "Sun", "merges": "S un", "raw_count": 244046, "count": 267599, "decode_str": "Sun"} -{"id": 4243, "token": "\u0120parts", "merges": "\u0120part s", "raw_count": 267656, "count": 267656, "decode_str": " parts"} -{"id": 9325, "token": "ador", "merges": "ad or", "raw_count": 211583, "count": 267762, "decode_str": "ador"} -{"id": 18717, "token": "KK", "merges": "K K", "raw_count": 267771, "count": 267771, "decode_str": "KK"} -{"id": 25240, "token": "XXXX", "merges": "XX XX", "raw_count": 267842, "count": 267842, "decode_str": "XXXX"} -{"id": 25553, "token": "rules", "merges": "r ules", "raw_count": 267858, "count": 267858, "decode_str": "rules"} -{"id": 52816, "token": "\u00e7\u0130\u00b7", "merges": "\u00e7\u0130 \u00b7", "raw_count": 267886, "count": 267886, "decode_str": "\u73b7"} -{"id": 3740, "token": "\u0120style", "merges": "\u0120st yle", "raw_count": 268016, "count": 268016, "decode_str": " style"} -{"id": 2793, "token": "\u0120experience", "merges": "\u0120exper ience", "raw_count": 268018, "count": 268018, "decode_str": " experience"} -{"id": 8833, "token": "byte", "merges": "by te", "raw_count": 268071, "count": 268071, "decode_str": "byte"} -{"id": 42918, "token": "JavaScript", "merges": "Java Script", "raw_count": 268080, "count": 268080, "decode_str": "JavaScript"} -{"id": 1263, "token": "\u0120study", "merges": "\u0120stud y", "raw_count": 245175, "count": 268107, "decode_str": " study"} -{"id": 5650, "token": "ura", "merges": "ur a", "raw_count": 255290, "count": 268150, "decode_str": "ura"} -{"id": 12915, "token": "inator", "merges": "in ator", "raw_count": 207685, "count": 268179, "decode_str": "inator"} -{"id": 25810, "token": "Micro", "merges": "M icro", "raw_count": 268302, "count": 268302, "decode_str": "Micro"} -{"id": 3949, "token": "\u0120vict", "merges": "\u0120v ict", "raw_count": 24048, "count": 268338, "decode_str": " vict"} -{"id": 51149, "token": "\u00e5\u013b\u00bb", "merges": "\u00e5\u013b \u00bb", "raw_count": 268349, "count": 268349, "decode_str": "\u567b"} -{"id": 1534, "token": "\u0120significant", "merges": "\u0120signific ant", "raw_count": 206602, "count": 268447, "decode_str": " significant"} -{"id": 9867, "token": "Find", "merges": "F ind", "raw_count": 268472, "count": 268472, "decode_str": "Find"} -{"id": 51247, "token": "\u00e5\u0142\u0129", "merges": "\u00e5\u0142 \u0129", "raw_count": 268590, "count": 268590, "decode_str": "\u5807"} -{"id": 5409, "token": "uman", "merges": "um an", "raw_count": 24390, "count": 268640, "decode_str": "uman"} -{"id": 54395, "token": "\u00e9\u013e\u0143", "merges": "\u00e9\u013e \u0143", "raw_count": 268754, "count": 268754, "decode_str": "\u972d"} -{"id": 48413, "token": "targets", "merges": "target s", "raw_count": 268847, "count": 268847, "decode_str": "targets"} -{"id": 17389, "token": "Rich", "merges": "R ich", "raw_count": 87791, "count": 268929, "decode_str": "Rich"} -{"id": 45381, "token": "\u0120'')", "merges": "\u0120' ')", "raw_count": 269063, "count": 269063, "decode_str": " '')"} -{"id": 35572, "token": "AQ", "merges": "A Q", "raw_count": 269150, "count": 269150, "decode_str": "AQ"} -{"id": 5706, "token": "\u0120Att", "merges": "\u0120A tt", "raw_count": 43952, "count": 269300, "decode_str": " Att"} -{"id": 3185, "token": "\u0120instead", "merges": "\u0120inst ead", "raw_count": 269304, "count": 269304, "decode_str": " instead"} -{"id": 8591, "token": "\u0120promote", "merges": "\u0120prom ote", "raw_count": 269395, "count": 269395, "decode_str": " promote"} -{"id": 7007, "token": "\u0120integer", "merges": "\u0120inte ger", "raw_count": 269454, "count": 269454, "decode_str": " integer"} -{"id": 15854, "token": "eno", "merges": "en o", "raw_count": 269461, "count": 269461, "decode_str": "eno"} -{"id": 24724, "token": "262", "merges": "26 2", "raw_count": 269470, "count": 269470, "decode_str": "262"} -{"id": 20888, "token": "ahoo", "merges": "ah oo", "raw_count": 209752, "count": 269555, "decode_str": "ahoo"} -{"id": 23169, "token": "\u0120req", "merges": "\u0120re q", "raw_count": 269583, "count": 269583, "decode_str": " req"} -{"id": 10794, "token": "\u0120inval", "merges": "\u0120inv al", "raw_count": 6272, "count": 269610, "decode_str": " inval"} -{"id": 5432, "token": "itz", "merges": "it z", "raw_count": 130801, "count": 269710, "decode_str": "itz"} -{"id": 21299, "token": "proc", "merges": "pro c", "raw_count": 269725, "count": 269725, "decode_str": "proc"} -{"id": 34418, "token": "],[", "merges": "], [", "raw_count": 269765, "count": 269765, "decode_str": "],["} -{"id": 25008, "token": "356", "merges": "35 6", "raw_count": 269912, "count": 269912, "decode_str": "356"} -{"id": 3681, "token": "amm", "merges": "am m", "raw_count": 155461, "count": 270020, "decode_str": "amm"} -{"id": 3595, "token": "\u0120evalu", "merges": "\u0120eval u", "raw_count": 20269, "count": 270027, "decode_str": " evalu"} -{"id": 52513, "token": "\u00e6\u00b2\u0143", "merges": "\u00e6\u00b2 \u0143", "raw_count": 270127, "count": 270127, "decode_str": "\u6cad"} -{"id": 6931, "token": "\u012039", "merges": "\u01203 9", "raw_count": 270159, "count": 270159, "decode_str": " 39"} -{"id": 7075, "token": "\u0120terror", "merges": "\u0120t error", "raw_count": 16097, "count": 270202, "decode_str": " terror"} -{"id": 35632, "token": "()),", "merges": "() ),", "raw_count": 270245, "count": 270245, "decode_str": "()),"} -{"id": 3724, "token": "Ps", "merges": "P s", "raw_count": 228372, "count": 270250, "decode_str": "Ps"} -{"id": 23705, "token": "observ", "merges": "ob serv", "raw_count": 229056, "count": 270370, "decode_str": "observ"} -{"id": 1598, "token": "ably", "merges": "ab ly", "raw_count": 51957, "count": 270415, "decode_str": "ably"} -{"id": 27632, "token": "805", "merges": "80 5", "raw_count": 270458, "count": 270458, "decode_str": "805"} -{"id": 19371, "token": "\u0120Response", "merges": "\u0120Res ponse", "raw_count": 270574, "count": 270574, "decode_str": " Response"} -{"id": 36302, "token": "verify", "merges": "ver ify", "raw_count": 270646, "count": 270646, "decode_str": "verify"} -{"id": 27591, "token": "******", "merges": "**** **", "raw_count": 270677, "count": 270677, "decode_str": "******"} -{"id": 54266, "token": "\u00e9\u0137\u00b3", "merges": "\u00e9\u0137 \u00b3", "raw_count": 270834, "count": 270834, "decode_str": "\u9573"} -{"id": 7699, "token": "\u0120san", "merges": "\u0120s an", "raw_count": 89547, "count": 270874, "decode_str": " san"} -{"id": 5563, "token": "\u0120mig", "merges": "\u0120m ig", "raw_count": 9691, "count": 270895, "decode_str": " mig"} -{"id": 47205, "token": "Magic", "merges": "M agic", "raw_count": 270902, "count": 270902, "decode_str": "Magic"} -{"id": 53986, "token": "\u00e8\u00b6\u00b8", "merges": "\u00e8\u00b6 \u00b8", "raw_count": 270954, "count": 270954, "decode_str": "\u8db8"} -{"id": 52709, "token": "\u00e7\u0123\u0140", "merges": "\u00e7\u0123 \u0140", "raw_count": 270966, "count": 270966, "decode_str": "\u705e"} -{"id": 3942, "token": "vey", "merges": "ve y", "raw_count": 130864, "count": 270977, "decode_str": "vey"} -{"id": 14375, "token": "ANG", "merges": "AN G", "raw_count": 233403, "count": 271159, "decode_str": "ANG"} -{"id": 31576, "token": "XR", "merges": "X R", "raw_count": 271349, "count": 271349, "decode_str": "XR"} -{"id": 13705, "token": "scription", "merges": "script ion", "raw_count": 198448, "count": 271386, "decode_str": "scription"} -{"id": 52681, "token": "\u00e6\u00ba\u0141", "merges": "\u00e6\u00ba \u0141", "raw_count": 271420, "count": 271420, "decode_str": "\u6e9f"} -{"id": 4074, "token": "ufact", "merges": "uf act", "raw_count": 35244, "count": 271444, "decode_str": "ufact"} -{"id": 51229, "token": "\u00e5\u0141\u0124", "merges": "\u00e5\u0141 \u0124", "raw_count": 271541, "count": 271541, "decode_str": "\u57c2"} -{"id": 11984, "token": "complete", "merges": "comple te", "raw_count": 230873, "count": 271586, "decode_str": "complete"} -{"id": 6942, "token": "Method", "merges": "M ethod", "raw_count": 241438, "count": 271646, "decode_str": "Method"} -{"id": 46238, "token": "Sets", "merges": "S ets", "raw_count": 271718, "count": 271718, "decode_str": "Sets"} -{"id": 20513, "token": "these", "merges": "the se", "raw_count": 271758, "count": 271758, "decode_str": "these"} -{"id": 9714, "token": "tyle", "merges": "ty le", "raw_count": 7570, "count": 272015, "decode_str": "tyle"} -{"id": 11273, "token": "rained", "merges": "ra ined", "raw_count": 241800, "count": 272132, "decode_str": "rained"} -{"id": 4385, "token": "\u0120comment", "merges": "\u0120com ment", "raw_count": 233497, "count": 272207, "decode_str": " comment"} -{"id": 54466, "token": "\u00e9\u00a3\u0137", "merges": "\u00e9\u00a3 \u0137", "raw_count": 272221, "count": 272221, "decode_str": "\u98d5"} -{"id": 3768, "token": "\u0120aw", "merges": "\u0120a w", "raw_count": 59037, "count": 272295, "decode_str": " aw"} -{"id": 22858, "token": "294", "merges": "29 4", "raw_count": 272391, "count": 272391, "decode_str": "294"} -{"id": 20376, "token": "phab", "merges": "ph ab", "raw_count": 23217, "count": 272397, "decode_str": "phab"} -{"id": 11040, "token": "HL", "merges": "H L", "raw_count": 271958, "count": 272450, "decode_str": "HL"} -{"id": 10641, "token": "wr", "merges": "w r", "raw_count": 100020, "count": 272575, "decode_str": "wr"} -{"id": 53391, "token": "\u00e7\u00bc\u013b", "merges": "\u00e7\u00bc \u013b", "raw_count": 272618, "count": 272618, "decode_str": "\u7f19"} -{"id": 6342, "token": "front", "merges": "fr ont", "raw_count": 224933, "count": 272623, "decode_str": "front"} -{"id": 2980, "token": "ening", "merges": "en ing", "raw_count": 137047, "count": 272625, "decode_str": "ening"} -{"id": 50651, "token": "\u00e5\u0123\u00bb", "merges": "\u00e5\u0123 \u00bb", "raw_count": 272683, "count": 272683, "decode_str": "\u507b"} -{"id": 37755, "token": "xp", "merges": "x p", "raw_count": 272699, "count": 272699, "decode_str": "xp"} -{"id": 6792, "token": "rehen", "merges": "re hen", "raw_count": 4205, "count": 272918, "decode_str": "rehen"} -{"id": 52455, "token": "\u00e6\u00b0\u00a6", "merges": "\u00e6\u00b0 \u00a6", "raw_count": 272991, "count": 272991, "decode_str": "\u6c26"} -{"id": 15079, "token": "rev", "merges": "re v", "raw_count": 273085, "count": 273085, "decode_str": "rev"} -{"id": 4152, "token": "band", "merges": "b and", "raw_count": 212333, "count": 273183, "decode_str": "band"} -{"id": 3515, "token": "\u0120running", "merges": "\u0120run ning", "raw_count": 273247, "count": 273247, "decode_str": " running"} -{"id": 2723, "token": "\u0120correspond", "merges": "\u0120cor respond", "raw_count": 32536, "count": 273322, "decode_str": " correspond"} -{"id": 10311, "token": "NOT", "merges": "N OT", "raw_count": 207817, "count": 273331, "decode_str": "NOT"} -{"id": 5601, "token": "\u0120prepar", "merges": "\u0120pre par", "raw_count": 63125, "count": 273540, "decode_str": " prepar"} -{"id": 6836, "token": "ola", "merges": "ol a", "raw_count": 273550, "count": 273604, "decode_str": "ola"} -{"id": 51290, "token": "\u00e5\u00a4\u0136", "merges": "\u00e5\u00a4 \u0136", "raw_count": 273632, "count": 273632, "decode_str": "\u5914"} -{"id": 15090, "token": "MAT", "merges": "M AT", "raw_count": 158725, "count": 273704, "decode_str": "MAT"} -{"id": 53370, "token": "\u00e7\u00bb\u00b6", "merges": "\u00e7\u00bb \u00b6", "raw_count": 273794, "count": 273794, "decode_str": "\u7ef6"} -{"id": 32423, "token": "TCP", "merges": "T CP", "raw_count": 273835, "count": 273835, "decode_str": "TCP"} -{"id": 3470, "token": "\u0120functions", "merges": "\u0120fun ctions", "raw_count": 273981, "count": 273981, "decode_str": " functions"} -{"id": 21830, "token": "resources", "merges": "res ources", "raw_count": 274101, "count": 274101, "decode_str": "resources"} -{"id": 33899, "token": "319", "merges": "3 19", "raw_count": 274106, "count": 274106, "decode_str": "319"} -{"id": 7544, "token": "\u01201999", "merges": "\u012019 99", "raw_count": 274114, "count": 274114, "decode_str": " 1999"} -{"id": 4550, "token": "odies", "merges": "od ies", "raw_count": 27897, "count": 274137, "decode_str": "odies"} -{"id": 37597, "token": "gpu", "merges": "g pu", "raw_count": 274271, "count": 274271, "decode_str": "gpu"} -{"id": 13883, "token": "Position", "merges": "P osition", "raw_count": 274316, "count": 274316, "decode_str": "Position"} -{"id": 11375, "token": "holder", "merges": "h older", "raw_count": 91001, "count": 274346, "decode_str": "holder"} -{"id": 4812, "token": "\u0120internal", "merges": "\u0120inter nal", "raw_count": 274543, "count": 274543, "decode_str": " internal"} -{"id": 13328, "token": "\u0120pars", "merges": "\u0120p ars", "raw_count": 39605, "count": 274563, "decode_str": " pars"} -{"id": 23829, "token": "337", "merges": "33 7", "raw_count": 274569, "count": 274569, "decode_str": "337"} -{"id": 10727, "token": "\u0120FROM", "merges": "\u0120FR OM", "raw_count": 274691, "count": 274691, "decode_str": " FROM"} -{"id": 2363, "token": "\u0120age", "merges": "\u0120a ge", "raw_count": 252939, "count": 274915, "decode_str": " age"} -{"id": 10144, "token": "ropy", "merges": "rop y", "raw_count": 235075, "count": 274982, "decode_str": "ropy"} -{"id": 52418, "token": "\u00e6\u00ae\u0134", "merges": "\u00e6\u00ae \u0134", "raw_count": 275188, "count": 275188, "decode_str": "\u6b92"} -{"id": 25121, "token": "272", "merges": "27 2", "raw_count": 275230, "count": 275230, "decode_str": "272"} -{"id": 3465, "token": "aves", "merges": "av es", "raw_count": 147818, "count": 275271, "decode_str": "aves"} -{"id": 52062, "token": "\u00e6\u0136\u00ab", "merges": "\u00e6\u0136 \u00ab", "raw_count": 275331, "count": 275331, "decode_str": "\u652b"} -{"id": 4006, "token": "bon", "merges": "b on", "raw_count": 172311, "count": 275363, "decode_str": "bon"} -{"id": 2340, "token": "\u0120investig", "merges": "\u0120invest ig", "raw_count": 3200, "count": 275366, "decode_str": " investig"} -{"id": 16896, "token": "^^", "merges": "^ ^", "raw_count": 243844, "count": 275366, "decode_str": "^^"} -{"id": 2889, "token": "\u0120nat", "merges": "\u0120n at", "raw_count": 42728, "count": 275736, "decode_str": " nat"} -{"id": 4840, "token": "\u0120mess", "merges": "\u0120m ess", "raw_count": 36755, "count": 275754, "decode_str": " mess"} -{"id": 30636, "token": "'+", "merges": "' +", "raw_count": 275758, "count": 275758, "decode_str": "'+"} -{"id": 3292, "token": "aving", "merges": "av ing", "raw_count": 62711, "count": 275779, "decode_str": "aving"} -{"id": 7476, "token": "ateral", "merges": "ater al", "raw_count": 19955, "count": 275926, "decode_str": "ateral"} -{"id": 23342, "token": "aaaa", "merges": "aa aa", "raw_count": 92960, "count": 276004, "decode_str": "aaaa"} -{"id": 34315, "token": "WHO", "merges": "WH O", "raw_count": 276064, "count": 276064, "decode_str": "WHO"} -{"id": 1783, "token": "\u0120analysis", "merges": "\u0120anal ysis", "raw_count": 276073, "count": 276073, "decode_str": " analysis"} -{"id": 10588, "token": "Control", "merges": "Cont rol", "raw_count": 255534, "count": 276111, "decode_str": "Control"} -{"id": 10845, "token": "PAR", "merges": "P AR", "raw_count": 202243, "count": 276120, "decode_str": "PAR"} -{"id": 51120, "token": "\u00e5\u0138\u013b", "merges": "\u00e5\u0138 \u013b", "raw_count": 276145, "count": 276145, "decode_str": "\u5599"} -{"id": 51391, "token": "\u00e5\u0143\u00aa", "merges": "\u00e5\u0143 \u00aa", "raw_count": 276292, "count": 276292, "decode_str": "\u5b6a"} -{"id": 18710, "token": "ategy", "merges": "ateg y", "raw_count": 169237, "count": 276417, "decode_str": "ategy"} -{"id": 4638, "token": "rum", "merges": "r um", "raw_count": 177360, "count": 276509, "decode_str": "rum"} -{"id": 9145, "token": "\u0120centre", "merges": "\u0120cent re", "raw_count": 276525, "count": 276525, "decode_str": " centre"} -{"id": 36022, "token": "colors", "merges": "col ors", "raw_count": 276633, "count": 276633, "decode_str": "colors"} -{"id": 38808, "token": "490", "merges": "4 90", "raw_count": 276645, "count": 276645, "decode_str": "490"} -{"id": 8407, "token": "afe", "merges": "a fe", "raw_count": 171154, "count": 276706, "decode_str": "afe"} -{"id": 52821, "token": "\u00e7\u0131\u0127", "merges": "\u00e7\u0131 \u0127", "raw_count": 276739, "count": 276739, "decode_str": "\u73c5"} -{"id": 2844, "token": "cing", "merges": "c ing", "raw_count": 31204, "count": 276822, "decode_str": "cing"} -{"id": 5178, "token": "Big", "merges": "B ig", "raw_count": 275289, "count": 276838, "decode_str": "Big"} -{"id": 7564, "token": "ben", "merges": "b en", "raw_count": 100614, "count": 277008, "decode_str": "ben"} -{"id": 2378, "token": "\u0120once", "merges": "\u0120on ce", "raw_count": 277046, "count": 277046, "decode_str": " once"} -{"id": 2605, "token": "\u0120structure", "merges": "\u0120struct ure", "raw_count": 277104, "count": 277104, "decode_str": " structure"} -{"id": 20936, "token": "operation", "merges": "oper ation", "raw_count": 277294, "count": 277294, "decode_str": "operation"} -{"id": 5247, "token": "lam", "merges": "l am", "raw_count": 264883, "count": 277401, "decode_str": "lam"} -{"id": 17333, "token": "padding", "merges": "p adding", "raw_count": 277489, "count": 277489, "decode_str": "padding"} -{"id": 30122, "token": "\u0120humanitarian", "merges": "\u0120human itarian", "raw_count": 277495, "count": 277495, "decode_str": " humanitarian"} -{"id": 31722, "token": "955", "merges": "95 5", "raw_count": 277572, "count": 277572, "decode_str": "955"} -{"id": 35343, "token": "\"\\", "merges": "\" \\", "raw_count": 277579, "count": 277579, "decode_str": "\"\\"} -{"id": 5855, "token": "\u0120weap", "merges": "\u0120we ap", "raw_count": 295, "count": 277640, "decode_str": " weap"} -{"id": 11718, "token": "016", "merges": "01 6", "raw_count": 277727, "count": 277727, "decode_str": "016"} -{"id": 4234, "token": "acing", "merges": "ac ing", "raw_count": 90666, "count": 277814, "decode_str": "acing"} -{"id": 29917, "token": "361", "merges": "36 1", "raw_count": 277855, "count": 277855, "decode_str": "361"} -{"id": 16420, "token": "rowser", "merges": "row ser", "raw_count": 16722, "count": 277878, "decode_str": "rowser"} -{"id": 16786, "token": "Dialog", "merges": "D ialog", "raw_count": 277911, "count": 277911, "decode_str": "Dialog"} -{"id": 4919, "token": "related", "merges": "rel ated", "raw_count": 272001, "count": 278073, "decode_str": "related"} -{"id": 2266, "token": "\u0120strong", "merges": "\u0120str ong", "raw_count": 178914, "count": 278207, "decode_str": " strong"} -{"id": 21862, "token": "WM", "merges": "W M", "raw_count": 278245, "count": 278245, "decode_str": "WM"} -{"id": 3652, "token": "\u0120building", "merges": "\u0120build ing", "raw_count": 278436, "count": 278436, "decode_str": " building"} -{"id": 6302, "token": "\":\"", "merges": "\": \"", "raw_count": 275004, "count": 278495, "decode_str": "\":\""} -{"id": 13015, "token": "forms", "merges": "form s", "raw_count": 277915, "count": 278536, "decode_str": "forms"} -{"id": 43523, "token": "518", "merges": "5 18", "raw_count": 278592, "count": 278592, "decode_str": "518"} -{"id": 4751, "token": "\u0120fully", "merges": "\u0120ful ly", "raw_count": 278611, "count": 278611, "decode_str": " fully"} -{"id": 51058, "token": "\u00e5\u0135\u012d", "merges": "\u00e5\u0135 \u012d", "raw_count": 278629, "count": 278629, "decode_str": "\u54cb"} -{"id": 2366, "token": "\u0120together", "merges": "\u0120to gether", "raw_count": 278632, "count": 278632, "decode_str": " together"} -{"id": 53762, "token": "\u00e8\u00a7\u0130", "merges": "\u00e8\u00a7 \u0130", "raw_count": 278637, "count": 278637, "decode_str": "\u89ce"} -{"id": 23852, "token": "Peter", "merges": "P eter", "raw_count": 278663, "count": 278663, "decode_str": "Peter"} -{"id": 8763, "token": "\u0120hidden", "merges": "\u0120h idden", "raw_count": 278853, "count": 278853, "decode_str": " hidden"} -{"id": 51985, "token": "\u00e6\u0130\u0129", "merges": "\u00e6\u0130 \u0129", "raw_count": 278900, "count": 278900, "decode_str": "\u6387"} -{"id": 3662, "token": "\u0120answer", "merges": "\u0120answ er", "raw_count": 278979, "count": 278979, "decode_str": " answer"} -{"id": 3908, "token": "\u0120statement", "merges": "\u0120stat ement", "raw_count": 279020, "count": 279020, "decode_str": " statement"} -{"id": 20921, "token": "\u0120ctx", "merges": "\u0120c tx", "raw_count": 279072, "count": 279072, "decode_str": " ctx"} -{"id": 8048, "token": ":\\", "merges": ": \\", "raw_count": 279074, "count": 279074, "decode_str": ":\\"} -{"id": 5345, "token": "\u012037", "merges": "\u01203 7", "raw_count": 279122, "count": 279122, "decode_str": " 37"} -{"id": 7781, "token": "Source", "merges": "S ource", "raw_count": 259188, "count": 279128, "decode_str": "Source"} -{"id": 15658, "token": "component", "merges": "comp onent", "raw_count": 279148, "count": 279148, "decode_str": "component"} -{"id": 19518, "token": "yset", "merges": "ys et", "raw_count": 278922, "count": 279197, "decode_str": "yset"} -{"id": 16880, "token": "Microsoft", "merges": "M icrosoft", "raw_count": 279346, "count": 279346, "decode_str": "Microsoft"} -{"id": 9816, "token": "IND", "merges": "IN D", "raw_count": 151088, "count": 279491, "decode_str": "IND"} -{"id": 4388, "token": "\u0120aim", "merges": "\u0120a im", "raw_count": 88641, "count": 279516, "decode_str": " aim"} -{"id": 47071, "token": "\u0120')", "merges": "\u0120' )", "raw_count": 279605, "count": 279605, "decode_str": " ')"} -{"id": 37556, "token": "QC", "merges": "Q C", "raw_count": 279706, "count": 279706, "decode_str": "QC"} -{"id": 2924, "token": "rown", "merges": "row n", "raw_count": 49642, "count": 279726, "decode_str": "rown"} -{"id": 38859, "token": "Amazon", "merges": "Ama zon", "raw_count": 279814, "count": 279814, "decode_str": "Amazon"} -{"id": 11027, "token": "017", "merges": "01 7", "raw_count": 279877, "count": 279877, "decode_str": "017"} -{"id": 53474, "token": "\u00e8\u0123\u00bf", "merges": "\u00e8\u0123 \u00bf", "raw_count": 279958, "count": 279958, "decode_str": "\u807f"} -{"id": 11958, "token": "black", "merges": "bl ack", "raw_count": 280091, "count": 280091, "decode_str": "black"} -{"id": 28474, "token": "orig", "merges": "or ig", "raw_count": 280195, "count": 280195, "decode_str": "orig"} -{"id": 14824, "token": "party", "merges": "part y", "raw_count": 280271, "count": 280271, "decode_str": "party"} -{"id": 16143, "token": "PUT", "merges": "P UT", "raw_count": 104698, "count": 280273, "decode_str": "PUT"} -{"id": 30544, "token": "seconds", "merges": "second s", "raw_count": 280345, "count": 280345, "decode_str": "seconds"} -{"id": 25716, "token": "EA", "merges": "E A", "raw_count": 280452, "count": 280452, "decode_str": "EA"} -{"id": 15990, "token": "\u0120agenda", "merges": "\u0120ag enda", "raw_count": 280462, "count": 280462, "decode_str": " agenda"} -{"id": 6672, "token": "care", "merges": "c are", "raw_count": 263731, "count": 280531, "decode_str": "care"} -{"id": 52773, "token": "\u00e7\u012b\u012f", "merges": "\u00e7\u012b \u012f", "raw_count": 280631, "count": 280631, "decode_str": "\u724d"} -{"id": 6404, "token": "amily", "merges": "am ily", "raw_count": 4947, "count": 280736, "decode_str": "amily"} -{"id": 28889, "token": "VT", "merges": "V T", "raw_count": 280869, "count": 280869, "decode_str": "VT"} -{"id": 3339, "token": "ulations", "merges": "ul ations", "raw_count": 34893, "count": 280885, "decode_str": "ulations"} -{"id": 2365, "token": "gether", "merges": "get her", "raw_count": 2276, "count": 280908, "decode_str": "gether"} -{"id": 10067, "token": "\u0120provisions", "merges": "\u0120prov isions", "raw_count": 280920, "count": 280920, "decode_str": " provisions"} -{"id": 10371, "token": "Child", "merges": "Ch ild", "raw_count": 161761, "count": 280959, "decode_str": "Child"} -{"id": 17140, "token": "capt", "merges": "c apt", "raw_count": 103151, "count": 280981, "decode_str": "capt"} -{"id": 24454, "token": "359", "merges": "35 9", "raw_count": 281043, "count": 281043, "decode_str": "359"} -{"id": 22172, "token": "audio", "merges": "aud io", "raw_count": 281105, "count": 281105, "decode_str": "audio"} -{"id": 4999, "token": "\u0120safe", "merges": "\u0120sa fe", "raw_count": 259769, "count": 281215, "decode_str": " safe"} -{"id": 50212, "token": "1914", "merges": "19 14", "raw_count": 281237, "count": 281237, "decode_str": "1914"} -{"id": 53568, "token": "\u00e8\u0129\u00be", "merges": "\u00e8\u0129 \u00be", "raw_count": 281266, "count": 281266, "decode_str": "\u81fe"} -{"id": 10452, "token": "SET", "merges": "S ET", "raw_count": 256945, "count": 281277, "decode_str": "SET"} -{"id": 54335, "token": "\u00e9\u013b\u00b2", "merges": "\u00e9\u013b \u00b2", "raw_count": 281302, "count": 281302, "decode_str": "\u9672"} -{"id": 2298, "token": "\u0120mor", "merges": "\u0120m or", "raw_count": 115420, "count": 281313, "decode_str": " mor"} -{"id": 21192, "token": "cad", "merges": "c ad", "raw_count": 280448, "count": 281316, "decode_str": "cad"} -{"id": 52375, "token": "\u00e6\u00a9\u0129", "merges": "\u00e6\u00a9 \u0129", "raw_count": 281364, "count": 281364, "decode_str": "\u6a47"} -{"id": 36089, "token": "generator", "merges": "gener ator", "raw_count": 281579, "count": 281579, "decode_str": "generator"} -{"id": 52260, "token": "\u00e6\u0141\u013a", "merges": "\u00e6\u0141 \u013a", "raw_count": 281642, "count": 281642, "decode_str": "\u67d8"} -{"id": 13374, "token": "prim", "merges": "pr im", "raw_count": 124050, "count": 281896, "decode_str": "prim"} -{"id": 2372, "token": "\u0120bit", "merges": "\u0120b it", "raw_count": 238166, "count": 281941, "decode_str": " bit"} -{"id": 12547, "token": "Tag", "merges": "T ag", "raw_count": 282038, "count": 282038, "decode_str": "Tag"} -{"id": 2831, "token": "\u0120cross", "merges": "\u0120c ross", "raw_count": 226870, "count": 282053, "decode_str": " cross"} -{"id": 53766, "token": "\u00e8\u00a7\u0140", "merges": "\u00e8\u00a7 \u0140", "raw_count": 282247, "count": 282247, "decode_str": "\u89de"} -{"id": 14069, "token": "etc", "merges": "et c", "raw_count": 282269, "count": 282269, "decode_str": "etc"} -{"id": 18243, "token": "SN", "merges": "S N", "raw_count": 282292, "count": 282292, "decode_str": "SN"} -{"id": 3426, "token": "\u0120complete", "merges": "\u0120comp lete", "raw_count": 282329, "count": 282329, "decode_str": " complete"} -{"id": 27315, "token": "Norm", "merges": "N orm", "raw_count": 282373, "count": 282373, "decode_str": "Norm"} -{"id": 7498, "token": "Rev", "merges": "R ev", "raw_count": 143350, "count": 282378, "decode_str": "Rev"} -{"id": 42882, "token": "endpoint", "merges": "end point", "raw_count": 282379, "count": 282379, "decode_str": "endpoint"} -{"id": 13461, "token": "\u0120weights", "merges": "\u0120weight s", "raw_count": 282409, "count": 282409, "decode_str": " weights"} -{"id": 24424, "token": "357", "merges": "35 7", "raw_count": 282722, "count": 282722, "decode_str": "357"} -{"id": 5522, "token": "\u0120package", "merges": "\u0120p ackage", "raw_count": 282828, "count": 282828, "decode_str": " package"} -{"id": 10842, "token": "tml", "merges": "t ml", "raw_count": 16064, "count": 282842, "decode_str": "tml"} -{"id": 53409, "token": "\u00e7\u00bd\u0124", "merges": "\u00e7\u00bd \u0124", "raw_count": 282998, "count": 282998, "decode_str": "\u7f42"} -{"id": 3639, "token": "hood", "merges": "h ood", "raw_count": 63620, "count": 283079, "decode_str": "hood"} -{"id": 9131, "token": "before", "merges": "b efore", "raw_count": 283091, "count": 283091, "decode_str": "before"} -{"id": 22157, "token": "building", "merges": "build ing", "raw_count": 283292, "count": 283292, "decode_str": "building"} -{"id": 52341, "token": "\u00e6\u00a5\u00a3", "merges": "\u00e6\u00a5 \u00a3", "raw_count": 283364, "count": 283364, "decode_str": "\u6963"} -{"id": 7140, "token": "\u0120category", "merges": "\u0120c ategory", "raw_count": 283379, "count": 283379, "decode_str": " category"} -{"id": 13570, "token": "Module", "merges": "Mod ule", "raw_count": 283450, "count": 283450, "decode_str": "Module"} -{"id": 4202, "token": "coming", "merges": "com ing", "raw_count": 114314, "count": 283461, "decode_str": "coming"} -{"id": 33759, "token": "UU", "merges": "U U", "raw_count": 283463, "count": 283463, "decode_str": "UU"} -{"id": 24580, "token": "MG", "merges": "M G", "raw_count": 283483, "count": 283483, "decode_str": "MG"} -{"id": 19335, "token": "dst", "merges": "d st", "raw_count": 283500, "count": 283500, "decode_str": "dst"} -{"id": 19462, "token": "testing", "merges": "test ing", "raw_count": 283540, "count": 283540, "decode_str": "testing"} -{"id": 25414, "token": "Phot", "merges": "Ph ot", "raw_count": 266209, "count": 283699, "decode_str": "Phot"} -{"id": 2469, "token": "\u0120past", "merges": "\u0120p ast", "raw_count": 271103, "count": 283843, "decode_str": " past"} -{"id": 7077, "token": "asy", "merges": "as y", "raw_count": 62599, "count": 283928, "decode_str": "asy"} -{"id": 52846, "token": "\u00e7\u0132\u0131", "merges": "\u00e7\u0132 \u0131", "raw_count": 284038, "count": 284038, "decode_str": "\u740f"} -{"id": 28708, "token": "nx", "merges": "n x", "raw_count": 284089, "count": 284089, "decode_str": "nx"} -{"id": 11589, "token": "Thread", "merges": "Th read", "raw_count": 284048, "count": 284101, "decode_str": "Thread"} -{"id": 51756, "token": "\u00e6\u0124\u00bb", "merges": "\u00e6\u0124 \u00bb", "raw_count": 284115, "count": 284115, "decode_str": "\u60bb"} -{"id": 2802, "token": "\u0120\u00e2\u0122\u013a", "merges": "\u0120\u00e2\u0122 \u013a", "raw_count": 284177, "count": 284177, "decode_str": " \u2018"} -{"id": 24677, "token": "385", "merges": "38 5", "raw_count": 284423, "count": 284423, "decode_str": "385"} -{"id": 8999, "token": "onents", "merges": "on ents", "raw_count": 17366, "count": 284431, "decode_str": "onents"} -{"id": 13238, "token": "Christ", "merges": "Ch rist", "raw_count": 205779, "count": 284584, "decode_str": "Christ"} -{"id": 3963, "token": "\u0120regular", "merges": "\u0120reg ular", "raw_count": 218250, "count": 284591, "decode_str": " regular"} -{"id": 22510, "token": "\u0120seq", "merges": "\u0120se q", "raw_count": 284595, "count": 284595, "decode_str": " seq"} -{"id": 49172, "token": "818", "merges": "8 18", "raw_count": 284699, "count": 284699, "decode_str": "818"} -{"id": 21619, "token": "lg", "merges": "l g", "raw_count": 284708, "count": 284708, "decode_str": "lg"} -{"id": 53118, "token": "\u00e7\u00a5\u013c", "merges": "\u00e7\u00a5 \u013c", "raw_count": 284710, "count": 284710, "decode_str": "\u795a"} -{"id": 24220, "token": "running", "merges": "run ning", "raw_count": 284862, "count": 284862, "decode_str": "running"} -{"id": 19879, "token": "controller", "merges": "cont roller", "raw_count": 285055, "count": 285055, "decode_str": "controller"} -{"id": 51733, "token": "\u00e6\u0123\u00bb", "merges": "\u00e6\u0123 \u00bb", "raw_count": 285081, "count": 285081, "decode_str": "\u607b"} -{"id": 53498, "token": "\u00e8\u0124\u00b1", "merges": "\u00e8\u0124 \u00b1", "raw_count": 285143, "count": 285143, "decode_str": "\u80b1"} -{"id": 6362, "token": "ja", "merges": "j a", "raw_count": 207531, "count": 285154, "decode_str": "ja"} -{"id": 16250, "token": "FAULT", "merges": "FA ULT", "raw_count": 2949, "count": 285201, "decode_str": "FAULT"} -{"id": 9263, "token": "Bu", "merges": "B u", "raw_count": 141594, "count": 285404, "decode_str": "Bu"} -{"id": 8331, "token": "missions", "merges": "miss ions", "raw_count": 163282, "count": 285482, "decode_str": "missions"} -{"id": 13457, "token": "Connection", "merges": "Conne ction", "raw_count": 285513, "count": 285513, "decode_str": "Connection"} -{"id": 10068, "token": "aration", "merges": "ar ation", "raw_count": 34847, "count": 285569, "decode_str": "aration"} -{"id": 23545, "token": "277", "merges": "27 7", "raw_count": 285708, "count": 285708, "decode_str": "277"} -{"id": 30061, "token": "pix", "merges": "p ix", "raw_count": 285778, "count": 285778, "decode_str": "pix"} -{"id": 27676, "token": "encoding", "merges": "enc oding", "raw_count": 285781, "count": 285781, "decode_str": "encoding"} -{"id": 9930, "token": "\u0120columns", "merges": "\u0120col umns", "raw_count": 285787, "count": 285787, "decode_str": " columns"} -{"id": 2753, "token": "\u0120syn", "merges": "\u0120sy n", "raw_count": 66944, "count": 285794, "decode_str": " syn"} -{"id": 28419, "token": "elements", "merges": "e lements", "raw_count": 285927, "count": 285927, "decode_str": "elements"} -{"id": 1894, "token": "\u0120character", "merges": "\u0120char acter", "raw_count": 192922, "count": 286032, "decode_str": " character"} -{"id": 19824, "token": "Network", "merges": "Net work", "raw_count": 286034, "count": 286034, "decode_str": "Network"} -{"id": 31459, "token": "602", "merges": "60 2", "raw_count": 286077, "count": 286077, "decode_str": "602"} -{"id": 23546, "token": "267", "merges": "26 7", "raw_count": 286179, "count": 286179, "decode_str": "267"} -{"id": 6538, "token": "sole", "merges": "so le", "raw_count": 11229, "count": 286199, "decode_str": "sole"} -{"id": 1466, "token": "Let", "merges": "L et", "raw_count": 243069, "count": 286287, "decode_str": "Let"} -{"id": 5047, "token": "rend", "merges": "ren d", "raw_count": 173141, "count": 286369, "decode_str": "rend"} -{"id": 10726, "token": "\u0120entity", "merges": "\u0120ent ity", "raw_count": 286408, "count": 286408, "decode_str": " entity"} -{"id": 11599, "token": "appy", "merges": "app y", "raw_count": 63483, "count": 286409, "decode_str": "appy"} -{"id": 11823, "token": "\u0120ignore", "merges": "\u0120ign ore", "raw_count": 286545, "count": 286545, "decode_str": " ignore"} -{"id": 14764, "token": "accept", "merges": "ac cept", "raw_count": 260990, "count": 286769, "decode_str": "accept"} -{"id": 4902, "token": "ooth", "merges": "o oth", "raw_count": 54450, "count": 286832, "decode_str": "ooth"} -{"id": 1943, "token": "\u0120big", "merges": "\u0120b ig", "raw_count": 211470, "count": 286898, "decode_str": " big"} -{"id": 53955, "token": "\u00e8\u00b5\u0135", "merges": "\u00e8\u00b5 \u0135", "raw_count": 286951, "count": 286951, "decode_str": "\u8d53"} -{"id": 2489, "token": "\u0120become", "merges": "\u0120bec ome", "raw_count": 286996, "count": 286996, "decode_str": " become"} -{"id": 12627, "token": "achine", "merges": "ach ine", "raw_count": 11129, "count": 287075, "decode_str": "achine"} -{"id": 20119, "token": "detail", "merges": "det ail", "raw_count": 287088, "count": 287088, "decode_str": "detail"} -{"id": 51582, "token": "\u00e5\u00ba\u00be", "merges": "\u00e5\u00ba \u00be", "raw_count": 287247, "count": 287247, "decode_str": "\u5ebe"} -{"id": 25133, "token": "456", "merges": "45 6", "raw_count": 287257, "count": 287257, "decode_str": "456"} -{"id": 43277, "token": "880", "merges": "8 80", "raw_count": 287257, "count": 287257, "decode_str": "880"} -{"id": 2871, "token": "\u00d0\u00b5\u00d0", "merges": "\u00d0\u00b5 \u00d0", "raw_count": 114, "count": 287267, "decode_str": "\u0435\ufffd"} -{"id": 7451, "token": "olean", "merges": "ole an", "raw_count": 1422, "count": 287297, "decode_str": "olean"} -{"id": 17586, "token": "Rober", "merges": "R ober", "raw_count": 63845, "count": 287337, "decode_str": "Rober"} -{"id": 50794, "token": "\u00e5\u012b\u0132", "merges": "\u00e5\u012b \u0132", "raw_count": 287351, "count": 287351, "decode_str": "\u5250"} -{"id": 19210, "token": "tool", "merges": "to ol", "raw_count": 245175, "count": 287353, "decode_str": "tool"} -{"id": 51780, "token": "\u00e6\u0125\u00b4", "merges": "\u00e6\u0125 \u00b4", "raw_count": 287394, "count": 287394, "decode_str": "\u60f4"} -{"id": 54142, "token": "\u00e9\u0123\u00bd", "merges": "\u00e9\u0123 \u00bd", "raw_count": 287425, "count": 287425, "decode_str": "\u907d"} -{"id": 1608, "token": "\u0120Sh", "merges": "\u0120S h", "raw_count": 63231, "count": 287539, "decode_str": " Sh"} -{"id": 2908, "token": "\u0120included", "merges": "\u0120includ ed", "raw_count": 287594, "count": 287594, "decode_str": " included"} -{"id": 1217, "token": "}{", "merges": "} {", "raw_count": 263866, "count": 287595, "decode_str": "}{"} -{"id": 3460, "token": "raction", "merges": "ra ction", "raw_count": 111916, "count": 287624, "decode_str": "raction"} -{"id": 4010, "token": ")=", "merges": ") =", "raw_count": 263209, "count": 287676, "decode_str": ")="} -{"id": 29279, "token": "Mobile", "merges": "M obile", "raw_count": 287780, "count": 287780, "decode_str": "Mobile"} -{"id": 15700, "token": "hist", "merges": "h ist", "raw_count": 287496, "count": 287891, "decode_str": "hist"} -{"id": 15337, "token": "review", "merges": "re view", "raw_count": 277444, "count": 287894, "decode_str": "review"} -{"id": 6661, "token": "\u0120configuration", "merges": "\u0120config uration", "raw_count": 287933, "count": 287933, "decode_str": " configuration"} -{"id": 32218, "token": "425", "merges": "4 25", "raw_count": 287954, "count": 287954, "decode_str": "425"} -{"id": 8426, "token": "\u0120justice", "merges": "\u0120just ice", "raw_count": 288007, "count": 288007, "decode_str": " justice"} -{"id": 25320, "token": "655", "merges": "65 5", "raw_count": 288066, "count": 288066, "decode_str": "655"} -{"id": 54181, "token": "\u00e9\u0125\u00ab", "merges": "\u00e9\u0125 \u00ab", "raw_count": 288091, "count": 288091, "decode_str": "\u90eb"} -{"id": 32310, "token": "MX", "merges": "M X", "raw_count": 288110, "count": 288110, "decode_str": "MX"} -{"id": 36028, "token": "\u0120\"{", "merges": "\u0120\" {", "raw_count": 288113, "count": 288113, "decode_str": " \"{"} -{"id": 13422, "token": "Search", "merges": "S earch", "raw_count": 288143, "count": 288143, "decode_str": "Search"} -{"id": 54148, "token": "\u00e9\u0124\u012d", "merges": "\u00e9\u0124 \u012d", "raw_count": 288172, "count": 288172, "decode_str": "\u908b"} -{"id": 8775, "token": "weet", "merges": "we et", "raw_count": 162460, "count": 288215, "decode_str": "weet"} -{"id": 35670, "token": "reply", "merges": "re ply", "raw_count": 288287, "count": 288287, "decode_str": "reply"} -{"id": 21464, "token": "\u0120metadata", "merges": "\u0120met adata", "raw_count": 288307, "count": 288307, "decode_str": " metadata"} -{"id": 49342, "token": "1911", "merges": "19 11", "raw_count": 288315, "count": 288315, "decode_str": "1911"} -{"id": 39799, "token": "today", "merges": "t oday", "raw_count": 288401, "count": 288401, "decode_str": "today"} -{"id": 17232, "token": "Sam", "merges": "S am", "raw_count": 288462, "count": 288462, "decode_str": "Sam"} -{"id": 16568, "token": "VA", "merges": "V A", "raw_count": 288511, "count": 288511, "decode_str": "VA"} -{"id": 24408, "token": "Comput", "merges": "Com put", "raw_count": 221840, "count": 288514, "decode_str": "Comput"} -{"id": 50547, "token": "\u00e4\u00bd\u0125", "merges": "\u00e4\u00bd \u0125", "raw_count": 288524, "count": 288524, "decode_str": "\u4f43"} -{"id": 2207, "token": "\u0120Or", "merges": "\u0120O r", "raw_count": 138996, "count": 288669, "decode_str": " Or"} -{"id": 6511, "token": "faces", "merges": "f aces", "raw_count": 234854, "count": 288690, "decode_str": "faces"} -{"id": 51272, "token": "\u00e5\u00a3\u0127", "merges": "\u00e5\u00a3 \u0127", "raw_count": 288697, "count": 288697, "decode_str": "\u58c5"} -{"id": 32688, "token": "canvas", "merges": "can vas", "raw_count": 288767, "count": 288767, "decode_str": "canvas"} -{"id": 13264, "token": "Task", "merges": "T ask", "raw_count": 288913, "count": 288913, "decode_str": "Task"} -{"id": 2783, "token": "\u0120considered", "merges": "\u0120cons idered", "raw_count": 288950, "count": 288950, "decode_str": " considered"} -{"id": 52748, "token": "\u00e7\u0126\u0139", "merges": "\u00e7\u0126 \u0139", "raw_count": 288958, "count": 288958, "decode_str": "\u7117"} -{"id": 27229, "token": "Live", "merges": "L ive", "raw_count": 289089, "count": 289089, "decode_str": "Live"} -{"id": 4995, "token": "utive", "merges": "ut ive", "raw_count": 44301, "count": 289276, "decode_str": "utive"} -{"id": 42047, "token": "760", "merges": "7 60", "raw_count": 289321, "count": 289321, "decode_str": "760"} -{"id": 1643, "token": "\u0120few", "merges": "\u0120fe w", "raw_count": 263479, "count": 289412, "decode_str": " few"} -{"id": 21874, "token": "323", "merges": "32 3", "raw_count": 289417, "count": 289417, "decode_str": "323"} -{"id": 7908, "token": "\u0120flag", "merges": "\u0120fl ag", "raw_count": 284379, "count": 289425, "decode_str": " flag"} -{"id": 3700, "token": "\u0120transfer", "merges": "\u0120trans fer", "raw_count": 231294, "count": 289462, "decode_str": " transfer"} -{"id": 52454, "token": "\u00e6\u00b0\u00a4", "merges": "\u00e6\u00b0 \u00a4", "raw_count": 289492, "count": 289492, "decode_str": "\u6c24"} -{"id": 52052, "token": "\u00e6\u0135\u013a", "merges": "\u00e6\u0135 \u013a", "raw_count": 289584, "count": 289584, "decode_str": "\u64d8"} -{"id": 48887, "token": "feat", "merges": "fe at", "raw_count": 289619, "count": 289619, "decode_str": "feat"} -{"id": 10361, "token": "\u00ec\u013f", "merges": "\u00ec \u013f", "raw_count": 60710, "count": 289719, "decode_str": "\ufffd"} -{"id": 51610, "token": "\u00e5\u00bc\u0143", "merges": "\u00e5\u00bc \u0143", "raw_count": 289722, "count": 289722, "decode_str": "\u5f2d"} -{"id": 3833, "token": "lor", "merges": "l or", "raw_count": 75739, "count": 289917, "decode_str": "lor"} -{"id": 17788, "token": "gp", "merges": "g p", "raw_count": 265615, "count": 289961, "decode_str": "gp"} -{"id": 17162, "token": "AH", "merges": "A H", "raw_count": 290041, "count": 290041, "decode_str": "AH"} -{"id": 3472, "token": "uous", "merges": "u ous", "raw_count": 127485, "count": 290062, "decode_str": "uous"} -{"id": 8777, "token": "ups", "merges": "up s", "raw_count": 288126, "count": 290157, "decode_str": "ups"} -{"id": 31287, "token": "nv", "merges": "n v", "raw_count": 290391, "count": 290391, "decode_str": "nv"} -{"id": 30152, "token": "ICT", "merges": "I CT", "raw_count": 289792, "count": 290418, "decode_str": "ICT"} -{"id": 52794, "token": "\u00e7\u012c\u0134", "merges": "\u00e7\u012c \u0134", "raw_count": 290566, "count": 290566, "decode_str": "\u7292"} -{"id": 8266, "token": "\u0120font", "merges": "\u0120f ont", "raw_count": 278594, "count": 290625, "decode_str": " font"} -{"id": 2662, "token": "ependent", "merges": "epend ent", "raw_count": 8282, "count": 290662, "decode_str": "ependent"} -{"id": 1975, "token": "ological", "merges": "olog ical", "raw_count": 98512, "count": 290686, "decode_str": "ological"} -{"id": 52484, "token": "\u00e6\u00b1\u00a9", "merges": "\u00e6\u00b1 \u00a9", "raw_count": 290773, "count": 290773, "decode_str": "\u6c69"} -{"id": 47911, "token": "hg", "merges": "h g", "raw_count": 290797, "count": 290797, "decode_str": "hg"} -{"id": 23126, "token": "336", "merges": "33 6", "raw_count": 290923, "count": 290923, "decode_str": "336"} -{"id": 5410, "token": "vest", "merges": "v est", "raw_count": 49463, "count": 290977, "decode_str": "vest"} -{"id": 3107, "token": "anks", "merges": "an ks", "raw_count": 98330, "count": 291078, "decode_str": "anks"} -{"id": 10422, "token": "aux", "merges": "au x", "raw_count": 291186, "count": 291186, "decode_str": "aux"} -{"id": 24951, "token": "progress", "merges": "pro gress", "raw_count": 291308, "count": 291308, "decode_str": "progress"} -{"id": 21280, "token": "city", "merges": "c ity", "raw_count": 291352, "count": 291352, "decode_str": "city"} -{"id": 50847, "token": "\u00e5\u012e\u0132", "merges": "\u00e5\u012e \u0132", "raw_count": 291412, "count": 291412, "decode_str": "\u5310"} -{"id": 6480, "token": "\u012038", "merges": "\u01203 8", "raw_count": 291440, "count": 291440, "decode_str": " 38"} -{"id": 6950, "token": "aren", "merges": "a ren", "raw_count": 142900, "count": 291445, "decode_str": "aren"} -{"id": 34338, "token": "wb", "merges": "w b", "raw_count": 291481, "count": 291481, "decode_str": "wb"} -{"id": 21553, "token": "257", "merges": "25 7", "raw_count": 291521, "count": 291521, "decode_str": "257"} -{"id": 3948, "token": "\u0120engine", "merges": "\u0120eng ine", "raw_count": 164792, "count": 291536, "decode_str": " engine"} -{"id": 11236, "token": "NP", "merges": "N P", "raw_count": 263454, "count": 291557, "decode_str": "NP"} -{"id": 2288, "token": "\u0120sens", "merges": "\u0120s ens", "raw_count": 15357, "count": 291791, "decode_str": " sens"} -{"id": 14825, "token": "modules", "merges": "mod ules", "raw_count": 291812, "count": 291812, "decode_str": "modules"} -{"id": 4043, "token": "ournal", "merges": "our nal", "raw_count": 501, "count": 291853, "decode_str": "ournal"} -{"id": 2636, "token": "\u0120ce", "merges": "\u0120c e", "raw_count": 92602, "count": 292098, "decode_str": " ce"} -{"id": 17257, "token": "\u0120verb", "merges": "\u0120ver b", "raw_count": 69083, "count": 292107, "decode_str": " verb"} -{"id": 4684, "token": "\u0120connect", "merges": "\u0120conne ct", "raw_count": 215206, "count": 292170, "decode_str": " connect"} -{"id": 12092, "token": "Hello", "merges": "H ello", "raw_count": 292205, "count": 292205, "decode_str": "Hello"} -{"id": 52043, "token": "\u00e6\u0134\u00b7", "merges": "\u00e6\u0134 \u00b7", "raw_count": 292279, "count": 292279, "decode_str": "\u64b7"} -{"id": 27893, "token": "313", "merges": "3 13", "raw_count": 292312, "count": 292312, "decode_str": "313"} -{"id": 30029, "token": "ignore", "merges": "ign ore", "raw_count": 292332, "count": 292332, "decode_str": "ignore"} -{"id": 6077, "token": "illa", "merges": "ill a", "raw_count": 248861, "count": 292335, "decode_str": "illa"} -{"id": 52839, "token": "\u00e7\u0131\u00ba", "merges": "\u00e7\u0131 \u00ba", "raw_count": 292346, "count": 292346, "decode_str": "\u73fa"} -{"id": 1620, "token": "\u0120never", "merges": "\u0120ne ver", "raw_count": 270834, "count": 292366, "decode_str": " never"} -{"id": 5115, "token": "\u0120achieve", "merges": "\u0120achie ve", "raw_count": 169478, "count": 292439, "decode_str": " achieve"} -{"id": 2744, "token": "idered", "merges": "ide red", "raw_count": 3576, "count": 292526, "decode_str": "idered"} -{"id": 2977, "token": "aging", "merges": "ag ing", "raw_count": 134291, "count": 292541, "decode_str": "aging"} -{"id": 8671, "token": "\u0120adopted", "merges": "\u0120adopt ed", "raw_count": 292624, "count": 292624, "decode_str": " adopted"} -{"id": 9134, "token": "property", "merges": "pro perty", "raw_count": 292667, "count": 292667, "decode_str": "property"} -{"id": 4285, "token": "\u0120mer", "merges": "\u0120m er", "raw_count": 43774, "count": 292775, "decode_str": " mer"} -{"id": 2057, "token": "\u0120either", "merges": "\u0120e ither", "raw_count": 292932, "count": 292932, "decode_str": " either"} -{"id": 3135, "token": "\u0120begin", "merges": "\u0120beg in", "raw_count": 151622, "count": 293055, "decode_str": " begin"} -{"id": 23625, "token": "322", "merges": "32 2", "raw_count": 293172, "count": 293172, "decode_str": "322"} -{"id": 11645, "token": "ACT", "merges": "A CT", "raw_count": 292626, "count": 293240, "decode_str": "ACT"} -{"id": 32303, "token": "Ctrl", "merges": "C trl", "raw_count": 293293, "count": 293293, "decode_str": "Ctrl"} -{"id": 29035, "token": "vp", "merges": "v p", "raw_count": 293386, "count": 293386, "decode_str": "vp"} -{"id": 13652, "token": "NI", "merges": "N I", "raw_count": 288649, "count": 293456, "decode_str": "NI"} -{"id": 13317, "token": "Column", "merges": "Col umn", "raw_count": 293479, "count": 293479, "decode_str": "Column"} -{"id": 2406, "token": "\u0120lower", "merges": "\u0120l ower", "raw_count": 285832, "count": 293558, "decode_str": " lower"} -{"id": 7499, "token": "\u0120FR", "merges": "\u0120F R", "raw_count": 18928, "count": 293619, "decode_str": " FR"} -{"id": 13266, "token": "DIR", "merges": "D IR", "raw_count": 293646, "count": 293646, "decode_str": "DIR"} -{"id": 3648, "token": "\u0120accom", "merges": "\u0120acc om", "raw_count": 2186, "count": 293650, "decode_str": " accom"} -{"id": 9973, "token": "|-", "merges": "| -", "raw_count": 293679, "count": 293679, "decode_str": "|-"} -{"id": 3679, "token": "clus", "merges": "cl us", "raw_count": 11547, "count": 293831, "decode_str": "clus"} -{"id": 15012, "token": "BY", "merges": "B Y", "raw_count": 281152, "count": 293836, "decode_str": "BY"} -{"id": 13690, "token": "FILE", "merges": "FI LE", "raw_count": 294006, "count": 294006, "decode_str": "FILE"} -{"id": 2937, "token": "itten", "merges": "itt en", "raw_count": 18371, "count": 294007, "decode_str": "itten"} -{"id": 23576, "token": "808", "merges": "80 8", "raw_count": 294010, "count": 294010, "decode_str": "808"} -{"id": 10897, "token": "\u00e2\u0138", "merges": "\u00e2 \u0138", "raw_count": 49770, "count": 294063, "decode_str": "\ufffd"} -{"id": 29251, "token": "603", "merges": "60 3", "raw_count": 294157, "count": 294157, "decode_str": "603"} -{"id": 14621, "token": "itarian", "merges": "it arian", "raw_count": 13323, "count": 294170, "decode_str": "itarian"} -{"id": 4208, "token": "itness", "merges": "it ness", "raw_count": 124992, "count": 294213, "decode_str": "itness"} -{"id": 24275, "token": "dates", "merges": "d ates", "raw_count": 294411, "count": 294411, "decode_str": "dates"} -{"id": 53761, "token": "\u00e8\u00a7\u012c", "merges": "\u00e8\u00a7 \u012c", "raw_count": 294447, "count": 294447, "decode_str": "\u89ca"} -{"id": 51893, "token": "\u00e6\u012d\u0126", "merges": "\u00e6\u012d \u0126", "raw_count": 294475, "count": 294475, "decode_str": "\u62c4"} -{"id": 8531, "token": "uint", "merges": "u int", "raw_count": 294507, "count": 294507, "decode_str": "uint"} -{"id": 3036, "token": "\u0120fig", "merges": "\u0120f ig", "raw_count": 119042, "count": 294569, "decode_str": " fig"} -{"id": 45995, "token": "1918", "merges": "19 18", "raw_count": 294585, "count": 294585, "decode_str": "1918"} -{"id": 23688, "token": "339", "merges": "33 9", "raw_count": 294610, "count": 294610, "decode_str": "339"} -{"id": 5594, "token": "java", "merges": "j ava", "raw_count": 294694, "count": 294694, "decode_str": "java"} -{"id": 12309, "token": "Pan", "merges": "P an", "raw_count": 194368, "count": 294864, "decode_str": "Pan"} -{"id": 9465, "token": "EXT", "merges": "EX T", "raw_count": 75025, "count": 295000, "decode_str": "EXT"} -{"id": 6130, "token": "greg", "merges": "g reg", "raw_count": 25003, "count": 295116, "decode_str": "greg"} -{"id": 54295, "token": "\u00e9\u013a\u012b", "merges": "\u00e9\u013a \u012b", "raw_count": 295149, "count": 295149, "decode_str": "\u9609"} -{"id": 34503, "token": "threshold", "merges": "th reshold", "raw_count": 295166, "count": 295166, "decode_str": "threshold"} -{"id": 5651, "token": "rian", "merges": "ri an", "raw_count": 190641, "count": 295356, "decode_str": "rian"} -{"id": 27076, "token": "duration", "merges": "d uration", "raw_count": 295475, "count": 295475, "decode_str": "duration"} -{"id": 51879, "token": "\u00e6\u012c\u00a1", "merges": "\u00e6\u012c \u00a1", "raw_count": 295491, "count": 295491, "decode_str": "\u62a1"} -{"id": 8236, "token": "media", "merges": "med ia", "raw_count": 295537, "count": 295537, "decode_str": "media"} -{"id": 3420, "token": "\u0120media", "merges": "\u0120med ia", "raw_count": 295597, "count": 295597, "decode_str": " media"} -{"id": 25805, "token": "608", "merges": "60 8", "raw_count": 295725, "count": 295725, "decode_str": "608"} -{"id": 50969, "token": "\u00e5\u0132\u00a1", "merges": "\u00e5\u0132 \u00a1", "raw_count": 295754, "count": 295754, "decode_str": "\u5421"} -{"id": 21940, "token": "021", "merges": "0 21", "raw_count": 295775, "count": 295775, "decode_str": "021"} -{"id": 27027, "token": "blocks", "merges": "bl ocks", "raw_count": 295877, "count": 295877, "decode_str": "blocks"} -{"id": 21095, "token": "349", "merges": "34 9", "raw_count": 295891, "count": 295891, "decode_str": "349"} -{"id": 51343, "token": "\u00e5\u00a6\u00a4", "merges": "\u00e5\u00a6 \u00a4", "raw_count": 295920, "count": 295920, "decode_str": "\u59a4"} -{"id": 52507, "token": "\u00e6\u00b2\u00a3", "merges": "\u00e6\u00b2 \u00a3", "raw_count": 295974, "count": 295974, "decode_str": "\u6ca3"} -{"id": 3355, "token": "ades", "merges": "ad es", "raw_count": 122607, "count": 295995, "decode_str": "ades"} -{"id": 21273, "token": "LOG", "merges": "LO G", "raw_count": 296051, "count": 296051, "decode_str": "LOG"} -{"id": 14660, "token": "Life", "merges": "L ife", "raw_count": 293748, "count": 296069, "decode_str": "Life"} -{"id": 7250, "token": "ested", "merges": "est ed", "raw_count": 104291, "count": 296086, "decode_str": "ested"} -{"id": 15883, "token": "Tom", "merges": "T om", "raw_count": 296114, "count": 296114, "decode_str": "Tom"} -{"id": 23053, "token": "links", "merges": "l inks", "raw_count": 296148, "count": 296148, "decode_str": "links"} -{"id": 9820, "token": "yes", "merges": "y es", "raw_count": 292170, "count": 296160, "decode_str": "yes"} -{"id": 8738, "token": "\u0120democr", "merges": "\u0120dem ocr", "raw_count": 28712, "count": 296223, "decode_str": " democr"} -{"id": 7639, "token": "ivation", "merges": "iv ation", "raw_count": 55700, "count": 296378, "decode_str": "ivation"} -{"id": 52225, "token": "\u00e6\u013f\u00b3", "merges": "\u00e6\u013f \u00b3", "raw_count": 296379, "count": 296379, "decode_str": "\u6773"} -{"id": 15259, "token": "\u0120callback", "merges": "\u0120call back", "raw_count": 296576, "count": 296576, "decode_str": " callback"} -{"id": 29795, "token": "Expl", "merges": "Ex pl", "raw_count": 296616, "count": 296616, "decode_str": "Expl"} -{"id": 14005, "token": "reference", "merges": "re ference", "raw_count": 296764, "count": 296764, "decode_str": "reference"} -{"id": 13378, "token": "Cle", "merges": "C le", "raw_count": 82273, "count": 296820, "decode_str": "Cle"} -{"id": 51212, "token": "\u00e5\u013f\u00b3", "merges": "\u00e5\u013f \u00b3", "raw_count": 296980, "count": 296980, "decode_str": "\u5773"} -{"id": 8316, "token": "mL", "merges": "m L", "raw_count": 297189, "count": 297189, "decode_str": "mL"} -{"id": 2176, "token": "\u0120certain", "merges": "\u0120c ertain", "raw_count": 247777, "count": 297191, "decode_str": " certain"} -{"id": 4260, "token": "\u0120mid", "merges": "\u0120m id", "raw_count": 270428, "count": 297232, "decode_str": " mid"} -{"id": 7606, "token": "usiness", "merges": "us iness", "raw_count": 6966, "count": 297250, "decode_str": "usiness"} -{"id": 34788, "token": "+=", "merges": "+ =", "raw_count": 297352, "count": 297352, "decode_str": "+="} -{"id": 3033, "token": "\u0120bound", "merges": "\u0120b ound", "raw_count": 126410, "count": 297363, "decode_str": " bound"} -{"id": 3669, "token": "iber", "merges": "ib er", "raw_count": 107878, "count": 297402, "decode_str": "iber"} -{"id": 14651, "token": "Cam", "merges": "C am", "raw_count": 147749, "count": 297593, "decode_str": "Cam"} -{"id": 40480, "token": "tasks", "merges": "t asks", "raw_count": 297779, "count": 297779, "decode_str": "tasks"} -{"id": 21285, "token": "direction", "merges": "d irection", "raw_count": 297882, "count": 297882, "decode_str": "direction"} -{"id": 3070, "token": "gree", "merges": "g ree", "raw_count": 18910, "count": 297944, "decode_str": "gree"} -{"id": 17183, "token": "pal", "merges": "p al", "raw_count": 298092, "count": 298092, "decode_str": "pal"} -{"id": 15803, "token": "SB", "merges": "S B", "raw_count": 298234, "count": 298234, "decode_str": "SB"} -{"id": 28113, "token": "correct", "merges": "cor rect", "raw_count": 298361, "count": 298361, "decode_str": "correct"} -{"id": 14996, "token": "program", "merges": "pro gram", "raw_count": 288239, "count": 298394, "decode_str": "program"} -{"id": 2315, "token": "\u0120press", "merges": "\u0120p ress", "raw_count": 122069, "count": 298437, "decode_str": " press"} -{"id": 54292, "token": "\u00e9\u013a\u0128", "merges": "\u00e9\u013a \u0128", "raw_count": 298517, "count": 298517, "decode_str": "\u9606"} -{"id": 18590, "token": "Global", "merges": "Gl obal", "raw_count": 298684, "count": 298684, "decode_str": "Global"} -{"id": 17272, "token": "\u012003", "merges": "\u01200 3", "raw_count": 298692, "count": 298692, "decode_str": " 03"} -{"id": 28662, "token": "contents", "merges": "cont ents", "raw_count": 298846, "count": 298846, "decode_str": "contents"} -{"id": 6332, "token": "\u0120errors", "merges": "\u0120err ors", "raw_count": 298865, "count": 298865, "decode_str": " errors"} -{"id": 50994, "token": "\u00e5\u0133\u0130", "merges": "\u00e5\u0133 \u0130", "raw_count": 298935, "count": 298935, "decode_str": "\u544e"} -{"id": 18938, "token": "Kit", "merges": "K it", "raw_count": 299002, "count": 299002, "decode_str": "Kit"} -{"id": 14422, "token": "Show", "merges": "Sh ow", "raw_count": 299061, "count": 299061, "decode_str": "Show"} -{"id": 9528, "token": "olid", "merges": "ol id", "raw_count": 44321, "count": 299205, "decode_str": "olid"} -{"id": 52556, "token": "\u00e6\u00b4\u013b", "merges": "\u00e6\u00b4 \u013b", "raw_count": 299233, "count": 299233, "decode_str": "\u6d19"} -{"id": 6424, "token": "\u0120criminal", "merges": "\u0120crim inal", "raw_count": 299240, "count": 299240, "decode_str": " criminal"} -{"id": 15035, "token": "export", "merges": "ex port", "raw_count": 299280, "count": 299280, "decode_str": "export"} -{"id": 10395, "token": "Vis", "merges": "V is", "raw_count": 68033, "count": 299318, "decode_str": "Vis"} -{"id": 52001, "token": "\u00e6\u0130\u00ac", "merges": "\u00e6\u0130 \u00ac", "raw_count": 299440, "count": 299440, "decode_str": "\u63ac"} -{"id": 51735, "token": "\u00e6\u0123\u00bf", "merges": "\u00e6\u0123 \u00bf", "raw_count": 299450, "count": 299450, "decode_str": "\u607f"} -{"id": 10082, "token": "mut", "merges": "m ut", "raw_count": 275647, "count": 299487, "decode_str": "mut"} -{"id": 13792, "token": "OST", "merges": "O ST", "raw_count": 127932, "count": 299516, "decode_str": "OST"} -{"id": 36517, "token": "CX", "merges": "C X", "raw_count": 299556, "count": 299556, "decode_str": "CX"} -{"id": 11425, "token": "should", "merges": "sh ould", "raw_count": 299582, "count": 299582, "decode_str": "should"} -{"id": 3699, "token": "culate", "merges": "cul ate", "raw_count": 169261, "count": 299662, "decode_str": "culate"} -{"id": 31482, "token": "\u0120stride", "merges": "\u0120str ide", "raw_count": 299684, "count": 299684, "decode_str": " stride"} -{"id": 12512, "token": "tri", "merges": "t ri", "raw_count": 254782, "count": 299700, "decode_str": "tri"} -{"id": 13967, "token": "Opt", "merges": "O pt", "raw_count": 219294, "count": 299719, "decode_str": "Opt"} -{"id": 15271, "token": "Vol", "merges": "V ol", "raw_count": 178039, "count": 299751, "decode_str": "Vol"} -{"id": 8309, "token": "enu", "merges": "en u", "raw_count": 30839, "count": 299774, "decode_str": "enu"} -{"id": 6585, "token": "\u01202001", "merges": "\u0120200 1", "raw_count": 299870, "count": 299870, "decode_str": " 2001"} -{"id": 25772, "token": "366", "merges": "36 6", "raw_count": 299893, "count": 299893, "decode_str": "366"} -{"id": 16077, "token": "pn", "merges": "p n", "raw_count": 299970, "count": 299970, "decode_str": "pn"} -{"id": 4670, "token": "iers", "merges": "i ers", "raw_count": 83971, "count": 300005, "decode_str": "iers"} -{"id": 4828, "token": "\u0120counter", "merges": "\u0120coun ter", "raw_count": 276393, "count": 300060, "decode_str": " counter"} -{"id": 3884, "token": "\u0120direction", "merges": "\u0120dire ction", "raw_count": 296146, "count": 300276, "decode_str": " direction"} -{"id": 5292, "token": "rey", "merges": "re y", "raw_count": 239323, "count": 300370, "decode_str": "rey"} -{"id": 22863, "token": "377", "merges": "37 7", "raw_count": 300515, "count": 300515, "decode_str": "377"} -{"id": 3492, "token": "\u0120video", "merges": "\u0120v ideo", "raw_count": 300520, "count": 300520, "decode_str": " video"} -{"id": 5010, "token": "\u0120otherwise", "merges": "\u0120other wise", "raw_count": 300564, "count": 300564, "decode_str": " otherwise"} -{"id": 26950, "token": "cnt", "merges": "c nt", "raw_count": 300625, "count": 300625, "decode_str": "cnt"} -{"id": 31011, "token": "]],", "merges": "] ],", "raw_count": 300754, "count": 300754, "decode_str": "]],"} -{"id": 13045, "token": "RES", "merges": "R ES", "raw_count": 206326, "count": 300770, "decode_str": "RES"} -{"id": 27440, "token": "PB", "merges": "P B", "raw_count": 300838, "count": 300838, "decode_str": "PB"} -{"id": 33461, "token": "chunk", "merges": "ch unk", "raw_count": 300920, "count": 300920, "decode_str": "chunk"} -{"id": 5910, "token": "\u012034", "merges": "\u01203 4", "raw_count": 300989, "count": 300989, "decode_str": " 34"} -{"id": 23360, "token": "286", "merges": "28 6", "raw_count": 301022, "count": 301022, "decode_str": "286"} -{"id": 1827, "token": "\u0120ide", "merges": "\u0120 ide", "raw_count": 18204, "count": 301046, "decode_str": " ide"} -{"id": 1694, "token": "\u0120got", "merges": "\u0120g ot", "raw_count": 285171, "count": 301099, "decode_str": " got"} -{"id": 8031, "token": "\u0120stack", "merges": "\u0120st ack", "raw_count": 284184, "count": 301144, "decode_str": " stack"} -{"id": 1415, "token": "\u0120signific", "merges": "\u0120sign ific", "raw_count": 1937, "count": 301188, "decode_str": " signific"} -{"id": 2584, "token": "\u0120toward", "merges": "\u0120to ward", "raw_count": 51121, "count": 301372, "decode_str": " toward"} -{"id": 28053, "token": "996", "merges": "99 6", "raw_count": 301430, "count": 301430, "decode_str": "996"} -{"id": 12641, "token": "ERROR", "merges": "ERR OR", "raw_count": 301548, "count": 301548, "decode_str": "ERROR"} -{"id": 4222, "token": "\u0120arch", "merges": "\u0120ar ch", "raw_count": 100592, "count": 301567, "decode_str": " arch"} -{"id": 6554, "token": "rer", "merges": "re r", "raw_count": 150646, "count": 301607, "decode_str": "rer"} -{"id": 15804, "token": "ACC", "merges": "AC C", "raw_count": 251108, "count": 301618, "decode_str": "ACC"} -{"id": 2585, "token": "elt", "merges": "el t", "raw_count": 178015, "count": 301649, "decode_str": "elt"} -{"id": 25289, "token": "348", "merges": "34 8", "raw_count": 301725, "count": 301725, "decode_str": "348"} -{"id": 19453, "token": "tests", "merges": "test s", "raw_count": 301750, "count": 301750, "decode_str": "tests"} -{"id": 4116, "token": "\u0120attention", "merges": "\u0120att ention", "raw_count": 301866, "count": 301866, "decode_str": " attention"} -{"id": 7206, "token": "\u0120oblig", "merges": "\u0120ob lig", "raw_count": 12146, "count": 301883, "decode_str": " oblig"} -{"id": 3513, "token": "\u0120police", "merges": "\u0120pol ice", "raw_count": 301910, "count": 301910, "decode_str": " police"} -{"id": 33390, "token": "flash", "merges": "fl ash", "raw_count": 301914, "count": 301914, "decode_str": "flash"} -{"id": 9468, "token": "dem", "merges": "d em", "raw_count": 128406, "count": 301929, "decode_str": "dem"} -{"id": 2506, "token": "\u0120doesn", "merges": "\u0120does n", "raw_count": 290436, "count": 302044, "decode_str": " doesn"} -{"id": 2818, "token": "\u0120affect", "merges": "\u0120a ffect", "raw_count": 79943, "count": 302050, "decode_str": " affect"} -{"id": 20129, "token": "government", "merges": "g overnment", "raw_count": 41696, "count": 302074, "decode_str": "government"} -{"id": 2900, "token": "\u0120solution", "merges": "\u0120sol ution", "raw_count": 302228, "count": 302228, "decode_str": " solution"} -{"id": 29042, "token": "mapping", "merges": "ma pping", "raw_count": 302261, "count": 302261, "decode_str": "mapping"} -{"id": 2067, "token": "\u0120several", "merges": "\u0120sever al", "raw_count": 302284, "count": 302284, "decode_str": " several"} -{"id": 6291, "token": "bert", "merges": "ber t", "raw_count": 294495, "count": 302307, "decode_str": "bert"} -{"id": 17013, "token": "509", "merges": "50 9", "raw_count": 302321, "count": 302321, "decode_str": "509"} -{"id": 28834, "token": "expand", "merges": "exp and", "raw_count": 302432, "count": 302432, "decode_str": "expand"} -{"id": 12558, "token": "Di", "merges": "D i", "raw_count": 285187, "count": 302478, "decode_str": "Di"} -{"id": 2734, "token": "\u0120clos", "merges": "\u0120cl os", "raw_count": 5006, "count": 302574, "decode_str": " clos"} -{"id": 23831, "token": "uffle", "merges": "uff le", "raw_count": 210575, "count": 302579, "decode_str": "uffle"} -{"id": 5732, "token": "urrent", "merges": "ur rent", "raw_count": 8029, "count": 302600, "decode_str": "urrent"} -{"id": 4355, "token": "ida", "merges": "id a", "raw_count": 290724, "count": 302704, "decode_str": "ida"} -{"id": 7783, "token": "\u0120150", "merges": "\u01201 50", "raw_count": 302761, "count": 302761, "decode_str": " 150"} -{"id": 3486, "token": "\u0120impact", "merges": "\u0120imp act", "raw_count": 252742, "count": 302987, "decode_str": " impact"} -{"id": 13571, "token": "\u0120ticket", "merges": "\u0120tick et", "raw_count": 303030, "count": 303030, "decode_str": " ticket"} -{"id": 7346, "token": "\u0120120", "merges": "\u01201 20", "raw_count": 303319, "count": 303319, "decode_str": " 120"} -{"id": 5995, "token": "\u0120symb", "merges": "\u0120sy mb", "raw_count": 8205, "count": 303510, "decode_str": " symb"} -{"id": 4428, "token": "\u0120contains", "merges": "\u0120cont ains", "raw_count": 303572, "count": 303572, "decode_str": " contains"} -{"id": 6963, "token": "\u0120king", "merges": "\u0120k ing", "raw_count": 150053, "count": 303586, "decode_str": " king"} -{"id": 2591, "token": "illed", "merges": "ill ed", "raw_count": 52506, "count": 303658, "decode_str": "illed"} -{"id": 15154, "token": "\u0120queue", "merges": "\u0120que ue", "raw_count": 303676, "count": 303676, "decode_str": " queue"} -{"id": 5018, "token": "\u0120steps", "merges": "\u0120st eps", "raw_count": 303763, "count": 303763, "decode_str": " steps"} -{"id": 6493, "token": "\u0120projects", "merges": "\u0120project s", "raw_count": 303812, "count": 303812, "decode_str": " projects"} -{"id": 5155, "token": "iance", "merges": "i ance", "raw_count": 88747, "count": 303932, "decode_str": "iance"} -{"id": 19283, "token": "iri", "merges": "ir i", "raw_count": 304057, "count": 304057, "decode_str": "iri"} -{"id": 25521, "token": "hello", "merges": "hell o", "raw_count": 304137, "count": 304137, "decode_str": "hello"} -{"id": 5173, "token": "je", "merges": "j e", "raw_count": 257233, "count": 304176, "decode_str": "je"} -{"id": 54174, "token": "\u00e9\u0125\u013e", "merges": "\u00e9\u0125 \u013e", "raw_count": 304220, "count": 304220, "decode_str": "\u90dc"} -{"id": 28094, "token": "mr", "merges": "m r", "raw_count": 304229, "count": 304229, "decode_str": "mr"} -{"id": 22818, "token": "276", "merges": "27 6", "raw_count": 304312, "count": 304312, "decode_str": "276"} -{"id": 13614, "token": "Ca", "merges": "C a", "raw_count": 304583, "count": 304583, "decode_str": "Ca"} -{"id": 8983, "token": "Post", "merges": "P ost", "raw_count": 290945, "count": 304652, "decode_str": "Post"} -{"id": 51107, "token": "\u00e5\u0137\u00be", "merges": "\u00e5\u0137 \u00be", "raw_count": 304676, "count": 304676, "decode_str": "\u557e"} -{"id": 2741, "token": "ensity", "merges": "ens ity", "raw_count": 54479, "count": 304689, "decode_str": "ensity"} -{"id": 2472, "token": "\u0120ear", "merges": "\u0120e ar", "raw_count": 27853, "count": 304755, "decode_str": " ear"} -{"id": 8990, "token": "\u0120API", "merges": "\u0120AP I", "raw_count": 304873, "count": 304873, "decode_str": " API"} -{"id": 52298, "token": "\u00e6\u00a1\u0127", "merges": "\u00e6\u00a1 \u0127", "raw_count": 304961, "count": 304961, "decode_str": "\u6845"} -{"id": 43007, "token": "ICU", "merges": "IC U", "raw_count": 305077, "count": 305077, "decode_str": "ICU"} -{"id": 54363, "token": "\u00e9\u013d\u012b", "merges": "\u00e9\u013d \u012b", "raw_count": 305150, "count": 305150, "decode_str": "\u96c9"} -{"id": 4668, "token": "\u0120military", "merges": "\u0120mil itary", "raw_count": 305155, "count": 305155, "decode_str": " military"} -{"id": 54496, "token": "\u00e9\u00aa\u012c", "merges": "\u00e9\u00aa \u012c", "raw_count": 305198, "count": 305198, "decode_str": "\u9a8a"} -{"id": 11688, "token": "Port", "merges": "P ort", "raw_count": 298564, "count": 305396, "decode_str": "Port"} -{"id": 10403, "token": "VAL", "merges": "V AL", "raw_count": 125937, "count": 305397, "decode_str": "VAL"} -{"id": 11538, "token": "Ap", "merges": "A p", "raw_count": 295596, "count": 305398, "decode_str": "Ap"} -{"id": 5630, "token": "ride", "merges": "r ide", "raw_count": 54473, "count": 305418, "decode_str": "ride"} -{"id": 24757, "token": "Hot", "merges": "H ot", "raw_count": 305433, "count": 305433, "decode_str": "Hot"} -{"id": 19395, "token": "KO", "merges": "K O", "raw_count": 305433, "count": 305433, "decode_str": "KO"} -{"id": 52125, "token": "\u00e6\u0139\u00bb", "merges": "\u00e6\u0139 \u00bb", "raw_count": 305474, "count": 305474, "decode_str": "\u65fb"} -{"id": 8629, "token": "null", "merges": "n ull", "raw_count": 305501, "count": 305501, "decode_str": "null"} -{"id": 5700, "token": "\u0120strategy", "merges": "\u0120strateg y", "raw_count": 305576, "count": 305576, "decode_str": " strategy"} -{"id": 4420, "token": "ares", "merges": "a res", "raw_count": 206435, "count": 305594, "decode_str": "ares"} -{"id": 51548, "token": "\u00e5\u00b9\u0136", "merges": "\u00e5\u00b9 \u0136", "raw_count": 305594, "count": 305594, "decode_str": "\u5e54"} -{"id": 2879, "token": "\u0120added", "merges": "\u0120add ed", "raw_count": 305603, "count": 305603, "decode_str": " added"} -{"id": 6363, "token": "\u0120pool", "merges": "\u0120p ool", "raw_count": 256382, "count": 305677, "decode_str": " pool"} -{"id": 4451, "token": "\u0120unique", "merges": "\u0120un ique", "raw_count": 305678, "count": 305678, "decode_str": " unique"} -{"id": 21562, "token": "atten", "merges": "att en", "raw_count": 305678, "count": 305678, "decode_str": "atten"} -{"id": 6095, "token": "\u0120requirements", "merges": "\u0120require ments", "raw_count": 305768, "count": 305768, "decode_str": " requirements"} -{"id": 29603, "token": "ratio", "merges": "rat io", "raw_count": 305792, "count": 305792, "decode_str": "ratio"} -{"id": 15961, "token": "Dan", "merges": "D an", "raw_count": 134033, "count": 305841, "decode_str": "Dan"} -{"id": 8332, "token": "\u0120provision", "merges": "\u0120prov ision", "raw_count": 239470, "count": 306148, "decode_str": " provision"} -{"id": 2096, "token": "\u0120understand", "merges": "\u0120under stand", "raw_count": 136649, "count": 306738, "decode_str": " understand"} -{"id": 27388, "token": "frames", "merges": "fr ames", "raw_count": 306795, "count": 306795, "decode_str": "frames"} -{"id": 53110, "token": "\u00e7\u00a5\u0129", "merges": "\u00e7\u00a5 \u0129", "raw_count": 306923, "count": 306923, "decode_str": "\u7947"} -{"id": 5741, "token": "ita", "merges": "it a", "raw_count": 290172, "count": 307022, "decode_str": "ita"} -{"id": 6955, "token": "SM", "merges": "S M", "raw_count": 305220, "count": 307155, "decode_str": "SM"} -{"id": 20954, "token": "605", "merges": "60 5", "raw_count": 307233, "count": 307233, "decode_str": "605"} -{"id": 21810, "token": "\u0120[(", "merges": "\u0120[ (", "raw_count": 307311, "count": 307311, "decode_str": " [("} -{"id": 18191, "token": "Cur", "merges": "C ur", "raw_count": 307361, "count": 307361, "decode_str": "Cur"} -{"id": 7447, "token": "anda", "merges": "and a", "raw_count": 297962, "count": 307582, "decode_str": "anda"} -{"id": 6851, "token": "fee", "merges": "fe e", "raw_count": 122313, "count": 307656, "decode_str": "fee"} -{"id": 53840, "token": "\u00e8\u00af\u00b0", "merges": "\u00e8\u00af \u00b0", "raw_count": 307681, "count": 307681, "decode_str": "\u8bf0"} -{"id": 13245, "token": "bind", "merges": "b ind", "raw_count": 307944, "count": 307944, "decode_str": "bind"} -{"id": 2931, "token": "\u0120defined", "merges": "\u0120def ined", "raw_count": 307946, "count": 307946, "decode_str": " defined"} -{"id": 13097, "token": "bus", "merges": "b us", "raw_count": 307959, "count": 307959, "decode_str": "bus"} -{"id": 4465, "token": "\u0120extra", "merges": "\u0120ext ra", "raw_count": 283218, "count": 307992, "decode_str": " extra"} -{"id": 7080, "token": "ala", "merges": "al a", "raw_count": 293870, "count": 308084, "decode_str": "ala"} -{"id": 2602, "token": "\u0120soft", "merges": "\u0120so ft", "raw_count": 102889, "count": 308088, "decode_str": " soft"} -{"id": 3057, "token": "\u0120contact", "merges": "\u0120cont act", "raw_count": 246556, "count": 308090, "decode_str": " contact"} -{"id": 16043, "token": "Star", "merges": "St ar", "raw_count": 308097, "count": 308097, "decode_str": "Star"} -{"id": 4079, "token": "uge", "merges": "u ge", "raw_count": 49074, "count": 308272, "decode_str": "uge"} -{"id": 5135, "token": "\u0120lib", "merges": "\u0120l ib", "raw_count": 232534, "count": 308287, "decode_str": " lib"} -{"id": 19122, "token": "vd", "merges": "v d", "raw_count": 308318, "count": 308318, "decode_str": "vd"} -{"id": 13834, "token": "Av", "merges": "A v", "raw_count": 241795, "count": 308455, "decode_str": "Av"} -{"id": 31369, "token": "parts", "merges": "part s", "raw_count": 308475, "count": 308475, "decode_str": "parts"} -{"id": 13788, "token": "Mus", "merges": "M us", "raw_count": 155099, "count": 308479, "decode_str": "Mus"} -{"id": 5888, "token": "\u0120encour", "merges": "\u0120enc our", "raw_count": 315, "count": 308577, "decode_str": " encour"} -{"id": 22391, "token": "326", "merges": "32 6", "raw_count": 308614, "count": 308614, "decode_str": "326"} -{"id": 23336, "token": "spl", "merges": "s pl", "raw_count": 308732, "count": 308732, "decode_str": "spl"} -{"id": 23735, "token": "274", "merges": "27 4", "raw_count": 308906, "count": 308906, "decode_str": "274"} -{"id": 3425, "token": "\u0120sequence", "merges": "\u0120sequ ence", "raw_count": 308989, "count": 308989, "decode_str": " sequence"} -{"id": 31013, "token": "855", "merges": "85 5", "raw_count": 309074, "count": 309074, "decode_str": "855"} -{"id": 17911, "token": "period", "merges": "per iod", "raw_count": 284004, "count": 309188, "decode_str": "period"} -{"id": 2466, "token": "rodu", "merges": "ro du", "raw_count": 9424, "count": 309226, "decode_str": "rodu"} -{"id": 2629, "token": "\u0120standard", "merges": "\u0120stand ard", "raw_count": 290939, "count": 309326, "decode_str": " standard"} -{"id": 35856, "token": "stderr", "merges": "st derr", "raw_count": 309338, "count": 309338, "decode_str": "stderr"} -{"id": 7982, "token": "\u0120metric", "merges": "\u0120met ric", "raw_count": 170074, "count": 309374, "decode_str": " metric"} -{"id": 8816, "token": "Po", "merges": "P o", "raw_count": 254729, "count": 309566, "decode_str": "Po"} -{"id": 5028, "token": "\u0120domain", "merges": "\u0120dom ain", "raw_count": 309600, "count": 309600, "decode_str": " domain"} -{"id": 8776, "token": "\u0120sector", "merges": "\u0120se ctor", "raw_count": 309665, "count": 309665, "decode_str": " sector"} -{"id": 5923, "token": "\u0120instr", "merges": "\u0120inst r", "raw_count": 27202, "count": 309954, "decode_str": " instr"} -{"id": 19091, "token": "subject", "merges": "sub ject", "raw_count": 310213, "count": 310213, "decode_str": "subject"} -{"id": 19484, "token": "parameter", "merges": "param eter", "raw_count": 310224, "count": 310224, "decode_str": "parameter"} -{"id": 51010, "token": "\u00e5\u0133\u00b7", "merges": "\u00e5\u0133 \u00b7", "raw_count": 310299, "count": 310299, "decode_str": "\u5477"} -{"id": 40397, "token": "magic", "merges": "m agic", "raw_count": 310330, "count": 310330, "decode_str": "magic"} -{"id": 2836, "token": "\u0120dig", "merges": "\u0120d ig", "raw_count": 29892, "count": 310376, "decode_str": " dig"} -{"id": 9139, "token": "\u0120territ", "merges": "\u0120ter rit", "raw_count": 469, "count": 310420, "decode_str": " territ"} -{"id": 19232, "token": "rf", "merges": "r f", "raw_count": 310456, "count": 310456, "decode_str": "rf"} -{"id": 4357, "token": "/>", "merges": "/ >", "raw_count": 236789, "count": 310473, "decode_str": "/>"} -{"id": 18380, "token": "\u0120sustainable", "merges": "\u0120sustain able", "raw_count": 310498, "count": 310498, "decode_str": " sustainable"} -{"id": 37027, "token": "rican", "merges": "ric an", "raw_count": 303510, "count": 310553, "decode_str": "rican"} -{"id": 1721, "token": "\u0120pot", "merges": "\u0120p ot", "raw_count": 46250, "count": 310590, "decode_str": " pot"} -{"id": 20298, "token": "327", "merges": "32 7", "raw_count": 310631, "count": 310631, "decode_str": "327"} -{"id": 11477, "token": "IVE", "merges": "IV E", "raw_count": 310666, "count": 310666, "decode_str": "IVE"} -{"id": 18390, "token": "231", "merges": "23 1", "raw_count": 310689, "count": 310689, "decode_str": "231"} -{"id": 7698, "token": "grade", "merges": "gr ade", "raw_count": 157592, "count": 310714, "decode_str": "grade"} -{"id": 39846, "token": "\u0120'{", "merges": "\u0120' {", "raw_count": 310755, "count": 310755, "decode_str": " '{"} -{"id": 2568, "token": "\u0120yet", "merges": "\u0120y et", "raw_count": 310790, "count": 310790, "decode_str": " yet"} -{"id": 4154, "token": "\u0120argument", "merges": "\u0120arg ument", "raw_count": 310825, "count": 310825, "decode_str": " argument"} -{"id": 6457, "token": "\u00c3\u00a2", "merges": "\u00c3 \u00a2", "raw_count": 307750, "count": 310847, "decode_str": "\u00e2"} -{"id": 17498, "token": "\u0120socket", "merges": "\u0120s ocket", "raw_count": 310965, "count": 310965, "decode_str": " socket"} -{"id": 4972, "token": "\u0120vector", "merges": "\u0120ve ctor", "raw_count": 310993, "count": 310993, "decode_str": " vector"} -{"id": 10431, "token": "HC", "merges": "H C", "raw_count": 309997, "count": 311040, "decode_str": "HC"} -{"id": 9639, "token": "STR", "merges": "ST R", "raw_count": 187241, "count": 311389, "decode_str": "STR"} -{"id": 5976, "token": "\u012042", "merges": "\u01204 2", "raw_count": 311450, "count": 311450, "decode_str": " 42"} -{"id": 7255, "token": "\u0120administr", "merges": "\u0120administ r", "raw_count": 11524, "count": 311504, "decode_str": " administr"} -{"id": 5102, "token": "ady", "merges": "ad y", "raw_count": 170650, "count": 311624, "decode_str": "ady"} -{"id": 52874, "token": "\u00e7\u0136\u0143", "merges": "\u00e7\u0136 \u0143", "raw_count": 311658, "count": 311658, "decode_str": "\u752d"} -{"id": 2467, "token": "\u00d0\u00b0\u00d0", "merges": "\u00d0\u00b0 \u00d0", "raw_count": 253, "count": 311677, "decode_str": "\u0430\ufffd"} -{"id": 12771, "token": "SIZE", "merges": "SI ZE", "raw_count": 311884, "count": 311884, "decode_str": "SIZE"} -{"id": 4817, "token": "\u0120passed", "merges": "\u0120pass ed", "raw_count": 311947, "count": 311947, "decode_str": " passed"} -{"id": 15422, "token": "none", "merges": "n one", "raw_count": 311993, "count": 311993, "decode_str": "none"} -{"id": 22253, "token": "series", "merges": "ser ies", "raw_count": 312114, "count": 312114, "decode_str": "series"} -{"id": 9981, "token": "IGHT", "merges": "IG HT", "raw_count": 215018, "count": 312127, "decode_str": "IGHT"} -{"id": 51138, "token": "\u00e5\u013b\u0136", "merges": "\u00e5\u013b \u0136", "raw_count": 312159, "count": 312159, "decode_str": "\u5654"} -{"id": 27617, "token": "\u0120attr", "merges": "\u0120att r", "raw_count": 312393, "count": 312393, "decode_str": " attr"} -{"id": 11139, "token": "plan", "merges": "pl an", "raw_count": 284691, "count": 312411, "decode_str": "plan"} -{"id": 53314, "token": "\u00e7\u00ba\u00a8", "merges": "\u00e7\u00ba \u00a8", "raw_count": 312476, "count": 312476, "decode_str": "\u7ea8"} -{"id": 8096, "token": "Am", "merges": "A m", "raw_count": 258686, "count": 312631, "decode_str": "Am"} -{"id": 13013, "token": "olo", "merges": "ol o", "raw_count": 312755, "count": 312755, "decode_str": "olo"} -{"id": 15875, "token": "rapper", "merges": "ra pper", "raw_count": 53016, "count": 312766, "decode_str": "rapper"} -{"id": 23525, "token": "243", "merges": "24 3", "raw_count": 312862, "count": 312862, "decode_str": "243"} -{"id": 23976, "token": "Ti", "merges": "T i", "raw_count": 312890, "count": 312890, "decode_str": "Ti"} -{"id": 5922, "token": "\u012033", "merges": "\u01203 3", "raw_count": 312930, "count": 312930, "decode_str": " 33"} -{"id": 6356, "token": "ih", "merges": "i h", "raw_count": 281933, "count": 312973, "decode_str": "ih"} -{"id": 2348, "token": "ened", "merges": "en ed", "raw_count": 124908, "count": 313053, "decode_str": "ened"} -{"id": 14598, "token": "[[", "merges": "[ [", "raw_count": 313102, "count": 313102, "decode_str": "[["} -{"id": 5222, "token": "\u0120norm", "merges": "\u0120n orm", "raw_count": 210216, "count": 313190, "decode_str": " norm"} -{"id": 1892, "token": "\u0120hard", "merges": "\u0120h ard", "raw_count": 204549, "count": 313255, "decode_str": " hard"} -{"id": 3394, "token": "\u0120events", "merges": "\u0120ev ents", "raw_count": 313308, "count": 313308, "decode_str": " events"} -{"id": 21149, "token": "244", "merges": "24 4", "raw_count": 313309, "count": 313309, "decode_str": "244"} -{"id": 30586, "token": "buff", "merges": "b uff", "raw_count": 313357, "count": 313357, "decode_str": "buff"} -{"id": 20390, "token": "\u0120cmd", "merges": "\u0120c md", "raw_count": 313663, "count": 313663, "decode_str": " cmd"} -{"id": 45327, "token": "Flash", "merges": "Fl ash", "raw_count": 313678, "count": 313678, "decode_str": "Flash"} -{"id": 14367, "token": "bad", "merges": "b ad", "raw_count": 313710, "count": 313710, "decode_str": "bad"} -{"id": 11965, "token": "INS", "merges": "IN S", "raw_count": 202696, "count": 313750, "decode_str": "INS"} -{"id": 1955, "token": "\u0120due", "merges": "\u0120d ue", "raw_count": 313776, "count": 313776, "decode_str": " due"} -{"id": 2556, "token": "\u0120according", "merges": "\u0120acc ording", "raw_count": 270374, "count": 313796, "decode_str": " according"} -{"id": 12982, "token": "language", "merges": "l anguage", "raw_count": 313901, "count": 313901, "decode_str": "language"} -{"id": 51088, "token": "\u00e5\u0137\u013e", "merges": "\u00e5\u0137 \u013e", "raw_count": 314075, "count": 314075, "decode_str": "\u555c"} -{"id": 18486, "token": "314", "merges": "3 14", "raw_count": 314116, "count": 314116, "decode_str": "314"} -{"id": 5929, "token": ".*", "merges": ". *", "raw_count": 313587, "count": 314132, "decode_str": ".*"} -{"id": 12058, "token": "018", "merges": "01 8", "raw_count": 314146, "count": 314146, "decode_str": "018"} -{"id": 8462, "token": "\u0120Py", "merges": "\u0120P y", "raw_count": 139340, "count": 314175, "decode_str": " Py"} -{"id": 2054, "token": "\u0120fri", "merges": "\u0120f ri", "raw_count": 5572, "count": 314451, "decode_str": " fri"} -{"id": 53125, "token": "\u00e7\u00a5\u00a2", "merges": "\u00e7\u00a5 \u00a2", "raw_count": 314474, "count": 314474, "decode_str": "\u7962"} -{"id": 46995, "token": "Wind", "merges": "W ind", "raw_count": 314731, "count": 314731, "decode_str": "Wind"} -{"id": 11749, "token": "Factory", "merges": "F actory", "raw_count": 314759, "count": 314759, "decode_str": "Factory"} -{"id": 9877, "token": "zi", "merges": "z i", "raw_count": 314852, "count": 314852, "decode_str": "zi"} -{"id": 8612, "token": "\u0120representative", "merges": "\u0120represent ative", "raw_count": 314901, "count": 314901, "decode_str": " representative"} -{"id": 52899, "token": "\u00e7\u0137\u00bf", "merges": "\u00e7\u0137 \u00bf", "raw_count": 314928, "count": 314928, "decode_str": "\u757f"} -{"id": 2308, "token": "\u0120levels", "merges": "\u0120level s", "raw_count": 314951, "count": 314951, "decode_str": " levels"} -{"id": 24235, "token": "263", "merges": "26 3", "raw_count": 314951, "count": 314951, "decode_str": "263"} -{"id": 8700, "token": "lang", "merges": "l ang", "raw_count": 314960, "count": 314960, "decode_str": "lang"} -{"id": 13839, "token": "Pos", "merges": "P os", "raw_count": 289179, "count": 315005, "decode_str": "Pos"} -{"id": 21381, "token": "Fire", "merges": "F ire", "raw_count": 315017, "count": 315017, "decode_str": "Fire"} -{"id": 12311, "token": "good", "merges": "g ood", "raw_count": 315020, "count": 315020, "decode_str": "good"} -{"id": 15830, "token": "[(", "merges": "[ (", "raw_count": 315138, "count": 315138, "decode_str": "[("} -{"id": 4496, "token": "\u0120please", "merges": "\u0120ple ase", "raw_count": 315203, "count": 315203, "decode_str": " please"} -{"id": 34776, "token": "tol", "merges": "t ol", "raw_count": 315283, "count": 315283, "decode_str": "tol"} -{"id": 4075, "token": "\u0120enh", "merges": "\u0120en h", "raw_count": 1404, "count": 315289, "decode_str": " enh"} -{"id": 6101, "token": "\u0120Any", "merges": "\u0120An y", "raw_count": 311863, "count": 315341, "decode_str": " Any"} -{"id": 9765, "token": "\u0120alpha", "merges": "\u0120al pha", "raw_count": 315395, "count": 315395, "decode_str": " alpha"} -{"id": 3657, "token": "\u0120prevent", "merges": "\u0120prev ent", "raw_count": 221219, "count": 315398, "decode_str": " prevent"} -{"id": 4908, "token": "\u0120extract", "merges": "\u0120ext ract", "raw_count": 251191, "count": 315433, "decode_str": " extract"} -{"id": 39167, "token": "Angel", "merges": "An gel", "raw_count": 315778, "count": 315778, "decode_str": "Angel"} -{"id": 53665, "token": "\u00e8\u0130\u0134", "merges": "\u00e8\u0130 \u0134", "raw_count": 315922, "count": 315922, "decode_str": "\u8392"} -{"id": 9582, "token": "anner", "merges": "ann er", "raw_count": 275588, "count": 316050, "decode_str": "anner"} -{"id": 29763, "token": "LU", "merges": "L U", "raw_count": 316119, "count": 316119, "decode_str": "LU"} -{"id": 2778, "token": "ief", "merges": "ie f", "raw_count": 49969, "count": 316146, "decode_str": "ief"} -{"id": 16690, "token": "release", "merges": "re lease", "raw_count": 316311, "count": 316311, "decode_str": "release"} -{"id": 5435, "token": "\u0120crim", "merges": "\u0120cr im", "raw_count": 6732, "count": 316363, "decode_str": " crim"} -{"id": 17744, "token": "\u0120prefix", "merges": "\u0120pre fix", "raw_count": 316435, "count": 316435, "decode_str": " prefix"} -{"id": 54306, "token": "\u00e9\u013a\u00a1", "merges": "\u00e9\u013a \u00a1", "raw_count": 316476, "count": 316476, "decode_str": "\u9621"} -{"id": 15049, "token": "interface", "merges": "inter face", "raw_count": 316568, "count": 316568, "decode_str": "interface"} -{"id": 8053, "token": "Query", "merges": "Qu ery", "raw_count": 279306, "count": 316648, "decode_str": "Query"} -{"id": 27101, "token": "508", "merges": "50 8", "raw_count": 316836, "count": 316836, "decode_str": "508"} -{"id": 38169, "token": "USD", "merges": "US D", "raw_count": 316837, "count": 316837, "decode_str": "USD"} -{"id": 3448, "token": "\u0120language", "merges": "\u0120l anguage", "raw_count": 316838, "count": 316838, "decode_str": " language"} -{"id": 53060, "token": "\u00e7\u0142\u013f", "merges": "\u00e7\u0142 \u013f", "raw_count": 316874, "count": 316874, "decode_str": "\u781d"} -{"id": 6666, "token": "ithub", "merges": "ith ub", "raw_count": 51016, "count": 316920, "decode_str": "ithub"} -{"id": 3120, "token": "\u0120card", "merges": "\u0120c ard", "raw_count": 287902, "count": 317057, "decode_str": " card"} -{"id": 54245, "token": "\u00e9\u0136\u00b9", "merges": "\u00e9\u0136 \u00b9", "raw_count": 317093, "count": 317093, "decode_str": "\u9539"} -{"id": 7241, "token": "\u0120protocol", "merges": "\u0120prot ocol", "raw_count": 317099, "count": 317099, "decode_str": " protocol"} -{"id": 52249, "token": "\u00e6\u0140\u00b3", "merges": "\u00e6\u0140 \u00b3", "raw_count": 317212, "count": 317212, "decode_str": "\u67b3"} -{"id": 51032, "token": "\u00e5\u0134\u013d", "merges": "\u00e5\u0134 \u013d", "raw_count": 317409, "count": 317409, "decode_str": "\u549b"} -{"id": 4861, "token": "ded", "merges": "d ed", "raw_count": 228315, "count": 317451, "decode_str": "ded"} -{"id": 3102, "token": "\u0120pattern", "merges": "\u0120pat tern", "raw_count": 245745, "count": 317503, "decode_str": " pattern"} -{"id": 28213, "token": "remote", "merges": "rem ote", "raw_count": 317607, "count": 317607, "decode_str": "remote"} -{"id": 24345, "token": "\u0120[],", "merges": "\u0120[ ],", "raw_count": 317736, "count": 317736, "decode_str": " [],"} -{"id": 36465, "token": "encoder", "merges": "enc oder", "raw_count": 317768, "count": 317768, "decode_str": "encoder"} -{"id": 19259, "token": "skip", "merges": "sk ip", "raw_count": 317788, "count": 317804, "decode_str": "skip"} -{"id": 13561, "token": "Que", "merges": "Q ue", "raw_count": 53904, "count": 317961, "decode_str": "Que"} -{"id": 5556, "token": "\u0120optim", "merges": "\u0120opt im", "raw_count": 187732, "count": 318034, "decode_str": " optim"} -{"id": 7823, "token": "\u0120policies", "merges": "\u0120polic ies", "raw_count": 318042, "count": 318042, "decode_str": " policies"} -{"id": 3791, "token": "\u0120opportun", "merges": "\u0120opp ortun", "raw_count": 2402, "count": 318046, "decode_str": " opportun"} -{"id": 13419, "token": "bat", "merges": "b at", "raw_count": 308467, "count": 318114, "decode_str": "bat"} -{"id": 52542, "token": "\u00e6\u00b3\u00b1", "merges": "\u00e6\u00b3 \u00b1", "raw_count": 318150, "count": 318150, "decode_str": "\u6cf1"} -{"id": 9016, "token": "css", "merges": "c ss", "raw_count": 318560, "count": 318560, "decode_str": "css"} -{"id": 11594, "token": "Function", "merges": "F unction", "raw_count": 318727, "count": 318727, "decode_str": "Function"} -{"id": 10715, "token": "Mode", "merges": "M ode", "raw_count": 318772, "count": 318772, "decode_str": "Mode"} -{"id": 15288, "token": "Lo", "merges": "L o", "raw_count": 230333, "count": 318902, "decode_str": "Lo"} -{"id": 17239, "token": "Paul", "merges": "Pa ul", "raw_count": 318936, "count": 318936, "decode_str": "Paul"} -{"id": 2839, "token": "\u0120rat", "merges": "\u0120r at", "raw_count": 146428, "count": 318957, "decode_str": " rat"} -{"id": 6017, "token": "sem", "merges": "se m", "raw_count": 198678, "count": 319018, "decode_str": "sem"} -{"id": 22270, "token": "295", "merges": "29 5", "raw_count": 319085, "count": 319085, "decode_str": "295"} -{"id": 15286, "token": "ARS", "merges": "AR S", "raw_count": 318028, "count": 319107, "decode_str": "ARS"} -{"id": 6464, "token": "ora", "merges": "or a", "raw_count": 311549, "count": 319246, "decode_str": "ora"} -{"id": 38447, "token": "620", "merges": "6 20", "raw_count": 319275, "count": 319275, "decode_str": "620"} -{"id": 4049, "token": "\u0120cam", "merges": "\u0120c am", "raw_count": 114070, "count": 319282, "decode_str": " cam"} -{"id": 43425, "token": "\u01202021", "merges": "\u012020 21", "raw_count": 319313, "count": 319313, "decode_str": " 2021"} -{"id": 19920, "token": "units", "merges": "un its", "raw_count": 318801, "count": 319373, "decode_str": "units"} -{"id": 18550, "token": "505", "merges": "50 5", "raw_count": 319447, "count": 319447, "decode_str": "505"} -{"id": 6213, "token": "ometry", "merges": "omet ry", "raw_count": 22021, "count": 319466, "decode_str": "ometry"} -{"id": 2371, "token": "rug", "merges": "ru g", "raw_count": 48466, "count": 319732, "decode_str": "rug"} -{"id": 53932, "token": "\u00e8\u00b4\u00b2", "merges": "\u00e8\u00b4 \u00b2", "raw_count": 319795, "count": 319795, "decode_str": "\u8d32"} -{"id": 17506, "token": "done", "merges": "d one", "raw_count": 319973, "count": 319973, "decode_str": "done"} -{"id": 3385, "token": "rav", "merges": "ra v", "raw_count": 163397, "count": 320185, "decode_str": "rav"} -{"id": 34195, "token": "oshop", "merges": "osh op", "raw_count": 314550, "count": 320221, "decode_str": "oshop"} -{"id": 17354, "token": "required", "merges": "requ ired", "raw_count": 320224, "count": 320224, "decode_str": "required"} -{"id": 7246, "token": "AAAA", "merges": "AA AA", "raw_count": 221606, "count": 320388, "decode_str": "AAAA"} -{"id": 5265, "token": "ipp", "merges": "i pp", "raw_count": 155320, "count": 320417, "decode_str": "ipp"} -{"id": 31362, "token": "488", "merges": "4 88", "raw_count": 320542, "count": 320542, "decode_str": "488"} -{"id": 10810, "token": "PER", "merges": "P ER", "raw_count": 320755, "count": 320755, "decode_str": "PER"} -{"id": 11536, "token": "clip", "merges": "cl ip", "raw_count": 264953, "count": 320922, "decode_str": "clip"} -{"id": 11325, "token": "019", "merges": "01 9", "raw_count": 320960, "count": 320960, "decode_str": "019"} -{"id": 19773, "token": "keep", "merges": "ke ep", "raw_count": 307179, "count": 321004, "decode_str": "keep"} -{"id": 5574, "token": "circ", "merges": "c irc", "raw_count": 69630, "count": 321029, "decode_str": "circ"} -{"id": 51248, "token": "\u00e5\u0142\u0133", "merges": "\u00e5\u0142 \u0133", "raw_count": 321058, "count": 321058, "decode_str": "\u5811"} -{"id": 52774, "token": "\u00e7\u012b\u0134", "merges": "\u00e7\u012b \u0134", "raw_count": 321122, "count": 321122, "decode_str": "\u7252"} -{"id": 28879, "token": "802", "merges": "80 2", "raw_count": 321226, "count": 321226, "decode_str": "802"} -{"id": 36575, "token": "translate", "merges": "trans late", "raw_count": 321330, "count": 321330, "decode_str": "translate"} -{"id": 32256, "token": "setText", "merges": "set Text", "raw_count": 321363, "count": 321363, "decode_str": "setText"} -{"id": 18448, "token": "James", "merges": "J ames", "raw_count": 321373, "count": 321373, "decode_str": "James"} -{"id": 35529, "token": "however", "merges": "how ever", "raw_count": 321475, "count": 321475, "decode_str": "however"} -{"id": 4273, "token": "\u0120bal", "merges": "\u0120b al", "raw_count": 54569, "count": 321607, "decode_str": " bal"} -{"id": 1948, "token": "\u0120mus", "merges": "\u0120m us", "raw_count": 66196, "count": 321638, "decode_str": " mus"} -{"id": 1705, "token": "\u0120come", "merges": "\u0120com e", "raw_count": 320300, "count": 321657, "decode_str": " come"} -{"id": 4036, "token": "\u0120ord", "merges": "\u0120or d", "raw_count": 151074, "count": 321816, "decode_str": " ord"} -{"id": 19537, "token": "News", "merges": "New s", "raw_count": 321869, "count": 321869, "decode_str": "News"} -{"id": 7322, "token": "gent", "merges": "g ent", "raw_count": 41796, "count": 321951, "decode_str": "gent"} -{"id": 5634, "token": "\u0120legis", "merges": "\u0120leg is", "raw_count": 132, "count": 322069, "decode_str": " legis"} -{"id": 43890, "token": "backend", "merges": "back end", "raw_count": 322074, "count": 322074, "decode_str": "backend"} -{"id": 8172, "token": "linear", "merges": "line ar", "raw_count": 309183, "count": 322433, "decode_str": "linear"} -{"id": 2827, "token": "\u0120er", "merges": "\u0120 er", "raw_count": 184003, "count": 322462, "decode_str": " er"} -{"id": 15656, "token": "pb", "merges": "p b", "raw_count": 322474, "count": 322576, "decode_str": "pb"} -{"id": 3343, "token": "\u0120wait", "merges": "\u0120w ait", "raw_count": 231647, "count": 322737, "decode_str": " wait"} -{"id": 45518, "token": "dirname", "merges": "dir name", "raw_count": 322782, "count": 322782, "decode_str": "dirname"} -{"id": 4000, "token": "\u0120rot", "merges": "\u0120ro t", "raw_count": 70845, "count": 322782, "decode_str": " rot"} -{"id": 3565, "token": "\u0120official", "merges": "\u0120offic ial", "raw_count": 178471, "count": 322784, "decode_str": " official"} -{"id": 52924, "token": "\u00e7\u0138\u00bd", "merges": "\u00e7\u0138 \u00bd", "raw_count": 322873, "count": 322873, "decode_str": "\u75bd"} -{"id": 22331, "token": "enabled", "merges": "en abled", "raw_count": 322925, "count": 322925, "decode_str": "enabled"} -{"id": 9347, "token": "\u0120initi", "merges": "\u0120init i", "raw_count": 11944, "count": 322979, "decode_str": " initi"} -{"id": 22232, "token": "242", "merges": "24 2", "raw_count": 323100, "count": 323100, "decode_str": "242"} -{"id": 14360, "token": "member", "merges": "m ember", "raw_count": 323372, "count": 323372, "decode_str": "member"} -{"id": 50846, "token": "\u00e5\u012e\u012f", "merges": "\u00e5\u012e \u012f", "raw_count": 323548, "count": 323548, "decode_str": "\u530d"} -{"id": 11897, "token": "\u0120compute", "merges": "\u0120comp ute", "raw_count": 323583, "count": 323583, "decode_str": " compute"} -{"id": 7988, "token": "LC", "merges": "L C", "raw_count": 310782, "count": 323704, "decode_str": "LC"} -{"id": 4503, "token": "\u0120equal", "merges": "\u0120equ al", "raw_count": 323721, "count": 323721, "decode_str": " equal"} -{"id": 16047, "token": "mov", "merges": "m ov", "raw_count": 146691, "count": 323739, "decode_str": "mov"} -{"id": 19762, "token": "jango", "merges": "j ango", "raw_count": 28997, "count": 323869, "decode_str": "jango"} -{"id": 14524, "token": "TEST", "merges": "TE ST", "raw_count": 324091, "count": 324091, "decode_str": "TEST"} -{"id": 4978, "token": "berg", "merges": "ber g", "raw_count": 277024, "count": 324119, "decode_str": "berg"} -{"id": 5805, "token": "ipment", "merges": "ip ment", "raw_count": 42812, "count": 324236, "decode_str": "ipment"} -{"id": 53674, "token": "\u00e8\u0130\u00b4", "merges": "\u00e8\u0130 \u00b4", "raw_count": 324240, "count": 324240, "decode_str": "\u83b4"} -{"id": 3391, "token": "vious", "merges": "v ious", "raw_count": 5868, "count": 324398, "decode_str": "vious"} -{"id": 12645, "token": "\u0120recommendations", "merges": "\u0120recommend ations", "raw_count": 324436, "count": 324436, "decode_str": " recommendations"} -{"id": 3275, "token": "\u0120production", "merges": "\u0120produ ction", "raw_count": 324487, "count": 324487, "decode_str": " production"} -{"id": 14151, "token": "dated", "merges": "d ated", "raw_count": 12660, "count": 324621, "decode_str": "dated"} -{"id": 3171, "token": "ills", "merges": "ill s", "raw_count": 146474, "count": 324897, "decode_str": "ills"} -{"id": 3939, "token": "\u0120active", "merges": "\u0120act ive", "raw_count": 324927, "count": 324927, "decode_str": " active"} -{"id": 4310, "token": "\u0120bank", "merges": "\u0120b ank", "raw_count": 269609, "count": 325078, "decode_str": " bank"} -{"id": 5726, "token": "pers", "merges": "p ers", "raw_count": 244347, "count": 325136, "decode_str": "pers"} -{"id": 3199, "token": "\u0120pan", "merges": "\u0120p an", "raw_count": 82640, "count": 325371, "decode_str": " pan"} -{"id": 14769, "token": "git", "merges": "g it", "raw_count": 325437, "count": 325437, "decode_str": "git"} -{"id": 5261, "token": "\u0120wid", "merges": "\u0120w id", "raw_count": 64939, "count": 325564, "decode_str": " wid"} -{"id": 2544, "token": "\u0120changes", "merges": "\u0120chang es", "raw_count": 325632, "count": 325632, "decode_str": " changes"} -{"id": 18068, "token": "gh", "merges": "g h", "raw_count": 325635, "count": 325635, "decode_str": "gh"} -{"id": 26032, "token": "compile", "merges": "comp ile", "raw_count": 325691, "count": 325691, "decode_str": "compile"} -{"id": 51349, "token": "\u00e5\u00a6\u00b2", "merges": "\u00e5\u00a6 \u00b2", "raw_count": 325985, "count": 325985, "decode_str": "\u59b2"} -{"id": 7811, "token": "\u0120department", "merges": "\u0120dep artment", "raw_count": 326058, "count": 326058, "decode_str": " department"} -{"id": 31055, "token": "690", "merges": "69 0", "raw_count": 326127, "count": 326127, "decode_str": "690"} -{"id": 15149, "token": "auto", "merges": "aut o", "raw_count": 326143, "count": 326143, "decode_str": "auto"} -{"id": 3072, "token": "\u0120population", "merges": "\u0120pop ulation", "raw_count": 326203, "count": 326203, "decode_str": " population"} -{"id": 19131, "token": "once", "merges": "on ce", "raw_count": 326250, "count": 326250, "decode_str": "once"} -{"id": 24444, "token": "Bay", "merges": "B ay", "raw_count": 324529, "count": 326318, "decode_str": "Bay"} -{"id": 5503, "token": "ota", "merges": "ot a", "raw_count": 288050, "count": 326337, "decode_str": "ota"} -{"id": 39871, "token": "rpm", "merges": "r pm", "raw_count": 326402, "count": 326402, "decode_str": "rpm"} -{"id": 39948, "token": "863", "merges": "86 3", "raw_count": 326404, "count": 326404, "decode_str": "863"} -{"id": 12380, "token": "condition", "merges": "cond ition", "raw_count": 245495, "count": 326412, "decode_str": "condition"} -{"id": 5231, "token": "\u0120actions", "merges": "\u0120a ctions", "raw_count": 326416, "count": 326416, "decode_str": " actions"} -{"id": 21949, "token": "peg", "merges": "pe g", "raw_count": 93877, "count": 326417, "decode_str": "peg"} -{"id": 24997, "token": "ipeline", "merges": "ip eline", "raw_count": 274348, "count": 326491, "decode_str": "ipeline"} -{"id": 3829, "token": "\u0120webs", "merges": "\u0120we bs", "raw_count": 22656, "count": 326663, "decode_str": " webs"} -{"id": 51133, "token": "\u00e5\u0138\u00ba", "merges": "\u00e5\u0138 \u00ba", "raw_count": 326664, "count": 326664, "decode_str": "\u55ba"} -{"id": 1465, "token": "\u0120hy", "merges": "\u0120h y", "raw_count": 46486, "count": 326846, "decode_str": " hy"} -{"id": 17149, "token": "quant", "merges": "qu ant", "raw_count": 149361, "count": 326914, "decode_str": "quant"} -{"id": 12522, "token": "012", "merges": "01 2", "raw_count": 326919, "count": 326919, "decode_str": "012"} -{"id": 21451, "token": "251", "merges": "25 1", "raw_count": 327137, "count": 327137, "decode_str": "251"} -{"id": 53538, "token": "\u00e8\u0126\u012f", "merges": "\u00e8\u0126 \u012f", "raw_count": 327204, "count": 327204, "decode_str": "\u810d"} -{"id": 39448, "token": "variables", "merges": "vari ables", "raw_count": 327385, "count": 327385, "decode_str": "variables"} -{"id": 11258, "token": "kind", "merges": "k ind", "raw_count": 310262, "count": 327539, "decode_str": "kind"} -{"id": 15266, "token": "\u0120optional", "merges": "\u0120opt ional", "raw_count": 327646, "count": 327646, "decode_str": " optional"} -{"id": 2880, "token": "iet", "merges": "i et", "raw_count": 181486, "count": 327810, "decode_str": "iet"} -{"id": 3855, "token": "igen", "merges": "ig en", "raw_count": 80496, "count": 327901, "decode_str": "igen"} -{"id": 28330, "token": "opts", "merges": "op ts", "raw_count": 328025, "count": 328025, "decode_str": "opts"} -{"id": 19339, "token": "University", "merges": "Un iversity", "raw_count": 328051, "count": 328051, "decode_str": "University"} -{"id": 24552, "token": "241", "merges": "24 1", "raw_count": 328091, "count": 328091, "decode_str": "241"} -{"id": 4588, "token": "\u0120actual", "merges": "\u0120act ual", "raw_count": 328219, "count": 328219, "decode_str": " actual"} -{"id": 4275, "token": "\u0120central", "merges": "\u0120cent ral", "raw_count": 317451, "count": 328247, "decode_str": " central"} -{"id": 15886, "token": "Enter", "merges": "En ter", "raw_count": 328343, "count": 328343, "decode_str": "Enter"} -{"id": 3137, "token": "\u0120compl", "merges": "\u0120com pl", "raw_count": 17519, "count": 328394, "decode_str": " compl"} -{"id": 22163, "token": "sam", "merges": "s am", "raw_count": 237992, "count": 328455, "decode_str": "sam"} -{"id": 43118, "token": ":.", "merges": ": .", "raw_count": 328459, "count": 328459, "decode_str": ":."} -{"id": 1331, "token": "\u0120ant", "merges": "\u0120an t", "raw_count": 83445, "count": 328481, "decode_str": " ant"} -{"id": 53711, "token": "\u00e8\u00a1\u00ae", "merges": "\u00e8\u00a1 \u00ae", "raw_count": 328572, "count": 328572, "decode_str": "\u886e"} -{"id": 11209, "token": "bits", "merges": "b its", "raw_count": 303997, "count": 328764, "decode_str": "bits"} -{"id": 2104, "token": "\u0120able", "merges": "\u0120ab le", "raw_count": 328819, "count": 328819, "decode_str": " able"} -{"id": 1919, "token": "\u0120until", "merges": "\u0120un til", "raw_count": 328906, "count": 328906, "decode_str": " until"} -{"id": 28488, "token": "Ama", "merges": "A ma", "raw_count": 49223, "count": 329037, "decode_str": "Ama"} -{"id": 6184, "token": "\u0120download", "merges": "\u0120down load", "raw_count": 247266, "count": 329201, "decode_str": " download"} -{"id": 15499, "token": "Graph", "merges": "G raph", "raw_count": 285765, "count": 329203, "decode_str": "Graph"} -{"id": 52462, "token": "\u00e6\u00b0\u00b2", "merges": "\u00e6\u00b0 \u00b2", "raw_count": 329249, "count": 329249, "decode_str": "\u6c32"} -{"id": 7792, "token": "\u0120framework", "merges": "\u0120frame work", "raw_count": 329271, "count": 329271, "decode_str": " framework"} -{"id": 1917, "token": "\u0120sever", "merges": "\u0120se ver", "raw_count": 7912, "count": 329271, "decode_str": " sever"} -{"id": 53997, "token": "\u00e8\u00b7\u013c", "merges": "\u00e8\u00b7 \u013c", "raw_count": 329440, "count": 329440, "decode_str": "\u8dda"} -{"id": 31251, "token": "interval", "merges": "inter val", "raw_count": 329516, "count": 329516, "decode_str": "interval"} -{"id": 52150, "token": "\u00e6\u013b\u0123", "merges": "\u00e6\u013b \u0123", "raw_count": 329659, "count": 329659, "decode_str": "\u6641"} -{"id": 2760, "token": "big", "merges": "b ig", "raw_count": 308359, "count": 329676, "decode_str": "big"} -{"id": 14071, "token": "orer", "merges": "ore r", "raw_count": 316466, "count": 329720, "decode_str": "orer"} -{"id": 3806, "token": "\u0120reference", "merges": "\u0120re ference", "raw_count": 329728, "count": 329728, "decode_str": " reference"} -{"id": 2572, "token": "\u0120increase", "merges": "\u0120incre ase", "raw_count": 329867, "count": 329867, "decode_str": " increase"} -{"id": 8311, "token": "ni", "merges": "n i", "raw_count": 329965, "count": 329974, "decode_str": "ni"} -{"id": 20723, "token": "Je", "merges": "J e", "raw_count": 330005, "count": 330005, "decode_str": "Je"} -{"id": 33658, "token": "dB", "merges": "d B", "raw_count": 330019, "count": 330019, "decode_str": "dB"} -{"id": 11695, "token": "Project", "merges": "Pro ject", "raw_count": 330097, "count": 330097, "decode_str": "Project"} -{"id": 52027, "token": "\u00e6\u0134\u0124", "merges": "\u00e6\u0134 \u0124", "raw_count": 330141, "count": 330141, "decode_str": "\u6482"} -{"id": 13694, "token": "Dir", "merges": "D ir", "raw_count": 330203, "count": 330203, "decode_str": "Dir"} -{"id": 4508, "token": "\u0120containing", "merges": "\u0120cont aining", "raw_count": 330282, "count": 330282, "decode_str": " containing"} -{"id": 6209, "token": "sens", "merges": "s ens", "raw_count": 59742, "count": 330347, "decode_str": "sens"} -{"id": 4781, "token": "alle", "merges": "al le", "raw_count": 82754, "count": 330466, "decode_str": "alle"} -{"id": 10003, "token": "\u0120institutions", "merges": "\u0120instit utions", "raw_count": 330481, "count": 330481, "decode_str": " institutions"} -{"id": 40064, "token": "cols", "merges": "col s", "raw_count": 330644, "count": 330644, "decode_str": "cols"} -{"id": 42921, "token": "avg", "merges": "av g", "raw_count": 330656, "count": 330656, "decode_str": "avg"} -{"id": 15161, "token": "254", "merges": "25 4", "raw_count": 330737, "count": 330737, "decode_str": "254"} -{"id": 2993, "token": "She", "merges": "S he", "raw_count": 149171, "count": 330807, "decode_str": "She"} -{"id": 11340, "token": "push", "merges": "p ush", "raw_count": 330850, "count": 330850, "decode_str": "push"} -{"id": 5849, "token": "asure", "merges": "as ure", "raw_count": 29654, "count": 331023, "decode_str": "asure"} -{"id": 54263, "token": "\u00e9\u0137\u0143", "merges": "\u00e9\u0137 \u0143", "raw_count": 331175, "count": 331175, "decode_str": "\u956d"} -{"id": 1759, "token": "\u0120observ", "merges": "\u0120ob serv", "raw_count": 33575, "count": 331210, "decode_str": " observ"} -{"id": 9521, "token": "\u0120requested", "merges": "\u0120request ed", "raw_count": 331246, "count": 331246, "decode_str": " requested"} -{"id": 18356, "token": "sr", "merges": "s r", "raw_count": 331251, "count": 331251, "decode_str": "sr"} -{"id": 6977, "token": "uce", "merges": "u ce", "raw_count": 83648, "count": 331291, "decode_str": "uce"} -{"id": 19164, "token": "original", "merges": "or iginal", "raw_count": 331390, "count": 331390, "decode_str": "original"} -{"id": 41316, "token": "extract", "merges": "ext ract", "raw_count": 331511, "count": 331511, "decode_str": "extract"} -{"id": 21663, "token": "Lab", "merges": "L ab", "raw_count": 249999, "count": 331536, "decode_str": "Lab"} -{"id": 15193, "token": "overnment", "merges": "overn ment", "raw_count": 16152, "count": 331630, "decode_str": "overnment"} -{"id": 1930, "token": "\u0120side", "merges": "\u0120s ide", "raw_count": 322075, "count": 331653, "decode_str": " side"} -{"id": 25025, "token": "678", "merges": "67 8", "raw_count": 331779, "count": 331779, "decode_str": "678"} -{"id": 3802, "token": "\u0120sn", "merges": "\u0120s n", "raw_count": 119766, "count": 331811, "decode_str": " sn"} -{"id": 7873, "token": "star", "merges": "st ar", "raw_count": 331899, "count": 331899, "decode_str": "star"} -{"id": 2533, "token": "\u0120separ", "merges": "\u0120se par", "raw_count": 29456, "count": 332171, "decode_str": " separ"} -{"id": 53613, "token": "\u00e8\u012c\u0130", "merges": "\u00e8\u012c \u0130", "raw_count": 332249, "count": 332249, "decode_str": "\u828e"} -{"id": 3248, "token": "ese", "merges": "es e", "raw_count": 293319, "count": 332335, "decode_str": "ese"} -{"id": 10882, "token": "\u0120Image", "merges": "\u0120Im age", "raw_count": 332408, "count": 332408, "decode_str": " Image"} -{"id": 54441, "token": "\u00e9\u00a2\u012b", "merges": "\u00e9\u00a2 \u012b", "raw_count": 332459, "count": 332459, "decode_str": "\u9889"} -{"id": 21129, "token": "Sequ", "merges": "S equ", "raw_count": 199165, "count": 332512, "decode_str": "Sequ"} -{"id": 54116, "token": "\u00e9\u0122\u00b5", "merges": "\u00e9\u0122 \u00b5", "raw_count": 332773, "count": 332773, "decode_str": "\u9035"} -{"id": 51418, "token": "\u00e5\u00ae\u00a5", "merges": "\u00e5\u00ae \u00a5", "raw_count": 332831, "count": 332831, "decode_str": "\u5ba5"} -{"id": 6210, "token": "\u0120wel", "merges": "\u0120w el", "raw_count": 93137, "count": 332838, "decode_str": " wel"} -{"id": 2718, "token": "\u0120systems", "merges": "\u0120system s", "raw_count": 332855, "count": 332855, "decode_str": " systems"} -{"id": 53207, "token": "\u00e7\u00ac\u012a", "merges": "\u00e7\u00ac \u012a", "raw_count": 332893, "count": 332893, "decode_str": "\u7b08"} -{"id": 33577, "token": "Office", "merges": "Off ice", "raw_count": 332898, "count": 332898, "decode_str": "Office"} -{"id": 5985, "token": "ki", "merges": "k i", "raw_count": 297044, "count": 333034, "decode_str": "ki"} -{"id": 2561, "token": "\u0120research", "merges": "\u0120rese arch", "raw_count": 329859, "count": 333522, "decode_str": " research"} -{"id": 3210, "token": "\u0120models", "merges": "\u0120mod els", "raw_count": 333594, "count": 333594, "decode_str": " models"} -{"id": 25208, "token": "403", "merges": "40 3", "raw_count": 333676, "count": 333676, "decode_str": "403"} -{"id": 17475, "token": "mc", "merges": "m c", "raw_count": 333919, "count": 333919, "decode_str": "mc"} -{"id": 1847, "token": "\u0120Pl", "merges": "\u0120P l", "raw_count": 33585, "count": 333945, "decode_str": " Pl"} -{"id": 4462, "token": "unn", "merges": "un n", "raw_count": 94678, "count": 334197, "decode_str": "unn"} -{"id": 3715, "token": "\u0120developed", "merges": "\u0120develop ed", "raw_count": 334233, "count": 334233, "decode_str": " developed"} -{"id": 9978, "token": "\u0120setup", "merges": "\u0120set up", "raw_count": 334248, "count": 334248, "decode_str": " setup"} -{"id": 52110, "token": "\u00e6\u0139\u0130", "merges": "\u00e6\u0139 \u0130", "raw_count": 334273, "count": 334273, "decode_str": "\u65ce"} -{"id": 26458, "token": "binary", "merges": "b inary", "raw_count": 334280, "count": 334280, "decode_str": "binary"} -{"id": 18392, "token": "247", "merges": "24 7", "raw_count": 334300, "count": 334300, "decode_str": "247"} -{"id": 35707, "token": "concat", "merges": "con cat", "raw_count": 334435, "count": 334435, "decode_str": "concat"} -{"id": 41282, "token": "filters", "merges": "fil ters", "raw_count": 334444, "count": 334444, "decode_str": "filters"} -{"id": 51517, "token": "\u00e5\u00b7\u00bd", "merges": "\u00e5\u00b7 \u00bd", "raw_count": 334519, "count": 334519, "decode_str": "\u5dfd"} -{"id": 15490, "token": "Day", "merges": "D ay", "raw_count": 334618, "count": 334618, "decode_str": "Day"} -{"id": 2589, "token": "\u0120conduct", "merges": "\u0120con duct", "raw_count": 158172, "count": 334629, "decode_str": " conduct"} -{"id": 2186, "token": "\u0120hold", "merges": "\u0120h old", "raw_count": 167323, "count": 334721, "decode_str": " hold"} -{"id": 2619, "token": "\u0120pick", "merges": "\u0120p ick", "raw_count": 275754, "count": 334724, "decode_str": " pick"} -{"id": 18269, "token": "TB", "merges": "T B", "raw_count": 334730, "count": 334730, "decode_str": "TB"} -{"id": 4647, "token": "\u0120apply", "merges": "\u0120app ly", "raw_count": 334756, "count": 334756, "decode_str": " apply"} -{"id": 45037, "token": "metrics", "merges": "metric s", "raw_count": 334786, "count": 334786, "decode_str": "metrics"} -{"id": 2702, "token": "icult", "merges": "ic ult", "raw_count": 27876, "count": 334875, "decode_str": "icult"} -{"id": 7999, "token": "INT", "merges": "IN T", "raw_count": 228545, "count": 334983, "decode_str": "INT"} -{"id": 20991, "token": "237", "merges": "23 7", "raw_count": 335081, "count": 335081, "decode_str": "237"} -{"id": 10327, "token": "OF", "merges": "O F", "raw_count": 309383, "count": 335112, "decode_str": "OF"} -{"id": 19948, "token": "384", "merges": "38 4", "raw_count": 335320, "count": 335320, "decode_str": "384"} -{"id": 53609, "token": "\u00e8\u012c\u012a", "merges": "\u00e8\u012c \u012a", "raw_count": 335330, "count": 335330, "decode_str": "\u8288"} -{"id": 16281, "token": "Pal", "merges": "P al", "raw_count": 332922, "count": 335365, "decode_str": "Pal"} -{"id": 11223, "token": "Em", "merges": "E m", "raw_count": 303864, "count": 335413, "decode_str": "Em"} -{"id": 11015, "token": "days", "merges": "d ays", "raw_count": 335445, "count": 335445, "decode_str": "days"} -{"id": 36742, "token": "mesh", "merges": "mes h", "raw_count": 335470, "count": 335470, "decode_str": "mesh"} -{"id": 27088, "token": "dv", "merges": "d v", "raw_count": 335483, "count": 335483, "decode_str": "dv"} -{"id": 4106, "token": "efore", "merges": "ef ore", "raw_count": 2487, "count": 335506, "decode_str": "efore"} -{"id": 24557, "token": "facebook", "merges": "face book", "raw_count": 335675, "count": 335675, "decode_str": "facebook"} -{"id": 8956, "token": "\u0120accordance", "merges": "\u0120accord ance", "raw_count": 335900, "count": 335900, "decode_str": " accordance"} -{"id": 5024, "token": "\u0120edge", "merges": "\u0120ed ge", "raw_count": 335900, "count": 335900, "decode_str": " edge"} -{"id": 2833, "token": "\u0120creat", "merges": "\u0120c reat", "raw_count": 8969, "count": 336304, "decode_str": " creat"} -{"id": 30738, "token": "__,", "merges": "__ ,", "raw_count": 336387, "count": 336387, "decode_str": "__,"} -{"id": 1769, "token": "\u00e3\u0125", "merges": "\u00e3 \u0125", "raw_count": 26865, "count": 336399, "decode_str": "\ufffd"} -{"id": 4524, "token": "under", "merges": "un der", "raw_count": 256528, "count": 336598, "decode_str": "under"} -{"id": 28011, "token": "reader", "merges": "read er", "raw_count": 336699, "count": 336699, "decode_str": "reader"} -{"id": 5134, "token": "ny", "merges": "n y", "raw_count": 309749, "count": 336712, "decode_str": "ny"} -{"id": 12094, "token": "Command", "merges": "Com mand", "raw_count": 336848, "count": 336848, "decode_str": "Command"} -{"id": 8083, "token": "\u0120union", "merges": "\u0120un ion", "raw_count": 336851, "count": 336851, "decode_str": " union"} -{"id": 52852, "token": "\u00e7\u0132\u00a8", "merges": "\u00e7\u0132 \u00a8", "raw_count": 336895, "count": 336895, "decode_str": "\u7428"} -{"id": 54136, "token": "\u00e9\u0123\u00a8", "merges": "\u00e9\u0123 \u00a8", "raw_count": 336941, "count": 336941, "decode_str": "\u9068"} -{"id": 16261, "token": "\u012002", "merges": "\u01200 2", "raw_count": 336971, "count": 336971, "decode_str": " 02"} -{"id": 1333, "token": "\u0120say", "merges": "\u0120s ay", "raw_count": 259057, "count": 337069, "decode_str": " say"} -{"id": 53071, "token": "\u00e7\u0142\u00bc", "merges": "\u00e7\u0142 \u00bc", "raw_count": 337173, "count": 337173, "decode_str": "\u783c"} -{"id": 37494, "token": "XP", "merges": "X P", "raw_count": 337212, "count": 337212, "decode_str": "XP"} -{"id": 8484, "token": "Us", "merges": "U s", "raw_count": 74506, "count": 337223, "decode_str": "Us"} -{"id": 4424, "token": "ffer", "merges": "ff er", "raw_count": 107702, "count": 337389, "decode_str": "ffer"} -{"id": 18237, "token": "Game", "merges": "G ame", "raw_count": 337487, "count": 337487, "decode_str": "Game"} -{"id": 14458, "token": "short", "merges": "sh ort", "raw_count": 337493, "count": 337493, "decode_str": "short"} -{"id": 38551, "token": "bps", "merges": "b ps", "raw_count": 337528, "count": 337528, "decode_str": "bps"} -{"id": 38924, "token": "bucket", "merges": "buck et", "raw_count": 337572, "count": 337572, "decode_str": "bucket"} -{"id": 2248, "token": "\u0120prim", "merges": "\u0120pr im", "raw_count": 35368, "count": 337586, "decode_str": " prim"} -{"id": 9669, "token": "coin", "merges": "co in", "raw_count": 325158, "count": 337907, "decode_str": "coin"} -{"id": 10818, "token": "Med", "merges": "M ed", "raw_count": 253651, "count": 337946, "decode_str": "Med"} -{"id": 4143, "token": "\u0120visit", "merges": "\u0120vis it", "raw_count": 296246, "count": 337956, "decode_str": " visit"} -{"id": 8116, "token": "Back", "merges": "B ack", "raw_count": 276007, "count": 338028, "decode_str": "Back"} -{"id": 5948, "token": "\u0120society", "merges": "\u0120s ociety", "raw_count": 338079, "count": 338079, "decode_str": " society"} -{"id": 52112, "token": "\u00e6\u0139\u0138", "merges": "\u00e6\u0139 \u0138", "raw_count": 338108, "count": 338108, "decode_str": "\u65d6"} -{"id": 22488, "token": "408", "merges": "40 8", "raw_count": 338222, "count": 338222, "decode_str": "408"} -{"id": 54355, "token": "\u00e9\u013c\u00bc", "merges": "\u00e9\u013c \u00bc", "raw_count": 338324, "count": 338324, "decode_str": "\u96bc"} -{"id": 18602, "token": "owner", "merges": "own er", "raw_count": 338366, "count": 338366, "decode_str": "owner"} -{"id": 38745, "token": "\u0120'_", "merges": "\u0120' _", "raw_count": 338388, "count": 338388, "decode_str": " '_"} -{"id": 1750, "token": "\u0120claim", "merges": "\u0120cl aim", "raw_count": 126679, "count": 338538, "decode_str": " claim"} -{"id": 2710, "token": "\u0120various", "merges": "\u0120var ious", "raw_count": 338559, "count": 338559, "decode_str": " various"} -{"id": 10608, "token": "\u0120\u00eb", "merges": "\u0120 \u00eb", "raw_count": 270550, "count": 338587, "decode_str": " \ufffd"} -{"id": 44828, "token": "730", "merges": "7 30", "raw_count": 338694, "count": 338694, "decode_str": "730"} -{"id": 9675, "token": "FOR", "merges": "F OR", "raw_count": 166908, "count": 339000, "decode_str": "FOR"} -{"id": 6752, "token": "\u01202002", "merges": "\u0120200 2", "raw_count": 339005, "count": 339005, "decode_str": " 2002"} -{"id": 17919, "token": "Press", "merges": "P ress", "raw_count": 337837, "count": 339022, "decode_str": "Press"} -{"id": 6740, "token": "\u0120src", "merges": "\u0120s rc", "raw_count": 339148, "count": 339148, "decode_str": " src"} -{"id": 6167, "token": "\u0120regist", "merges": "\u0120reg ist", "raw_count": 47666, "count": 339160, "decode_str": " regist"} -{"id": 2238, "token": "\u0120kind", "merges": "\u0120k ind", "raw_count": 271845, "count": 339261, "decode_str": " kind"} -{"id": 17424, "token": "bg", "merges": "b g", "raw_count": 339275, "count": 339275, "decode_str": "bg"} -{"id": 52721, "token": "\u00e7\u0124\u0122", "merges": "\u00e7\u0124 \u0122", "raw_count": 339284, "count": 339284, "decode_str": "\u7080"} -{"id": 2887, "token": "see", "merges": "se e", "raw_count": 290724, "count": 339432, "decode_str": "see"} -{"id": 48184, "token": "1932", "merges": "19 32", "raw_count": 339668, "count": 339668, "decode_str": "1932"} -{"id": 3371, "token": "\u0120jo", "merges": "\u0120j o", "raw_count": 43204, "count": 339750, "decode_str": " jo"} -{"id": 11241, "token": "Update", "merges": "Up date", "raw_count": 340127, "count": 340127, "decode_str": "Update"} -{"id": 35392, "token": "\u00e7\u00b6", "merges": "\u00e7 \u00b6", "raw_count": 97111, "count": 340195, "decode_str": "\ufffd"} -{"id": 22156, "token": "Auto", "merges": "Aut o", "raw_count": 340196, "count": 340196, "decode_str": "Auto"} -{"id": 10612, "token": "Sl", "merges": "S l", "raw_count": 256648, "count": 340410, "decode_str": "Sl"} -{"id": 4151, "token": "\u0120inform", "merges": "\u0120in form", "raw_count": 94955, "count": 340597, "decode_str": " inform"} -{"id": 5894, "token": "zon", "merges": "z on", "raw_count": 34556, "count": 340611, "decode_str": "zon"} -{"id": 54252, "token": "\u00e9\u0137\u012b", "merges": "\u00e9\u0137 \u012b", "raw_count": 340732, "count": 340732, "decode_str": "\u9549"} -{"id": 22067, "token": "253", "merges": "25 3", "raw_count": 340775, "count": 340775, "decode_str": "253"} -{"id": 50507, "token": "\u00e4\u00bb\u0140", "merges": "\u00e4\u00bb \u0140", "raw_count": 340777, "count": 340777, "decode_str": "\u4ede"} -{"id": 19558, "token": "uu", "merges": "u u", "raw_count": 340783, "count": 340783, "decode_str": "uu"} -{"id": 6366, "token": "ERT", "merges": "ER T", "raw_count": 140592, "count": 341049, "decode_str": "ERT"} -{"id": 11530, "token": "Stud", "merges": "St ud", "raw_count": 38619, "count": 341360, "decode_str": "Stud"} -{"id": 53544, "token": "\u00e8\u0126\u013a", "merges": "\u00e8\u0126 \u013a", "raw_count": 341436, "count": 341436, "decode_str": "\u8118"} -{"id": 10382, "token": "\u0120serial", "merges": "\u0120ser ial", "raw_count": 296711, "count": 341540, "decode_str": " serial"} -{"id": 4359, "token": "\u0120clust", "merges": "\u0120cl ust", "raw_count": 6207, "count": 341619, "decode_str": " clust"} -{"id": 7646, "token": "\u0120template", "merges": "\u0120tem plate", "raw_count": 341630, "count": 341630, "decode_str": " template"} -{"id": 5740, "token": "\u0120description", "merges": "\u0120descript ion", "raw_count": 341732, "count": 341732, "decode_str": " description"} -{"id": 30784, "token": "JR", "merges": "J R", "raw_count": 341911, "count": 341911, "decode_str": "JR"} -{"id": 8546, "token": "Spec", "merges": "S pec", "raw_count": 253538, "count": 342007, "decode_str": "Spec"} -{"id": 28229, "token": "(\"/", "merges": "(\" /", "raw_count": 342038, "count": 342038, "decode_str": "(\"/"} -{"id": 20743, "token": "RX", "merges": "R X", "raw_count": 342111, "count": 342111, "decode_str": "RX"} -{"id": 26520, "token": "proxy", "merges": "pro xy", "raw_count": 342342, "count": 342342, "decode_str": "proxy"} -{"id": 23741, "token": "]*", "merges": "] *", "raw_count": 342399, "count": 342399, "decode_str": "]*"} -{"id": 1805, "token": "\u0120better", "merges": "\u0120bet ter", "raw_count": 342434, "count": 342434, "decode_str": " better"} -{"id": 2949, "token": "\u0120IN", "merges": "\u0120I N", "raw_count": 151065, "count": 342475, "decode_str": " IN"} -{"id": 8242, "token": "ORD", "merges": "OR D", "raw_count": 108629, "count": 342482, "decode_str": "ORD"} -{"id": 3598, "token": "\u0120constit", "merges": "\u0120const it", "raw_count": 4479, "count": 342814, "decode_str": " constit"} -{"id": 54287, "token": "\u00e9\u0139\u00be", "merges": "\u00e9\u0139 \u00be", "raw_count": 342905, "count": 342905, "decode_str": "\u95fe"} -{"id": 23454, "token": "details", "merges": "det ails", "raw_count": 342967, "count": 342967, "decode_str": "details"} -{"id": 11502, "token": "NET", "merges": "N ET", "raw_count": 343028, "count": 343028, "decode_str": "NET"} -{"id": 54222, "token": "\u00e9\u0136\u0128", "merges": "\u00e9\u0136 \u0128", "raw_count": 343034, "count": 343034, "decode_str": "\u9506"} -{"id": 39757, "token": "quee", "merges": "que e", "raw_count": 343090, "count": 343090, "decode_str": "quee"} -{"id": 12929, "token": "nex", "merges": "ne x", "raw_count": 100055, "count": 343098, "decode_str": "nex"} -{"id": 2376, "token": "stit", "merges": "st it", "raw_count": 62721, "count": 343199, "decode_str": "stit"} -{"id": 13148, "token": "\u0120tensor", "merges": "\u0120tens or", "raw_count": 343412, "count": 343412, "decode_str": " tensor"} -{"id": 38016, "token": "\u0120Optional", "merges": "\u0120Opt ional", "raw_count": 343482, "count": 343482, "decode_str": " Optional"} -{"id": 1158, "token": "\u0120think", "merges": "\u0120th ink", "raw_count": 284077, "count": 343522, "decode_str": " think"} -{"id": 38599, "token": "610", "merges": "6 10", "raw_count": 343946, "count": 343946, "decode_str": "610"} -{"id": 26631, "token": "PHP", "merges": "PH P", "raw_count": 343969, "count": 343969, "decode_str": "PHP"} -{"id": 52688, "token": "\u00e6\u00ba\u00b4", "merges": "\u00e6\u00ba \u00b4", "raw_count": 344111, "count": 344111, "decode_str": "\u6eb4"} -{"id": 50567, "token": "\u00e4\u00bd\u00af", "merges": "\u00e4\u00bd \u00af", "raw_count": 344147, "count": 344147, "decode_str": "\u4f6f"} -{"id": 11001, "token": "Mult", "merges": "M ult", "raw_count": 109373, "count": 344267, "decode_str": "Mult"} -{"id": 1921, "token": "\u0120reason", "merges": "\u0120re ason", "raw_count": 237100, "count": 344481, "decode_str": " reason"} -{"id": 24841, "token": "topic", "merges": "top ic", "raw_count": 344541, "count": 344541, "decode_str": "topic"} -{"id": 29006, "token": "?.", "merges": "? .", "raw_count": 344595, "count": 344595, "decode_str": "?."} -{"id": 18446, "token": "FB", "merges": "F B", "raw_count": 344695, "count": 344695, "decode_str": "FB"} -{"id": 7704, "token": "road", "merges": "ro ad", "raw_count": 100587, "count": 344735, "decode_str": "road"} -{"id": 7396, "token": "ORT", "merges": "OR T", "raw_count": 120692, "count": 344838, "decode_str": "ORT"} -{"id": 50641, "token": "\u00e5\u0123\u012a", "merges": "\u00e5\u0123 \u012a", "raw_count": 344851, "count": 344851, "decode_str": "\u5048"} -{"id": 3330, "token": "\u0120win", "merges": "\u0120w in", "raw_count": 275022, "count": 344938, "decode_str": " win"} -{"id": 2015, "token": "********", "merges": "**** ****", "raw_count": 117503, "count": 344948, "decode_str": "********"} -{"id": 1475, "token": "\u0120around", "merges": "\u0120ar ound", "raw_count": 344952, "count": 344952, "decode_str": " around"} -{"id": 12871, "token": "Bit", "merges": "B it", "raw_count": 312148, "count": 345082, "decode_str": "Bit"} -{"id": 28183, "token": "AAA", "merges": "AA A", "raw_count": 345135, "count": 345135, "decode_str": "AAA"} -{"id": 6854, "token": "utor", "merges": "ut or", "raw_count": 207160, "count": 345202, "decode_str": "utor"} -{"id": 22639, "token": "\u0120timeout", "merges": "\u0120time out", "raw_count": 345308, "count": 345308, "decode_str": " timeout"} -{"id": 3674, "token": "\u0120mach", "merges": "\u0120m ach", "raw_count": 14160, "count": 345313, "decode_str": " mach"} -{"id": 14398, "token": "uler", "merges": "ul er", "raw_count": 338292, "count": 345406, "decode_str": "uler"} -{"id": 6724, "token": "\u0120Ret", "merges": "\u0120R et", "raw_count": 44734, "count": 345672, "decode_str": " Ret"} -{"id": 3290, "token": "\u0120quality", "merges": "\u0120qu ality", "raw_count": 345916, "count": 345916, "decode_str": " quality"} -{"id": 33031, "token": "640", "merges": "6 40", "raw_count": 345931, "count": 345931, "decode_str": "640"} -{"id": 45061, "token": "dj", "merges": "d j", "raw_count": 346003, "count": 346003, "decode_str": "dj"} -{"id": 9068, "token": "nc", "merges": "n c", "raw_count": 333575, "count": 346064, "decode_str": "nc"} -{"id": 1897, "token": "\u0120days", "merges": "\u0120d ays", "raw_count": 346107, "count": 346107, "decode_str": " days"} -{"id": 8085, "token": "\u0120split", "merges": "\u0120s plit", "raw_count": 346186, "count": 346186, "decode_str": " split"} -{"id": 2959, "token": "\u0120received", "merges": "\u0120rece ived", "raw_count": 346473, "count": 346473, "decode_str": " received"} -{"id": 3058, "token": "\u0120needed", "merges": "\u0120need ed", "raw_count": 346520, "count": 346520, "decode_str": " needed"} -{"id": 1654, "token": "\u0120happ", "merges": "\u0120ha pp", "raw_count": 4666, "count": 346559, "decode_str": " happ"} -{"id": 10265, "token": "\u0120sustain", "merges": "\u0120sust ain", "raw_count": 22124, "count": 346890, "decode_str": " sustain"} -{"id": 2493, "token": "\u0120relations", "merges": "\u0120rel ations", "raw_count": 150413, "count": 346892, "decode_str": " relations"} -{"id": 24614, "token": "455", "merges": "45 5", "raw_count": 346918, "count": 346918, "decode_str": "455"} -{"id": 2419, "token": "\u0120house", "merges": "\u0120h ouse", "raw_count": 278086, "count": 346940, "decode_str": " house"} -{"id": 13804, "token": "Har", "merges": "H ar", "raw_count": 231605, "count": 346949, "decode_str": "Har"} -{"id": 6775, "token": "rivate", "merges": "riv ate", "raw_count": 3047, "count": 347072, "decode_str": "rivate"} -{"id": 14805, "token": "\u012001", "merges": "\u01200 1", "raw_count": 347102, "count": 347102, "decode_str": " 01"} -{"id": 19686, "token": "COL", "merges": "C OL", "raw_count": 159223, "count": 347171, "decode_str": "COL"} -{"id": 1725, "token": "\u0120hig", "merges": "\u0120h ig", "raw_count": 4416, "count": 347237, "decode_str": " hig"} -{"id": 2475, "token": "\u0120comput", "merges": "\u0120comp ut", "raw_count": 3806, "count": 347388, "decode_str": " comput"} -{"id": 52053, "token": "\u00e6\u0135\u0140", "merges": "\u00e6\u0135 \u0140", "raw_count": 347604, "count": 347604, "decode_str": "\u64de"} -{"id": 32315, "token": "assertEquals", "merges": "assert Equals", "raw_count": 347633, "count": 347633, "decode_str": "assertEquals"} -{"id": 9784, "token": "common", "merges": "com mon", "raw_count": 342906, "count": 347708, "decode_str": "common"} -{"id": 25340, "token": "verb", "merges": "ver b", "raw_count": 96474, "count": 347818, "decode_str": "verb"} -{"id": 9150, "token": "Dec", "merges": "D ec", "raw_count": 191131, "count": 347889, "decode_str": "Dec"} -{"id": 18609, "token": "trl", "merges": "tr l", "raw_count": 6557, "count": 347995, "decode_str": "trl"} -{"id": 4181, "token": "\u0120distance", "merges": "\u0120dist ance", "raw_count": 348199, "count": 348199, "decode_str": " distance"} -{"id": 2194, "token": "];", "merges": "] ;", "raw_count": 316391, "count": 348334, "decode_str": "];"} -{"id": 11104, "token": "\u0120attribute", "merges": "\u0120att ribute", "raw_count": 348440, "count": 348440, "decode_str": " attribute"} -{"id": 4100, "token": "gorith", "merges": "gor ith", "raw_count": 3150, "count": 348458, "decode_str": "gorith"} -{"id": 22109, "token": "\u0120parser", "merges": "\u0120p arser", "raw_count": 348484, "count": 348484, "decode_str": " parser"} -{"id": 3219, "token": "gest", "merges": "g est", "raw_count": 46313, "count": 348565, "decode_str": "gest"} -{"id": 20199, "token": "single", "merges": "sing le", "raw_count": 348770, "count": 348770, "decode_str": "single"} -{"id": 3370, "token": "illi", "merges": "ill i", "raw_count": 85858, "count": 348814, "decode_str": "illi"} -{"id": 2642, "token": "\u0120dri", "merges": "\u0120d ri", "raw_count": 7924, "count": 348858, "decode_str": " dri"} -{"id": 20869, "token": "SEC", "merges": "SE C", "raw_count": 348880, "count": 348880, "decode_str": "SEC"} -{"id": 9147, "token": "Pat", "merges": "P at", "raw_count": 154999, "count": 348926, "decode_str": "Pat"} -{"id": 5639, "token": "\u0120foreign", "merges": "\u0120fore ign", "raw_count": 331228, "count": 348960, "decode_str": " foreign"} -{"id": 3757, "token": "gn", "merges": "g n", "raw_count": 195588, "count": 348990, "decode_str": "gn"} -{"id": 3888, "token": "\u0120images", "merges": "\u0120im ages", "raw_count": 348999, "count": 348999, "decode_str": " images"} -{"id": 25354, "token": "symbol", "merges": "s ymbol", "raw_count": 349034, "count": 349034, "decode_str": "symbol"} -{"id": 4761, "token": "ersion", "merges": "ers ion", "raw_count": 20959, "count": 349136, "decode_str": "ersion"} -{"id": 40340, "token": "GMP", "merges": "G MP", "raw_count": 349140, "count": 349140, "decode_str": "GMP"} -{"id": 22337, "token": "created", "merges": "cre ated", "raw_count": 349233, "count": 349233, "decode_str": "created"} -{"id": 11556, "token": "\u0120cache", "merges": "\u0120c ache", "raw_count": 349265, "count": 349265, "decode_str": " cache"} -{"id": 23398, "token": "WC", "merges": "W C", "raw_count": 349397, "count": 349397, "decode_str": "WC"} -{"id": 6036, "token": "\u0120joint", "merges": "\u0120j oint", "raw_count": 284933, "count": 349459, "decode_str": " joint"} -{"id": 13283, "token": "\u0120hash", "merges": "\u0120has h", "raw_count": 349489, "count": 349489, "decode_str": " hash"} -{"id": 5242, "token": "aly", "merges": "al y", "raw_count": 148956, "count": 349492, "decode_str": "aly"} -{"id": 12442, "token": "Met", "merges": "M et", "raw_count": 243678, "count": 349540, "decode_str": "Met"} -{"id": 51620, "token": "\u00e5\u00bd\u0139", "merges": "\u00e5\u00bd \u0139", "raw_count": 349555, "count": 349555, "decode_str": "\u5f57"} -{"id": 53445, "token": "\u00e8\u0122\u0128", "merges": "\u00e8\u0122 \u0128", "raw_count": 349696, "count": 349696, "decode_str": "\u8006"} -{"id": 28941, "token": "1234", "merges": "12 34", "raw_count": 349699, "count": 349699, "decode_str": "1234"} -{"id": 8769, "token": "*^", "merges": "* ^", "raw_count": 349812, "count": 349812, "decode_str": "*^"} -{"id": 4242, "token": "\u0120failed", "merges": "\u0120fail ed", "raw_count": 349846, "count": 349846, "decode_str": " failed"} -{"id": 15085, "token": "igin", "merges": "ig in", "raw_count": 5053, "count": 349878, "decode_str": "igin"} -{"id": 6245, "token": "ameter", "merges": "am eter", "raw_count": 46193, "count": 349944, "decode_str": "ameter"} -{"id": 1918, "token": "\u0120give", "merges": "\u0120g ive", "raw_count": 350001, "count": 350001, "decode_str": " give"} -{"id": 11635, "token": "enda", "merges": "end a", "raw_count": 69675, "count": 350137, "decode_str": "enda"} -{"id": 3007, "token": "\u0120coll", "merges": "\u0120col l", "raw_count": 84117, "count": 350179, "decode_str": " coll"} -{"id": 51154, "token": "\u00e5\u013d\u0136", "merges": "\u00e5\u013d \u0136", "raw_count": 350195, "count": 350195, "decode_str": "\u56d4"} -{"id": 16910, "token": "Tim", "merges": "T im", "raw_count": 285039, "count": 350238, "decode_str": "Tim"} -{"id": 9434, "token": "ASE", "merges": "AS E", "raw_count": 161194, "count": 350317, "decode_str": "ASE"} -{"id": 5733, "token": "\u0120Add", "merges": "\u0120A dd", "raw_count": 248920, "count": 350421, "decode_str": " Add"} -{"id": 3603, "token": "\u0120elements", "merges": "\u0120ele ments", "raw_count": 350619, "count": 350619, "decode_str": " elements"} -{"id": 22917, "token": "EB", "merges": "E B", "raw_count": 350648, "count": 350648, "decode_str": "EB"} -{"id": 4274, "token": "\u0120deb", "merges": "\u0120de b", "raw_count": 22360, "count": 350701, "decode_str": " deb"} -{"id": 2541, "token": "respond", "merges": "resp ond", "raw_count": 48315, "count": 350715, "decode_str": "respond"} -{"id": 2200, "token": "ried", "merges": "ri ed", "raw_count": 44866, "count": 350716, "decode_str": "ried"} -{"id": 3089, "token": "\u0120chall", "merges": "\u0120ch all", "raw_count": 4566, "count": 350830, "decode_str": " chall"} -{"id": 4690, "token": "rael", "merges": "ra el", "raw_count": 338188, "count": 350870, "decode_str": "rael"} -{"id": 8903, "token": "Ag", "merges": "A g", "raw_count": 317913, "count": 350899, "decode_str": "Ag"} -{"id": 50556, "token": "\u00e4\u00bd\u013c", "merges": "\u00e4\u00bd \u013c", "raw_count": 350919, "count": 350919, "decode_str": "\u4f5a"} -{"id": 3009, "token": "ledge", "merges": "led ge", "raw_count": 44159, "count": 350968, "decode_str": "ledge"} -{"id": 41127, "token": "GRE", "merges": "G RE", "raw_count": 350984, "count": 350984, "decode_str": "GRE"} -{"id": 26562, "token": "WW", "merges": "W W", "raw_count": 351032, "count": 351032, "decode_str": "WW"} -{"id": 52929, "token": "\u00e7\u0139\u012a", "merges": "\u00e7\u0139 \u012a", "raw_count": 351076, "count": 351076, "decode_str": "\u75c8"} -{"id": 3341, "token": "inally", "merges": "in ally", "raw_count": 301817, "count": 351110, "decode_str": "inally"} -{"id": 24208, "token": "289", "merges": "28 9", "raw_count": 351220, "count": 351220, "decode_str": "289"} -{"id": 25879, "token": "\u0120Qt", "merges": "\u0120Q t", "raw_count": 351268, "count": 351268, "decode_str": " Qt"} -{"id": 52096, "token": "\u00e6\u0138\u00a1", "merges": "\u00e6\u0138 \u00a1", "raw_count": 351308, "count": 351308, "decode_str": "\u65a1"} -{"id": 54151, "token": "\u00e9\u0124\u0137", "merges": "\u00e9\u0124 \u0137", "raw_count": 351459, "count": 351459, "decode_str": "\u9095"} -{"id": 27644, "token": "signal", "merges": "sign al", "raw_count": 351472, "count": 351472, "decode_str": "signal"} -{"id": 6118, "token": "ners", "merges": "n ers", "raw_count": 100291, "count": 351716, "decode_str": "ners"} -{"id": 2454, "token": "\u0120face", "merges": "\u0120f ace", "raw_count": 318711, "count": 351721, "decode_str": " face"} -{"id": 7649, "token": "\u0120mand", "merges": "\u0120m and", "raw_count": 19261, "count": 351829, "decode_str": " mand"} -{"id": 9389, "token": "two", "merges": "t wo", "raw_count": 351847, "count": 351847, "decode_str": "two"} -{"id": 31169, "token": "kj", "merges": "k j", "raw_count": 352282, "count": 352282, "decode_str": "kj"} -{"id": 41680, "token": "710", "merges": "7 10", "raw_count": 352359, "count": 352359, "decode_str": "710"} -{"id": 28904, "token": "boxes", "merges": "box es", "raw_count": 352447, "count": 352447, "decode_str": "boxes"} -{"id": 52625, "token": "\u00e6\u00b6\u00bf", "merges": "\u00e6\u00b6 \u00bf", "raw_count": 352447, "count": 352447, "decode_str": "\u6dbf"} -{"id": 13119, "token": "\u0120Create", "merges": "\u0120C reate", "raw_count": 352549, "count": 352549, "decode_str": " Create"} -{"id": 23402, "token": "296", "merges": "29 6", "raw_count": 352599, "count": 352599, "decode_str": "296"} -{"id": 3065, "token": "ferences", "merges": "fe rences", "raw_count": 114977, "count": 352617, "decode_str": "ferences"} -{"id": 9706, "token": "\u0120encoding", "merges": "\u0120enc oding", "raw_count": 352632, "count": 352632, "decode_str": " encoding"} -{"id": 4516, "token": "\u0120supported", "merges": "\u0120support ed", "raw_count": 352642, "count": 352642, "decode_str": " supported"} -{"id": 16065, "token": "switch", "merges": "sw itch", "raw_count": 352649, "count": 352649, "decode_str": "switch"} -{"id": 53508, "token": "\u00e8\u0125\u0126", "merges": "\u00e8\u0125 \u0126", "raw_count": 352649, "count": 352649, "decode_str": "\u80c4"} -{"id": 51011, "token": "\u00e5\u0133\u00b8", "merges": "\u00e5\u0133 \u00b8", "raw_count": 352730, "count": 352730, "decode_str": "\u5478"} -{"id": 8678, "token": "iki", "merges": "ik i", "raw_count": 167534, "count": 352799, "decode_str": "iki"} -{"id": 53068, "token": "\u00e7\u0142\u00b7", "merges": "\u00e7\u0142 \u00b7", "raw_count": 352799, "count": 352799, "decode_str": "\u7837"} -{"id": 18744, "token": "Michael", "merges": "Mich ael", "raw_count": 352817, "count": 352817, "decode_str": "Michael"} -{"id": 8972, "token": "009", "merges": "00 9", "raw_count": 352899, "count": 352899, "decode_str": "009"} -{"id": 45386, "token": "820", "merges": "8 20", "raw_count": 353068, "count": 353068, "decode_str": "820"} -{"id": 5040, "token": "cons", "merges": "con s", "raw_count": 201316, "count": 353130, "decode_str": "cons"} -{"id": 2100, "token": "\u0120circ", "merges": "\u0120c irc", "raw_count": 11866, "count": 353388, "decode_str": " circ"} -{"id": 22011, "token": "329", "merges": "32 9", "raw_count": 353427, "count": 353427, "decode_str": "329"} -{"id": 17151, "token": "Hy", "merges": "H y", "raw_count": 184127, "count": 353437, "decode_str": "Hy"} -{"id": 5542, "token": "\u0120stream", "merges": "\u0120st ream", "raw_count": 335950, "count": 353610, "decode_str": " stream"} -{"id": 32023, "token": "MHz", "merges": "M Hz", "raw_count": 353742, "count": 353742, "decode_str": "MHz"} -{"id": 3342, "token": "bf", "merges": "b f", "raw_count": 351178, "count": 353750, "decode_str": "bf"} -{"id": 5012, "token": "\u0120reports", "merges": "\u0120report s", "raw_count": 353837, "count": 353837, "decode_str": " reports"} -{"id": 51337, "token": "\u00e5\u00a6\u0135", "merges": "\u00e5\u00a6 \u0135", "raw_count": 354178, "count": 354178, "decode_str": "\u5993"} -{"id": 5436, "token": "apping", "merges": "app ing", "raw_count": 70615, "count": 354228, "decode_str": "apping"} -{"id": 16799, "token": ")~", "merges": ") ~", "raw_count": 354305, "count": 354305, "decode_str": ")~"} -{"id": 53025, "token": "\u00e7\u013f\u00a2", "merges": "\u00e7\u013f \u00a2", "raw_count": 354479, "count": 354479, "decode_str": "\u7762"} -{"id": 8846, "token": "QU", "merges": "Q U", "raw_count": 317906, "count": 354552, "decode_str": "QU"} -{"id": 40967, "token": "edges", "merges": "ed ges", "raw_count": 354558, "count": 354558, "decode_str": "edges"} -{"id": 1642, "token": "\u0120ask", "merges": "\u0120as k", "raw_count": 155123, "count": 354560, "decode_str": " ask"} -{"id": 2206, "token": "\u0120sat", "merges": "\u0120s at", "raw_count": 86050, "count": 354567, "decode_str": " sat"} -{"id": 3236, "token": "\u0120original", "merges": "\u0120orig inal", "raw_count": 354708, "count": 354708, "decode_str": " original"} -{"id": 5967, "token": "house", "merges": "h ouse", "raw_count": 309229, "count": 354865, "decode_str": "house"} -{"id": 49227, "token": "699", "merges": "6 99", "raw_count": 354959, "count": 354959, "decode_str": "699"} -{"id": 11950, "token": "changed", "merges": "ch anged", "raw_count": 319068, "count": 354979, "decode_str": "changed"} -{"id": 24803, "token": "278", "merges": "27 8", "raw_count": 355052, "count": 355052, "decode_str": "278"} -{"id": 2645, "token": "\u0120cy", "merges": "\u0120c y", "raw_count": 143264, "count": 355061, "decode_str": " cy"} -{"id": 3124, "token": "theta", "merges": "the ta", "raw_count": 355112, "count": 355112, "decode_str": "theta"} -{"id": 19097, "token": "\u0120tmp", "merges": "\u0120t mp", "raw_count": 355130, "count": 355130, "decode_str": " tmp"} -{"id": 52226, "token": "\u00e6\u013f\u00b5", "merges": "\u00e6\u013f \u00b5", "raw_count": 355180, "count": 355180, "decode_str": "\u6775"} -{"id": 578, "token": "_{", "merges": "_ {", "raw_count": 255236, "count": 355346, "decode_str": "_{"} -{"id": 43698, "token": "780", "merges": "7 80", "raw_count": 355453, "count": 355453, "decode_str": "780"} -{"id": 34458, "token": "540", "merges": "5 40", "raw_count": 355473, "count": 355473, "decode_str": "540"} -{"id": 53249, "token": "\u00e7\u00ae\u00b4", "merges": "\u00e7\u00ae \u00b4", "raw_count": 355542, "count": 355542, "decode_str": "\u7bb4"} -{"id": 10203, "token": "Gener", "merges": "G ener", "raw_count": 69651, "count": 355549, "decode_str": "Gener"} -{"id": 50605, "token": "\u00e4\u00bf\u0141", "merges": "\u00e4\u00bf \u0141", "raw_count": 355638, "count": 355638, "decode_str": "\u4fdf"} -{"id": 15155, "token": "Mo", "merges": "M o", "raw_count": 355667, "count": 355667, "decode_str": "Mo"} -{"id": 14794, "token": "Ins", "merges": "In s", "raw_count": 273827, "count": 355856, "decode_str": "Ins"} -{"id": 11872, "token": "outer", "merges": "ou ter", "raw_count": 131168, "count": 355882, "decode_str": "outer"} -{"id": 26651, "token": "actual", "merges": "act ual", "raw_count": 356012, "count": 356012, "decode_str": "actual"} -{"id": 7122, "token": "\u0120god", "merges": "\u0120g od", "raw_count": 337692, "count": 356108, "decode_str": " god"} -{"id": 3310, "token": "\u0120contract", "merges": "\u0120cont ract", "raw_count": 171638, "count": 356136, "decode_str": " contract"} -{"id": 29228, "token": "Inc", "merges": "In c", "raw_count": 356159, "count": 356159, "decode_str": "Inc"} -{"id": 24748, "token": "IPS", "merges": "IP S", "raw_count": 356348, "count": 356348, "decode_str": "IPS"} -{"id": 7632, "token": "\u0120nodes", "merges": "\u0120n odes", "raw_count": 356399, "count": 356399, "decode_str": " nodes"} -{"id": 51097, "token": "\u00e5\u0137\u00ae", "merges": "\u00e5\u0137 \u00ae", "raw_count": 356526, "count": 356526, "decode_str": "\u556e"} -{"id": 6420, "token": "\u0120south", "merges": "\u0120s outh", "raw_count": 349647, "count": 356532, "decode_str": " south"} -{"id": 53638, "token": "\u00e8\u012d\u012d", "merges": "\u00e8\u012d \u012d", "raw_count": 356701, "count": 356701, "decode_str": "\u82cb"} -{"id": 23922, "token": "338", "merges": "33 8", "raw_count": 356727, "count": 356727, "decode_str": "338"} -{"id": 1802, "token": "\u0120belie", "merges": "\u0120bel ie", "raw_count": 1637, "count": 357072, "decode_str": " belie"} -{"id": 12790, "token": "flags", "merges": "fl ags", "raw_count": 357074, "count": 357074, "decode_str": "flags"} -{"id": 14541, "token": "found", "merges": "f ound", "raw_count": 357092, "count": 357092, "decode_str": "found"} -{"id": 3964, "token": "ham", "merges": "h am", "raw_count": 241210, "count": 357145, "decode_str": "ham"} -{"id": 6069, "token": "\u0120nuclear", "merges": "\u0120nucle ar", "raw_count": 357188, "count": 357188, "decode_str": " nuclear"} -{"id": 30928, "token": "CSS", "merges": "C SS", "raw_count": 357284, "count": 357284, "decode_str": "CSS"} -{"id": 10495, "token": "forward", "merges": "for ward", "raw_count": 351093, "count": 357345, "decode_str": "forward"} -{"id": 24211, "token": "Linear", "merges": "Line ar", "raw_count": 356676, "count": 357572, "decode_str": "Linear"} -{"id": 4236, "token": "\u0120selected", "merges": "\u0120se lected", "raw_count": 357593, "count": 357593, "decode_str": " selected"} -{"id": 50808, "token": "\u00e5\u012b\u00bd", "merges": "\u00e5\u012b \u00bd", "raw_count": 357676, "count": 357676, "decode_str": "\u527d"} -{"id": 9860, "token": "\u0120grid", "merges": "\u0120gr id", "raw_count": 357701, "count": 357701, "decode_str": " grid"} -{"id": 2626, "token": "\u0120third", "merges": "\u0120th ird", "raw_count": 357718, "count": 357718, "decode_str": " third"} -{"id": 21124, "token": "\u0120redirect", "merges": "\u0120red irect", "raw_count": 357830, "count": 357830, "decode_str": " redirect"} -{"id": 3623, "token": "lier", "merges": "li er", "raw_count": 230899, "count": 357862, "decode_str": "lier"} -{"id": 2047, "token": "ograph", "merges": "og raph", "raw_count": 26183, "count": 357926, "decode_str": "ograph"} -{"id": 19751, "token": "question", "merges": "quest ion", "raw_count": 357951, "count": 357951, "decode_str": "question"} -{"id": 15362, "token": "___", "merges": "__ _", "raw_count": 358022, "count": 358022, "decode_str": "___"} -{"id": 23659, "token": ",.", "merges": ", .", "raw_count": 358089, "count": 358089, "decode_str": ",."} -{"id": 13996, "token": "Step", "merges": "Ste p", "raw_count": 358128, "count": 358128, "decode_str": "Step"} -{"id": 12995, "token": "SELECT", "merges": "SE LECT", "raw_count": 358136, "count": 358136, "decode_str": "SELECT"} -{"id": 10914, "token": "FD", "merges": "F D", "raw_count": 358115, "count": 358170, "decode_str": "FD"} -{"id": 1781, "token": "\u0120large", "merges": "\u0120lar ge", "raw_count": 358291, "count": 358291, "decode_str": " large"} -{"id": 54508, "token": "\u00e9\u00aa\u00a1", "merges": "\u00e9\u00aa \u00a1", "raw_count": 358830, "count": 358830, "decode_str": "\u9aa1"} -{"id": 31070, "token": "Qt", "merges": "Q t", "raw_count": 358896, "count": 358896, "decode_str": "Qt"} -{"id": 4170, "token": "aily", "merges": "ail y", "raw_count": 31585, "count": 358990, "decode_str": "aily"} -{"id": 15996, "token": "}'", "merges": "} '", "raw_count": 359177, "count": 359177, "decode_str": "}'"} -{"id": 8605, "token": "\u0120[[", "merges": "\u0120[ [", "raw_count": 359055, "count": 359246, "decode_str": " [["} -{"id": 5581, "token": "php", "merges": "ph p", "raw_count": 359492, "count": 359492, "decode_str": "php"} -{"id": 40199, "token": "nice", "merges": "n ice", "raw_count": 359584, "count": 359584, "decode_str": "nice"} -{"id": 10496, "token": "015", "merges": "01 5", "raw_count": 359734, "count": 359734, "decode_str": "015"} -{"id": 15020, "token": "+)", "merges": "+ )", "raw_count": 201769, "count": 359738, "decode_str": "+)"} -{"id": 23163, "token": "279", "merges": "27 9", "raw_count": 359845, "count": 359845, "decode_str": "279"} -{"id": 8901, "token": "isa", "merges": "is a", "raw_count": 358330, "count": 359875, "decode_str": "isa"} -{"id": 24948, "token": "402", "merges": "40 2", "raw_count": 359907, "count": 359907, "decode_str": "402"} -{"id": 53404, "token": "\u00e7\u00bc\u00b0", "merges": "\u00e7\u00bc \u00b0", "raw_count": 359925, "count": 359925, "decode_str": "\u7f30"} -{"id": 10816, "token": "person", "merges": "p erson", "raw_count": 355340, "count": 360104, "decode_str": "person"} -{"id": 3881, "token": "joy", "merges": "j oy", "raw_count": 122270, "count": 360110, "decode_str": "joy"} -{"id": 41122, "token": "freq", "merges": "f req", "raw_count": 360509, "count": 360509, "decode_str": "freq"} -{"id": 5800, "token": "isd", "merges": "is d", "raw_count": 242031, "count": 360747, "decode_str": "isd"} -{"id": 34297, "token": "KM", "merges": "K M", "raw_count": 360757, "count": 360757, "decode_str": "KM"} -{"id": 7172, "token": "oday", "merges": "od ay", "raw_count": 25085, "count": 360861, "decode_str": "oday"} -{"id": 54224, "token": "\u00e9\u0136\u012b", "merges": "\u00e9\u0136 \u012b", "raw_count": 360873, "count": 360873, "decode_str": "\u9509"} -{"id": 9292, "token": "tax", "merges": "ta x", "raw_count": 223667, "count": 360913, "decode_str": "tax"} -{"id": 2535, "token": "\u0120complet", "merges": "\u0120comp let", "raw_count": 8909, "count": 360995, "decode_str": " complet"} -{"id": 2770, "token": "\u0120focus", "merges": "\u0120f ocus", "raw_count": 215058, "count": 361011, "decode_str": " focus"} -{"id": 43996, "token": "DJ", "merges": "D J", "raw_count": 361182, "count": 361182, "decode_str": "DJ"} -{"id": 2027, "token": "hing", "merges": "h ing", "raw_count": 42883, "count": 361266, "decode_str": "hing"} -{"id": 12161, "token": "Pass", "merges": "P ass", "raw_count": 238700, "count": 361334, "decode_str": "Pass"} -{"id": 4714, "token": "well", "merges": "w ell", "raw_count": 329431, "count": 361377, "decode_str": "well"} -{"id": 19332, "token": "194", "merges": "19 4", "raw_count": 361401, "count": 361401, "decode_str": "194"} -{"id": 10560, "token": "TYPE", "merges": "T YPE", "raw_count": 361487, "count": 361487, "decode_str": "TYPE"} -{"id": 6382, "token": "\u0120polic", "merges": "\u0120pol ic", "raw_count": 5238, "count": 361594, "decode_str": " polic"} -{"id": 9466, "token": "OCK", "merges": "OC K", "raw_count": 150000, "count": 361639, "decode_str": "OCK"} -{"id": 1526, "token": "ething", "merges": "eth ing", "raw_count": 2499, "count": 361718, "decode_str": "ething"} -{"id": 10282, "token": "Work", "merges": "W ork", "raw_count": 279281, "count": 361796, "decode_str": "Work"} -{"id": 27043, "token": "998", "merges": "99 8", "raw_count": 361830, "count": 361830, "decode_str": "998"} -{"id": 1537, "token": "\u0120might", "merges": "\u0120m ight", "raw_count": 351921, "count": 361841, "decode_str": " might"} -{"id": 37155, "token": "470", "merges": "4 70", "raw_count": 361889, "count": 361889, "decode_str": "470"} -{"id": 15004, "token": "cert", "merges": "c ert", "raw_count": 360546, "count": 361907, "decode_str": "cert"} -{"id": 9379, "token": "Ob", "merges": "O b", "raw_count": 64768, "count": 362064, "decode_str": "Ob"} -{"id": 52372, "token": "\u00e6\u00a8\u00bd", "merges": "\u00e6\u00a8 \u00bd", "raw_count": 362137, "count": 362137, "decode_str": "\u6a3d"} -{"id": 11551, "token": "shift", "merges": "sh ift", "raw_count": 353698, "count": 362481, "decode_str": "shift"} -{"id": 2282, "token": "\u0120course", "merges": "\u0120cour se", "raw_count": 362544, "count": 362544, "decode_str": " course"} -{"id": 6720, "token": "abilities", "merges": "ab ilities", "raw_count": 113776, "count": 362602, "decode_str": "abilities"} -{"id": 1895, "token": "\u0120problem", "merges": "\u0120proble m", "raw_count": 352659, "count": 362765, "decode_str": " problem"} -{"id": 22524, "token": "unique", "merges": "un ique", "raw_count": 362828, "count": 362828, "decode_str": "unique"} -{"id": 8422, "token": "-(", "merges": "- (", "raw_count": 362892, "count": 362892, "decode_str": "-("} -{"id": 2500, "token": "\u0120tw", "merges": "\u0120t w", "raw_count": 94983, "count": 362925, "decode_str": " tw"} -{"id": 3081, "token": "\u0120additional", "merges": "\u0120addition al", "raw_count": 362929, "count": 362929, "decode_str": " additional"} -{"id": 3510, "token": "\u0120types", "merges": "\u0120typ es", "raw_count": 363092, "count": 363092, "decode_str": " types"} -{"id": 3682, "token": "apan", "merges": "ap an", "raw_count": 281966, "count": 363140, "decode_str": "apan"} -{"id": 53379, "token": "\u00e7\u00bc\u0126", "merges": "\u00e7\u00bc \u0126", "raw_count": 363259, "count": 363259, "decode_str": "\u7f04"} -{"id": 7050, "token": "Element", "merges": "E lement", "raw_count": 345316, "count": 363276, "decode_str": "Element"} -{"id": 51048, "token": "\u00e5\u0134\u00bb", "merges": "\u00e5\u0134 \u00bb", "raw_count": 363280, "count": 363280, "decode_str": "\u54bb"} -{"id": 5404, "token": "lict", "merges": "lic t", "raw_count": 66664, "count": 363419, "decode_str": "lict"} -{"id": 5495, "token": "ipe", "merges": "i pe", "raw_count": 241205, "count": 363489, "decode_str": "ipe"} -{"id": 53206, "token": "\u00e7\u00ac\u0128", "merges": "\u00e7\u00ac \u0128", "raw_count": 363511, "count": 363511, "decode_str": "\u7b06"} -{"id": 22219, "token": "(\"%", "merges": "(\" %", "raw_count": 363549, "count": 363549, "decode_str": "(\"%"} -{"id": 7694, "token": "arl", "merges": "ar l", "raw_count": 162822, "count": 363632, "decode_str": "arl"} -{"id": 12898, "token": "desc", "merges": "des c", "raw_count": 363731, "count": 363731, "decode_str": "desc"} -{"id": 23459, "token": "NV", "merges": "N V", "raw_count": 363809, "count": 363809, "decode_str": "NV"} -{"id": 53085, "token": "\u00e7\u00a2\u012b", "merges": "\u00e7\u00a2 \u012b", "raw_count": 363933, "count": 363933, "decode_str": "\u7889"} -{"id": 15061, "token": "Na", "merges": "N a", "raw_count": 333307, "count": 363957, "decode_str": "Na"} -{"id": 50553, "token": "\u00e4\u00bd\u0139", "merges": "\u00e4\u00bd \u0139", "raw_count": 364133, "count": 364133, "decode_str": "\u4f57"} -{"id": 35366, "token": "980", "merges": "9 80", "raw_count": 364224, "count": 364224, "decode_str": "980"} -{"id": 3742, "token": "lish", "merges": "l ish", "raw_count": 82678, "count": 364408, "decode_str": "lish"} -{"id": 7791, "token": "month", "merges": "mon th", "raw_count": 324822, "count": 364493, "decode_str": "month"} -{"id": 50674, "token": "\u00e5\u0126\u012d", "merges": "\u00e5\u0126 \u012d", "raw_count": 364813, "count": 364813, "decode_str": "\u510b"} -{"id": 12261, "token": "TP", "merges": "T P", "raw_count": 364183, "count": 364861, "decode_str": "TP"} -{"id": 42362, "token": "1934", "merges": "19 34", "raw_count": 364882, "count": 364882, "decode_str": "1934"} -{"id": 7261, "token": "kl", "merges": "k l", "raw_count": 359743, "count": 364886, "decode_str": "kl"} -{"id": 13060, "token": "watch", "merges": "w atch", "raw_count": 364972, "count": 364972, "decode_str": "watch"} -{"id": 15507, "token": "speed", "merges": "spe ed", "raw_count": 365281, "count": 365281, "decode_str": "speed"} -{"id": 11379, "token": "./", "merges": ". /", "raw_count": 200381, "count": 365285, "decode_str": "./"} -{"id": 17670, "token": "dm", "merges": "d m", "raw_count": 365287, "count": 365287, "decode_str": "dm"} -{"id": 8296, "token": "III", "merges": "II I", "raw_count": 364205, "count": 365396, "decode_str": "III"} -{"id": 4895, "token": "\u0120returned", "merges": "\u0120return ed", "raw_count": 365643, "count": 365643, "decode_str": " returned"} -{"id": 2939, "token": "\u0120assess", "merges": "\u0120ass ess", "raw_count": 61751, "count": 365684, "decode_str": " assess"} -{"id": 8974, "token": "quare", "merges": "qu are", "raw_count": 147329, "count": 365986, "decode_str": "quare"} -{"id": 3790, "token": "\u0120round", "merges": "\u0120r ound", "raw_count": 338507, "count": 366008, "decode_str": " round"} -{"id": 1357, "token": "\u00e3\u0124", "merges": "\u00e3 \u0124", "raw_count": 11375, "count": 366029, "decode_str": "\ufffd"} -{"id": 54344, "token": "\u00e9\u013c\u012f", "merges": "\u00e9\u013c \u012f", "raw_count": 366074, "count": 366074, "decode_str": "\u968d"} -{"id": 2032, "token": "\u0120true", "merges": "\u0120tr ue", "raw_count": 366131, "count": 366131, "decode_str": " true"} -{"id": 52055, "token": "\u00e6\u0135\u00a2", "merges": "\u00e6\u0135 \u00a2", "raw_count": 366236, "count": 366236, "decode_str": "\u64e2"} -{"id": 4232, "token": "\u0120established", "merges": "\u0120establ ished", "raw_count": 366406, "count": 366406, "decode_str": " established"} -{"id": 14353, "token": "iu", "merges": "i u", "raw_count": 293345, "count": 366419, "decode_str": "iu"} -{"id": 10859, "token": "Sch", "merges": "S ch", "raw_count": 366564, "count": 366564, "decode_str": "Sch"} -{"id": 54227, "token": "\u00e9\u0136\u0131", "merges": "\u00e9\u0136 \u0131", "raw_count": 366595, "count": 366595, "decode_str": "\u950f"} -{"id": 3378, "token": "With", "merges": "W ith", "raw_count": 332978, "count": 366683, "decode_str": "With"} -{"id": 21881, "token": "flix", "merges": "fl ix", "raw_count": 364508, "count": 366770, "decode_str": "flix"} -{"id": 5624, "token": "/(", "merges": "/ (", "raw_count": 353276, "count": 366779, "decode_str": "/("} -{"id": 4515, "token": "wards", "merges": "ward s", "raw_count": 168969, "count": 366957, "decode_str": "wards"} -{"id": 14102, "token": "Sur", "merges": "S ur", "raw_count": 138776, "count": 367040, "decode_str": "Sur"} -{"id": 748, "token": "\u0120}", "merges": "\u0120 }", "raw_count": 289183, "count": 367061, "decode_str": " }"} -{"id": 53669, "token": "\u00e8\u0130\u0142", "merges": "\u00e8\u0130 \u0142", "raw_count": 367258, "count": 367258, "decode_str": "\u83a0"} -{"id": 20680, "token": "405", "merges": "40 5", "raw_count": 367492, "count": 367492, "decode_str": "405"} -{"id": 3580, "token": "\u0120products", "merges": "\u0120product s", "raw_count": 367526, "count": 367526, "decode_str": " products"} -{"id": 2750, "token": "\u0120benef", "merges": "\u0120ben ef", "raw_count": 12393, "count": 367588, "decode_str": " benef"} -{"id": 7449, "token": "\u012000", "merges": "\u0120 00", "raw_count": 367687, "count": 367687, "decode_str": " 00"} -{"id": 5338, "token": "inner", "merges": "in ner", "raw_count": 327931, "count": 367761, "decode_str": "inner"} -{"id": 12847, "token": "bc", "merges": "b c", "raw_count": 367781, "count": 367781, "decode_str": "bc"} -{"id": 33325, "token": "ariat", "merges": "ari at", "raw_count": 367827, "count": 367827, "decode_str": "ariat"} -{"id": 51221, "token": "\u00e5\u0140\u0142", "merges": "\u00e5\u0140 \u0142", "raw_count": 367840, "count": 367840, "decode_str": "\u57a0"} -{"id": 2355, "token": "asing", "merges": "as ing", "raw_count": 74814, "count": 367876, "decode_str": "asing"} -{"id": 52782, "token": "\u00e7\u012b\u00a6", "merges": "\u00e7\u012b \u00a6", "raw_count": 367881, "count": 367881, "decode_str": "\u7266"} -{"id": 10650, "token": "IME", "merges": "IM E", "raw_count": 129720, "count": 367957, "decode_str": "IME"} -{"id": 22035, "token": "team", "merges": "te am", "raw_count": 367985, "count": 367985, "decode_str": "team"} -{"id": 12648, "token": "AE", "merges": "A E", "raw_count": 367903, "count": 368083, "decode_str": "AE"} -{"id": 6683, "token": "ye", "merges": "y e", "raw_count": 269429, "count": 368112, "decode_str": "ye"} -{"id": 7158, "token": "\u0120accord", "merges": "\u0120acc ord", "raw_count": 19510, "count": 368136, "decode_str": " accord"} -{"id": 13934, "token": "pair", "merges": "p air", "raw_count": 360695, "count": 368247, "decode_str": "pair"} -{"id": 19198, "token": "hook", "merges": "h ook", "raw_count": 368461, "count": 368475, "decode_str": "hook"} -{"id": 54504, "token": "\u00e9\u00aa\u013d", "merges": "\u00e9\u00aa \u013d", "raw_count": 368816, "count": 368816, "decode_str": "\u9a9b"} -{"id": 6002, "token": "oz", "merges": "o z", "raw_count": 316636, "count": 369144, "decode_str": "oz"} -{"id": 54243, "token": "\u00e9\u0136\u00b2", "merges": "\u00e9\u0136 \u00b2", "raw_count": 369210, "count": 369210, "decode_str": "\u9532"} -{"id": 3720, "token": "\u0120basis", "merges": "\u0120bas is", "raw_count": 369526, "count": 369526, "decode_str": " basis"} -{"id": 16433, "token": "`.", "merges": "` .", "raw_count": 369608, "count": 369608, "decode_str": "`."} -{"id": 8107, "token": "\u0120reverse", "merges": "\u0120re verse", "raw_count": 369632, "count": 369632, "decode_str": " reverse"} -{"id": 11021, "token": "Output", "merges": "Out put", "raw_count": 367122, "count": 369656, "decode_str": "Output"} -{"id": 7858, "token": "LS", "merges": "L S", "raw_count": 310581, "count": 369667, "decode_str": "LS"} -{"id": 47868, "token": "1943", "merges": "19 43", "raw_count": 369744, "count": 369744, "decode_str": "1943"} -{"id": 54492, "token": "\u00e9\u00aa\u0127", "merges": "\u00e9\u00aa \u0127", "raw_count": 370028, "count": 370028, "decode_str": "\u9a85"} -{"id": 4961, "token": "\u0120exists", "merges": "\u0120ex ists", "raw_count": 370169, "count": 370169, "decode_str": " exists"} -{"id": 10075, "token": "prot", "merges": "pro t", "raw_count": 113632, "count": 370483, "decode_str": "prot"} -{"id": 2191, "token": "ney", "merges": "ne y", "raw_count": 284086, "count": 370486, "decode_str": "ney"} -{"id": 39156, "token": "570", "merges": "5 70", "raw_count": 370586, "count": 370586, "decode_str": "570"} -{"id": 28928, "token": "argv", "merges": "arg v", "raw_count": 371063, "count": 371063, "decode_str": "argv"} -{"id": 22313, "token": "266", "merges": "26 6", "raw_count": 371079, "count": 371079, "decode_str": "266"} -{"id": 2341, "token": "\u0120energy", "merges": "\u0120en ergy", "raw_count": 371098, "count": 371098, "decode_str": " energy"} -{"id": 39413, "token": "compute", "merges": "comput e", "raw_count": 371166, "count": 371166, "decode_str": "compute"} -{"id": 4118, "token": "###", "merges": "## #", "raw_count": 371595, "count": 371595, "decode_str": "###"} -{"id": 4803, "token": "\u0120rules", "merges": "\u0120r ules", "raw_count": 371618, "count": 371618, "decode_str": " rules"} -{"id": 53569, "token": "\u00e8\u012a\u0122", "merges": "\u00e8\u012a \u0122", "raw_count": 371796, "count": 371796, "decode_str": "\u8200"} -{"id": 32514, "token": "reverse", "merges": "re verse", "raw_count": 371821, "count": 371821, "decode_str": "reverse"} -{"id": 53820, "token": "\u00e8\u00af\u013a", "merges": "\u00e8\u00af \u013a", "raw_count": 371973, "count": 371973, "decode_str": "\u8bd8"} -{"id": 4212, "token": "\u0120users", "merges": "\u0120us ers", "raw_count": 372032, "count": 372032, "decode_str": " users"} -{"id": 1512, "token": "\u0120too", "merges": "\u0120to o", "raw_count": 372140, "count": 372140, "decode_str": " too"} -{"id": 53592, "token": "\u00e8\u012a\u00b7", "merges": "\u00e8\u012a \u00b7", "raw_count": 372151, "count": 372151, "decode_str": "\u8237"} -{"id": 3169, "token": "based", "merges": "b ased", "raw_count": 372332, "count": 372332, "decode_str": "based"} -{"id": 7432, "token": "sin", "merges": "s in", "raw_count": 364894, "count": 372577, "decode_str": "sin"} -{"id": 2161, "token": "osp", "merges": "os p", "raw_count": 75926, "count": 372586, "decode_str": "osp"} -{"id": 20438, "token": "252", "merges": "25 2", "raw_count": 372757, "count": 372757, "decode_str": "252"} -{"id": 10478, "token": "\u0120header", "merges": "\u0120head er", "raw_count": 372831, "count": 372831, "decode_str": " header"} -{"id": 4434, "token": "ouble", "merges": "ou ble", "raw_count": 24022, "count": 372917, "decode_str": "ouble"} -{"id": 15992, "token": "Sk", "merges": "S k", "raw_count": 316196, "count": 372937, "decode_str": "Sk"} -{"id": 6268, "token": "\u0120std", "merges": "\u0120st d", "raw_count": 373254, "count": 373254, "decode_str": " std"} -{"id": 13294, "token": "\u0120padding", "merges": "\u0120p adding", "raw_count": 373341, "count": 373341, "decode_str": " padding"} -{"id": 52637, "token": "\u00e6\u00b7\u0140", "merges": "\u00e6\u00b7 \u0140", "raw_count": 373501, "count": 373501, "decode_str": "\u6dde"} -{"id": 4187, "token": "ulate", "merges": "ul ate", "raw_count": 214821, "count": 373643, "decode_str": "ulate"} -{"id": 51652, "token": "\u00e5\u00be\u013e", "merges": "\u00e5\u00be \u013e", "raw_count": 373687, "count": 373687, "decode_str": "\u5f9c"} -{"id": 37222, "token": "Smart", "merges": "Sm art", "raw_count": 373950, "count": 373950, "decode_str": "Smart"} -{"id": 2220, "token": "\u0120upon", "merges": "\u0120up on", "raw_count": 373989, "count": 373989, "decode_str": " upon"} -{"id": 36660, "token": "\u0120\")", "merges": "\u0120\" )", "raw_count": 374132, "count": 374132, "decode_str": " \")"} -{"id": 16911, "token": "Equals", "merges": "Equ als", "raw_count": 26417, "count": 374205, "decode_str": "Equals"} -{"id": 52016, "token": "\u00e6\u0131\u0138", "merges": "\u00e6\u0131 \u0138", "raw_count": 374422, "count": 374422, "decode_str": "\u63d6"} -{"id": 14600, "token": "article", "merges": "art icle", "raw_count": 374244, "count": 374521, "decode_str": "article"} -{"id": 2473, "token": "atory", "merges": "at ory", "raw_count": 207082, "count": 374593, "decode_str": "atory"} -{"id": 47383, "token": "KG", "merges": "K G", "raw_count": 374612, "count": 374612, "decode_str": "KG"} -{"id": 18689, "token": "expr", "merges": "ex pr", "raw_count": 374566, "count": 374704, "decode_str": "expr"} -{"id": 32095, "token": "/{", "merges": "/ {", "raw_count": 374814, "count": 374814, "decode_str": "/{"} -{"id": 41148, "token": "/%", "merges": "/ %", "raw_count": 374967, "count": 374967, "decode_str": "/%"} -{"id": 7992, "token": "Ext", "merges": "E xt", "raw_count": 223604, "count": 375040, "decode_str": "Ext"} -{"id": 9494, "token": "Hel", "merges": "H el", "raw_count": 172704, "count": 375218, "decode_str": "Hel"} -{"id": 12879, "token": "area", "merges": "are a", "raw_count": 364178, "count": 375273, "decode_str": "area"} -{"id": 51100, "token": "\u00e5\u0137\u00b2", "merges": "\u00e5\u0137 \u00b2", "raw_count": 375540, "count": 375540, "decode_str": "\u5572"} -{"id": 46707, "token": "attrs", "merges": "attr s", "raw_count": 375750, "count": 375750, "decode_str": "attrs"} -{"id": 8147, "token": "ERE", "merges": "ER E", "raw_count": 58794, "count": 375774, "decode_str": "ERE"} -{"id": 6618, "token": "\u0120Set", "merges": "\u0120S et", "raw_count": 310752, "count": 376077, "decode_str": " Set"} -{"id": 51643, "token": "\u00e5\u00be\u012b", "merges": "\u00e5\u00be \u012b", "raw_count": 376271, "count": 376271, "decode_str": "\u5f89"} -{"id": 3479, "token": "RNA", "merges": "R NA", "raw_count": 364648, "count": 376275, "decode_str": "RNA"} -{"id": 4778, "token": "\u0120variable", "merges": "\u0120vari able", "raw_count": 376426, "count": 376426, "decode_str": " variable"} -{"id": 10996, "token": "Oper", "merges": "O per", "raw_count": 171642, "count": 376490, "decode_str": "Oper"} -{"id": 7669, "token": "AGE", "merges": "AG E", "raw_count": 193338, "count": 376588, "decode_str": "AGE"} -{"id": 2590, "token": "\u0120clear", "merges": "\u0120cle ar", "raw_count": 351789, "count": 376700, "decode_str": " clear"} -{"id": 5571, "token": "\u012070", "merges": "\u01207 0", "raw_count": 376712, "count": 376712, "decode_str": " 70"} -{"id": 12551, "token": "\u0120Opt", "merges": "\u0120O pt", "raw_count": 19103, "count": 376714, "decode_str": " Opt"} -{"id": 22179, "token": "191", "merges": "19 1", "raw_count": 376730, "count": 376730, "decode_str": "191"} -{"id": 4574, "token": "overn", "merges": "over n", "raw_count": 3812, "count": 376970, "decode_str": "overn"} -{"id": 19758, "token": "abc", "merges": "ab c", "raw_count": 377073, "count": 377073, "decode_str": "abc"} -{"id": 20371, "token": "PRO", "merges": "PR O", "raw_count": 377183, "count": 377183, "decode_str": "PRO"} -{"id": 3325, "token": "\u0120nucle", "merges": "\u0120n ucle", "raw_count": 2142, "count": 377201, "decode_str": " nucle"} -{"id": 5285, "token": "ctors", "merges": "ct ors", "raw_count": 41640, "count": 377470, "decode_str": "ctors"} -{"id": 53234, "token": "\u00e7\u0143\u00b5", "merges": "\u00e7\u0143 \u00b5", "raw_count": 377530, "count": 377530, "decode_str": "\u7b75"} -{"id": 15215, "token": "\u0120255", "merges": "\u012025 5", "raw_count": 377594, "count": 377594, "decode_str": " 255"} -{"id": 11344, "token": "ttp", "merges": "tt p", "raw_count": 6712, "count": 377647, "decode_str": "ttp"} -{"id": 52834, "token": "\u00e7\u0131\u00a9", "merges": "\u00e7\u0131 \u00a9", "raw_count": 377657, "count": 377657, "decode_str": "\u73e9"} -{"id": 4569, "token": "\u0120appropriate", "merges": "\u0120appropri ate", "raw_count": 377719, "count": 377719, "decode_str": " appropriate"} -{"id": 54527, "token": "\u00e9\u00bb\u012f", "merges": "\u00e9\u00bb \u012f", "raw_count": 377989, "count": 377989, "decode_str": "\u9ecd"} -{"id": 39043, "token": "bias", "merges": "bi as", "raw_count": 378299, "count": 378299, "decode_str": "bias"} -{"id": 52634, "token": "\u00e6\u00b7\u0138", "merges": "\u00e6\u00b7 \u0138", "raw_count": 378401, "count": 378401, "decode_str": "\u6dd6"} -{"id": 30225, "token": "\u0120'-", "merges": "\u0120' -", "raw_count": 378429, "count": 378429, "decode_str": " '-"} -{"id": 22440, "token": "\u0120username", "merges": "\u0120user name", "raw_count": 378450, "count": 378450, "decode_str": " username"} -{"id": 6708, "token": "itory", "merges": "it ory", "raw_count": 16292, "count": 378625, "decode_str": "itory"} -{"id": 18534, "token": "cloud", "merges": "cl oud", "raw_count": 378774, "count": 378774, "decode_str": "cloud"} -{"id": 4681, "token": ".[", "merges": ". [", "raw_count": 377702, "count": 378817, "decode_str": ".["} -{"id": 6598, "token": "\u00e2\u0122\u013f.", "merges": "\u00e2\u0122\u013f .", "raw_count": 378855, "count": 378855, "decode_str": "\u201d."} -{"id": 3535, "token": "itation", "merges": "it ation", "raw_count": 101987, "count": 378968, "decode_str": "itation"} -{"id": 23260, "token": "246", "merges": "24 6", "raw_count": 379030, "count": 379030, "decode_str": "246"} -{"id": 17044, "token": "BN", "merges": "B N", "raw_count": 295068, "count": 379104, "decode_str": "BN"} -{"id": 51649, "token": "\u00e5\u00be\u0137", "merges": "\u00e5\u00be \u0137", "raw_count": 379225, "count": 379225, "decode_str": "\u5f95"} -{"id": 6599, "token": "icrosoft", "merges": "icro soft", "raw_count": 776, "count": 379260, "decode_str": "icrosoft"} -{"id": 3181, "token": "times", "merges": "t imes", "raw_count": 379343, "count": 379343, "decode_str": "times"} -{"id": 15580, "token": "DT", "merges": "D T", "raw_count": 379418, "count": 379418, "decode_str": "DT"} -{"id": 2285, "token": "\u0120team", "merges": "\u0120te am", "raw_count": 376301, "count": 379795, "decode_str": " team"} -{"id": 3372, "token": "lig", "merges": "l ig", "raw_count": 58398, "count": 379798, "decode_str": "lig"} -{"id": 9423, "token": "\u0120Check", "merges": "\u0120Che ck", "raw_count": 379835, "count": 379835, "decode_str": " Check"} -{"id": 1840, "token": "\u0120above", "merges": "\u0120ab ove", "raw_count": 379903, "count": 379903, "decode_str": " above"} -{"id": 53243, "token": "\u00e7\u00ae\u0137", "merges": "\u00e7\u00ae \u0137", "raw_count": 379942, "count": 379942, "decode_str": "\u7b95"} -{"id": 7100, "token": "press", "merges": "p ress", "raw_count": 223239, "count": 380041, "decode_str": "press"} -{"id": 2928, "token": "\u0120answ", "merges": "\u0120an sw", "raw_count": 1684, "count": 380297, "decode_str": " answ"} -{"id": 3606, "token": "tered", "merges": "te red", "raw_count": 60436, "count": 380553, "decode_str": "tered"} -{"id": 2212, "token": "illion", "merges": "ill ion", "raw_count": 24474, "count": 380570, "decode_str": "illion"} -{"id": 1878, "token": "\u0120least", "merges": "\u0120le ast", "raw_count": 380840, "count": 380840, "decode_str": " least"} -{"id": 2268, "token": "\u0120crit", "merges": "\u0120c rit", "raw_count": 10355, "count": 381021, "decode_str": " crit"} -{"id": 11943, "token": "nan", "merges": "n an", "raw_count": 380749, "count": 381110, "decode_str": "nan"} -{"id": 1901, "token": "\u0120invol", "merges": "\u0120inv ol", "raw_count": 2320, "count": 381121, "decode_str": " invol"} -{"id": 2982, "token": "\u0120maint", "merges": "\u0120m aint", "raw_count": 1748, "count": 381196, "decode_str": " maint"} -{"id": 20785, "token": "227", "merges": "22 7", "raw_count": 381248, "count": 381248, "decode_str": "227"} -{"id": 3183, "token": "\u0120recogn", "merges": "\u0120rec ogn", "raw_count": 8907, "count": 381364, "decode_str": " recogn"} -{"id": 2069, "token": "\u0120times", "merges": "\u0120t imes", "raw_count": 379594, "count": 381475, "decode_str": " times"} -{"id": 5629, "token": "ario", "merges": "ar io", "raw_count": 225585, "count": 381526, "decode_str": "ario"} -{"id": 3006, "token": "izing", "merges": "iz ing", "raw_count": 261136, "count": 381611, "decode_str": "izing"} -{"id": 51003, "token": "\u00e5\u0133\u00a4", "merges": "\u00e5\u0133 \u00a4", "raw_count": 381794, "count": 381794, "decode_str": "\u5464"} -{"id": 7279, "token": "\u0120consult", "merges": "\u0120cons ult", "raw_count": 90133, "count": 381882, "decode_str": " consult"} -{"id": 3149, "token": "oved", "merges": "ov ed", "raw_count": 162430, "count": 381945, "decode_str": "oved"} -{"id": 17187, "token": "region", "merges": "reg ion", "raw_count": 381966, "count": 381966, "decode_str": "region"} -{"id": 2281, "token": "\u0120rate", "merges": "\u0120r ate", "raw_count": 382233, "count": 382233, "decode_str": " rate"} -{"id": 3508, "token": "oon", "merges": "o on", "raw_count": 306166, "count": 382240, "decode_str": "oon"} -{"id": 2353, "token": "\u0120beg", "merges": "\u0120be g", "raw_count": 22982, "count": 382277, "decode_str": " beg"} -{"id": 23292, "token": "269", "merges": "26 9", "raw_count": 382281, "count": 382281, "decode_str": "269"} -{"id": 54278, "token": "\u00e9\u0139\u00b0", "merges": "\u00e9\u0139 \u00b0", "raw_count": 382360, "count": 382360, "decode_str": "\u95f0"} -{"id": 4960, "token": "iform", "merges": "if orm", "raw_count": 13758, "count": 382451, "decode_str": "iform"} -{"id": 6646, "token": "ello", "merges": "ell o", "raw_count": 70964, "count": 382488, "decode_str": "ello"} -{"id": 20704, "token": "memory", "merges": "mem ory", "raw_count": 382509, "count": 382509, "decode_str": "memory"} -{"id": 8222, "token": "effect", "merges": "ef fect", "raw_count": 226594, "count": 382544, "decode_str": "effect"} -{"id": 14800, "token": "\u0120inputs", "merges": "\u0120input s", "raw_count": 382793, "count": 382793, "decode_str": " inputs"} -{"id": 4055, "token": "\u0120center", "merges": "\u0120cent er", "raw_count": 382868, "count": 382868, "decode_str": " center"} -{"id": 3820, "token": "\u0120aud", "merges": "\u0120a ud", "raw_count": 77090, "count": 382881, "decode_str": " aud"} -{"id": 53376, "token": "\u00e7\u00bb\u00be", "merges": "\u00e7\u00bb \u00be", "raw_count": 383185, "count": 383185, "decode_str": "\u7efe"} -{"id": 2401, "token": "ival", "merges": "iv al", "raw_count": 117621, "count": 383288, "decode_str": "ival"} -{"id": 46912, "token": "{'", "merges": "{ '", "raw_count": 383349, "count": 383349, "decode_str": "{'"} -{"id": 51670, "token": "\u00e5\u00bf\u0138", "merges": "\u00e5\u00bf \u0138", "raw_count": 383350, "count": 383350, "decode_str": "\u5fd6"} -{"id": 25192, "token": "tb", "merges": "t b", "raw_count": 383372, "count": 383372, "decode_str": "tb"} -{"id": 22358, "token": "wx", "merges": "w x", "raw_count": 383372, "count": 383372, "decode_str": "wx"} -{"id": 4657, "token": "\u0120store", "merges": "\u0120st ore", "raw_count": 383540, "count": 383540, "decode_str": " store"} -{"id": 7517, "token": "\u0120mission", "merges": "\u0120m ission", "raw_count": 377767, "count": 383587, "decode_str": " mission"} -{"id": 26059, "token": "attributes", "merges": "att ributes", "raw_count": 383697, "count": 383697, "decode_str": "attributes"} -{"id": 53876, "token": "\u00e8\u00b0\u0141", "merges": "\u00e8\u00b0 \u0141", "raw_count": 383697, "count": 383697, "decode_str": "\u8c1f"} -{"id": 4500, "token": "\u0120option", "merges": "\u0120opt ion", "raw_count": 364979, "count": 383716, "decode_str": " option"} -{"id": 1875, "token": "aring", "merges": "ar ing", "raw_count": 76288, "count": 384016, "decode_str": "aring"} -{"id": 12303, "token": "bp", "merges": "b p", "raw_count": 384110, "count": 384110, "decode_str": "bp"} -{"id": 19261, "token": "feed", "merges": "fe ed", "raw_count": 309247, "count": 384152, "decode_str": "feed"} -{"id": 15228, "token": "Mich", "merges": "M ich", "raw_count": 31341, "count": 384158, "decode_str": "Mich"} -{"id": 8774, "token": "summary", "merges": "sum mary", "raw_count": 384221, "count": 384221, "decode_str": "summary"} -{"id": 15735, "token": "available", "merges": "av ailable", "raw_count": 361668, "count": 384272, "decode_str": "available"} -{"id": 34906, "token": "485", "merges": "4 85", "raw_count": 384392, "count": 384392, "decode_str": "485"} -{"id": 6517, "token": "\u0120exception", "merges": "\u0120ex ception", "raw_count": 379561, "count": 384618, "decode_str": " exception"} -{"id": 20907, "token": "factory", "merges": "f actory", "raw_count": 384207, "count": 384699, "decode_str": "factory"} -{"id": 52315, "token": "\u00e6\u00a1\u00a7", "merges": "\u00e6\u00a1 \u00a7", "raw_count": 384807, "count": 384807, "decode_str": "\u6867"} -{"id": 3927, "token": "aries", "merges": "ar ies", "raw_count": 191823, "count": 385179, "decode_str": "aries"} -{"id": 8009, "token": "dule", "merges": "du le", "raw_count": 12451, "count": 385385, "decode_str": "dule"} -{"id": 4764, "token": "\u0120parameter", "merges": "\u0120param eter", "raw_count": 385395, "count": 385395, "decode_str": " parameter"} -{"id": 11500, "token": "gel", "merges": "g el", "raw_count": 56021, "count": 385678, "decode_str": "gel"} -{"id": 26422, "token": "358", "merges": "35 8", "raw_count": 385918, "count": 385918, "decode_str": "358"} -{"id": 6705, "token": "\u012064", "merges": "\u01206 4", "raw_count": 386074, "count": 386074, "decode_str": " 64"} -{"id": 35422, "token": "pars", "merges": "p ars", "raw_count": 386079, "count": 386079, "decode_str": "pars"} -{"id": 20735, "token": "221", "merges": "22 1", "raw_count": 386194, "count": 386194, "decode_str": "221"} -{"id": 2523, "token": "\u0120issue", "merges": "\u0120iss ue", "raw_count": 386237, "count": 386237, "decode_str": " issue"} -{"id": 3399, "token": "bor", "merges": "b or", "raw_count": 97326, "count": 386650, "decode_str": "bor"} -{"id": 7397, "token": "organ", "merges": "or gan", "raw_count": 202999, "count": 386686, "decode_str": "organ"} -{"id": 15738, "token": "entials", "merges": "ential s", "raw_count": 269676, "count": 386781, "decode_str": "entials"} -{"id": 51307, "token": "\u00e5\u00a5\u0124", "merges": "\u00e5\u00a5 \u0124", "raw_count": 387005, "count": 387005, "decode_str": "\u5942"} -{"id": 5871, "token": "\u0120operations", "merges": "\u0120oper ations", "raw_count": 387202, "count": 387202, "decode_str": " operations"} -{"id": 7484, "token": "\u0120plot", "merges": "\u0120pl ot", "raw_count": 365112, "count": 387340, "decode_str": " plot"} -{"id": 33111, "token": "\u0120ferry", "merges": "\u0120fer ry", "raw_count": 387412, "count": 387412, "decode_str": " ferry"} -{"id": 20487, "token": "239", "merges": "23 9", "raw_count": 387462, "count": 387462, "decode_str": "239"} -{"id": 12919, "token": "Process", "merges": "Pro cess", "raw_count": 271644, "count": 387597, "decode_str": "Process"} -{"id": 52532, "token": "\u00e6\u00b3\u0142", "merges": "\u00e6\u00b3 \u0142", "raw_count": 387635, "count": 387635, "decode_str": "\u6ce0"} -{"id": 54472, "token": "\u00e9\u00a3\u00a8", "merges": "\u00e9\u00a3 \u00a8", "raw_count": 387721, "count": 387721, "decode_str": "\u98e8"} -{"id": 9006, "token": "AF", "merges": "A F", "raw_count": 387510, "count": 387759, "decode_str": "AF"} -{"id": 8475, "token": "inates", "merges": "in ates", "raw_count": 206130, "count": 387818, "decode_str": "inates"} -{"id": 1900, "token": "\u0120always", "merges": "\u0120al ways", "raw_count": 387959, "count": 387959, "decode_str": " always"} -{"id": 4109, "token": "\u0120ter", "merges": "\u0120t er", "raw_count": 37735, "count": 388008, "decode_str": " ter"} -{"id": 34477, "token": "XXX", "merges": "XX X", "raw_count": 388135, "count": 388135, "decode_str": "XXX"} -{"id": 53908, "token": "\u00e8\u00b2\u0127", "merges": "\u00e8\u00b2 \u0127", "raw_count": 388214, "count": 388214, "decode_str": "\u8c85"} -{"id": 10019, "token": "iginal", "merges": "ig inal", "raw_count": 1979, "count": 388307, "decode_str": "iginal"} -{"id": 6048, "token": "\u0120((", "merges": "\u0120( (", "raw_count": 388347, "count": 388347, "decode_str": " (("} -{"id": 8340, "token": "buf", "merges": "b uf", "raw_count": 374437, "count": 388478, "decode_str": "buf"} -{"id": 17406, "token": "course", "merges": "c ourse", "raw_count": 387713, "count": 388708, "decode_str": "course"} -{"id": 9692, "token": "Ac", "merges": "A c", "raw_count": 200556, "count": 389078, "decode_str": "Ac"} -{"id": 52586, "token": "\u00e6\u00b5\u013e", "merges": "\u00e6\u00b5 \u013e", "raw_count": 389191, "count": 389191, "decode_str": "\u6d5c"} -{"id": 8897, "token": "008", "merges": "00 8", "raw_count": 389246, "count": 389246, "decode_str": "008"} -{"id": 3540, "token": "\u0120track", "merges": "\u0120tr ack", "raw_count": 241074, "count": 389284, "decode_str": " track"} -{"id": 10828, "token": "Init", "merges": "In it", "raw_count": 245276, "count": 389330, "decode_str": "Init"} -{"id": 1927, "token": "\u0120rese", "merges": "\u0120re se", "raw_count": 2531, "count": 389345, "decode_str": " rese"} -{"id": 50657, "token": "\u00e5\u0124\u00a3", "merges": "\u00e5\u0124 \u00a3", "raw_count": 389371, "count": 389371, "decode_str": "\u50a3"} -{"id": 17820, "token": "375", "merges": "37 5", "raw_count": 389409, "count": 389409, "decode_str": "375"} -{"id": 6958, "token": "Date", "merges": "D ate", "raw_count": 323909, "count": 389427, "decode_str": "Date"} -{"id": 1023, "token": "\u0120Se", "merges": "\u0120S e", "raw_count": 66134, "count": 389518, "decode_str": " Se"} -{"id": 2810, "token": "\u0120close", "merges": "\u0120cl ose", "raw_count": 389597, "count": 389597, "decode_str": " close"} -{"id": 1856, "token": "hib", "merges": "h ib", "raw_count": 146383, "count": 389785, "decode_str": "hib"} -{"id": 1679, "token": "\u0120less", "merges": "\u0120l ess", "raw_count": 292008, "count": 389804, "decode_str": " less"} -{"id": 51794, "token": "\u00e6\u0126\u00ab", "merges": "\u00e6\u0126 \u00ab", "raw_count": 389848, "count": 389848, "decode_str": "\u612b"} -{"id": 5525, "token": "004", "merges": "00 4", "raw_count": 389851, "count": 389851, "decode_str": "004"} -{"id": 3157, "token": "\u0120improve", "merges": "\u0120impro ve", "raw_count": 255580, "count": 390060, "decode_str": " improve"} -{"id": 3067, "token": "\u0120adj", "merges": "\u0120ad j", "raw_count": 100951, "count": 390127, "decode_str": " adj"} -{"id": 53621, "token": "\u00e8\u012c\u00a9", "merges": "\u00e8\u012c \u00a9", "raw_count": 390617, "count": 390617, "decode_str": "\u82a9"} -{"id": 2021, "token": "\u0120family", "merges": "\u0120fam ily", "raw_count": 390818, "count": 390818, "decode_str": " family"} -{"id": 8594, "token": "obe", "merges": "ob e", "raw_count": 365791, "count": 390933, "decode_str": "obe"} -{"id": 16145, "token": "ixel", "merges": "ix el", "raw_count": 13736, "count": 391101, "decode_str": "ixel"} -{"id": 20360, "token": "223", "merges": "22 3", "raw_count": 391243, "count": 391243, "decode_str": "223"} -{"id": 4735, "token": "\u0120feature", "merges": "\u0120fe ature", "raw_count": 391364, "count": 391364, "decode_str": " feature"} -{"id": 6469, "token": "\u01202003", "merges": "\u0120200 3", "raw_count": 391471, "count": 391471, "decode_str": " 2003"} -{"id": 18788, "token": "apply", "merges": "app ly", "raw_count": 391590, "count": 391590, "decode_str": "apply"} -{"id": 11956, "token": "quot", "merges": "qu ot", "raw_count": 391832, "count": 391832, "decode_str": "quot"} -{"id": 860, "token": "\u00c3\u00a9", "merges": "\u00c3 \u00a9", "raw_count": 144566, "count": 391839, "decode_str": "\u00e9"} -{"id": 1956, "token": "egin", "merges": "eg in", "raw_count": 3925, "count": 391842, "decode_str": "egin"} -{"id": 3354, "token": "den", "merges": "d en", "raw_count": 336347, "count": 391850, "decode_str": "den"} -{"id": 54506, "token": "\u00e9\u00aa\u0140", "merges": "\u00e9\u00aa \u0140", "raw_count": 391897, "count": 391897, "decode_str": "\u9a9e"} -{"id": 2901, "token": "\u0120trad", "merges": "\u0120tr ad", "raw_count": 6307, "count": 391933, "decode_str": " trad"} -{"id": 8486, "token": "Det", "merges": "D et", "raw_count": 99527, "count": 391963, "decode_str": "Det"} -{"id": 25318, "token": "collection", "merges": "col lection", "raw_count": 392153, "count": 392153, "decode_str": "collection"} -{"id": 3503, "token": "^*", "merges": "^ *", "raw_count": 356378, "count": 392263, "decode_str": "^*"} -{"id": 3296, "token": "hem", "merges": "he m", "raw_count": 110393, "count": 392298, "decode_str": "hem"} -{"id": 8826, "token": "some", "merges": "s ome", "raw_count": 380978, "count": 392376, "decode_str": "some"} -{"id": 14329, "token": "scope", "merges": "sc ope", "raw_count": 392760, "count": 392760, "decode_str": "scope"} -{"id": 5616, "token": "lem", "merges": "le m", "raw_count": 92120, "count": 392767, "decode_str": "lem"} -{"id": 24407, "token": "ARM", "merges": "AR M", "raw_count": 392814, "count": 392814, "decode_str": "ARM"} -{"id": 6432, "token": "Pe", "merges": "P e", "raw_count": 298816, "count": 392846, "decode_str": "Pe"} -{"id": 14035, "token": "\u0120dir", "merges": "\u0120d ir", "raw_count": 392880, "count": 392880, "decode_str": " dir"} -{"id": 23370, "token": "\u0120api", "merges": "\u0120ap i", "raw_count": 392891, "count": 392891, "decode_str": " api"} -{"id": 28207, "token": "warning", "merges": "w arning", "raw_count": 392937, "count": 392937, "decode_str": "warning"} -{"id": 22084, "token": "wi", "merges": "w i", "raw_count": 392953, "count": 392953, "decode_str": "wi"} -{"id": 3160, "token": "reet", "merges": "re et", "raw_count": 50151, "count": 393026, "decode_str": "reet"} -{"id": 53865, "token": "\u00e8\u00b0\u0133", "merges": "\u00e8\u00b0 \u0133", "raw_count": 393080, "count": 393080, "decode_str": "\u8c11"} -{"id": 13159, "token": "Valid", "merges": "Val id", "raw_count": 183972, "count": 393194, "decode_str": "Valid"} -{"id": 5051, "token": "urity", "merges": "ur ity", "raw_count": 28482, "count": 393223, "decode_str": "urity"} -{"id": 4485, "token": "------", "merges": "---- --", "raw_count": 354161, "count": 393232, "decode_str": "------"} -{"id": 11671, "token": "'\\", "merges": "' \\", "raw_count": 393316, "count": 393316, "decode_str": "'\\"} -{"id": 3516, "token": "itary", "merges": "it ary", "raw_count": 50662, "count": 393675, "decode_str": "itary"} -{"id": 6570, "token": "ATION", "merges": "AT ION", "raw_count": 263483, "count": 393767, "decode_str": "ATION"} -{"id": 50689, "token": "\u00e5\u0127\u0138", "merges": "\u00e5\u0127 \u0138", "raw_count": 394070, "count": 394070, "decode_str": "\u5156"} -{"id": 1614, "token": "\u0120turn", "merges": "\u0120t urn", "raw_count": 223372, "count": 394110, "decode_str": " turn"} -{"id": 31158, "token": "training", "merges": "tra ining", "raw_count": 394133, "count": 394133, "decode_str": "training"} -{"id": 2739, "token": "\u0120food", "merges": "\u0120f ood", "raw_count": 369813, "count": 394147, "decode_str": " food"} -{"id": 10149, "token": "\u0120keys", "merges": "\u0120ke ys", "raw_count": 394161, "count": 394161, "decode_str": " keys"} -{"id": 6656, "token": "arian", "merges": "ar ian", "raw_count": 94401, "count": 394162, "decode_str": "arian"} -{"id": 2060, "token": "\u0120individual", "merges": "\u0120ind ividual", "raw_count": 246531, "count": 394201, "decode_str": " individual"} -{"id": 1740, "token": "\u0120four", "merges": "\u0120f our", "raw_count": 292190, "count": 394369, "decode_str": " four"} -{"id": 54462, "token": "\u00e9\u00a2\u00a7", "merges": "\u00e9\u00a2 \u00a7", "raw_count": 394371, "count": 394371, "decode_str": "\u98a7"} -{"id": 5039, "token": "Ab", "merges": "A b", "raw_count": 270760, "count": 394386, "decode_str": "Ab"} -{"id": 32888, "token": "lr", "merges": "l r", "raw_count": 394420, "count": 394420, "decode_str": "lr"} -{"id": 48280, "token": "curr", "merges": "cur r", "raw_count": 394522, "count": 394522, "decode_str": "curr"} -{"id": 41391, "token": "\u00e2\u0122\u00a6\u00e2\u0122\u00a6\u00e2\u0122\u00a6\u00e2\u0122\u00a6", "merges": "\u00e2\u0122\u00a6\u00e2\u0122\u00a6 \u00e2\u0122\u00a6\u00e2\u0122\u00a6", "raw_count": 394690, "count": 394690, "decode_str": "\u2026\u2026\u2026\u2026"} -{"id": 1742, "token": "\u0120prob", "merges": "\u0120pro b", "raw_count": 138595, "count": 395077, "decode_str": " prob"} -{"id": 3004, "token": "mitted", "merges": "m itted", "raw_count": 44215, "count": 395096, "decode_str": "mitted"} -{"id": 20974, "token": "returns", "merges": "return s", "raw_count": 395233, "count": 395233, "decode_str": "returns"} -{"id": 18582, "token": "HP", "merges": "H P", "raw_count": 395246, "count": 395246, "decode_str": "HP"} -{"id": 5930, "token": "ignment", "merges": "ign ment", "raw_count": 155844, "count": 395392, "decode_str": "ignment"} -{"id": 8207, "token": "Ind", "merges": "In d", "raw_count": 258682, "count": 395443, "decode_str": "Ind"} -{"id": 9026, "token": "Script", "merges": "S cript", "raw_count": 120646, "count": 395520, "decode_str": "Script"} -{"id": 22341, "token": "355", "merges": "35 5", "raw_count": 395625, "count": 395625, "decode_str": "355"} -{"id": 25797, "token": "401", "merges": "4 01", "raw_count": 395627, "count": 395627, "decode_str": "401"} -{"id": 6421, "token": "dy", "merges": "d y", "raw_count": 383808, "count": 395641, "decode_str": "dy"} -{"id": 31952, "token": "rgb", "merges": "rg b", "raw_count": 395690, "count": 395690, "decode_str": "rgb"} -{"id": 38049, "token": "960", "merges": "9 60", "raw_count": 395821, "count": 395821, "decode_str": "960"} -{"id": 53910, "token": "\u00e8\u00b2\u0136", "merges": "\u00e8\u00b2 \u0136", "raw_count": 395853, "count": 395853, "decode_str": "\u8c94"} -{"id": 20083, "token": "Watch", "merges": "W atch", "raw_count": 395924, "count": 395924, "decode_str": "Watch"} -{"id": 2515, "token": "\u0120conditions", "merges": "\u0120condition s", "raw_count": 395983, "count": 395983, "decode_str": " conditions"} -{"id": 14947, "token": "World", "merges": "W orld", "raw_count": 396008, "count": 396008, "decode_str": "World"} -{"id": 7957, "token": "fast", "merges": "f ast", "raw_count": 337166, "count": 396023, "decode_str": "fast"} -{"id": 46241, "token": "-\"", "merges": "- \"", "raw_count": 396111, "count": 396111, "decode_str": "-\""} -{"id": 1861, "token": "amma", "merges": "am ma", "raw_count": 18353, "count": 396335, "decode_str": "amma"} -{"id": 4112, "token": "\u0120situation", "merges": "\u0120sit uation", "raw_count": 396371, "count": 396371, "decode_str": " situation"} -{"id": 1199, "token": "\u0120much", "merges": "\u0120m uch", "raw_count": 396137, "count": 396379, "decode_str": " much"} -{"id": 4345, "token": "\u0120agreement", "merges": "\u0120agre ement", "raw_count": 396457, "count": 396457, "decode_str": " agreement"} -{"id": 3576, "token": "\u0120effective", "merges": "\u0120effect ive", "raw_count": 396458, "count": 396458, "decode_str": " effective"} -{"id": 5856, "token": "Context", "merges": "Con text", "raw_count": 396499, "count": 396499, "decode_str": "Context"} -{"id": 8912, "token": "allow", "merges": "all ow", "raw_count": 225905, "count": 396530, "decode_str": "allow"} -{"id": 54513, "token": "\u00e9\u00aa\u00b0", "merges": "\u00e9\u00aa \u00b0", "raw_count": 397118, "count": 397118, "decode_str": "\u9ab0"} -{"id": 9019, "token": "Action", "merges": "A ction", "raw_count": 397129, "count": 397129, "decode_str": "Action"} -{"id": 42704, "token": "1944", "merges": "19 44", "raw_count": 397149, "count": 397149, "decode_str": "1944"} -{"id": 22000, "token": "309", "merges": "30 9", "raw_count": 397457, "count": 397457, "decode_str": "309"} -{"id": 10849, "token": "untime", "merges": "unt ime", "raw_count": 2884, "count": 397495, "decode_str": "untime"} -{"id": 4068, "token": "ibrary", "merges": "ibr ary", "raw_count": 6142, "count": 397541, "decode_str": "ibrary"} -{"id": 15576, "token": "edit", "merges": "ed it", "raw_count": 397762, "count": 397762, "decode_str": "edit"} -{"id": 23025, "token": "285", "merges": "28 5", "raw_count": 397769, "count": 397769, "decode_str": "285"} -{"id": 26221, "token": "398", "merges": "39 8", "raw_count": 397984, "count": 397984, "decode_str": "398"} -{"id": 2321, "token": "aug", "merges": "a ug", "raw_count": 175227, "count": 398081, "decode_str": "aug"} -{"id": 11061, "token": "\u0120bytes", "merges": "\u0120by tes", "raw_count": 398170, "count": 398170, "decode_str": " bytes"} -{"id": 3847, "token": "zy", "merges": "z y", "raw_count": 274068, "count": 398191, "decode_str": "zy"} -{"id": 12016, "token": "\u0120deleg", "merges": "\u0120de leg", "raw_count": 117019, "count": 398246, "decode_str": " deleg"} -{"id": 9656, "token": "LECT", "merges": "LE CT", "raw_count": 21253, "count": 398262, "decode_str": "LECT"} -{"id": 7563, "token": "\u0120budget", "merges": "\u0120bud get", "raw_count": 367932, "count": 398367, "decode_str": " budget"} -{"id": 2685, "token": "\u0120flow", "merges": "\u0120f low", "raw_count": 206664, "count": 398385, "decode_str": " flow"} -{"id": 8265, "token": "neg", "merges": "ne g", "raw_count": 223870, "count": 398481, "decode_str": "neg"} -{"id": 23725, "token": "upper", "merges": "upp er", "raw_count": 398493, "count": 398493, "decode_str": "upper"} -{"id": 10854, "token": "Down", "merges": "D own", "raw_count": 281428, "count": 398552, "decode_str": "Down"} -{"id": 24202, "token": "\u0120TODO", "merges": "\u0120TOD O", "raw_count": 398983, "count": 398983, "decode_str": " TODO"} -{"id": 19631, "token": "193", "merges": "19 3", "raw_count": 399199, "count": 399199, "decode_str": "193"} -{"id": 9852, "token": "pin", "merges": "p in", "raw_count": 390801, "count": 399216, "decode_str": "pin"} -{"id": 4387, "token": "public", "merges": "p ublic", "raw_count": 399302, "count": 399302, "decode_str": "public"} -{"id": 16350, "token": "Sn", "merges": "S n", "raw_count": 361015, "count": 399814, "decode_str": "Sn"} -{"id": 52723, "token": "\u00e7\u0124\u0127", "merges": "\u00e7\u0124 \u0127", "raw_count": 400121, "count": 400121, "decode_str": "\u7085"} -{"id": 13753, "token": "SW", "merges": "S W", "raw_count": 400192, "count": 400192, "decode_str": "SW"} -{"id": 17400, "token": "\u0120env", "merges": "\u0120en v", "raw_count": 400325, "count": 400325, "decode_str": " env"} -{"id": 5540, "token": "\u012036", "merges": "\u01203 6", "raw_count": 400420, "count": 400420, "decode_str": " 36"} -{"id": 7469, "token": "\u0120300", "merges": "\u01203 00", "raw_count": 400461, "count": 400461, "decode_str": " 300"} -{"id": 31543, "token": "440", "merges": "4 40", "raw_count": 400523, "count": 400523, "decode_str": "440"} -{"id": 6249, "token": "\u0120sust", "merges": "\u0120su st", "raw_count": 3054, "count": 400535, "decode_str": " sust"} -{"id": 49812, "token": "1933", "merges": "19 33", "raw_count": 400692, "count": 400692, "decode_str": "1933"} -{"id": 30889, "token": "410", "merges": "4 10", "raw_count": 400742, "count": 400742, "decode_str": "410"} -{"id": 4868, "token": "\u0120score", "merges": "\u0120sc ore", "raw_count": 400901, "count": 400901, "decode_str": " score"} -{"id": 4384, "token": "\u0120web", "merges": "\u0120we b", "raw_count": 387150, "count": 400973, "decode_str": " web"} -{"id": 2514, "token": "medi", "merges": "med i", "raw_count": 49831, "count": 401110, "decode_str": "medi"} -{"id": 51963, "token": "\u00e6\u012f\u012d", "merges": "\u00e6\u012f \u012d", "raw_count": 401297, "count": 401297, "decode_str": "\u634b"} -{"id": 53897, "token": "\u00e8\u00b1\u012b", "merges": "\u00e8\u00b1 \u012b", "raw_count": 401303, "count": 401303, "decode_str": "\u8c49"} -{"id": 4086, "token": "\u0120rule", "merges": "\u0120r ule", "raw_count": 401351, "count": 401351, "decode_str": " rule"} -{"id": 1574, "token": "ently", "merges": "ent ly", "raw_count": 50131, "count": 401382, "decode_str": "ently"} -{"id": 8494, "token": "Rem", "merges": "R em", "raw_count": 184165, "count": 401493, "decode_str": "Rem"} -{"id": 14091, "token": "stud", "merges": "st ud", "raw_count": 139686, "count": 401551, "decode_str": "stud"} -{"id": 25522, "token": "database", "merges": "dat abase", "raw_count": 401581, "count": 401581, "decode_str": "database"} -{"id": 22130, "token": "328", "merges": "32 8", "raw_count": 401867, "count": 401867, "decode_str": "328"} -{"id": 18763, "token": "\u0120TOD", "merges": "\u0120T OD", "raw_count": 1869, "count": 401877, "decode_str": " TOD"} -{"id": 22714, "token": "predict", "merges": "pred ict", "raw_count": 396017, "count": 401955, "decode_str": "predict"} -{"id": 8560, "token": "prop", "merges": "pro p", "raw_count": 345586, "count": 402054, "decode_str": "prop"} -{"id": 20520, "token": "248", "merges": "24 8", "raw_count": 402076, "count": 402076, "decode_str": "248"} -{"id": 15614, "token": "Cap", "merges": "C ap", "raw_count": 380389, "count": 402191, "decode_str": "Cap"} -{"id": 28873, "token": "502", "merges": "50 2", "raw_count": 402217, "count": 402217, "decode_str": "502"} -{"id": 14444, "token": "Tree", "merges": "T ree", "raw_count": 402221, "count": 402221, "decode_str": "Tree"} -{"id": 7681, "token": "\u0120technical", "merges": "\u0120techn ical", "raw_count": 402479, "count": 402479, "decode_str": " technical"} -{"id": 22882, "token": "secret", "merges": "se cret", "raw_count": 402541, "count": 402541, "decode_str": "secret"} -{"id": 1708, "token": "\u0120light", "merges": "\u0120l ight", "raw_count": 323875, "count": 402999, "decode_str": " light"} -{"id": 33529, "token": "GHz", "merges": "G Hz", "raw_count": 403020, "count": 403020, "decode_str": "GHz"} -{"id": 3741, "token": "icles", "merges": "ic les", "raw_count": 103986, "count": 403043, "decode_str": "icles"} -{"id": 53034, "token": "\u00e7\u013f\u00bd", "merges": "\u00e7\u013f \u00bd", "raw_count": 403052, "count": 403052, "decode_str": "\u777d"} -{"id": 8934, "token": "Eng", "merges": "E ng", "raw_count": 72864, "count": 403133, "decode_str": "Eng"} -{"id": 8476, "token": "tab", "merges": "t ab", "raw_count": 403215, "count": 403215, "decode_str": "tab"} -{"id": 26848, "token": "\u0120',", "merges": "\u0120' ,", "raw_count": 403237, "count": 403237, "decode_str": " ',"} -{"id": 53884, "token": "\u00e8\u00b0\u00a9", "merges": "\u00e8\u00b0 \u00a9", "raw_count": 403256, "count": 403256, "decode_str": "\u8c29"} -{"id": 27564, "token": "loader", "merges": "load er", "raw_count": 403330, "count": 403330, "decode_str": "loader"} -{"id": 2128, "token": "\u0120jud", "merges": "\u0120j ud", "raw_count": 41114, "count": 403515, "decode_str": " jud"} -{"id": 17448, "token": "Li", "merges": "L i", "raw_count": 403517, "count": 403517, "decode_str": "Li"} -{"id": 3892, "token": "gor", "merges": "g or", "raw_count": 55065, "count": 403523, "decode_str": "gor"} -{"id": 13721, "token": "1111", "merges": "11 11", "raw_count": 264584, "count": 403626, "decode_str": "1111"} -{"id": 5187, "token": "inese", "merges": "ines e", "raw_count": 309634, "count": 403646, "decode_str": "inese"} -{"id": 1522, "token": "ittle", "merges": "itt le", "raw_count": 20680, "count": 403785, "decode_str": "ittle"} -{"id": 2160, "token": "\u0120sequ", "merges": "\u0120se qu", "raw_count": 7615, "count": 403926, "decode_str": " sequ"} -{"id": 5329, "token": "\u012045", "merges": "\u01204 5", "raw_count": 404011, "count": 404011, "decode_str": " 45"} -{"id": 5796, "token": "\u0120pal", "merges": "\u0120p al", "raw_count": 332178, "count": 404039, "decode_str": " pal"} -{"id": 29370, "token": "iq", "merges": "i q", "raw_count": 404072, "count": 404072, "decode_str": "iq"} -{"id": 18999, "token": "PATH", "merges": "P ATH", "raw_count": 404093, "count": 404093, "decode_str": "PATH"} -{"id": 3461, "token": "\u0120communic", "merges": "\u0120commun ic", "raw_count": 9679, "count": 404320, "decode_str": " communic"} -{"id": 17895, "token": "Rob", "merges": "R ob", "raw_count": 404339, "count": 404339, "decode_str": "Rob"} -{"id": 11860, "token": "shot", "merges": "sh ot", "raw_count": 78101, "count": 404347, "decode_str": "shot"} -{"id": 14699, "token": "iso", "merges": "is o", "raw_count": 404486, "count": 404486, "decode_str": "iso"} -{"id": 7352, "token": "uy", "merges": "u y", "raw_count": 147653, "count": 404537, "decode_str": "uy"} -{"id": 8224, "token": "Manager", "merges": "Man ager", "raw_count": 404562, "count": 404562, "decode_str": "Manager"} -{"id": 6929, "token": "acle", "merges": "ac le", "raw_count": 269008, "count": 404621, "decode_str": "acle"} -{"id": 4078, "token": "ociety", "merges": "oci ety", "raw_count": 57299, "count": 404643, "decode_str": "ociety"} -{"id": 5029, "token": ")).", "merges": ") ).", "raw_count": 404745, "count": 404745, "decode_str": "))."} -{"id": 13019, "token": "Level", "merges": "Le vel", "raw_count": 404849, "count": 404849, "decode_str": "Level"} -{"id": 23616, "token": "rica", "merges": "ric a", "raw_count": 405042, "count": 405042, "decode_str": "rica"} -{"id": 44142, "token": "scores", "merges": "sc ores", "raw_count": 405107, "count": 405107, "decode_str": "scores"} -{"id": 5724, "token": "\u0120monitor", "merges": "\u0120mon itor", "raw_count": 142184, "count": 405154, "decode_str": " monitor"} -{"id": 4777, "token": "stances", "merges": "st ances", "raw_count": 242734, "count": 405157, "decode_str": "stances"} -{"id": 28368, "token": "hp", "merges": "h p", "raw_count": 405364, "count": 405364, "decode_str": "hp"} -{"id": 1953, "token": "\u0120question", "merges": "\u0120quest ion", "raw_count": 357579, "count": 405494, "decode_str": " question"} -{"id": 54029, "token": "\u00e8\u00bd\u00b2", "merges": "\u00e8\u00bd \u00b2", "raw_count": 405587, "count": 405587, "decode_str": "\u8f72"} -{"id": 12753, "token": "Num", "merges": "N um", "raw_count": 366658, "count": 405624, "decode_str": "Num"} -{"id": 2458, "token": "ians", "merges": "i ans", "raw_count": 283357, "count": 405825, "decode_str": "ians"} -{"id": 5128, "token": "\u0120Data", "merges": "\u0120D ata", "raw_count": 405890, "count": 405890, "decode_str": " Data"} -{"id": 2921, "token": "ros", "merges": "ro s", "raw_count": 353177, "count": 405959, "decode_str": "ros"} -{"id": 24507, "token": "buck", "merges": "b uck", "raw_count": 68463, "count": 406035, "decode_str": "buck"} -{"id": 17394, "token": "tp", "merges": "t p", "raw_count": 406058, "count": 406058, "decode_str": "tp"} -{"id": 51924, "token": "\u00e6\u012d\u00ae", "merges": "\u00e6\u012d \u00ae", "raw_count": 406061, "count": 406061, "decode_str": "\u62ee"} -{"id": 10147, "token": "ULT", "merges": "UL T", "raw_count": 37140, "count": 406193, "decode_str": "ULT"} -{"id": 3760, "token": "rial", "merges": "ri al", "raw_count": 59829, "count": 406266, "decode_str": "rial"} -{"id": 13409, "token": "lan", "merges": "l an", "raw_count": 406272, "count": 406272, "decode_str": "lan"} -{"id": 16878, "token": "aml", "merges": "am l", "raw_count": 53398, "count": 406344, "decode_str": "aml"} -{"id": 9166, "token": "\u0120400", "merges": "\u01204 00", "raw_count": 406352, "count": 406352, "decode_str": " 400"} -{"id": 14581, "token": "Si", "merges": "S i", "raw_count": 406432, "count": 406432, "decode_str": "Si"} -{"id": 33844, "token": "messages", "merges": "m essages", "raw_count": 406534, "count": 406534, "decode_str": "messages"} -{"id": 6293, "token": "\u0120thread", "merges": "\u0120th read", "raw_count": 330967, "count": 406585, "decode_str": " thread"} -{"id": 54167, "token": "\u00e9\u0124\u00ba", "merges": "\u00e9\u0124 \u00ba", "raw_count": 406618, "count": 406618, "decode_str": "\u90ba"} -{"id": 2920, "token": "fully", "merges": "ful ly", "raw_count": 174746, "count": 406775, "decode_str": "fully"} -{"id": 19402, "token": "properties", "merges": "pro perties", "raw_count": 406982, "count": 406982, "decode_str": "properties"} -{"id": 3352, "token": "\u0120proced", "merges": "\u0120pro ced", "raw_count": 2227, "count": 407067, "decode_str": " proced"} -{"id": 2219, "token": "\u0120cases", "merges": "\u0120c ases", "raw_count": 407106, "count": 407106, "decode_str": " cases"} -{"id": 52351, "token": "\u00e6\u00a7\u012e", "merges": "\u00e6\u00a7 \u012e", "raw_count": 407333, "count": 407333, "decode_str": "\u69cc"} -{"id": 25085, "token": "388", "merges": "38 8", "raw_count": 407362, "count": 407362, "decode_str": "388"} -{"id": 11801, "token": "eff", "merges": "e ff", "raw_count": 200595, "count": 407465, "decode_str": "eff"} -{"id": 54294, "token": "\u00e9\u013a\u012a", "merges": "\u00e9\u013a \u012a", "raw_count": 407466, "count": 407466, "decode_str": "\u9608"} -{"id": 20085, "token": "upload", "merges": "u pload", "raw_count": 385529, "count": 407644, "decode_str": "upload"} -{"id": 16206, "token": "...,", "merges": ".. .,", "raw_count": 390066, "count": 407677, "decode_str": "...,"} -{"id": 2159, "token": "\u0120short", "merges": "\u0120sh ort", "raw_count": 269579, "count": 407913, "decode_str": " short"} -{"id": 53523, "token": "\u00e8\u0125\u00ab", "merges": "\u00e8\u0125 \u00ab", "raw_count": 408165, "count": 408165, "decode_str": "\u80eb"} -{"id": 13995, "token": "'}", "merges": "' }", "raw_count": 408170, "count": 408170, "decode_str": "'}"} -{"id": 3552, "token": "\u0120cred", "merges": "\u0120c red", "raw_count": 72513, "count": 408349, "decode_str": " cred"} -{"id": 3609, "token": "\u0120select", "merges": "\u0120se lect", "raw_count": 322281, "count": 408364, "decode_str": " select"} -{"id": 11840, "token": "OG", "merges": "O G", "raw_count": 371507, "count": 408367, "decode_str": "OG"} -{"id": 20206, "token": "ookie", "merges": "ook ie", "raw_count": 45189, "count": 408383, "decode_str": "ookie"} -{"id": 18493, "token": "197", "merges": "19 7", "raw_count": 408550, "count": 408550, "decode_str": "197"} -{"id": 10099, "token": "Page", "merges": "P age", "raw_count": 408558, "count": 408558, "decode_str": "Page"} -{"id": 24558, "token": "219", "merges": "2 19", "raw_count": 408679, "count": 408679, "decode_str": "219"} -{"id": 36688, "token": "exc", "merges": "ex c", "raw_count": 408820, "count": 408820, "decode_str": "exc"} -{"id": 25798, "token": "cred", "merges": "c red", "raw_count": 408841, "count": 408841, "decode_str": "cred"} -{"id": 23593, "token": "dump", "merges": "d ump", "raw_count": 408847, "count": 408847, "decode_str": "dump"} -{"id": 52827, "token": "\u00e7\u0131\u0132", "merges": "\u00e7\u0131 \u0132", "raw_count": 408851, "count": 408851, "decode_str": "\u73d0"} -{"id": 52908, "token": "\u00e7\u0138\u013f", "merges": "\u00e7\u0138 \u013f", "raw_count": 408854, "count": 408854, "decode_str": "\u759d"} -{"id": 51642, "token": "\u00e5\u00be\u0129", "merges": "\u00e5\u00be \u0129", "raw_count": 408870, "count": 408870, "decode_str": "\u5f87"} -{"id": 2735, "token": "abor", "merges": "ab or", "raw_count": 65819, "count": 408871, "decode_str": "abor"} -{"id": 52980, "token": "\u00e7\u013d\u0124", "merges": "\u00e7\u013d \u0124", "raw_count": 409010, "count": 409010, "decode_str": "\u76c2"} -{"id": 8819, "token": "ws", "merges": "w s", "raw_count": 405392, "count": 409057, "decode_str": "ws"} -{"id": 27496, "token": "755", "merges": "75 5", "raw_count": 409335, "count": 409335, "decode_str": "755"} -{"id": 22519, "token": "335", "merges": "33 5", "raw_count": 409492, "count": 409492, "decode_str": "335"} -{"id": 2097, "token": "\u0120means", "merges": "\u0120me ans", "raw_count": 409493, "count": 409493, "decode_str": " means"} -{"id": 2480, "token": "mber", "merges": "m ber", "raw_count": 191647, "count": 409586, "decode_str": "mber"} -{"id": 1858, "token": "ilar", "merges": "il ar", "raw_count": 22542, "count": 409602, "decode_str": "ilar"} -{"id": 3805, "token": "\u0120grad", "merges": "\u0120gr ad", "raw_count": 162228, "count": 409606, "decode_str": " grad"} -{"id": 53796, "token": "\u00e8\u00ae\u00b4", "merges": "\u00e8\u00ae \u00b4", "raw_count": 409647, "count": 409647, "decode_str": "\u8bb4"} -{"id": 52311, "token": "\u00e6\u00a1\u00a2", "merges": "\u00e6\u00a1 \u00a2", "raw_count": 409651, "count": 409651, "decode_str": "\u6862"} -{"id": 9179, "token": "Result", "merges": "Res ult", "raw_count": 409726, "count": 409726, "decode_str": "Result"} -{"id": 4254, "token": "\u0120operation", "merges": "\u0120oper ation", "raw_count": 409831, "count": 409831, "decode_str": " operation"} -{"id": 5113, "token": "\u0120objects", "merges": "\u0120object s", "raw_count": 409890, "count": 409890, "decode_str": " objects"} -{"id": 3131, "token": "ocr", "merges": "oc r", "raw_count": 52365, "count": 410077, "decode_str": "ocr"} -{"id": 3765, "token": "\u0120prep", "merges": "\u0120pre p", "raw_count": 50015, "count": 410079, "decode_str": " prep"} -{"id": 42663, "token": "lst", "merges": "l st", "raw_count": 410131, "count": 410131, "decode_str": "lst"} -{"id": 10320, "token": "wan", "merges": "w an", "raw_count": 404105, "count": 410138, "decode_str": "wan"} -{"id": 45819, "token": "1936", "merges": "19 36", "raw_count": 410195, "count": 410195, "decode_str": "1936"} -{"id": 15453, "token": "bn", "merges": "b n", "raw_count": 410275, "count": 410275, "decode_str": "bn"} -{"id": 15810, "token": "attribute", "merges": "att ribute", "raw_count": 410302, "count": 410302, "decode_str": "attribute"} -{"id": 2665, "token": "ortun", "merges": "ort un", "raw_count": 18500, "count": 410436, "decode_str": "ortun"} -{"id": 53035, "token": "\u00e7\u013f\u00be", "merges": "\u00e7\u013f \u00be", "raw_count": 410482, "count": 410482, "decode_str": "\u777e"} -{"id": 11796, "token": "Art", "merges": "A rt", "raw_count": 364188, "count": 410611, "decode_str": "Art"} -{"id": 5585, "token": "agement", "merges": "ag ement", "raw_count": 31903, "count": 410736, "decode_str": "agement"} -{"id": 3814, "token": "uel", "merges": "u el", "raw_count": 198377, "count": 410831, "decode_str": "uel"} -{"id": 53524, "token": "\u00e8\u0125\u0143", "merges": "\u00e8\u0125 \u0143", "raw_count": 410946, "count": 410946, "decode_str": "\u80ed"} -{"id": 2426, "token": "\u0120terms", "merges": "\u0120term s", "raw_count": 411006, "count": 411006, "decode_str": " terms"} -{"id": 3877, "token": "\u0120note", "merges": "\u0120not e", "raw_count": 411059, "count": 411059, "decode_str": " note"} -{"id": 5100, "token": "\u0120establish", "merges": "\u0120establ ish", "raw_count": 179285, "count": 411092, "decode_str": " establish"} -{"id": 3000, "token": "\u0120words", "merges": "\u0120wor ds", "raw_count": 411098, "count": 411098, "decode_str": " words"} -{"id": 53948, "token": "\u00e8\u00b5\u012a", "merges": "\u00e8\u00b5 \u012a", "raw_count": 411275, "count": 411275, "decode_str": "\u8d48"} -{"id": 24124, "token": "extra", "merges": "ext ra", "raw_count": 411348, "count": 411348, "decode_str": "extra"} -{"id": 25359, "token": "invalid", "merges": "in valid", "raw_count": 411428, "count": 411428, "decode_str": "invalid"} -{"id": 40116, "token": "(['", "merges": "( ['", "raw_count": 411645, "count": 411645, "decode_str": "(['"} -{"id": 1728, "token": "\u0120home", "merges": "\u0120h ome", "raw_count": 384781, "count": 411647, "decode_str": " home"} -{"id": 3714, "token": "\u0120ps", "merges": "\u0120p s", "raw_count": 302411, "count": 411729, "decode_str": " ps"} -{"id": 1571, "token": "\u0120determ", "merges": "\u0120det erm", "raw_count": 2838, "count": 411734, "decode_str": " determ"} -{"id": 3523, "token": "\u0120stop", "merges": "\u0120st op", "raw_count": 411794, "count": 411794, "decode_str": " stop"} -{"id": 38280, "token": "630", "merges": "6 30", "raw_count": 411897, "count": 411897, "decode_str": "630"} -{"id": 7739, "token": "%.", "merges": "% .", "raw_count": 412025, "count": 412025, "decode_str": "%."} -{"id": 20668, "token": "trace", "merges": "tr ace", "raw_count": 412208, "count": 412208, "decode_str": "trace"} -{"id": 2821, "token": "iding", "merges": "id ing", "raw_count": 71194, "count": 412399, "decode_str": "iding"} -{"id": 52844, "token": "\u00e7\u0132\u012c", "merges": "\u00e7\u0132 \u012c", "raw_count": 412595, "count": 412595, "decode_str": "\u740a"} -{"id": 3283, "token": "\u0120predict", "merges": "\u0120pred ict", "raw_count": 160708, "count": 412725, "decode_str": " predict"} -{"id": 7125, "token": "\u0120arguments", "merges": "\u0120arg uments", "raw_count": 412948, "count": 412948, "decode_str": " arguments"} -{"id": 5202, "token": "\u0120tree", "merges": "\u0120t ree", "raw_count": 412983, "count": 412983, "decode_str": " tree"} -{"id": 21596, "token": "download", "merges": "down load", "raw_count": 413014, "count": 413014, "decode_str": "download"} -{"id": 3209, "token": "iddle", "merges": "idd le", "raw_count": 14821, "count": 413123, "decode_str": "iddle"} -{"id": 3744, "token": "\u0120ful", "merges": "\u0120f ul", "raw_count": 9221, "count": 413183, "decode_str": " ful"} -{"id": 12722, "token": "disc", "merges": "d isc", "raw_count": 405514, "count": 413355, "decode_str": "disc"} -{"id": 1639, "token": "\u0120Cl", "merges": "\u0120C l", "raw_count": 60388, "count": 413489, "decode_str": " Cl"} -{"id": 8016, "token": "NF", "merges": "N F", "raw_count": 376665, "count": 413674, "decode_str": "NF"} -{"id": 51028, "token": "\u00e5\u0134\u0139", "merges": "\u00e5\u0134 \u0139", "raw_count": 413846, "count": 413846, "decode_str": "\u5497"} -{"id": 10292, "token": "Min", "merges": "M in", "raw_count": 365125, "count": 413903, "decode_str": "Min"} -{"id": 52684, "token": "\u00e6\u00ba\u00a7", "merges": "\u00e6\u00ba \u00a7", "raw_count": 413916, "count": 413916, "decode_str": "\u6ea7"} -{"id": 5535, "token": "\u0120upd", "merges": "\u0120up d", "raw_count": 20974, "count": 413921, "decode_str": " upd"} -{"id": 52666, "token": "\u00e6\u00b8\u00a5", "merges": "\u00e6\u00b8 \u00a5", "raw_count": 414074, "count": 414074, "decode_str": "\u6e25"} -{"id": 2319, "token": "\u0120discuss", "merges": "\u0120disc uss", "raw_count": 70645, "count": 414148, "decode_str": " discuss"} -{"id": 4926, "token": "roy", "merges": "ro y", "raw_count": 93210, "count": 414287, "decode_str": "roy"} -{"id": 16352, "token": ";\"", "merges": "; \"", "raw_count": 414311, "count": 414311, "decode_str": ";\""} -{"id": 3005, "token": "delta", "merges": "d elta", "raw_count": 414331, "count": 414331, "decode_str": "delta"} -{"id": 14463, "token": "Tra", "merges": "T ra", "raw_count": 170730, "count": 414509, "decode_str": "Tra"} -{"id": 13382, "token": "prom", "merges": "p rom", "raw_count": 260492, "count": 414571, "decode_str": "prom"} -{"id": 1529, "token": "\u0120another", "merges": "\u0120an other", "raw_count": 414789, "count": 414789, "decode_str": " another"} -{"id": 4107, "token": "\u0120fre", "merges": "\u0120f re", "raw_count": 147868, "count": 414852, "decode_str": " fre"} -{"id": 2800, "token": "\u0120six", "merges": "\u0120s ix", "raw_count": 284863, "count": 414887, "decode_str": " six"} -{"id": 2461, "token": "beta", "merges": "b eta", "raw_count": 414889, "count": 414889, "decode_str": "beta"} -{"id": 1837, "token": "\u0120dr", "merges": "\u0120d r", "raw_count": 104102, "count": 414997, "decode_str": " dr"} -{"id": 54012, "token": "\u00e8\u00ba\u0129", "merges": "\u00e8\u00ba \u0129", "raw_count": 415218, "count": 415218, "decode_str": "\u8e87"} -{"id": 19012, "token": "factor", "merges": "f actor", "raw_count": 415690, "count": 415690, "decode_str": "factor"} -{"id": 10569, "token": "IX", "merges": "I X", "raw_count": 344564, "count": 415714, "decode_str": "IX"} -{"id": 13041, "token": "rb", "merges": "r b", "raw_count": 415780, "count": 415780, "decode_str": "rb"} -{"id": 7114, "token": "\u0120tens", "merges": "\u0120t ens", "raw_count": 16814, "count": 415953, "decode_str": " tens"} -{"id": 5371, "token": "what", "merges": "w hat", "raw_count": 395363, "count": 416012, "decode_str": "what"} -{"id": 6309, "token": "just", "merges": "j ust", "raw_count": 213233, "count": 416033, "decode_str": "just"} -{"id": 37326, "token": "OTA", "merges": "OT A", "raw_count": 416043, "count": 416043, "decode_str": "OTA"} -{"id": 22693, "token": "321", "merges": "32 1", "raw_count": 416044, "count": 416044, "decode_str": "321"} -{"id": 9764, "token": "ouch", "merges": "ou ch", "raw_count": 110383, "count": 416242, "decode_str": "ouch"} -{"id": 51320, "token": "\u00e5\u00a5\u013a", "merges": "\u00e5\u00a5 \u013a", "raw_count": 416375, "count": 416375, "decode_str": "\u5958"} -{"id": 15348, "token": "LINE", "merges": "L INE", "raw_count": 414666, "count": 416815, "decode_str": "LINE"} -{"id": 2256, "token": "\u0120subject", "merges": "\u0120sub ject", "raw_count": 336917, "count": 416846, "decode_str": " subject"} -{"id": 22187, "token": "233", "merges": "23 3", "raw_count": 416881, "count": 416881, "decode_str": "233"} -{"id": 3526, "token": "idge", "merges": "id ge", "raw_count": 37845, "count": 417083, "decode_str": "idge"} -{"id": 47208, "token": "1935", "merges": "19 35", "raw_count": 417199, "count": 417199, "decode_str": "1935"} -{"id": 16895, "token": "plugin", "merges": "pl ugin", "raw_count": 417221, "count": 417221, "decode_str": "plugin"} -{"id": 5395, "token": "rices", "merges": "ric es", "raw_count": 136114, "count": 417248, "decode_str": "rices"} -{"id": 844, "token": "\u0120We", "merges": "\u0120W e", "raw_count": 284410, "count": 417304, "decode_str": " We"} -{"id": 6525, "token": "anges", "merges": "ang es", "raw_count": 118882, "count": 417305, "decode_str": "anges"} -{"id": 53398, "token": "\u00e7\u00bc\u00a5", "merges": "\u00e7\u00bc \u00a5", "raw_count": 417452, "count": 417452, "decode_str": "\u7f25"} -{"id": 53734, "token": "\u00e8\u00a3\u0128", "merges": "\u00e8\u00a3 \u0128", "raw_count": 417468, "count": 417468, "decode_str": "\u88c6"} -{"id": 2457, "token": "\u0120final", "merges": "\u0120f inal", "raw_count": 415924, "count": 417711, "decode_str": " final"} -{"id": 5831, "token": "0001", "merges": "00 01", "raw_count": 401622, "count": 417754, "decode_str": "0001"} -{"id": 14714, "token": "rank", "merges": "r ank", "raw_count": 378307, "count": 417765, "decode_str": "rank"} -{"id": 8139, "token": "\u0120\u00e2\u0122\u00a6", "merges": "\u0120\u00e2\u0122 \u00a6", "raw_count": 417803, "count": 417803, "decode_str": " \u2026"} -{"id": 25802, "token": "vars", "merges": "v ars", "raw_count": 417870, "count": 417870, "decode_str": "vars"} -{"id": 15179, "token": "engine", "merges": "eng ine", "raw_count": 397940, "count": 417877, "decode_str": "engine"} -{"id": 8112, "token": "END", "merges": "EN D", "raw_count": 417898, "count": 417898, "decode_str": "END"} -{"id": 3334, "token": "\u0120install", "merges": "\u0120inst all", "raw_count": 157675, "count": 417997, "decode_str": " install"} -{"id": 9245, "token": "si", "merges": "s i", "raw_count": 418060, "count": 418060, "decode_str": "si"} -{"id": 5368, "token": "\u0120existing", "merges": "\u0120exist ing", "raw_count": 418297, "count": 418297, "decode_str": " existing"} -{"id": 50615, "token": "\u00e4\u00bf\u00b8", "merges": "\u00e4\u00bf \u00b8", "raw_count": 418432, "count": 418432, "decode_str": "\u4ff8"} -{"id": 4694, "token": "vision", "merges": "v ision", "raw_count": 298357, "count": 418544, "decode_str": "vision"} -{"id": 2630, "token": "\u0120compon", "merges": "\u0120comp on", "raw_count": 775, "count": 418728, "decode_str": " compon"} -{"id": 21934, "token": "sequence", "merges": "sequ ence", "raw_count": 418753, "count": 418753, "decode_str": "sequence"} -{"id": 4411, "token": "aur", "merges": "a ur", "raw_count": 160135, "count": 418794, "decode_str": "aur"} -{"id": 51845, "token": "\u00e6\u012b\u00a6", "merges": "\u00e6\u012b \u00a6", "raw_count": 418805, "count": 418805, "decode_str": "\u6266"} -{"id": 8409, "token": "\u0120offset", "merges": "\u0120off set", "raw_count": 387122, "count": 418855, "decode_str": " offset"} -{"id": 40692, "token": "CES", "merges": "C ES", "raw_count": 405224, "count": 418872, "decode_str": "CES"} -{"id": 11808, "token": "Sum", "merges": "S um", "raw_count": 243600, "count": 418965, "decode_str": "Sum"} -{"id": 50538, "token": "\u00e4\u00bc\u00ab", "merges": "\u00e4\u00bc \u00ab", "raw_count": 419840, "count": 419840, "decode_str": "\u4f2b"} -{"id": 21397, "token": "324", "merges": "32 4", "raw_count": 420066, "count": 420066, "decode_str": "324"} -{"id": 52004, "token": "\u00e6\u0130\u00b3", "merges": "\u00e6\u0130 \u00b3", "raw_count": 420199, "count": 420199, "decode_str": "\u63b3"} -{"id": 14922, "token": "CB", "merges": "C B", "raw_count": 420261, "count": 420261, "decode_str": "CB"} -{"id": 15741, "token": "hex", "merges": "he x", "raw_count": 420265, "count": 420265, "decode_str": "hex"} -{"id": 3991, "token": "\u0120appropri", "merges": "\u0120appro pri", "raw_count": 21302, "count": 420371, "decode_str": " appropri"} -{"id": 6426, "token": "ker", "merges": "k er", "raw_count": 383723, "count": 420396, "decode_str": "ker"} -{"id": 4661, "token": "\u0120Che", "merges": "\u0120C he", "raw_count": 37403, "count": 420412, "decode_str": " Che"} -{"id": 6285, "token": "hr", "merges": "h r", "raw_count": 409400, "count": 420513, "decode_str": "hr"} -{"id": 2550, "token": "\u0120cannot", "merges": "\u0120can not", "raw_count": 420522, "count": 420522, "decode_str": " cannot"} -{"id": 5048, "token": "\u0120channel", "merges": "\u0120ch annel", "raw_count": 420587, "count": 420587, "decode_str": " channel"} -{"id": 15705, "token": "Super", "merges": "Su per", "raw_count": 420591, "count": 420591, "decode_str": "Super"} -{"id": 3055, "token": "\u0120private", "merges": "\u0120priv ate", "raw_count": 420670, "count": 420670, "decode_str": " private"} -{"id": 9803, "token": "LD", "merges": "L D", "raw_count": 410617, "count": 420823, "decode_str": "LD"} -{"id": 9305, "token": "\u0120raw", "merges": "\u0120ra w", "raw_count": 420964, "count": 420964, "decode_str": " raw"} -{"id": 20617, "token": "vari", "merges": "v ari", "raw_count": 93617, "count": 421002, "decode_str": "vari"} -{"id": 40100, "token": "680", "merges": "6 80", "raw_count": 421148, "count": 421148, "decode_str": "680"} -{"id": 6157, "token": "\u01202004", "merges": "\u0120200 4", "raw_count": 421206, "count": 421206, "decode_str": " 2004"} -{"id": 52797, "token": "\u00e7\u012c\u00b7", "merges": "\u00e7\u012c \u00b7", "raw_count": 421326, "count": 421326, "decode_str": "\u72b7"} -{"id": 6595, "token": "rie", "merges": "ri e", "raw_count": 164100, "count": 421332, "decode_str": "rie"} -{"id": 31794, "token": "OA", "merges": "O A", "raw_count": 421512, "count": 421512, "decode_str": "OA"} -{"id": 4900, "token": "\u0120ign", "merges": "\u0120 ign", "raw_count": 10279, "count": 421585, "decode_str": " ign"} -{"id": 9824, "token": "Filter", "merges": "Fil ter", "raw_count": 421637, "count": 421637, "decode_str": "Filter"} -{"id": 15418, "token": "David", "merges": "Dav id", "raw_count": 421659, "count": 421659, "decode_str": "David"} -{"id": 9992, "token": "020", "merges": "0 20", "raw_count": 421665, "count": 421665, "decode_str": "020"} -{"id": 53990, "token": "\u00e8\u00b7\u0126", "merges": "\u00e8\u00b7 \u0126", "raw_count": 421951, "count": 421951, "decode_str": "\u8dc4"} -{"id": 8662, "token": "Char", "merges": "Ch ar", "raw_count": 220055, "count": 421967, "decode_str": "Char"} -{"id": 50968, "token": "\u00e5\u0132\u0142", "merges": "\u00e5\u0132 \u0142", "raw_count": 422215, "count": 422215, "decode_str": "\u5420"} -{"id": 1985, "token": "\u0120rad", "merges": "\u0120r ad", "raw_count": 79096, "count": 422306, "decode_str": " rad"} -{"id": 4979, "token": "\u0120transform", "merges": "\u0120trans form", "raw_count": 256683, "count": 422455, "decode_str": " transform"} -{"id": 19639, "token": "\u00e2\u0122\u00a6.", "merges": "\u00e2\u0122\u00a6 .", "raw_count": 422613, "count": 422613, "decode_str": "\u2026."} -{"id": 18645, "token": "variable", "merges": "v ariable", "raw_count": 422681, "count": 422681, "decode_str": "variable"} -{"id": 4436, "token": "\u0120sche", "merges": "\u0120sc he", "raw_count": 6069, "count": 422682, "decode_str": " sche"} -{"id": 26673, "token": "369", "merges": "36 9", "raw_count": 422720, "count": 422720, "decode_str": "369"} -{"id": 54051, "token": "\u00e8\u00be\u013a", "merges": "\u00e8\u00be \u013a", "raw_count": 422838, "count": 422838, "decode_str": "\u8f98"} -{"id": 34751, "token": "PET", "merges": "P ET", "raw_count": 422904, "count": 422904, "decode_str": "PET"} -{"id": 52826, "token": "\u00e7\u0131\u0131", "merges": "\u00e7\u0131 \u0131", "raw_count": 422973, "count": 422973, "decode_str": "\u73cf"} -{"id": 24040, "token": "\u0120programmes", "merges": "\u0120program mes", "raw_count": 423019, "count": 423019, "decode_str": " programmes"} -{"id": 2992, "token": "*,", "merges": "* ,", "raw_count": 415578, "count": 423128, "decode_str": "*,"} -{"id": 7647, "token": "La", "merges": "L a", "raw_count": 382989, "count": 423350, "decode_str": "La"} -{"id": 54525, "token": "\u00e9\u00ab\u00bb", "merges": "\u00e9\u00ab \u00bb", "raw_count": 423465, "count": 423465, "decode_str": "\u9afb"} -{"id": 46407, "token": "599", "merges": "5 99", "raw_count": 423486, "count": 423486, "decode_str": "599"} -{"id": 2543, "token": "\u0120mechan", "merges": "\u0120me chan", "raw_count": 5220, "count": 423620, "decode_str": " mechan"} -{"id": 2593, "token": "\u0120section", "merges": "\u0120se ction", "raw_count": 422585, "count": 423664, "decode_str": " section"} -{"id": 7420, "token": "Pre", "merges": "P re", "raw_count": 314783, "count": 423767, "decode_str": "Pre"} -{"id": 43345, "token": "1951", "merges": "19 51", "raw_count": 424221, "count": 424221, "decode_str": "1951"} -{"id": 53383, "token": "\u00e7\u00bc\u012a", "merges": "\u00e7\u00bc \u012a", "raw_count": 424324, "count": 424324, "decode_str": "\u7f08"} -{"id": 8519, "token": "control", "merges": "cont rol", "raw_count": 374839, "count": 424477, "decode_str": "control"} -{"id": 46525, "token": "737", "merges": "7 37", "raw_count": 424484, "count": 424484, "decode_str": "737"} -{"id": 2045, "token": "\u0120previous", "merges": "\u0120prev ious", "raw_count": 329450, "count": 424601, "decode_str": " previous"} -{"id": 2453, "token": "\u0120cult", "merges": "\u0120c ult", "raw_count": 4465, "count": 424661, "decode_str": " cult"} -{"id": 52943, "token": "\u00e7\u0139\u00a7", "merges": "\u00e7\u0139 \u00a7", "raw_count": 424816, "count": 424816, "decode_str": "\u75e7"} -{"id": 16641, "token": "Found", "merges": "F ound", "raw_count": 151474, "count": 424952, "decode_str": "Found"} -{"id": 10295, "token": "\u0120kernel", "merges": "\u0120k ernel", "raw_count": 424992, "count": 424992, "decode_str": " kernel"} -{"id": 2852, "token": "\u0120future", "merges": "\u0120f uture", "raw_count": 425205, "count": 425205, "decode_str": " future"} -{"id": 11632, "token": "\u0120func", "merges": "\u0120fun c", "raw_count": 414857, "count": 425354, "decode_str": " func"} -{"id": 11257, "token": "Instance", "merges": "In stance", "raw_count": 406401, "count": 425410, "decode_str": "Instance"} -{"id": 19504, "token": "Invalid", "merges": "In valid", "raw_count": 425418, "count": 425418, "decode_str": "Invalid"} -{"id": 52540, "token": "\u00e6\u00b3\u00af", "merges": "\u00e6\u00b3 \u00af", "raw_count": 425460, "count": 425460, "decode_str": "\u6cef"} -{"id": 27348, "token": "311", "merges": "3 11", "raw_count": 425546, "count": 425546, "decode_str": "311"} -{"id": 3584, "token": "\u0120pack", "merges": "\u0120p ack", "raw_count": 91696, "count": 425647, "decode_str": " pack"} -{"id": 53642, "token": "\u00e8\u012d\u0134", "merges": "\u00e8\u012d \u0134", "raw_count": 426031, "count": 426031, "decode_str": "\u82d2"} -{"id": 8590, "token": "Content", "merges": "Cont ent", "raw_count": 426451, "count": 426451, "decode_str": "Content"} -{"id": 3386, "token": "\u0120features", "merges": "\u0120fe atures", "raw_count": 426572, "count": 426572, "decode_str": " features"} -{"id": 23869, "token": "=%", "merges": "= %", "raw_count": 426602, "count": 426602, "decode_str": "=%"} -{"id": 2459, "token": "\u0120ann", "merges": "\u0120an n", "raw_count": 64154, "count": 426742, "decode_str": " ann"} -{"id": 51397, "token": "\u00e5\u0143\u00ba", "merges": "\u00e5\u0143 \u00ba", "raw_count": 426875, "count": 426875, "decode_str": "\u5b7a"} -{"id": 3450, "token": "osition", "merges": "os ition", "raw_count": 13206, "count": 426980, "decode_str": "osition"} -{"id": 3306, "token": "document", "merges": "d ocument", "raw_count": 398351, "count": 427214, "decode_str": "document"} -{"id": 15778, "token": "VI", "merges": "V I", "raw_count": 427255, "count": 427255, "decode_str": "VI"} -{"id": 54448, "token": "\u00e9\u00a2\u0136", "merges": "\u00e9\u00a2 \u0136", "raw_count": 427286, "count": 427286, "decode_str": "\u9894"} -{"id": 37514, "token": "KD", "merges": "K D", "raw_count": 427380, "count": 427380, "decode_str": "KD"} -{"id": 4311, "token": "\u0120scale", "merges": "\u0120sc ale", "raw_count": 427426, "count": 427426, "decode_str": " scale"} -{"id": 26369, "token": "1967", "merges": "19 67", "raw_count": 427453, "count": 427453, "decode_str": "1967"} -{"id": 9873, "token": "Cor", "merges": "C or", "raw_count": 310801, "count": 427531, "decode_str": "Cor"} -{"id": 10040, "token": "\u0120iter", "merges": "\u0120it er", "raw_count": 285402, "count": 427712, "decode_str": " iter"} -{"id": 51937, "token": "\u00e6\u012e\u0130", "merges": "\u00e6\u012e \u0130", "raw_count": 427719, "count": 427719, "decode_str": "\u630e"} -{"id": 7810, "token": "ASS", "merges": "AS S", "raw_count": 169073, "count": 427747, "decode_str": "ASS"} -{"id": 2966, "token": "inn", "merges": "in n", "raw_count": 260423, "count": 427784, "decode_str": "inn"} -{"id": 7438, "token": "imer", "merges": "im er", "raw_count": 52954, "count": 427820, "decode_str": "imer"} -{"id": 1393, "token": "\u0120appe", "merges": "\u0120ap pe", "raw_count": 2818, "count": 427975, "decode_str": " appe"} -{"id": 1842, "token": "\u0120eas", "merges": "\u0120e as", "raw_count": 17755, "count": 428223, "decode_str": " eas"} -{"id": 9328, "token": "they", "merges": "the y", "raw_count": 428306, "count": 428306, "decode_str": "they"} -{"id": 17659, "token": "NH", "merges": "N H", "raw_count": 428339, "count": 428339, "decode_str": "NH"} -{"id": 2143, "token": "\u0120school", "merges": "\u0120s chool", "raw_count": 300835, "count": 428604, "decode_str": " school"} -{"id": 27865, "token": "555", "merges": "55 5", "raw_count": 428712, "count": 428712, "decode_str": "555"} -{"id": 13903, "token": "ango", "merges": "ang o", "raw_count": 104859, "count": 428728, "decode_str": "ango"} -{"id": 45202, "token": "1942", "merges": "19 42", "raw_count": 428731, "count": 428731, "decode_str": "1942"} -{"id": 53600, "token": "\u00e8\u012b\u00ae", "merges": "\u00e8\u012b \u00ae", "raw_count": 428745, "count": 428745, "decode_str": "\u826e"} -{"id": 2279, "token": "utes", "merges": "ut es", "raw_count": 62506, "count": 428828, "decode_str": "utes"} -{"id": 2276, "token": "fficient", "merges": "ffic ient", "raw_count": 32279, "count": 428861, "decode_str": "fficient"} -{"id": 14119, "token": "ocker", "merges": "ock er", "raw_count": 239157, "count": 429001, "decode_str": "ocker"} -{"id": 4494, "token": "\u0120descript", "merges": "\u0120desc ript", "raw_count": 1323, "count": 429079, "decode_str": " descript"} -{"id": 2498, "token": "]).", "merges": "] ).", "raw_count": 429089, "count": 429089, "decode_str": "])."} -{"id": 12543, "token": "install", "merges": "inst all", "raw_count": 347504, "count": 429183, "decode_str": "install"} -{"id": 12023, "token": "Server", "merges": "Ser ver", "raw_count": 429187, "count": 429187, "decode_str": "Server"} -{"id": 11798, "token": "irection", "merges": "ire ction", "raw_count": 37579, "count": 429388, "decode_str": "irection"} -{"id": 51597, "token": "\u00e5\u00bc\u012d", "merges": "\u00e5\u00bc \u012d", "raw_count": 429394, "count": 429394, "decode_str": "\u5f0b"} -{"id": 17258, "token": "MIN", "merges": "M IN", "raw_count": 429583, "count": 429583, "decode_str": "MIN"} -{"id": 16191, "token": "selected", "merges": "se lected", "raw_count": 429679, "count": 429679, "decode_str": "selected"} -{"id": 8015, "token": "ERR", "merges": "ER R", "raw_count": 128891, "count": 430439, "decode_str": "ERR"} -{"id": 7761, "token": "System", "merges": "S ystem", "raw_count": 430499, "count": 430499, "decode_str": "System"} -{"id": 4097, "token": "\u0120AP", "merges": "\u0120A P", "raw_count": 54769, "count": 430534, "decode_str": " AP"} -{"id": 7317, "token": "cut", "merges": "c ut", "raw_count": 344500, "count": 430598, "decode_str": "cut"} -{"id": 3831, "token": "\u0120contain", "merges": "\u0120cont ain", "raw_count": 194967, "count": 430620, "decode_str": " contain"} -{"id": 28985, "token": "convert", "merges": "con vert", "raw_count": 430753, "count": 430753, "decode_str": "convert"} -{"id": 11728, "token": "Acc", "merges": "A cc", "raw_count": 232362, "count": 430930, "decode_str": "Acc"} -{"id": 38589, "token": "repo", "merges": "rep o", "raw_count": 431234, "count": 431234, "decode_str": "repo"} -{"id": 54158, "token": "\u00e9\u0124\u00ac", "merges": "\u00e9 \u0124\u00ac", "raw_count": 431299, "count": 431299, "decode_str": "\u90ac"} -{"id": 19443, "token": "217", "merges": "2 17", "raw_count": 431303, "count": 431303, "decode_str": "217"} -{"id": 2531, "token": "istic", "merges": "ist ic", "raw_count": 207339, "count": 431467, "decode_str": "istic"} -{"id": 3861, "token": "\u0120prot", "merges": "\u0120pro t", "raw_count": 39815, "count": 431526, "decode_str": " prot"} -{"id": 5355, "token": "*(", "merges": "* (", "raw_count": 428513, "count": 431586, "decode_str": "*("} -{"id": 42594, "token": "12345", "merges": "12 345", "raw_count": 431588, "count": 431588, "decode_str": "12345"} -{"id": 3061, "token": "\u0120decision", "merges": "\u0120dec ision", "raw_count": 431680, "count": 431680, "decode_str": " decision"} -{"id": 2701, "token": "\u0120limit", "merges": "\u0120lim it", "raw_count": 348139, "count": 431810, "decode_str": " limit"} -{"id": 7157, "token": "unc", "merges": "un c", "raw_count": 159192, "count": 431984, "decode_str": "unc"} -{"id": 30663, "token": "Tech", "merges": "T ech", "raw_count": 432058, "count": 432058, "decode_str": "Tech"} -{"id": 9194, "token": "fd", "merges": "f d", "raw_count": 432075, "count": 432075, "decode_str": "fd"} -{"id": 5297, "token": "ci", "merges": "c i", "raw_count": 368638, "count": 432188, "decode_str": "ci"} -{"id": 31984, "token": "answer", "merges": "ans wer", "raw_count": 432215, "count": 432215, "decode_str": "answer"} -{"id": 4025, "token": "pret", "merges": "p ret", "raw_count": 210577, "count": 432505, "decode_str": "pret"} -{"id": 2318, "token": "\u0120ple", "merges": "\u0120p le", "raw_count": 9548, "count": 432558, "decode_str": " ple"} -{"id": 4901, "token": "\u0120enter", "merges": "\u0120ent er", "raw_count": 219034, "count": 432788, "decode_str": " enter"} -{"id": 20528, "token": "steps", "merges": "st eps", "raw_count": 429620, "count": 432866, "decode_str": "steps"} -{"id": 2898, "token": "\u0120application", "merges": "\u0120applic ation", "raw_count": 432876, "count": 432876, "decode_str": " application"} -{"id": 6606, "token": "rive", "merges": "ri ve", "raw_count": 58095, "count": 432904, "decode_str": "rive"} -{"id": 2567, "token": "\u0120company", "merges": "\u0120comp any", "raw_count": 432992, "count": 432992, "decode_str": " company"} -{"id": 43062, "token": "Excel", "merges": "Ex cel", "raw_count": 432997, "count": 432997, "decode_str": "Excel"} -{"id": 3585, "token": "\u0120rev", "merges": "\u0120re v", "raw_count": 130268, "count": 433113, "decode_str": " rev"} -{"id": 26423, "token": "PDF", "merges": "PD F", "raw_count": 433209, "count": 433209, "decode_str": "PDF"} -{"id": 2609, "token": "sqrt", "merges": "s qrt", "raw_count": 433384, "count": 433384, "decode_str": "sqrt"} -{"id": 2126, "token": "\u0120employ", "merges": "\u0120em ploy", "raw_count": 14791, "count": 433470, "decode_str": " employ"} -{"id": 10030, "token": "\u0120Key", "merges": "\u0120K ey", "raw_count": 433836, "count": 433836, "decode_str": " Key"} -{"id": 2182, "token": "ising", "merges": "is ing", "raw_count": 79614, "count": 433854, "decode_str": "ising"} -{"id": 12965, "token": "Run", "merges": "R un", "raw_count": 348097, "count": 433894, "decode_str": "Run"} -{"id": 2878, "token": "ilt", "merges": "il t", "raw_count": 103394, "count": 433944, "decode_str": "ilt"} -{"id": 8100, "token": "ACK", "merges": "AC K", "raw_count": 268142, "count": 434227, "decode_str": "ACK"} -{"id": 2997, "token": "\u0120accept", "merges": "\u0120ac cept", "raw_count": 178059, "count": 434459, "decode_str": " accept"} -{"id": 7611, "token": "SR", "merges": "S R", "raw_count": 390293, "count": 434507, "decode_str": "SR"} -{"id": 2575, "token": "aced", "merges": "ac ed", "raw_count": 69161, "count": 434547, "decode_str": "aced"} -{"id": 11495, "token": "Label", "merges": "L abel", "raw_count": 434640, "count": 434640, "decode_str": "Label"} -{"id": 16054, "token": "fg", "merges": "f g", "raw_count": 169017, "count": 434670, "decode_str": "fg"} -{"id": 11773, "token": "Mc", "merges": "M c", "raw_count": 380091, "count": 434799, "decode_str": "Mc"} -{"id": 2918, "token": "\u0120held", "merges": "\u0120he ld", "raw_count": 435092, "count": 435092, "decode_str": " held"} -{"id": 9294, "token": "Handler", "merges": "Hand ler", "raw_count": 435215, "count": 435244, "decode_str": "Handler"} -{"id": 6584, "token": "vi", "merges": "v i", "raw_count": 395297, "count": 435717, "decode_str": "vi"} -{"id": 2534, "token": "\u0120bar", "merges": "\u0120b ar", "raw_count": 349444, "count": 435876, "decode_str": " bar"} -{"id": 52708, "token": "\u00e7\u0123\u0131", "merges": "\u00e7\u0123 \u0131", "raw_count": 435991, "count": 435991, "decode_str": "\u704f"} -{"id": 53556, "token": "\u00e8\u0129\u0125", "merges": "\u00e8\u0129 \u0125", "raw_count": 436241, "count": 436241, "decode_str": "\u81c3"} -{"id": 3190, "token": "ynam", "merges": "yn am", "raw_count": 48791, "count": 436342, "decode_str": "ynam"} -{"id": 51531, "token": "\u00e5\u00b8\u013c", "merges": "\u00e5\u00b8 \u013c", "raw_count": 436639, "count": 436639, "decode_str": "\u5e1a"} -{"id": 3093, "token": "ili", "merges": "il i", "raw_count": 209174, "count": 436755, "decode_str": "ili"} -{"id": 11830, "token": "dl", "merges": "d l", "raw_count": 437079, "count": 437079, "decode_str": "dl"} -{"id": 42093, "token": "1939", "merges": "19 39", "raw_count": 437102, "count": 437102, "decode_str": "1939"} -{"id": 7711, "token": "YPE", "merges": "Y PE", "raw_count": 29712, "count": 437320, "decode_str": "YPE"} -{"id": 51702, "token": "\u00e6\u0122\u00a6", "merges": "\u00e6\u0122 \u00a6", "raw_count": 437446, "count": 437446, "decode_str": "\u6026"} -{"id": 4910, "token": "\u0120fields", "merges": "\u0120field s", "raw_count": 437458, "count": 437458, "decode_str": " fields"} -{"id": 7310, "token": "OUT", "merges": "OU T", "raw_count": 349383, "count": 437478, "decode_str": "OUT"} -{"id": 14223, "token": "BUG", "merges": "BU G", "raw_count": 256309, "count": 437578, "decode_str": "BUG"} -{"id": 1695, "token": "ertain", "merges": "ert ain", "raw_count": 34426, "count": 437633, "decode_str": "ertain"} -{"id": 30189, "token": ">=", "merges": "> =", "raw_count": 437774, "count": 437774, "decode_str": ">="} -{"id": 5844, "token": "bm", "merges": "b m", "raw_count": 437843, "count": 437843, "decode_str": "bm"} -{"id": 50577, "token": "\u00e4\u00be\u0131", "merges": "\u00e4\u00be \u0131", "raw_count": 437859, "count": 437859, "decode_str": "\u4f8f"} -{"id": 18835, "token": "mk", "merges": "m k", "raw_count": 262034, "count": 438079, "decode_str": "mk"} -{"id": 7689, "token": "End", "merges": "E nd", "raw_count": 390328, "count": 438131, "decode_str": "End"} -{"id": 52981, "token": "\u00e7\u013d\u0127", "merges": "\u00e7\u013d \u0127", "raw_count": 438513, "count": 438513, "decode_str": "\u76c5"} -{"id": 10708, "token": "package", "merges": "p ackage", "raw_count": 438624, "count": 438624, "decode_str": "package"} -{"id": 3086, "token": "anced", "merges": "an ced", "raw_count": 32779, "count": 438666, "decode_str": "anced"} -{"id": 34321, "token": "RGB", "merges": "R GB", "raw_count": 438870, "count": 438870, "decode_str": "RGB"} -{"id": 10050, "token": "chain", "merges": "ch ain", "raw_count": 416985, "count": 438951, "decode_str": "chain"} -{"id": 51137, "token": "\u00e5\u013b\u0130", "merges": "\u00e5\u013b \u0130", "raw_count": 438999, "count": 438999, "decode_str": "\u564e"} -{"id": 41858, "token": "1947", "merges": "19 47", "raw_count": 439248, "count": 439248, "decode_str": "1947"} -{"id": 2190, "token": "\u0120among", "merges": "\u0120am ong", "raw_count": 425892, "count": 439424, "decode_str": " among"} -{"id": 20969, "token": "events", "merges": "ev ents", "raw_count": 439641, "count": 439641, "decode_str": "events"} -{"id": 2144, "token": "\u0120material", "merges": "\u0120m aterial", "raw_count": 248272, "count": 439762, "decode_str": " material"} -{"id": 4249, "token": "ership", "merges": "ers hip", "raw_count": 44446, "count": 440026, "decode_str": "ership"} -{"id": 31930, "token": "extend", "merges": "ext end", "raw_count": 440033, "count": 440033, "decode_str": "extend"} -{"id": 11141, "token": "Arg", "merges": "Ar g", "raw_count": 109534, "count": 440255, "decode_str": "Arg"} -{"id": 13888, "token": "KEY", "merges": "KE Y", "raw_count": 440390, "count": 440390, "decode_str": "KEY"} -{"id": 24796, "token": "fail", "merges": "f ail", "raw_count": 440680, "count": 440680, "decode_str": "fail"} -{"id": 2218, "token": "\u0120done", "merges": "\u0120d one", "raw_count": 440729, "count": 440729, "decode_str": " done"} -{"id": 22214, "token": "storage", "merges": "st orage", "raw_count": 440777, "count": 440777, "decode_str": "storage"} -{"id": 48099, "token": "AMD", "merges": "AM D", "raw_count": 441091, "count": 441091, "decode_str": "AMD"} -{"id": 31663, "token": "GW", "merges": "G W", "raw_count": 441128, "count": 441128, "decode_str": "GW"} -{"id": 2179, "token": "iving", "merges": "iv ing", "raw_count": 31492, "count": 441182, "decode_str": "iving"} -{"id": 3148, "token": "\u0120display", "merges": "\u0120dis play", "raw_count": 366013, "count": 441206, "decode_str": " display"} -{"id": 1626, "token": "ury", "merges": "ur y", "raw_count": 119361, "count": 441552, "decode_str": "ury"} -{"id": 7187, "token": "bal", "merges": "b al", "raw_count": 184249, "count": 441727, "decode_str": "bal"} -{"id": 13813, "token": "Tube", "merges": "T ube", "raw_count": 433792, "count": 441739, "decode_str": "Tube"} -{"id": 53050, "token": "\u00e7\u0141\u00be", "merges": "\u00e7\u0141 \u00be", "raw_count": 441835, "count": 441835, "decode_str": "\u77fe"} -{"id": 7475, "token": "Gen", "merges": "G en", "raw_count": 295298, "count": 441915, "decode_str": "Gen"} -{"id": 28560, "token": "318", "merges": "3 18", "raw_count": 441976, "count": 441976, "decode_str": "318"} -{"id": 53860, "token": "\u00e8\u00b0\u012e", "merges": "\u00e8\u00b0 \u012e", "raw_count": 442017, "count": 442017, "decode_str": "\u8c0c"} -{"id": 4007, "token": "\u0120president", "merges": "\u0120pres ident", "raw_count": 402526, "count": 442215, "decode_str": " president"} -{"id": 22328, "token": "history", "merges": "h istory", "raw_count": 442218, "count": 442218, "decode_str": "history"} -{"id": 16450, "token": "generate", "merges": "gen erate", "raw_count": 435378, "count": 442427, "decode_str": "generate"} -{"id": 13299, "token": "container", "merges": "cont ainer", "raw_count": 442549, "count": 442549, "decode_str": "container"} -{"id": 21378, "token": "238", "merges": "23 8", "raw_count": 442583, "count": 442583, "decode_str": "238"} -{"id": 3870, "token": "iven", "merges": "iv en", "raw_count": 12520, "count": 442620, "decode_str": "iven"} -{"id": 6675, "token": "########", "merges": "#### ####", "raw_count": 65938, "count": 442912, "decode_str": "########"} -{"id": 4924, "token": "free", "merges": "f ree", "raw_count": 443352, "count": 443352, "decode_str": "free"} -{"id": 25472, "token": "325", "merges": "3 25", "raw_count": 443762, "count": 443762, "decode_str": "325"} -{"id": 9458, "token": "bound", "merges": "b ound", "raw_count": 347009, "count": 444073, "decode_str": "bound"} -{"id": 7737, "token": "hentic", "merges": "hen tic", "raw_count": 38326, "count": 444085, "decode_str": "hentic"} -{"id": 6016, "token": "\u0120handle", "merges": "\u0120hand le", "raw_count": 444120, "count": 444120, "decode_str": " handle"} -{"id": 9960, "token": "sur", "merges": "s ur", "raw_count": 238175, "count": 444122, "decode_str": "sur"} -{"id": 11717, "token": "master", "merges": "m aster", "raw_count": 444728, "count": 444728, "decode_str": "master"} -{"id": 53413, "token": "\u00e7\u00bd\u0136", "merges": "\u00e7\u00bd \u0136", "raw_count": 444888, "count": 444888, "decode_str": "\u7f54"} -{"id": 44606, "token": "1941", "merges": "19 41", "raw_count": 445127, "count": 445127, "decode_str": "1941"} -{"id": 52698, "token": "\u00e6\u00bc\u0137", "merges": "\u00e6\u00bc \u0137", "raw_count": 445211, "count": 445211, "decode_str": "\u6f15"} -{"id": 7720, "token": "ector", "merges": "ect or", "raw_count": 127686, "count": 445217, "decode_str": "ector"} -{"id": 1756, "token": "\u0120grow", "merges": "\u0120g row", "raw_count": 59158, "count": 445302, "decode_str": " grow"} -{"id": 52703, "token": "\u00e6\u00bc\u00af", "merges": "\u00e6\u00bc \u00af", "raw_count": 445436, "count": 445436, "decode_str": "\u6f2f"} -{"id": 9034, "token": "Dr", "merges": "D r", "raw_count": 412119, "count": 445748, "decode_str": "Dr"} -{"id": 679, "token": "math", "merges": "m ath", "raw_count": 413215, "count": 445787, "decode_str": "math"} -{"id": 2902, "token": "ama", "merges": "am a", "raw_count": 405938, "count": 446248, "decode_str": "ama"} -{"id": 1611, "token": "\u0120try", "merges": "\u0120tr y", "raw_count": 322206, "count": 446268, "decode_str": " try"} -{"id": 2668, "token": "\u0120taken", "merges": "\u0120t aken", "raw_count": 446503, "count": 446503, "decode_str": " taken"} -{"id": 53453, "token": "\u00e8\u0122\u013b", "merges": "\u00e8\u0122 \u013b", "raw_count": 446542, "count": 446542, "decode_str": "\u8019"} -{"id": 2627, "token": "ucle", "merges": "uc le", "raw_count": 10536, "count": 446647, "decode_str": "ucle"} -{"id": 53856, "token": "\u00e8\u00b0\u0128", "merges": "\u00e8\u00b0 \u0128", "raw_count": 446655, "count": 446655, "decode_str": "\u8c06"} -{"id": 51598, "token": "\u00e5\u00bc\u0133", "merges": "\u00e5\u00bc \u0133", "raw_count": 446704, "count": 446704, "decode_str": "\u5f11"} -{"id": 21294, "token": "entity", "merges": "ent ity", "raw_count": 446952, "count": 446952, "decode_str": "entity"} -{"id": 20207, "token": "312", "merges": "3 12", "raw_count": 447126, "count": 447126, "decode_str": "312"} -{"id": 2897, "token": "\u0120ang", "merges": "\u0120an g", "raw_count": 134986, "count": 447148, "decode_str": " ang"} -{"id": 13745, "token": "Core", "merges": "C ore", "raw_count": 447258, "count": 447258, "decode_str": "Core"} -{"id": 52531, "token": "\u00e6\u00b3\u0140", "merges": "\u00e6\u00b3 \u0140", "raw_count": 447296, "count": 447296, "decode_str": "\u6cde"} -{"id": 1602, "token": "\u0120beh", "merges": "\u0120be h", "raw_count": 4300, "count": 447310, "decode_str": " beh"} -{"id": 2301, "token": "\u0120mil", "merges": "\u0120m il", "raw_count": 49650, "count": 447373, "decode_str": " mil"} -{"id": 7273, "token": "UD", "merges": "U D", "raw_count": 391343, "count": 447427, "decode_str": "UD"} -{"id": 6783, "token": "\u0120500", "merges": "\u01205 00", "raw_count": 447503, "count": 447503, "decode_str": " 500"} -{"id": 1855, "token": "\u0120mov", "merges": "\u0120m ov", "raw_count": 20199, "count": 447833, "decode_str": " mov"} -{"id": 2397, "token": "\u0120repl", "merges": "\u0120re pl", "raw_count": 19428, "count": 447871, "decode_str": " repl"} -{"id": 6417, "token": "roller", "merges": "roll er", "raw_count": 15670, "count": 447893, "decode_str": "roller"} -{"id": 38758, "token": "plemented", "merges": "plement ed", "raw_count": 448312, "count": 448312, "decode_str": "plemented"} -{"id": 2961, "token": "aged", "merges": "ag ed", "raw_count": 152850, "count": 448423, "decode_str": "aged"} -{"id": 6004, "token": "\u0120Test", "merges": "\u0120T est", "raw_count": 408287, "count": 448443, "decode_str": " Test"} -{"id": 51984, "token": "\u00e6\u0130\u0124", "merges": "\u00e6\u0130 \u0124", "raw_count": 448597, "count": 448597, "decode_str": "\u6382"} -{"id": 50962, "token": "\u00e5\u0132\u0138", "merges": "\u00e5\u0132 \u0138", "raw_count": 448704, "count": 448704, "decode_str": "\u5416"} -{"id": 1557, "token": "\u0120care", "merges": "\u0120c are", "raw_count": 291388, "count": 448747, "decode_str": " care"} -{"id": 52157, "token": "\u00e6\u013b\u0136", "merges": "\u00e6\u013b \u0136", "raw_count": 448965, "count": 448965, "decode_str": "\u6654"} -{"id": 53991, "token": "\u00e8\u00b7\u0128", "merges": "\u00e8\u00b7 \u0128", "raw_count": 449040, "count": 449040, "decode_str": "\u8dc6"} -{"id": 6325, "token": "\u0120empty", "merges": "\u0120empt y", "raw_count": 449129, "count": 449129, "decode_str": " empty"} -{"id": 52488, "token": "\u00e6\u00b1\u00b4", "merges": "\u00e6\u00b1 \u00b4", "raw_count": 449152, "count": 449152, "decode_str": "\u6c74"} -{"id": 2216, "token": "\u0120design", "merges": "\u0120des ign", "raw_count": 297703, "count": 449163, "decode_str": " design"} -{"id": 7165, "token": "}.", "merges": "} .", "raw_count": 449123, "count": 449176, "decode_str": "}."} -{"id": 1846, "token": "\u0120common", "merges": "\u0120comm on", "raw_count": 418785, "count": 449250, "decode_str": " common"} -{"id": 2663, "token": "rew", "merges": "re w", "raw_count": 168881, "count": 449354, "decode_str": "rew"} -{"id": 1622, "token": "ither", "merges": "it her", "raw_count": 39366, "count": 449455, "decode_str": "ither"} -{"id": 2987, "token": "\u0120works", "merges": "\u0120wor ks", "raw_count": 257191, "count": 449458, "decode_str": " works"} -{"id": 51966, "token": "\u00e6\u012f\u0130", "merges": "\u00e6\u012f \u0130", "raw_count": 449666, "count": 449666, "decode_str": "\u634e"} -{"id": 2814, "token": "onal", "merges": "on al", "raw_count": 44491, "count": 449805, "decode_str": "onal"} -{"id": 8447, "token": "Number", "merges": "N umber", "raw_count": 450071, "count": 450071, "decode_str": "Number"} -{"id": 10407, "token": "ailable", "merges": "ail able", "raw_count": 1572, "count": 450179, "decode_str": "ailable"} -{"id": 5582, "token": "han", "merges": "h an", "raw_count": 307241, "count": 450323, "decode_str": "han"} -{"id": 2659, "token": "\u0120land", "merges": "\u0120l and", "raw_count": 344590, "count": 450344, "decode_str": " land"} -{"id": 54380, "token": "\u00e9\u013e\u0123", "merges": "\u00e9\u013e \u0123", "raw_count": 450495, "count": 450495, "decode_str": "\u9701"} -{"id": 52911, "token": "\u00e7\u0138\u00a3", "merges": "\u00e7\u0138 \u00a3", "raw_count": 450522, "count": 450522, "decode_str": "\u75a3"} -{"id": 21645, "token": "307", "merges": "30 7", "raw_count": 450567, "count": 450567, "decode_str": "307"} -{"id": 894, "token": "\u0120cell", "merges": "\u0120c ell", "raw_count": 330528, "count": 450677, "decode_str": " cell"} -{"id": 27429, "token": "derr", "merges": "der r", "raw_count": 141363, "count": 450701, "decode_str": "derr"} -{"id": 4328, "token": "\u0120location", "merges": "\u0120loc ation", "raw_count": 450819, "count": 450819, "decode_str": " location"} -{"id": 53690, "token": "\u00e8\u013b\u00b1", "merges": "\u00e8\u013b \u00b1", "raw_count": 451190, "count": 451190, "decode_str": "\u8671"} -{"id": 20871, "token": "]+", "merges": "] +", "raw_count": 451333, "count": 451333, "decode_str": "]+"} -{"id": 21358, "token": "236", "merges": "23 6", "raw_count": 451724, "count": 451724, "decode_str": "236"} -{"id": 14661, "token": "ummy", "merges": "um my", "raw_count": 142446, "count": 451801, "decode_str": "ummy"} -{"id": 29309, "token": "coord", "merges": "co ord", "raw_count": 451848, "count": 451848, "decode_str": "coord"} -{"id": 22746, "token": "\u0120\".", "merges": "\u0120\" .", "raw_count": 452312, "count": 452312, "decode_str": " \"."} -{"id": 9115, "token": "lements", "merges": "le ments", "raw_count": 23060, "count": 452424, "decode_str": "lements"} -{"id": 11200, "token": "Token", "merges": "T oken", "raw_count": 452470, "count": 452470, "decode_str": "Token"} -{"id": 3309, "token": "\u0120necessary", "merges": "\u0120necess ary", "raw_count": 452471, "count": 452471, "decode_str": " necessary"} -{"id": 52624, "token": "\u00e6\u00b6\u00b8", "merges": "\u00e6\u00b6 \u00b8", "raw_count": 452473, "count": 452473, "decode_str": "\u6db8"} -{"id": 2119, "token": "\u0120sure", "merges": "\u0120su re", "raw_count": 436648, "count": 452666, "decode_str": " sure"} -{"id": 17107, "token": "229", "merges": "22 9", "raw_count": 452812, "count": 452812, "decode_str": "229"} -{"id": 3812, "token": "\u0120draw", "merges": "\u0120d raw", "raw_count": 352011, "count": 452872, "decode_str": " draw"} -{"id": 38862, "token": "530", "merges": "5 30", "raw_count": 453126, "count": 453126, "decode_str": "530"} -{"id": 45915, "token": "GPU", "merges": "G PU", "raw_count": 453236, "count": 453236, "decode_str": "GPU"} -{"id": 53866, "token": "\u00e8\u00b0\u0134", "merges": "\u00e8\u00b0 \u0134", "raw_count": 453271, "count": 453271, "decode_str": "\u8c12"} -{"id": 1821, "token": "\u0120men", "merges": "\u0120m en", "raw_count": 257629, "count": 453363, "decode_str": " men"} -{"id": 51071, "token": "\u00e5\u0135\u00a7", "merges": "\u00e5\u0135 \u00a7", "raw_count": 453363, "count": 453363, "decode_str": "\u54e7"} -{"id": 3471, "token": "\u0120ge", "merges": "\u0120g e", "raw_count": 214057, "count": 453432, "decode_str": " ge"} -{"id": 16360, "token": "writer", "merges": "writ er", "raw_count": 453457, "count": 453457, "decode_str": "writer"} -{"id": 3627, "token": "ula", "merges": "ul a", "raw_count": 184638, "count": 453727, "decode_str": "ula"} -{"id": 18635, "token": "Fore", "merges": "F ore", "raw_count": 395867, "count": 453845, "decode_str": "Fore"} -{"id": 53310, "token": "\u00e7\u00ba\u00a3", "merges": "\u00e7\u00ba \u00a3", "raw_count": 453849, "count": 453849, "decode_str": "\u7ea3"} -{"id": 13608, "token": "news", "merges": "new s", "raw_count": 453869, "count": 453869, "decode_str": "news"} -{"id": 20546, "token": "\u0120headers", "merges": "\u0120head ers", "raw_count": 453953, "count": 453953, "decode_str": " headers"} -{"id": 4539, "token": "uns", "merges": "un s", "raw_count": 394945, "count": 454318, "decode_str": "uns"} -{"id": 13982, "token": "comment", "merges": "com ment", "raw_count": 454609, "count": 454609, "decode_str": "comment"} -{"id": 7519, "token": "CK", "merges": "C K", "raw_count": 368681, "count": 454791, "decode_str": "CK"} -{"id": 1517, "token": "\u0120bre", "merges": "\u0120b re", "raw_count": 24615, "count": 454923, "decode_str": " bre"} -{"id": 52792, "token": "\u00e7\u012c\u012c", "merges": "\u00e7\u012c \u012c", "raw_count": 455140, "count": 455140, "decode_str": "\u728a"} -{"id": 19816, "token": "171", "merges": "17 1", "raw_count": 455321, "count": 455321, "decode_str": "171"} -{"id": 14168, "token": "\u0120math", "merges": "\u0120m ath", "raw_count": 455338, "count": 455338, "decode_str": " math"} -{"id": 3451, "token": "\u0120correct", "merges": "\u0120corre ct", "raw_count": 326260, "count": 455509, "decode_str": " correct"} -{"id": 1260, "token": "\u0120som", "merges": "\u0120s om", "raw_count": 113215, "count": 455732, "decode_str": " som"} -{"id": 53063, "token": "\u00e7\u0142\u00a7", "merges": "\u00e7\u0142 \u00a7", "raw_count": 455774, "count": 455774, "decode_str": "\u7827"} -{"id": 6358, "token": "ias", "merges": "i as", "raw_count": 173631, "count": 455913, "decode_str": "ias"} -{"id": 50793, "token": "\u00e5\u012b\u012e", "merges": "\u00e5\u012b \u012e", "raw_count": 455972, "count": 455972, "decode_str": "\u524c"} -{"id": 2981, "token": "xi", "merges": "x i", "raw_count": 434494, "count": 455995, "decode_str": "xi"} -{"id": 36016, "token": "810", "merges": "8 10", "raw_count": 456019, "count": 456019, "decode_str": "810"} -{"id": 20895, "token": "181", "merges": "18 1", "raw_count": 456138, "count": 456138, "decode_str": "181"} -{"id": 1770, "token": "\u0120month", "merges": "\u0120mon th", "raw_count": 224556, "count": 456159, "decode_str": " month"} -{"id": 33229, "token": "+\"", "merges": "+ \"", "raw_count": 456343, "count": 456343, "decode_str": "+\""} -{"id": 29858, "token": "Alpha", "merges": "Al pha", "raw_count": 456346, "count": 456346, "decode_str": "Alpha"} -{"id": 9041, "token": "uan", "merges": "u an", "raw_count": 454022, "count": 456546, "decode_str": "uan"} -{"id": 8875, "token": "ICE", "merges": "IC E", "raw_count": 416106, "count": 456739, "decode_str": "ICE"} -{"id": 50642, "token": "\u00e5\u0123\u012e", "merges": "\u00e5\u0123 \u012e", "raw_count": 456750, "count": 456750, "decode_str": "\u504c"} -{"id": 5091, "token": "\u012090", "merges": "\u01209 0", "raw_count": 456760, "count": 456760, "decode_str": " 90"} -{"id": 54474, "token": "\u00e9\u00a6\u0123", "merges": "\u00e9\u00a6 \u0123", "raw_count": 456777, "count": 456777, "decode_str": "\u9981"} -{"id": 39182, "token": "fake", "merges": "f ake", "raw_count": 457212, "count": 457212, "decode_str": "fake"} -{"id": 12502, "token": "yy", "merges": "y y", "raw_count": 424007, "count": 457267, "decode_str": "yy"} -{"id": 8252, "token": "Start", "merges": "St art", "raw_count": 401609, "count": 457306, "decode_str": "Start"} -{"id": 11148, "token": "Dev", "merges": "D ev", "raw_count": 242183, "count": 457345, "decode_str": "Dev"} -{"id": 11404, "token": "prov", "merges": "pro v", "raw_count": 130267, "count": 457453, "decode_str": "prov"} -{"id": 3235, "token": "Table", "merges": "T able", "raw_count": 457469, "count": 457469, "decode_str": "Table"} -{"id": 6475, "token": "ader", "merges": "ad er", "raw_count": 135880, "count": 457499, "decode_str": "ader"} -{"id": 22122, "token": "choice", "merges": "cho ice", "raw_count": 457681, "count": 457681, "decode_str": "choice"} -{"id": 32875, "token": "()))", "merges": "() ))", "raw_count": 457720, "count": 457720, "decode_str": "()))"} -{"id": 5766, "token": "\u0120empt", "merges": "\u0120em pt", "raw_count": 8850, "count": 457979, "decode_str": " empt"} -{"id": 3529, "token": "that", "merges": "th at", "raw_count": 458053, "count": 458053, "decode_str": "that"} -{"id": 14362, "token": "Dat", "merges": "D at", "raw_count": 327559, "count": 458068, "decode_str": "Dat"} -{"id": 5447, "token": "\u0120database", "merges": "\u0120dat abase", "raw_count": 458218, "count": 458218, "decode_str": " database"} -{"id": 4219, "token": "izes", "merges": "iz es", "raw_count": 309598, "count": 458505, "decode_str": "izes"} -{"id": 4076, "token": "\u0120clean", "merges": "\u0120cle an", "raw_count": 288611, "count": 458532, "decode_str": " clean"} -{"id": 30289, "token": "warn", "merges": "w arn", "raw_count": 458634, "count": 458634, "decode_str": "warn"} -{"id": 52251, "token": "\u00e6\u0140\u00b7", "merges": "\u00e6\u0140 \u00b7", "raw_count": 458823, "count": 458823, "decode_str": "\u67b7"} -{"id": 9198, "token": "blog", "merges": "bl og", "raw_count": 414022, "count": 459029, "decode_str": "blog"} -{"id": 16983, "token": "fp", "merges": "f p", "raw_count": 459077, "count": 459077, "decode_str": "fp"} -{"id": 1906, "token": "mu", "merges": "m u", "raw_count": 435672, "count": 459090, "decode_str": "mu"} -{"id": 13357, "token": "\u0120\"/", "merges": "\u0120\" /", "raw_count": 459299, "count": 459299, "decode_str": " \"/"} -{"id": 10975, "token": "bool", "merges": "b ool", "raw_count": 459423, "count": 459423, "decode_str": "bool"} -{"id": 11876, "token": "\u0120sys", "merges": "\u0120s ys", "raw_count": 455502, "count": 459634, "decode_str": " sys"} -{"id": 1872, "token": "\u0120hist", "merges": "\u0120h ist", "raw_count": 48813, "count": 459904, "decode_str": " hist"} -{"id": 7461, "token": "then", "merges": "the n", "raw_count": 199771, "count": 459920, "decode_str": "then"} -{"id": 50879, "token": "\u00e5\u012f\u0140", "merges": "\u00e5\u012f \u0140", "raw_count": 459977, "count": 459977, "decode_str": "\u535e"} -{"id": 1691, "token": "\u0120put", "merges": "\u0120p ut", "raw_count": 403837, "count": 460041, "decode_str": " put"} -{"id": 21361, "token": "249", "merges": "24 9", "raw_count": 460513, "count": 460513, "decode_str": "249"} -{"id": 54192, "token": "\u00e9\u0127\u0139", "merges": "\u00e9\u0127 \u0139", "raw_count": 460521, "count": 460521, "decode_str": "\u9157"} -{"id": 166, "token": "\u00ea", "merges": "NULL", "raw_count": 60031, "count": 460537, "decode_str": "\ufffd"} -{"id": 50948, "token": "\u00e5\u0131\u00bc", "merges": "\u00e5\u0131 \u00bc", "raw_count": 460540, "count": 460540, "decode_str": "\u53fc"} -{"id": 29331, "token": "\u0120lambda", "merges": "\u0120l ambda", "raw_count": 460566, "count": 460566, "decode_str": " lambda"} -{"id": 8614, "token": "\u0120hotel", "merges": "\u0120hot el", "raw_count": 460593, "count": 460593, "decode_str": " hotel"} -{"id": 10528, "token": "zero", "merges": "z ero", "raw_count": 449906, "count": 460783, "decode_str": "zero"} -{"id": 4692, "token": "ano", "merges": "an o", "raw_count": 416934, "count": 460823, "decode_str": "ano"} -{"id": 5011, "token": "otion", "merges": "ot ion", "raw_count": 98092, "count": 460858, "decode_str": "otion"} -{"id": 23282, "token": "essages", "merges": "ess ages", "raw_count": 5000, "count": 460982, "decode_str": "essages"} -{"id": 1523, "token": "ately", "merges": "at ely", "raw_count": 33847, "count": 461002, "decode_str": "ately"} -{"id": 11804, "token": "VM", "merges": "V M", "raw_count": 453936, "count": 461068, "decode_str": "VM"} -{"id": 54009, "token": "\u00e8\u00b7\u00ba", "merges": "\u00e8\u00b7 \u00ba", "raw_count": 461349, "count": 461349, "decode_str": "\u8dfa"} -{"id": 15093, "token": "rule", "merges": "ru le", "raw_count": 461365, "count": 461365, "decode_str": "rule"} -{"id": 5524, "token": "\u0120bud", "merges": "\u0120b ud", "raw_count": 51705, "count": 461366, "decode_str": " bud"} -{"id": 1998, "token": "rences", "merges": "ren ces", "raw_count": 30791, "count": 461470, "decode_str": "rences"} -{"id": 2201, "token": "\u0120major", "merges": "\u0120m ajor", "raw_count": 359556, "count": 461518, "decode_str": " major"} -{"id": 5354, "token": "ensions", "merges": "ens ions", "raw_count": 132438, "count": 461520, "decode_str": "ensions"} -{"id": 2638, "token": "ceed", "merges": "ce ed", "raw_count": 50287, "count": 461749, "decode_str": "ceed"} -{"id": 20122, "token": "zh", "merges": "z h", "raw_count": 461779, "count": 461779, "decode_str": "zh"} -{"id": 54475, "token": "\u00e9\u00a6\u0126", "merges": "\u00e9\u00a6 \u0126", "raw_count": 461827, "count": 461827, "decode_str": "\u9984"} -{"id": 2747, "token": "gment", "merges": "g ment", "raw_count": 5176, "count": 462014, "decode_str": "gment"} -{"id": 31491, "token": "tuple", "merges": "t uple", "raw_count": 462063, "count": 462063, "decode_str": "tuple"} -{"id": 7893, "token": "mid", "merges": "m id", "raw_count": 429555, "count": 462322, "decode_str": "mid"} -{"id": 54290, "token": "\u00e9\u013a\u0124", "merges": "\u00e9\u013a \u0124", "raw_count": 462328, "count": 462328, "decode_str": "\u9602"} -{"id": 11387, "token": "Top", "merges": "T op", "raw_count": 462512, "count": 462512, "decode_str": "Top"} -{"id": 7533, "token": "\u0120settings", "merges": "\u0120sett ings", "raw_count": 462546, "count": 462546, "decode_str": " settings"} -{"id": 11368, "token": "jpg", "merges": "j pg", "raw_count": 462586, "count": 462586, "decode_str": "jpg"} -{"id": 52346, "token": "\u00e6\u00a5\u00b9", "merges": "\u00e6\u00a5 \u00b9", "raw_count": 462642, "count": 462642, "decode_str": "\u6979"} -{"id": 20431, "token": "Power", "merges": "P ower", "raw_count": 462806, "count": 462806, "decode_str": "Power"} -{"id": 52126, "token": "\u00e6\u013a\u0122", "merges": "\u00e6\u013a \u0122", "raw_count": 462879, "count": 462879, "decode_str": "\u6600"} -{"id": 889, "token": "}\\", "merges": "} \\", "raw_count": 368300, "count": 463099, "decode_str": "}\\"} -{"id": 22913, "token": "268", "merges": "26 8", "raw_count": 463120, "count": 463120, "decode_str": "268"} -{"id": 6587, "token": "RL", "merges": "R L", "raw_count": 148186, "count": 463181, "decode_str": "RL"} -{"id": 5350, "token": "\u0120capacity", "merges": "\u0120capac ity", "raw_count": 463526, "count": 463526, "decode_str": " capacity"} -{"id": 14643, "token": "1989", "merges": "19 89", "raw_count": 463722, "count": 463722, "decode_str": "1989"} -{"id": 7732, "token": "\u0120persons", "merges": "\u0120pers ons", "raw_count": 463844, "count": 463844, "decode_str": " persons"} -{"id": 2905, "token": "\u0120related", "merges": "\u0120rel ated", "raw_count": 464206, "count": 464206, "decode_str": " related"} -{"id": 22340, "token": "prev", "merges": "pre v", "raw_count": 464250, "count": 464250, "decode_str": "prev"} -{"id": 2791, "token": "\u0120market", "merges": "\u0120mark et", "raw_count": 378824, "count": 464289, "decode_str": " market"} -{"id": 11468, "token": "=-", "merges": "= -", "raw_count": 450346, "count": 464374, "decode_str": "=-"} -{"id": 4019, "token": "za", "merges": "z a", "raw_count": 292552, "count": 464522, "decode_str": "za"} -{"id": 2944, "token": "\u0120decl", "merges": "\u0120de cl", "raw_count": 13997, "count": 464545, "decode_str": " decl"} -{"id": 3397, "token": "istics", "merges": "ist ics", "raw_count": 130471, "count": 464700, "decode_str": "istics"} -{"id": 17915, "token": "dn", "merges": "d n", "raw_count": 464877, "count": 464877, "decode_str": "dn"} -{"id": 54255, "token": "\u00e9\u0137\u0132", "merges": "\u00e9\u0137 \u0132", "raw_count": 464996, "count": 464996, "decode_str": "\u9550"} -{"id": 31569, "token": "qa", "merges": "q a", "raw_count": 465677, "count": 465677, "decode_str": "qa"} -{"id": 11285, "token": "hs", "merges": "h s", "raw_count": 413795, "count": 465725, "decode_str": "hs"} -{"id": 53727, "token": "\u00e8\u00a2\u00a4", "merges": "\u00e8\u00a2 \u00a4", "raw_count": 465827, "count": 465827, "decode_str": "\u88a4"} -{"id": 2304, "token": "\u0120mar", "merges": "\u0120m ar", "raw_count": 148843, "count": 465853, "decode_str": " mar"} -{"id": 4329, "token": "\u0120lat", "merges": "\u0120l at", "raw_count": 214351, "count": 465875, "decode_str": " lat"} -{"id": 2622, "token": "\u0120normal", "merges": "\u0120n ormal", "raw_count": 211496, "count": 465909, "decode_str": " normal"} -{"id": 6542, "token": "Array", "merges": "Ar ray", "raw_count": 462128, "count": 466205, "decode_str": "Array"} -{"id": 10186, "token": "world", "merges": "w orld", "raw_count": 466273, "count": 466273, "decode_str": "world"} -{"id": 2971, "token": "ster", "merges": "st er", "raw_count": 318160, "count": 466283, "decode_str": "ster"} -{"id": 3466, "token": "dered", "merges": "de red", "raw_count": 161552, "count": 466400, "decode_str": "dered"} -{"id": 5543, "token": "AND", "merges": "AN D", "raw_count": 363942, "count": 466484, "decode_str": "AND"} -{"id": 51669, "token": "\u00e5\u00bf\u0134", "merges": "\u00e5\u00bf \u0134", "raw_count": 466581, "count": 466581, "decode_str": "\u5fd2"} -{"id": 37262, "token": "Conv", "merges": "Con v", "raw_count": 466599, "count": 466599, "decode_str": "Conv"} -{"id": 1824, "token": "\u0120water", "merges": "\u0120w ater", "raw_count": 466868, "count": 466868, "decode_str": " water"} -{"id": 42910, "token": "-%", "merges": "- %", "raw_count": 466892, "count": 466892, "decode_str": "-%"} -{"id": 35191, "token": "510", "merges": "5 10", "raw_count": 466991, "count": 466991, "decode_str": "510"} -{"id": 51996, "token": "\u00e6\u0130\u00a3", "merges": "\u00e6\u0130 \u00a3", "raw_count": 467092, "count": 467092, "decode_str": "\u63a3"} -{"id": 18552, "token": "Alex", "merges": "A lex", "raw_count": 381953, "count": 467106, "decode_str": "Alex"} -{"id": 1698, "token": "\u0120low", "merges": "\u0120l ow", "raw_count": 354835, "count": 467312, "decode_str": " low"} -{"id": 4468, "token": "\u0120concern", "merges": "\u0120concer n", "raw_count": 205682, "count": 467442, "decode_str": " concern"} -{"id": 3247, "token": "olve", "merges": "ol ve", "raw_count": 176778, "count": 467499, "decode_str": "olve"} -{"id": 19581, "token": "amount", "merges": "am ount", "raw_count": 467808, "count": 467808, "decode_str": "amount"} -{"id": 3505, "token": "\u0120princ", "merges": "\u0120pr inc", "raw_count": 12804, "count": 467969, "decode_str": " princ"} -{"id": 4579, "token": "\u0120email", "merges": "\u0120em ail", "raw_count": 434829, "count": 468168, "decode_str": " email"} -{"id": 2846, "token": "\u0120city", "merges": "\u0120c ity", "raw_count": 468796, "count": 468796, "decode_str": " city"} -{"id": 13259, "token": "application", "merges": "app lication", "raw_count": 468807, "count": 468807, "decode_str": "application"} -{"id": 2881, "token": "ply", "merges": "p ly", "raw_count": 61158, "count": 468810, "decode_str": "ply"} -{"id": 20411, "token": "Pod", "merges": "P od", "raw_count": 466831, "count": 468907, "decode_str": "Pod"} -{"id": 23367, "token": "\u0120zip", "merges": "\u0120z ip", "raw_count": 469373, "count": 469373, "decode_str": " zip"} -{"id": 20455, "token": "Parser", "merges": "P arser", "raw_count": 469427, "count": 469427, "decode_str": "Parser"} -{"id": 4650, "token": "round", "merges": "r ound", "raw_count": 387714, "count": 469505, "decode_str": "round"} -{"id": 3562, "token": "\u0120created", "merges": "\u0120cre ated", "raw_count": 469676, "count": 469676, "decode_str": " created"} -{"id": 9210, "token": "vas", "merges": "v as", "raw_count": 46418, "count": 470036, "decode_str": "vas"} -{"id": 20664, "token": "161", "merges": "16 1", "raw_count": 470267, "count": 470267, "decode_str": "161"} -{"id": 8719, "token": "gener", "merges": "gen er", "raw_count": 79574, "count": 470444, "decode_str": "gener"} -{"id": 20583, "token": "tm", "merges": "t m", "raw_count": 470477, "count": 470477, "decode_str": "tm"} -{"id": 41960, "token": "1930", "merges": "19 30", "raw_count": 470521, "count": 470521, "decode_str": "1930"} -{"id": 53814, "token": "\u00e8\u00af\u012d", "merges": "\u00e8\u00af \u012d", "raw_count": 470560, "count": 470560, "decode_str": "\u8bcb"} -{"id": 2661, "token": "\u0120calcul", "merges": "\u0120cal cul", "raw_count": 13654, "count": 470590, "decode_str": " calcul"} -{"id": 9453, "token": "when", "merges": "w hen", "raw_count": 470723, "count": 470723, "decode_str": "when"} -{"id": 3204, "token": "unch", "merges": "un ch", "raw_count": 187479, "count": 471002, "decode_str": "unch"} -{"id": 54317, "token": "\u00e9\u013b\u0124", "merges": "\u00e9\u013b \u0124", "raw_count": 471116, "count": 471116, "decode_str": "\u9642"} -{"id": 1335, "token": "\u0120still", "merges": "\u0120st ill", "raw_count": 471720, "count": 471720, "decode_str": " still"} -{"id": 4448, "token": "ris", "merges": "r is", "raw_count": 276192, "count": 471792, "decode_str": "ris"} -{"id": 17280, "token": "\u0120\"%", "merges": "\u0120\" %", "raw_count": 471792, "count": 471792, "decode_str": " \"%"} -{"id": 52583, "token": "\u00e6\u00b5\u0136", "merges": "\u00e6\u00b5 \u0136", "raw_count": 471859, "count": 471859, "decode_str": "\u6d54"} -{"id": 2408, "token": "\u0120amount", "merges": "\u0120am ount", "raw_count": 409088, "count": 472025, "decode_str": " amount"} -{"id": 2672, "token": "ober", "merges": "o ber", "raw_count": 167486, "count": 472130, "decode_str": "ober"} -{"id": 5892, "token": "Exp", "merges": "Ex p", "raw_count": 247263, "count": 472404, "decode_str": "Exp"} -{"id": 14432, "token": "9999", "merges": "99 99", "raw_count": 417934, "count": 472510, "decode_str": "9999"} -{"id": 4791, "token": "\u012035", "merges": "\u01203 5", "raw_count": 472833, "count": 472833, "decode_str": " 35"} -{"id": 52458, "token": "\u00e6\u00b0\u00aa", "merges": "\u00e6\u00b0 \u00aa", "raw_count": 472901, "count": 472901, "decode_str": "\u6c2a"} -{"id": 17173, "token": "LV", "merges": "L V", "raw_count": 472988, "count": 472988, "decode_str": "LV"} -{"id": 9566, "token": "ACE", "merges": "AC E", "raw_count": 395516, "count": 473398, "decode_str": "ACE"} -{"id": 3136, "token": "oke", "merges": "o ke", "raw_count": 265760, "count": 473839, "decode_str": "oke"} -{"id": 51833, "token": "\u00e6\u012b\u012a", "merges": "\u00e6\u012b \u012a", "raw_count": 474670, "count": 474670, "decode_str": "\u6248"} -{"id": 11144, "token": "Block", "merges": "B lock", "raw_count": 474728, "count": 474728, "decode_str": "Block"} -{"id": 54086, "token": "\u00e8\u00bf\u00a9", "merges": "\u00e8\u00bf \u00a9", "raw_count": 474747, "count": 474747, "decode_str": "\u8fe9"} -{"id": 52233, "token": "\u00e6\u0140\u0129", "merges": "\u00e6\u0140 \u0129", "raw_count": 474851, "count": 474851, "decode_str": "\u6787"} -{"id": 50643, "token": "\u00e5\u0123\u0130", "merges": "\u00e5\u0123 \u0130", "raw_count": 474965, "count": 474965, "decode_str": "\u504e"} -{"id": 4161, "token": "GF", "merges": "G F", "raw_count": 367266, "count": 475259, "decode_str": "GF"} -{"id": 4218, "token": "Cal", "merges": "C al", "raw_count": 336523, "count": 475277, "decode_str": "Cal"} -{"id": 9617, "token": "\u0120directory", "merges": "\u0120direct ory", "raw_count": 475584, "count": 475584, "decode_str": " directory"} -{"id": 2508, "token": "\u0120detail", "merges": "\u0120det ail", "raw_count": 101376, "count": 475750, "decode_str": " detail"} -{"id": 30094, "token": "(\"\\", "merges": "(\" \\", "raw_count": 475896, "count": 475896, "decode_str": "(\"\\"} -{"id": 16741, "token": "ijing", "merges": "ij ing", "raw_count": 474049, "count": 475906, "decode_str": "ijing"} -{"id": 2171, "token": "\u0120diff", "merges": "\u0120dif f", "raw_count": 184214, "count": 475990, "decode_str": " diff"} -{"id": 5804, "token": "Can", "merges": "C an", "raw_count": 359767, "count": 476348, "decode_str": "Can"} -{"id": 44611, "token": "1938", "merges": "19 38", "raw_count": 476440, "count": 476440, "decode_str": "1938"} -{"id": 1168, "token": "->", "merges": "- >", "raw_count": 433532, "count": 476446, "decode_str": "->"} -{"id": 37269, "token": "\u00c2\u00b7\u00c2\u00b7\u00c2\u00b7", "merges": "\u00c2\u00b7\u00c2\u00b7 \u00c2\u00b7", "raw_count": 476522, "count": 476522, "decode_str": "\u00b7\u00b7\u00b7"} -{"id": 8078, "token": "\u0120Type", "merges": "\u0120T ype", "raw_count": 476537, "count": 476537, "decode_str": " Type"} -{"id": 25328, "token": "socket", "merges": "s ocket", "raw_count": 476620, "count": 476620, "decode_str": "socket"} -{"id": 21970, "token": "volume", "merges": "vol ume", "raw_count": 476645, "count": 476645, "decode_str": "volume"} -{"id": 17922, "token": "tk", "merges": "t k", "raw_count": 476696, "count": 476696, "decode_str": "tk"} -{"id": 2034, "token": "sel", "merges": "s el", "raw_count": 240903, "count": 476758, "decode_str": "sel"} -{"id": 52227, "token": "\u00e6\u013f\u00b7", "merges": "\u00e6\u013f \u00b7", "raw_count": 476879, "count": 476879, "decode_str": "\u6777"} -{"id": 3561, "token": "umb", "merges": "um b", "raw_count": 186266, "count": 476933, "decode_str": "umb"} -{"id": 29397, "token": "pick", "merges": "p ick", "raw_count": 477184, "count": 477184, "decode_str": "pick"} -{"id": 52804, "token": "\u00e7\u0130\u0133", "merges": "\u00e7\u0130 \u0133", "raw_count": 477301, "count": 477301, "decode_str": "\u7391"} -{"id": 9624, "token": "Load", "merges": "L oad", "raw_count": 232477, "count": 477310, "decode_str": "Load"} -{"id": 4029, "token": "pan", "merges": "p an", "raw_count": 203745, "count": 477624, "decode_str": "pan"} -{"id": 45422, "token": "offer", "merges": "off er", "raw_count": 477631, "count": 477631, "decode_str": "offer"} -{"id": 6455, "token": "\u0120convert", "merges": "\u0120con vert", "raw_count": 386466, "count": 477678, "decode_str": " convert"} -{"id": 4376, "token": "\u0120price", "merges": "\u0120pr ice", "raw_count": 477719, "count": 477719, "decode_str": " price"} -{"id": 20064, "token": ",*", "merges": ", *", "raw_count": 477739, "count": 477739, "decode_str": ",*"} -{"id": 7459, "token": "oded", "merges": "od ed", "raw_count": 131183, "count": 477844, "decode_str": "oded"} -{"id": 6648, "token": "Map", "merges": "M ap", "raw_count": 477014, "count": 477891, "decode_str": "Map"} -{"id": 9088, "token": "there", "merges": "the re", "raw_count": 452555, "count": 477925, "decode_str": "there"} -{"id": 12352, "token": "dc", "merges": "d c", "raw_count": 477935, "count": 477935, "decode_str": "dc"} -{"id": 23558, "token": "298", "merges": "29 8", "raw_count": 478088, "count": 478088, "decode_str": "298"} -{"id": 3943, "token": "\u0120unit", "merges": "\u0120un it", "raw_count": 478161, "count": 478161, "decode_str": " unit"} -{"id": 2173, "token": "\u0120specific", "merges": "\u0120spec ific", "raw_count": 446967, "count": 478216, "decode_str": " specific"} -{"id": 16719, "token": "depth", "merges": "dep th", "raw_count": 478298, "count": 478298, "decode_str": "depth"} -{"id": 13017, "token": "final", "merges": "f inal", "raw_count": 478589, "count": 478589, "decode_str": "final"} -{"id": 6014, "token": "Act", "merges": "A ct", "raw_count": 208064, "count": 479131, "decode_str": "Act"} -{"id": 53525, "token": "\u00e8\u0125\u00af", "merges": "\u00e8\u0125 \u00af", "raw_count": 479203, "count": 479203, "decode_str": "\u80ef"} -{"id": 4346, "token": "unction", "merges": "un ction", "raw_count": 14925, "count": 479238, "decode_str": "unction"} -{"id": 9665, "token": "dx", "merges": "d x", "raw_count": 479263, "count": 479263, "decode_str": "dx"} -{"id": 32040, "token": "Tok", "merges": "T ok", "raw_count": 479321, "count": 479321, "decode_str": "Tok"} -{"id": 14592, "token": "TM", "merges": "T M", "raw_count": 479475, "count": 479475, "decode_str": "TM"} -{"id": 51112, "token": "\u00e5\u0138\u0128", "merges": "\u00e5\u0138 \u0128", "raw_count": 479504, "count": 479504, "decode_str": "\u5586"} -{"id": 9395, "token": "Create", "merges": "C reate", "raw_count": 479033, "count": 479529, "decode_str": "Create"} -{"id": 32383, "token": "460", "merges": "4 60", "raw_count": 479719, "count": 479719, "decode_str": "460"} -{"id": 4024, "token": "inate", "merges": "in ate", "raw_count": 92925, "count": 479813, "decode_str": "inate"} -{"id": 1435, "token": "idence", "merges": "id ence", "raw_count": 48084, "count": 479821, "decode_str": "idence"} -{"id": 19875, "token": "pd", "merges": "p d", "raw_count": 479824, "count": 479824, "decode_str": "pd"} -{"id": 18116, "token": "\u0120'\\", "merges": "\u0120' \\", "raw_count": 479883, "count": 479883, "decode_str": " '\\"} -{"id": 19105, "token": "184", "merges": "18 4", "raw_count": 479918, "count": 479918, "decode_str": "184"} -{"id": 28880, "token": "777", "merges": "77 7", "raw_count": 479997, "count": 479997, "decode_str": "777"} -{"id": 3104, "token": "\u0120lines", "merges": "\u0120l ines", "raw_count": 480228, "count": 480228, "decode_str": " lines"} -{"id": 14201, "token": "Cr", "merges": "C r", "raw_count": 480260, "count": 480260, "decode_str": "Cr"} -{"id": 12494, "token": "\u0120paragraph", "merges": "\u0120par agraph", "raw_count": 405490, "count": 480379, "decode_str": " paragraph"} -{"id": 52628, "token": "\u00e6\u00b7\u0127", "merges": "\u00e6\u00b7 \u0127", "raw_count": 480380, "count": 480380, "decode_str": "\u6dc5"} -{"id": 22562, "token": "kernel", "merges": "k ernel", "raw_count": 480433, "count": 480433, "decode_str": "kernel"} -{"id": 1597, "token": "thing", "merges": "th ing", "raw_count": 93575, "count": 480606, "decode_str": "thing"} -{"id": 21196, "token": "states", "merges": "st ates", "raw_count": 480552, "count": 480825, "decode_str": "states"} -{"id": 21345, "token": "226", "merges": "22 6", "raw_count": 481005, "count": 481005, "decode_str": "226"} -{"id": 3117, "token": ")}", "merges": ") }", "raw_count": 479978, "count": 481021, "decode_str": ")}"} -{"id": 12456, "token": "UP", "merges": "U P", "raw_count": 481277, "count": 481277, "decode_str": "UP"} -{"id": 3496, "token": "\u0120ir", "merges": "\u0120 ir", "raw_count": 399783, "count": 481793, "decode_str": " ir"} -{"id": 11264, "token": "site", "merges": "s ite", "raw_count": 481973, "count": 481973, "decode_str": "site"} -{"id": 7821, "token": "inv", "merges": "in v", "raw_count": 391829, "count": 482247, "decode_str": "inv"} -{"id": 12574, "token": "render", "merges": "ren der", "raw_count": 471549, "count": 482281, "decode_str": "render"} -{"id": 3316, "token": "\u0120indust", "merges": "\u0120ind ust", "raw_count": 2740, "count": 482571, "decode_str": " indust"} -{"id": 4004, "token": "lation", "merges": "l ation", "raw_count": 23998, "count": 482697, "decode_str": "lation"} -{"id": 52822, "token": "\u00e7\u0131\u012a", "merges": "\u00e7\u0131 \u012a", "raw_count": 482750, "count": 482750, "decode_str": "\u73c8"} -{"id": 2755, "token": "omet", "merges": "om et", "raw_count": 44429, "count": 482863, "decode_str": "omet"} -{"id": 12579, "token": "late", "merges": "l ate", "raw_count": 160146, "count": 483013, "decode_str": "late"} -{"id": 1138, "token": "\">", "merges": "\" >", "raw_count": 387348, "count": 483055, "decode_str": "\">"} -{"id": 9339, "token": "ZE", "merges": "Z E", "raw_count": 119708, "count": 483128, "decode_str": "ZE"} -{"id": 23850, "token": "390", "merges": "39 0", "raw_count": 483138, "count": 483138, "decode_str": "390"} -{"id": 1599, "token": "\u0120mean", "merges": "\u0120me an", "raw_count": 366157, "count": 483215, "decode_str": " mean"} -{"id": 54510, "token": "\u00e9\u00aa\u00a5", "merges": "\u00e9\u00aa \u00a5", "raw_count": 483479, "count": 483479, "decode_str": "\u9aa5"} -{"id": 3817, "token": "\u0120box", "merges": "\u0120b ox", "raw_count": 355662, "count": 483637, "decode_str": " box"} -{"id": 9337, "token": "fill", "merges": "f ill", "raw_count": 462102, "count": 484168, "decode_str": "fill"} -{"id": 38765, "token": "1940", "merges": "19 40", "raw_count": 484306, "count": 484306, "decode_str": "1940"} -{"id": 1753, "token": "\u0120que", "merges": "\u0120qu e", "raw_count": 146033, "count": 484363, "decode_str": " que"} -{"id": 9304, "token": "Mon", "merges": "M on", "raw_count": 384844, "count": 484395, "decode_str": "Mon"} -{"id": 4790, "token": "ymbol", "merges": "ymb ol", "raw_count": 13281, "count": 484432, "decode_str": "ymbol"} -{"id": 5307, "token": "\u01202000", "merges": "\u01202 000", "raw_count": 484448, "count": 484448, "decode_str": " 2000"} -{"id": 30716, "token": "validate", "merges": "valid ate", "raw_count": 484507, "count": 484507, "decode_str": "validate"} -{"id": 10287, "token": "Str", "merges": "St r", "raw_count": 329263, "count": 484530, "decode_str": "Str"} -{"id": 54536, "token": "\u00e9\u00bb\u013f", "merges": "\u00e9\u00bb \u013f", "raw_count": 484551, "count": 484551, "decode_str": "\u9edd"} -{"id": 9505, "token": "Status", "merges": "St atus", "raw_count": 484557, "count": 484557, "decode_str": "Status"} -{"id": 22029, "token": "258", "merges": "25 8", "raw_count": 484627, "count": 484627, "decode_str": "258"} -{"id": 3758, "token": "apter", "merges": "ap ter", "raw_count": 5240, "count": 484883, "decode_str": "apter"} -{"id": 4760, "token": "\u0120player", "merges": "\u0120play er", "raw_count": 485010, "count": 485010, "decode_str": " player"} -{"id": 51685, "token": "\u00e5\u00bf\u00bf", "merges": "\u00e5\u00bf \u00bf", "raw_count": 485107, "count": 485107, "decode_str": "\u5fff"} -{"id": 25041, "token": "Mock", "merges": "M ock", "raw_count": 485200, "count": 485200, "decode_str": "Mock"} -{"id": 169, "token": "\u00ed", "merges": "NULL", "raw_count": 196346, "count": 485259, "decode_str": "\ufffd"} -{"id": 37594, "token": "\"].", "merges": "\" ].", "raw_count": 485338, "count": 485338, "decode_str": "\"]."} -{"id": 1960, "token": "\u0120cour", "merges": "\u0120c our", "raw_count": 10181, "count": 485339, "decode_str": " cour"} -{"id": 53223, "token": "\u00e7\u0143\u0131", "merges": "\u00e7\u0143 \u0131", "raw_count": 485397, "count": 485397, "decode_str": "\u7b4f"} -{"id": 9709, "token": "Mar", "merges": "M ar", "raw_count": 445613, "count": 485408, "decode_str": "Mar"} -{"id": 12022, "token": "hot", "merges": "h ot", "raw_count": 471640, "count": 485520, "decode_str": "hot"} -{"id": 2390, "token": "\u0120groups", "merges": "\u0120gr oups", "raw_count": 485765, "count": 485765, "decode_str": " groups"} -{"id": 1600, "token": "\u0120interest", "merges": "\u0120inte rest", "raw_count": 222590, "count": 485831, "decode_str": " interest"} -{"id": 24670, "token": "cluster", "merges": "cl uster", "raw_count": 485964, "count": 485964, "decode_str": "cluster"} -{"id": 4509, "token": "From", "merges": "F rom", "raw_count": 458572, "count": 486321, "decode_str": "From"} -{"id": 50617, "token": "\u00e4\u00bf\u00be", "merges": "\u00e4\u00bf \u00be", "raw_count": 486415, "count": 486415, "decode_str": "\u4ffe"} -{"id": 5007, "token": "\u0120send", "merges": "\u0120s end", "raw_count": 486500, "count": 486500, "decode_str": " send"} -{"id": 6741, "token": "ilder", "merges": "il der", "raw_count": 17100, "count": 486582, "decode_str": "ilder"} -{"id": 9553, "token": "enter", "merges": "ent er", "raw_count": 270502, "count": 486784, "decode_str": "enter"} -{"id": 4696, "token": "ael", "merges": "a el", "raw_count": 66608, "count": 486863, "decode_str": "ael"} -{"id": 3254, "token": "ites", "merges": "it es", "raw_count": 211441, "count": 487001, "decode_str": "ites"} -{"id": 18686, "token": "Home", "merges": "H ome", "raw_count": 487187, "count": 487187, "decode_str": "Home"} -{"id": 11316, "token": "cb", "merges": "c b", "raw_count": 487216, "count": 487216, "decode_str": "cb"} -{"id": 2014, "token": "\u0120single", "merges": "\u0120sing le", "raw_count": 487241, "count": 487241, "decode_str": " single"} -{"id": 20210, "token": "234", "merges": "23 4", "raw_count": 487286, "count": 487286, "decode_str": "234"} -{"id": 4431, "token": "itions", "merges": "ition s", "raw_count": 189114, "count": 487550, "decode_str": "itions"} -{"id": 2035, "token": "usion", "merges": "us ion", "raw_count": 143204, "count": 487588, "decode_str": "usion"} -{"id": 3042, "token": "isf", "merges": "is f", "raw_count": 286783, "count": 487602, "decode_str": "isf"} -{"id": 7049, "token": "\u0120tick", "merges": "\u0120t ick", "raw_count": 92218, "count": 487725, "decode_str": " tick"} -{"id": 6655, "token": "ests", "merges": "est s", "raw_count": 109875, "count": 487834, "decode_str": "ests"} -{"id": 17223, "token": "212", "merges": "2 12", "raw_count": 488033, "count": 488033, "decode_str": "212"} -{"id": 10948, "token": "ATH", "merges": "AT H", "raw_count": 62563, "count": 488044, "decode_str": "ATH"} -{"id": 24270, "token": "seed", "merges": "se ed", "raw_count": 488415, "count": 488415, "decode_str": "seed"} -{"id": 2339, "token": "ales", "merges": "al es", "raw_count": 115489, "count": 488559, "decode_str": "ales"} -{"id": 22872, "token": "policy", "merges": "pol icy", "raw_count": 488579, "count": 488579, "decode_str": "policy"} -{"id": 53557, "token": "\u00e8\u0129\u0128", "merges": "\u00e8\u0129 \u0128", "raw_count": 488654, "count": 488654, "decode_str": "\u81c6"} -{"id": 51116, "token": "\u00e5\u0138\u012d", "merges": "\u00e5\u0138 \u012d", "raw_count": 488691, "count": 488691, "decode_str": "\u558b"} -{"id": 12297, "token": "FE", "merges": "F E", "raw_count": 489069, "count": 489069, "decode_str": "FE"} -{"id": 4623, "token": "\u0120relevant", "merges": "\u0120rele vant", "raw_count": 489337, "count": 489337, "decode_str": " relevant"} -{"id": 5042, "token": "\u0120^", "merges": "\u0120 ^", "raw_count": 489394, "count": 489394, "decode_str": " ^"} -{"id": 9177, "token": "power", "merges": "p ower", "raw_count": 445862, "count": 489436, "decode_str": "power"} -{"id": 14776, "token": "uda", "merges": "ud a", "raw_count": 489442, "count": 489442, "decode_str": "uda"} -{"id": 53273, "token": "\u00e7\u00b2\u00b3", "merges": "\u00e7\u00b2 \u00b3", "raw_count": 489637, "count": 489637, "decode_str": "\u7cb3"} -{"id": 7916, "token": "layout", "merges": "l ayout", "raw_count": 489677, "count": 489677, "decode_str": "layout"} -{"id": 50917, "token": "\u00e5\u0131\u0123", "merges": "\u00e5\u0131 \u0123", "raw_count": 489677, "count": 489677, "decode_str": "\u53c1"} -{"id": 3198, "token": "\u0120needs", "merges": "\u0120need s", "raw_count": 489769, "count": 489769, "decode_str": " needs"} -{"id": 8962, "token": "uv", "merges": "u v", "raw_count": 486821, "count": 490005, "decode_str": "uv"} -{"id": 2351, "token": "ivity", "merges": "iv ity", "raw_count": 98095, "count": 490016, "decode_str": "ivity"} -{"id": 6855, "token": "fa", "merges": "f a", "raw_count": 457140, "count": 490324, "decode_str": "fa"} -{"id": 51829, "token": "\u00e6\u012a\u00be", "merges": "\u00e6\u012a \u00be", "raw_count": 490360, "count": 490360, "decode_str": "\u623e"} -{"id": 19893, "token": "distance", "merges": "d istance", "raw_count": 490464, "count": 490464, "decode_str": "distance"} -{"id": 7482, "token": "\u0120draft", "merges": "\u0120d raft", "raw_count": 425244, "count": 490562, "decode_str": " draft"} -{"id": 9499, "token": "Ke", "merges": "K e", "raw_count": 235695, "count": 490689, "decode_str": "Ke"} -{"id": 2343, "token": "\u0120lo", "merges": "\u0120l o", "raw_count": 99938, "count": 490820, "decode_str": " lo"} -{"id": 24717, "token": "fetch", "merges": "f etch", "raw_count": 490957, "count": 490957, "decode_str": "fetch"} -{"id": 822, "token": "========", "merges": "==== ====", "raw_count": 24828, "count": 491190, "decode_str": "========"} -{"id": 11746, "token": "menu", "merges": "men u", "raw_count": 491232, "count": 491232, "decode_str": "menu"} -{"id": 3828, "token": "\u0120layer", "merges": "\u0120lay er", "raw_count": 491474, "count": 491474, "decode_str": " layer"} -{"id": 54378, "token": "\u00e9\u013d\u00b9", "merges": "\u00e9\u013d \u00b9", "raw_count": 491622, "count": 491622, "decode_str": "\u96f9"} -{"id": 5380, "token": "oute", "merges": "ou te", "raw_count": 21954, "count": 491672, "decode_str": "oute"} -{"id": 54612, "token": "\u00ef\u00bc\u013f", "merges": "\u00ef\u00bc \u013f", "raw_count": 491719, "count": 491719, "decode_str": " "} -{"id": 8894, "token": "\u0120\"\\", "merges": "\u0120\" \\", "raw_count": 491791, "count": 491791, "decode_str": " \"\\"} -{"id": 51292, "token": "\u00e5\u00a4\u013b", "merges": "\u00e5\u00a4 \u013b", "raw_count": 491804, "count": 491804, "decode_str": "\u5919"} -{"id": 23926, "token": "368", "merges": "36 8", "raw_count": 491972, "count": 491972, "decode_str": "368"} -{"id": 4302, "token": "\u0120technology", "merges": "\u0120techn ology", "raw_count": 491989, "count": 491989, "decode_str": " technology"} -{"id": 4530, "token": "ka", "merges": "k a", "raw_count": 394533, "count": 492015, "decode_str": "ka"} -{"id": 54444, "token": "\u00e9\u00a2\u012f", "merges": "\u00e9\u00a2 \u012f", "raw_count": 492172, "count": 492172, "decode_str": "\u988d"} -{"id": 53114, "token": "\u00e7\u00a5\u0132", "merges": "\u00e7\u00a5 \u0132", "raw_count": 492276, "count": 492276, "decode_str": "\u7950"} -{"id": 13634, "token": "zone", "merges": "z one", "raw_count": 470383, "count": 492476, "decode_str": "zone"} -{"id": 775, "token": "\u0120Ch", "merges": "\u0120C h", "raw_count": 109219, "count": 492484, "decode_str": " Ch"} -{"id": 11917, "token": "hu", "merges": "h u", "raw_count": 491504, "count": 492634, "decode_str": "hu"} -{"id": 5583, "token": "\u0120recommend", "merges": "\u0120recomm end", "raw_count": 54655, "count": 492749, "decode_str": " recommend"} -{"id": 9863, "token": "vals", "merges": "v als", "raw_count": 441205, "count": 492803, "decode_str": "vals"} -{"id": 6117, "token": "ERS", "merges": "ER S", "raw_count": 336208, "count": 492835, "decode_str": "ERS"} -{"id": 51765, "token": "\u00e6\u0125\u013a", "merges": "\u00e6\u0125 \u013a", "raw_count": 492919, "count": 492919, "decode_str": "\u60d8"} -{"id": 2517, "token": "une", "merges": "un e", "raw_count": 440051, "count": 493032, "decode_str": "une"} -{"id": 6635, "token": "\u0120generate", "merges": "\u0120gener ate", "raw_count": 493122, "count": 493122, "decode_str": " generate"} -{"id": 2910, "token": "ball", "merges": "b all", "raw_count": 367274, "count": 493129, "decode_str": "ball"} -{"id": 53741, "token": "\u00e8\u00a3\u00a8", "merges": "\u00e8\u00a3 \u00a8", "raw_count": 493251, "count": 493251, "decode_str": "\u88e8"} -{"id": 34230, "token": "430", "merges": "4 30", "raw_count": 493335, "count": 493335, "decode_str": "430"} -{"id": 25647, "token": "ABC", "merges": "AB C", "raw_count": 493374, "count": 493374, "decode_str": "ABC"} -{"id": 39511, "token": "1954", "merges": "19 54", "raw_count": 493494, "count": 493494, "decode_str": "1954"} -{"id": 40533, "token": "1953", "merges": "19 53", "raw_count": 493621, "count": 493621, "decode_str": "1953"} -{"id": 21226, "token": "YY", "merges": "Y Y", "raw_count": 493822, "count": 493822, "decode_str": "YY"} -{"id": 16659, "token": "python", "merges": "py thon", "raw_count": 493941, "count": 493941, "decode_str": "python"} -{"id": 914, "token": "\u0120Un", "merges": "\u0120U n", "raw_count": 143033, "count": 494521, "decode_str": " Un"} -{"id": 2670, "token": "\u0120site", "merges": "\u0120s ite", "raw_count": 494742, "count": 494742, "decode_str": " site"} -{"id": 13010, "token": "LP", "merges": "L P", "raw_count": 494236, "count": 494747, "decode_str": "LP"} -{"id": 16179, "token": "visor", "merges": "vis or", "raw_count": 482759, "count": 494958, "decode_str": "visor"} -{"id": 18895, "token": "222", "merges": "22 2", "raw_count": 494991, "count": 494991, "decode_str": "222"} -{"id": 36245, "token": "915", "merges": "9 15", "raw_count": 495057, "count": 495057, "decode_str": "915"} -{"id": 51365, "token": "\u00e5\u00a7\u013f", "merges": "\u00e5\u00a7 \u013f", "raw_count": 495338, "count": 495338, "decode_str": "\u59dd"} -{"id": 7456, "token": "Service", "merges": "S ervice", "raw_count": 495380, "count": 495380, "decode_str": "Service"} -{"id": 20395, "token": "259", "merges": "25 9", "raw_count": 495405, "count": 495405, "decode_str": "259"} -{"id": 51759, "token": "\u00e6\u0125\u0128", "merges": "\u00e6\u0125 \u0128", "raw_count": 495447, "count": 495447, "decode_str": "\u60c6"} -{"id": 13837, "token": "TF", "merges": "T F", "raw_count": 479716, "count": 495563, "decode_str": "TF"} -{"id": 18804, "token": "174", "merges": "17 4", "raw_count": 495834, "count": 495834, "decode_str": "174"} -{"id": 1709, "token": "\u0120associ", "merges": "\u0120ass oci", "raw_count": 4544, "count": 495866, "decode_str": " associ"} -{"id": 17444, "token": "GD", "merges": "G D", "raw_count": 496349, "count": 496349, "decode_str": "GD"} -{"id": 50639, "token": "\u00e5\u0123\u0125", "merges": "\u00e5\u0123 \u0125", "raw_count": 496368, "count": 496368, "decode_str": "\u5043"} -{"id": 52873, "token": "\u00e7\u0136\u00ac", "merges": "\u00e7\u0136 \u00ac", "raw_count": 496797, "count": 496797, "decode_str": "\u752c"} -{"id": 2438, "token": "\u0120aff", "merges": "\u0120a ff", "raw_count": 42986, "count": 496908, "decode_str": " aff"} -{"id": 1958, "token": "ividual", "merges": "ivid ual", "raw_count": 355, "count": 496954, "decode_str": "ividual"} -{"id": 23481, "token": "chat", "merges": "ch at", "raw_count": 497056, "count": 497056, "decode_str": "chat"} -{"id": 9098, "token": "\u01201000", "merges": "\u01201 000", "raw_count": 497111, "count": 497111, "decode_str": " 1000"} -{"id": 2563, "token": "\u0120ep", "merges": "\u0120e p", "raw_count": 94489, "count": 497444, "decode_str": " ep"} -{"id": 6784, "token": "MR", "merges": "M R", "raw_count": 481030, "count": 497681, "decode_str": "MR"} -{"id": 53441, "token": "\u00e7\u00be\u00bf", "merges": "\u00e7\u00be \u00bf", "raw_count": 497881, "count": 497881, "decode_str": "\u7fbf"} -{"id": 28355, "token": "1966", "merges": "19 66", "raw_count": 498076, "count": 498076, "decode_str": "1966"} -{"id": 23097, "token": "NB", "merges": "N B", "raw_count": 498490, "count": 498490, "decode_str": "NB"} -{"id": 20104, "token": "callback", "merges": "call back", "raw_count": 498523, "count": 498523, "decode_str": "callback"} -{"id": 1302, "token": "\u0120court", "merges": "\u0120c ourt", "raw_count": 399150, "count": 498891, "decode_str": " court"} -{"id": 34493, "token": "1961", "merges": "19 61", "raw_count": 498939, "count": 498939, "decode_str": "1961"} -{"id": 19034, "token": "\u0120dictionary", "merges": "\u0120d ictionary", "raw_count": 499065, "count": 499065, "decode_str": " dictionary"} -{"id": 20450, "token": "275", "merges": "27 5", "raw_count": 499110, "count": 499110, "decode_str": "275"} -{"id": 6548, "token": "\u0120returns", "merges": "\u0120return s", "raw_count": 499411, "count": 499411, "decode_str": " returns"} -{"id": 23320, "token": "setup", "merges": "set up", "raw_count": 499610, "count": 499610, "decode_str": "setup"} -{"id": 53399, "token": "\u00e7\u00bc\u00a8", "merges": "\u00e7\u00bc \u00a8", "raw_count": 499732, "count": 499732, "decode_str": "\u7f28"} -{"id": 7580, "token": "Ent", "merges": "E nt", "raw_count": 101018, "count": 499745, "decode_str": "Ent"} -{"id": 25892, "token": "1969", "merges": "19 69", "raw_count": 499850, "count": 499850, "decode_str": "1969"} -{"id": 4843, "token": "asc", "merges": "as c", "raw_count": 181309, "count": 499867, "decode_str": "asc"} -{"id": 1285, "token": "arly", "merges": "ar ly", "raw_count": 31885, "count": 499916, "decode_str": "arly"} -{"id": 12205, "token": "Window", "merges": "W indow", "raw_count": 500102, "count": 500102, "decode_str": "Window"} -{"id": 9324, "token": "OB", "merges": "O B", "raw_count": 392843, "count": 500207, "decode_str": "OB"} -{"id": 22981, "token": "218", "merges": "2 18", "raw_count": 500534, "count": 500534, "decode_str": "218"} -{"id": 7958, "token": "uz", "merges": "u z", "raw_count": 453465, "count": 500553, "decode_str": "uz"} -{"id": 14853, "token": "SF", "merges": "S F", "raw_count": 500575, "count": 500575, "decode_str": "SF"} -{"id": 3497, "token": "\u0120window", "merges": "\u0120w indow", "raw_count": 394019, "count": 500627, "decode_str": " window"} -{"id": 3569, "token": "\u0120political", "merges": "\u0120polit ical", "raw_count": 500736, "count": 500736, "decode_str": " political"} -{"id": 53821, "token": "\u00e8\u00af\u013b", "merges": "\u00e8\u00af \u013b", "raw_count": 501012, "count": 501012, "decode_str": "\u8bd9"} -{"id": 38874, "token": "660", "merges": "6 60", "raw_count": 501212, "count": 501212, "decode_str": "660"} -{"id": 4642, "token": "vec", "merges": "ve c", "raw_count": 494066, "count": 501317, "decode_str": "vec"} -{"id": 4580, "token": "irt", "merges": "ir t", "raw_count": 110967, "count": 501327, "decode_str": "irt"} -{"id": 6684, "token": "\u0120developing", "merges": "\u0120develop ing", "raw_count": 501554, "count": 501554, "decode_str": " developing"} -{"id": 16455, "token": "video", "merges": "v ideo", "raw_count": 501593, "count": 501593, "decode_str": "video"} -{"id": 53382, "token": "\u00e7\u00bc\u0129", "merges": "\u00e7\u00bc \u0129", "raw_count": 501609, "count": 501609, "decode_str": "\u7f07"} -{"id": 13924, "token": "Ah", "merges": "A h", "raw_count": 501745, "count": 501745, "decode_str": "Ah"} -{"id": 6905, "token": "IST", "merges": "I ST", "raw_count": 269109, "count": 501764, "decode_str": "IST"} -{"id": 9296, "token": "rat", "merges": "r at", "raw_count": 185485, "count": 501787, "decode_str": "rat"} -{"id": 51550, "token": "\u00e5\u00b9\u00a1", "merges": "\u00e5\u00b9 \u00a1", "raw_count": 502095, "count": 502095, "decode_str": "\u5e61"} -{"id": 53567, "token": "\u00e8\u0129\u00bc", "merges": "\u00e8\u0129 \u00bc", "raw_count": 502179, "count": 502179, "decode_str": "\u81fc"} -{"id": 3143, "token": "\u0120achie", "merges": "\u0120a chie", "raw_count": 647, "count": 502319, "decode_str": " achie"} -{"id": 3410, "token": "\u0120sample", "merges": "\u0120sam ple", "raw_count": 502554, "count": 502554, "decode_str": " sample"} -{"id": 11352, "token": "\u0120delete", "merges": "\u0120de lete", "raw_count": 502590, "count": 502590, "decode_str": " delete"} -{"id": 15293, "token": "TI", "merges": "T I", "raw_count": 501369, "count": 502599, "decode_str": "TI"} -{"id": 12631, "token": "gex", "merges": "ge x", "raw_count": 31991, "count": 502703, "decode_str": "gex"} -{"id": 8989, "token": "\u0120mask", "merges": "\u0120m ask", "raw_count": 454323, "count": 503095, "decode_str": " mask"} -{"id": 5454, "token": "\u0120trade", "merges": "\u0120tr ade", "raw_count": 503165, "count": 503165, "decode_str": " trade"} -{"id": 2985, "token": "\u0120miss", "merges": "\u0120m iss", "raw_count": 61010, "count": 503210, "decode_str": " miss"} -{"id": 3197, "token": "used", "merges": "us ed", "raw_count": 354304, "count": 503577, "decode_str": "used"} -{"id": 3114, "token": "\u0120community", "merges": "\u0120commun ity", "raw_count": 503587, "count": 503587, "decode_str": " community"} -{"id": 14337, "token": "role", "merges": "ro le", "raw_count": 480437, "count": 503872, "decode_str": "role"} -{"id": 2598, "token": "So", "merges": "S o", "raw_count": 323286, "count": 503936, "decode_str": "So"} -{"id": 24987, "token": "vr", "merges": "v r", "raw_count": 504286, "count": 504286, "decode_str": "vr"} -{"id": 8301, "token": "SON", "merges": "S ON", "raw_count": 167997, "count": 504350, "decode_str": "SON"} -{"id": 4957, "token": "\u0120items", "merges": "\u0120it ems", "raw_count": 504424, "count": 504424, "decode_str": " items"} -{"id": 16777, "token": "comput", "merges": "com put", "raw_count": 77099, "count": 504626, "decode_str": "comput"} -{"id": 32549, "token": "timestamp", "merges": "tim estamp", "raw_count": 504670, "count": 504670, "decode_str": "timestamp"} -{"id": 50977, "token": "\u00e5\u0132\u00ae", "merges": "\u00e5\u0132 \u00ae", "raw_count": 504894, "count": 504894, "decode_str": "\u542e"} -{"id": 53850, "token": "\u00e8\u00af\u00bf", "merges": "\u00e8\u00af \u00bf", "raw_count": 504917, "count": 504917, "decode_str": "\u8bff"} -{"id": 4233, "token": "gy", "merges": "g y", "raw_count": 222085, "count": 504935, "decode_str": "gy"} -{"id": 4239, "token": "pid", "merges": "p id", "raw_count": 397705, "count": 505347, "decode_str": "pid"} -{"id": 7741, "token": "\u0120resource", "merges": "\u0120res ource", "raw_count": 505383, "count": 505383, "decode_str": " resource"} -{"id": 35163, "token": "CCT", "merges": "C CT", "raw_count": 505401, "count": 505401, "decode_str": "CCT"} -{"id": 2899, "token": "\u0120integr", "merges": "\u0120inte gr", "raw_count": 14251, "count": 505467, "decode_str": " integr"} -{"id": 13301, "token": "\u0120labels", "merges": "\u0120lab els", "raw_count": 505559, "count": 505559, "decode_str": " labels"} -{"id": 52391, "token": "\u00e6\u0143\u0128", "merges": "\u00e6\u0143 \u0128", "raw_count": 505800, "count": 505800, "decode_str": "\u6b46"} -{"id": 2137, "token": "\u0120war", "merges": "\u0120w ar", "raw_count": 281423, "count": 506171, "decode_str": " war"} -{"id": 8890, "token": "called", "merges": "call ed", "raw_count": 506249, "count": 506249, "decode_str": "called"} -{"id": 2867, "token": "\u0120property", "merges": "\u0120proper ty", "raw_count": 507139, "count": 507139, "decode_str": " property"} -{"id": 20700, "token": "182", "merges": "18 2", "raw_count": 507166, "count": 507166, "decode_str": "182"} -{"id": 13272, "token": "}\"", "merges": "} \"", "raw_count": 507230, "count": 507230, "decode_str": "}\""} -{"id": 2274, "token": "qrt", "merges": "q rt", "raw_count": 9007, "count": 507345, "decode_str": "qrt"} -{"id": 20285, "token": "counter", "merges": "c ounter", "raw_count": 507509, "count": 507509, "decode_str": "counter"} -{"id": 7109, "token": "tex", "merges": "te x", "raw_count": 161568, "count": 507689, "decode_str": "tex"} -{"id": 12583, "token": "cam", "merges": "c am", "raw_count": 292336, "count": 508043, "decode_str": "cam"} -{"id": 4570, "token": "perty", "merges": "per ty", "raw_count": 7257, "count": 508125, "decode_str": "perty"} -{"id": 6163, "token": "cks", "merges": "c ks", "raw_count": 160684, "count": 508291, "decode_str": "cks"} -{"id": 53275, "token": "\u00e7\u00b2\u00bc", "merges": "\u00e7\u00b2 \u00bc", "raw_count": 508476, "count": 508476, "decode_str": "\u7cbc"} -{"id": 52587, "token": "\u00e6\u00b5\u00a3", "merges": "\u00e6\u00b5 \u00a3", "raw_count": 508485, "count": 508485, "decode_str": "\u6d63"} -{"id": 2005, "token": "igma", "merges": "ig ma", "raw_count": 24404, "count": 508591, "decode_str": "igma"} -{"id": 7616, "token": "\u0120specified", "merges": "\u0120spec ified", "raw_count": 508639, "count": 508639, "decode_str": " specified"} -{"id": 9926, "token": "perties", "merges": "per ties", "raw_count": 929, "count": 508696, "decode_str": "perties"} -{"id": 1530, "token": "agn", "merges": "ag n", "raw_count": 89088, "count": 508697, "decode_str": "agn"} -{"id": 5973, "token": "ya", "merges": "y a", "raw_count": 488510, "count": 508732, "decode_str": "ya"} -{"id": 9111, "token": "bu", "merges": "b u", "raw_count": 142303, "count": 508808, "decode_str": "bu"} -{"id": 22728, "token": "iao", "merges": "ia o", "raw_count": 509062, "count": 509062, "decode_str": "iao"} -{"id": 4838, "token": "003", "merges": "00 3", "raw_count": 509098, "count": 509098, "decode_str": "003"} -{"id": 599, "token": "}}", "merges": "} }", "raw_count": 244281, "count": 509157, "decode_str": "}}"} -{"id": 3163, "token": "amed", "merges": "am ed", "raw_count": 104913, "count": 509209, "decode_str": "amed"} -{"id": 10754, "token": "Ver", "merges": "V er", "raw_count": 433008, "count": 509240, "decode_str": "Ver"} -{"id": 17306, "token": "187", "merges": "18 7", "raw_count": 509445, "count": 509445, "decode_str": "187"} -{"id": 52823, "token": "\u00e7\u0131\u012b", "merges": "\u00e7\u0131 \u012b", "raw_count": 509547, "count": 509547, "decode_str": "\u73c9"} -{"id": 4780, "token": "\u0120progress", "merges": "\u0120pro gress", "raw_count": 471078, "count": 510376, "decode_str": " progress"} -{"id": 45499, "token": "tokens", "merges": "tok ens", "raw_count": 510401, "count": 510401, "decode_str": "tokens"} -{"id": 16736, "token": "cost", "merges": "c ost", "raw_count": 510565, "count": 510565, "decode_str": "cost"} -{"id": 16929, "token": "Space", "merges": "S pace", "raw_count": 510993, "count": 510993, "decode_str": "Space"} -{"id": 13712, "token": "track", "merges": "tr ack", "raw_count": 509229, "count": 511067, "decode_str": "track"} -{"id": 2017, "token": "\u0120div", "merges": "\u0120d iv", "raw_count": 130345, "count": 511100, "decode_str": " div"} -{"id": 11000, "token": "vector", "merges": "ve ctor", "raw_count": 511285, "count": 511285, "decode_str": "vector"} -{"id": 4730, "token": "\u0120education", "merges": "\u0120educ ation", "raw_count": 511297, "count": 511297, "decode_str": " education"} -{"id": 39855, "token": "601", "merges": "6 01", "raw_count": 511380, "count": 511380, "decode_str": "601"} -{"id": 54389, "token": "\u00e9\u013e\u0131", "merges": "\u00e9\u013e \u0131", "raw_count": 511796, "count": 511796, "decode_str": "\u970f"} -{"id": 52926, "token": "\u00e7\u0139\u0124", "merges": "\u00e7\u0139 \u0124", "raw_count": 511861, "count": 511861, "decode_str": "\u75c2"} -{"id": 17523, "token": "pattern", "merges": "pat tern", "raw_count": 512044, "count": 512044, "decode_str": "pattern"} -{"id": 18278, "token": "FM", "merges": "F M", "raw_count": 512178, "count": 512178, "decode_str": "FM"} -{"id": 1880, "token": "\u0120whether", "merges": "\u0120whe ther", "raw_count": 512340, "count": 512340, "decode_str": " whether"} -{"id": 6802, "token": "Rep", "merges": "R ep", "raw_count": 215174, "count": 512345, "decode_str": "Rep"} -{"id": 13863, "token": "children", "merges": "child ren", "raw_count": 509479, "count": 512357, "decode_str": "children"} -{"id": 2338, "token": "uit", "merges": "u it", "raw_count": 199266, "count": 512470, "decode_str": "uit"} -{"id": 53618, "token": "\u00e8\u012c\u00a1", "merges": "\u00e8\u012c \u00a1", "raw_count": 512595, "count": 512595, "decode_str": "\u82a1"} -{"id": 2240, "token": "\u0120ben", "merges": "\u0120b en", "raw_count": 62992, "count": 513057, "decode_str": " ben"} -{"id": 8297, "token": "inte", "merges": "in te", "raw_count": 128836, "count": 513172, "decode_str": "inte"} -{"id": 51164, "token": "\u00e5\u013d\u00a7", "merges": "\u00e5\u013d \u00a7", "raw_count": 513175, "count": 513175, "decode_str": "\u56e7"} -{"id": 2832, "token": "\u0120htt", "merges": "\u0120h tt", "raw_count": 37958, "count": 513205, "decode_str": " htt"} -{"id": 53496, "token": "\u00e8\u0124\u00ae", "merges": "\u00e8\u0124 \u00ae", "raw_count": 513299, "count": 513299, "decode_str": "\u80ae"} -{"id": 32847, "token": "SIM", "merges": "S IM", "raw_count": 513449, "count": 513449, "decode_str": "SIM"} -{"id": 1700, "token": "osed", "merges": "os ed", "raw_count": 23230, "count": 513752, "decode_str": "osed"} -{"id": 1162, "token": "\u0120et", "merges": "\u0120 et", "raw_count": 275819, "count": 513832, "decode_str": " et"} -{"id": 11927, "token": "DD", "merges": "D D", "raw_count": 513849, "count": 513849, "decode_str": "DD"} -{"id": 6124, "token": "Code", "merges": "C ode", "raw_count": 514178, "count": 514178, "decode_str": "Code"} -{"id": 4320, "token": "\u0120legal", "merges": "\u0120leg al", "raw_count": 514240, "count": 514240, "decode_str": " legal"} -{"id": 1650, "token": "\u0120example", "merges": "\u0120exam ple", "raw_count": 514282, "count": 514282, "decode_str": " example"} -{"id": 51012, "token": "\u00e5\u0133\u00bb", "merges": "\u00e5\u0133 \u00bb", "raw_count": 514517, "count": 514517, "decode_str": "\u547b"} -{"id": 52619, "token": "\u00e6\u00b6\u00aa", "merges": "\u00e6\u00b6 \u00aa", "raw_count": 514709, "count": 514709, "decode_str": "\u6daa"} -{"id": 53004, "token": "\u00e7\u013e\u012a", "merges": "\u00e7\u013e \u012a", "raw_count": 514971, "count": 514971, "decode_str": "\u7708"} -{"id": 21020, "token": "Play", "merges": "Pl ay", "raw_count": 515386, "count": 515386, "decode_str": "Play"} -{"id": 4742, "token": "ky", "merges": "k y", "raw_count": 318189, "count": 515426, "decode_str": "ky"} -{"id": 14075, "token": "loop", "merges": "lo op", "raw_count": 515465, "count": 515465, "decode_str": "loop"} -{"id": 8932, "token": "Base", "merges": "B ase", "raw_count": 515860, "count": 515860, "decode_str": "Base"} -{"id": 41646, "token": "1948", "merges": "19 48", "raw_count": 516099, "count": 516099, "decode_str": "1948"} -{"id": 52953, "token": "\u00e7\u0139\u00bf", "merges": "\u00e7\u0139 \u00bf", "raw_count": 516245, "count": 516245, "decode_str": "\u75ff"} -{"id": 52371, "token": "\u00e6\u00a8\u00b5", "merges": "\u00e6\u00a8 \u00b5", "raw_count": 516424, "count": 516424, "decode_str": "\u6a35"} -{"id": 14712, "token": "\u0120temp", "merges": "\u0120tem p", "raw_count": 516445, "count": 516445, "decode_str": " temp"} -{"id": 29759, "token": "(**", "merges": "( **", "raw_count": 516456, "count": 516456, "decode_str": "(**"} -{"id": 19454, "token": "\u0120europe", "merges": "\u0120e urope", "raw_count": 516593, "count": 516620, "decode_str": " europe"} -{"id": 24218, "token": "ICO", "merges": "IC O", "raw_count": 516692, "count": 516692, "decode_str": "ICO"} -{"id": 172, "token": "\u00f0", "merges": "NULL", "raw_count": 363360, "count": 516734, "decode_str": "\ufffd"} -{"id": 4216, "token": "\u0120graph", "merges": "\u0120g raph", "raw_count": 432758, "count": 516771, "decode_str": " graph"} -{"id": 2436, "token": "\u0120necess", "merges": "\u0120ne cess", "raw_count": 14171, "count": 517297, "decode_str": " necess"} -{"id": 3490, "token": "\u0120force", "merges": "\u0120for ce", "raw_count": 517474, "count": 517474, "decode_str": " force"} -{"id": 3285, "token": "\u012029", "merges": "\u01202 9", "raw_count": 452555, "count": 517603, "decode_str": " 29"} -{"id": 34605, "token": "paths", "merges": "path s", "raw_count": 518124, "count": 518124, "decode_str": "paths"} -{"id": 41083, "token": "1952", "merges": "19 52", "raw_count": 518473, "count": 518473, "decode_str": "1952"} -{"id": 8506, "token": "AY", "merges": "A Y", "raw_count": 288345, "count": 519011, "decode_str": "AY"} -{"id": 6055, "token": "\u0120protection", "merges": "\u0120prote ction", "raw_count": 519105, "count": 519105, "decode_str": " protection"} -{"id": 11447, "token": "\u0120User", "merges": "\u0120U ser", "raw_count": 519434, "count": 519434, "decode_str": " User"} -{"id": 1347, "token": "\u0120perform", "merges": "\u0120per form", "raw_count": 151907, "count": 519461, "decode_str": " perform"} -{"id": 11478, "token": "Bo", "merges": "B o", "raw_count": 311099, "count": 519497, "decode_str": "Bo"} -{"id": 53316, "token": "\u00e7\u00ba\u00ab", "merges": "\u00e7\u00ba \u00ab", "raw_count": 519623, "count": 519623, "decode_str": "\u7eab"} -{"id": 2792, "token": "\u0120points", "merges": "\u0120point s", "raw_count": 519966, "count": 519966, "decode_str": " points"} -{"id": 51981, "token": "\u00e6\u012f\u00ba", "merges": "\u00e6\u012f \u00ba", "raw_count": 520228, "count": 520228, "decode_str": "\u637a"} -{"id": 19196, "token": "196", "merges": "19 6", "raw_count": 520265, "count": 520265, "decode_str": "196"} -{"id": 8718, "token": "\u0120ok", "merges": "\u0120o k", "raw_count": 520330, "count": 520330, "decode_str": " ok"} -{"id": 12403, "token": "Dav", "merges": "D av", "raw_count": 42031, "count": 520383, "decode_str": "Dav"} -{"id": 1674, "token": "\u00d1\u0123", "merges": "\u00d1 \u0123", "raw_count": 47841, "count": 520601, "decode_str": "\u0441"} -{"id": 3630, "token": "\u0120write", "merges": "\u0120wr ite", "raw_count": 520608, "count": 520608, "decode_str": " write"} -{"id": 7076, "token": "mand", "merges": "m and", "raw_count": 103640, "count": 520613, "decode_str": "mand"} -{"id": 25929, "token": "1968", "merges": "19 68", "raw_count": 520705, "count": 520705, "decode_str": "1968"} -{"id": 9832, "token": "Tem", "merges": "T em", "raw_count": 213986, "count": 520802, "decode_str": "Tem"} -{"id": 6811, "token": "ti", "merges": "t i", "raw_count": 486439, "count": 520877, "decode_str": "ti"} -{"id": 9275, "token": "pdf", "merges": "p df", "raw_count": 520922, "count": 520922, "decode_str": "pdf"} -{"id": 21197, "token": "213", "merges": "2 13", "raw_count": 521092, "count": 521092, "decode_str": "213"} -{"id": 4035, "token": "\u0120continue", "merges": "\u0120contin ue", "raw_count": 521232, "count": 521232, "decode_str": " continue"} -{"id": 27363, "token": "Python", "merges": "Py thon", "raw_count": 521246, "count": 521246, "decode_str": "Python"} -{"id": 3056, "token": "oms", "merges": "om s", "raw_count": 272981, "count": 521266, "decode_str": "oms"} -{"id": 9750, "token": "fin", "merges": "f in", "raw_count": 265082, "count": 521356, "decode_str": "fin"} -{"id": 4827, "token": "TER", "merges": "T ER", "raw_count": 258586, "count": 521383, "decode_str": "TER"} -{"id": 7193, "token": "ailed", "merges": "ail ed", "raw_count": 46489, "count": 521516, "decode_str": "ailed"} -{"id": 53288, "token": "\u00e7\u00b3\u0142", "merges": "\u00e7\u00b3 \u0142", "raw_count": 521529, "count": 521529, "decode_str": "\u7ce0"} -{"id": 7549, "token": "rency", "merges": "ren cy", "raw_count": 138233, "count": 521695, "decode_str": "rency"} -{"id": 50908, "token": "\u00e5\u0130\u013f", "merges": "\u00e5\u0130 \u013f", "raw_count": 521704, "count": 521704, "decode_str": "\u539d"} -{"id": 5417, "token": "\u0120ID", "merges": "\u0120I D", "raw_count": 471926, "count": 521906, "decode_str": " ID"} -{"id": 18202, "token": "207", "merges": "20 7", "raw_count": 522013, "count": 522013, "decode_str": "207"} -{"id": 18467, "token": "164", "merges": "16 4", "raw_count": 522076, "count": 522076, "decode_str": "164"} -{"id": 4461, "token": "room", "merges": "ro om", "raw_count": 401701, "count": 522090, "decode_str": "room"} -{"id": 1612, "token": "\u0120power", "merges": "\u0120p ower", "raw_count": 471554, "count": 522151, "decode_str": " power"} -{"id": 38678, "token": "950", "merges": "9 50", "raw_count": 522188, "count": 522188, "decode_str": "950"} -{"id": 1365, "token": "ially", "merges": "ial ly", "raw_count": 40004, "count": 522214, "decode_str": "ially"} -{"id": 32581, "token": "optim", "merges": "opt im", "raw_count": 522478, "count": 522478, "decode_str": "optim"} -{"id": 5568, "token": "ban", "merges": "b an", "raw_count": 401219, "count": 522587, "decode_str": "ban"} -{"id": 2492, "token": "iation", "merges": "i ation", "raw_count": 162731, "count": 523005, "decode_str": "iation"} -{"id": 2092, "token": "iment", "merges": "im ent", "raw_count": 256109, "count": 523014, "decode_str": "iment"} -{"id": 5806, "token": "\u0120filter", "merges": "\u0120fil ter", "raw_count": 490835, "count": 523075, "decode_str": " filter"} -{"id": 6328, "token": "YS", "merges": "Y S", "raw_count": 461036, "count": 523110, "decode_str": "YS"} -{"id": 1995, "token": "ajor", "merges": "aj or", "raw_count": 6830, "count": 523139, "decode_str": "ajor"} -{"id": 4562, "token": "\u012031", "merges": "\u01203 1", "raw_count": 523263, "count": 523263, "decode_str": " 31"} -{"id": 18969, "token": "icode", "merges": "ic ode", "raw_count": 69010, "count": 523589, "decode_str": "icode"} -{"id": 1978, "token": "\u0120keep", "merges": "\u0120ke ep", "raw_count": 434318, "count": 524139, "decode_str": " keep"} -{"id": 18982, "token": "schema", "merges": "sche ma", "raw_count": 524244, "count": 524244, "decode_str": "schema"} -{"id": 43885, "token": "stdout", "merges": "std out", "raw_count": 524285, "count": 524285, "decode_str": "stdout"} -{"id": 27976, "token": ":%", "merges": ": %", "raw_count": 524307, "count": 524307, "decode_str": ":%"} -{"id": 7872, "token": "option", "merges": "opt ion", "raw_count": 524342, "count": 524342, "decode_str": "option"} -{"id": 51615, "token": "\u00e5\u00bc\u00bc", "merges": "\u00e5\u00bc \u00bc", "raw_count": 524482, "count": 524482, "decode_str": "\u5f3c"} -{"id": 16368, "token": "zip", "merges": "z ip", "raw_count": 524604, "count": 524604, "decode_str": "zip"} -{"id": 50588, "token": "\u00e4\u00be\u00ac", "merges": "\u00e4\u00be \u00ac", "raw_count": 524638, "count": 524638, "decode_str": "\u4fac"} -{"id": 36122, "token": "1959", "merges": "19 59", "raw_count": 524647, "count": 524647, "decode_str": "1959"} -{"id": 35669, "token": "MW", "merges": "M W", "raw_count": 524826, "count": 524826, "decode_str": "MW"} -{"id": 26758, "token": "directory", "merges": "d irectory", "raw_count": 524937, "count": 524937, "decode_str": "directory"} -{"id": 1495, "token": "\u0120life", "merges": "\u0120l ife", "raw_count": 525224, "count": 525224, "decode_str": " life"} -{"id": 5523, "token": "005", "merges": "00 5", "raw_count": 525302, "count": 525302, "decode_str": "005"} -{"id": 53318, "token": "\u00e7\u00ba\u0143", "merges": "\u00e7\u00ba \u0143", "raw_count": 525557, "count": 525557, "decode_str": "\u7ead"} -{"id": 4898, "token": "\u0120height", "merges": "\u0120he ight", "raw_count": 520370, "count": 526022, "decode_str": " height"} -{"id": 2664, "token": "\u010a\u0109\u0109\u0109\u0109", "merges": "\u010a\u0109\u0109 \u0109\u0109", "raw_count": 317448, "count": 526038, "decode_str": "\n\t\t\t\t"} -{"id": 22700, "token": "1973", "merges": "19 73", "raw_count": 526583, "count": 526583, "decode_str": "1973"} -{"id": 831, "token": "\u0120This", "merges": "\u0120Th is", "raw_count": 526633, "count": 526633, "decode_str": " This"} -{"id": 14831, "token": "xs", "merges": "x s", "raw_count": 526851, "count": 526851, "decode_str": "xs"} -{"id": 30488, "token": "1963", "merges": "19 63", "raw_count": 526900, "count": 526900, "decode_str": "1963"} -{"id": 50940, "token": "\u00e5\u0131\u00b1", "merges": "\u00e5\u0131 \u00b1", "raw_count": 527014, "count": 527014, "decode_str": "\u53f1"} -{"id": 53742, "token": "\u00e8\u00a3\u00b1", "merges": "\u00e8\u00a3 \u00b1", "raw_count": 527058, "count": 527058, "decode_str": "\u88f1"} -{"id": 52336, "token": "\u00e6\u00a5\u0136", "merges": "\u00e6\u00a5 \u0136", "raw_count": 527381, "count": 527381, "decode_str": "\u6954"} -{"id": 53724, "token": "\u00e8\u00a2\u0134", "merges": "\u00e8\u00a2 \u0134", "raw_count": 527444, "count": 527444, "decode_str": "\u8892"} -{"id": 1720, "token": "\u0120Re", "merges": "\u0120R e", "raw_count": 163094, "count": 527530, "decode_str": " Re"} -{"id": 10516, "token": "Link", "merges": "L ink", "raw_count": 411362, "count": 527818, "decode_str": "Link"} -{"id": 53410, "token": "\u00e7\u00bd\u0126", "merges": "\u00e7\u00bd \u0126", "raw_count": 527986, "count": 527986, "decode_str": "\u7f44"} -{"id": 6116, "token": "Rec", "merges": "R ec", "raw_count": 268522, "count": 528105, "decode_str": "Rec"} -{"id": 23896, "token": "timeout", "merges": "time out", "raw_count": 528273, "count": 528273, "decode_str": "timeout"} -{"id": 6573, "token": "Color", "merges": "Col or", "raw_count": 528643, "count": 528643, "decode_str": "Color"} -{"id": 3592, "token": "ett", "merges": "et t", "raw_count": 206440, "count": 528664, "decode_str": "ett"} -{"id": 28403, "token": "1965", "merges": "19 65", "raw_count": 528700, "count": 528700, "decode_str": "1965"} -{"id": 1516, "token": "\u0120elect", "merges": "\u0120e lect", "raw_count": 31042, "count": 528850, "decode_str": " elect"} -{"id": 5757, "token": "ART", "merges": "AR T", "raw_count": 245022, "count": 528915, "decode_str": "ART"} -{"id": 4056, "token": "\u0120streng", "merges": "\u0120st reng", "raw_count": 5264, "count": 529073, "decode_str": " streng"} -{"id": 9249, "token": "ourse", "merges": "our se", "raw_count": 28010, "count": 529171, "decode_str": "ourse"} -{"id": 5693, "token": "\u012048", "merges": "\u01204 8", "raw_count": 529318, "count": 529318, "decode_str": " 48"} -{"id": 3389, "token": "\u0120document", "merges": "\u0120d ocument", "raw_count": 387082, "count": 529517, "decode_str": " document"} -{"id": 1795, "token": "\u0120bro", "merges": "\u0120b ro", "raw_count": 38067, "count": 529708, "decode_str": " bro"} -{"id": 8250, "token": "clear", "merges": "cle ar", "raw_count": 517146, "count": 529712, "decode_str": "clear"} -{"id": 5079, "token": "\u0120civil", "merges": "\u0120c ivil", "raw_count": 349618, "count": 530139, "decode_str": " civil"} -{"id": 51897, "token": "\u00e6\u012d\u012a", "merges": "\u00e6\u012d \u012a", "raw_count": 530273, "count": 530273, "decode_str": "\u62c8"} -{"id": 18962, "token": "141", "merges": "14 1", "raw_count": 530762, "count": 530762, "decode_str": "141"} -{"id": 3062, "token": "more", "merges": "m ore", "raw_count": 490005, "count": 530832, "decode_str": "more"} -{"id": 2942, "token": "chie", "merges": "ch ie", "raw_count": 26886, "count": 530855, "decode_str": "chie"} -{"id": 52109, "token": "\u00e6\u0139\u012e", "merges": "\u00e6\u0139 \u012e", "raw_count": 530928, "count": 530928, "decode_str": "\u65cc"} -{"id": 14942, "token": "AX", "merges": "A X", "raw_count": 530937, "count": 530937, "decode_str": "AX"} -{"id": 4601, "token": "encies", "merges": "enc ies", "raw_count": 74216, "count": 530970, "decode_str": "encies"} -{"id": 2165, "token": "\u0120game", "merges": "\u0120g ame", "raw_count": 527674, "count": 531309, "decode_str": " game"} -{"id": 53246, "token": "\u00e7\u00ae\u00ab", "merges": "\u00e7\u00ae \u00ab", "raw_count": 531480, "count": 531480, "decode_str": "\u7bab"} -{"id": 1778, "token": "\u0120indic", "merges": "\u0120ind ic", "raw_count": 14638, "count": 531642, "decode_str": " indic"} -{"id": 22062, "token": "1974", "merges": "19 74", "raw_count": 531843, "count": 531843, "decode_str": "1974"} -{"id": 54082, "token": "\u00e8\u00bf\u00a2", "merges": "\u00e8\u00bf \u00a2", "raw_count": 531911, "count": 531911, "decode_str": "\u8fe2"} -{"id": 2688, "token": "artment", "merges": "art ment", "raw_count": 57987, "count": 531975, "decode_str": "artment"} -{"id": 53113, "token": "\u00e7\u00a5\u0130", "merges": "\u00e7\u00a5 \u0130", "raw_count": 532057, "count": 532057, "decode_str": "\u794e"} -{"id": 12977, "token": "]-", "merges": "] -", "raw_count": 532338, "count": 532339, "decode_str": "]-"} -{"id": 19511, "token": "reset", "merges": "res et", "raw_count": 532494, "count": 532494, "decode_str": "reset"} -{"id": 11667, "token": "example", "merges": "ex ample", "raw_count": 532632, "count": 532632, "decode_str": "example"} -{"id": 12295, "token": "GP", "merges": "G P", "raw_count": 435266, "count": 532769, "decode_str": "GP"} -{"id": 4749, "token": "Sim", "merges": "S im", "raw_count": 278084, "count": 533034, "decode_str": "Sim"} -{"id": 54253, "token": "\u00e9\u0137\u012e", "merges": "\u00e9\u0137 \u012e", "raw_count": 533162, "count": 533162, "decode_str": "\u954c"} -{"id": 2049, "token": "\u0120comb", "merges": "\u0120com b", "raw_count": 92392, "count": 533297, "decode_str": " comb"} -{"id": 47432, "token": "\u0120):", "merges": "\u0120 ):", "raw_count": 533386, "count": 533386, "decode_str": " ):"} -{"id": 2658, "token": "ixed", "merges": "ix ed", "raw_count": 41113, "count": 533756, "decode_str": "ixed"} -{"id": 24185, "token": "666", "merges": "66 6", "raw_count": 533849, "count": 533849, "decode_str": "666"} -{"id": 3353, "token": "\\\\", "merges": "\\ \\", "raw_count": 434657, "count": 533902, "decode_str": "\\\\"} -{"id": 2720, "token": "\u0120prior", "merges": "\u0120pri or", "raw_count": 184242, "count": 533955, "decode_str": " prior"} -{"id": 23760, "token": "HTTP", "merges": "H TTP", "raw_count": 533955, "count": 533955, "decode_str": "HTTP"} -{"id": 3232, "token": "\u0120administ", "merges": "\u0120ad minist", "raw_count": 1415, "count": 534131, "decode_str": " administ"} -{"id": 2244, "token": "urs", "merges": "ur s", "raw_count": 149656, "count": 534231, "decode_str": "urs"} -{"id": 2643, "token": "\u0120corre", "merges": "\u0120cor re", "raw_count": 6436, "count": 534369, "decode_str": " corre"} -{"id": 27071, "token": "\u0120idx", "merges": "\u0120id x", "raw_count": 534466, "count": 534466, "decode_str": " idx"} -{"id": 3672, "token": "\u0120areas", "merges": "\u0120are as", "raw_count": 534542, "count": 534542, "decode_str": " areas"} -{"id": 46295, "token": "]):", "merges": "] ):", "raw_count": 534627, "count": 534627, "decode_str": "]):"} -{"id": 17101, "token": "flag", "merges": "fl ag", "raw_count": 534914, "count": 534914, "decode_str": "flag"} -{"id": 9169, "token": "\u01202020", "merges": "\u012020 20", "raw_count": 535054, "count": 535054, "decode_str": " 2020"} -{"id": 42046, "token": "580", "merges": "5 80", "raw_count": 535114, "count": 535114, "decode_str": "580"} -{"id": 35364, "token": "1957", "merges": "19 57", "raw_count": 535257, "count": 535257, "decode_str": "1957"} -{"id": 5857, "token": "\u0120entry", "merges": "\u0120ent ry", "raw_count": 535351, "count": 535351, "decode_str": " entry"} -{"id": 2730, "token": "><", "merges": "> <", "raw_count": 531697, "count": 535519, "decode_str": "><"} -{"id": 51038, "token": "\u00e5\u0134\u00a9", "merges": "\u00e5\u0134 \u00a9", "raw_count": 535593, "count": 535593, "decode_str": "\u54a9"} -{"id": 3234, "token": "________", "merges": "____ ____", "raw_count": 276287, "count": 535628, "decode_str": "________"} -{"id": 1503, "token": "\u0120Z", "merges": "\u0120 Z", "raw_count": 436898, "count": 535629, "decode_str": " Z"} -{"id": 2919, "token": "\u0120region", "merges": "\u0120reg ion", "raw_count": 536175, "count": 536175, "decode_str": " region"} -{"id": 9962, "token": "----------", "merges": "-------- --", "raw_count": 508763, "count": 536432, "decode_str": "----------"} -{"id": 2136, "token": "\u0120business", "merges": "\u0120bus iness", "raw_count": 482360, "count": 536475, "decode_str": " business"} -{"id": 10206, "token": "CG", "merges": "C G", "raw_count": 534176, "count": 536482, "decode_str": "CG"} -{"id": 2551, "token": "span", "merges": "sp an", "raw_count": 532092, "count": 536761, "decode_str": "span"} -{"id": 11423, "token": "annot", "merges": "ann ot", "raw_count": 92966, "count": 536792, "decode_str": "annot"} -{"id": 10895, "token": "\u0120dataset", "merges": "\u0120datas et", "raw_count": 536959, "count": 536959, "decode_str": " dataset"} -{"id": 52496, "token": "\u00e6\u00b2\u0127", "merges": "\u00e6\u00b2 \u0127", "raw_count": 537060, "count": 537060, "decode_str": "\u6c85"} -{"id": 9834, "token": "addr", "merges": "add r", "raw_count": 537210, "count": 537210, "decode_str": "addr"} -{"id": 1176, "token": "\u0120Com", "merges": "\u0120C om", "raw_count": 67173, "count": 537273, "decode_str": " Com"} -{"id": 53880, "token": "\u00e8\u00b0\u00a5", "merges": "\u00e8\u00b0 \u00a5", "raw_count": 537448, "count": 537448, "decode_str": "\u8c25"} -{"id": 2445, "token": "clude", "merges": "clud e", "raw_count": 13668, "count": 537680, "decode_str": "clude"} -{"id": 35556, "token": "560", "merges": "5 60", "raw_count": 537841, "count": 537841, "decode_str": "560"} -{"id": 5283, "token": "\u0120adopt", "merges": "\u0120ad opt", "raw_count": 84086, "count": 538138, "decode_str": " adopt"} -{"id": 3165, "token": "atal", "merges": "at al", "raw_count": 187084, "count": 538216, "decode_str": "atal"} -{"id": 19044, "token": "302", "merges": "30 2", "raw_count": 538355, "count": 538355, "decode_str": "302"} -{"id": 52856, "token": "\u00e7\u0132\u00b0", "merges": "\u00e7\u0132 \u00b0", "raw_count": 538375, "count": 538375, "decode_str": "\u7430"} -{"id": 52683, "token": "\u00e6\u00ba\u00a5", "merges": "\u00e6\u00ba \u00a5", "raw_count": 538416, "count": 538416, "decode_str": "\u6ea5"} -{"id": 43474, "token": "911", "merges": "9 11", "raw_count": 538560, "count": 538560, "decode_str": "911"} -{"id": 9033, "token": "ATA", "merges": "AT A", "raw_count": 255141, "count": 538623, "decode_str": "ATA"} -{"id": 44902, "token": "outputs", "merges": "output s", "raw_count": 538669, "count": 538669, "decode_str": "outputs"} -{"id": 35704, "token": "payload", "merges": "pay load", "raw_count": 538779, "count": 538779, "decode_str": "payload"} -{"id": 1925, "token": "\u0120called", "merges": "\u0120call ed", "raw_count": 538782, "count": 538782, "decode_str": " called"} -{"id": 51066, "token": "\u00e5\u0135\u0136", "merges": "\u00e5\u0135 \u0136", "raw_count": 539049, "count": 539049, "decode_str": "\u54d4"} -{"id": 21317, "token": "265", "merges": "26 5", "raw_count": 539202, "count": 539202, "decode_str": "265"} -{"id": 17984, "token": "264", "merges": "2 64", "raw_count": 539202, "count": 539202, "decode_str": "264"} -{"id": 6188, "token": "oom", "merges": "o om", "raw_count": 132936, "count": 539703, "decode_str": "oom"} -{"id": 11097, "token": "fix", "merges": "f ix", "raw_count": 223289, "count": 539724, "decode_str": "fix"} -{"id": 3396, "token": "itude", "merges": "it ude", "raw_count": 343169, "count": 539770, "decode_str": "itude"} -{"id": 7775, "token": "\u0120\u00ec", "merges": "\u0120 \u00ec", "raw_count": 349118, "count": 539906, "decode_str": " \ufffd"} -{"id": 3348, "token": "ae", "merges": "a e", "raw_count": 449275, "count": 540090, "decode_str": "ae"} -{"id": 12455, "token": "Sw", "merges": "S w", "raw_count": 253354, "count": 540606, "decode_str": "Sw"} -{"id": 45528, "token": "!\u00e2\u0122\u013b", "merges": "! \u00e2\u0122\u013b", "raw_count": 540674, "count": 540674, "decode_str": "!\u2019"} -{"id": 35031, "token": "Internet", "merges": "Intern et", "raw_count": 540784, "count": 540784, "decode_str": "Internet"} -{"id": 18146, "token": "167", "merges": "16 7", "raw_count": 540875, "count": 540875, "decode_str": "167"} -{"id": 1984, "token": "\u0120book", "merges": "\u0120b ook", "raw_count": 370475, "count": 540936, "decode_str": " book"} -{"id": 22836, "token": "errors", "merges": "err ors", "raw_count": 541255, "count": 541255, "decode_str": "errors"} -{"id": 5057, "token": "\u0120Get", "merges": "\u0120G et", "raw_count": 530009, "count": 541267, "decode_str": " Get"} -{"id": 5711, "token": "vo", "merges": "v o", "raw_count": 296147, "count": 541372, "decode_str": "vo"} -{"id": 8358, "token": "wer", "merges": "w er", "raw_count": 61539, "count": 541593, "decode_str": "wer"} -{"id": 51811, "token": "\u00e6\u012a\u012f", "merges": "\u00e6\u012a \u012f", "raw_count": 541598, "count": 541598, "decode_str": "\u620d"} -{"id": 54464, "token": "\u00e9\u00a3\u0134", "merges": "\u00e9\u00a3 \u0134", "raw_count": 541663, "count": 541663, "decode_str": "\u98d2"} -{"id": 51907, "token": "\u00e6\u012d\u0139", "merges": "\u00e6\u012d \u0139", "raw_count": 541696, "count": 541696, "decode_str": "\u62d7"} -{"id": 11147, "token": "ONE", "merges": "ON E", "raw_count": 484845, "count": 541757, "decode_str": "ONE"} -{"id": 6438, "token": "after", "merges": "a fter", "raw_count": 525600, "count": 541808, "decode_str": "after"} -{"id": 8906, "token": "util", "merges": "ut il", "raw_count": 541841, "count": 541841, "decode_str": "util"} -{"id": 1224, "token": "ought", "merges": "oug ht", "raw_count": 58288, "count": 541889, "decode_str": "ought"} -{"id": 1493, "token": "ysis", "merges": "ys is", "raw_count": 7912, "count": 541954, "decode_str": "ysis"} -{"id": 12062, "token": "\u0120),", "merges": "\u0120 ),", "raw_count": 541978, "count": 541978, "decode_str": " ),"} -{"id": 45750, "token": "1937", "merges": "19 37", "raw_count": 542030, "count": 542030, "decode_str": "1937"} -{"id": 8880, "token": "Button", "merges": "But ton", "raw_count": 542136, "count": 542136, "decode_str": "Button"} -{"id": 2297, "token": "\u0120neg", "merges": "\u0120ne g", "raw_count": 88150, "count": 542424, "decode_str": " neg"} -{"id": 2261, "token": "ounds", "merges": "ound s", "raw_count": 62451, "count": 542588, "decode_str": "ounds"} -{"id": 5353, "token": "aud", "merges": "a ud", "raw_count": 230835, "count": 542627, "decode_str": "aud"} -{"id": 40648, "token": "\"-", "merges": "\" -", "raw_count": 542645, "count": 542645, "decode_str": "\"-"} -{"id": 5403, "token": "\u01202006", "merges": "\u0120200 6", "raw_count": 542857, "count": 542857, "decode_str": " 2006"} -{"id": 52971, "token": "\u00e7\u013c\u0130", "merges": "\u00e7\u013c \u0130", "raw_count": 542867, "count": 542867, "decode_str": "\u768e"} -{"id": 53719, "token": "\u00e8\u00a2\u0126", "merges": "\u00e8\u00a2 \u0126", "raw_count": 543251, "count": 543251, "decode_str": "\u8884"} -{"id": 53020, "token": "\u00e7\u013f\u0129", "merges": "\u00e7\u013f \u0129", "raw_count": 543332, "count": 543332, "decode_str": "\u7747"} -{"id": 52274, "token": "\u00e6\u0142\u0122", "merges": "\u00e6\u0142 \u0122", "raw_count": 543692, "count": 543692, "decode_str": "\u6800"} -{"id": 21092, "token": "183", "merges": "18 3", "raw_count": 543921, "count": 543921, "decode_str": "183"} -{"id": 41356, "token": "768", "merges": "7 68", "raw_count": 543945, "count": 543945, "decode_str": "768"} -{"id": 4527, "token": "Of", "merges": "O f", "raw_count": 531379, "count": 544055, "decode_str": "Of"} -{"id": 53695, "token": "\u00e8\u013e\u0135", "merges": "\u00e8 \u013e\u0135", "raw_count": 544091, "count": 544091, "decode_str": "\u8713"} -{"id": 1794, "token": "\u0120bi", "merges": "\u0120b i", "raw_count": 195009, "count": 544708, "decode_str": " bi"} -{"id": 12896, "token": "groups", "merges": "gr oups", "raw_count": 541931, "count": 544751, "decode_str": "groups"} -{"id": 4192, "token": "\u0120capac", "merges": "\u0120cap ac", "raw_count": 3177, "count": 544926, "decode_str": " capac"} -{"id": 20087, "token": "1977", "merges": "19 77", "raw_count": 545045, "count": 545045, "decode_str": "1977"} -{"id": 8975, "token": "Client", "merges": "Cl ient", "raw_count": 545048, "count": 545048, "decode_str": "Client"} -{"id": 54234, "token": "\u00e9\u0136\u00a2", "merges": "\u00e9\u0136 \u00a2", "raw_count": 545533, "count": 545533, "decode_str": "\u9522"} -{"id": 15597, "token": "HTML", "merges": "HT ML", "raw_count": 541742, "count": 545985, "decode_str": "HTML"} -{"id": 765, "token": "\u00e3\u0123", "merges": "\u00e3 \u0123", "raw_count": 6727, "count": 546096, "decode_str": "\ufffd"} -{"id": 8998, "token": "BE", "merges": "B E", "raw_count": 528020, "count": 546275, "decode_str": "BE"} -{"id": 52694, "token": "\u00e6\u00bc\u012b", "merges": "\u00e6\u00bc \u012b", "raw_count": 546359, "count": 546359, "decode_str": "\u6f09"} -{"id": 51719, "token": "\u00e6\u0123\u00a3", "merges": "\u00e6\u0123 \u00a3", "raw_count": 546586, "count": 546586, "decode_str": "\u6063"} -{"id": 3374, "token": "\u0120issues", "merges": "\u0120iss ues", "raw_count": 546609, "count": 546609, "decode_str": " issues"} -{"id": 34918, "token": "\u013e\u0135", "merges": "\u013e \u0135", "raw_count": 2308, "count": 546876, "decode_str": "\ufffd\ufffd"} -{"id": 37972, "token": "499", "merges": "4 99", "raw_count": 547239, "count": 547239, "decode_str": "499"} -{"id": 11174, "token": "dig", "merges": "d ig", "raw_count": 196964, "count": 547314, "decode_str": "dig"} -{"id": 53362, "token": "\u00e7\u00bb\u00ab", "merges": "\u00e7\u00bb \u00ab", "raw_count": 547485, "count": 547485, "decode_str": "\u7eeb"} -{"id": 20084, "token": "333", "merges": "33 3", "raw_count": 547646, "count": 547646, "decode_str": "333"} -{"id": 12788, "token": "agent", "merges": "ag ent", "raw_count": 546131, "count": 547754, "decode_str": "agent"} -{"id": 2554, "token": "\u0120role", "merges": "\u0120ro le", "raw_count": 548006, "count": 548006, "decode_str": " role"} -{"id": 16296, "token": "\"?", "merges": "\" ?", "raw_count": 542726, "count": 548042, "decode_str": "\"?"} -{"id": 52972, "token": "\u00e7\u013c\u0133", "merges": "\u00e7\u013c \u0133", "raw_count": 548196, "count": 548196, "decode_str": "\u7691"} -{"id": 4315, "token": "\u0120matrix", "merges": "\u0120mat rix", "raw_count": 548406, "count": 548406, "decode_str": " matrix"} -{"id": 19042, "token": "305", "merges": "30 5", "raw_count": 548869, "count": 548869, "decode_str": "305"} -{"id": 8388, "token": "\u0120fer", "merges": "\u0120f er", "raw_count": 156545, "count": 549505, "decode_str": " fer"} -{"id": 3105, "token": "\u0120Not", "merges": "\u0120N ot", "raw_count": 522968, "count": 549607, "decode_str": " Not"} -{"id": 10628, "token": "umps", "merges": "um ps", "raw_count": 528099, "count": 549622, "decode_str": "umps"} -{"id": 28001, "token": "990", "merges": "99 0", "raw_count": 549918, "count": 549918, "decode_str": "990"} -{"id": 5826, "token": "\u01202005", "merges": "\u0120200 5", "raw_count": 550019, "count": 550019, "decode_str": " 2005"} -{"id": 52061, "token": "\u00e6\u0136\u00a5", "merges": "\u00e6\u0136 \u00a5", "raw_count": 550541, "count": 550541, "decode_str": "\u6525"} -{"id": 1472, "token": "'re", "merges": "' re", "raw_count": 551034, "count": 551034, "decode_str": "'re"} -{"id": 43144, "token": "()[", "merges": "() [", "raw_count": 551102, "count": 551102, "decode_str": "()["} -{"id": 2441, "token": "ection", "merges": "e ction", "raw_count": 39170, "count": 551185, "decode_str": "ection"} -{"id": 1355, "token": "\u0120small", "merges": "\u0120sm all", "raw_count": 434069, "count": 551450, "decode_str": " small"} -{"id": 52869, "token": "\u00e7\u0136\u00a5", "merges": "\u00e7\u0136 \u00a5", "raw_count": 551602, "count": 551602, "decode_str": "\u7525"} -{"id": 14396, "token": "screen", "merges": "s creen", "raw_count": 551959, "count": 551959, "decode_str": "screen"} -{"id": 1959, "token": "\u0120free", "merges": "\u0120f ree", "raw_count": 504857, "count": 552724, "decode_str": " free"} -{"id": 17465, "token": "limit", "merges": "lim it", "raw_count": 552750, "count": 552750, "decode_str": "limit"} -{"id": 6555, "token": "eric", "merges": "er ic", "raw_count": 105777, "count": 552810, "decode_str": "eric"} -{"id": 53561, "token": "\u00e8\u0129\u00a7", "merges": "\u00e8\u0129 \u00a7", "raw_count": 552985, "count": 552985, "decode_str": "\u81e7"} -{"id": 1937, "token": "\u0120opp", "merges": "\u0120o pp", "raw_count": 62323, "count": 553091, "decode_str": " opp"} -{"id": 3188, "token": "come", "merges": "c ome", "raw_count": 150408, "count": 553459, "decode_str": "come"} -{"id": 2705, "token": "ruction", "merges": "ru ction", "raw_count": 36904, "count": 554466, "decode_str": "ruction"} -{"id": 52294, "token": "\u00e6\u00a1\u0122", "merges": "\u00e6\u00a1 \u0122", "raw_count": 554508, "count": 554508, "decode_str": "\u6840"} -{"id": 1819, "token": "\u00d0\u00be\u00d0", "merges": "\u00d0\u00be \u00d0", "raw_count": 120, "count": 554511, "decode_str": "\u043e\ufffd"} -{"id": 13884, "token": "mate", "merges": "m ate", "raw_count": 551421, "count": 554911, "decode_str": "mate"} -{"id": 5065, "token": "Comp", "merges": "Com p", "raw_count": 203511, "count": 555061, "decode_str": "Comp"} -{"id": 1871, "token": "'d", "merges": "' d", "raw_count": 555501, "count": 555501, "decode_str": "'d"} -{"id": 8385, "token": "\u0120assistance", "merges": "\u0120ass istance", "raw_count": 555556, "count": 555556, "decode_str": " assistance"} -{"id": 3404, "token": "At", "merges": "A t", "raw_count": 423011, "count": 555561, "decode_str": "At"} -{"id": 47235, "token": "BBC", "merges": "B BC", "raw_count": 555675, "count": 555675, "decode_str": "BBC"} -{"id": 2542, "token": "imate", "merges": "im ate", "raw_count": 173227, "count": 556162, "decode_str": "imate"} -{"id": 31068, "token": "Twitter", "merges": "Tw itter", "raw_count": 556344, "count": 556344, "decode_str": "Twitter"} -{"id": 1014, "token": "\u0120even", "merges": "\u0120ev en", "raw_count": 502187, "count": 556560, "decode_str": " even"} -{"id": 38460, "token": "1955", "merges": "19 55", "raw_count": 556749, "count": 556749, "decode_str": "1955"} -{"id": 370, "token": "\u0120$", "merges": "\u0120 $", "raw_count": 496364, "count": 557113, "decode_str": " $"} -{"id": 6156, "token": "va", "merges": "v a", "raw_count": 556004, "count": 557314, "decode_str": "va"} -{"id": 51059, "token": "\u00e5\u0135\u012e", "merges": "\u00e5\u0135 \u012e", "raw_count": 557364, "count": 557364, "decode_str": "\u54cc"} -{"id": 36950, "token": "\u0120numpy", "merges": "\u0120num py", "raw_count": 557609, "count": 557609, "decode_str": " numpy"} -{"id": 25137, "token": "\u0120'%", "merges": "\u0120' %", "raw_count": 557981, "count": 557981, "decode_str": " '%"} -{"id": 5316, "token": "cher", "merges": "c her", "raw_count": 387484, "count": 558460, "decode_str": "cher"} -{"id": 51716, "token": "\u00e6\u0123\u013b", "merges": "\u00e6\u0123 \u013b", "raw_count": 558563, "count": 558563, "decode_str": "\u6059"} -{"id": 21340, "token": "288", "merges": "28 8", "raw_count": 558683, "count": 558683, "decode_str": "288"} -{"id": 3022, "token": "like", "merges": "li ke", "raw_count": 534780, "count": 558946, "decode_str": "like"} -{"id": 1115, "token": "\u0120anal", "merges": "\u0120an al", "raw_count": 6501, "count": 558990, "decode_str": " anal"} -{"id": 17161, "token": "154", "merges": "15 4", "raw_count": 559027, "count": 559027, "decode_str": "154"} -{"id": 15164, "token": "rg", "merges": "r g", "raw_count": 163493, "count": 559183, "decode_str": "rg"} -{"id": 1815, "token": "mun", "merges": "m un", "raw_count": 54994, "count": 559474, "decode_str": "mun"} -{"id": 2507, "token": "\u0120exc", "merges": "\u0120ex c", "raw_count": 362214, "count": 559581, "decode_str": " exc"} -{"id": 2042, "token": "If", "merges": "I f", "raw_count": 559924, "count": 559924, "decode_str": "If"} -{"id": 4093, "token": "sing", "merges": "s ing", "raw_count": 107478, "count": 560266, "decode_str": "sing"} -{"id": 20045, "token": "\u0120sorted", "merges": "\u0120sort ed", "raw_count": 560930, "count": 560930, "decode_str": " sorted"} -{"id": 53040, "token": "\u00e7\u0141\u013e", "merges": "\u00e7\u0141 \u013e", "raw_count": 561117, "count": 561117, "decode_str": "\u77dc"} -{"id": 1353, "token": "'m", "merges": "' m", "raw_count": 561217, "count": 561217, "decode_str": "'m"} -{"id": 18795, "token": "151", "merges": "15 1", "raw_count": 561618, "count": 561618, "decode_str": "151"} -{"id": 2283, "token": "\u0120pract", "merges": "\u0120p ract", "raw_count": 18823, "count": 561688, "decode_str": " pract"} -{"id": 22558, "token": "exception", "merges": "ex ception", "raw_count": 561758, "count": 561758, "decode_str": "exception"} -{"id": 6669, "token": "TC", "merges": "T C", "raw_count": 498659, "count": 561770, "decode_str": "TC"} -{"id": 19603, "token": "162", "merges": "16 2", "raw_count": 561979, "count": 561979, "decode_str": "162"} -{"id": 2430, "token": "\u0120require", "merges": "\u0120requ ire", "raw_count": 178752, "count": 562043, "decode_str": " require"} -{"id": 4626, "token": "anged", "merges": "ang ed", "raw_count": 31746, "count": 562077, "decode_str": "anged"} -{"id": 17537, "token": "224", "merges": "2 24", "raw_count": 562486, "count": 562486, "decode_str": "224"} -{"id": 5335, "token": "raint", "merges": "ra int", "raw_count": 37947, "count": 562577, "decode_str": "raint"} -{"id": 51040, "token": "\u00e5\u0134\u00ab", "merges": "\u00e5\u0134 \u00ab", "raw_count": 562580, "count": 562580, "decode_str": "\u54ab"} -{"id": 15905, "token": "register", "merges": "reg ister", "raw_count": 562820, "count": 562820, "decode_str": "register"} -{"id": 51082, "token": "\u00e5\u0137\u0126", "merges": "\u00e5\u0137 \u0126", "raw_count": 562882, "count": 562882, "decode_str": "\u5544"} -{"id": 23482, "token": "1972", "merges": "19 72", "raw_count": 562924, "count": 562924, "decode_str": "1972"} -{"id": 8478, "token": "Br", "merges": "B r", "raw_count": 343621, "count": 562932, "decode_str": "Br"} -{"id": 51683, "token": "\u00e5\u00bf\u00bb", "merges": "\u00e5\u00bf \u00bb", "raw_count": 562982, "count": 562982, "decode_str": "\u5ffb"} -{"id": 29639, "token": "1964", "merges": "19 64", "raw_count": 563110, "count": 563110, "decode_str": "1964"} -{"id": 54616, "token": "\u00ef\u00bc\u00bc", "merges": "\u00ef\u00bc \u00bc", "raw_count": 563325, "count": 563325, "decode_str": " "} -{"id": 2486, "token": "\u0120include", "merges": "\u0120includ e", "raw_count": 563341, "count": 563341, "decode_str": " include"} -{"id": 3223, "token": "stant", "merges": "st ant", "raw_count": 64841, "count": 563454, "decode_str": "stant"} -{"id": 5934, "token": "istory", "merges": "ist ory", "raw_count": 5532, "count": 563546, "decode_str": "istory"} -{"id": 9854, "token": "~,", "merges": "~ ,", "raw_count": 563746, "count": 563746, "decode_str": "~,"} -{"id": 9687, "token": "Conne", "merges": "Con ne", "raw_count": 129906, "count": 563956, "decode_str": "Conne"} -{"id": 1242, "token": "ively", "merges": "iv ely", "raw_count": 98598, "count": 563980, "decode_str": "ively"} -{"id": 7912, "token": "Bar", "merges": "B ar", "raw_count": 563807, "count": 564222, "decode_str": "Bar"} -{"id": 12323, "token": "Book", "merges": "B ook", "raw_count": 531470, "count": 564362, "decode_str": "Book"} -{"id": 9536, "token": "NAME", "merges": "NA ME", "raw_count": 564447, "count": 564447, "decode_str": "NAME"} -{"id": 52756, "token": "\u00e7\u0126\u00b1", "merges": "\u00e7\u0126 \u00b1", "raw_count": 564485, "count": 564485, "decode_str": "\u7131"} -{"id": 2749, "token": "\u0120propos", "merges": "\u0120pro pos", "raw_count": 2110, "count": 564507, "decode_str": " propos"} -{"id": 53393, "token": "\u00e7\u00bc\u013e", "merges": "\u00e7\u00bc \u013e", "raw_count": 564691, "count": 564691, "decode_str": "\u7f1c"} -{"id": 3097, "token": "uth", "merges": "ut h", "raw_count": 113998, "count": 564972, "decode_str": "uth"} -{"id": 1573, "token": "ording", "merges": "ord ing", "raw_count": 62506, "count": 565048, "decode_str": "ording"} -{"id": 1634, "token": "ves", "merges": "v es", "raw_count": 172427, "count": 565100, "decode_str": "ves"} -{"id": 13994, "token": "custom", "merges": "c ustom", "raw_count": 387330, "count": 565143, "decode_str": "custom"} -{"id": 7834, "token": "Part", "merges": "P art", "raw_count": 332067, "count": 565555, "decode_str": "Part"} -{"id": 5626, "token": "ALL", "merges": "AL L", "raw_count": 440609, "count": 565613, "decode_str": "ALL"} -{"id": 39134, "token": "1920", "merges": "19 20", "raw_count": 565926, "count": 565926, "decode_str": "1920"} -{"id": 4060, "token": "\u0120title", "merges": "\u0120t itle", "raw_count": 565993, "count": 565993, "decode_str": " title"} -{"id": 20778, "token": "1975", "merges": "19 75", "raw_count": 566102, "count": 566102, "decode_str": "1975"} -{"id": 24869, "token": "\u0120-=", "merges": "\u0120- =", "raw_count": 566296, "count": 566296, "decode_str": " -="} -{"id": 52613, "token": "\u00e6\u00b6\u00a3", "merges": "\u00e6\u00b6 \u00a3", "raw_count": 566469, "count": 566469, "decode_str": "\u6da3"} -{"id": 53072, "token": "\u00e7\u0142\u00be", "merges": "\u00e7\u0142 \u00be", "raw_count": 566504, "count": 566504, "decode_str": "\u783e"} -{"id": 4124, "token": "ports", "merges": "port s", "raw_count": 282383, "count": 566536, "decode_str": "ports"} -{"id": 3993, "token": "atives", "merges": "at ives", "raw_count": 101534, "count": 566852, "decode_str": "atives"} -{"id": 2683, "token": "irm", "merges": "ir m", "raw_count": 57000, "count": 566892, "decode_str": "irm"} -{"id": 2317, "token": "\u0120space", "merges": "\u0120sp ace", "raw_count": 557949, "count": 566961, "decode_str": " space"} -{"id": 22740, "token": "Cloud", "merges": "Cl oud", "raw_count": 567206, "count": 567206, "decode_str": "Cloud"} -{"id": 3602, "token": "\u0120parameters", "merges": "\u0120param eters", "raw_count": 567232, "count": 567232, "decode_str": " parameters"} -{"id": 36268, "token": "uuid", "merges": "u uid", "raw_count": 567321, "count": 567321, "decode_str": "uuid"} -{"id": 50953, "token": "\u00e5\u0132\u0128", "merges": "\u00e5\u0132 \u0128", "raw_count": 567349, "count": 567349, "decode_str": "\u5406"} -{"id": 25836, "token": "serial", "merges": "ser ial", "raw_count": 567546, "count": 567546, "decode_str": "serial"} -{"id": 5785, "token": "Reg", "merges": "R eg", "raw_count": 273156, "count": 567822, "decode_str": "Reg"} -{"id": 48700, "token": "SZ", "merges": "S Z", "raw_count": 568241, "count": 568241, "decode_str": "SZ"} -{"id": 1264, "token": "\u0120three", "merges": "\u0120th ree", "raw_count": 568255, "count": 568255, "decode_str": " three"} -{"id": 2156, "token": "orth", "merges": "or th", "raw_count": 76766, "count": 568381, "decode_str": "orth"} -{"id": 8677, "token": "El", "merges": "E l", "raw_count": 504167, "count": 568508, "decode_str": "El"} -{"id": 3435, "token": "\u012027", "merges": "\u01202 7", "raw_count": 520926, "count": 568722, "decode_str": " 27"} -{"id": 6809, "token": "\u0120tag", "merges": "\u0120t ag", "raw_count": 545462, "count": 568751, "decode_str": " tag"} -{"id": 25887, "token": "xxx", "merges": "xx x", "raw_count": 568871, "count": 568871, "decode_str": "xxx"} -{"id": 4173, "token": "ico", "merges": "ic o", "raw_count": 478053, "count": 568879, "decode_str": "ico"} -{"id": 1520, "token": "ured", "merges": "u red", "raw_count": 170771, "count": 568907, "decode_str": "ured"} -{"id": 13801, "token": "EP", "merges": "E P", "raw_count": 568952, "count": 568952, "decode_str": "EP"} -{"id": 5479, "token": "ESS", "merges": "ES S", "raw_count": 209108, "count": 568967, "decode_str": "ESS"} -{"id": 3377, "token": "ado", "merges": "ad o", "raw_count": 381747, "count": 569335, "decode_str": "ado"} -{"id": 15907, "token": "177", "merges": "17 7", "raw_count": 569360, "count": 569360, "decode_str": "177"} -{"id": 1896, "token": "\u0120possible", "merges": "\u0120poss ible", "raw_count": 569484, "count": 569484, "decode_str": " possible"} -{"id": 33380, "token": "samples", "merges": "s amples", "raw_count": 569494, "count": 569494, "decode_str": "samples"} -{"id": 6842, "token": "reshold", "merges": "resh old", "raw_count": 20361, "count": 569625, "decode_str": "reshold"} -{"id": 22275, "token": "prob", "merges": "pro b", "raw_count": 569635, "count": 569635, "decode_str": "prob"} -{"id": 1380, "token": "\u0120//", "merges": "\u0120 //", "raw_count": 565854, "count": 569720, "decode_str": " //"} -{"id": 4304, "token": "known", "merges": "kn own", "raw_count": 122759, "count": 570110, "decode_str": "known"} -{"id": 14267, "token": "category", "merges": "c ategory", "raw_count": 570447, "count": 570447, "decode_str": "category"} -{"id": 2587, "token": "irl", "merges": "ir l", "raw_count": 78504, "count": 570997, "decode_str": "irl"} -{"id": 19057, "token": "hidden", "merges": "h idden", "raw_count": 571042, "count": 571042, "decode_str": "hidden"} -{"id": 52293, "token": "\u00e6\u0142\u00be", "merges": "\u00e6\u0142 \u00be", "raw_count": 571084, "count": 571084, "decode_str": "\u683e"} -{"id": 53430, "token": "\u00e7\u00be\u0141", "merges": "\u00e7\u00be \u0141", "raw_count": 571477, "count": 571477, "decode_str": "\u7f9f"} -{"id": 3491, "token": "\u0120copy", "merges": "\u0120c opy", "raw_count": 495570, "count": 571840, "decode_str": " copy"} -{"id": 2322, "token": "ibility", "merges": "ib ility", "raw_count": 93153, "count": 572128, "decode_str": "ibility"} -{"id": 7582, "token": "author", "merges": "aut hor", "raw_count": 469266, "count": 572462, "decode_str": "author"} -{"id": 50469, "token": "\u00e4\u00ba\u013a", "merges": "\u00e4\u00ba \u013a", "raw_count": 572468, "count": 572468, "decode_str": "\u4e98"} -{"id": 43971, "token": "indices", "merges": "ind ices", "raw_count": 572517, "count": 572517, "decode_str": "indices"} -{"id": 6052, "token": "Per", "merges": "P er", "raw_count": 382013, "count": 572752, "decode_str": "Per"} -{"id": 5084, "token": "\u0120column", "merges": "\u0120col umn", "raw_count": 572449, "count": 573090, "decode_str": " column"} -{"id": 52515, "token": "\u00e6\u00b2\u00b1", "merges": "\u00e6\u00b2 \u00b1", "raw_count": 573507, "count": 573507, "decode_str": "\u6cb1"} -{"id": 1434, "token": "acter", "merges": "act er", "raw_count": 18653, "count": 573911, "decode_str": "acter"} -{"id": 15332, "token": "PN", "merges": "P N", "raw_count": 567799, "count": 574222, "decode_str": "PN"} -{"id": 4602, "token": "\u0120connection", "merges": "\u0120conne ction", "raw_count": 574331, "count": 574331, "decode_str": " connection"} -{"id": 10579, "token": "UC", "merges": "U C", "raw_count": 545162, "count": 574720, "decode_str": "UC"} -{"id": 6333, "token": "\u0120module", "merges": "\u0120mod ule", "raw_count": 574785, "count": 574785, "decode_str": " module"} -{"id": 7553, "token": "tw", "merges": "t w", "raw_count": 437131, "count": 574809, "decode_str": "tw"} -{"id": 53219, "token": "\u00e7\u00ac\u00ba", "merges": "\u00e7\u00ac \u00ba", "raw_count": 575056, "count": 575056, "decode_str": "\u7b3a"} -{"id": 19934, "token": "apple", "merges": "app le", "raw_count": 575440, "count": 575440, "decode_str": "apple"} -{"id": 19490, "token": "245", "merges": "24 5", "raw_count": 575643, "count": 575643, "decode_str": "245"} -{"id": 2314, "token": "\u0120polit", "merges": "\u0120pol it", "raw_count": 4217, "count": 575735, "decode_str": " polit"} -{"id": 1104, "token": "ients", "merges": "i ents", "raw_count": 218801, "count": 575921, "decode_str": "ients"} -{"id": 20333, "token": "172", "merges": "17 2", "raw_count": 575981, "count": 575981, "decode_str": "172"} -{"id": 29996, "token": "\u0120'.", "merges": "\u0120' .", "raw_count": 576346, "count": 576346, "decode_str": " '."} -{"id": 5361, "token": "ding", "merges": "d ing", "raw_count": 435896, "count": 576360, "decode_str": "ding"} -{"id": 8522, "token": "unit", "merges": "un it", "raw_count": 569599, "count": 576454, "decode_str": "unit"} -{"id": 16223, "token": "report", "merges": "re port", "raw_count": 555638, "count": 576592, "decode_str": "report"} -{"id": 6846, "token": "-------", "merges": "---- ---", "raw_count": 479413, "count": 576722, "decode_str": "-------"} -{"id": 4396, "token": "zz", "merges": "z z", "raw_count": 422054, "count": 576872, "decode_str": "zz"} -{"id": 4750, "token": "\u0120staff", "merges": "\u0120st aff", "raw_count": 576940, "count": 576940, "decode_str": " staff"} -{"id": 3173, "token": "\u0120Im", "merges": "\u0120I m", "raw_count": 62575, "count": 576977, "decode_str": " Im"} -{"id": 52073, "token": "\u00e6\u0137\u0137", "merges": "\u00e6\u0137 \u0137", "raw_count": 577065, "count": 577065, "decode_str": "\u6555"} -{"id": 15900, "token": "Store", "merges": "St ore", "raw_count": 577174, "count": 577174, "decode_str": "Store"} -{"id": 9278, "token": "GET", "merges": "G ET", "raw_count": 527502, "count": 577204, "decode_str": "GET"} -{"id": 3823, "token": "ivil", "merges": "iv il", "raw_count": 4265, "count": 577379, "decode_str": "ivil"} -{"id": 2979, "token": "ences", "merges": "en ces", "raw_count": 250724, "count": 577442, "decode_str": "ences"} -{"id": 6878, "token": "Count", "merges": "C ount", "raw_count": 521138, "count": 577488, "decode_str": "Count"} -{"id": 3170, "token": "yp", "merges": "y p", "raw_count": 288663, "count": 577948, "decode_str": "yp"} -{"id": 1774, "token": "\u0120important", "merges": "\u0120import ant", "raw_count": 565803, "count": 577991, "decode_str": " important"} -{"id": 4873, "token": "RI", "merges": "R I", "raw_count": 332376, "count": 578239, "decode_str": "RI"} -{"id": 2560, "token": "ibr", "merges": "ib r", "raw_count": 74254, "count": 578386, "decode_str": "ibr"} -{"id": 52909, "token": "\u00e7\u0138\u0141", "merges": "\u00e7\u0138 \u0141", "raw_count": 578387, "count": 578387, "decode_str": "\u759f"} -{"id": 50410, "token": "\u00e4\u00b8\u0137", "merges": "\u00e4\u00b8 \u0137", "raw_count": 578427, "count": 578427, "decode_str": "\u4e15"} -{"id": 950, "token": "ourt", "merges": "our t", "raw_count": 16092, "count": 578847, "decode_str": "ourt"} -{"id": 4721, "token": "istry", "merges": "ist ry", "raw_count": 39190, "count": 579057, "decode_str": "istry"} -{"id": 5450, "token": "rome", "merges": "rom e", "raw_count": 438331, "count": 579162, "decode_str": "rome"} -{"id": 6788, "token": "\").", "merges": "\" ).", "raw_count": 579472, "count": 579472, "decode_str": "\")."} -{"id": 8982, "token": "Input", "merges": "In put", "raw_count": 575373, "count": 579510, "decode_str": "Input"} -{"id": 5096, "token": "\u012080", "merges": "\u01208 0", "raw_count": 579800, "count": 579800, "decode_str": " 80"} -{"id": 54183, "token": "\u00e9\u0125\u00b4", "merges": "\u00e9\u0125 \u00b4", "raw_count": 580455, "count": 580455, "decode_str": "\u90f4"} -{"id": 32796, "token": "1962", "merges": "19 62", "raw_count": 580598, "count": 580598, "decode_str": "1962"} -{"id": 8435, "token": "rl", "merges": "r l", "raw_count": 157597, "count": 581089, "decode_str": "rl"} -{"id": 1195, "token": "\u0120tri", "merges": "\u0120t ri", "raw_count": 79144, "count": 581319, "decode_str": " tri"} -{"id": 6601, "token": "Att", "merges": "A tt", "raw_count": 225522, "count": 581968, "decode_str": "Att"} -{"id": 2039, "token": "\u0120offic", "merges": "\u0120off ic", "raw_count": 6794, "count": 582058, "decode_str": " offic"} -{"id": 4674, "token": "section", "merges": "se ction", "raw_count": 522455, "count": 582697, "decode_str": "section"} -{"id": 1697, "token": "\u00d1\u0122", "merges": "\u00d1 \u0122", "raw_count": 104723, "count": 583196, "decode_str": "\u0440"} -{"id": 52921, "token": "\u00e7\u0138\u00b8", "merges": "\u00e7\u0138 \u00b8", "raw_count": 583512, "count": 583512, "decode_str": "\u75b8"} -{"id": 14778, "token": "widget", "merges": "wid get", "raw_count": 496259, "count": 583645, "decode_str": "widget"} -{"id": 5215, "token": "\u01202007", "merges": "\u0120200 7", "raw_count": 583681, "count": 583681, "decode_str": " 2007"} -{"id": 5949, "token": "Event", "merges": "E vent", "raw_count": 572563, "count": 583692, "decode_str": "Event"} -{"id": 1580, "token": "\u0120since", "merges": "\u0120s ince", "raw_count": 559390, "count": 583837, "decode_str": " since"} -{"id": 3048, "token": "\u0120link", "merges": "\u0120l ink", "raw_count": 439504, "count": 584193, "decode_str": " link"} -{"id": 14461, "token": "best", "merges": "b est", "raw_count": 579354, "count": 584225, "decode_str": "best"} -{"id": 53800, "token": "\u00e8\u00ae\u00b9", "merges": "\u00e8\u00ae \u00b9", "raw_count": 584410, "count": 584410, "decode_str": "\u8bb9"} -{"id": 13611, "token": "~)", "merges": "~ )", "raw_count": 584531, "count": 584531, "decode_str": "~)"} -{"id": 53349, "token": "\u00e7\u00bb\u013d", "merges": "\u00e7\u00bb \u013d", "raw_count": 584566, "count": 584566, "decode_str": "\u7edb"} -{"id": 6031, "token": "\u0120efforts", "merges": "\u0120effort s", "raw_count": 585186, "count": 585186, "decode_str": " efforts"} -{"id": 1414, "token": "\u0120expl", "merges": "\u0120ex pl", "raw_count": 8803, "count": 585464, "decode_str": " expl"} -{"id": 11004, "token": "empty", "merges": "empt y", "raw_count": 585444, "count": 585481, "decode_str": "empty"} -{"id": 50485, "token": "\u00e4\u00ba\u00b3", "merges": "\u00e4\u00ba \u00b3", "raw_count": 585549, "count": 585549, "decode_str": "\u4eb3"} -{"id": 15882, "token": "157", "merges": "15 7", "raw_count": 585575, "count": 585575, "decode_str": "157"} -{"id": 7865, "token": "Call", "merges": "C all", "raw_count": 432028, "count": 585618, "decode_str": "Call"} -{"id": 9939, "token": "note", "merges": "not e", "raw_count": 579571, "count": 585731, "decode_str": "note"} -{"id": 21866, "token": "214", "merges": "2 14", "raw_count": 586191, "count": 586191, "decode_str": "214"} -{"id": 2213, "token": "\u0120Res", "merges": "\u0120R es", "raw_count": 116162, "count": 586279, "decode_str": " Res"} -{"id": 10094, "token": "agraph", "merges": "ag raph", "raw_count": 19422, "count": 586438, "decode_str": "agraph"} -{"id": 21151, "token": "173", "merges": "17 3", "raw_count": 586570, "count": 586570, "decode_str": "173"} -{"id": 6934, "token": "osh", "merges": "os h", "raw_count": 194109, "count": 586734, "decode_str": "osh"} -{"id": 5318, "token": "onent", "merges": "on ent", "raw_count": 86124, "count": 586950, "decode_str": "onent"} -{"id": 5550, "token": "\u0120(\"", "merges": "\u0120( \"", "raw_count": 583497, "count": 586997, "decode_str": " (\""} -{"id": 9229, "token": "center", "merges": "cent er", "raw_count": 587096, "count": 587096, "decode_str": "center"} -{"id": 18040, "token": "206", "merges": "20 6", "raw_count": 587150, "count": 587150, "decode_str": "206"} -{"id": 1230, "token": "ually", "merges": "u ally", "raw_count": 51495, "count": 587247, "decode_str": "ually"} -{"id": 9290, "token": "card", "merges": "c ard", "raw_count": 581995, "count": 587294, "decode_str": "card"} -{"id": 13070, "token": "help", "merges": "hel p", "raw_count": 587602, "count": 587602, "decode_str": "help"} -{"id": 9738, "token": "click", "merges": "cl ick", "raw_count": 583762, "count": 588505, "decode_str": "click"} -{"id": 16271, "token": "153", "merges": "15 3", "raw_count": 588667, "count": 588667, "decode_str": "153"} -{"id": 2124, "token": "ergy", "merges": "erg y", "raw_count": 16964, "count": 588713, "decode_str": "ergy"} -{"id": 7483, "token": "only", "merges": "on ly", "raw_count": 541861, "count": 588766, "decode_str": "only"} -{"id": 11618, "token": "vm", "merges": "v m", "raw_count": 575340, "count": 589058, "decode_str": "vm"} -{"id": 2093, "token": "\u0120cho", "merges": "\u0120ch o", "raw_count": 31005, "count": 589322, "decode_str": " cho"} -{"id": 51928, "token": "\u00e6\u012d\u00b4", "merges": "\u00e6\u012d \u00b4", "raw_count": 589412, "count": 589412, "decode_str": "\u62f4"} -{"id": 52581, "token": "\u00e6\u00b5\u0134", "merges": "\u00e6\u00b5 \u0134", "raw_count": 589438, "count": 589438, "decode_str": "\u6d52"} -{"id": 2729, "token": "ached", "merges": "ac hed", "raw_count": 102839, "count": 589967, "decode_str": "ached"} -{"id": 54388, "token": "\u00e9\u013e\u0130", "merges": "\u00e9\u013e \u0130", "raw_count": 590103, "count": 590103, "decode_str": "\u970e"} -{"id": 2373, "token": "iver", "merges": "i ver", "raw_count": 215657, "count": 590303, "decode_str": "iver"} -{"id": 18220, "token": "Win", "merges": "W in", "raw_count": 590906, "count": 590906, "decode_str": "Win"} -{"id": 8059, "token": "\u0120conference", "merges": "\u0120con ference", "raw_count": 591451, "count": 591451, "decode_str": " conference"} -{"id": 4871, "token": "\u0120width", "merges": "\u0120w idth", "raw_count": 580988, "count": 592021, "decode_str": " width"} -{"id": 11317, "token": "uri", "merges": "ur i", "raw_count": 592348, "count": 592348, "decode_str": "uri"} -{"id": 1300, "token": "igned", "merges": "ign ed", "raw_count": 122913, "count": 592600, "decode_str": "igned"} -{"id": 10352, "token": "bas", "merges": "b as", "raw_count": 319298, "count": 592758, "decode_str": "bas"} -{"id": 5386, "token": "\u0120remove", "merges": "\u0120rem ove", "raw_count": 592868, "count": 592868, "decode_str": " remove"} -{"id": 3436, "token": "\u012026", "merges": "\u01202 6", "raw_count": 567778, "count": 592879, "decode_str": " 26"} -{"id": 2007, "token": "\u0120further", "merges": "\u0120f urther", "raw_count": 577783, "count": 593286, "decode_str": " further"} -{"id": 52137, "token": "\u00e6\u013a\u013b", "merges": "\u00e6\u013a \u013b", "raw_count": 593439, "count": 593439, "decode_str": "\u6619"} -{"id": 52414, "token": "\u00e6\u00ae\u0129", "merges": "\u00e6\u00ae \u0129", "raw_count": 593712, "count": 593712, "decode_str": "\u6b87"} -{"id": 1745, "token": "\u0120typ", "merges": "\u0120ty p", "raw_count": 64423, "count": 593740, "decode_str": " typ"} -{"id": 2731, "token": "ires", "merges": "i res", "raw_count": 106547, "count": 593742, "decode_str": "ires"} -{"id": 22530, "token": "stats", "merges": "st ats", "raw_count": 593819, "count": 593819, "decode_str": "stats"} -{"id": 2990, "token": "\u0120network", "merges": "\u0120net work", "raw_count": 569198, "count": 594072, "decode_str": " network"} -{"id": 51308, "token": "\u00e5\u00a5\u0126", "merges": "\u00e5\u00a5 \u0126", "raw_count": 594333, "count": 594333, "decode_str": "\u5944"} -{"id": 3711, "token": "\u0120map", "merges": "\u0120m ap", "raw_count": 591457, "count": 594756, "decode_str": " map"} -{"id": 51754, "token": "\u00e6\u0124\u00b4", "merges": "\u00e6\u0124 \u00b4", "raw_count": 594988, "count": 594988, "decode_str": "\u60b4"} -{"id": 1675, "token": "\u0120respect", "merges": "\u0120res pect", "raw_count": 381476, "count": 594990, "decode_str": " respect"} -{"id": 8692, "token": "\u0120info", "merges": "\u0120inf o", "raw_count": 594996, "count": 594996, "decode_str": " info"} -{"id": 8656, "token": "high", "merges": "h igh", "raw_count": 525094, "count": 595084, "decode_str": "high"} -{"id": 2610, "token": "ino", "merges": "in o", "raw_count": 491727, "count": 595301, "decode_str": "ino"} -{"id": 1576, "token": "ways", "merges": "w ays", "raw_count": 82631, "count": 595518, "decode_str": "ways"} -{"id": 1640, "token": "\u00d0\u00bd", "merges": "\u00d0 \u00bd", "raw_count": 59938, "count": 595678, "decode_str": "\u043d"} -{"id": 51096, "token": "\u00e5\u0137\u00ac", "merges": "\u00e5\u0137 \u00ac", "raw_count": 595731, "count": 595731, "decode_str": "\u556c"} -{"id": 54618, "token": "\u00ef\u00bc\u00be", "merges": "\u00ef\u00bc \u00be", "raw_count": 595852, "count": 595852, "decode_str": " "} -{"id": 9228, "token": "}/", "merges": "} /", "raw_count": 597138, "count": 597138, "decode_str": "}/"} -{"id": 3658, "token": "ements", "merges": "em ents", "raw_count": 47559, "count": 597257, "decode_str": "ements"} -{"id": 14385, "token": "\u0120secretary", "merges": "\u0120secret ary", "raw_count": 597289, "count": 597289, "decode_str": " secretary"} -{"id": 51080, "token": "\u00e5\u0135\u00bd", "merges": "\u00e5\u0135 \u00bd", "raw_count": 597397, "count": 597397, "decode_str": "\u54fd"} -{"id": 3836, "token": "isions", "merges": "is ions", "raw_count": 92106, "count": 597416, "decode_str": "isions"} -{"id": 16607, "token": "146", "merges": "14 6", "raw_count": 597430, "count": 597430, "decode_str": "146"} -{"id": 2158, "token": "ering", "merges": "er ing", "raw_count": 220098, "count": 597504, "decode_str": "ering"} -{"id": 3145, "token": "View", "merges": "V iew", "raw_count": 541525, "count": 597529, "decode_str": "View"} -{"id": 17440, "token": "driver", "merges": "d river", "raw_count": 597541, "count": 597541, "decode_str": "driver"} -{"id": 54265, "token": "\u00e9\u0137\u00b0", "merges": "\u00e9\u0137 \u00b0", "raw_count": 598136, "count": 598136, "decode_str": "\u9570"} -{"id": 2811, "token": "where", "merges": "w here", "raw_count": 488238, "count": 598321, "decode_str": "where"} -{"id": 11023, "token": "buffer", "merges": "b uffer", "raw_count": 598418, "count": 598418, "decode_str": "buffer"} -{"id": 7174, "token": "006", "merges": "00 6", "raw_count": 598765, "count": 598765, "decode_str": "006"} -{"id": 9293, "token": "spe", "merges": "s pe", "raw_count": 153939, "count": 598788, "decode_str": "spe"} -{"id": 9807, "token": "Open", "merges": "O pen", "raw_count": 598809, "count": 598809, "decode_str": "Open"} -{"id": 15987, "token": "users", "merges": "us ers", "raw_count": 598825, "count": 598825, "decode_str": "users"} -{"id": 3241, "token": "ste", "merges": "st e", "raw_count": 428369, "count": 598865, "decode_str": "ste"} -{"id": 6003, "token": "\u0120organization", "merges": "\u0120organ ization", "raw_count": 598878, "count": 598878, "decode_str": " organization"} -{"id": 1988, "token": "ison", "merges": "is on", "raw_count": 230254, "count": 598900, "decode_str": "ison"} -{"id": 5593, "token": "\u0120measures", "merges": "\u0120meas ures", "raw_count": 598961, "count": 598961, "decode_str": " measures"} -{"id": 50635, "token": "\u00e5\u0122\u0143", "merges": "\u00e5\u0122 \u0143", "raw_count": 598974, "count": 598974, "decode_str": "\u502d"} -{"id": 54520, "token": "\u00e9\u00ab\u012d", "merges": "\u00e9\u00ab \u012d", "raw_count": 599453, "count": 599453, "decode_str": "\u9acb"} -{"id": 6443, "token": "core", "merges": "c ore", "raw_count": 598927, "count": 600003, "decode_str": "core"} -{"id": 51018, "token": "\u00e5\u0134\u0126", "merges": "\u00e5\u0134 \u0126", "raw_count": 600334, "count": 600334, "decode_str": "\u5484"} -{"id": 53939, "token": "\u00e8\u00b4\u00bb", "merges": "\u00e8\u00b4 \u00bb", "raw_count": 600413, "count": 600413, "decode_str": "\u8d3b"} -{"id": 2117, "token": "\u0120abs", "merges": "\u0120ab s", "raw_count": 335608, "count": 600554, "decode_str": " abs"} -{"id": 5696, "token": "LA", "merges": "L A", "raw_count": 477063, "count": 600962, "decode_str": "LA"} -{"id": 1936, "token": "\u0120vol", "merges": "\u0120v ol", "raw_count": 78116, "count": 601060, "decode_str": " vol"} -{"id": 54220, "token": "\u00e9\u0136\u0126", "merges": "\u00e9\u0136 \u0126", "raw_count": 601085, "count": 601085, "decode_str": "\u9504"} -{"id": 8947, "token": "ova", "merges": "ov a", "raw_count": 589261, "count": 601354, "decode_str": "ova"} -{"id": 2329, "token": "\u0120air", "merges": "\u0120a ir", "raw_count": 407979, "count": 601414, "decode_str": " air"} -{"id": 7366, "token": "edia", "merges": "ed ia", "raw_count": 174833, "count": 602131, "decode_str": "edia"} -{"id": 3428, "token": "rim", "merges": "r im", "raw_count": 148511, "count": 602349, "decode_str": "rim"} -{"id": 4774, "token": "force", "merges": "for ce", "raw_count": 379092, "count": 602726, "decode_str": "force"} -{"id": 4832, "token": "\u0120financial", "merges": "\u0120financ ial", "raw_count": 603555, "count": 603555, "decode_str": " financial"} -{"id": 1577, "token": "\u0120struct", "merges": "\u0120st ruct", "raw_count": 184036, "count": 603924, "decode_str": " struct"} -{"id": 9511, "token": "home", "merges": "h ome", "raw_count": 604130, "count": 604130, "decode_str": "home"} -{"id": 1659, "token": "\u0120place", "merges": "\u0120pl ace", "raw_count": 568899, "count": 604143, "decode_str": " place"} -{"id": 1037, "token": "ically", "merges": "ical ly", "raw_count": 92912, "count": 604999, "decode_str": "ically"} -{"id": 3106, "token": "inks", "merges": "in ks", "raw_count": 51928, "count": 605199, "decode_str": "inks"} -{"id": 25263, "token": "Plus", "merges": "Pl us", "raw_count": 605227, "count": 605227, "decode_str": "Plus"} -{"id": 32490, "token": "Linux", "merges": "L inux", "raw_count": 605245, "count": 605245, "decode_str": "Linux"} -{"id": 8469, "token": "Gu", "merges": "G u", "raw_count": 455377, "count": 605345, "decode_str": "Gu"} -{"id": 6717, "token": "Ass", "merges": "A ss", "raw_count": 237356, "count": 605621, "decode_str": "Ass"} -{"id": 50956, "token": "\u00e5\u0132\u012d", "merges": "\u00e5\u0132 \u012d", "raw_count": 605661, "count": 605661, "decode_str": "\u540b"} -{"id": 16437, "token": "clean", "merges": "cle an", "raw_count": 511508, "count": 605822, "decode_str": "clean"} -{"id": 9780, "token": "AK", "merges": "A K", "raw_count": 600052, "count": 606136, "decode_str": "AK"} -{"id": 20777, "token": "308", "merges": "30 8", "raw_count": 606220, "count": 606220, "decode_str": "308"} -{"id": 50579, "token": "\u00e4\u00be\u0139", "merges": "\u00e4\u00be \u0139", "raw_count": 606347, "count": 606347, "decode_str": "\u4f97"} -{"id": 53930, "token": "\u00e8\u00b4\u00b0", "merges": "\u00e8\u00b4 \u00b0", "raw_count": 606442, "count": 606442, "decode_str": "\u8d30"} -{"id": 51944, "token": "\u00e6\u012e\u0140", "merges": "\u00e6\u012e \u0140", "raw_count": 606487, "count": 606487, "decode_str": "\u631e"} -{"id": 54487, "token": "\u00e9\u00a6\u00a5", "merges": "\u00e9\u00a6 \u00a5", "raw_count": 606578, "count": 606578, "decode_str": "\u99a5"} -{"id": 25756, "token": "commit", "merges": "com mit", "raw_count": 606622, "count": 606622, "decode_str": "commit"} -{"id": 4896, "token": "works", "merges": "w orks", "raw_count": 445494, "count": 606723, "decode_str": "works"} -{"id": 5751, "token": "kt", "merges": "k t", "raw_count": 594344, "count": 606829, "decode_str": "kt"} -{"id": 13997, "token": "\u0120ip", "merges": "\u0120 ip", "raw_count": 606903, "count": 606903, "decode_str": " ip"} -{"id": 1754, "token": "\u0120based", "merges": "\u0120b ased", "raw_count": 607303, "count": 607303, "decode_str": " based"} -{"id": 9547, "token": "Mat", "merges": "M at", "raw_count": 269067, "count": 607654, "decode_str": "Mat"} -{"id": 51654, "token": "\u00e5\u00be\u00a8", "merges": "\u00e5\u00be \u00a8", "raw_count": 607942, "count": 607942, "decode_str": "\u5fa8"} -{"id": 17184, "token": "176", "merges": "17 6", "raw_count": 608330, "count": 608330, "decode_str": "176"} -{"id": 11154, "token": "ctx", "merges": "ct x", "raw_count": 608349, "count": 608349, "decode_str": "ctx"} -{"id": 6972, "token": "mo", "merges": "m o", "raw_count": 590579, "count": 608533, "decode_str": "mo"} -{"id": 43970, "token": "1946", "merges": "19 46", "raw_count": 609001, "count": 609001, "decode_str": "1946"} -{"id": 4045, "token": "Do", "merges": "D o", "raw_count": 443243, "count": 609369, "decode_str": "Do"} -{"id": 4612, "token": "Def", "merges": "D ef", "raw_count": 234334, "count": 609470, "decode_str": "Def"} -{"id": 50620, "token": "\u00e5\u0122\u0131", "merges": "\u00e5\u0122 \u0131", "raw_count": 609575, "count": 609575, "decode_str": "\u500f"} -{"id": 52894, "token": "\u00e7\u0137\u00b2", "merges": "\u00e7\u0137 \u00b2", "raw_count": 609577, "count": 609577, "decode_str": "\u7572"} -{"id": 1741, "token": "ivid", "merges": "iv id", "raw_count": 53881, "count": 609876, "decode_str": "ivid"} -{"id": 17364, "token": "142", "merges": "14 2", "raw_count": 610133, "count": 610133, "decode_str": "142"} -{"id": 1339, "token": "\u0120let", "merges": "\u0120le t", "raw_count": 230440, "count": 610238, "decode_str": " let"} -{"id": 8567, "token": "png", "merges": "p ng", "raw_count": 610349, "count": 610349, "decode_str": "png"} -{"id": 4175, "token": "mar", "merges": "m ar", "raw_count": 343144, "count": 610676, "decode_str": "mar"} -{"id": 4949, "token": "hold", "merges": "h old", "raw_count": 357142, "count": 611238, "decode_str": "hold"} -{"id": 6204, "token": "look", "merges": "l ook", "raw_count": 332831, "count": 611336, "decode_str": "look"} -{"id": 51128, "token": "\u00e5\u0138\u00b3", "merges": "\u00e5\u0138 \u00b3", "raw_count": 612288, "count": 612288, "decode_str": "\u55b3"} -{"id": 19813, "token": "1976", "merges": "19 76", "raw_count": 612763, "count": 612763, "decode_str": "1976"} -{"id": 3284, "token": "\u0120element", "merges": "\u0120e lement", "raw_count": 598178, "count": 612872, "decode_str": " element"} -{"id": 8889, "token": "\u0120organizations", "merges": "\u0120organ izations", "raw_count": 613379, "count": 613379, "decode_str": " organizations"} -{"id": 52660, "token": "\u00e6\u00b8\u013c", "merges": "\u00e6\u00b8 \u013c", "raw_count": 613402, "count": 613402, "decode_str": "\u6e1a"} -{"id": 4012, "token": "atform", "merges": "at form", "raw_count": 5673, "count": 613479, "decode_str": "atform"} -{"id": 12795, "token": "agic", "merges": "ag ic", "raw_count": 22765, "count": 613612, "decode_str": "agic"} -{"id": 6435, "token": "GG", "merges": "G G", "raw_count": 586069, "count": 614231, "decode_str": "GG"} -{"id": 9933, "token": "\u0120regional", "merges": "\u0120reg ional", "raw_count": 614482, "count": 614482, "decode_str": " regional"} -{"id": 1077, "token": "\u0120very", "merges": "\u0120 very", "raw_count": 614511, "count": 614511, "decode_str": " very"} -{"id": 5456, "token": "[]", "merges": "[ ]", "raw_count": 585722, "count": 614718, "decode_str": "[]"} -{"id": 5474, "token": "\u0120doc", "merges": "\u0120d oc", "raw_count": 357378, "count": 614890, "decode_str": " doc"} -{"id": 1983, "token": "imal", "merges": "im al", "raw_count": 206750, "count": 615111, "decode_str": "imal"} -{"id": 8997, "token": "Off", "merges": "O ff", "raw_count": 155285, "count": 615331, "decode_str": "Off"} -{"id": 53835, "token": "\u00e8\u00af\u00a9", "merges": "\u00e8\u00af \u00a9", "raw_count": 616265, "count": 616265, "decode_str": "\u8be9"} -{"id": 1555, "token": "\u0120treat", "merges": "\u0120t reat", "raw_count": 45141, "count": 616298, "decode_str": " treat"} -{"id": 3328, "token": "eration", "merges": "er ation", "raw_count": 283196, "count": 616848, "decode_str": "eration"} -{"id": 35000, "token": "-------------------------------------", "merges": "-------------------------------- -----", "raw_count": 616855, "count": 616855, "decode_str": "-------------------------------------"} -{"id": 1909, "token": "As", "merges": "A s", "raw_count": 421813, "count": 616908, "decode_str": "As"} -{"id": 7931, "token": "007", "merges": "00 7", "raw_count": 617139, "count": 617139, "decode_str": "007"} -{"id": 12764, "token": "Hi", "merges": "H i", "raw_count": 617139, "count": 617139, "decode_str": "Hi"} -{"id": 2294, "token": "\u0120priv", "merges": "\u0120p riv", "raw_count": 21132, "count": 617700, "decode_str": " priv"} -{"id": 52969, "token": "\u00e7\u013c\u012a", "merges": "\u00e7\u013c \u012a", "raw_count": 617819, "count": 617819, "decode_str": "\u7688"} -{"id": 51542, "token": "\u00e5\u00b8\u00bc", "merges": "\u00e5\u00b8 \u00bc", "raw_count": 617847, "count": 617847, "decode_str": "\u5e3c"} -{"id": 1468, "token": "aim", "merges": "a im", "raw_count": 132462, "count": 617982, "decode_str": "aim"} -{"id": 17472, "token": "152", "merges": "15 2", "raw_count": 618664, "count": 618664, "decode_str": "152"} -{"id": 3349, "token": "\u012028", "merges": "\u01202 8", "raw_count": 603722, "count": 618684, "decode_str": " 28"} -{"id": 2737, "token": "urope", "merges": "uro pe", "raw_count": 27733, "count": 618803, "decode_str": "urope"} -{"id": 14009, "token": "209", "merges": "20 9", "raw_count": 618867, "count": 618867, "decode_str": "209"} -{"id": 31248, "token": "columns", "merges": "col umns", "raw_count": 619125, "count": 619125, "decode_str": "columns"} -{"id": 53521, "token": "\u00e8\u0125\u00a5", "merges": "\u00e8\u0125 \u00a5", "raw_count": 619511, "count": 619511, "decode_str": "\u80e5"} -{"id": 9906, "token": "google", "merges": "go ogle", "raw_count": 600586, "count": 619548, "decode_str": "google"} -{"id": 2476, "token": "ption", "merges": "pt ion", "raw_count": 28936, "count": 619554, "decode_str": "ption"} -{"id": 25138, "token": "QQ", "merges": "Q Q", "raw_count": 619590, "count": 619590, "decode_str": "QQ"} -{"id": 25246, "token": ")!", "merges": ") !", "raw_count": 619614, "count": 619614, "decode_str": ")!"} -{"id": 4139, "token": "ervice", "merges": "erv ice", "raw_count": 54033, "count": 619937, "decode_str": "ervice"} -{"id": 2972, "token": "\u0120block", "merges": "\u0120bl ock", "raw_count": 534675, "count": 620283, "decode_str": " block"} -{"id": 4610, "token": "\u0120options", "merges": "\u0120opt ions", "raw_count": 620621, "count": 620621, "decode_str": " options"} -{"id": 1223, "token": "\u0120while", "merges": "\u0120wh ile", "raw_count": 620809, "count": 620809, "decode_str": " while"} -{"id": 52046, "token": "\u00e6\u0135\u0122", "merges": "\u00e6\u0135 \u0122", "raw_count": 620876, "count": 620876, "decode_str": "\u64c0"} -{"id": 1409, "token": "\u0120proble", "merges": "\u0120pro ble", "raw_count": 438, "count": 621009, "decode_str": " proble"} -{"id": 39596, "token": "Tensor", "merges": "T ensor", "raw_count": 621134, "count": 621134, "decode_str": "Tensor"} -{"id": 23822, "token": "\u0120republic", "merges": "\u0120rep ublic", "raw_count": 621190, "count": 621190, "decode_str": " republic"} -{"id": 51147, "token": "\u00e5\u013b\u00b1", "merges": "\u00e5\u013b \u00b1", "raw_count": 621275, "count": 621275, "decode_str": "\u5671"} -{"id": 51982, "token": "\u00e6\u012f\u00bb", "merges": "\u00e6\u012f \u00bb", "raw_count": 621323, "count": 621323, "decode_str": "\u637b"} -{"id": 52412, "token": "\u00e6\u00ae\u0125", "merges": "\u00e6\u00ae \u0125", "raw_count": 621449, "count": 621449, "decode_str": "\u6b83"} -{"id": 2569, "token": "atter", "merges": "at ter", "raw_count": 208732, "count": 621901, "decode_str": "atter"} -{"id": 9819, "token": "{\"", "merges": "{ \"", "raw_count": 599532, "count": 622196, "decode_str": "{\""} -{"id": 17393, "token": "Widget", "merges": "W idget", "raw_count": 622712, "count": 622712, "decode_str": "Widget"} -{"id": 6504, "token": "Inter", "merges": "In ter", "raw_count": 388707, "count": 622914, "decode_str": "Inter"} -{"id": 10697, "token": "Car", "merges": "C ar", "raw_count": 571360, "count": 622973, "decode_str": "Car"} -{"id": 18698, "token": "tv", "merges": "t v", "raw_count": 622993, "count": 622993, "decode_str": "tv"} -{"id": 2103, "token": "alf", "merges": "al f", "raw_count": 85192, "count": 623296, "decode_str": "alf"} -{"id": 4804, "token": "\u0120meeting", "merges": "\u0120meet ing", "raw_count": 623388, "count": 623388, "decode_str": " meeting"} -{"id": 54070, "token": "\u00e8\u00bf\u0124", "merges": "\u00e8\u00bf \u0124", "raw_count": 624123, "count": 624123, "decode_str": "\u8fc2"} -{"id": 3028, "token": "tic", "merges": "t ic", "raw_count": 110710, "count": 624454, "decode_str": "tic"} -{"id": 1866, "token": "ten", "merges": "t en", "raw_count": 348680, "count": 624664, "decode_str": "ten"} -{"id": 53123, "token": "\u00e7\u00a5\u0141", "merges": "\u00e7\u00a5 \u0141", "raw_count": 624760, "count": 624760, "decode_str": "\u795f"} -{"id": 3498, "token": "px", "merges": "p x", "raw_count": 587697, "count": 624780, "decode_str": "px"} -{"id": 10773, "token": "access", "merges": "ac cess", "raw_count": 602810, "count": 624833, "decode_str": "access"} -{"id": 11427, "token": "sv", "merges": "s v", "raw_count": 313717, "count": 624896, "decode_str": "sv"} -{"id": 3483, "token": "\u0120strateg", "merges": "\u0120str ateg", "raw_count": 6824, "count": 625273, "decode_str": " strateg"} -{"id": 24728, "token": "+,", "merges": "+ ,", "raw_count": 625308, "count": 625308, "decode_str": "+,"} -{"id": 2423, "token": "ocus", "merges": "oc us", "raw_count": 31058, "count": 625567, "decode_str": "ocus"} -{"id": 15743, "token": "POST", "merges": "PO ST", "raw_count": 625707, "count": 625707, "decode_str": "POST"} -{"id": 22800, "token": "China", "merges": "Ch ina", "raw_count": 625914, "count": 625914, "decode_str": "China"} -{"id": 53417, "token": "\u00e7\u00bd\u00a1", "merges": "\u00e7\u00bd \u00a1", "raw_count": 625959, "count": 625959, "decode_str": "\u7f61"} -{"id": 2382, "token": "ribution", "merges": "rib ution", "raw_count": 60436, "count": 626169, "decode_str": "ribution"} -{"id": 8575, "token": "OH", "merges": "O H", "raw_count": 619509, "count": 626731, "decode_str": "OH"} -{"id": 1609, "token": "\u0120occ", "merges": "\u0120o cc", "raw_count": 45999, "count": 626795, "decode_str": " occ"} -{"id": 51209, "token": "\u00e5\u013f\u00a8", "merges": "\u00e5\u013f \u00a8", "raw_count": 627132, "count": 627132, "decode_str": "\u5768"} -{"id": 1437, "token": "\u0120quest", "merges": "\u0120qu est", "raw_count": 25244, "count": 627134, "decode_str": " quest"} -{"id": 5638, "token": "........", "merges": ".... ....", "raw_count": 314026, "count": 627294, "decode_str": "........"} -{"id": 2316, "token": "\u0120room", "merges": "\u0120ro om", "raw_count": 452986, "count": 627757, "decode_str": " room"} -{"id": 3186, "token": "\u0120search", "merges": "\u0120se arch", "raw_count": 598477, "count": 628030, "decode_str": " search"} -{"id": 54375, "token": "\u00e9\u013d\u00b3", "merges": "\u00e9\u013d \u00b3", "raw_count": 628094, "count": 628094, "decode_str": "\u96f3"} -{"id": 3945, "token": "term", "merges": "ter m", "raw_count": 511471, "count": 628387, "decode_str": "term"} -{"id": 20611, "token": "404", "merges": "40 4", "raw_count": 628520, "count": 628520, "decode_str": "404"} -{"id": 7282, "token": "BP", "merges": "B P", "raw_count": 624687, "count": 628694, "decode_str": "BP"} -{"id": 7047, "token": "Fil", "merges": "F il", "raw_count": 91546, "count": 628847, "decode_str": "Fil"} -{"id": 13057, "token": "edge", "merges": "ed ge", "raw_count": 616560, "count": 628850, "decode_str": "edge"} -{"id": 18873, "token": "\u0120\",", "merges": "\u0120\" ,", "raw_count": 629179, "count": 629179, "decode_str": " \","} -{"id": 4077, "token": "\u0120arr", "merges": "\u0120ar r", "raw_count": 324050, "count": 629342, "decode_str": " arr"} -{"id": 3755, "token": "reng", "merges": "ren g", "raw_count": 38703, "count": 629605, "decode_str": "reng"} -{"id": 1431, "token": "\u0120fam", "merges": "\u0120f am", "raw_count": 11553, "count": 629915, "decode_str": " fam"} -{"id": 2170, "token": "\u0120area", "merges": "\u0120are a", "raw_count": 629988, "count": 629988, "decode_str": " area"} -{"id": 42825, "token": "mini", "merges": "min i", "raw_count": 630124, "count": 630124, "decode_str": "mini"} -{"id": 50522, "token": "\u00e4\u00bc\u0130", "merges": "\u00e4\u00bc \u0130", "raw_count": 630841, "count": 630841, "decode_str": "\u4f0e"} -{"id": 51366, "token": "\u00e5\u00a7\u00a3", "merges": "\u00e5\u00a7 \u00a3", "raw_count": 630901, "count": 630901, "decode_str": "\u59e3"} -{"id": 9042, "token": "DM", "merges": "D M", "raw_count": 630921, "count": 630921, "decode_str": "DM"} -{"id": 53038, "token": "\u00e7\u0141\u0139", "merges": "\u00e7\u0141 \u0139", "raw_count": 631012, "count": 631012, "decode_str": "\u77d7"} -{"id": 1607, "token": "\u0120imp", "merges": "\u0120im p", "raw_count": 149496, "count": 631255, "decode_str": " imp"} -{"id": 2008, "token": "epend", "merges": "ep end", "raw_count": 7853, "count": 631459, "decode_str": "epend"} -{"id": 1637, "token": "alpha", "merges": "al pha", "raw_count": 631485, "count": 631485, "decode_str": "alpha"} -{"id": 1421, "token": "\u0120lead", "merges": "\u0120le ad", "raw_count": 171498, "count": 631542, "decode_str": " lead"} -{"id": 19209, "token": "price", "merges": "pr ice", "raw_count": 631896, "count": 631896, "decode_str": "price"} -{"id": 54132, "token": "\u00e9\u0123\u013d", "merges": "\u00e9\u0123 \u013d", "raw_count": 631973, "count": 631973, "decode_str": "\u905b"} -{"id": 24413, "token": "POS", "merges": "P OS", "raw_count": 632155, "count": 632155, "decode_str": "POS"} -{"id": 51979, "token": "\u00e6\u012f\u00b6", "merges": "\u00e6\u012f \u00b6", "raw_count": 632240, "count": 632240, "decode_str": "\u6376"} -{"id": 53251, "token": "\u00e7\u00b1\u0123", "merges": "\u00e7\u00b1 \u0123", "raw_count": 632297, "count": 632297, "decode_str": "\u7c41"} -{"id": 17490, "token": "203", "merges": "20 3", "raw_count": 632320, "count": 632320, "decode_str": "203"} -{"id": 10548, "token": "Inst", "merges": "In st", "raw_count": 571172, "count": 632405, "decode_str": "Inst"} -{"id": 5607, "token": "EE", "merges": "E E", "raw_count": 392869, "count": 632456, "decode_str": "EE"} -{"id": 2133, "token": "\u0120body", "merges": "\u0120b ody", "raw_count": 632458, "count": 632458, "decode_str": " body"} -{"id": 22308, "token": "290", "merges": "29 0", "raw_count": 632567, "count": 632567, "decode_str": "290"} -{"id": 20914, "token": "303", "merges": "30 3", "raw_count": 632643, "count": 632643, "decode_str": "303"} -{"id": 51148, "token": "\u00e5\u013b\u00b6", "merges": "\u00e5\u013b \u00b6", "raw_count": 632839, "count": 632839, "decode_str": "\u5676"} -{"id": 11429, "token": "etch", "merges": "et ch", "raw_count": 89267, "count": 633404, "decode_str": "etch"} -{"id": 2680, "token": "minist", "merges": "min ist", "raw_count": 8653, "count": 633495, "decode_str": "minist"} -{"id": 16150, "token": "143", "merges": "14 3", "raw_count": 633513, "count": 633513, "decode_str": "143"} -{"id": 1682, "token": "\u0120best", "merges": "\u0120b est", "raw_count": 633538, "count": 633538, "decode_str": " best"} -{"id": 54399, "token": "\u00e9\u013e\u00b9", "merges": "\u00e9\u013e \u00b9", "raw_count": 633739, "count": 633739, "decode_str": "\u9739"} -{"id": 1625, "token": "\u0120sing", "merges": "\u0120s ing", "raw_count": 81133, "count": 634023, "decode_str": " sing"} -{"id": 6721, "token": "DL", "merges": "D L", "raw_count": 484440, "count": 634230, "decode_str": "DL"} -{"id": 4584, "token": "aker", "merges": "ak er", "raw_count": 494468, "count": 634869, "decode_str": "aker"} -{"id": 21351, "token": "215", "merges": "2 15", "raw_count": 635298, "count": 635298, "decode_str": "215"} -{"id": 1563, "token": "\u0120following", "merges": "\u0120follow ing", "raw_count": 635477, "count": 635477, "decode_str": " following"} -{"id": 2235, "token": "\u0120pri", "merges": "\u0120p ri", "raw_count": 30222, "count": 635684, "decode_str": " pri"} -{"id": 2331, "token": "ogn", "merges": "og n", "raw_count": 56011, "count": 635874, "decode_str": "ogn"} -{"id": 7507, "token": "comple", "merges": "com ple", "raw_count": 34938, "count": 636206, "decode_str": "comple"} -{"id": 51016, "token": "\u00e5\u0134\u0123", "merges": "\u00e5\u0134 \u0123", "raw_count": 636427, "count": 636427, "decode_str": "\u5481"} -{"id": 30496, "token": "office", "merges": "off ice", "raw_count": 636435, "count": 636435, "decode_str": "office"} -{"id": 51783, "token": "\u00e6\u0125\u00ba", "merges": "\u00e6\u0125 \u00ba", "raw_count": 636457, "count": 636457, "decode_str": "\u60fa"} -{"id": 17271, "token": "216", "merges": "2 16", "raw_count": 636652, "count": 636652, "decode_str": "216"} -{"id": 12566, "token": "success", "merges": "su ccess", "raw_count": 623703, "count": 636743, "decode_str": "success"} -{"id": 2743, "token": "\u0120regard", "merges": "\u0120reg ard", "raw_count": 365755, "count": 636907, "decode_str": " regard"} -{"id": 2757, "token": "\u0120viol", "merges": "\u0120vi ol", "raw_count": 4941, "count": 637084, "decode_str": " viol"} -{"id": 19334, "token": "Pay", "merges": "P ay", "raw_count": 558844, "count": 637113, "decode_str": "Pay"} -{"id": 31385, "token": "\u0120pd", "merges": "\u0120p d", "raw_count": 637155, "count": 637155, "decode_str": " pd"} -{"id": 1701, "token": "ised", "merges": "is ed", "raw_count": 154871, "count": 637323, "decode_str": "ised"} -{"id": 12068, "token": "agram", "merges": "ag ram", "raw_count": 634383, "count": 638188, "decode_str": "agram"} -{"id": 53798, "token": "\u00e8\u00ae\u00b7", "merges": "\u00e8\u00ae \u00b7", "raw_count": 638286, "count": 638286, "decode_str": "\u8bb7"} -{"id": 52729, "token": "\u00e7\u0124\u0137", "merges": "\u00e7\u0124 \u0137", "raw_count": 638462, "count": 638462, "decode_str": "\u7095"} -{"id": 18359, "token": "189", "merges": "18 9", "raw_count": 638919, "count": 638919, "decode_str": "189"} -{"id": 5703, "token": "Read", "merges": "R ead", "raw_count": 358667, "count": 639004, "decode_str": "Read"} -{"id": 4595, "token": "ara", "merges": "ar a", "raw_count": 619117, "count": 639161, "decode_str": "ara"} -{"id": 52329, "token": "\u00e6\u00a3\u00a3", "merges": "\u00e6\u00a3 \u00a3", "raw_count": 640304, "count": 640304, "decode_str": "\u68e3"} -{"id": 51276, "token": "\u00e5\u00a3\u0137", "merges": "\u00e5\u00a3 \u0137", "raw_count": 640341, "count": 640341, "decode_str": "\u58d5"} -{"id": 2628, "token": "\u0120job", "merges": "\u0120j ob", "raw_count": 515557, "count": 640709, "decode_str": " job"} -{"id": 1965, "token": "\u0120impro", "merges": "\u0120im pro", "raw_count": 7763, "count": 641047, "decode_str": " impro"} -{"id": 4032, "token": "supp", "merges": "s upp", "raw_count": 316920, "count": 641179, "decode_str": "supp"} -{"id": 38340, "token": "Io", "merges": "I o", "raw_count": 641227, "count": 641227, "decode_str": "Io"} -{"id": 2291, "token": "chan", "merges": "ch an", "raw_count": 198998, "count": 641691, "decode_str": "chan"} -{"id": 858, "token": "\u0120did", "merges": "\u0120d id", "raw_count": 501709, "count": 641777, "decode_str": " did"} -{"id": 22314, "token": ":-", "merges": ": -", "raw_count": 641858, "count": 641858, "decode_str": ":-"} -{"id": 2247, "token": "ament", "merges": "am ent", "raw_count": 236688, "count": 641910, "decode_str": "ament"} -{"id": 1981, "token": "ling", "merges": "l ing", "raw_count": 384954, "count": 641929, "decode_str": "ling"} -{"id": 3929, "token": "\u0120article", "merges": "\u0120art icle", "raw_count": 642503, "count": 642503, "decode_str": " article"} -{"id": 30105, "token": "\u0120cv", "merges": "\u0120c v", "raw_count": 642702, "count": 642702, "decode_str": " cv"} -{"id": 4771, "token": "\u0120server", "merges": "\u0120ser ver", "raw_count": 642858, "count": 642858, "decode_str": " server"} -{"id": 7566, "token": "ainer", "merges": "ain er", "raw_count": 44747, "count": 643085, "decode_str": "ainer"} -{"id": 3336, "token": "\u0120educ", "merges": "\u0120ed uc", "raw_count": 7597, "count": 643189, "decode_str": " educ"} -{"id": 20559, "token": "patch", "merges": "p atch", "raw_count": 629497, "count": 643319, "decode_str": "patch"} -{"id": 1382, "token": "ving", "merges": "v ing", "raw_count": 67161, "count": 643324, "decode_str": "ving"} -{"id": 5738, "token": "ua", "merges": "u a", "raw_count": 415861, "count": 643407, "decode_str": "ua"} -{"id": 17726, "token": "195", "merges": "19 5", "raw_count": 643546, "count": 643546, "decode_str": "195"} -{"id": 2147, "token": "ched", "merges": "c hed", "raw_count": 201067, "count": 643620, "decode_str": "ched"} -{"id": 6560, "token": "Ne", "merges": "N e", "raw_count": 538958, "count": 643963, "decode_str": "Ne"} -{"id": 50645, "token": "\u00e5\u0123\u0137", "merges": "\u00e5\u0123 \u0137", "raw_count": 644088, "count": 644088, "decode_str": "\u5055"} -{"id": 8835, "token": "WH", "merges": "W H", "raw_count": 264099, "count": 644406, "decode_str": "WH"} -{"id": 50851, "token": "\u00e5\u012e\u013f", "merges": "\u00e5\u012e \u013f", "raw_count": 644412, "count": 644412, "decode_str": "\u531d"} -{"id": 5623, "token": "Sub", "merges": "S ub", "raw_count": 549478, "count": 644484, "decode_str": "Sub"} -{"id": 53748, "token": "\u00e8\u00a6\u0125", "merges": "\u00e8\u00a6 \u0125", "raw_count": 644880, "count": 644880, "decode_str": "\u8983"} -{"id": 7621, "token": "\u0120datas", "merges": "\u0120dat as", "raw_count": 36034, "count": 644928, "decode_str": " datas"} -{"id": 7430, "token": "rypt", "merges": "ry pt", "raw_count": 236124, "count": 645189, "decode_str": "rypt"} -{"id": 54480, "token": "\u00e9\u00a6\u012f", "merges": "\u00e9\u00a6 \u012f", "raw_count": 645209, "count": 645209, "decode_str": "\u998d"} -{"id": 3178, "token": "arc", "merges": "ar c", "raw_count": 359055, "count": 645238, "decode_str": "arc"} -{"id": 54452, "token": "\u00e9\u00a2\u013c", "merges": "\u00e9\u00a2 \u013c", "raw_count": 645272, "count": 645272, "decode_str": "\u989a"} -{"id": 1425, "token": ".\u00e2\u0122\u013f", "merges": ". \u00e2\u0122\u013f", "raw_count": 645467, "count": 645504, "decode_str": ".\u201d"} -{"id": 2698, "token": ".)", "merges": ". )", "raw_count": 645517, "count": 645517, "decode_str": ".)"} -{"id": 14555, "token": "147", "merges": "14 7", "raw_count": 645660, "count": 645660, "decode_str": "147"} -{"id": 6744, "token": "Dis", "merges": "D is", "raw_count": 325460, "count": 646045, "decode_str": "Dis"} -{"id": 5391, "token": "ini", "merges": "in i", "raw_count": 635903, "count": 646251, "decode_str": "ini"} -{"id": 14729, "token": "profile", "merges": "pro file", "raw_count": 646521, "count": 646521, "decode_str": "profile"} -{"id": 2153, "token": "oney", "merges": "one y", "raw_count": 81510, "count": 647375, "decode_str": "oney"} -{"id": 52940, "token": "\u00e7\u0139\u00a2", "merges": "\u00e7\u0139 \u00a2", "raw_count": 647776, "count": 647776, "decode_str": "\u75e2"} -{"id": 15227, "token": "sort", "merges": "s ort", "raw_count": 647868, "count": 647868, "decode_str": "sort"} -{"id": 53899, "token": "\u00e8\u00b1\u012e", "merges": "\u00e8\u00b1 \u012e", "raw_count": 648182, "count": 648182, "decode_str": "\u8c4c"} -{"id": 25348, "token": "tok", "merges": "t ok", "raw_count": 137810, "count": 648211, "decode_str": "tok"} -{"id": 1524, "token": "\u0120real", "merges": "\u0120re al", "raw_count": 427145, "count": 648474, "decode_str": " real"} -{"id": 20694, "token": "228", "merges": "22 8", "raw_count": 648818, "count": 648818, "decode_str": "228"} -{"id": 38832, "token": "2100", "merges": "21 00", "raw_count": 648881, "count": 648881, "decode_str": "2100"} -{"id": 9030, "token": "Gl", "merges": "G l", "raw_count": 350256, "count": 648940, "decode_str": "Gl"} -{"id": 54620, "token": "\u00ef\u00bd\u0122", "merges": "\u00ef\u00bd \u0122", "raw_count": 648982, "count": 648982, "decode_str": " "} -{"id": 13776, "token": "idget", "merges": "id get", "raw_count": 26451, "count": 649163, "decode_str": "idget"} -{"id": 10930, "token": "WS", "merges": "W S", "raw_count": 621975, "count": 649334, "decode_str": "WS"} -{"id": 23695, "token": "340", "merges": "3 40", "raw_count": 649934, "count": 649934, "decode_str": "340"} -{"id": 2840, "token": "\u0120custom", "merges": "\u0120c ustom", "raw_count": 224687, "count": 650037, "decode_str": " custom"} -{"id": 3179, "token": "vant", "merges": "v ant", "raw_count": 56357, "count": 650377, "decode_str": "vant"} -{"id": 2394, "token": "verage", "merges": "ver age", "raw_count": 9956, "count": 650409, "decode_str": "verage"} -{"id": 986, "token": "\"}", "merges": "\" }", "raw_count": 301552, "count": 650817, "decode_str": "\"}"} -{"id": 17864, "token": "179", "merges": "17 9", "raw_count": 651595, "count": 651595, "decode_str": "179"} -{"id": 3187, "token": "\u0120fund", "merges": "\u0120fun d", "raw_count": 322101, "count": 652117, "decode_str": " fund"} -{"id": 13393, "token": "handle", "merges": "hand le", "raw_count": 652245, "count": 652245, "decode_str": "handle"} -{"id": 2001, "token": "outh", "merges": "ou th", "raw_count": 49930, "count": 652639, "decode_str": "outh"} -{"id": 52415, "token": "\u00e6\u00ae\u012b", "merges": "\u00e6\u00ae \u012b", "raw_count": 653017, "count": 653017, "decode_str": "\u6b89"} -{"id": 54031, "token": "\u00e8\u00bd\u00b6", "merges": "\u00e8\u00bd \u00b6", "raw_count": 653061, "count": 653061, "decode_str": "\u8f76"} -{"id": 13437, "token": "diff", "merges": "d iff", "raw_count": 608912, "count": 653133, "decode_str": "diff"} -{"id": 2110, "token": "nal", "merges": "n al", "raw_count": 45588, "count": 653218, "decode_str": "nal"} -{"id": 4117, "token": ",'", "merges": ", '", "raw_count": 647392, "count": 653388, "decode_str": ",'"} -{"id": 53548, "token": "\u00e8\u0126\u00af", "merges": "\u00e8\u0126 \u00af", "raw_count": 653481, "count": 653481, "decode_str": "\u812f"} -{"id": 2611, "token": "\u0120particip", "merges": "\u0120partic ip", "raw_count": 11885, "count": 653830, "decode_str": " particip"} -{"id": 5392, "token": "wid", "merges": "w id", "raw_count": 70055, "count": 653992, "decode_str": "wid"} -{"id": 2574, "token": "eq", "merges": "e q", "raw_count": 555700, "count": 654082, "decode_str": "eq"} -{"id": 3020, "token": "wise", "merges": "w ise", "raw_count": 222879, "count": 654767, "decode_str": "wise"} -{"id": 53231, "token": "\u00e7\u0143\u0142", "merges": "\u00e7\u0143 \u0142", "raw_count": 655121, "count": 655121, "decode_str": "\u7b60"} -{"id": 7570, "token": "INE", "merges": "IN E", "raw_count": 219422, "count": 655619, "decode_str": "INE"} -{"id": 2113, "token": "iple", "merges": "ip le", "raw_count": 34326, "count": 655914, "decode_str": "iple"} -{"id": 1578, "token": "\u0120es", "merges": "\u0120 es", "raw_count": 170644, "count": 655997, "decode_str": " es"} -{"id": 1908, "token": "\u0120consider", "merges": "\u0120cons ider", "raw_count": 257316, "count": 656230, "decode_str": " consider"} -{"id": 3128, "token": "\u0120party", "merges": "\u0120part y", "raw_count": 656394, "count": 656394, "decode_str": " party"} -{"id": 30337, "token": ":`", "merges": ": `", "raw_count": 656541, "count": 656541, "decode_str": ":`"} -{"id": 1027, "token": "\u0120different", "merges": "\u0120diffe rent", "raw_count": 595102, "count": 656995, "decode_str": " different"} -{"id": 25569, "token": "420", "merges": "4 20", "raw_count": 657142, "count": 657142, "decode_str": "420"} -{"id": 20649, "token": "manager", "merges": "man ager", "raw_count": 657794, "count": 657794, "decode_str": "manager"} -{"id": 1660, "token": "\u0120redu", "merges": "\u0120re du", "raw_count": 10289, "count": 658465, "decode_str": " redu"} -{"id": 5045, "token": "case", "merges": "c ase", "raw_count": 646399, "count": 658593, "decode_str": "case"} -{"id": 17398, "token": "Fin", "merges": "F in", "raw_count": 559389, "count": 658868, "decode_str": "Fin"} -{"id": 5496, "token": "Size", "merges": "S ize", "raw_count": 659672, "count": 659672, "decode_str": "Size"} -{"id": 2095, "token": "iversity", "merges": "ivers ity", "raw_count": 53176, "count": 659770, "decode_str": "iversity"} -{"id": 3463, "token": "By", "merges": "B y", "raw_count": 516068, "count": 661471, "decode_str": "By"} -{"id": 32174, "token": "850", "merges": "8 50", "raw_count": 661671, "count": 661671, "decode_str": "850"} -{"id": 51992, "token": "\u00e6\u0130\u0138", "merges": "\u00e6\u0130 \u0138", "raw_count": 661974, "count": 661974, "decode_str": "\u6396"} -{"id": 1683, "token": "\u0120chang", "merges": "\u0120ch ang", "raw_count": 34730, "count": 661997, "decode_str": " chang"} -{"id": 9868, "token": "\u0120password", "merges": "\u0120pass word", "raw_count": 644285, "count": 662288, "decode_str": " password"} -{"id": 53848, "token": "\u00e8\u00af\u00bd", "merges": "\u00e8\u00af \u00bd", "raw_count": 662304, "count": 662304, "decode_str": "\u8bfd"} -{"id": 12070, "token": "SQL", "merges": "S QL", "raw_count": 631572, "count": 662370, "decode_str": "SQL"} -{"id": 6603, "token": "NE", "merges": "N E", "raw_count": 457591, "count": 663174, "decode_str": "NE"} -{"id": 28199, "token": "('/", "merges": "(' /", "raw_count": 663307, "count": 663307, "decode_str": "('/"} -{"id": 51275, "token": "\u00e5\u00a3\u0133", "merges": "\u00e5\u00a3 \u0133", "raw_count": 663697, "count": 663697, "decode_str": "\u58d1"} -{"id": 20926, "token": "\u0120df", "merges": "\u0120d f", "raw_count": 663777, "count": 663777, "decode_str": " df"} -{"id": 17986, "token": "Parameters", "merges": "Param eters", "raw_count": 663922, "count": 663922, "decode_str": "Parameters"} -{"id": 3154, "token": "\u0120dest", "merges": "\u0120d est", "raw_count": 245526, "count": 664167, "decode_str": " dest"} -{"id": 8111, "token": "rows", "merges": "row s", "raw_count": 644003, "count": 665029, "decode_str": "rows"} -{"id": 53807, "token": "\u00e8\u00af\u0125", "merges": "\u00e8\u00af \u0125", "raw_count": 665098, "count": 665098, "decode_str": "\u8bc3"} -{"id": 2197, "token": "\u0120sent", "merges": "\u0120s ent", "raw_count": 338084, "count": 665230, "decode_str": " sent"} -{"id": 38249, "token": "1956", "merges": "19 56", "raw_count": 665293, "count": 665293, "decode_str": "1956"} -{"id": 42739, "token": "weights", "merges": "we ights", "raw_count": 665314, "count": 665314, "decode_str": "weights"} -{"id": 6180, "token": "Field", "merges": "F ield", "raw_count": 583077, "count": 665618, "decode_str": "Field"} -{"id": 8108, "token": "pload", "merges": "pl oad", "raw_count": 24111, "count": 665751, "decode_str": "pload"} -{"id": 17445, "token": "axy", "merges": "ax y", "raw_count": 654959, "count": 665770, "decode_str": "axy"} -{"id": 4969, "token": "\u0120instit", "merges": "\u0120inst it", "raw_count": 29741, "count": 666114, "decode_str": " instit"} -{"id": 1863, "token": "\u0120sw", "merges": "\u0120s w", "raw_count": 288119, "count": 666125, "decode_str": " sw"} -{"id": 50927, "token": "\u00e5\u0131\u0141", "merges": "\u00e5\u0131 \u0141", "raw_count": 666522, "count": 666522, "decode_str": "\u53df"} -{"id": 1786, "token": "\u0120health", "merges": "\u0120he alth", "raw_count": 597480, "count": 666563, "decode_str": " health"} -{"id": 1467, "token": "rict", "merges": "ric t", "raw_count": 63810, "count": 666702, "decode_str": "rict"} -{"id": 19393, "token": "Gal", "merges": "G al", "raw_count": 666997, "count": 666997, "decode_str": "Gal"} -{"id": 7638, "token": "Pol", "merges": "P ol", "raw_count": 311447, "count": 667050, "decode_str": "Pol"} -{"id": 14403, "token": "192", "merges": "19 2", "raw_count": 667161, "count": 667161, "decode_str": "192"} -{"id": 3414, "token": "\u0120sett", "merges": "\u0120set t", "raw_count": 8120, "count": 667267, "decode_str": " sett"} -{"id": 2269, "token": "erc", "merges": "er c", "raw_count": 144473, "count": 667566, "decode_str": "erc"} -{"id": 2788, "token": "uk", "merges": "u k", "raw_count": 475435, "count": 667747, "decode_str": "uk"} -{"id": 13914, "token": "ounter", "merges": "oun ter", "raw_count": 14685, "count": 667847, "decode_str": "ounter"} -{"id": 1073, "token": "\u0120di", "merges": "\u0120d i", "raw_count": 173770, "count": 668067, "decode_str": " di"} -{"id": 51676, "token": "\u00e5\u00bf\u00a1", "merges": "\u00e5\u00bf \u00a1", "raw_count": 668174, "count": 668174, "decode_str": "\u5fe1"} -{"id": 2252, "token": "most", "merges": "m ost", "raw_count": 249516, "count": 668875, "decode_str": "most"} -{"id": 50676, "token": "\u00e5\u0126\u00a1", "merges": "\u00e5\u0126 \u00a1", "raw_count": 669076, "count": 669076, "decode_str": "\u5121"} -{"id": 7864, "token": "FS", "merges": "F S", "raw_count": 668849, "count": 669247, "decode_str": "FS"} -{"id": 7073, "token": "FP", "merges": "F P", "raw_count": 602241, "count": 669253, "decode_str": "FP"} -{"id": 3302, "token": "\u0120initial", "merges": "\u0120init ial", "raw_count": 411531, "count": 669315, "decode_str": " initial"} -{"id": 24867, "token": "pH", "merges": "p H", "raw_count": 669547, "count": 669547, "decode_str": "pH"} -{"id": 1310, "token": "\u0120If", "merges": "\u0120I f", "raw_count": 669632, "count": 669632, "decode_str": " If"} -{"id": 54356, "token": "\u00e9\u013c\u00bd", "merges": "\u00e9\u013c \u00bd", "raw_count": 669858, "count": 669858, "decode_str": "\u96bd"} -{"id": 2893, "token": "ternal", "merges": "tern al", "raw_count": 9461, "count": 669898, "decode_str": "ternal"} -{"id": 53872, "token": "\u00e8\u00b0\u013b", "merges": "\u00e8\u00b0 \u013b", "raw_count": 669973, "count": 669973, "decode_str": "\u8c19"} -{"id": 17882, "token": "\u0120'/", "merges": "\u0120' /", "raw_count": 670697, "count": 670697, "decode_str": " '/"} -{"id": 2539, "token": "\u0120respons", "merges": "\u0120resp ons", "raw_count": 6404, "count": 670861, "decode_str": " respons"} -{"id": 14447, "token": "insert", "merges": "ins ert", "raw_count": 670997, "count": 670997, "decode_str": "insert"} -{"id": 2444, "token": "\u0120working", "merges": "\u0120work ing", "raw_count": 671485, "count": 671485, "decode_str": " working"} -{"id": 53826, "token": "\u00e8\u00af\u0141", "merges": "\u00e8\u00af \u0141", "raw_count": 672169, "count": 672169, "decode_str": "\u8bdf"} -{"id": 20270, "token": "186", "merges": "18 6", "raw_count": 672424, "count": 672424, "decode_str": "186"} -{"id": 3849, "token": "earch", "merges": "ear ch", "raw_count": 36195, "count": 672485, "decode_str": "earch"} -{"id": 17803, "token": "\u00e2\u0122\u0136\u00e2\u0122\u0136\u00e2\u0122\u0136\u00e2\u0122\u0136", "merges": "\u00e2\u0122\u0136\u00e2\u0122\u0136 \u00e2\u0122\u0136\u00e2\u0122\u0136", "raw_count": 262808, "count": 672564, "decode_str": "\u2014\u2014\u2014\u2014"} -{"id": 1582, "token": "akes", "merges": "ak es", "raw_count": 185035, "count": 672826, "decode_str": "akes"} -{"id": 3243, "token": "light", "merges": "l ight", "raw_count": 374618, "count": 673126, "decode_str": "light"} -{"id": 1039, "token": "\u0120way", "merges": "\u0120w ay", "raw_count": 673250, "count": 673250, "decode_str": " way"} -{"id": 4567, "token": "\u012032", "merges": "\u01203 2", "raw_count": 673354, "count": 673354, "decode_str": " 32"} -{"id": 53202, "token": "\u00e7\u00ab\u00ba", "merges": "\u00e7\u00ab \u00ba", "raw_count": 673404, "count": 673404, "decode_str": "\u7afa"} -{"id": 7481, "token": "_,", "merges": "_ ,", "raw_count": 673498, "count": 673498, "decode_str": "_,"} -{"id": 51547, "token": "\u00e5\u00b9\u012e", "merges": "\u00e5\u00b9 \u012e", "raw_count": 673686, "count": 673686, "decode_str": "\u5e4c"} -{"id": 19078, "token": "initial", "merges": "init ial", "raw_count": 673791, "count": 673791, "decode_str": "initial"} -{"id": 14066, "token": "wd", "merges": "w d", "raw_count": 673813, "count": 673813, "decode_str": "wd"} -{"id": 15845, "token": "bytes", "merges": "by tes", "raw_count": 674040, "count": 674040, "decode_str": "bytes"} -{"id": 4454, "token": "\u0120names", "merges": "\u0120n ames", "raw_count": 498344, "count": 674128, "decode_str": " names"} -{"id": 36739, "token": ";,", "merges": "; ,", "raw_count": 674395, "count": 674395, "decode_str": ";,"} -{"id": 31343, "token": "\u0120tuple", "merges": "\u0120t uple", "raw_count": 674571, "count": 674571, "decode_str": " tuple"} -{"id": 1236, "token": "\u0120lar", "merges": "\u0120l ar", "raw_count": 27977, "count": 674683, "decode_str": " lar"} -{"id": 7258, "token": "GC", "merges": "G C", "raw_count": 639834, "count": 674716, "decode_str": "GC"} -{"id": 2114, "token": "aken", "merges": "ak en", "raw_count": 39284, "count": 674807, "decode_str": "aken"} -{"id": 3579, "token": "\u0120forward", "merges": "\u0120for ward", "raw_count": 617314, "count": 674888, "decode_str": " forward"} -{"id": 5256, "token": "dot", "merges": "d ot", "raw_count": 674894, "count": 674894, "decode_str": "dot"} -{"id": 17962, "token": "166", "merges": "16 6", "raw_count": 674917, "count": 674917, "decode_str": "166"} -{"id": 10114, "token": "HA", "merges": "H A", "raw_count": 674991, "count": 674991, "decode_str": "HA"} -{"id": 1914, "token": "ien", "merges": "i en", "raw_count": 258045, "count": 675106, "decode_str": "ien"} -{"id": 52620, "token": "\u00e6\u00b6\u00ae", "merges": "\u00e6\u00b6 \u00ae", "raw_count": 675373, "count": 675373, "decode_str": "\u6dae"} -{"id": 54617, "token": "\u00ef\u00bc\u00bd", "merges": "\u00ef\u00bc \u00bd", "raw_count": 675855, "count": 675855, "decode_str": " "} -{"id": 4695, "token": "\u01202008", "merges": "\u0120200 8", "raw_count": 675874, "count": 675874, "decode_str": " 2008"} -{"id": 3796, "token": "erson", "merges": "ers on", "raw_count": 124113, "count": 676275, "decode_str": "erson"} -{"id": 2777, "token": "\u0120eval", "merges": "\u0120ev al", "raw_count": 190737, "count": 676409, "decode_str": " eval"} -{"id": 6577, "token": "ND", "merges": "N D", "raw_count": 472401, "count": 676893, "decode_str": "ND"} -{"id": 1485, "token": "\u0120inc", "merges": "\u0120in c", "raw_count": 137881, "count": 677107, "decode_str": " inc"} -{"id": 8810, "token": "inux", "merges": "in ux", "raw_count": 24085, "count": 677217, "decode_str": "inux"} -{"id": 7551, "token": "orted", "merges": "ort ed", "raw_count": 488195, "count": 677497, "decode_str": "orted"} -{"id": 2122, "token": "ered", "merges": "e red", "raw_count": 206692, "count": 677868, "decode_str": "ered"} -{"id": 32960, "token": "399", "merges": "3 99", "raw_count": 678121, "count": 678121, "decode_str": "399"} -{"id": 2496, "token": "ude", "merges": "ud e", "raw_count": 110788, "count": 678393, "decode_str": "ude"} -{"id": 21271, "token": "PLC", "merges": "PL C", "raw_count": 678087, "count": 678476, "decode_str": "PLC"} -{"id": 3906, "token": "\u0120office", "merges": "\u0120off ice", "raw_count": 678627, "count": 678627, "decode_str": " office"} -{"id": 54469, "token": "\u00e9\u00a3\u013c", "merges": "\u00e9\u00a3 \u013c", "raw_count": 678715, "count": 678715, "decode_str": "\u98da"} -{"id": 16702, "token": "transform", "merges": "trans form", "raw_count": 678915, "count": 678915, "decode_str": "transform"} -{"id": 53873, "token": "\u00e8\u00b0\u013c", "merges": "\u00e8\u00b0 \u013c", "raw_count": 679431, "count": 679431, "decode_str": "\u8c1a"} -{"id": 2198, "token": "rist", "merges": "r ist", "raw_count": 135235, "count": 679948, "decode_str": "rist"} -{"id": 37028, "token": "umpy", "merges": "ump y", "raw_count": 680028, "count": 680028, "decode_str": "umpy"} -{"id": 22181, "token": "cfg", "merges": "cf g", "raw_count": 680048, "count": 680048, "decode_str": "cfg"} -{"id": 8683, "token": "SO", "merges": "S O", "raw_count": 681268, "count": 681268, "decode_str": "SO"} -{"id": 36743, "token": "\u0120datetime", "merges": "\u0120dat etime", "raw_count": 681744, "count": 681744, "decode_str": " datetime"} -{"id": 1718, "token": "\u0120invest", "merges": "\u0120inv est", "raw_count": 27216, "count": 682064, "decode_str": " invest"} -{"id": 4909, "token": "font", "merges": "f ont", "raw_count": 655043, "count": 682064, "decode_str": "font"} -{"id": 8060, "token": "button", "merges": "but ton", "raw_count": 682256, "count": 682256, "decode_str": "button"} -{"id": 4748, "token": "\u01202009", "merges": "\u0120200 9", "raw_count": 682691, "count": 682691, "decode_str": " 2009"} -{"id": 53177, "token": "\u00e7\u00a8\u00b7", "merges": "\u00e7\u00a8 \u00b7", "raw_count": 682767, "count": 682767, "decode_str": "\u7a37"} -{"id": 4008, "token": "cast", "merges": "c ast", "raw_count": 473531, "count": 682838, "decode_str": "cast"} -{"id": 36354, "token": "1945", "merges": "19 45", "raw_count": 682856, "count": 682856, "decode_str": "1945"} -{"id": 984, "token": "\u0120because", "merges": "\u0120bec ause", "raw_count": 682944, "count": 682944, "decode_str": " because"} -{"id": 19136, "token": "232", "merges": "2 32", "raw_count": 683343, "count": 683343, "decode_str": "232"} -{"id": 2424, "token": "\u0120required", "merges": "\u0120requ ired", "raw_count": 683361, "count": 683361, "decode_str": " required"} -{"id": 4160, "token": "non", "merges": "n on", "raw_count": 678282, "count": 683605, "decode_str": "non"} -{"id": 5430, "token": "how", "merges": "h ow", "raw_count": 346891, "count": 683956, "decode_str": "how"} -{"id": 2400, "token": "ged", "merges": "g ed", "raw_count": 249175, "count": 684017, "decode_str": "ged"} -{"id": 52942, "token": "\u00e7\u0139\u00a4", "merges": "\u00e7\u0139 \u00a4", "raw_count": 684417, "count": 684417, "decode_str": "\u75e4"} -{"id": 2221, "token": "\u0120super", "merges": "\u0120su per", "raw_count": 543091, "count": 684526, "decode_str": " super"} -{"id": 5641, "token": "space", "merges": "sp ace", "raw_count": 672884, "count": 684607, "decode_str": "space"} -{"id": 52585, "token": "\u00e6\u00b5\u013c", "merges": "\u00e6\u00b5 \u013c", "raw_count": 684701, "count": 684701, "decode_str": "\u6d5a"} -{"id": 8976, "token": "uster", "merges": "ust er", "raw_count": 53115, "count": 685044, "decode_str": "uster"} -{"id": 5546, "token": "car", "merges": "c ar", "raw_count": 612764, "count": 685160, "decode_str": "car"} -{"id": 2118, "token": "\u0120move", "merges": "\u0120m ove", "raw_count": 479381, "count": 685444, "decode_str": " move"} -{"id": 20890, "token": "\u0120``", "merges": "\u0120` `", "raw_count": 685744, "count": 685744, "decode_str": " ``"} -{"id": 7064, "token": "dt", "merges": "d t", "raw_count": 685992, "count": 685992, "decode_str": "dt"} -{"id": 11125, "token": "fi", "merges": "f i", "raw_count": 686157, "count": 686157, "decode_str": "fi"} -{"id": 13324, "token": "lat", "merges": "l at", "raw_count": 502943, "count": 686197, "decode_str": "lat"} -{"id": 4450, "token": "\u0120board", "merges": "\u0120bo ard", "raw_count": 676997, "count": 687352, "decode_str": " board"} -{"id": 15850, "token": "\u0120cooperation", "merges": "\u0120cooper ation", "raw_count": 687799, "count": 687799, "decode_str": " cooperation"} -{"id": 14073, "token": "\u0120db", "merges": "\u0120d b", "raw_count": 687799, "count": 687799, "decode_str": " db"} -{"id": 1453, "token": "\u0120control", "merges": "\u0120cont rol", "raw_count": 611834, "count": 687904, "decode_str": " control"} -{"id": 4121, "token": "ocks", "merges": "oc ks", "raw_count": 139344, "count": 688151, "decode_str": "ocks"} -{"id": 29377, "token": "decode", "merges": "de code", "raw_count": 688205, "count": 688205, "decode_str": "decode"} -{"id": 8766, "token": "stat", "merges": "st at", "raw_count": 459986, "count": 688303, "decode_str": "stat"} -{"id": 32460, "token": "channels", "merges": "ch annels", "raw_count": 688491, "count": 688491, "decode_str": "channels"} -{"id": 2801, "token": "\u0120weight", "merges": "\u0120we ight", "raw_count": 357605, "count": 688940, "decode_str": " weight"} -{"id": 2168, "token": "\u0120already", "merges": "\u0120al ready", "raw_count": 689097, "count": 689097, "decode_str": " already"} -{"id": 19874, "token": "exit", "merges": "ex it", "raw_count": 689183, "count": 689183, "decode_str": "exit"} -{"id": 6064, "token": "\u0120resolution", "merges": "\u0120res olution", "raw_count": 689329, "count": 689329, "decode_str": " resolution"} -{"id": 4676, "token": "\u0120parties", "merges": "\u0120part ies", "raw_count": 690276, "count": 690276, "decode_str": " parties"} -{"id": 51446, "token": "\u00e5\u00af\u00ae", "merges": "\u00e5\u00af \u00ae", "raw_count": 690660, "count": 690660, "decode_str": "\u5bee"} -{"id": 8682, "token": "Point", "merges": "P oint", "raw_count": 558530, "count": 690690, "decode_str": "Point"} -{"id": 2323, "token": "\u0120success", "merges": "\u0120su ccess", "raw_count": 270140, "count": 690703, "decode_str": " success"} -{"id": 19770, "token": "classes", "merges": "class es", "raw_count": 690712, "count": 690712, "decode_str": "classes"} -{"id": 2758, "token": "\u0120members", "merges": "\u0120mem bers", "raw_count": 603164, "count": 691926, "decode_str": " members"} -{"id": 54613, "token": "\u00ef\u00bc\u0140", "merges": "\u00ef\u00bc \u0140", "raw_count": 692062, "count": 692062, "decode_str": " "} -{"id": 18950, "token": "306", "merges": "30 6", "raw_count": 692172, "count": 692172, "decode_str": "306"} -{"id": 3558, "token": "\u0120member", "merges": "\u0120mem ber", "raw_count": 693077, "count": 693077, "decode_str": " member"} -{"id": 53032, "token": "\u00e7\u013f\u00ac", "merges": "\u00e7\u013f \u00ac", "raw_count": 693420, "count": 693420, "decode_str": "\u776c"} -{"id": 18355, "token": "VP", "merges": "V P", "raw_count": 692066, "count": 693488, "decode_str": "VP"} -{"id": 51346, "token": "\u00e5\u00a6\u00a9", "merges": "\u00e5\u00a6 \u00a9", "raw_count": 693691, "count": 693691, "decode_str": "\u59a9"} -{"id": 8282, "token": "HS", "merges": "H S", "raw_count": 693402, "count": 693846, "decode_str": "HS"} -{"id": 1676, "token": "stand", "merges": "st and", "raw_count": 82897, "count": 693864, "decode_str": "stand"} -{"id": 1711, "token": "\u0120old", "merges": "\u0120o ld", "raw_count": 596473, "count": 694096, "decode_str": " old"} -{"id": 2062, "token": "\u0120orig", "merges": "\u0120or ig", "raw_count": 81496, "count": 694193, "decode_str": " orig"} -{"id": 2957, "token": "\u0120loss", "merges": "\u0120l oss", "raw_count": 603002, "count": 694336, "decode_str": " loss"} -{"id": 14061, "token": "wait", "merges": "w ait", "raw_count": 694373, "count": 694448, "decode_str": "wait"} -{"id": 51883, "token": "\u00e6\u012c\u00a8", "merges": "\u00e6\u012c \u00a8", "raw_count": 694593, "count": 694593, "decode_str": "\u62a8"} -{"id": 28850, "token": "sleep", "merges": "s leep", "raw_count": 694992, "count": 694992, "decode_str": "sleep"} -{"id": 5416, "token": "\u0120ensure", "merges": "\u0120ens ure", "raw_count": 695020, "count": 695020, "decode_str": " ensure"} -{"id": 2180, "token": "\u0120period", "merges": "\u0120per iod", "raw_count": 526626, "count": 695088, "decode_str": " period"} -{"id": 52350, "token": "\u00e6\u00a7\u0125", "merges": "\u00e6\u00a7 \u0125", "raw_count": 695170, "count": 695170, "decode_str": "\u69c3"} -{"id": 8289, "token": "sd", "merges": "s d", "raw_count": 579420, "count": 695449, "decode_str": "sd"} -{"id": 8732, "token": "John", "merges": "J ohn", "raw_count": 595255, "count": 695558, "decode_str": "John"} -{"id": 8417, "token": "BM", "merges": "B M", "raw_count": 685634, "count": 695582, "decode_str": "BM"} -{"id": 3514, "token": "airs", "merges": "air s", "raw_count": 285341, "count": 696007, "decode_str": "airs"} -{"id": 8510, "token": "writ", "merges": "w rit", "raw_count": 179134, "count": 696079, "decode_str": "writ"} -{"id": 1585, "token": "aterial", "merges": "ater ial", "raw_count": 6084, "count": 696082, "decode_str": "aterial"} -{"id": 1617, "token": "\u0120condition", "merges": "\u0120con dition", "raw_count": 214328, "count": 696083, "decode_str": " condition"} -{"id": 1801, "token": "\u0120prof", "merges": "\u0120pro f", "raw_count": 42902, "count": 696155, "decode_str": " prof"} -{"id": 52461, "token": "\u00e6\u00b0\u00b0", "merges": "\u00e6\u00b0 \u00b0", "raw_count": 696304, "count": 696304, "decode_str": "\u6c30"} -{"id": 17391, "token": "208", "merges": "20 8", "raw_count": 696510, "count": 696510, "decode_str": "208"} -{"id": 9063, "token": "Check", "merges": "Che ck", "raw_count": 609490, "count": 696560, "decode_str": "Check"} -{"id": 50486, "token": "\u00e4\u00ba\u00b5", "merges": "\u00e4\u00ba \u00b5", "raw_count": 696631, "count": 696631, "decode_str": "\u4eb5"} -{"id": 51688, "token": "\u00e6\u0122\u0124", "merges": "\u00e6\u0122 \u0124", "raw_count": 696656, "count": 696656, "decode_str": "\u6002"} -{"id": 21552, "token": "metadata", "merges": "met adata", "raw_count": 697262, "count": 697262, "decode_str": "metadata"} -{"id": 5904, "token": "izations", "merges": "iz ations", "raw_count": 83916, "count": 697295, "decode_str": "izations"} -{"id": 23059, "token": "tags", "merges": "t ags", "raw_count": 697311, "count": 697311, "decode_str": "tags"} -{"id": 33990, "token": "layers", "merges": "l ayers", "raw_count": 697480, "count": 697480, "decode_str": "layers"} -{"id": 50976, "token": "\u00e5\u0132\u0143", "merges": "\u00e5\u0132 \u0143", "raw_count": 697670, "count": 697670, "decode_str": "\u542d"} -{"id": 10468, "token": "opp", "merges": "o pp", "raw_count": 689939, "count": 697699, "decode_str": "opp"} -{"id": 4836, "token": "\u0120task", "merges": "\u0120t ask", "raw_count": 690157, "count": 697936, "decode_str": " task"} -{"id": 3621, "token": "lease", "merges": "le ase", "raw_count": 28466, "count": 698051, "decode_str": "lease"} -{"id": 54244, "token": "\u00e9\u0136\u00b5", "merges": "\u00e9\u0136 \u00b5", "raw_count": 698325, "count": 698325, "decode_str": "\u9535"} -{"id": 53718, "token": "\u00e8\u00a2\u0124", "merges": "\u00e8\u00a2 \u0124", "raw_count": 698985, "count": 698985, "decode_str": "\u8882"} -{"id": 3346, "token": "\u0120...", "merges": "\u0120 ...", "raw_count": 685687, "count": 699366, "decode_str": " ..."} -{"id": 5036, "token": "ech", "merges": "e ch", "raw_count": 137961, "count": 700465, "decode_str": "ech"} -{"id": 2960, "token": "ada", "merges": "ad a", "raw_count": 640625, "count": 700749, "decode_str": "ada"} -{"id": 53355, "token": "\u00e7\u00bb\u00a2", "merges": "\u00e7\u00bb \u00a2", "raw_count": 700782, "count": 700782, "decode_str": "\u7ee2"} -{"id": 32689, "token": "501", "merges": "5 01", "raw_count": 700968, "count": 700968, "decode_str": "501"} -{"id": 51633, "token": "\u00e5\u00bd\u00b7", "merges": "\u00e5\u00bd \u00b7", "raw_count": 701004, "count": 701004, "decode_str": "\u5f77"} -{"id": 6288, "token": "Hand", "merges": "H and", "raw_count": 135919, "count": 701209, "decode_str": "Hand"} -{"id": 53610, "token": "\u00e8\u012c\u012c", "merges": "\u00e8\u012c \u012c", "raw_count": 701828, "count": 701828, "decode_str": "\u828a"} -{"id": 20348, "token": "login", "merges": "log in", "raw_count": 702005, "count": 702005, "decode_str": "login"} -{"id": 1097, "token": "\u0120both", "merges": "\u0120b oth", "raw_count": 702119, "count": 702119, "decode_str": " both"} -{"id": 2166, "token": "itted", "merges": "itt ed", "raw_count": 102599, "count": 702210, "decode_str": "itted"} -{"id": 37673, "token": "LG", "merges": "L G", "raw_count": 703954, "count": 703954, "decode_str": "LG"} -{"id": 2532, "token": "uture", "merges": "ut ure", "raw_count": 5410, "count": 703955, "decode_str": "uture"} -{"id": 52528, "token": "\u00e6\u00b3\u0135", "merges": "\u00e6\u00b3 \u0135", "raw_count": 704048, "count": 704048, "decode_str": "\u6cd3"} -{"id": 3445, "token": "ymb", "merges": "ym b", "raw_count": 94120, "count": 704323, "decode_str": "ymb"} -{"id": 16989, "token": "148", "merges": "14 8", "raw_count": 704483, "count": 704483, "decode_str": "148"} -{"id": 17094, "token": "sent", "merges": "s ent", "raw_count": 448863, "count": 704651, "decode_str": "sent"} -{"id": 8759, "token": "creen", "merges": "cre en", "raw_count": 27457, "count": 704749, "decode_str": "creen"} -{"id": 45443, "token": "]['", "merges": "] ['", "raw_count": 705527, "count": 705527, "decode_str": "]['"} -{"id": 2328, "token": "\u0120dom", "merges": "\u0120d om", "raw_count": 50481, "count": 705937, "decode_str": " dom"} -{"id": 51805, "token": "\u00e6\u0127\u00b5", "merges": "\u00e6\u0127 \u00b5", "raw_count": 705941, "count": 705941, "decode_str": "\u6175"} -{"id": 2595, "token": "ground", "merges": "gr ound", "raw_count": 165740, "count": 706102, "decode_str": "ground"} -{"id": 52860, "token": "\u00e7\u0132\u00b5", "merges": "\u00e7\u0132 \u00b5", "raw_count": 706625, "count": 706625, "decode_str": "\u7435"} -{"id": 3511, "token": "\u0120hot", "merges": "\u0120h ot", "raw_count": 114212, "count": 707159, "decode_str": " hot"} -{"id": 1989, "token": "But", "merges": "B ut", "raw_count": 165132, "count": 707268, "decode_str": "But"} -{"id": 14191, "token": "Tw", "merges": "T w", "raw_count": 145466, "count": 707608, "decode_str": "Tw"} -{"id": 5351, "token": "ails", "merges": "ail s", "raw_count": 169311, "count": 707679, "decode_str": "ails"} -{"id": 34525, "token": "CNN", "merges": "C NN", "raw_count": 707712, "count": 707712, "decode_str": "CNN"} -{"id": 8052, "token": "adding", "merges": "add ing", "raw_count": 33505, "count": 707807, "decode_str": "adding"} -{"id": 12348, "token": "TTP", "merges": "TT P", "raw_count": 11905, "count": 707889, "decode_str": "TTP"} -{"id": 50428, "token": "\u00e4\u00b8\u00b6", "merges": "\u00e4\u00b8 \u00b6", "raw_count": 708041, "count": 708041, "decode_str": "\u4e36"} -{"id": 919, "token": "\u0120sur", "merges": "\u0120s ur", "raw_count": 58266, "count": 708322, "decode_str": " sur"} -{"id": 3646, "token": "\u0120policy", "merges": "\u0120pol icy", "raw_count": 708324, "count": 708324, "decode_str": " policy"} -{"id": 2149, "token": "ored", "merges": "ore d", "raw_count": 259974, "count": 708328, "decode_str": "ored"} -{"id": 22093, "token": "Word", "merges": "W ord", "raw_count": 708564, "count": 708564, "decode_str": "Word"} -{"id": 17015, "token": "131", "merges": "13 1", "raw_count": 708602, "count": 708602, "decode_str": "131"} -{"id": 15352, "token": "record", "merges": "rec ord", "raw_count": 694630, "count": 708663, "decode_str": "record"} -{"id": 2780, "token": "\u0120ut", "merges": "\u0120 ut", "raw_count": 337054, "count": 709159, "decode_str": " ut"} -{"id": 53626, "token": "\u00e8\u012c\u00ae", "merges": "\u00e8\u012c \u00ae", "raw_count": 709474, "count": 709474, "decode_str": "\u82ae"} -{"id": 19286, "token": "models", "merges": "mod els", "raw_count": 709730, "count": 709730, "decode_str": "models"} -{"id": 3518, "token": "actions", "merges": "a ctions", "raw_count": 579897, "count": 709879, "decode_str": "actions"} -{"id": 596, "token": "\u0120Th", "merges": "\u0120T h", "raw_count": 42592, "count": 709972, "decode_str": " Th"} -{"id": 12492, "token": "irectory", "merges": "irect ory", "raw_count": 9883, "count": 710099, "decode_str": "irectory"} -{"id": 1635, "token": "\u0120addition", "merges": "\u0120add ition", "raw_count": 332484, "count": 710105, "decode_str": " addition"} -{"id": 10994, "token": "metric", "merges": "met ric", "raw_count": 337615, "count": 710153, "decode_str": "metric"} -{"id": 15781, "token": "204", "merges": "20 4", "raw_count": 710280, "count": 710280, "decode_str": "204"} -{"id": 4522, "token": "\u0120tim", "merges": "\u0120t im", "raw_count": 192397, "count": 710312, "decode_str": " tim"} -{"id": 51532, "token": "\u00e5\u00b8\u013d", "merges": "\u00e5\u00b8 \u013d", "raw_count": 710808, "count": 710808, "decode_str": "\u5e1b"} -{"id": 6177, "token": ")?", "merges": ") ?", "raw_count": 711021, "count": 711021, "decode_str": ")?"} -{"id": 743, "token": "\u0120An", "merges": "\u0120A n", "raw_count": 181601, "count": 711343, "decode_str": " An"} -{"id": 16198, "token": "156", "merges": "15 6", "raw_count": 711570, "count": 711570, "decode_str": "156"} -{"id": 3434, "token": "\u0120effort", "merges": "\u0120eff ort", "raw_count": 126547, "count": 711733, "decode_str": " effort"} -{"id": 14531, "token": "ialize", "merges": "ial ize", "raw_count": 156946, "count": 712015, "decode_str": "ialize"} -{"id": 2120, "token": "\u0120full", "merges": "\u0120f ull", "raw_count": 712322, "count": 712322, "decode_str": " full"} -{"id": 2105, "token": "\u0120cost", "merges": "\u0120c ost", "raw_count": 440220, "count": 712560, "decode_str": " cost"} -{"id": 14390, "token": "\u0120parse", "merges": "\u0120par se", "raw_count": 712703, "count": 712703, "decode_str": " parse"} -{"id": 9762, "token": "\u0120requests", "merges": "\u0120request s", "raw_count": 712998, "count": 712998, "decode_str": " requests"} -{"id": 1293, "token": "\u0120without", "merges": "\u0120with out", "raw_count": 713703, "count": 713703, "decode_str": " without"} -{"id": 52830, "token": "\u00e7\u0131\u0140", "merges": "\u00e7\u0131 \u0140", "raw_count": 713715, "count": 713715, "decode_str": "\u73de"} -{"id": 53427, "token": "\u00e7\u00be\u0136", "merges": "\u00e7\u00be \u0136", "raw_count": 713906, "count": 713906, "decode_str": "\u7f94"} -{"id": 13121, "token": "stop", "merges": "st op", "raw_count": 714224, "count": 714224, "decode_str": "stop"} -{"id": 2273, "token": "\u0120fore", "merges": "\u0120f ore", "raw_count": 44081, "count": 714344, "decode_str": " fore"} -{"id": 13517, "token": "domain", "merges": "dom ain", "raw_count": 714743, "count": 714743, "decode_str": "domain"} -{"id": 52602, "token": "\u00e6\u00b6\u0130", "merges": "\u00e6\u00b6 \u0130", "raw_count": 715228, "count": 715228, "decode_str": "\u6d8e"} -{"id": 5300, "token": "\u0120resources", "merges": "\u0120res ources", "raw_count": 715418, "count": 715418, "decode_str": " resources"} -{"id": 1146, "token": "\u0120being", "merges": "\u0120be ing", "raw_count": 715758, "count": 715758, "decode_str": " being"} -{"id": 52768, "token": "\u00e7\u012a\u00bb", "merges": "\u00e7\u012a \u00bb", "raw_count": 716208, "count": 716208, "decode_str": "\u723b"} -{"id": 10394, "token": "system", "merges": "s ystem", "raw_count": 678990, "count": 716222, "decode_str": "system"} -{"id": 4966, "token": "ATE", "merges": "AT E", "raw_count": 273410, "count": 716286, "decode_str": "ATE"} -{"id": 28647, "token": "MAC", "merges": "M AC", "raw_count": 716295, "count": 716295, "decode_str": "MAC"} -{"id": 23139, "token": "370", "merges": "37 0", "raw_count": 716384, "count": 716384, "decode_str": "370"} -{"id": 6901, "token": "TS", "merges": "T S", "raw_count": 692203, "count": 716983, "decode_str": "TS"} -{"id": 4330, "token": "ener", "merges": "en er", "raw_count": 112077, "count": 717227, "decode_str": "ener"} -{"id": 20238, "token": "handler", "merges": "hand ler", "raw_count": 717229, "count": 717229, "decode_str": "handler"} -{"id": 7316, "token": "\u0120query", "merges": "\u0120qu ery", "raw_count": 717406, "count": 717406, "decode_str": " query"} -{"id": 24594, "token": "feature", "merges": "fe ature", "raw_count": 717650, "count": 717650, "decode_str": "feature"} -{"id": 3424, "token": "++", "merges": "+ +", "raw_count": 525114, "count": 718380, "decode_str": "++"} -{"id": 53837, "token": "\u00e8\u00af\u00ac", "merges": "\u00e8\u00af \u00ac", "raw_count": 718687, "count": 718687, "decode_str": "\u8bec"} -{"id": 6453, "token": "RS", "merges": "R S", "raw_count": 718560, "count": 719201, "decode_str": "RS"} -{"id": 1389, "token": "\u00d0\u00b8", "merges": "\u00d0 \u00b8", "raw_count": 99740, "count": 719462, "decode_str": "\u0438"} -{"id": 1107, "token": "\u0120years", "merges": "\u0120year s", "raw_count": 719909, "count": 719909, "decode_str": " years"} -{"id": 10812, "token": "dest", "merges": "d est", "raw_count": 349784, "count": 719968, "decode_str": "dest"} -{"id": 2079, "token": "ressed", "merges": "ress ed", "raw_count": 123302, "count": 720107, "decode_str": "ressed"} -{"id": 3230, "token": "ana", "merges": "an a", "raw_count": 711583, "count": 720441, "decode_str": "ana"} -{"id": 1651, "token": "chool", "merges": "ch ool", "raw_count": 41966, "count": 720498, "decode_str": "chool"} -{"id": 1817, "token": "ird", "merges": "ir d", "raw_count": 106616, "count": 720543, "decode_str": "ird"} -{"id": 5321, "token": "\u0120save", "merges": "\u0120sa ve", "raw_count": 721259, "count": 721259, "decode_str": " save"} -{"id": 53082, "token": "\u00e7\u00a1\u00bc", "merges": "\u00e7\u00a1 \u00bc", "raw_count": 721472, "count": 721472, "decode_str": "\u787c"} -{"id": 11972, "token": "thread", "merges": "th read", "raw_count": 571600, "count": 721895, "decode_str": "thread"} -{"id": 5672, "token": "true", "merges": "tr ue", "raw_count": 721928, "count": 721928, "decode_str": "true"} -{"id": 2292, "token": "ubl", "merges": "ub l", "raw_count": 79921, "count": 721966, "decode_str": "ubl"} -{"id": 1309, "token": "\u0120during", "merges": "\u0120d uring", "raw_count": 722005, "count": 722005, "decode_str": " during"} -{"id": 28476, "token": "1960", "merges": "19 60", "raw_count": 722044, "count": 722044, "decode_str": "1960"} -{"id": 10288, "token": "ariable", "merges": "ari able", "raw_count": 1902, "count": 722142, "decode_str": "ariable"} -{"id": 51770, "token": "\u00e6\u0125\u00a6", "merges": "\u00e6\u0125 \u00a6", "raw_count": 722581, "count": 722581, "decode_str": "\u60e6"} -{"id": 16691, "token": "general", "merges": "gen eral", "raw_count": 723181, "count": 723181, "decode_str": "general"} -{"id": 8491, "token": "fit", "merges": "f it", "raw_count": 651328, "count": 723414, "decode_str": "fit"} -{"id": 52502, "token": "\u00e6\u00b2\u0135", "merges": "\u00e6\u00b2 \u0135", "raw_count": 723863, "count": 723863, "decode_str": "\u6c93"} -{"id": 54614, "token": "\u00ef\u00bc\u0142", "merges": "\u00ef\u00bc \u0142", "raw_count": 724416, "count": 724416, "decode_str": " "} -{"id": 7796, "token": "\u0120assembly", "merges": "\u0120as sembly", "raw_count": 724621, "count": 724621, "decode_str": " assembly"} -{"id": 54519, "token": "\u00e9\u00ab\u0127", "merges": "\u00e9\u00ab \u0127", "raw_count": 724621, "count": 724621, "decode_str": "\u9ac5"} -{"id": 3454, "token": "mary", "merges": "m ary", "raw_count": 41975, "count": 724641, "decode_str": "mary"} -{"id": 3098, "token": "\u0120eff", "merges": "\u0120e ff", "raw_count": 13502, "count": 725390, "decode_str": " eff"} -{"id": 1669, "token": "\u0120left", "merges": "\u0120le ft", "raw_count": 725585, "count": 725585, "decode_str": " left"} -{"id": 8412, "token": "display", "merges": "dis play", "raw_count": 725330, "count": 726319, "decode_str": "display"} -{"id": 54515, "token": "\u00e9\u00aa\u00b7", "merges": "\u00e9\u00aa \u00b7", "raw_count": 726367, "count": 726367, "decode_str": "\u9ab7"} -{"id": 2813, "token": "\u0120device", "merges": "\u0120dev ice", "raw_count": 726524, "count": 726524, "decode_str": " device"} -{"id": 5688, "token": "lication", "merges": "lic ation", "raw_count": 2102, "count": 726664, "decode_str": "lication"} -{"id": 3522, "token": "\u0120date", "merges": "\u0120d ate", "raw_count": 726938, "count": 726938, "decode_str": " date"} -{"id": 50600, "token": "\u00e4\u00bf\u0133", "merges": "\u00e4\u00bf \u0133", "raw_count": 726939, "count": 726939, "decode_str": "\u4fd1"} -{"id": 3109, "token": "ender", "merges": "end er", "raw_count": 181441, "count": 727271, "decode_str": "ender"} -{"id": 9815, "token": "second", "merges": "se cond", "raw_count": 394286, "count": 727696, "decode_str": "second"} -{"id": 6194, "token": "\u0120train", "merges": "\u0120tra in", "raw_count": 672068, "count": 727707, "decode_str": " train"} -{"id": 3495, "token": "\u012023", "merges": "\u01202 3", "raw_count": 727807, "count": 727807, "decode_str": " 23"} -{"id": 3213, "token": "\u0120step", "merges": "\u0120st ep", "raw_count": 727812, "count": 727812, "decode_str": " step"} -{"id": 1270, "token": "\u0120great", "merges": "\u0120g reat", "raw_count": 392860, "count": 727878, "decode_str": " great"} -{"id": 1924, "token": "\u0120record", "merges": "\u0120rec ord", "raw_count": 480682, "count": 727894, "decode_str": " record"} -{"id": 52093, "token": "\u00e6\u0138\u013d", "merges": "\u00e6\u0138 \u013d", "raw_count": 728421, "count": 728421, "decode_str": "\u659b"} -{"id": 2232, "token": "\u0120ele", "merges": "\u0120e le", "raw_count": 72966, "count": 728579, "decode_str": " ele"} -{"id": 1367, "token": "\u00d1\u0124", "merges": "\u00d1 \u0124", "raw_count": 83359, "count": 728749, "decode_str": "\u0442"} -{"id": 18121, "token": "163", "merges": "16 3", "raw_count": 728835, "count": 728835, "decode_str": "163"} -{"id": 7559, "token": "Ge", "merges": "G e", "raw_count": 410339, "count": 728868, "decode_str": "Ge"} -{"id": 18428, "token": "network", "merges": "net work", "raw_count": 728986, "count": 728986, "decode_str": "network"} -{"id": 2913, "token": "year", "merges": "y ear", "raw_count": 667379, "count": 728992, "decode_str": "year"} -{"id": 22986, "token": "RF", "merges": "R F", "raw_count": 729472, "count": 729472, "decode_str": "RF"} -{"id": 53737, "token": "\u00e8\u00a3\u013a", "merges": "\u00e8\u00a3 \u013a", "raw_count": 729697, "count": 729697, "decode_str": "\u88d8"} -{"id": 17312, "token": "cv", "merges": "c v", "raw_count": 729898, "count": 729898, "decode_str": "cv"} -{"id": 28581, "token": "316", "merges": "3 16", "raw_count": 730149, "count": 730149, "decode_str": "316"} -{"id": 15468, "token": "134", "merges": "13 4", "raw_count": 730236, "count": 730236, "decode_str": "134"} -{"id": 10989, "token": "TD", "merges": "T D", "raw_count": 721884, "count": 730615, "decode_str": "TD"} -{"id": 26687, "token": "folder", "merges": "f older", "raw_count": 730631, "count": 730631, "decode_str": "folder"} -{"id": 1685, "token": "\u0120bus", "merges": "\u0120b us", "raw_count": 118291, "count": 731060, "decode_str": " bus"} -{"id": 18284, "token": "_(", "merges": "_ (", "raw_count": 731293, "count": 731293, "decode_str": "_("} -{"id": 50653, "token": "\u00e5\u0124\u0122", "merges": "\u00e5\u0124 \u0122", "raw_count": 731414, "count": 731414, "decode_str": "\u5080"} -{"id": 52956, "token": "\u00e7\u013b\u0138", "merges": "\u00e7\u013b \u0138", "raw_count": 731596, "count": 731596, "decode_str": "\u7656"} -{"id": 2890, "token": "ties", "merges": "t ies", "raw_count": 13970, "count": 731837, "decode_str": "ties"} -{"id": 7084, "token": "SL", "merges": "S L", "raw_count": 707976, "count": 732056, "decode_str": "SL"} -{"id": 1489, "token": "urther", "merges": "ur ther", "raw_count": 532, "count": 732063, "decode_str": "urther"} -{"id": 14441, "token": "\u0120msg", "merges": "\u0120m sg", "raw_count": 726185, "count": 732092, "decode_str": " msg"} -{"id": 27095, "token": "windows", "merges": "w indows", "raw_count": 732165, "count": 732165, "decode_str": "windows"} -{"id": 6579, "token": "asks", "merges": "as ks", "raw_count": 159080, "count": 732820, "decode_str": "asks"} -{"id": 2392, "token": "ators", "merges": "at ors", "raw_count": 414782, "count": 732952, "decode_str": "ators"} -{"id": 5801, "token": "hi", "merges": "h i", "raw_count": 663342, "count": 733094, "decode_str": "hi"} -{"id": 12233, "token": "drop", "merges": "d rop", "raw_count": 707799, "count": 733294, "decode_str": "drop"} -{"id": 51590, "token": "\u00e5\u00bb\u00bf", "merges": "\u00e5 \u00bb\u00bf", "raw_count": 734547, "count": 734547, "decode_str": "\u5eff"} -{"id": 10136, "token": "tx", "merges": "t x", "raw_count": 455509, "count": 734581, "decode_str": "tx"} -{"id": 4323, "token": "\u0120management", "merges": "\u0120manag ement", "raw_count": 734837, "count": 734837, "decode_str": " management"} -{"id": 5281, "token": "\u0120shape", "merges": "\u0120sh ape", "raw_count": 735258, "count": 735258, "decode_str": " shape"} -{"id": 13518, "token": "meta", "merges": "m eta", "raw_count": 735327, "count": 735327, "decode_str": "meta"} -{"id": 1060, "token": "\u0120here", "merges": "\u0120he re", "raw_count": 699922, "count": 735388, "decode_str": " here"} -{"id": 11070, "token": "PG", "merges": "P G", "raw_count": 732683, "count": 735486, "decode_str": "PG"} -{"id": 26813, "token": "720", "merges": "7 20", "raw_count": 735850, "count": 735850, "decode_str": "720"} -{"id": 12196, "token": "\u0120('", "merges": "\u0120( '", "raw_count": 735883, "count": 735883, "decode_str": " ('"} -{"id": 8944, "token": "Sm", "merges": "S m", "raw_count": 157932, "count": 735987, "decode_str": "Sm"} -{"id": 1790, "token": "\u0120sit", "merges": "\u0120s it", "raw_count": 63633, "count": 736209, "decode_str": " sit"} -{"id": 31060, "token": "MV", "merges": "M V", "raw_count": 737138, "count": 737138, "decode_str": "MV"} -{"id": 2134, "token": "angle", "merges": "ang le", "raw_count": 600651, "count": 737545, "decode_str": "angle"} -{"id": 6028, "token": "UE", "merges": "U E", "raw_count": 398140, "count": 737658, "decode_str": "UE"} -{"id": 1211, "token": "\u0120own", "merges": "\u0120o wn", "raw_count": 447520, "count": 738125, "decode_str": " own"} -{"id": 3750, "token": "ius", "merges": "i us", "raw_count": 297809, "count": 738208, "decode_str": "ius"} -{"id": 1684, "token": "\u0120pop", "merges": "\u0120p op", "raw_count": 141795, "count": 738212, "decode_str": " pop"} -{"id": 2603, "token": "\u0120source", "merges": "\u0120s ource", "raw_count": 739399, "count": 739399, "decode_str": " source"} -{"id": 3474, "token": "const", "merges": "con st", "raw_count": 498625, "count": 739505, "decode_str": "const"} -{"id": 54621, "token": "\u00ef\u00bd\u013d", "merges": "\u00ef\u00bd \u013d", "raw_count": 739943, "count": 739943, "decode_str": " "} -{"id": 54622, "token": "\u00ef\u00bd\u013f", "merges": "\u00ef\u00bd \u013f", "raw_count": 740036, "count": 740036, "decode_str": " "} -{"id": 1243, "token": "ained", "merges": "ain ed", "raw_count": 62565, "count": 740200, "decode_str": "ained"} -{"id": 54239, "token": "\u00e9\u0136\u0143", "merges": "\u00e9\u0136 \u0143", "raw_count": 740583, "count": 740583, "decode_str": "\u952d"} -{"id": 4072, "token": "\u01202013", "merges": "\u0120201 3", "raw_count": 740621, "count": 740621, "decode_str": " 2013"} -{"id": 52245, "token": "\u00e6\u0140\u0143", "merges": "\u00e6\u0140 \u0143", "raw_count": 740835, "count": 740835, "decode_str": "\u67ad"} -{"id": 34417, "token": ":]", "merges": ": ]", "raw_count": 740869, "count": 740869, "decode_str": ":]"} -{"id": 50721, "token": "\u00e5\u0128\u00a2", "merges": "\u00e5\u0128 \u00a2", "raw_count": 741157, "count": 741157, "decode_str": "\u51a2"} -{"id": 54007, "token": "\u00e8\u00b7\u00b7", "merges": "\u00e8\u00b7 \u00b7", "raw_count": 741351, "count": 741351, "decode_str": "\u8df7"} -{"id": 7474, "token": "Message", "merges": "M essage", "raw_count": 741781, "count": 741781, "decode_str": "Message"} -{"id": 50825, "token": "\u00e5\u012c\u00be", "merges": "\u00e5\u012c \u00be", "raw_count": 741880, "count": 741880, "decode_str": "\u52be"} -{"id": 2485, "token": "ga", "merges": "g a", "raw_count": 562726, "count": 742112, "decode_str": "ga"} -{"id": 8600, "token": "\u0120render", "merges": "\u0120ren der", "raw_count": 710536, "count": 742424, "decode_str": " render"} -{"id": 2502, "token": "\u0120red", "merges": "\u0120re d", "raw_count": 333299, "count": 742778, "decode_str": " red"} -{"id": 3525, "token": "era", "merges": "er a", "raw_count": 261327, "count": 742939, "decode_str": "era"} -{"id": 8029, "token": "ributes", "merges": "ribut es", "raw_count": 14992, "count": 743109, "decode_str": "ributes"} -{"id": 52979, "token": "\u00e7\u013c\u00bf", "merges": "\u00e7\u013c \u00bf", "raw_count": 743130, "count": 743130, "decode_str": "\u76bf"} -{"id": 4115, "token": "eline", "merges": "el ine", "raw_count": 168058, "count": 743572, "decode_str": "eline"} -{"id": 5008, "token": "\u0120convention", "merges": "\u0120conv ention", "raw_count": 700135, "count": 743721, "decode_str": " convention"} -{"id": 3239, "token": "\u0120page", "merges": "\u0120p age", "raw_count": 743836, "count": 743836, "decode_str": " page"} -{"id": 4041, "token": "One", "merges": "O ne", "raw_count": 743878, "count": 743878, "decode_str": "One"} -{"id": 7510, "token": "Fe", "merges": "F e", "raw_count": 410882, "count": 744402, "decode_str": "Fe"} -{"id": 2037, "token": "ember", "merges": "em ber", "raw_count": 204079, "count": 745277, "decode_str": "ember"} -{"id": 2264, "token": "\u0120total", "merges": "\u0120tot al", "raw_count": 745294, "count": 745294, "decode_str": " total"} -{"id": 5032, "token": "\u0120]", "merges": "\u0120 ]", "raw_count": 742291, "count": 745856, "decode_str": " ]"} -{"id": 24384, "token": "\u00bb\u00bf", "merges": "\u00bb \u00bf", "raw_count": 10442, "count": 745925, "decode_str": "\ufffd\ufffd"} -{"id": 4752, "token": "cos", "merges": "c os", "raw_count": 694236, "count": 745974, "decode_str": "cos"} -{"id": 24224, "token": "embed", "merges": "em bed", "raw_count": 704778, "count": 745991, "decode_str": "embed"} -{"id": 6030, "token": "uffer", "merges": "uff er", "raw_count": 17856, "count": 746232, "decode_str": "uffer"} -{"id": 1818, "token": "\u0120change", "merges": "\u0120ch ange", "raw_count": 746555, "count": 746555, "decode_str": " change"} -{"id": 54624, "token": "\u00ef\u00bd\u0142", "merges": "\u00ef\u00bd \u0142", "raw_count": 746983, "count": 746983, "decode_str": " "} -{"id": 2278, "token": "\u0120review", "merges": "\u0120re view", "raw_count": 562303, "count": 747519, "decode_str": " review"} -{"id": 51184, "token": "\u00e5\u013e\u00a9", "merges": "\u00e5\u013e \u00a9", "raw_count": 747993, "count": 747993, "decode_str": "\u5729"} -{"id": 2189, "token": "side", "merges": "s ide", "raw_count": 401463, "count": 748037, "decode_str": "side"} -{"id": 54001, "token": "\u00e8\u00b7\u00a4", "merges": "\u00e8\u00b7 \u00a4", "raw_count": 748084, "count": 748084, "decode_str": "\u8de4"} -{"id": 1246, "token": "\u0120present", "merges": "\u0120pres ent", "raw_count": 510061, "count": 748334, "decode_str": " present"} -{"id": 15497, "token": "137", "merges": "13 7", "raw_count": 748811, "count": 748811, "decode_str": "137"} -{"id": 4826, "token": "style", "merges": "st yle", "raw_count": 747743, "count": 748935, "decode_str": "style"} -{"id": 50735, "token": "\u00e5\u0128\u00bd", "merges": "\u00e5\u0128 \u00bd", "raw_count": 749591, "count": 749591, "decode_str": "\u51bd"} -{"id": 753, "token": "\u0120said", "merges": "\u0120sa id", "raw_count": 749778, "count": 749778, "decode_str": " said"} -{"id": 2848, "token": "anguage", "merges": "angu age", "raw_count": 9343, "count": 750529, "decode_str": "anguage"} -{"id": 13485, "token": "images", "merges": "im ages", "raw_count": 750644, "count": 750644, "decode_str": "images"} -{"id": 6074, "token": "Info", "merges": "In fo", "raw_count": 750687, "count": 750687, "decode_str": "Info"} -{"id": 4368, "token": "ocol", "merges": "oc ol", "raw_count": 21217, "count": 751009, "decode_str": "ocol"} -{"id": 4059, "token": "\u01202014", "merges": "\u0120201 4", "raw_count": 751144, "count": 751144, "decode_str": " 2014"} -{"id": 54497, "token": "\u00e9\u00aa\u012d", "merges": "\u00e9\u00aa \u012d", "raw_count": 751388, "count": 751388, "decode_str": "\u9a8b"} -{"id": 2209, "token": "\u0120eng", "merges": "\u0120en g", "raw_count": 60527, "count": 752221, "decode_str": " eng"} -{"id": 9507, "token": "COM", "merges": "C OM", "raw_count": 616758, "count": 752288, "decode_str": "COM"} -{"id": 2978, "token": "\u0120length", "merges": "\u0120l ength", "raw_count": 690979, "count": 753300, "decode_str": " length"} -{"id": 53964, "token": "\u00e8\u00b5\u00a1", "merges": "\u00e8\u00b5 \u00a1", "raw_count": 753366, "count": 753366, "decode_str": "\u8d61"} -{"id": 6697, "token": "actory", "merges": "act ory", "raw_count": 26145, "count": 754391, "decode_str": "actory"} -{"id": 3220, "token": "My", "merges": "M y", "raw_count": 750342, "count": 754723, "decode_str": "My"} -{"id": 2230, "token": "mission", "merges": "m ission", "raw_count": 265866, "count": 755084, "decode_str": "mission"} -{"id": 1046, "token": "\u0120every", "merges": "\u0120e very", "raw_count": 476798, "count": 755272, "decode_str": " every"} -{"id": 5530, "token": "soft", "merges": "so ft", "raw_count": 329991, "count": 755480, "decode_str": "soft"} -{"id": 1947, "token": "ung", "merges": "un g", "raw_count": 559139, "count": 755507, "decode_str": "ung"} -{"id": 9782, "token": "\u0120ng", "merges": "\u0120n g", "raw_count": 755701, "count": 755701, "decode_str": " ng"} -{"id": 11779, "token": "MAX", "merges": "MA X", "raw_count": 755961, "count": 755961, "decode_str": "MAX"} -{"id": 11296, "token": "sql", "merges": "s ql", "raw_count": 712242, "count": 755975, "decode_str": "sql"} -{"id": 43518, "token": "2800", "merges": "28 00", "raw_count": 756131, "count": 756131, "decode_str": "2800"} -{"id": 9387, "token": "Pa", "merges": "P a", "raw_count": 437222, "count": 756158, "decode_str": "Pa"} -{"id": 4332, "token": "\u01202011", "merges": "\u0120201 1", "raw_count": 756260, "count": 756260, "decode_str": " 2011"} -{"id": 52938, "token": "\u00e7\u0139\u0140", "merges": "\u00e7\u0139 \u0140", "raw_count": 756517, "count": 756517, "decode_str": "\u75de"} -{"id": 1388, "token": "\u0120day", "merges": "\u0120d ay", "raw_count": 747597, "count": 756630, "decode_str": " day"} -{"id": 3903, "token": "anch", "merges": "an ch", "raw_count": 187516, "count": 756865, "decode_str": "anch"} -{"id": 8500, "token": "ao", "merges": "a o", "raw_count": 756115, "count": 757090, "decode_str": "ao"} -{"id": 4083, "token": "\u0120financ", "merges": "\u0120fin anc", "raw_count": 3112, "count": 757120, "decode_str": " financ"} -{"id": 6553, "token": "draw", "merges": "d raw", "raw_count": 678186, "count": 757140, "decode_str": "draw"} -{"id": 1290, "token": "\u0120poss", "merges": "\u0120pos s", "raw_count": 16383, "count": 758017, "decode_str": " poss"} -{"id": 5367, "token": "po", "merges": "p o", "raw_count": 613078, "count": 759007, "decode_str": "po"} -{"id": 7536, "token": "Box", "merges": "B ox", "raw_count": 698609, "count": 759149, "decode_str": "Box"} -{"id": 2370, "token": "ories", "merges": "or ies", "raw_count": 146751, "count": 759552, "decode_str": "ories"} -{"id": 1798, "token": "\u0120particular", "merges": "\u0120partic ular", "raw_count": 492598, "count": 759637, "decode_str": " particular"} -{"id": 14380, "token": "133", "merges": "13 3", "raw_count": 759730, "count": 759730, "decode_str": "133"} -{"id": 52441, "token": "\u00e6\u00af\u00a1", "merges": "\u00e6\u00af \u00a1", "raw_count": 759755, "count": 759755, "decode_str": "\u6be1"} -{"id": 7414, "token": "MD", "merges": "M D", "raw_count": 750935, "count": 759763, "decode_str": "MD"} -{"id": 1561, "token": "\u0120within", "merges": "\u0120with in", "raw_count": 759926, "count": 759926, "decode_str": " within"} -{"id": 54298, "token": "\u00e9\u013a\u0133", "merges": "\u00e9\u013a \u0133", "raw_count": 760150, "count": 760150, "decode_str": "\u9611"} -{"id": 3818, "token": "\u0120recomm", "merges": "\u0120re comm", "raw_count": 4108, "count": 761070, "decode_str": " recomm"} -{"id": 3767, "token": "men", "merges": "m en", "raw_count": 257145, "count": 761943, "decode_str": "men"} -{"id": 53622, "token": "\u00e8\u012c\u00aa", "merges": "\u00e8\u012c \u00aa", "raw_count": 761954, "count": 761954, "decode_str": "\u82aa"} -{"id": 2107, "token": "ued", "merges": "u ed", "raw_count": 241329, "count": 762409, "decode_str": "ued"} -{"id": 15106, "token": "move", "merges": "m ove", "raw_count": 762497, "count": 762497, "decode_str": "move"} -{"id": 18161, "token": "202", "merges": "20 2", "raw_count": 762762, "count": 762762, "decode_str": "202"} -{"id": 51943, "token": "\u00e6\u012e\u013f", "merges": "\u00e6\u012e \u013f", "raw_count": 763216, "count": 763216, "decode_str": "\u631d"} -{"id": 4947, "token": "Class", "merges": "Cl ass", "raw_count": 721787, "count": 763820, "decode_str": "Class"} -{"id": 52428, "token": "\u00e6\u00af\u0124", "merges": "\u00e6\u00af \u0124", "raw_count": 763842, "count": 763842, "decode_str": "\u6bc2"} -{"id": 5188, "token": "\u0120lab", "merges": "\u0120l ab", "raw_count": 66966, "count": 764274, "decode_str": " lab"} -{"id": 53331, "token": "\u00e7\u00ba\u00be", "merges": "\u00e7\u00ba \u00be", "raw_count": 764341, "count": 764341, "decode_str": "\u7ebe"} -{"id": 799, "token": "\u0120stud", "merges": "\u0120st ud", "raw_count": 6286, "count": 764628, "decode_str": " stud"} -{"id": 2154, "token": "div", "merges": "d iv", "raw_count": 720296, "count": 764704, "decode_str": "div"} -{"id": 2356, "token": "cted", "merges": "ct ed", "raw_count": 101404, "count": 765100, "decode_str": "cted"} -{"id": 14819, "token": "Py", "merges": "P y", "raw_count": 244608, "count": 765854, "decode_str": "Py"} -{"id": 31111, "token": "1024", "merges": "10 24", "raw_count": 766199, "count": 766199, "decode_str": "1024"} -{"id": 1007, "token": "\u0120look", "merges": "\u0120l ook", "raw_count": 323760, "count": 766938, "decode_str": " look"} -{"id": 11022, "token": "pad", "merges": "p ad", "raw_count": 761356, "count": 767055, "decode_str": "pad"} -{"id": 2421, "token": "ony", "merges": "on y", "raw_count": 403076, "count": 767333, "decode_str": "ony"} -{"id": 5214, "token": "RA", "merges": "R A", "raw_count": 514732, "count": 767885, "decode_str": "RA"} -{"id": 15640, "token": "\u0120[\"", "merges": "\u0120[ \"", "raw_count": 767901, "count": 767901, "decode_str": " [\""} -{"id": 53788, "token": "\u00e8\u00ae\u00aa", "merges": "\u00e8\u00ae \u00aa", "raw_count": 767992, "count": 767992, "decode_str": "\u8baa"} -{"id": 8020, "token": "ji", "merges": "j i", "raw_count": 682523, "count": 768146, "decode_str": "ji"} -{"id": 5707, "token": "CON", "merges": "C ON", "raw_count": 275619, "count": 768215, "decode_str": "CON"} -{"id": 1462, "token": "\u0120stand", "merges": "\u0120st and", "raw_count": 96247, "count": 768255, "decode_str": " stand"} -{"id": 15024, "token": "resource", "merges": "res ource", "raw_count": 768378, "count": 768378, "decode_str": "resource"} -{"id": 1799, "token": "\u0120applic", "merges": "\u0120app lic", "raw_count": 2008, "count": 768553, "decode_str": " applic"} -{"id": 3099, "token": "miss", "merges": "m iss", "raw_count": 144238, "count": 768609, "decode_str": "miss"} -{"id": 4050, "token": "\u01202012", "merges": "\u0120201 2", "raw_count": 768931, "count": 768931, "decode_str": " 2012"} -{"id": 3091, "token": "\u0120shall", "merges": "\u0120sh all", "raw_count": 754100, "count": 769219, "decode_str": " shall"} -{"id": 10252, "token": "Red", "merges": "R ed", "raw_count": 662278, "count": 769333, "decode_str": "Red"} -{"id": 5230, "token": "\u0120root", "merges": "\u0120ro ot", "raw_count": 770252, "count": 770252, "decode_str": " root"} -{"id": 1645, "token": "\u0120rece", "merges": "\u0120re ce", "raw_count": 26486, "count": 770650, "decode_str": " rece"} -{"id": 14517, "token": ".(", "merges": ". (", "raw_count": 770763, "count": 770763, "decode_str": ".("} -{"id": 3869, "token": "orks", "merges": "or ks", "raw_count": 7777, "count": 771036, "decode_str": "orks"} -{"id": 6320, "token": "normal", "merges": "n ormal", "raw_count": 762625, "count": 771042, "decode_str": "normal"} -{"id": 16763, "token": "205", "merges": "20 5", "raw_count": 771369, "count": 771369, "decode_str": "205"} -{"id": 1887, "token": "oor", "merges": "o or", "raw_count": 167333, "count": 771452, "decode_str": "oor"} -{"id": 4881, "token": "oto", "merges": "ot o", "raw_count": 413377, "count": 771867, "decode_str": "oto"} -{"id": 3614, "token": "https", "merges": "htt ps", "raw_count": 772192, "count": 772192, "decode_str": "https"} -{"id": 8904, "token": "DB", "merges": "D B", "raw_count": 764399, "count": 772323, "decode_str": "DB"} -{"id": 2782, "token": "\u0120concer", "merges": "\u0120con cer", "raw_count": 122, "count": 772345, "decode_str": " concer"} -{"id": 3295, "token": "\u0120color", "merges": "\u0120col or", "raw_count": 759279, "count": 772876, "decode_str": " color"} -{"id": 12850, "token": "norm", "merges": "n orm", "raw_count": 771508, "count": 773823, "decode_str": "norm"} -{"id": 52435, "token": "\u00e6\u00af\u0135", "merges": "\u00e6\u00af \u0135", "raw_count": 773892, "count": 773892, "decode_str": "\u6bd3"} -{"id": 19569, "token": "310", "merges": "3 10", "raw_count": 773943, "count": 773943, "decode_str": "310"} -{"id": 23764, "token": "\u0120img", "merges": "\u0120im g", "raw_count": 774427, "count": 774427, "decode_str": " img"} -{"id": 9878, "token": "river", "merges": "ri ver", "raw_count": 53185, "count": 774540, "decode_str": "river"} -{"id": 5072, "token": "Me", "merges": "M e", "raw_count": 607966, "count": 774881, "decode_str": "Me"} -{"id": 4805, "token": "bin", "merges": "b in", "raw_count": 701379, "count": 775340, "decode_str": "bin"} -{"id": 1460, "token": "\u0120pur", "merges": "\u0120p ur", "raw_count": 30552, "count": 775713, "decode_str": " pur"} -{"id": 1175, "token": "\u0120good", "merges": "\u0120go od", "raw_count": 592833, "count": 775738, "decode_str": " good"} -{"id": 7941, "token": "BR", "merges": "B R", "raw_count": 775888, "count": 775888, "decode_str": "BR"} -{"id": 11969, "token": "equal", "merges": "equ al", "raw_count": 766802, "count": 775922, "decode_str": "equal"} -{"id": 8497, "token": "Note", "merges": "N ote", "raw_count": 776279, "count": 776279, "decode_str": "Note"} -{"id": 3152, "token": "Wh", "merges": "W h", "raw_count": 541419, "count": 776873, "decode_str": "Wh"} -{"id": 6764, "token": "FR", "merges": "F R", "raw_count": 649764, "count": 776888, "decode_str": "FR"} -{"id": 14477, "token": "connection", "merges": "conne ction", "raw_count": 776946, "count": 776946, "decode_str": "connection"} -{"id": 16717, "token": "149", "merges": "14 9", "raw_count": 777142, "count": 777142, "decode_str": "149"} -{"id": 25950, "token": "encode", "merges": "enc ode", "raw_count": 777242, "count": 777242, "decode_str": "encode"} -{"id": 5038, "token": "ayout", "merges": "ay out", "raw_count": 22400, "count": 777294, "decode_str": "ayout"} -{"id": 54084, "token": "\u00e8\u00bf\u00a5", "merges": "\u00e8\u00bf \u00a5", "raw_count": 777806, "count": 777806, "decode_str": "\u8fe5"} -{"id": 11546, "token": "full", "merges": "f ull", "raw_count": 778101, "count": 778101, "decode_str": "full"} -{"id": 3737, "token": "ica", "merges": "ic a", "raw_count": 747568, "count": 778403, "decode_str": "ica"} -{"id": 8883, "token": "ayers", "merges": "ay ers", "raw_count": 45941, "count": 778655, "decode_str": "ayers"} -{"id": 54465, "token": "\u00e9\u00a3\u0135", "merges": "\u00e9\u00a3 \u0135", "raw_count": 778861, "count": 778861, "decode_str": "\u98d3"} -{"id": 4476, "token": "Des", "merges": "D es", "raw_count": 254585, "count": 779351, "decode_str": "Des"} -{"id": 1575, "token": "orn", "merges": "or n", "raw_count": 250994, "count": 779777, "decode_str": "orn"} -{"id": 18833, "token": "utils", "merges": "ut ils", "raw_count": 779894, "count": 779894, "decode_str": "utils"} -{"id": 5273, "token": "sembly", "merges": "semb ly", "raw_count": 207, "count": 780073, "decode_str": "sembly"} -{"id": 53215, "token": "\u00e7\u00ac\u0142", "merges": "\u00e7\u00ac \u0142", "raw_count": 780140, "count": 780140, "decode_str": "\u7b20"} -{"id": 2108, "token": "ours", "merges": "our s", "raw_count": 264512, "count": 780307, "decode_str": "ours"} -{"id": 6189, "token": "Trans", "merges": "Tr ans", "raw_count": 381302, "count": 781076, "decode_str": "Trans"} -{"id": 52754, "token": "\u00e7\u0126\u00af", "merges": "\u00e7\u0126 \u00af", "raw_count": 781223, "count": 781223, "decode_str": "\u712f"} -{"id": 20070, "token": "178", "merges": "17 8", "raw_count": 781328, "count": 781328, "decode_str": "178"} -{"id": 2344, "token": "\u0120fac", "merges": "\u0120f ac", "raw_count": 29989, "count": 781393, "decode_str": " fac"} -{"id": 1483, "token": "itive", "merges": "it ive", "raw_count": 104106, "count": 781465, "decode_str": "itive"} -{"id": 13521, "token": "\u0120programme", "merges": "\u0120program me", "raw_count": 781804, "count": 781804, "decode_str": " programme"} -{"id": 53164, "token": "\u00e7\u00a7\u00bd", "merges": "\u00e7\u00a7 \u00bd", "raw_count": 781819, "count": 781819, "decode_str": "\u79fd"} -{"id": 9481, "token": "leep", "merges": "le ep", "raw_count": 28608, "count": 782434, "decode_str": "leep"} -{"id": 5981, "token": "\u0120format", "merges": "\u0120form at", "raw_count": 756069, "count": 783144, "decode_str": " format"} -{"id": 14633, "token": "GM", "merges": "G M", "raw_count": 783274, "count": 783274, "decode_str": "GM"} -{"id": 10669, "token": "\u0120token", "merges": "\u0120to ken", "raw_count": 783358, "count": 783358, "decode_str": " token"} -{"id": 53907, "token": "\u00e8\u00b2\u0124", "merges": "\u00e8\u00b2 \u0124", "raw_count": 783410, "count": 783410, "decode_str": "\u8c82"} -{"id": 3360, "token": "utions", "merges": "ut ions", "raw_count": 64046, "count": 783483, "decode_str": "utions"} -{"id": 1629, "token": "\u0120sk", "merges": "\u0120s k", "raw_count": 166519, "count": 783683, "decode_str": " sk"} -{"id": 2085, "token": "\u0120provide", "merges": "\u0120prov ide", "raw_count": 784105, "count": 784105, "decode_str": " provide"} -{"id": 3557, "token": "icon", "merges": "ic on", "raw_count": 638488, "count": 784317, "decode_str": "icon"} -{"id": 16320, "token": "Intern", "merges": "In tern", "raw_count": 15885, "count": 784513, "decode_str": "Intern"} -{"id": 53141, "token": "\u00e7\u00a6\u00ba", "merges": "\u00e7\u00a6 \u00ba", "raw_count": 784641, "count": 784641, "decode_str": "\u79ba"} -{"id": 17880, "token": "utf", "merges": "ut f", "raw_count": 784784, "count": 784784, "decode_str": "utf"} -{"id": 2098, "token": "\u0120plan", "merges": "\u0120pl an", "raw_count": 447722, "count": 784864, "decode_str": " plan"} -{"id": 4241, "token": "Object", "merges": "O bject", "raw_count": 709855, "count": 785294, "decode_str": "Object"} -{"id": 4305, "token": "js", "merges": "j s", "raw_count": 785147, "count": 785908, "decode_str": "js"} -{"id": 4123, "token": "la", "merges": "l a", "raw_count": 690410, "count": 785955, "decode_str": "la"} -{"id": 2075, "token": "\u0120pay", "merges": "\u0120p ay", "raw_count": 284320, "count": 786050, "decode_str": " pay"} -{"id": 52737, "token": "\u00e7\u0124\u00af", "merges": "\u00e7\u0124 \u00af", "raw_count": 786186, "count": 786186, "decode_str": "\u70af"} -{"id": 1548, "token": "\u0120ident", "merges": "\u0120 ident", "raw_count": 32614, "count": 786673, "decode_str": " ident"} -{"id": 5475, "token": "Item", "merges": "It em", "raw_count": 765199, "count": 787436, "decode_str": "Item"} -{"id": 2751, "token": "imum", "merges": "im um", "raw_count": 15772, "count": 787919, "decode_str": "imum"} -{"id": 1053, "token": "\u0120don", "merges": "\u0120d on", "raw_count": 592757, "count": 788184, "decode_str": " don"} -{"id": 3733, "token": "\u0120training", "merges": "\u0120tra ining", "raw_count": 788365, "count": 788365, "decode_str": " training"} -{"id": 11030, "token": "Param", "merges": "Par am", "raw_count": 124590, "count": 788512, "decode_str": "Param"} -{"id": 3642, "token": "lin", "merges": "l in", "raw_count": 554224, "count": 788607, "decode_str": "lin"} -{"id": 10239, "token": "\u0120cooper", "merges": "\u0120co oper", "raw_count": 42613, "count": 789162, "decode_str": " cooper"} -{"id": 9431, "token": "NC", "merges": "N C", "raw_count": 789654, "count": 789654, "decode_str": "NC"} -{"id": 1776, "token": "aining", "merges": "ain ing", "raw_count": 144551, "count": 789909, "decode_str": "aining"} -{"id": 4712, "token": "\u0120activities", "merges": "\u0120activ ities", "raw_count": 790412, "count": 790412, "decode_str": " activities"} -{"id": 7527, "token": "scale", "merges": "sc ale", "raw_count": 790908, "count": 790908, "decode_str": "scale"} -{"id": 9270, "token": "Frame", "merges": "Fr ame", "raw_count": 759060, "count": 790935, "decode_str": "Frame"} -{"id": 3017, "token": "ols", "merges": "ol s", "raw_count": 118331, "count": 791170, "decode_str": "ols"} -{"id": 21980, "token": "480", "merges": "4 80", "raw_count": 791515, "count": 791515, "decode_str": "480"} -{"id": 1581, "token": "\u0120allow", "merges": "\u0120all ow", "raw_count": 341152, "count": 791738, "decode_str": " allow"} -{"id": 1693, "token": "\u0120rele", "merges": "\u0120re le", "raw_count": 5021, "count": 791878, "decode_str": " rele"} -{"id": 7530, "token": "ugin", "merges": "ug in", "raw_count": 3637, "count": 791994, "decode_str": "ugin"} -{"id": 15445, "token": "prefix", "merges": "pref ix", "raw_count": 792104, "count": 792104, "decode_str": "prefix"} -{"id": 52970, "token": "\u00e7\u013c\u012d", "merges": "\u00e7\u013c \u012d", "raw_count": 792483, "count": 792483, "decode_str": "\u768b"} -{"id": 36193, "token": "logging", "merges": "log ging", "raw_count": 792638, "count": 792638, "decode_str": "logging"} -{"id": 2530, "token": "\u0120provided", "merges": "\u0120prov ided", "raw_count": 792750, "count": 792750, "decode_str": " provided"} -{"id": 2177, "token": "\u0120vi", "merges": "\u0120v i", "raw_count": 132211, "count": 793114, "decode_str": " vi"} -{"id": 1834, "token": "ended", "merges": "end ed", "raw_count": 132333, "count": 793256, "decode_str": "ended"} -{"id": 16903, "token": "198", "merges": "19 8", "raw_count": 794692, "count": 794692, "decode_str": "198"} -{"id": 2888, "token": ")*", "merges": ") *", "raw_count": 707232, "count": 794708, "decode_str": ")*"} -{"id": 4156, "token": "\u0120global", "merges": "\u0120gl obal", "raw_count": 794796, "count": 794796, "decode_str": " global"} -{"id": 29200, "token": "?\u00e2\u0122\u013b", "merges": "? \u00e2\u0122\u013b", "raw_count": 794840, "count": 794840, "decode_str": "?\u2019"} -{"id": 3167, "token": "\u0120host", "merges": "\u0120h ost", "raw_count": 653635, "count": 796115, "decode_str": " host"} -{"id": 1567, "token": "ived", "merges": "iv ed", "raw_count": 76759, "count": 796140, "decode_str": "ived"} -{"id": 6565, "token": "ords", "merges": "ord s", "raw_count": 415962, "count": 796188, "decode_str": "ords"} -{"id": 51762, "token": "\u00e6\u0125\u012d", "merges": "\u00e6\u0125 \u012d", "raw_count": 797141, "count": 797141, "decode_str": "\u60cb"} -{"id": 2613, "token": "\u0120base", "merges": "\u0120b ase", "raw_count": 789668, "count": 797584, "decode_str": " base"} -{"id": 2669, "token": "\u0120agre", "merges": "\u0120ag re", "raw_count": 457, "count": 797812, "decode_str": " agre"} -{"id": 1551, "token": "\u0120rest", "merges": "\u0120re st", "raw_count": 227225, "count": 797858, "decode_str": " rest"} -{"id": 15364, "token": "estamp", "merges": "est amp", "raw_count": 49811, "count": 798391, "decode_str": "estamp"} -{"id": 19722, "token": "\u0120filename", "merges": "\u0120fil ename", "raw_count": 798464, "count": 798464, "decode_str": " filename"} -{"id": 37731, "token": ":)", "merges": ": )", "raw_count": 798690, "count": 798690, "decode_str": ":)"} -{"id": 1862, "token": "elta", "merges": "el ta", "raw_count": 274109, "count": 798972, "decode_str": "elta"} -{"id": 6357, "token": "ca", "merges": "c a", "raw_count": 799319, "count": 799319, "decode_str": "ca"} -{"id": 5054, "token": "\u0120economic", "merges": "\u0120econom ic", "raw_count": 799419, "count": 799419, "decode_str": " economic"} -{"id": 8887, "token": "CV", "merges": "C V", "raw_count": 799742, "count": 800013, "decode_str": "CV"} -{"id": 8022, "token": "PI", "merges": "P I", "raw_count": 778190, "count": 800124, "decode_str": "PI"} -{"id": 12042, "token": "bot", "merges": "b ot", "raw_count": 800235, "count": 800235, "decode_str": "bot"} -{"id": 53784, "token": "\u00e8\u00ae\u00a5", "merges": "\u00e8\u00ae \u00a5", "raw_count": 800306, "count": 800306, "decode_str": "\u8ba5"} -{"id": 5529, "token": "UM", "merges": "U M", "raw_count": 483854, "count": 800515, "decode_str": "UM"} -{"id": 53667, "token": "\u00e8\u0130\u013a", "merges": "\u00e8\u0130 \u013a", "raw_count": 800602, "count": 800602, "decode_str": "\u8398"} -{"id": 15787, "token": "admin", "merges": "ad min", "raw_count": 801071, "count": 801071, "decode_str": "admin"} -{"id": 9244, "token": "Su", "merges": "S u", "raw_count": 156155, "count": 801149, "decode_str": "Su"} -{"id": 24058, "token": "argument", "merges": "arg ument", "raw_count": 801282, "count": 801282, "decode_str": "argument"} -{"id": 6330, "token": "\u0120peace", "merges": "\u0120pe ace", "raw_count": 703075, "count": 801595, "decode_str": " peace"} -{"id": 6549, "token": "real", "merges": "re al", "raw_count": 791110, "count": 802887, "decode_str": "real"} -{"id": 54391, "token": "\u00e9\u013e\u0135", "merges": "\u00e9\u013e \u0135", "raw_count": 803216, "count": 803216, "decode_str": "\u9713"} -{"id": 4367, "token": "\u0120files", "merges": "\u0120fil es", "raw_count": 776223, "count": 804099, "decode_str": " files"} -{"id": 10600, "token": "obs", "merges": "ob s", "raw_count": 585927, "count": 804221, "decode_str": "obs"} -{"id": 9715, "token": "URL", "merges": "UR L", "raw_count": 803789, "count": 804230, "decode_str": "URL"} -{"id": 10531, "token": "element", "merges": "e lement", "raw_count": 804397, "count": 804397, "decode_str": "element"} -{"id": 53105, "token": "\u00e7\u00a4\u00b4", "merges": "\u00e7\u00a4 \u00b4", "raw_count": 804468, "count": 804468, "decode_str": "\u7934"} -{"id": 2715, "token": "\u0120version", "merges": "\u0120vers ion", "raw_count": 804626, "count": 804626, "decode_str": " version"} -{"id": 4438, "token": "\u0120mode", "merges": "\u0120mod e", "raw_count": 804670, "count": 804670, "decode_str": " mode"} -{"id": 52478, "token": "\u00e6\u00b1\u0140", "merges": "\u00e6\u00b1 \u0140", "raw_count": 804915, "count": 804915, "decode_str": "\u6c5e"} -{"id": 1579, "token": "\u0120lim", "merges": "\u0120l im", "raw_count": 42080, "count": 804936, "decode_str": " lim"} -{"id": 4393, "token": "semb", "merges": "se mb", "raw_count": 2467, "count": 805258, "decode_str": "semb"} -{"id": 53240, "token": "\u00e7\u00ae\u012f", "merges": "\u00e7\u00ae \u012f", "raw_count": 805372, "count": 805372, "decode_str": "\u7b8d"} -{"id": 2675, "token": "\u0120social", "merges": "\u0120s ocial", "raw_count": 774384, "count": 805583, "decode_str": " social"} -{"id": 25107, "token": ".\")", "merges": ".\" )", "raw_count": 805794, "count": 805794, "decode_str": ".\")"} -{"id": 971, "token": "\u0120want", "merges": "\u0120w ant", "raw_count": 631551, "count": 806129, "decode_str": " want"} -{"id": 3126, "token": "\u0120environment", "merges": "\u0120en vironment", "raw_count": 556399, "count": 806632, "decode_str": " environment"} -{"id": 6155, "token": "Config", "merges": "Con fig", "raw_count": 670845, "count": 806756, "decode_str": "Config"} -{"id": 52861, "token": "\u00e7\u0132\u00b6", "merges": "\u00e7\u0132 \u00b6", "raw_count": 806757, "count": 806757, "decode_str": "\u7436"} -{"id": 2205, "token": "ley", "merges": "le y", "raw_count": 722700, "count": 807229, "decode_str": "ley"} -{"id": 9604, "token": "Response", "merges": "Res ponse", "raw_count": 807477, "count": 807477, "decode_str": "Response"} -{"id": 52962, "token": "\u00e7\u013b\u00b8", "merges": "\u00e7\u013b \u00b8", "raw_count": 808241, "count": 808241, "decode_str": "\u7678"} -{"id": 52076, "token": "\u00e6\u0137\u013f", "merges": "\u00e6\u0137 \u013f", "raw_count": 808596, "count": 808596, "decode_str": "\u655d"} -{"id": 38592, "token": "Dict", "merges": "D ict", "raw_count": 809244, "count": 809244, "decode_str": "Dict"} -{"id": 6690, "token": "ialog", "merges": "ial og", "raw_count": 24003, "count": 809896, "decode_str": "ialog"} -{"id": 3938, "token": "unk", "merges": "un k", "raw_count": 238090, "count": 809914, "decode_str": "unk"} -{"id": 51710, "token": "\u00e6\u0123\u0125", "merges": "\u00e6\u0123 \u0125", "raw_count": 809963, "count": 809963, "decode_str": "\u6043"} -{"id": 6665, "token": "ync", "merges": "yn c", "raw_count": 89128, "count": 810278, "decode_str": "ync"} -{"id": 23580, "token": "315", "merges": "3 15", "raw_count": 810585, "count": 810585, "decode_str": "315"} -{"id": 1946, "token": "ending", "merges": "end ing", "raw_count": 267938, "count": 810811, "decode_str": "ending"} -{"id": 4421, "token": "cap", "merges": "c ap", "raw_count": 517529, "count": 811326, "decode_str": "cap"} -{"id": 28259, "token": "VS", "merges": "V S", "raw_count": 811332, "count": 811332, "decode_str": "VS"} -{"id": 871, "token": "\u0120know", "merges": "\u0120kn ow", "raw_count": 526596, "count": 811585, "decode_str": " know"} -{"id": 3925, "token": "\u012060", "merges": "\u01206 0", "raw_count": 812609, "count": 812609, "decode_str": " 60"} -{"id": 50608, "token": "\u00e4\u00bf\u00aa", "merges": "\u00e4\u00bf \u00aa", "raw_count": 812750, "count": 812750, "decode_str": "\u4fea"} -{"id": 54111, "token": "\u00e9\u0122\u0140", "merges": "\u00e9\u0122 \u0140", "raw_count": 813055, "count": 813055, "decode_str": "\u901e"} -{"id": 52882, "token": "\u00e7\u0136\u00ba", "merges": "\u00e7\u0136 \u00ba", "raw_count": 813062, "count": 813062, "decode_str": "\u753a"} -{"id": 51168, "token": "\u00e5\u013d\u00b1", "merges": "\u00e5\u013d \u00b1", "raw_count": 813687, "count": 813687, "decode_str": "\u56f1"} -{"id": 6217, "token": "GR", "merges": "G R", "raw_count": 655257, "count": 814286, "decode_str": "GR"} -{"id": 6060, "token": "Index", "merges": "In dex", "raw_count": 810606, "count": 814492, "decode_str": "Index"} -{"id": 14546, "token": "CN", "merges": "C N", "raw_count": 814534, "count": 814534, "decode_str": "CN"} -{"id": 53720, "token": "\u00e8\u00a2\u0127", "merges": "\u00e8\u00a2 \u0127", "raw_count": 814544, "count": 814544, "decode_str": "\u8885"} -{"id": 17809, "token": "169", "merges": "16 9", "raw_count": 814816, "count": 814816, "decode_str": "169"} -{"id": 53385, "token": "\u00e7\u00bc\u0130", "merges": "\u00e7\u00bc \u0130", "raw_count": 815730, "count": 815730, "decode_str": "\u7f0e"} -{"id": 2130, "token": "\u0120available", "merges": "\u0120avail able", "raw_count": 815853, "count": 815853, "decode_str": " available"} -{"id": 10172, "token": "BB", "merges": "B B", "raw_count": 814669, "count": 816030, "decode_str": "BB"} -{"id": 1882, "token": "pped", "merges": "pp ed", "raw_count": 274451, "count": 816102, "decode_str": "pped"} -{"id": 3703, "token": "oe", "merges": "o e", "raw_count": 619013, "count": 816371, "decode_str": "oe"} -{"id": 976, "token": "uch", "merges": "u ch", "raw_count": 140785, "count": 816742, "decode_str": "uch"} -{"id": 13031, "token": "\u0120mock", "merges": "\u0120m ock", "raw_count": 812003, "count": 816775, "decode_str": " mock"} -{"id": 4442, "token": "oding", "merges": "od ing", "raw_count": 49919, "count": 817069, "decode_str": "oding"} -{"id": 4267, "token": "\u01202010", "merges": "\u0120201 0", "raw_count": 817138, "count": 817138, "decode_str": " 2010"} -{"id": 7229, "token": "xml", "merges": "x ml", "raw_count": 817252, "count": 817288, "decode_str": "xml"} -{"id": 7844, "token": "\u0120axis", "merges": "\u0120ax is", "raw_count": 817469, "count": 817469, "decode_str": " axis"} -{"id": 1980, "token": "\u0120local", "merges": "\u0120loc al", "raw_count": 783006, "count": 817487, "decode_str": " local"} -{"id": 52059, "token": "\u00e6\u0136\u013a", "merges": "\u00e6\u0136 \u013a", "raw_count": 818332, "count": 818332, "decode_str": "\u6518"} -{"id": 54196, "token": "\u00e9\u0127\u00a3", "merges": "\u00e9\u0127 \u00a3", "raw_count": 818863, "count": 818863, "decode_str": "\u9163"} -{"id": 5906, "token": "actor", "merges": "act or", "raw_count": 285781, "count": 818915, "decode_str": "actor"} -{"id": 52649, "token": "\u00e6\u00b7\u00bc", "merges": "\u00e6\u00b7 \u00bc", "raw_count": 819224, "count": 819224, "decode_str": "\u6dfc"} -{"id": 37044, "token": "1900", "merges": "19 00", "raw_count": 819582, "count": 819582, "decode_str": "1900"} -{"id": 1142, "token": "\u0120many", "merges": "\u0120man y", "raw_count": 820278, "count": 820278, "decode_str": " many"} -{"id": 22670, "token": "conn", "merges": "con n", "raw_count": 820327, "count": 820327, "decode_str": "conn"} -{"id": 11869, "token": "store", "merges": "st ore", "raw_count": 820471, "count": 820471, "decode_str": "store"} -{"id": 36377, "token": "datetime", "merges": "dat etime", "raw_count": 821114, "count": 821114, "decode_str": "datetime"} -{"id": 1552, "token": "This", "merges": "Th is", "raw_count": 821227, "count": 821227, "decode_str": "This"} -{"id": 1379, "token": "\u0120take", "merges": "\u0120t ake", "raw_count": 817608, "count": 821328, "decode_str": " take"} -{"id": 1931, "token": "\u0120tot", "merges": "\u0120to t", "raw_count": 49453, "count": 821666, "decode_str": " tot"} -{"id": 2374, "token": "On", "merges": "O n", "raw_count": 504320, "count": 821846, "decode_str": "On"} -{"id": 6247, "token": "\u01202019", "merges": "\u0120201 9", "raw_count": 822020, "count": 822020, "decode_str": " 2019"} -{"id": 54340, "token": "\u00e9\u013c\u0127", "merges": "\u00e9\u013c \u0127", "raw_count": 822335, "count": 822335, "decode_str": "\u9685"} -{"id": 2324, "token": "ores", "merges": "o res", "raw_count": 163984, "count": 822385, "decode_str": "ores"} -{"id": 51834, "token": "\u00e6\u012b\u012b", "merges": "\u00e6\u012b \u012b", "raw_count": 823216, "count": 823216, "decode_str": "\u6249"} -{"id": 13309, "token": ";&", "merges": "; &", "raw_count": 823250, "count": 823250, "decode_str": ";&"} -{"id": 2829, "token": "\u0120table", "merges": "\u0120t able", "raw_count": 807371, "count": 823837, "decode_str": " table"} -{"id": 4963, "token": "stream", "merges": "st ream", "raw_count": 754193, "count": 823887, "decode_str": "stream"} -{"id": 6998, "token": "Group", "merges": "Gr oup", "raw_count": 797895, "count": 824174, "decode_str": "Group"} -{"id": 6567, "token": ",-", "merges": ", -", "raw_count": 824807, "count": 824807, "decode_str": ",-"} -{"id": 10052, "token": "ictionary", "merges": "iction ary", "raw_count": 4506, "count": 825253, "decode_str": "ictionary"} -{"id": 3387, "token": "\u012040", "merges": "\u01204 0", "raw_count": 825373, "count": 825373, "decode_str": " 40"} -{"id": 5677, "token": "Out", "merges": "O ut", "raw_count": 446018, "count": 825729, "decode_str": "Out"} -{"id": 6678, "token": "sa", "merges": "s a", "raw_count": 554308, "count": 825947, "decode_str": "sa"} -{"id": 5267, "token": "dr", "merges": "d r", "raw_count": 609646, "count": 826333, "decode_str": "dr"} -{"id": 6825, "token": "Request", "merges": "Re quest", "raw_count": 826734, "count": 826734, "decode_str": "Request"} -{"id": 14571, "token": "seq", "merges": "se q", "raw_count": 827088, "count": 827088, "decode_str": "seq"} -{"id": 8159, "token": "pg", "merges": "p g", "raw_count": 364880, "count": 827466, "decode_str": "pg"} -{"id": 5792, "token": "lt", "merges": "l t", "raw_count": 658878, "count": 827888, "decode_str": "lt"} -{"id": 9104, "token": "010", "merges": "01 0", "raw_count": 828004, "count": 828004, "decode_str": "010"} -{"id": 1471, "token": "\u0120dem", "merges": "\u0120d em", "raw_count": 111444, "count": 828014, "decode_str": " dem"} -{"id": 1716, "token": "\u0120Con", "merges": "\u0120C on", "raw_count": 122992, "count": 828184, "decode_str": " Con"} -{"id": 5443, "token": "State", "merges": "St ate", "raw_count": 827873, "count": 829101, "decode_str": "State"} -{"id": 53428, "token": "\u00e7\u00be\u013c", "merges": "\u00e7\u00be \u013c", "raw_count": 829523, "count": 829523, "decode_str": "\u7f9a"} -{"id": 14399, "token": "auth", "merges": "aut h", "raw_count": 831003, "count": 831003, "decode_str": "auth"} -{"id": 50622, "token": "\u00e5\u0122\u0136", "merges": "\u00e5\u0122 \u0136", "raw_count": 832454, "count": 832454, "decode_str": "\u5014"} -{"id": 32522, "token": "1950", "merges": "19 50", "raw_count": 832586, "count": 832586, "decode_str": "1950"} -{"id": 54044, "token": "\u00e8\u00be\u012f", "merges": "\u00e8\u00be \u012f", "raw_count": 832772, "count": 832772, "decode_str": "\u8f8d"} -{"id": 1891, "token": "\u0120fail", "merges": "\u0120f ail", "raw_count": 163602, "count": 833366, "decode_str": " fail"} -{"id": 1174, "token": "\u0120exam", "merges": "\u0120ex am", "raw_count": 24165, "count": 833811, "decode_str": " exam"} -{"id": 14783, "token": "132", "merges": "13 2", "raw_count": 834362, "count": 834362, "decode_str": "132"} -{"id": 2151, "token": "\u0120children", "merges": "\u0120child ren", "raw_count": 834964, "count": 834964, "decode_str": " children"} -{"id": 45564, "token": "\"])", "merges": "\" ])", "raw_count": 835294, "count": 835294, "decode_str": "\"])"} -{"id": 970, "token": "\u0120using", "merges": "\u0120us ing", "raw_count": 835357, "count": 835357, "decode_str": " using"} -{"id": 7538, "token": "GE", "merges": "G E", "raw_count": 762702, "count": 835399, "decode_str": "GE"} -{"id": 18263, "token": "1981", "merges": "19 81", "raw_count": 835459, "count": 835459, "decode_str": "1981"} -{"id": 3191, "token": "ilities", "merges": "il ities", "raw_count": 57547, "count": 836111, "decode_str": "ilities"} -{"id": 972, "token": "ever", "merges": "e ver", "raw_count": 149525, "count": 836125, "decode_str": "ever"} -{"id": 6706, "token": "\u0120af", "merges": "\u0120a f", "raw_count": 829617, "count": 837290, "decode_str": " af"} -{"id": 15144, "token": "121", "merges": "12 1", "raw_count": 837533, "count": 837533, "decode_str": "121"} -{"id": 41770, "token": "yield", "merges": "y ield", "raw_count": 837761, "count": 837761, "decode_str": "yield"} -{"id": 22041, "token": "parameters", "merges": "param eters", "raw_count": 837912, "count": 837912, "decode_str": "parameters"} -{"id": 2346, "token": "sequ", "merges": "se qu", "raw_count": 37253, "count": 838682, "decode_str": "sequ"} -{"id": 5330, "token": "Exception", "merges": "Ex ception", "raw_count": 833824, "count": 838902, "decode_str": "Exception"} -{"id": 51667, "token": "\u00e5\u00bf\u0132", "merges": "\u00e5\u00bf \u0132", "raw_count": 838967, "count": 838967, "decode_str": "\u5fd0"} -{"id": 6633, "token": "reate", "merges": "re ate", "raw_count": 6983, "count": 839061, "decode_str": "reate"} -{"id": 14487, "token": "queue", "merges": "que ue", "raw_count": 839160, "count": 839160, "decode_str": "queue"} -{"id": 52040, "token": "\u00e6\u0134\u00ae", "merges": "\u00e6\u0134 \u00ae", "raw_count": 839193, "count": 839193, "decode_str": "\u64ae"} -{"id": 15078, "token": "\u0120''", "merges": "\u0120' '", "raw_count": 839277, "count": 839277, "decode_str": " ''"} -{"id": 50848, "token": "\u00e5\u012e\u0137", "merges": "\u00e5\u012e \u0137", "raw_count": 839513, "count": 839513, "decode_str": "\u5315"} -{"id": 51668, "token": "\u00e5\u00bf\u0133", "merges": "\u00e5\u00bf \u0133", "raw_count": 839885, "count": 839885, "decode_str": "\u5fd1"} -{"id": 3803, "token": "pper", "merges": "pp er", "raw_count": 313089, "count": 840055, "decode_str": "pper"} -{"id": 31517, "token": "idian", "merges": "id ian", "raw_count": 840177, "count": 840177, "decode_str": "idian"} -{"id": 34650, "token": "HK", "merges": "H K", "raw_count": 840345, "count": 840345, "decode_str": "HK"} -{"id": 53879, "token": "\u00e8\u00b0\u00a4", "merges": "\u00e8\u00b0 \u00a4", "raw_count": 840855, "count": 840855, "decode_str": "\u8c24"} -{"id": 53612, "token": "\u00e8\u012c\u012f", "merges": "\u00e8\u012c \u012f", "raw_count": 841206, "count": 841206, "decode_str": "\u828d"} -{"id": 52064, "token": "\u00e6\u0136\u00b8", "merges": "\u00e6\u0136 \u00b8", "raw_count": 841832, "count": 841832, "decode_str": "\u6538"} -{"id": 19568, "token": "235", "merges": "23 5", "raw_count": 842651, "count": 842651, "decode_str": "235"} -{"id": 6766, "token": "FI", "merges": "F I", "raw_count": 371305, "count": 842705, "decode_str": "FI"} -{"id": 49860, "token": "\u0120enumerate", "merges": "\u0120enum erate", "raw_count": 842923, "count": 842923, "decode_str": " enumerate"} -{"id": 3307, "token": "\u012022", "merges": "\u01202 2", "raw_count": 842969, "count": 842969, "decode_str": " 22"} -{"id": 2776, "token": "String", "merges": "St ring", "raw_count": 743281, "count": 843079, "decode_str": "String"} -{"id": 10008, "token": "description", "merges": "des cription", "raw_count": 843456, "count": 843456, "decode_str": "description"} -{"id": 3225, "token": "pri", "merges": "p ri", "raw_count": 116226, "count": 845089, "decode_str": "pri"} -{"id": 1398, "token": "\u0120desc", "merges": "\u0120des c", "raw_count": 152997, "count": 845763, "decode_str": " desc"} -{"id": 14849, "token": "cursor", "merges": "cur sor", "raw_count": 838786, "count": 845911, "decode_str": "cursor"} -{"id": 3761, "token": "\u0120match", "merges": "\u0120mat ch", "raw_count": 723003, "count": 846121, "decode_str": " match"} -{"id": 13362, "token": "hash", "merges": "h ash", "raw_count": 846434, "count": 846434, "decode_str": "hash"} -{"id": 4717, "token": "Add", "merges": "A dd", "raw_count": 498752, "count": 846511, "decode_str": "Add"} -{"id": 52809, "token": "\u00e7\u0130\u00a5", "merges": "\u00e7\u0130 \u00a5", "raw_count": 846746, "count": 846746, "decode_str": "\u73a5"} -{"id": 2477, "token": "enn", "merges": "en n", "raw_count": 358828, "count": 846749, "decode_str": "enn"} -{"id": 8119, "token": "\u0120commission", "merges": "\u0120comm ission", "raw_count": 706621, "count": 846988, "decode_str": " commission"} -{"id": 7614, "token": "src", "merges": "s rc", "raw_count": 847748, "count": 847748, "decode_str": "src"} -{"id": 1411, "token": "\u0120against", "merges": "\u0120again st", "raw_count": 848508, "count": 848508, "decode_str": " against"} -{"id": 845, "token": "\u0120diffe", "merges": "\u0120dif fe", "raw_count": 2544, "count": 849003, "decode_str": " diffe"} -{"id": 51194, "token": "\u00e5\u013f\u012f", "merges": "\u00e5\u013f \u012f", "raw_count": 850058, "count": 850058, "decode_str": "\u574d"} -{"id": 3923, "token": "\u0120command", "merges": "\u0120comm and", "raw_count": 796868, "count": 851056, "decode_str": " command"} -{"id": 52701, "token": "\u00e6\u00bc\u00aa", "merges": "\u00e6\u00bc \u00aa", "raw_count": 851100, "count": 851100, "decode_str": "\u6f2a"} -{"id": 51034, "token": "\u00e5\u0134\u00a4", "merges": "\u00e5\u0134 \u00a4", "raw_count": 851158, "count": 851158, "decode_str": "\u54a4"} -{"id": 8873, "token": "entry", "merges": "ent ry", "raw_count": 851181, "count": 851181, "decode_str": "entry"} -{"id": 1343, "token": "til", "merges": "t il", "raw_count": 154106, "count": 851744, "decode_str": "til"} -{"id": 15419, "token": "eval", "merges": "ev al", "raw_count": 698599, "count": 851849, "decode_str": "eval"} -{"id": 54348, "token": "\u00e9\u013c\u013a", "merges": "\u00e9\u013c \u013a", "raw_count": 851867, "count": 851867, "decode_str": "\u9698"} -{"id": 53271, "token": "\u00e7\u00b2\u00b1", "merges": "\u00e7\u00b2 \u00b1", "raw_count": 852078, "count": 852078, "decode_str": "\u7cb1"} -{"id": 13695, "token": "channel", "merges": "ch annel", "raw_count": 853552, "count": 853552, "decode_str": "channel"} -{"id": 1627, "token": "ackage", "merges": "ack age", "raw_count": 8598, "count": 853741, "decode_str": "ackage"} -{"id": 7509, "token": "product", "merges": "pro duct", "raw_count": 685541, "count": 854606, "decode_str": "product"} -{"id": 8528, "token": "VD", "merges": "V D", "raw_count": 841642, "count": 854926, "decode_str": "VD"} -{"id": 4104, "token": "\u01202015", "merges": "\u0120201 5", "raw_count": 854981, "count": 854981, "decode_str": " 2015"} -{"id": 15968, "token": "Return", "merges": "Ret urn", "raw_count": 855033, "count": 855033, "decode_str": "Return"} -{"id": 1825, "token": "aps", "merges": "ap s", "raw_count": 256440, "count": 855085, "decode_str": "aps"} -{"id": 1083, "token": "\u0120case", "merges": "\u0120c ase", "raw_count": 855151, "count": 855151, "decode_str": " case"} -{"id": 43824, "token": "inputs", "merges": "input s", "raw_count": 855414, "count": 855414, "decode_str": "inputs"} -{"id": 12428, "token": "location", "merges": "l ocation", "raw_count": 854172, "count": 855687, "decode_str": "location"} -{"id": 9684, "token": "Max", "merges": "M ax", "raw_count": 802677, "count": 855773, "decode_str": "Max"} -{"id": 1499, "token": "\u0120sl", "merges": "\u0120s l", "raw_count": 210925, "count": 856454, "decode_str": " sl"} -{"id": 20686, "token": "1970", "merges": "19 70", "raw_count": 858781, "count": 858781, "decode_str": "1970"} -{"id": 3665, "token": "\u0120frame", "merges": "\u0120fr ame", "raw_count": 483878, "count": 858861, "decode_str": " frame"} -{"id": 4807, "token": "Int", "merges": "In t", "raw_count": 820161, "count": 859229, "decode_str": "Int"} -{"id": 54479, "token": "\u00e9\u00a6\u012d", "merges": "\u00e9\u00a6 \u012d", "raw_count": 859369, "count": 859369, "decode_str": "\u998b"} -{"id": 51175, "token": "\u00e5\u013e\u0125", "merges": "\u00e5\u013e \u0125", "raw_count": 859823, "count": 859823, "decode_str": "\u5703"} -{"id": 1670, "token": "\u0120ve", "merges": "\u0120 ve", "raw_count": 87069, "count": 860073, "decode_str": " ve"} -{"id": 4699, "token": "002", "merges": "00 2", "raw_count": 860078, "count": 860078, "decode_str": "002"} -{"id": 52153, "token": "\u00e6\u013b\u012e", "merges": "\u00e6\u013b \u012e", "raw_count": 860228, "count": 860228, "decode_str": "\u664c"} -{"id": 1129, "token": "\u0120med", "merges": "\u0120m ed", "raw_count": 93980, "count": 860743, "decode_str": " med"} -{"id": 3696, "token": "kn", "merges": "k n", "raw_count": 283188, "count": 860933, "decode_str": "kn"} -{"id": 53436, "token": "\u00e7\u00be\u00af", "merges": "\u00e7\u00be \u00af", "raw_count": 861464, "count": 861464, "decode_str": "\u7faf"} -{"id": 10730, "token": "pool", "merges": "p ool", "raw_count": 861352, "count": 861611, "decode_str": "pool"} -{"id": 17455, "token": "job", "merges": "j ob", "raw_count": 861862, "count": 861862, "decode_str": "job"} -{"id": 779, "token": "\u0120him", "merges": "\u0120h im", "raw_count": 755269, "count": 861971, "decode_str": " him"} -{"id": 6844, "token": ")\"", "merges": ") \"", "raw_count": 862611, "count": 862611, "decode_str": ")\""} -{"id": 12110, "token": "foo", "merges": "f oo", "raw_count": 862774, "count": 862774, "decode_str": "foo"} -{"id": 1994, "token": "hy", "merges": "h y", "raw_count": 307486, "count": 862850, "decode_str": "hy"} -{"id": 52917, "token": "\u00e7\u0138\u00b1", "merges": "\u00e7\u0138 \u00b1", "raw_count": 863202, "count": 863202, "decode_str": "\u75b1"} -{"id": 923, "token": "\u0120see", "merges": "\u0120se e", "raw_count": 630890, "count": 863738, "decode_str": " see"} -{"id": 2214, "token": "For", "merges": "F or", "raw_count": 619069, "count": 863766, "decode_str": "For"} -{"id": 13935, "token": "RO", "merges": "R O", "raw_count": 727623, "count": 864518, "decode_str": "RO"} -{"id": 15793, "token": "account", "merges": "acc ount", "raw_count": 864888, "count": 864888, "decode_str": "account"} -{"id": 53260, "token": "\u00e7\u00b2\u0133", "merges": "\u00e7\u00b2 \u0133", "raw_count": 864935, "count": 864935, "decode_str": "\u7c91"} -{"id": 2855, "token": "struct", "merges": "st ruct", "raw_count": 228783, "count": 864987, "decode_str": "struct"} -{"id": 9961, "token": "mult", "merges": "m ult", "raw_count": 456881, "count": 865166, "decode_str": "mult"} -{"id": 26109, "token": "tensor", "merges": "t ensor", "raw_count": 865569, "count": 865569, "decode_str": "tensor"} -{"id": 4614, "token": "rad", "merges": "r ad", "raw_count": 415709, "count": 865919, "decode_str": "rad"} -{"id": 19469, "token": "Java", "merges": "J ava", "raw_count": 597880, "count": 865960, "decode_str": "Java"} -{"id": 16582, "token": "SK", "merges": "S K", "raw_count": 866007, "count": 866158, "decode_str": "SK"} -{"id": 53649, "token": "\u00e8\u012d\u0140", "merges": "\u00e8\u012d \u0140", "raw_count": 866609, "count": 866609, "decode_str": "\u82de"} -{"id": 2242, "token": "\u0120lay", "merges": "\u0120l ay", "raw_count": 51919, "count": 867164, "decode_str": " lay"} -{"id": 7955, "token": "dep", "merges": "d ep", "raw_count": 389636, "count": 867934, "decode_str": "dep"} -{"id": 54033, "token": "\u00e8\u00bd\u00bc", "merges": "\u00e8\u00bd \u00bc", "raw_count": 868266, "count": 868266, "decode_str": "\u8f7c"} -{"id": 11631, "token": "column", "merges": "col umn", "raw_count": 868732, "count": 869274, "decode_str": "column"} -{"id": 1543, "token": "\u0120results", "merges": "\u0120result s", "raw_count": 869381, "count": 869381, "decode_str": " results"} -{"id": 52656, "token": "\u00e6\u00b8\u0130", "merges": "\u00e6\u00b8 \u0130", "raw_count": 869414, "count": 869414, "decode_str": "\u6e0e"} -{"id": 52743, "token": "\u00e7\u0125\u00bd", "merges": "\u00e7 \u0125\u00bd", "raw_count": 869749, "count": 869749, "decode_str": "\u70fd"} -{"id": 7301, "token": "\u0120bool", "merges": "\u0120b ool", "raw_count": 869812, "count": 869812, "decode_str": " bool"} -{"id": 52177, "token": "\u00e6\u013d\u013e", "merges": "\u00e6\u013d \u013e", "raw_count": 870974, "count": 870974, "decode_str": "\u66dc"} -{"id": 3664, "token": "\";", "merges": "\" ;", "raw_count": 867881, "count": 871019, "decode_str": "\";"} -{"id": 15381, "token": "player", "merges": "play er", "raw_count": 868789, "count": 871489, "decode_str": "player"} -{"id": 12548, "token": "VC", "merges": "V C", "raw_count": 870842, "count": 871627, "decode_str": "VC"} -{"id": 14832, "token": "225", "merges": "2 25", "raw_count": 872106, "count": 872106, "decode_str": "225"} -{"id": 53454, "token": "\u00e8\u0122\u00a6", "merges": "\u00e8\u0122 \u00a6", "raw_count": 872168, "count": 872168, "decode_str": "\u8026"} -{"id": 2711, "token": "alt", "merges": "al t", "raw_count": 447492, "count": 872956, "decode_str": "alt"} -{"id": 52362, "token": "\u00e6\u00a7\u00bf", "merges": "\u00e6\u00a7 \u00bf", "raw_count": 873165, "count": 873165, "decode_str": "\u69ff"} -{"id": 5232, "token": "Form", "merges": "F orm", "raw_count": 552760, "count": 873499, "decode_str": "Form"} -{"id": 51742, "token": "\u00e6\u0124\u013c", "merges": "\u00e6\u0124 \u013c", "raw_count": 874415, "count": 874415, "decode_str": "\u609a"} -{"id": 1170, "token": "aking", "merges": "ak ing", "raw_count": 74304, "count": 875502, "decode_str": "aking"} -{"id": 7265, "token": "main", "merges": "m ain", "raw_count": 875785, "count": 875785, "decode_str": "main"} -{"id": 54128, "token": "\u00e9\u0123\u0132", "merges": "\u00e9\u0123 \u0132", "raw_count": 876371, "count": 876371, "decode_str": "\u9050"} -{"id": 53658, "token": "\u00e8\u012d\u00b7", "merges": "\u00e8\u012d \u00b7", "raw_count": 876384, "count": 876384, "decode_str": "\u82f7"} -{"id": 10565, "token": "axis", "merges": "ax is", "raw_count": 875814, "count": 876545, "decode_str": "axis"} -{"id": 3244, "token": "\u0120exec", "merges": "\u0120ex ec", "raw_count": 106621, "count": 877110, "decode_str": " exec"} -{"id": 1238, "token": "oid", "merges": "o id", "raw_count": 387964, "count": 877414, "decode_str": "oid"} -{"id": 50568, "token": "\u00e4\u00bd\u00b0", "merges": "\u00e4\u00bd \u00b0", "raw_count": 877550, "count": 877550, "decode_str": "\u4f70"} -{"id": 53882, "token": "\u00e8\u00b0\u00a7", "merges": "\u00e8\u00b0 \u00a7", "raw_count": 877574, "count": 877574, "decode_str": "\u8c27"} -{"id": 34368, "token": "']['", "merges": "'] ['", "raw_count": 878052, "count": 878052, "decode_str": "']['"} -{"id": 26451, "token": "nodes", "merges": "n odes", "raw_count": 878415, "count": 878415, "decode_str": "nodes"} -{"id": 2275, "token": "eb", "merges": "e b", "raw_count": 529306, "count": 878500, "decode_str": "eb"} -{"id": 7573, "token": "Te", "merges": "T e", "raw_count": 436675, "count": 878654, "decode_str": "Te"} -{"id": 51035, "token": "\u00e5\u0134\u00a6", "merges": "\u00e5\u0134 \u00a6", "raw_count": 878856, "count": 878856, "decode_str": "\u54a6"} -{"id": 4639, "token": "FL", "merges": "F L", "raw_count": 667895, "count": 879389, "decode_str": "FL"} -{"id": 9334, "token": "GT", "merges": "G T", "raw_count": 879769, "count": 879769, "decode_str": "GT"} -{"id": 921, "token": "\u0120show", "merges": "\u0120sh ow", "raw_count": 614810, "count": 879844, "decode_str": " show"} -{"id": 51818, "token": "\u00e6\u012a\u013d", "merges": "\u00e6\u012a \u013d", "raw_count": 880088, "count": 880088, "decode_str": "\u621b"} -{"id": 3866, "token": "script", "merges": "sc ript", "raw_count": 477495, "count": 880631, "decode_str": "script"} -{"id": 2586, "token": "\u0120country", "merges": "\u0120count ry", "raw_count": 871289, "count": 880887, "decode_str": " country"} -{"id": 2528, "token": "\u0120establ", "merges": "\u0120est abl", "raw_count": 187, "count": 881489, "decode_str": " establ"} -{"id": 1886, "token": "isk", "merges": "is k", "raw_count": 150687, "count": 881967, "decode_str": "isk"} -{"id": 15220, "token": "136", "merges": "13 6", "raw_count": 882287, "count": 882287, "decode_str": "136"} -{"id": 9679, "token": ")),", "merges": ") ),", "raw_count": 882971, "count": 882971, "decode_str": ")),"} -{"id": 7034, "token": "Aut", "merges": "A ut", "raw_count": 239012, "count": 883118, "decode_str": "Aut"} -{"id": 51406, "token": "\u00e5\u00ae\u0137", "merges": "\u00e5\u00ae \u0137", "raw_count": 884439, "count": 884439, "decode_str": "\u5b95"} -{"id": 52616, "token": "\u00e6\u00b6\u00a7", "merges": "\u00e6\u00b6 \u00a7", "raw_count": 884559, "count": 884559, "decode_str": "\u6da7"} -{"id": 1822, "token": "uro", "merges": "u ro", "raw_count": 145447, "count": 885474, "decode_str": "uro"} -{"id": 52603, "token": "\u00e6\u00b6\u0135", "merges": "\u00e6\u00b6 \u0135", "raw_count": 886130, "count": 886130, "decode_str": "\u6d93"} -{"id": 3686, "token": "\u0120sort", "merges": "\u0120s ort", "raw_count": 284194, "count": 886136, "decode_str": " sort"} -{"id": 1078, "token": "\u0120before", "merges": "\u0120be fore", "raw_count": 878918, "count": 886183, "decode_str": " before"} -{"id": 19390, "token": "exists", "merges": "ex ists", "raw_count": 886720, "count": 886720, "decode_str": "exists"} -{"id": 50561, "token": "\u00e4\u00bd\u00a2", "merges": "\u00e4\u00bd \u00a2", "raw_count": 886850, "count": 886850, "decode_str": "\u4f62"} -{"id": 2694, "token": "raft", "merges": "ra ft", "raw_count": 87123, "count": 886936, "decode_str": "raft"} -{"id": 15564, "token": "{}", "merges": "{ }", "raw_count": 887275, "count": 887275, "decode_str": "{}"} -{"id": 52146, "token": "\u00e6\u013a\u00b5", "merges": "\u00e6\u013a \u00b5", "raw_count": 887285, "count": 887285, "decode_str": "\u6635"} -{"id": 1734, "token": "ety", "merges": "et y", "raw_count": 82502, "count": 887434, "decode_str": "ety"} -{"id": 2196, "token": "ards", "merges": "ard s", "raw_count": 168720, "count": 888099, "decode_str": "ards"} -{"id": 2336, "token": "\u0120ver", "merges": "\u0120 ver", "raw_count": 155116, "count": 888510, "decode_str": " ver"} -{"id": 3996, "token": "Ed", "merges": "E d", "raw_count": 281152, "count": 888614, "decode_str": "Ed"} -{"id": 2600, "token": "\u0120content", "merges": "\u0120cont ent", "raw_count": 888126, "count": 888650, "decode_str": " content"} -{"id": 10946, "token": "offset", "merges": "off set", "raw_count": 888682, "count": 888682, "decode_str": "offset"} -{"id": 13686, "token": "window", "merges": "w indow", "raw_count": 888883, "count": 888883, "decode_str": "window"} -{"id": 51891, "token": "\u00e6\u012c\u00bf", "merges": "\u00e6\u012c \u00bf", "raw_count": 889492, "count": 889492, "decode_str": "\u62bf"} -{"id": 1013, "token": "--------------------------------", "merges": "---------------- ----------------", "raw_count": 7562, "count": 890407, "decode_str": "--------------------------------"} -{"id": 2488, "token": "\u0120author", "merges": "\u0120aut hor", "raw_count": 259163, "count": 890864, "decode_str": " author"} -{"id": 2784, "token": "pping", "merges": "pp ing", "raw_count": 312986, "count": 891833, "decode_str": "pping"} -{"id": 34857, "token": "\u00e2\u0122\u00a6\u00e2\u0122\u013f", "merges": "\u00e2\u0122\u00a6 \u00e2\u0122\u013f", "raw_count": 892036, "count": 892036, "decode_str": "\u2026\u201d"} -{"id": 15972, "token": "\u0120enum", "merges": "\u0120en um", "raw_count": 39855, "count": 892160, "decode_str": " enum"} -{"id": 5268, "token": "\u0120client", "merges": "\u0120cl ient", "raw_count": 892231, "count": 892231, "decode_str": " client"} -{"id": 5203, "token": "\u0120label", "merges": "\u0120l abel", "raw_count": 869298, "count": 892685, "decode_str": " label"} -{"id": 5063, "token": "abled", "merges": "ab led", "raw_count": 23611, "count": 893076, "decode_str": "abled"} -{"id": 1143, "token": "aint", "merges": "ain t", "raw_count": 103733, "count": 893082, "decode_str": "aint"} -{"id": 8625, "token": "vol", "merges": "v ol", "raw_count": 401175, "count": 894428, "decode_str": "vol"} -{"id": 10339, "token": "GS", "merges": "G S", "raw_count": 865131, "count": 894483, "decode_str": "GS"} -{"id": 52013, "token": "\u00e6\u0131\u012f", "merges": "\u00e6\u0131 \u012f", "raw_count": 895343, "count": 895343, "decode_str": "\u63cd"} -{"id": 6586, "token": "Image", "merges": "Im age", "raw_count": 892388, "count": 895369, "decode_str": "Image"} -{"id": 3994, "token": "\u0120ens", "merges": "\u0120en s", "raw_count": 7900, "count": 895405, "decode_str": " ens"} -{"id": 2767, "token": "inary", "merges": "in ary", "raw_count": 55123, "count": 895692, "decode_str": "inary"} -{"id": 1459, "token": "\u0120vari", "merges": "\u0120var i", "raw_count": 10180, "count": 896056, "decode_str": " vari"} -{"id": 1112, "token": "\u0120bel", "merges": "\u0120b el", "raw_count": 119348, "count": 896505, "decode_str": " bel"} -{"id": 2192, "token": "\u0120inf", "merges": "\u0120in f", "raw_count": 152485, "count": 896514, "decode_str": " inf"} -{"id": 50716, "token": "\u00e5\u0128\u0139", "merges": "\u00e5\u0128 \u0139", "raw_count": 897140, "count": 897140, "decode_str": "\u5197"} -{"id": 53705, "token": "\u00e8\u00a1\u00a2", "merges": "\u00e8\u00a1 \u00a2", "raw_count": 897252, "count": 897252, "decode_str": "\u8862"} -{"id": 9163, "token": "sche", "merges": "sc he", "raw_count": 43466, "count": 897800, "decode_str": "sche"} -{"id": 2487, "token": "ones", "merges": "on es", "raw_count": 607194, "count": 897964, "decode_str": "ones"} -{"id": 50854, "token": "\u00e5\u012e\u00a3", "merges": "\u00e5\u012e \u00a3", "raw_count": 898125, "count": 898125, "decode_str": "\u5323"} -{"id": 51741, "token": "\u00e6\u0124\u0138", "merges": "\u00e6\u0124 \u0138", "raw_count": 898582, "count": 898582, "decode_str": "\u6096"} -{"id": 51139, "token": "\u00e5\u013b\u0139", "merges": "\u00e5\u013b \u0139", "raw_count": 898807, "count": 898807, "decode_str": "\u5657"} -{"id": 36265, "token": "1958", "merges": "19 58", "raw_count": 898943, "count": 898943, "decode_str": "1958"} -{"id": 17554, "token": "rand", "merges": "r and", "raw_count": 899112, "count": 899112, "decode_str": "rand"} -{"id": 53286, "token": "\u00e7\u00b3\u013e", "merges": "\u00e7\u00b3 \u013e", "raw_count": 899338, "count": 899338, "decode_str": "\u7cdc"} -{"id": 4069, "token": "itter", "merges": "it ter", "raw_count": 139379, "count": 899530, "decode_str": "itter"} -{"id": 3701, "token": "function", "merges": "fun ction", "raw_count": 843602, "count": 899961, "decode_str": "function"} -{"id": 4423, "token": "orage", "merges": "or age", "raw_count": 11885, "count": 899994, "decode_str": "orage"} -{"id": 7239, "token": "\u0120py", "merges": "\u0120p y", "raw_count": 665702, "count": 900853, "decode_str": " py"} -{"id": 1427, "token": "ulation", "merges": "ul ation", "raw_count": 192412, "count": 900933, "decode_str": "ulation"} -{"id": 8586, "token": "oder", "merges": "od er", "raw_count": 90183, "count": 901462, "decode_str": "oder"} -{"id": 3159, "token": "\u0120word", "merges": "\u0120wor d", "raw_count": 887920, "count": 901886, "decode_str": " word"} -{"id": 6140, "token": "Pr", "merges": "P r", "raw_count": 313568, "count": 902173, "decode_str": "Pr"} -{"id": 50810, "token": "\u00e5\u012c\u012a", "merges": "\u00e5\u012c \u012a", "raw_count": 903236, "count": 903236, "decode_str": "\u5288"} -{"id": 1885, "token": "\u0120product", "merges": "\u0120produ ct", "raw_count": 456997, "count": 903449, "decode_str": " product"} -{"id": 7092, "token": "\u0120implementation", "merges": "\u0120implement ation", "raw_count": 903956, "count": 903956, "decode_str": " implementation"} -{"id": 7817, "token": "BU", "merges": "B U", "raw_count": 382246, "count": 904467, "decode_str": "BU"} -{"id": 2885, "token": "\u0120parent", "merges": "\u0120pa rent", "raw_count": 741701, "count": 904521, "decode_str": " parent"} -{"id": 2084, "token": "unt", "merges": "un t", "raw_count": 214491, "count": 904552, "decode_str": "unt"} -{"id": 7059, "token": "annels", "merges": "ann els", "raw_count": 37108, "count": 904554, "decode_str": "annels"} -{"id": 52529, "token": "\u00e6\u00b3\u0139", "merges": "\u00e6\u00b3 \u0139", "raw_count": 904754, "count": 904754, "decode_str": "\u6cd7"} -{"id": 13381, "token": "126", "merges": "12 6", "raw_count": 904958, "count": 904958, "decode_str": "126"} -{"id": 11063, "token": "Mark", "merges": "M ark", "raw_count": 693633, "count": 905663, "decode_str": "Mark"} -{"id": 958, "token": "\u0120fact", "merges": "\u0120f act", "raw_count": 282558, "count": 906197, "decode_str": " fact"} -{"id": 2063, "token": "\u0120pred", "merges": "\u0120p red", "raw_count": 273858, "count": 906541, "decode_str": " pred"} -{"id": 2804, "token": "ike", "merges": "i ke", "raw_count": 580483, "count": 907058, "decode_str": "ike"} -{"id": 53637, "token": "\u00e8\u012d\u0129", "merges": "\u00e8\u012d \u0129", "raw_count": 907372, "count": 907372, "decode_str": "\u82c7"} -{"id": 1233, "token": "\u0120prote", "merges": "\u0120pro te", "raw_count": 3478, "count": 907670, "decode_str": " prote"} -{"id": 10240, "token": "amples", "merges": "am ples", "raw_count": 22816, "count": 908161, "decode_str": "amples"} -{"id": 1899, "token": "\u0120position", "merges": "\u0120pos ition", "raw_count": 685052, "count": 908168, "decode_str": " position"} -{"id": 51436, "token": "\u00e5\u00af\u0132", "merges": "\u00e5\u00af \u0132", "raw_count": 908802, "count": 908802, "decode_str": "\u5bd0"} -{"id": 4297, "token": "gu", "merges": "g u", "raw_count": 590849, "count": 909958, "decode_str": "gu"} -{"id": 1554, "token": "\u0120mult", "merges": "\u0120m ult", "raw_count": 208633, "count": 910301, "decode_str": " mult"} -{"id": 5990, "token": "GL", "merges": "G L", "raw_count": 870847, "count": 911480, "decode_str": "GL"} -{"id": 6689, "token": "she", "merges": "s he", "raw_count": 496013, "count": 911492, "decode_str": "she"} -{"id": 53869, "token": "\u00e8\u00b0\u0137", "merges": "\u00e8\u00b0 \u0137", "raw_count": 911520, "count": 911520, "decode_str": "\u8c15"} -{"id": 25265, "token": "csv", "merges": "cs v", "raw_count": 911654, "count": 911654, "decode_str": "csv"} -{"id": 1436, "token": "\u0120person", "merges": "\u0120pers on", "raw_count": 400685, "count": 911934, "decode_str": " person"} -{"id": 1666, "token": "\u0120bas", "merges": "\u0120b as", "raw_count": 143364, "count": 912263, "decode_str": " bas"} -{"id": 1024, "token": "\u0120now", "merges": "\u0120n ow", "raw_count": 898912, "count": 912462, "decode_str": " now"} -{"id": 51681, "token": "\u00e5\u00bf\u00b1", "merges": "\u00e5\u00bf \u00b1", "raw_count": 912484, "count": 912484, "decode_str": "\u5ff1"} -{"id": 752, "token": "\u0120what", "merges": "\u0120wh at", "raw_count": 895935, "count": 912526, "decode_str": " what"} -{"id": 1935, "token": "ware", "merges": "w are", "raw_count": 447988, "count": 912852, "decode_str": "ware"} -{"id": 50860, "token": "\u00e5\u012e\u00be", "merges": "\u00e5\u012e \u00be", "raw_count": 913180, "count": 913180, "decode_str": "\u533e"} -{"id": 51419, "token": "\u00e5\u00ae\u00a6", "merges": "\u00e5\u00ae \u00a6", "raw_count": 913255, "count": 913255, "decode_str": "\u5ba6"} -{"id": 3992, "token": "cell", "merges": "c ell", "raw_count": 674358, "count": 913283, "decode_str": "cell"} -{"id": 1775, "token": "\u0120sam", "merges": "\u0120s am", "raw_count": 113885, "count": 913492, "decode_str": " sam"} -{"id": 2953, "token": "\u0120address", "merges": "\u0120add ress", "raw_count": 747543, "count": 913653, "decode_str": " address"} -{"id": 1528, "token": "ior", "merges": "i or", "raw_count": 440166, "count": 914154, "decode_str": "ior"} -{"id": 1226, "token": "ather", "merges": "at her", "raw_count": 170937, "count": 914429, "decode_str": "ather"} -{"id": 8601, "token": "rot", "merges": "ro t", "raw_count": 645028, "count": 914848, "decode_str": "rot"} -{"id": 4507, "token": "active", "merges": "act ive", "raw_count": 809071, "count": 914881, "decode_str": "active"} -{"id": 1141, "token": "\u0120incre", "merges": "\u0120in cre", "raw_count": 6865, "count": 914994, "decode_str": " incre"} -{"id": 4708, "token": "RT", "merges": "R T", "raw_count": 879385, "count": 915305, "decode_str": "RT"} -{"id": 16767, "token": "345", "merges": "34 5", "raw_count": 483819, "count": 915407, "decode_str": "345"} -{"id": 4193, "token": "bi", "merges": "b i", "raw_count": 501543, "count": 915738, "decode_str": "bi"} -{"id": 52805, "token": "\u00e7\u0130\u0138", "merges": "\u00e7\u0130 \u0138", "raw_count": 915763, "count": 915763, "decode_str": "\u7396"} -{"id": 52850, "token": "\u00e7\u0132\u00a5", "merges": "\u00e7\u0132 \u00a5", "raw_count": 915839, "count": 915839, "decode_str": "\u7425"} -{"id": 1704, "token": "sec", "merges": "se c", "raw_count": 406855, "count": 915848, "decode_str": "sec"} -{"id": 1463, "token": "\u0120proper", "merges": "\u0120pro per", "raw_count": 109602, "count": 916123, "decode_str": " proper"} -{"id": 1308, "token": "\u0120br", "merges": "\u0120b r", "raw_count": 187318, "count": 916305, "decode_str": " br"} -{"id": 1755, "token": "\u0120top", "merges": "\u0120to p", "raw_count": 620990, "count": 916396, "decode_str": " top"} -{"id": 32300, "token": ".\u00e2\u0122\u013e", "merges": ". \u00e2\u0122\u013e", "raw_count": 916915, "count": 916915, "decode_str": ".\u201c"} -{"id": 2851, "token": "td", "merges": "t d", "raw_count": 892593, "count": 916974, "decode_str": "td"} -{"id": 24070, "token": "330", "merges": "3 30", "raw_count": 917304, "count": 917304, "decode_str": "330"} -{"id": 1048, "token": "\u0120long", "merges": "\u0120l ong", "raw_count": 650316, "count": 917381, "decode_str": " long"} -{"id": 2368, "token": "uation", "merges": "u ation", "raw_count": 198817, "count": 917982, "decode_str": "uation"} -{"id": 1256, "token": "ression", "merges": "ress ion", "raw_count": 187003, "count": 918499, "decode_str": "ression"} -{"id": 51766, "token": "\u00e6\u0125\u013c", "merges": "\u00e6\u0125 \u013c", "raw_count": 918966, "count": 918966, "decode_str": "\u60da"} -{"id": 51019, "token": "\u00e5\u0134\u0128", "merges": "\u00e5\u0134 \u0128", "raw_count": 919162, "count": 919162, "decode_str": "\u5486"} -{"id": 840, "token": "\u0120then", "merges": "\u0120the n", "raw_count": 919396, "count": 919396, "decode_str": " then"} -{"id": 8632, "token": "dec", "merges": "de c", "raw_count": 655296, "count": 919507, "decode_str": "dec"} -{"id": 52550, "token": "\u00e6\u00b3\u00be", "merges": "\u00e6\u00b3 \u00be", "raw_count": 919997, "count": 919997, "decode_str": "\u6cfe"} -{"id": 54481, "token": "\u00e9\u00a6\u0131", "merges": "\u00e9\u00a6 \u0131", "raw_count": 920141, "count": 920141, "decode_str": "\u998f"} -{"id": 53809, "token": "\u00e8\u00af\u0127", "merges": "\u00e8\u00af \u0127", "raw_count": 920226, "count": 920226, "decode_str": "\u8bc5"} -{"id": 751, "token": "\u0120like", "merges": "\u0120li ke", "raw_count": 908616, "count": 920478, "decode_str": " like"} -{"id": 5245, "token": "\u0120coord", "merges": "\u0120co ord", "raw_count": 201800, "count": 921128, "decode_str": " coord"} -{"id": 5552, "token": "\u0120List", "merges": "\u0120L ist", "raw_count": 918214, "count": 921188, "decode_str": " List"} -{"id": 48257, "token": "\u0120nn", "merges": "\u0120n n", "raw_count": 921295, "count": 921295, "decode_str": " nn"} -{"id": 3317, "token": "\u0120dim", "merges": "\u0120d im", "raw_count": 563475, "count": 921559, "decode_str": " dim"} -{"id": 6104, "token": "Sp", "merges": "S p", "raw_count": 586860, "count": 921805, "decode_str": "Sp"} -{"id": 14351, "token": "122", "merges": "12 2", "raw_count": 921892, "count": 921892, "decode_str": "122"} -{"id": 51878, "token": "\u00e6\u012c\u0142", "merges": "\u00e6\u012c \u0142", "raw_count": 921893, "count": 921893, "decode_str": "\u62a0"} -{"id": 2116, "token": "ohn", "merges": "oh n", "raw_count": 106022, "count": 922205, "decode_str": "ohn"} -{"id": 13397, "token": "124", "merges": "12 4", "raw_count": 922456, "count": 922456, "decode_str": "124"} -{"id": 43201, "token": "1080", "merges": "10 80", "raw_count": 922599, "count": 922599, "decode_str": "1080"} -{"id": 2695, "token": "ops", "merges": "op s", "raw_count": 676886, "count": 922639, "decode_str": "ops"} -{"id": 2245, "token": "\u0120port", "merges": "\u0120p ort", "raw_count": 670272, "count": 923668, "decode_str": " port"} -{"id": 50949, "token": "\u00e5\u0131\u00bd", "merges": "\u00e5\u0131 \u00bd", "raw_count": 923871, "count": 923871, "decode_str": "\u53fd"} -{"id": 1860, "token": "plic", "merges": "pl ic", "raw_count": 186733, "count": 924200, "decode_str": "plic"} -{"id": 954, "token": "\u0120most", "merges": "\u0120m ost", "raw_count": 881439, "count": 924241, "decode_str": " most"} -{"id": 51220, "token": "\u00e5\u0140\u013d", "merges": "\u00e5\u0140 \u013d", "raw_count": 924242, "count": 924242, "decode_str": "\u579b"} -{"id": 1361, "token": "\u0120help", "merges": "\u0120hel p", "raw_count": 786895, "count": 924630, "decode_str": " help"} -{"id": 1820, "token": "reen", "merges": "re en", "raw_count": 36035, "count": 924965, "decode_str": "reen"} -{"id": 3412, "token": "bject", "merges": "b ject", "raw_count": 26687, "count": 925036, "decode_str": "bject"} -{"id": 2271, "token": "ique", "merges": "i que", "raw_count": 153369, "count": 925180, "decode_str": "ique"} -{"id": 14604, "token": "\u0120batch", "merges": "\u0120b atch", "raw_count": 925659, "count": 925659, "decode_str": " batch"} -{"id": 52725, "token": "\u00e7\u0124\u012c", "merges": "\u00e7\u0124 \u012c", "raw_count": 925708, "count": 925708, "decode_str": "\u708a"} -{"id": 17579, "token": "\u0120{\"", "merges": "\u0120{ \"", "raw_count": 925971, "count": 925971, "decode_str": " {\""} -{"id": 10606, "token": "','", "merges": "', '", "raw_count": 926143, "count": 926143, "decode_str": "','"} -{"id": 52198, "token": "\u00e6\u013e\u0143", "merges": "\u00e6\u013e \u0143", "raw_count": 926697, "count": 926697, "decode_str": "\u672d"} -{"id": 2255, "token": "\u0120women", "merges": "\u0120wom en", "raw_count": 926877, "count": 926877, "decode_str": " women"} -{"id": 2510, "token": "ges", "merges": "g es", "raw_count": 154445, "count": 927059, "decode_str": "ges"} -{"id": 1273, "token": "\u0120second", "merges": "\u0120se cond", "raw_count": 628293, "count": 927447, "decode_str": " second"} -{"id": 52316, "token": "\u00e6\u00a1\u00a8", "merges": "\u00e6\u00a1 \u00a8", "raw_count": 928067, "count": 928067, "decode_str": "\u6868"} -{"id": 16523, "token": "Args", "merges": "Ar gs", "raw_count": 921680, "count": 928292, "decode_str": "Args"} -{"id": 11113, "token": "pu", "merges": "p u", "raw_count": 529339, "count": 929270, "decode_str": "pu"} -{"id": 1724, "token": "\u0120cal", "merges": "\u0120c al", "raw_count": 160551, "count": 929899, "decode_str": " cal"} -{"id": 25674, "token": "continue", "merges": "contin ue", "raw_count": 930045, "count": 930045, "decode_str": "continue"} -{"id": 1888, "token": "\u0120vers", "merges": "\u0120 vers", "raw_count": 10360, "count": 930119, "decode_str": " vers"} -{"id": 1961, "token": "\u0120avail", "merges": "\u0120av ail", "raw_count": 23362, "count": 930143, "decode_str": " avail"} -{"id": 9473, "token": "||", "merges": "| |", "raw_count": 930344, "count": 930344, "decode_str": "||"} -{"id": 6159, "token": "BI", "merges": "B I", "raw_count": 899766, "count": 930666, "decode_str": "BI"} -{"id": 1110, "token": "\u0120those", "merges": "\u0120th ose", "raw_count": 930843, "count": 930843, "decode_str": " those"} -{"id": 7135, "token": "select", "merges": "se lect", "raw_count": 794491, "count": 931116, "decode_str": "select"} -{"id": 1345, "token": "\u0120public", "merges": "\u0120p ublic", "raw_count": 791759, "count": 932009, "decode_str": " public"} -{"id": 1502, "token": "ots", "merges": "ot s", "raw_count": 406458, "count": 932443, "decode_str": "ots"} -{"id": 13473, "token": "tor", "merges": "t or", "raw_count": 932381, "count": 932501, "decode_str": "tor"} -{"id": 2657, "token": "\u010a\u0109\u0109\u0109", "merges": "\u010a\u0109\u0109 \u0109", "raw_count": 932730, "count": 932730, "decode_str": "\n\t\t\t"} -{"id": 1272, "token": "ved", "merges": "v ed", "raw_count": 82399, "count": 933482, "decode_str": "ved"} -{"id": 51127, "token": "\u00e5\u0138\u00b1", "merges": "\u00e5\u0138 \u00b1", "raw_count": 933801, "count": 933801, "decode_str": "\u55b1"} -{"id": 18912, "token": "\u0120params", "merges": "\u0120par ams", "raw_count": 934264, "count": 934264, "decode_str": " params"} -{"id": 1510, "token": "\u0120meas", "merges": "\u0120me as", "raw_count": 11184, "count": 934933, "decode_str": " meas"} -{"id": 7585, "token": "web", "merges": "we b", "raw_count": 874624, "count": 935487, "decode_str": "web"} -{"id": 18647, "token": "1979", "merges": "19 79", "raw_count": 935668, "count": 935668, "decode_str": "1979"} -{"id": 12973, "token": "lower", "merges": "low er", "raw_count": 932867, "count": 935708, "decode_str": "lower"} -{"id": 12251, "token": "\u0120\"\"\"", "merges": "\u0120\"\" \"", "raw_count": 935932, "count": 935932, "decode_str": " \"\"\""} -{"id": 3878, "token": "pen", "merges": "p en", "raw_count": 205566, "count": 936274, "decode_str": "pen"} -{"id": 3632, "token": "\u0120random", "merges": "\u0120r andom", "raw_count": 894993, "count": 936925, "decode_str": " random"} -{"id": 53730, "token": "\u00e8\u00a2\u00b1", "merges": "\u00e8\u00a2 \u00b1", "raw_count": 937198, "count": 937198, "decode_str": "\u88b1"} -{"id": 53180, "token": "\u00e7\u00a8\u00bc", "merges": "\u00e7\u00a8 \u00bc", "raw_count": 937213, "count": 937213, "decode_str": "\u7a3c"} -{"id": 869, "token": "\u0120pat", "merges": "\u0120p at", "raw_count": 88251, "count": 937574, "decode_str": " pat"} -{"id": 24327, "token": "Air", "merges": "A ir", "raw_count": 938185, "count": 938185, "decode_str": "Air"} -{"id": 15069, "token": "fields", "merges": "field s", "raw_count": 938304, "count": 938304, "decode_str": "fields"} -{"id": 2824, "token": "ips", "merges": "ip s", "raw_count": 667517, "count": 938410, "decode_str": "ips"} -{"id": 1417, "token": "less", "merges": "l ess", "raw_count": 453178, "count": 938518, "decode_str": "less"} -{"id": 54410, "token": "\u00e9\u013f\u00b3", "merges": "\u00e9\u013f \u00b3", "raw_count": 938869, "count": 938869, "decode_str": "\u9773"} -{"id": 53830, "token": "\u00e8\u00af\u00a3", "merges": "\u00e8\u00af \u00a3", "raw_count": 939111, "count": 939111, "decode_str": "\u8be3"} -{"id": 17220, "token": "159", "merges": "15 9", "raw_count": 939318, "count": 939318, "decode_str": "159"} -{"id": 3816, "token": "\u0120ren", "merges": "\u0120re n", "raw_count": 96380, "count": 940092, "decode_str": " ren"} -{"id": 2706, "token": "ches", "merges": "c hes", "raw_count": 335377, "count": 940187, "decode_str": "ches"} -{"id": 2875, "token": "orld", "merges": "or ld", "raw_count": 25417, "count": 940499, "decode_str": "orld"} -{"id": 3127, "token": "\u012021", "merges": "\u01202 1", "raw_count": 940531, "count": 940531, "decode_str": " 21"} -{"id": 53112, "token": "\u00e7\u00a5\u012b", "merges": "\u00e7\u00a5 \u012b", "raw_count": 941582, "count": 941582, "decode_str": "\u7949"} -{"id": 51689, "token": "\u00e6\u0122\u0127", "merges": "\u00e6\u0122 \u0127", "raw_count": 941644, "count": 941644, "decode_str": "\u6005"} -{"id": 54250, "token": "\u00e9\u0137\u0124", "merges": "\u00e9\u0137 \u0124", "raw_count": 942104, "count": 942104, "decode_str": "\u9542"} -{"id": 54060, "token": "\u00e8\u00be\u00ab", "merges": "\u00e8\u00be \u00ab", "raw_count": 942630, "count": 942630, "decode_str": "\u8fab"} -{"id": 6369, "token": "NT", "merges": "N T", "raw_count": 771168, "count": 943023, "decode_str": "NT"} -{"id": 1487, "token": "ides", "merges": "id es", "raw_count": 331956, "count": 943566, "decode_str": "ides"} -{"id": 40928, "token": "!,", "merges": "! ,", "raw_count": 943742, "count": 943742, "decode_str": "!,"} -{"id": 11252, "token": "API", "merges": "AP I", "raw_count": 944111, "count": 944172, "decode_str": "API"} -{"id": 12265, "token": "\u0120council", "merges": "\u0120coun cil", "raw_count": 944441, "count": 944441, "decode_str": " council"} -{"id": 10928, "token": "\u0120obj", "merges": "\u0120ob j", "raw_count": 939172, "count": 944782, "decode_str": " obj"} -{"id": 6917, "token": "mt", "merges": "m t", "raw_count": 554563, "count": 945289, "decode_str": "mt"} -{"id": 18663, "token": "158", "merges": "15 8", "raw_count": 945752, "count": 945752, "decode_str": "158"} -{"id": 10146, "token": "header", "merges": "head er", "raw_count": 945839, "count": 945839, "decode_str": "header"} -{"id": 1066, "token": "\u0120down", "merges": "\u0120d own", "raw_count": 567510, "count": 945882, "decode_str": " down"} -{"id": 54100, "token": "\u00e9\u0122\u0127", "merges": "\u00e9\u0122 \u0127", "raw_count": 946033, "count": 946033, "decode_str": "\u9005"} -{"id": 10637, "token": "255", "merges": "25 5", "raw_count": 946221, "count": 946221, "decode_str": "255"} -{"id": 53844, "token": "\u00e8\u00af\u00b6", "merges": "\u00e8\u00af \u00b6", "raw_count": 946318, "count": 946318, "decode_str": "\u8bf6"} -{"id": 53224, "token": "\u00e7\u0143\u0132", "merges": "\u00e7\u0143 \u0132", "raw_count": 946927, "count": 946927, "decode_str": "\u7b50"} -{"id": 52941, "token": "\u00e7\u0139\u00a3", "merges": "\u00e7\u0139 \u00a3", "raw_count": 947538, "count": 947538, "decode_str": "\u75e3"} -{"id": 41291, "token": "\u0120kw", "merges": "\u0120k w", "raw_count": 947607, "count": 947607, "decode_str": " kw"} -{"id": 12080, "token": "pay", "merges": "p ay", "raw_count": 264762, "count": 947808, "decode_str": "pay"} -{"id": 51960, "token": "\u00e6\u012f\u0127", "merges": "\u00e6\u012f \u0127", "raw_count": 947818, "count": 947818, "decode_str": "\u6345"} -{"id": 7930, "token": "umns", "merges": "um ns", "raw_count": 5816, "count": 948073, "decode_str": "umns"} -{"id": 28862, "token": "features", "merges": "fe atures", "raw_count": 949104, "count": 949104, "decode_str": "features"} -{"id": 6712, "token": "weight", "merges": "we ight", "raw_count": 871602, "count": 949866, "decode_str": "weight"} -{"id": 714, "token": "\u0120Y", "merges": "\u0120 Y", "raw_count": 664682, "count": 950019, "decode_str": " Y"} -{"id": 31036, "token": "650", "merges": "6 50", "raw_count": 950692, "count": 950692, "decode_str": "650"} -{"id": 53590, "token": "\u00e8\u012a\u00b5", "merges": "\u00e8\u012a \u00b5", "raw_count": 951194, "count": 951194, "decode_str": "\u8235"} -{"id": 2038, "token": "ready", "merges": "read y", "raw_count": 141852, "count": 951337, "decode_str": "ready"} -{"id": 15270, "token": "139", "merges": "13 9", "raw_count": 953327, "count": 953327, "decode_str": "139"} -{"id": 2287, "token": "ands", "merges": "and s", "raw_count": 229583, "count": 953767, "decode_str": "ands"} -{"id": 1330, "token": "ffic", "merges": "ff ic", "raw_count": 91673, "count": 953787, "decode_str": "ffic"} -{"id": 51393, "token": "\u00e5\u0143\u00b0", "merges": "\u00e5\u0143 \u00b0", "raw_count": 954117, "count": 954117, "decode_str": "\u5b70"} -{"id": 10706, "token": "types", "merges": "typ es", "raw_count": 952667, "count": 954710, "decode_str": "types"} -{"id": 1604, "token": "\u0120adv", "merges": "\u0120ad v", "raw_count": 24841, "count": 954735, "decode_str": " adv"} -{"id": 43508, "token": ",)", "merges": ", )", "raw_count": 955325, "count": 955325, "decode_str": ",)"} -{"id": 6541, "token": "KE", "merges": "K E", "raw_count": 470139, "count": 955600, "decode_str": "KE"} -{"id": 1172, "token": "\u0120exper", "merges": "\u0120ex per", "raw_count": 2236, "count": 955751, "decode_str": " exper"} -{"id": 1482, "token": "ience", "merges": "i ence", "raw_count": 121037, "count": 955793, "decode_str": "ience"} -{"id": 3238, "token": "\u0120services", "merges": "\u0120serv ices", "raw_count": 955938, "count": 955938, "decode_str": " services"} -{"id": 1360, "token": "dition", "merges": "d ition", "raw_count": 54427, "count": 956115, "decode_str": "dition"} -{"id": 1751, "token": "ene", "merges": "en e", "raw_count": 245509, "count": 956489, "decode_str": "ene"} -{"id": 1207, "token": "\u00d0\u00b5", "merges": "\u00d0 \u00b5", "raw_count": 81113, "count": 956779, "decode_str": "\u0435"} -{"id": 849, "token": "\u0120how", "merges": "\u0120h ow", "raw_count": 713888, "count": 956798, "decode_str": " how"} -{"id": 6952, "token": "mes", "merges": "m es", "raw_count": 178662, "count": 957980, "decode_str": "mes"} -{"id": 880, "token": "](", "merges": "] (", "raw_count": 796649, "count": 958542, "decode_str": "]("} -{"id": 53262, "token": "\u00e7\u00b2\u0137", "merges": "\u00e7\u00b2 \u0137", "raw_count": 958604, "count": 958604, "decode_str": "\u7c95"} -{"id": 3489, "token": "ENT", "merges": "EN T", "raw_count": 389772, "count": 958652, "decode_str": "ENT"} -{"id": 7666, "token": "ernel", "merges": "ern el", "raw_count": 12090, "count": 959043, "decode_str": "ernel"} -{"id": 47985, "token": "\u0120dtype", "merges": "\u0120d type", "raw_count": 959926, "count": 959926, "decode_str": " dtype"} -{"id": 5658, "token": "you", "merges": "y ou", "raw_count": 960085, "count": 960085, "decode_str": "you"} -{"id": 8539, "token": "').", "merges": "' ).", "raw_count": 960108, "count": 960108, "decode_str": "')."} -{"id": 6226, "token": "cel", "merges": "c el", "raw_count": 415209, "count": 960452, "decode_str": "cel"} -{"id": 1307, "token": "\u0120term", "merges": "\u0120t erm", "raw_count": 303006, "count": 960533, "decode_str": " term"} -{"id": 3781, "token": "\u0120array", "merges": "\u0120ar ray", "raw_count": 962035, "count": 962035, "decode_str": " array"} -{"id": 1294, "token": "\u0120Pro", "merges": "\u0120P ro", "raw_count": 448430, "count": 962508, "decode_str": " Pro"} -{"id": 47762, "token": "IBM", "merges": "IB M", "raw_count": 963931, "count": 963931, "decode_str": "IBM"} -{"id": 52144, "token": "\u00e6\u013a\u00b1", "merges": "\u00e6\u013a \u00b1", "raw_count": 965036, "count": 965036, "decode_str": "\u6631"} -{"id": 1266, "token": "gg", "merges": "g g", "raw_count": 506740, "count": 965093, "decode_str": "gg"} -{"id": 1727, "token": "ends", "merges": "end s", "raw_count": 491269, "count": 965756, "decode_str": "ends"} -{"id": 13815, "token": "Mac", "merges": "M ac", "raw_count": 965816, "count": 965816, "decode_str": "Mac"} -{"id": 17790, "token": "OSS", "merges": "OS S", "raw_count": 961828, "count": 966094, "decode_str": "OSS"} -{"id": 50599, "token": "\u00e4\u00bf\u0132", "merges": "\u00e4\u00bf \u0132", "raw_count": 967008, "count": 967008, "decode_str": "\u4fd0"} -{"id": 52700, "token": "\u00e6\u00bc\u00a9", "merges": "\u00e6\u00bc \u00a9", "raw_count": 968704, "count": 968704, "decode_str": "\u6f29"} -{"id": 1152, "token": "\u00d0\u00b0", "merges": "\u00d0 \u00b0", "raw_count": 151618, "count": 968999, "decode_str": "\u0430"} -{"id": 4641, "token": "UL", "merges": "U L", "raw_count": 523769, "count": 969001, "decode_str": "UL"} -{"id": 50965, "token": "\u00e5\u0132\u013f", "merges": "\u00e5\u0132 \u013f", "raw_count": 969159, "count": 969159, "decode_str": "\u541d"} -{"id": 53242, "token": "\u00e7\u00ae\u0136", "merges": "\u00e7\u00ae \u0136", "raw_count": 969363, "count": 969363, "decode_str": "\u7b94"} -{"id": 3886, "token": "TH", "merges": "T H", "raw_count": 711222, "count": 970080, "decode_str": "TH"} -{"id": 812, "token": "\u0120could", "merges": "\u0120c ould", "raw_count": 925144, "count": 970276, "decode_str": " could"} -{"id": 1964, "token": "\u0120prom", "merges": "\u0120pro m", "raw_count": 16839, "count": 970285, "decode_str": " prom"} -{"id": 4741, "token": "OV", "merges": "O V", "raw_count": 382857, "count": 970556, "decode_str": "OV"} -{"id": 47886, "token": "CAD", "merges": "C AD", "raw_count": 970977, "count": 970977, "decode_str": "CAD"} -{"id": 51751, "token": "\u00e6\u0124\u00af", "merges": "\u00e6\u0124 \u00af", "raw_count": 971014, "count": 971014, "decode_str": "\u60af"} -{"id": 7386, "token": "CF", "merges": "C F", "raw_count": 937704, "count": 971378, "decode_str": "CF"} -{"id": 12113, "token": "words", "merges": "word s", "raw_count": 756697, "count": 971669, "decode_str": "words"} -{"id": 13482, "token": "129", "merges": "12 9", "raw_count": 971835, "count": 971835, "decode_str": "129"} -{"id": 1488, "token": "\u0120wr", "merges": "\u0120w r", "raw_count": 26975, "count": 971938, "decode_str": " wr"} -{"id": 2721, "token": "ze", "merges": "z e", "raw_count": 772913, "count": 972545, "decode_str": "ze"} -{"id": 7083, "token": "cr", "merges": "c r", "raw_count": 957814, "count": 973185, "decode_str": "cr"} -{"id": 8768, "token": "FO", "merges": "F O", "raw_count": 760558, "count": 973209, "decode_str": "FO"} -{"id": 53129, "token": "\u00e7\u00a5\u00af", "merges": "\u00e7\u00a5 \u00af", "raw_count": 973638, "count": 973638, "decode_str": "\u796f"} -{"id": 26452, "token": "~(", "merges": "~ (", "raw_count": 973649, "count": 973649, "decode_str": "~("} -{"id": 5168, "token": "di", "merges": "d i", "raw_count": 749106, "count": 974255, "decode_str": "di"} -{"id": 2435, "token": "angu", "merges": "ang u", "raw_count": 54939, "count": 974454, "decode_str": "angu"} -{"id": 2555, "token": "oll", "merges": "ol l", "raw_count": 282357, "count": 975594, "decode_str": "oll"} -{"id": 51666, "token": "\u00e5\u00bf\u0131", "merges": "\u00e5\u00bf \u0131", "raw_count": 976159, "count": 976159, "decode_str": "\u5fcf"} -{"id": 54145, "token": "\u00e9\u0124\u0124", "merges": "\u00e9\u0124 \u0124", "raw_count": 976321, "count": 976321, "decode_str": "\u9082"} -{"id": 12588, "token": "tree", "merges": "t ree", "raw_count": 976514, "count": 976514, "decode_str": "tree"} -{"id": 1974, "token": "acy", "merges": "ac y", "raw_count": 466379, "count": 977368, "decode_str": "acy"} -{"id": 5190, "token": "``", "merges": "` `", "raw_count": 931418, "count": 977410, "decode_str": "``"} -{"id": 12292, "token": "tim", "merges": "t im", "raw_count": 470170, "count": 977641, "decode_str": "tim"} -{"id": 51776, "token": "\u00e6\u0125\u0143", "merges": "\u00e6\u0125 \u0143", "raw_count": 978041, "count": 978041, "decode_str": "\u60ed"} -{"id": 51321, "token": "\u00e5\u00a5\u013c", "merges": "\u00e5\u00a5 \u013c", "raw_count": 978256, "count": 978256, "decode_str": "\u595a"} -{"id": 4427, "token": "rate", "merges": "r ate", "raw_count": 914663, "count": 978972, "decode_str": "rate"} -{"id": 5719, "token": "mail", "merges": "m ail", "raw_count": 651084, "count": 979317, "decode_str": "mail"} -{"id": 21328, "token": "Ra", "merges": "R a", "raw_count": 979387, "count": 979387, "decode_str": "Ra"} -{"id": 11167, "token": "&#", "merges": "& #", "raw_count": 825173, "count": 979786, "decode_str": "&#"} -{"id": 11499, "token": "pref", "merges": "p ref", "raw_count": 188439, "count": 980543, "decode_str": "pref"} -{"id": 2061, "token": "org", "merges": "or g", "raw_count": 891996, "count": 980700, "decode_str": "org"} -{"id": 2452, "token": "ension", "merges": "ens ion", "raw_count": 104694, "count": 981411, "decode_str": "ension"} -{"id": 14322, "token": "113", "merges": "11 3", "raw_count": 982301, "count": 982301, "decode_str": "113"} -{"id": 1394, "token": "You", "merges": "Y ou", "raw_count": 983254, "count": 983254, "decode_str": "You"} -{"id": 52906, "token": "\u00e7\u0138\u013b", "merges": "\u00e7\u0138 \u013b", "raw_count": 984240, "count": 984240, "decode_str": "\u7599"} -{"id": 2087, "token": "\u0120general", "merges": "\u0120gener al", "raw_count": 971765, "count": 984340, "decode_str": " general"} -{"id": 17615, "token": "301", "merges": "3 01", "raw_count": 985413, "count": 985413, "decode_str": "301"} -{"id": 5425, "token": "ifier", "merges": "if ier", "raw_count": 471626, "count": 985530, "decode_str": "ifier"} -{"id": 54165, "token": "\u00e9\u0124\u00b8", "merges": "\u00e9\u0124 \u00b8", "raw_count": 986040, "count": 986040, "decode_str": "\u90b8"} -{"id": 2395, "token": "\u0120account", "merges": "\u0120acc ount", "raw_count": 672961, "count": 986151, "decode_str": " account"} -{"id": 16460, "token": "1983", "merges": "19 83", "raw_count": 986192, "count": 986192, "decode_str": "1983"} -{"id": 51387, "token": "\u00e5\u0143\u00a2", "merges": "\u00e5\u0143 \u00a2", "raw_count": 986303, "count": 986303, "decode_str": "\u5b62"} -{"id": 51819, "token": "\u00e6\u012a\u0141", "merges": "\u00e6\u012a \u0141", "raw_count": 988078, "count": 988078, "decode_str": "\u621f"} -{"id": 7722, "token": "MC", "merges": "M C", "raw_count": 986961, "count": 988207, "decode_str": "MC"} -{"id": 1616, "token": "\u0120mark", "merges": "\u0120m ark", "raw_count": 172791, "count": 988352, "decode_str": " mark"} -{"id": 1068, "token": "\u00d0\u00be", "merges": "\u00d0 \u00be", "raw_count": 51540, "count": 989330, "decode_str": "\u043e"} -{"id": 4026, "token": "arning", "merges": "ar ning", "raw_count": 5761, "count": 989366, "decode_str": "arning"} -{"id": 17786, "token": "185", "merges": "18 5", "raw_count": 989919, "count": 989919, "decode_str": "185"} -{"id": 9151, "token": "DC", "merges": "D C", "raw_count": 990504, "count": 990504, "decode_str": "DC"} -{"id": 36676, "token": "'].", "merges": "' ].", "raw_count": 991467, "count": 991467, "decode_str": "']."} -{"id": 3074, "token": "All", "merges": "A ll", "raw_count": 879346, "count": 992693, "decode_str": "All"} -{"id": 2948, "token": "import", "merges": "im port", "raw_count": 951085, "count": 993352, "decode_str": "import"} -{"id": 19233, "token": "512", "merges": "5 12", "raw_count": 993473, "count": 993473, "decode_str": "512"} -{"id": 7557, "token": "Line", "merges": "L ine", "raw_count": 634938, "count": 993728, "decode_str": "Line"} -{"id": 1649, "token": "\u0120vis", "merges": "\u0120v is", "raw_count": 52344, "count": 994207, "decode_str": " vis"} -{"id": 6892, "token": "Che", "merges": "C he", "raw_count": 297848, "count": 994408, "decode_str": "Che"} -{"id": 1905, "token": "\u0120\u00e2\u0122\u0136", "merges": "\u0120\u00e2\u0122 \u0136", "raw_count": 994872, "count": 994872, "decode_str": " \u2014"} -{"id": 51708, "token": "\u00e6\u0122\u00bc", "merges": "\u00e6\u0122 \u00bc", "raw_count": 995064, "count": 995064, "decode_str": "\u603c"} -{"id": 1632, "token": "iness", "merges": "in ess", "raw_count": 98762, "count": 995648, "decode_str": "iness"} -{"id": 52413, "token": "\u00e6\u00ae\u0128", "merges": "\u00e6\u00ae \u0128", "raw_count": 995731, "count": 995731, "decode_str": "\u6b86"} -{"id": 11946, "token": "127", "merges": "12 7", "raw_count": 996225, "count": 996225, "decode_str": "127"} -{"id": 11489, "token": "sn", "merges": "s n", "raw_count": 870662, "count": 996711, "decode_str": "sn"} -{"id": 1761, "token": "rap", "merges": "ra p", "raw_count": 401507, "count": 996716, "decode_str": "rap"} -{"id": 53157, "token": "\u00e7\u00a7\u00a7", "merges": "\u00e7\u00a7 \u00a7", "raw_count": 996925, "count": 996925, "decode_str": "\u79e7"} -{"id": 4380, "token": "ights", "merges": "ight s", "raw_count": 248118, "count": 997111, "decode_str": "ights"} -{"id": 52314, "token": "\u00e6\u00a1\u00a6", "merges": "\u00e6\u00a1 \u00a6", "raw_count": 998260, "count": 998260, "decode_str": "\u6866"} -{"id": 12231, "token": "117", "merges": "11 7", "raw_count": 998922, "count": 998922, "decode_str": "117"} -{"id": 6329, "token": "MO", "merges": "M O", "raw_count": 748299, "count": 1001116, "decode_str": "MO"} -{"id": 53863, "token": "\u00e8\u00b0\u0131", "merges": "\u00e8\u00b0 \u0131", "raw_count": 1001307, "count": 1001307, "decode_str": "\u8c0f"} -{"id": 1951, "token": "aces", "merges": "ac es", "raw_count": 140583, "count": 1002080, "decode_str": "aces"} -{"id": 7604, "token": "tra", "merges": "t ra", "raw_count": 463736, "count": 1002680, "decode_str": "tra"} -{"id": 5394, "token": "idden", "merges": "idd en", "raw_count": 87546, "count": 1002900, "decode_str": "idden"} -{"id": 2127, "token": "\u0120code", "merges": "\u0120c ode", "raw_count": 989164, "count": 1003076, "decode_str": " code"} -{"id": 1280, "token": "ategory", "merges": "ateg ory", "raw_count": 1472, "count": 1003197, "decode_str": "ategory"} -{"id": 51279, "token": "\u00e5\u00a3\u00ac", "merges": "\u00e5\u00a3 \u00ac", "raw_count": 1003785, "count": 1003785, "decode_str": "\u58ec"} -{"id": 8076, "token": "cat", "merges": "c at", "raw_count": 667630, "count": 1003987, "decode_str": "cat"} -{"id": 5993, "token": "BL", "merges": "B L", "raw_count": 899886, "count": 1004054, "decode_str": "BL"} -{"id": 52931, "token": "\u00e7\u0139\u012c", "merges": "\u00e7\u0139 \u012c", "raw_count": 1004283, "count": 1004283, "decode_str": "\u75ca"} -{"id": 2289, "token": "\u0120access", "merges": "\u0120acc ess", "raw_count": 819819, "count": 1005468, "decode_str": " access"} -{"id": 15054, "token": "155", "merges": "15 5", "raw_count": 1005799, "count": 1005799, "decode_str": "155"} -{"id": 1220, "token": "\u0120sol", "merges": "\u0120s ol", "raw_count": 104666, "count": 1005854, "decode_str": " sol"} -{"id": 5449, "token": "flow", "merges": "f low", "raw_count": 803584, "count": 1006062, "decode_str": "flow"} -{"id": 11145, "token": "make", "merges": "m ake", "raw_count": 1006725, "count": 1006725, "decode_str": "make"} -{"id": 3612, "token": "ken", "merges": "k en", "raw_count": 130947, "count": 1006903, "decode_str": "ken"} -{"id": 4883, "token": "NS", "merges": "N S", "raw_count": 980644, "count": 1007160, "decode_str": "NS"} -{"id": 7110, "token": "has", "merges": "h as", "raw_count": 1008911, "count": 1008911, "decode_str": "has"} -{"id": 1316, "token": "uss", "merges": "us s", "raw_count": 378567, "count": 1009056, "decode_str": "uss"} -{"id": 10613, "token": "service", "merges": "serv ice", "raw_count": 1009105, "count": 1009105, "decode_str": "service"} -{"id": 5092, "token": "can", "merges": "c an", "raw_count": 643084, "count": 1009603, "decode_str": "can"} -{"id": 3615, "token": "char", "merges": "ch ar", "raw_count": 675045, "count": 1009865, "decode_str": "char"} -{"id": 1055, "token": "\u0120effect", "merges": "\u0120e ffect", "raw_count": 255854, "count": 1010606, "decode_str": " effect"} -{"id": 14817, "token": "UV", "merges": "U V", "raw_count": 1010795, "count": 1010795, "decode_str": "UV"} -{"id": 53661, "token": "\u00e8\u0130\u0127", "merges": "\u00e8\u0130 \u0127", "raw_count": 1010883, "count": 1010883, "decode_str": "\u8385"} -{"id": 1589, "token": "ration", "merges": "r ation", "raw_count": 50800, "count": 1011047, "decode_str": "ration"} -{"id": 50406, "token": "\u00e4\u00b8\u0132", "merges": "\u00e4\u00b8 \u0132", "raw_count": 1011399, "count": 1011399, "decode_str": "\u4e10"} -{"id": 9188, "token": "sign", "merges": "s ign", "raw_count": 462967, "count": 1012013, "decode_str": "sign"} -{"id": 3706, "token": "\u0120;", "merges": "\u0120 ;", "raw_count": 996332, "count": 1012035, "decode_str": " ;"} -{"id": 51777, "token": "\u00e6\u0125\u00ae", "merges": "\u00e6\u0125 \u00ae", "raw_count": 1012159, "count": 1012159, "decode_str": "\u60ee"} -{"id": 1430, "token": "ability", "merges": "ab ility", "raw_count": 339769, "count": 1012220, "decode_str": "ability"} -{"id": 17636, "token": ">>>", "merges": ">> >", "raw_count": 1012367, "count": 1012367, "decode_str": ">>>"} -{"id": 53403, "token": "\u00e7\u00bc\u00ae", "merges": "\u00e7\u00bc \u00ae", "raw_count": 1012941, "count": 1012941, "decode_str": "\u7f2e"} -{"id": 4227, "token": "\u0120instance", "merges": "\u0120inst ance", "raw_count": 1012625, "count": 1013169, "decode_str": " instance"} -{"id": 2260, "token": "lambda", "merges": "l ambda", "raw_count": 1013522, "count": 1013522, "decode_str": "lambda"} -{"id": 51810, "token": "\u00e6\u012a\u012e", "merges": "\u00e6\u012a \u012e", "raw_count": 1013742, "count": 1013742, "decode_str": "\u620c"} -{"id": 52732, "token": "\u00e7\u0124\u013e", "merges": "\u00e7\u0124 \u013e", "raw_count": 1014320, "count": 1014320, "decode_str": "\u709c"} -{"id": 52610, "token": "\u00e6\u00b6\u0141", "merges": "\u00e6\u00b6 \u0141", "raw_count": 1015023, "count": 1015023, "decode_str": "\u6d9f"} -{"id": 9498, "token": "%),", "merges": "% ),", "raw_count": 1015202, "count": 1015202, "decode_str": "%),"} -{"id": 10261, "token": "~~~~", "merges": "~~ ~~", "raw_count": 672923, "count": 1015433, "decode_str": "~~~~"} -{"id": 6350, "token": "QL", "merges": "Q L", "raw_count": 272979, "count": 1016051, "decode_str": "QL"} -{"id": 948, "token": "\u0120sim", "merges": "\u0120s im", "raw_count": 162248, "count": 1016185, "decode_str": " sim"} -{"id": 52182, "token": "\u00e6\u013d\u00b3", "merges": "\u00e6\u013d \u00b3", "raw_count": 1016191, "count": 1016191, "decode_str": "\u66f3"} -{"id": 4022, "token": "\u01202016", "merges": "\u0120201 6", "raw_count": 1017199, "count": 1017199, "decode_str": " 2016"} -{"id": 2226, "token": "\u0120exist", "merges": "\u0120ex ist", "raw_count": 484657, "count": 1017984, "decode_str": " exist"} -{"id": 52820, "token": "\u00e7\u0131\u0124", "merges": "\u00e7\u0131 \u0124", "raw_count": 1019908, "count": 1019908, "decode_str": "\u73c2"} -{"id": 2513, "token": "Is", "merges": "I s", "raw_count": 960600, "count": 1020220, "decode_str": "Is"} -{"id": 20340, "token": ".....", "merges": ".. ...", "raw_count": 1020367, "count": 1020367, "decode_str": "....."} -{"id": 1735, "token": "\u0120next", "merges": "\u0120ne xt", "raw_count": 1021725, "count": 1021725, "decode_str": " next"} -{"id": 8504, "token": "NN", "merges": "N N", "raw_count": 299658, "count": 1021808, "decode_str": "NN"} -{"id": 1109, "token": "rm", "merges": "r m", "raw_count": 732848, "count": 1022172, "decode_str": "rm"} -{"id": 54146, "token": "\u00e9\u0124\u0125", "merges": "\u00e9\u0124 \u0125", "raw_count": 1023619, "count": 1023619, "decode_str": "\u9083"} -{"id": 1210, "token": "\u0120ins", "merges": "\u0120in s", "raw_count": 75170, "count": 1023920, "decode_str": " ins"} -{"id": 16848, "token": "sample", "merges": "s ample", "raw_count": 1023967, "count": 1023967, "decode_str": "sample"} -{"id": 50560, "token": "\u00e4\u00bd\u0141", "merges": "\u00e4\u00bd \u0141", "raw_count": 1024401, "count": 1024401, "decode_str": "\u4f5f"} -{"id": 9989, "token": "BO", "merges": "B O", "raw_count": 831580, "count": 1024630, "decode_str": "BO"} -{"id": 28321, "token": "550", "merges": "5 50", "raw_count": 1025493, "count": 1025493, "decode_str": "550"} -{"id": 46150, "token": "plt", "merges": "pl t", "raw_count": 1025863, "count": 1025863, "decode_str": "plt"} -{"id": 4168, "token": "change", "merges": "ch ange", "raw_count": 577028, "count": 1026733, "decode_str": "change"} -{"id": 51513, "token": "\u00e5\u00b7\u00b3", "merges": "\u00e5\u00b7 \u00b3", "raw_count": 1026743, "count": 1026743, "decode_str": "\u5df3"} -{"id": 52044, "token": "\u00e6\u0134\u00b8", "merges": "\u00e6\u0134 \u00b8", "raw_count": 1028183, "count": 1028183, "decode_str": "\u64b8"} -{"id": 1261, "token": "ven", "merges": "v en", "raw_count": 319449, "count": 1028506, "decode_str": "ven"} -{"id": 12964, "token": "fc", "merges": "f c", "raw_count": 1028551, "count": 1028551, "decode_str": "fc"} -{"id": 10936, "token": "vs", "merges": "v s", "raw_count": 1028779, "count": 1028779, "decode_str": "vs"} -{"id": 2142, "token": "ocial", "merges": "oc ial", "raw_count": 9816, "count": 1029187, "decode_str": "ocial"} -{"id": 4482, "token": "bb", "merges": "b b", "raw_count": 1015308, "count": 1029574, "decode_str": "bb"} -{"id": 3161, "token": "gress", "merges": "g ress", "raw_count": 26651, "count": 1030331, "decode_str": "gress"} -{"id": 1592, "token": "fer", "merges": "f er", "raw_count": 224046, "count": 1030442, "decode_str": "fer"} -{"id": 6075, "token": "Ser", "merges": "S er", "raw_count": 153131, "count": 1030509, "decode_str": "Ser"} -{"id": 2842, "token": "ideo", "merges": "ide o", "raw_count": 14241, "count": 1030641, "decode_str": "ideo"} -{"id": 32887, "token": "TOP", "merges": "T OP", "raw_count": 1031736, "count": 1031736, "decode_str": "TOP"} -{"id": 54301, "token": "\u00e9\u013a\u0138", "merges": "\u00e9\u013a \u0138", "raw_count": 1032058, "count": 1032058, "decode_str": "\u9616"} -{"id": 53232, "token": "\u00e7\u0143\u00b1", "merges": "\u00e7\u0143 \u00b1", "raw_count": 1032352, "count": 1032352, "decode_str": "\u7b71"} -{"id": 34963, "token": "520", "merges": "5 20", "raw_count": 1032783, "count": 1032783, "decode_str": "520"} -{"id": 1391, "token": "\u0120cle", "merges": "\u0120c le", "raw_count": 32494, "count": 1033028, "decode_str": " cle"} -{"id": 13210, "token": "116", "merges": "11 6", "raw_count": 1033770, "count": 1033770, "decode_str": "116"} -{"id": 1160, "token": "\u0120made", "merges": "\u0120m ade", "raw_count": 1034381, "count": 1034381, "decode_str": " made"} -{"id": 21599, "token": "execute", "merges": "exec ute", "raw_count": 1034602, "count": 1034602, "decode_str": "execute"} -{"id": 15476, "token": "grid", "merges": "gr id", "raw_count": 1034970, "count": 1034970, "decode_str": "grid"} -{"id": 52930, "token": "\u00e7\u0139\u012b", "merges": "\u00e7\u0139 \u012b", "raw_count": 1036132, "count": 1036132, "decode_str": "\u75c9"} -{"id": 1544, "token": "ral", "merges": "r al", "raw_count": 330060, "count": 1037246, "decode_str": "ral"} -{"id": 13118, "token": "conv", "merges": "con v", "raw_count": 1035685, "count": 1037270, "decode_str": "conv"} -{"id": 973, "token": "\u0120well", "merges": "\u0120w ell", "raw_count": 1020271, "count": 1037333, "decode_str": " well"} -{"id": 10536, "token": "HD", "merges": "H D", "raw_count": 1036957, "count": 1037413, "decode_str": "HD"} -{"id": 1972, "token": "ances", "merges": "an ces", "raw_count": 306159, "count": 1037742, "decode_str": "ances"} -{"id": 1606, "token": "\u0120wom", "merges": "\u0120w om", "raw_count": 1841, "count": 1038426, "decode_str": " wom"} -{"id": 2187, "token": "empt", "merges": "em pt", "raw_count": 32844, "count": 1039157, "decode_str": "empt"} -{"id": 1859, "token": "\u0120view", "merges": "\u0120v iew", "raw_count": 783273, "count": 1039284, "decode_str": " view"} -{"id": 1072, "token": "\u0120same", "merges": "\u0120s ame", "raw_count": 1039370, "count": 1039370, "decode_str": " same"} -{"id": 8561, "token": "BD", "merges": "B D", "raw_count": 1037898, "count": 1039883, "decode_str": "BD"} -{"id": 4762, "token": "rep", "merges": "re p", "raw_count": 323323, "count": 1040150, "decode_str": "rep"} -{"id": 52446, "token": "\u00e6\u00b0\u0135", "merges": "\u00e6\u00b0 \u0135", "raw_count": 1040243, "count": 1040243, "decode_str": "\u6c13"} -{"id": 54092, "token": "\u00e8\u00bf\u00b8", "merges": "\u00e8\u00bf \u00b8", "raw_count": 1040331, "count": 1040331, "decode_str": "\u8ff8"} -{"id": 6623, "token": "Fl", "merges": "F l", "raw_count": 504394, "count": 1040662, "decode_str": "Fl"} -{"id": 51447, "token": "\u00e5\u00af\u00b0", "merges": "\u00e5\u00af \u00b0", "raw_count": 1041417, "count": 1041417, "decode_str": "\u5bf0"} -{"id": 6839, "token": "inst", "merges": "in st", "raw_count": 490734, "count": 1041600, "decode_str": "inst"} -{"id": 51021, "token": "\u00e5\u0134\u0130", "merges": "\u00e5\u0134 \u0130", "raw_count": 1043669, "count": 1043669, "decode_str": "\u548e"} -{"id": 17103, "token": "1982", "merges": "19 82", "raw_count": 1044077, "count": 1044077, "decode_str": "1982"} -{"id": 54186, "token": "\u00e9\u0127\u012b", "merges": "\u00e9\u0127 \u012b", "raw_count": 1044951, "count": 1044951, "decode_str": "\u9149"} -{"id": 52642, "token": "\u00e6\u00b7\u00ac", "merges": "\u00e6\u00b7 \u00ac", "raw_count": 1045231, "count": 1045231, "decode_str": "\u6dec"} -{"id": 52047, "token": "\u00e6\u0135\u0124", "merges": "\u00e6\u0135 \u0124", "raw_count": 1045861, "count": 1045861, "decode_str": "\u64c2"} -{"id": 4658, "token": "lib", "merges": "l ib", "raw_count": 978943, "count": 1046593, "decode_str": "lib"} -{"id": 1090, "token": "ince", "merges": "in ce", "raw_count": 74242, "count": 1046929, "decode_str": "ince"} -{"id": 53022, "token": "\u00e7\u013f\u0133", "merges": "\u00e7\u013f \u0133", "raw_count": 1046954, "count": 1046954, "decode_str": "\u7751"} -{"id": 7040, "token": "-----", "merges": "---- -", "raw_count": 401517, "count": 1048247, "decode_str": "-----"} -{"id": 51223, "token": "\u00e5\u0140\u00a3", "merges": "\u00e5\u0140 \u00a3", "raw_count": 1048271, "count": 1048271, "decode_str": "\u57a3"} -{"id": 4066, "token": "pat", "merges": "p at", "raw_count": 291210, "count": 1048282, "decode_str": "pat"} -{"id": 1807, "token": "uck", "merges": "u ck", "raw_count": 224210, "count": 1048353, "decode_str": "uck"} -{"id": 53307, "token": "\u00e7\u00ba\u0124", "merges": "\u00e7\u00ba \u0124", "raw_count": 1048391, "count": 1048391, "decode_str": "\u7e82"} -{"id": 14708, "token": "\"))", "merges": "\" ))", "raw_count": 1048446, "count": 1048446, "decode_str": "\"))"} -{"id": 6989, "token": "User", "merges": "U ser", "raw_count": 1000641, "count": 1048725, "decode_str": "User"} -{"id": 54302, "token": "\u00e9\u013a\u013b", "merges": "\u00e9\u013a \u013b", "raw_count": 1049013, "count": 1049013, "decode_str": "\u9619"} -{"id": 9180, "token": "MB", "merges": "M B", "raw_count": 1025438, "count": 1049730, "decode_str": "MB"} -{"id": 52473, "token": "\u00e6\u00b1\u0132", "merges": "\u00e6\u00b1 \u0132", "raw_count": 1049743, "count": 1049743, "decode_str": "\u6c50"} -{"id": 20773, "token": "gb", "merges": "g b", "raw_count": 972171, "count": 1049975, "decode_str": "gb"} -{"id": 21391, "token": "\"],", "merges": "\" ],", "raw_count": 1050010, "count": 1050010, "decode_str": "\"],"} -{"id": 2714, "token": "\u0120special", "merges": "\u0120spec ial", "raw_count": 899118, "count": 1051547, "decode_str": " special"} -{"id": 1255, "token": "ness", "merges": "n ess", "raw_count": 433960, "count": 1051764, "decode_str": "ness"} -{"id": 53662, "token": "\u00e8\u0130\u0128", "merges": "\u00e8\u0130 \u0128", "raw_count": 1052485, "count": 1052485, "decode_str": "\u8386"} -{"id": 1319, "token": "ality", "merges": "al ity", "raw_count": 240670, "count": 1052623, "decode_str": "ality"} -{"id": 20256, "token": "270", "merges": "27 0", "raw_count": 1052831, "count": 1052831, "decode_str": "270"} -{"id": 929, "token": "\u0120\u00d0", "merges": "\u0120 \u00d0", "raw_count": 13867, "count": 1052974, "decode_str": " \ufffd"} -{"id": 52790, "token": "\u00e7\u012c\u0123", "merges": "\u00e7\u012c \u0123", "raw_count": 1054279, "count": 1054279, "decode_str": "\u7281"} -{"id": 52975, "token": "\u00e7\u013c\u013b", "merges": "\u00e7\u013c \u013b", "raw_count": 1054595, "count": 1054595, "decode_str": "\u7699"} -{"id": 4286, "token": "abase", "merges": "ab ase", "raw_count": 13639, "count": 1055111, "decode_str": "abase"} -{"id": 4786, "token": "fo", "merges": "f o", "raw_count": 279504, "count": 1056076, "decode_str": "fo"} -{"id": 51929, "token": "\u00e6\u012d\u00b7", "merges": "\u00e6\u012d \u00b7", "raw_count": 1056111, "count": 1056111, "decode_str": "\u62f7"} -{"id": 1973, "token": "\u0120build", "merges": "\u0120bu ild", "raw_count": 685809, "count": 1057626, "decode_str": " build"} -{"id": 1426, "token": "irc", "merges": "ir c", "raw_count": 125046, "count": 1057971, "decode_str": "irc"} -{"id": 3671, "token": "fs", "merges": "f s", "raw_count": 1037604, "count": 1058038, "decode_str": "fs"} -{"id": 2865, "token": "isc", "merges": "is c", "raw_count": 180648, "count": 1058170, "decode_str": "isc"} -{"id": 5455, "token": "Path", "merges": "P ath", "raw_count": 957719, "count": 1059481, "decode_str": "Path"} -{"id": 1390, "token": "\u0120last", "merges": "\u0120l ast", "raw_count": 1013262, "count": 1059573, "decode_str": " last"} -{"id": 1428, "token": "ished", "merges": "is hed", "raw_count": 97715, "count": 1060562, "decode_str": "ished"} -{"id": 1933, "token": ")/", "merges": ") /", "raw_count": 954168, "count": 1061184, "decode_str": ")/"} -{"id": 3264, "token": "\u0120expected", "merges": "\u0120expect ed", "raw_count": 1061444, "count": 1061444, "decode_str": " expected"} -{"id": 2231, "token": "lected", "merges": "lect ed", "raw_count": 34180, "count": 1061610, "decode_str": "lected"} -{"id": 4971, "token": "grad", "merges": "gr ad", "raw_count": 785612, "count": 1061808, "decode_str": "grad"} -{"id": 9688, "token": "\u0120url", "merges": "\u0120ur l", "raw_count": 1061875, "count": 1061875, "decode_str": " url"} -{"id": 1546, "token": "ural", "merges": "ur al", "raw_count": 123820, "count": 1063292, "decode_str": "ural"} -{"id": 2410, "token": "\u0120conv", "merges": "\u0120con v", "raw_count": 192815, "count": 1063864, "decode_str": " conv"} -{"id": 1831, "token": "por", "merges": "p or", "raw_count": 228917, "count": 1063879, "decode_str": "por"} -{"id": 1564, "token": "ivers", "merges": "i vers", "raw_count": 61369, "count": 1064123, "decode_str": "ivers"} -{"id": 53944, "token": "\u00e8\u00b5\u0124", "merges": "\u00e8\u00b5 \u0124", "raw_count": 1064685, "count": 1064685, "decode_str": "\u8d42"} -{"id": 2375, "token": "uf", "merges": "u f", "raw_count": 348507, "count": 1065447, "decode_str": "uf"} -{"id": 8190, "token": "contin", "merges": "cont in", "raw_count": 54225, "count": 1065687, "decode_str": "contin"} -{"id": 16372, "token": "iph", "merges": "ip h", "raw_count": 1066742, "count": 1066742, "decode_str": "iph"} -{"id": 51497, "token": "\u00e5\u00b1\u00b9", "merges": "\u00e5\u00b1 \u00b9", "raw_count": 1066928, "count": 1066928, "decode_str": "\u5c79"} -{"id": 4769, "token": "Time", "merges": "T ime", "raw_count": 893042, "count": 1066987, "decode_str": "Time"} -{"id": 53422, "token": "\u00e7\u00bd\u00b9", "merges": "\u00e7\u00bd \u00b9", "raw_count": 1067519, "count": 1067519, "decode_str": "\u7f79"} -{"id": 52521, "token": "\u00e6\u00b2\u00bd", "merges": "\u00e6\u00b2 \u00bd", "raw_count": 1067609, "count": 1067609, "decode_str": "\u6cbd"} -{"id": 8547, "token": "template", "merges": "tem plate", "raw_count": 1067797, "count": 1067797, "decode_str": "template"} -{"id": 1729, "token": "\u0120cap", "merges": "\u0120c ap", "raw_count": 117401, "count": 1068836, "decode_str": " cap"} -{"id": 1351, "token": "ane", "merges": "an e", "raw_count": 479147, "count": 1069676, "decode_str": "ane"} -{"id": 12250, "token": "req", "merges": "re q", "raw_count": 709211, "count": 1069720, "decode_str": "req"} -{"id": 1350, "token": "ross", "merges": "ro ss", "raw_count": 117485, "count": 1069761, "decode_str": "ross"} -{"id": 54626, "token": "\u00e3\u0122\u013b", "merges": "\u00e3\u0122 \u013b", "raw_count": 1069821, "count": 1069821, "decode_str": " "} -{"id": 52848, "token": "\u00e7\u0132\u013d", "merges": "\u00e7\u0132 \u013d", "raw_count": 1070980, "count": 1070980, "decode_str": "\u741b"} -{"id": 5200, "token": "ls", "merges": "l s", "raw_count": 992953, "count": 1071664, "decode_str": "ls"} -{"id": 841, "token": "\u0120these", "merges": "\u0120the se", "raw_count": 1072090, "count": 1072090, "decode_str": " these"} -{"id": 6441, "token": "mem", "merges": "m em", "raw_count": 448547, "count": 1073468, "decode_str": "mem"} -{"id": 52335, "token": "\u00e6\u00a5\u0124", "merges": "\u00e6\u00a5 \u0124", "raw_count": 1073875, "count": 1073875, "decode_str": "\u6942"} -{"id": 8744, "token": ")+", "merges": ") +", "raw_count": 1043703, "count": 1074293, "decode_str": ")+"} -{"id": 1096, "token": "ared", "merges": "a red", "raw_count": 133373, "count": 1074574, "decode_str": "ared"} -{"id": 11455, "token": "uid", "merges": "u id", "raw_count": 507342, "count": 1074663, "decode_str": "uid"} -{"id": 53059, "token": "\u00e7\u0142\u013c", "merges": "\u00e7\u0142 \u013c", "raw_count": 1074858, "count": 1074858, "decode_str": "\u781a"} -{"id": 1957, "token": "\u0120represent", "merges": "\u0120rep resent", "raw_count": 94361, "count": 1074860, "decode_str": " represent"} -{"id": 1461, "token": "\u0120conf", "merges": "\u0120con f", "raw_count": 224803, "count": 1075833, "decode_str": " conf"} -{"id": 2815, "token": "lim", "merges": "l im", "raw_count": 334097, "count": 1076298, "decode_str": "lim"} -{"id": 27641, "token": "headers", "merges": "head ers", "raw_count": 1078035, "count": 1078035, "decode_str": "headers"} -{"id": 11838, "token": "145", "merges": "14 5", "raw_count": 1074653, "count": 1078117, "decode_str": "145"} -{"id": 1519, "token": "ott", "merges": "ot t", "raw_count": 298076, "count": 1078659, "decode_str": "ott"} -{"id": 1327, "token": "\u0120non", "merges": "\u0120n on", "raw_count": 1041408, "count": 1078718, "decode_str": " non"} -{"id": 6674, "token": "matrix", "merges": "mat rix", "raw_count": 1075111, "count": 1078899, "decode_str": "matrix"} -{"id": 1813, "token": "icro", "merges": "ic ro", "raw_count": 15468, "count": 1079250, "decode_str": "icro"} -{"id": 7054, "token": "break", "merges": "bre ak", "raw_count": 1064569, "count": 1079531, "decode_str": "break"} -{"id": 1791, "token": "\u0120leg", "merges": "\u0120le g", "raw_count": 52309, "count": 1080390, "decode_str": " leg"} -{"id": 7696, "token": "ponse", "merges": "p onse", "raw_count": 2544, "count": 1080595, "decode_str": "ponse"} -{"id": 1944, "token": "ij", "merges": "i j", "raw_count": 370534, "count": 1081268, "decode_str": "ij"} -{"id": 1501, "token": "\u0120post", "merges": "\u0120p ost", "raw_count": 768405, "count": 1081553, "decode_str": " post"} -{"id": 1514, "token": "ium", "merges": "i um", "raw_count": 439484, "count": 1082240, "decode_str": "ium"} -{"id": 2333, "token": "\u0120manag", "merges": "\u0120man ag", "raw_count": 2285, "count": 1083106, "decode_str": " manag"} -{"id": 846, "token": "\u0120after", "merges": "\u0120a fter", "raw_count": 1021301, "count": 1083180, "decode_str": " after"} -{"id": 17494, "token": "settings", "merges": "sett ings", "raw_count": 1083276, "count": 1083276, "decode_str": "settings"} -{"id": 51609, "token": "\u00e5\u00bc\u00a9", "merges": "\u00e5\u00bc \u00a9", "raw_count": 1083853, "count": 1083853, "decode_str": "\u5f29"} -{"id": 2036, "token": "\u0120net", "merges": "\u0120n et", "raw_count": 389006, "count": 1085362, "decode_str": " net"} -{"id": 3783, "token": "ios", "merges": "i os", "raw_count": 1043809, "count": 1085944, "decode_str": "ios"} -{"id": 52095, "token": "\u00e6\u0138\u0141", "merges": "\u00e6\u0138 \u0141", "raw_count": 1085998, "count": 1085998, "decode_str": "\u659f"} -{"id": 3014, "token": "pose", "merges": "p ose", "raw_count": 826252, "count": 1086139, "decode_str": "pose"} -{"id": 15148, "token": "138", "merges": "13 8", "raw_count": 1086876, "count": 1086876, "decode_str": "138"} -{"id": 1739, "token": "apt", "merges": "a pt", "raw_count": 166232, "count": 1086906, "decode_str": "apt"} -{"id": 3708, "token": "\u0120status", "merges": "\u0120stat us", "raw_count": 1087593, "count": 1087593, "decode_str": " status"} -{"id": 1262, "token": "\u0120disc", "merges": "\u0120dis c", "raw_count": 52519, "count": 1087866, "decode_str": " disc"} -{"id": 50742, "token": "\u00e5\u0129\u012d", "merges": "\u00e5\u0129 \u012d", "raw_count": 1088188, "count": 1088188, "decode_str": "\u51cb"} -{"id": 10122, "token": "\u0120>=", "merges": "\u0120> =", "raw_count": 1088244, "count": 1088244, "decode_str": " >="} -{"id": 1766, "token": "\u0120bo", "merges": "\u0120b o", "raw_count": 79639, "count": 1088334, "decode_str": " bo"} -{"id": 50606, "token": "\u00e4\u00bf\u00a8", "merges": "\u00e4\u00bf \u00a8", "raw_count": 1088719, "count": 1088719, "decode_str": "\u4fe8"} -{"id": 7436, "token": "height", "merges": "he ight", "raw_count": 1089323, "count": 1089323, "decode_str": "height"} -{"id": 11025, "token": "connect", "merges": "conne ct", "raw_count": 1055824, "count": 1089448, "decode_str": "connect"} -{"id": 25989, "token": "Apple", "merges": "App le", "raw_count": 1089544, "count": 1089544, "decode_str": "Apple"} -{"id": 5156, "token": "ocket", "merges": "ock et", "raw_count": 145896, "count": 1090520, "decode_str": "ocket"} -{"id": 4779, "token": "Man", "merges": "M an", "raw_count": 490077, "count": 1090634, "decode_str": "Man"} -{"id": 3459, "token": "cription", "merges": "cript ion", "raw_count": 69198, "count": 1090934, "decode_str": "cription"} -{"id": 52074, "token": "\u00e6\u0137\u0138", "merges": "\u00e6\u0137 \u0138", "raw_count": 1090958, "count": 1090958, "decode_str": "\u6556"} -{"id": 8433, "token": "sg", "merges": "s g", "raw_count": 226309, "count": 1091932, "decode_str": "sg"} -{"id": 12985, "token": "cache", "merges": "c ache", "raw_count": 1092309, "count": 1092309, "decode_str": "cache"} -{"id": 1420, "token": "atic", "merges": "at ic", "raw_count": 207600, "count": 1093467, "decode_str": "atic"} -{"id": 9742, "token": "stack", "merges": "st ack", "raw_count": 1094177, "count": 1094722, "decode_str": "stack"} -{"id": 51824, "token": "\u00e6\u012a\u00ae", "merges": "\u00e6\u012a \u00ae", "raw_count": 1095364, "count": 1095364, "decode_str": "\u622e"} -{"id": 12780, "token": "tmp", "merges": "t mp", "raw_count": 1095574, "count": 1095574, "decode_str": "tmp"} -{"id": 51214, "token": "\u00e5\u013f\u00b7", "merges": "\u00e5\u013f \u00b7", "raw_count": 1096898, "count": 1096898, "decode_str": "\u5777"} -{"id": 8259, "token": "conf", "merges": "con f", "raw_count": 856272, "count": 1097813, "decode_str": "conf"} -{"id": 870, "token": ">", "merges": "> >", "raw_count": 662695, "count": 1763124, "decode_str": ">>"} -{"id": 51715, "token": "\u00e6\u0123\u0137", "merges": "\u00e6\u0123 \u0137", "raw_count": 1764174, "count": 1764174, "decode_str": "\u6055"} -{"id": 4490, "token": "TT", "merges": "T T", "raw_count": 922794, "count": 1765246, "decode_str": "TT"} -{"id": 51434, "token": "\u00e5\u00af\u0129", "merges": "\u00e5\u00af \u0129", "raw_count": 1765396, "count": 1765396, "decode_str": "\u5bc7"} -{"id": 1638, "token": "\u012014", "merges": "\u01201 4", "raw_count": 1499360, "count": 1765864, "decode_str": " 14"} -{"id": 3013, "token": "ises", "merges": "is es", "raw_count": 1420705, "count": 1766111, "decode_str": "ises"} -{"id": 1334, "token": "ider", "merges": "id er", "raw_count": 368023, "count": 1766707, "decode_str": "ider"} -{"id": 3054, "token": "\u0120states", "merges": "\u0120st ates", "raw_count": 1767971, "count": 1767971, "decode_str": " states"} -{"id": 2010, "token": "\u0120else", "merges": "\u0120el se", "raw_count": 1735955, "count": 1768014, "decode_str": " else"} -{"id": 4084, "token": "uild", "merges": "u ild", "raw_count": 100562, "count": 1769159, "decode_str": "uild"} -{"id": 13851, "token": "168", "merges": "16 8", "raw_count": 1769368, "count": 1769368, "decode_str": "168"} -{"id": 2211, "token": "oper", "merges": "op er", "raw_count": 310363, "count": 1770352, "decode_str": "oper"} -{"id": 3789, "token": "plate", "merges": "pl ate", "raw_count": 79421, "count": 1770712, "decode_str": "plate"} -{"id": 2380, "token": "\u0120response", "merges": "\u0120resp onse", "raw_count": 1771052, "count": 1771052, "decode_str": " response"} -{"id": 10886, "token": "\u0120dict", "merges": "\u0120d ict", "raw_count": 1756311, "count": 1771734, "decode_str": " dict"} -{"id": 50474, "token": "\u00e4\u00ba\u00a2", "merges": "\u00e4\u00ba \u00a2", "raw_count": 1772133, "count": 1772133, "decode_str": "\u4ea2"} -{"id": 52408, "token": "\u00e6\u0143\u00b9", "merges": "\u00e6\u0143 \u00b9", "raw_count": 1773147, "count": 1773147, "decode_str": "\u6b79"} -{"id": 52467, "token": "\u00e6\u00b1\u0122", "merges": "\u00e6\u00b1 \u0122", "raw_count": 1774692, "count": 1774692, "decode_str": "\u6c40"} -{"id": 15723, "token": "Fi", "merges": "F i", "raw_count": 1756791, "count": 1775284, "decode_str": "Fi"} -{"id": 1134, "token": "****", "merges": "** **", "raw_count": 614879, "count": 1775573, "decode_str": "****"} -{"id": 5324, "token": "HT", "merges": "H T", "raw_count": 917597, "count": 1775709, "decode_str": "HT"} -{"id": 2002, "token": "iron", "merges": "ir on", "raw_count": 70413, "count": 1776364, "decode_str": "iron"} -{"id": 53012, "token": "\u00e7\u013e\u00a9", "merges": "\u00e7\u013e \u00a9", "raw_count": 1776817, "count": 1776817, "decode_str": "\u7729"} -{"id": 51799, "token": "\u00e6\u0127\u0133", "merges": "\u00e6\u0127 \u0133", "raw_count": 1778659, "count": 1778659, "decode_str": "\u6151"} -{"id": 13752, "token": "\u00e3\u0122\u012f", "merges": "\u00e3\u0122 \u012f", "raw_count": 1781562, "count": 1781562, "decode_str": "\u300d"} -{"id": 1151, "token": "\u0120ser", "merges": "\u0120s er", "raw_count": 143947, "count": 1781677, "decode_str": " ser"} -{"id": 13748, "token": "\u00e3\u0122\u012e", "merges": "\u00e3\u0122 \u012e", "raw_count": 1782516, "count": 1782516, "decode_str": "\u300c"} -{"id": 6198, "token": "phone", "merges": "ph one", "raw_count": 1721775, "count": 1783664, "decode_str": "phone"} -{"id": 50973, "token": "\u00e5\u0132\u00a9", "merges": "\u00e5\u0132 \u00a9", "raw_count": 1784588, "count": 1784588, "decode_str": "\u5429"} -{"id": 168, "token": "\u00ec", "merges": "NULL", "raw_count": 297783, "count": 1785863, "decode_str": "\ufffd"} -{"id": 701, "token": "\u0120bet", "merges": "\u0120b et", "raw_count": 52509, "count": 1785909, "decode_str": " bet"} -{"id": 50574, "token": "\u00e4\u00be\u0126", "merges": "\u00e4\u00be \u0126", "raw_count": 1786123, "count": 1786123, "decode_str": "\u4f84"} -{"id": 5943, "token": "gs", "merges": "g s", "raw_count": 861523, "count": 1790141, "decode_str": "gs"} -{"id": 54014, "token": "\u00e8\u00ba\u00ac", "merges": "\u00e8\u00ba \u00ac", "raw_count": 1790335, "count": 1790335, "decode_str": "\u8eac"} -{"id": 10978, "token": "filter", "merges": "fil ter", "raw_count": 1791175, "count": 1791175, "decode_str": "filter"} -{"id": 699, "token": "fter", "merges": "f ter", "raw_count": 29952, "count": 1791419, "decode_str": "fter"} -{"id": 6402, "token": "MI", "merges": "M I", "raw_count": 1449097, "count": 1792770, "decode_str": "MI"} -{"id": 2562, "token": "iter", "merges": "it er", "raw_count": 1406055, "count": 1792805, "decode_str": "iter"} -{"id": 3837, "token": "Ad", "merges": "A d", "raw_count": 1280616, "count": 1793648, "decode_str": "Ad"} -{"id": 3322, "token": "UR", "merges": "U R", "raw_count": 673926, "count": 1793967, "decode_str": "UR"} -{"id": 51254, "token": "\u00e5\u0142\u00b0", "merges": "\u00e5\u0142 \u00b0", "raw_count": 1794425, "count": 1794425, "decode_str": "\u5830"} -{"id": 11313, "token": "ensor", "merges": "ens or", "raw_count": 139702, "count": 1795023, "decode_str": "ensor"} -{"id": 53487, "token": "\u00e8\u0124\u013d", "merges": "\u00e8\u0124 \u013d", "raw_count": 1796128, "count": 1796128, "decode_str": "\u809b"} -{"id": 8384, "token": "next", "merges": "ne xt", "raw_count": 1796968, "count": 1796968, "decode_str": "next"} -{"id": 3373, "token": "rc", "merges": "r c", "raw_count": 586344, "count": 1797016, "decode_str": "rc"} -{"id": 3453, "token": "\u0120output", "merges": "\u0120out put", "raw_count": 1571178, "count": 1797153, "decode_str": " output"} -{"id": 51150, "token": "\u00e5\u013b\u00bc", "merges": "\u00e5\u013b \u00bc", "raw_count": 1800266, "count": 1800266, "decode_str": "\u567c"} -{"id": 8606, "token": "find", "merges": "f ind", "raw_count": 1800838, "count": 1801005, "decode_str": "find"} -{"id": 1828, "token": "ccess", "merges": "cc ess", "raw_count": 30104, "count": 1801230, "decode_str": "ccess"} -{"id": 3431, "token": "dis", "merges": "d is", "raw_count": 614111, "count": 1801900, "decode_str": "dis"} -{"id": 1793, "token": "ference", "merges": "fe rence", "raw_count": 207401, "count": 1802478, "decode_str": "ference"} -{"id": 51341, "token": "\u00e5\u00a6\u0140", "merges": "\u00e5\u00a6 \u0140", "raw_count": 1802915, "count": 1802915, "decode_str": "\u599e"} -{"id": 1232, "token": "\u0120process", "merges": "\u0120pro cess", "raw_count": 1270779, "count": 1804599, "decode_str": " process"} -{"id": 53230, "token": "\u00e7\u0143\u013f", "merges": "\u00e7\u0143 \u013f", "raw_count": 1805714, "count": 1805714, "decode_str": "\u7b5d"} -{"id": 52843, "token": "\u00e7\u0132\u012b", "merges": "\u00e7\u0132 \u012b", "raw_count": 1805979, "count": 1805979, "decode_str": "\u7409"} -{"id": 25964, "token": "objects", "merges": "object s", "raw_count": 1806209, "count": 1806209, "decode_str": "objects"} -{"id": 15645, "token": "450", "merges": "4 50", "raw_count": 1806300, "count": 1806300, "decode_str": "450"} -{"id": 50602, "token": "\u00e4\u00bf\u013a", "merges": "\u00e4\u00bf \u013a", "raw_count": 1808796, "count": 1808796, "decode_str": "\u4fd8"} -{"id": 51562, "token": "\u00e5\u00ba\u0129", "merges": "\u00e5\u00ba \u0129", "raw_count": 1809060, "count": 1809060, "decode_str": "\u5e87"} -{"id": 50672, "token": "\u00e5\u0125\u00bb", "merges": "\u00e5\u0125 \u00bb", "raw_count": 1810497, "count": 1810497, "decode_str": "\u50fb"} -{"id": 52164, "token": "\u00e6\u013b\u00a4", "merges": "\u00e6\u013b \u00a4", "raw_count": 1811775, "count": 1811775, "decode_str": "\u6664"} -{"id": 9599, "token": "float", "merges": "fl oat", "raw_count": 1811950, "count": 1811950, "decode_str": "float"} -{"id": 51838, "token": "\u00e6\u012b\u0134", "merges": "\u00e6\u012b \u0134", "raw_count": 1813646, "count": 1813646, "decode_str": "\u6252"} -{"id": 1884, "token": "\u012030", "merges": "\u01203 0", "raw_count": 1669755, "count": 1814193, "decode_str": " 30"} -{"id": 4061, "token": "SC", "merges": "S C", "raw_count": 1775184, "count": 1817504, "decode_str": "SC"} -{"id": 19084, "token": "qq", "merges": "q q", "raw_count": 1817646, "count": 1817646, "decode_str": "qq"} -{"id": 54103, "token": "\u00e9\u0122\u012f", "merges": "\u00e9\u0122 \u012f", "raw_count": 1818447, "count": 1818447, "decode_str": "\u900d"} -{"id": 2805, "token": "\u0120q", "merges": "\u0120 q", "raw_count": 1819530, "count": 1819585, "decode_str": " q"} -{"id": 5382, "token": "\u0120item", "merges": "\u0120it em", "raw_count": 1820295, "count": 1820295, "decode_str": " item"} -{"id": 7263, "token": "\u0120tor", "merges": "\u0120t or", "raw_count": 41088, "count": 1821648, "decode_str": " tor"} -{"id": 15261, "token": "save", "merges": "s ave", "raw_count": 1822189, "count": 1822189, "decode_str": "save"} -{"id": 5472, "token": "IB", "merges": "I B", "raw_count": 747902, "count": 1823824, "decode_str": "IB"} -{"id": 54296, "token": "\u00e9\u013a\u0130", "merges": "\u00e9\u013a \u0130", "raw_count": 1826047, "count": 1826047, "decode_str": "\u960e"} -{"id": 787, "token": "\u0120bl", "merges": "\u0120b l", "raw_count": 196486, "count": 1827487, "decode_str": " bl"} -{"id": 3649, "token": "acc", "merges": "ac c", "raw_count": 664703, "count": 1832636, "decode_str": "acc"} -{"id": 715, "token": "\u0120into", "merges": "\u0120int o", "raw_count": 1832141, "count": 1834445, "decode_str": " into"} -{"id": 3068, "token": "umn", "merges": "um n", "raw_count": 28782, "count": 1835622, "decode_str": "umn"} -{"id": 1883, "token": "ream", "merges": "re am", "raw_count": 224546, "count": 1836164, "decode_str": "ream"} -{"id": 2505, "token": "\u0120text", "merges": "\u0120te xt", "raw_count": 1709789, "count": 1836549, "decode_str": " text"} -{"id": 7417, "token": "rip", "merges": "ri p", "raw_count": 548949, "count": 1838824, "decode_str": "rip"} -{"id": 52018, "token": "\u00e6\u0131\u00a3", "merges": "\u00e6\u0131 \u00a3", "raw_count": 1839058, "count": 1839058, "decode_str": "\u63e3"} -{"id": 53500, "token": "\u00e8\u0124\u00b4", "merges": "\u00e8\u0124 \u00b4", "raw_count": 1839090, "count": 1839090, "decode_str": "\u80b4"} -{"id": 1491, "token": "\u0120information", "merges": "\u0120in formation", "raw_count": 1839528, "count": 1839528, "decode_str": " information"} -{"id": 1547, "token": "\u0120hum", "merges": "\u0120h um", "raw_count": 35300, "count": 1839642, "decode_str": " hum"} -{"id": 14711, "token": "118", "merges": "11 8", "raw_count": 1839903, "count": 1839903, "decode_str": "118"} -{"id": 3899, "token": "met", "merges": "m et", "raw_count": 316670, "count": 1841949, "decode_str": "met"} -{"id": 34551, "token": "Returns", "merges": "Ret urns", "raw_count": 1843723, "count": 1843723, "decode_str": "Returns"} -{"id": 53348, "token": "\u00e7\u00bb\u013c", "merges": "\u00e7\u00bb \u013c", "raw_count": 1844021, "count": 1844021, "decode_str": "\u7eda"} -{"id": 1336, "token": "ters", "merges": "ter s", "raw_count": 363653, "count": 1845241, "decode_str": "ters"} -{"id": 4793, "token": "base", "merges": "b ase", "raw_count": 1846978, "count": 1846978, "decode_str": "base"} -{"id": 4071, "token": "ayer", "merges": "ay er", "raw_count": 97083, "count": 1847012, "decode_str": "ayer"} -{"id": 52639, "token": "\u00e6\u00b7\u00a4", "merges": "\u00e6\u00b7 \u00a4", "raw_count": 1847041, "count": 1847041, "decode_str": "\u6de4"} -{"id": 1765, "token": "ump", "merges": "um p", "raw_count": 247440, "count": 1847564, "decode_str": "ump"} -{"id": 5089, "token": "Test", "merges": "T est", "raw_count": 1517181, "count": 1849513, "decode_str": "Test"} -{"id": 54437, "token": "\u00e9\u00a2\u0127", "merges": "\u00e9\u00a2 \u0127", "raw_count": 1851042, "count": 1851042, "decode_str": "\u9885"} -{"id": 51482, "token": "\u00e5\u00b1\u012b", "merges": "\u00e5\u00b1 \u012b", "raw_count": 1855980, "count": 1855980, "decode_str": "\u5c49"} -{"id": 1808, "token": "ern", "merges": "er n", "raw_count": 290728, "count": 1856308, "decode_str": "ern"} -{"id": 1167, "token": "\u0120mem", "merges": "\u0120m em", "raw_count": 102550, "count": 1857748, "decode_str": " mem"} -{"id": 3544, "token": "ags", "merges": "ag s", "raw_count": 187861, "count": 1859074, "decode_str": "ags"} -{"id": 3180, "token": "odes", "merges": "od es", "raw_count": 238788, "count": 1859746, "decode_str": "odes"} -{"id": 6071, "token": "content", "merges": "cont ent", "raw_count": 1863494, "count": 1863494, "decode_str": "content"} -{"id": 12426, "token": "session", "merges": "s ession", "raw_count": 1862077, "count": 1863781, "decode_str": "session"} -{"id": 5996, "token": "post", "merges": "p ost", "raw_count": 1702659, "count": 1865052, "decode_str": "post"} -{"id": 1713, "token": "____", "merges": "__ __", "raw_count": 727997, "count": 1866186, "decode_str": "____"} -{"id": 4666, "token": "\u0120node", "merges": "\u0120n ode", "raw_count": 1866259, "count": 1866259, "decode_str": " node"} -{"id": 4608, "token": "hand", "merges": "h and", "raw_count": 464083, "count": 1868128, "decode_str": "hand"} -{"id": 784, "token": "ious", "merges": "i ous", "raw_count": 121685, "count": 1869427, "decode_str": "ious"} -{"id": 52490, "token": "\u00e6\u00b1\u00b9", "merges": "\u00e6\u00b1 \u00b9", "raw_count": 1870917, "count": 1870917, "decode_str": "\u6c79"} -{"id": 1661, "token": "rel", "merges": "re l", "raw_count": 917056, "count": 1872243, "decode_str": "rel"} -{"id": 2451, "token": "\u0120check", "merges": "\u0120che ck", "raw_count": 1576821, "count": 1872763, "decode_str": " check"} -{"id": 1086, "token": "\u0120dec", "merges": "\u0120de c", "raw_count": 200330, "count": 1875739, "decode_str": " dec"} -{"id": 51156, "token": "\u00e5\u013d\u013c", "merges": "\u00e5\u013d \u013c", "raw_count": 1875888, "count": 1875888, "decode_str": "\u56da"} -{"id": 3594, "token": "Gr", "merges": "G r", "raw_count": 549104, "count": 1877330, "decode_str": "Gr"} -{"id": 2936, "token": "\u0120ur", "merges": "\u0120 ur", "raw_count": 329789, "count": 1879115, "decode_str": " ur"} -{"id": 50762, "token": "\u00e5\u0129\u00bf", "merges": "\u00e5\u0129 \u00bf", "raw_count": 1879336, "count": 1879336, "decode_str": "\u51ff"} -{"id": 1279, "token": "any", "merges": "an y", "raw_count": 640810, "count": 1882164, "decode_str": "any"} -{"id": 52204, "token": "\u00e6\u013e\u00bd", "merges": "\u00e6\u013e \u00bd", "raw_count": 1882329, "count": 1882329, "decode_str": "\u673d"} -{"id": 3956, "token": "top", "merges": "t op", "raw_count": 1428142, "count": 1882726, "decode_str": "top"} -{"id": 625, "token": "\u0120more", "merges": "\u0120m ore", "raw_count": 1871148, "count": 1885828, "decode_str": " more"} -{"id": 51603, "token": "\u00e5\u00bc\u013d", "merges": "\u00e5\u00bc \u013d", "raw_count": 1885892, "count": 1885892, "decode_str": "\u5f1b"} -{"id": 51211, "token": "\u00e5\u013f\u00af", "merges": "\u00e5\u013f \u00af", "raw_count": 1886379, "count": 1886379, "decode_str": "\u576f"} -{"id": 3205, "token": "iles", "merges": "il es", "raw_count": 215706, "count": 1887768, "decode_str": "iles"} -{"id": 627, "token": "\u0120there", "merges": "\u0120the re", "raw_count": 1470412, "count": 1888523, "decode_str": " there"} -{"id": 2874, "token": "001", "merges": "00 1", "raw_count": 1888885, "count": 1888885, "decode_str": "001"} -{"id": 521, "token": "\u0120his", "merges": "\u0120h is", "raw_count": 1890283, "count": 1890283, "decode_str": " his"} -{"id": 1370, "token": "az", "merges": "a z", "raw_count": 780852, "count": 1891809, "decode_str": "az"} -{"id": 1329, "token": "\u0120support", "merges": "\u0120supp ort", "raw_count": 1318572, "count": 1891897, "decode_str": " support"} -{"id": 1358, "token": "://", "merges": ": //", "raw_count": 1892061, "count": 1892061, "decode_str": "://"} -{"id": 52960, "token": "\u00e7\u013b\u00a3", "merges": "\u00e7\u013b \u00a3", "raw_count": 1892214, "count": 1892214, "decode_str": "\u7663"} -{"id": 862, "token": "olog", "merges": "ol og", "raw_count": 73780, "count": 1893995, "decode_str": "olog"} -{"id": 52088, "token": "\u00e6\u0138\u0132", "merges": "\u00e6\u0138 \u0132", "raw_count": 1894675, "count": 1894675, "decode_str": "\u6590"} -{"id": 54421, "token": "\u00e9\u0141\u00b6", "merges": "\u00e9\u0141 \u00b6", "raw_count": 1894709, "count": 1894709, "decode_str": "\u97f6"} -{"id": 3979, "token": "BC", "merges": "B C", "raw_count": 1122415, "count": 1896332, "decode_str": "BC"} -{"id": 53650, "token": "\u00e8\u012d\u0141", "merges": "\u00e8\u012d \u0141", "raw_count": 1897735, "count": 1897735, "decode_str": "\u82df"} -{"id": 7700, "token": "bug", "merges": "b ug", "raw_count": 570968, "count": 1898681, "decode_str": "bug"} -{"id": 2440, "token": "\u0120development", "merges": "\u0120develop ment", "raw_count": 1888433, "count": 1899834, "decode_str": " development"} -{"id": 2621, "token": "order", "merges": "or der", "raw_count": 1463127, "count": 1901325, "decode_str": "order"} -{"id": 51228, "token": "\u00e5\u0140\u00ae", "merges": "\u00e5\u0140 \u00ae", "raw_count": 1903044, "count": 1903044, "decode_str": "\u57ae"} -{"id": 2974, "token": "html", "merges": "ht ml", "raw_count": 1888554, "count": 1905028, "decode_str": "html"} -{"id": 4237, "token": "EX", "merges": "E X", "raw_count": 1464194, "count": 1905605, "decode_str": "EX"} -{"id": 53540, "token": "\u00e8\u0126\u0132", "merges": "\u00e8\u0126 \u0132", "raw_count": 1905858, "count": 1905858, "decode_str": "\u8110"} -{"id": 52819, "token": "\u00e7\u0131\u0122", "merges": "\u00e7\u0131 \u0122", "raw_count": 1906391, "count": 1906391, "decode_str": "\u73c0"} -{"id": 1368, "token": "oh", "merges": "o h", "raw_count": 691229, "count": 1907448, "decode_str": "oh"} -{"id": 5781, "token": "aa", "merges": "a a", "raw_count": 1227274, "count": 1907727, "decode_str": "aa"} -{"id": 54517, "token": "\u00e9\u00aa\u00bc", "merges": "\u00e9\u00aa \u00bc", "raw_count": 1910445, "count": 1910445, "decode_str": "\u9abc"} -{"id": 3596, "token": "\u0120config", "merges": "\u0120con fig", "raw_count": 1464446, "count": 1911238, "decode_str": " config"} -{"id": 17479, "token": "filename", "merges": "fil ename", "raw_count": 1916363, "count": 1916363, "decode_str": "filename"} -{"id": 380, "token": "\u0120The", "merges": "\u0120T he", "raw_count": 1765903, "count": 1918698, "decode_str": " The"} -{"id": 51892, "token": "\u00e6\u012d\u0124", "merges": "\u00e6\u012d \u0124", "raw_count": 1918831, "count": 1918831, "decode_str": "\u62c2"} -{"id": 53861, "token": "\u00e8\u00b0\u012f", "merges": "\u00e8\u00b0 \u012f", "raw_count": 1918868, "count": 1918868, "decode_str": "\u8c0d"} -{"id": 51036, "token": "\u00e5\u0134\u00a7", "merges": "\u00e5\u0134 \u00a7", "raw_count": 1918966, "count": 1918966, "decode_str": "\u54a7"} -{"id": 1150, "token": "\u0120loc", "merges": "\u0120l oc", "raw_count": 171621, "count": 1919099, "decode_str": " loc"} -{"id": 52676, "token": "\u00e6\u00ba\u0127", "merges": "\u00e6\u00ba \u0127", "raw_count": 1919842, "count": 1919842, "decode_str": "\u6e85"} -{"id": 54364, "token": "\u00e9\u013d\u012e", "merges": "\u00e9\u013d \u012e", "raw_count": 1923229, "count": 1923229, "decode_str": "\u96cc"} -{"id": 23941, "token": "batch", "merges": "b atch", "raw_count": 1925117, "count": 1925117, "decode_str": "batch"} -{"id": 1041, "token": "hes", "merges": "he s", "raw_count": 309231, "count": 1927904, "decode_str": "hes"} -{"id": 51444, "token": "\u00e5\u00af\u00a5", "merges": "\u00e5\u00af \u00a5", "raw_count": 1928620, "count": 1928620, "decode_str": "\u5be5"} -{"id": 53076, "token": "\u00e7\u00a1\u0134", "merges": "\u00e7\u00a1 \u0134", "raw_count": 1929243, "count": 1929243, "decode_str": "\u7852"} -{"id": 2618, "token": "Id", "merges": "I d", "raw_count": 1618001, "count": 1930929, "decode_str": "Id"} -{"id": 4514, "token": "\u0120commit", "merges": "\u0120comm it", "raw_count": 141230, "count": 1930985, "decode_str": " commit"} -{"id": 12731, "token": "1995", "merges": "19 95", "raw_count": 1934310, "count": 1934310, "decode_str": "1995"} -{"id": 1688, "token": "hor", "merges": "h or", "raw_count": 144979, "count": 1934744, "decode_str": "hor"} -{"id": 2775, "token": "CH", "merges": "C H", "raw_count": 1340525, "count": 1935071, "decode_str": "CH"} -{"id": 52334, "token": "\u00e6\u00a3\u00ba", "merges": "\u00e6\u00a3 \u00ba", "raw_count": 1935426, "count": 1935426, "decode_str": "\u68fa"} -{"id": 4149, "token": "version", "merges": "vers ion", "raw_count": 1783942, "count": 1935497, "decode_str": "version"} -{"id": 12487, "token": "1996", "merges": "199 6", "raw_count": 1936530, "count": 1936530, "decode_str": "1996"} -{"id": 1655, "token": "\u0120current", "merges": "\u0120cur rent", "raw_count": 1670362, "count": 1936672, "decode_str": " current"} -{"id": 50666, "token": "\u00e5\u0125\u013c", "merges": "\u00e5\u0125 \u013c", "raw_count": 1938709, "count": 1938709, "decode_str": "\u50da"} -{"id": 2420, "token": "table", "merges": "t able", "raw_count": 1939604, "count": 1939604, "decode_str": "table"} -{"id": 4113, "token": "ui", "merges": "u i", "raw_count": 1479618, "count": 1939679, "decode_str": "ui"} -{"id": 51249, "token": "\u00e5\u0142\u0137", "merges": "\u00e5\u0142 \u0137", "raw_count": 1940795, "count": 1940795, "decode_str": "\u5815"} -{"id": 934, "token": "ble", "merges": "b le", "raw_count": 264458, "count": 1941025, "decode_str": "ble"} -{"id": 52778, "token": "\u00e7\u012b\u0141", "merges": "\u00e7\u012b \u0141", "raw_count": 1941692, "count": 1941692, "decode_str": "\u725f"} -{"id": 50933, "token": "\u00e5\u0131\u00a8", "merges": "\u00e5\u0131 \u00a8", "raw_count": 1942974, "count": 1942974, "decode_str": "\u53e8"} -{"id": 5465, "token": "host", "merges": "h ost", "raw_count": 1563637, "count": 1944049, "decode_str": "host"} -{"id": 1486, "token": "\u0120err", "merges": "\u0120 err", "raw_count": 402803, "count": 1944410, "decode_str": " err"} -{"id": 12390, "token": "\u0120nations", "merges": "\u0120n ations", "raw_count": 1945393, "count": 1945393, "decode_str": " nations"} -{"id": 52058, "token": "\u00e6\u0136\u0134", "merges": "\u00e6\u0136 \u0134", "raw_count": 1946324, "count": 1946324, "decode_str": "\u6512"} -{"id": 2935, "token": "resh", "merges": "res h", "raw_count": 732024, "count": 1946493, "decode_str": "resh"} -{"id": 792, "token": "ular", "merges": "ul ar", "raw_count": 197754, "count": 1946719, "decode_str": "ular"} -{"id": 999, "token": "ew", "merges": "e w", "raw_count": 361498, "count": 1947671, "decode_str": "ew"} -{"id": 51500, "token": "\u00e5\u00b7\u012f", "merges": "\u00e5\u00b7 \u012f", "raw_count": 1951741, "count": 1951741, "decode_str": "\u5dcd"} -{"id": 4132, "token": "ML", "merges": "M L", "raw_count": 1056449, "count": 1951825, "decode_str": "ML"} -{"id": 16159, "token": "idx", "merges": "id x", "raw_count": 1953177, "count": 1953177, "decode_str": "idx"} -{"id": 53778, "token": "\u00e8\u0143\u00ac", "merges": "\u00e8\u0143 \u00ac", "raw_count": 1953432, "count": 1953432, "decode_str": "\u8b6c"} -{"id": 1125, "token": "\u0120aut", "merges": "\u0120a ut", "raw_count": 120253, "count": 1957220, "decode_str": " aut"} -{"id": 53139, "token": "\u00e7\u00a6\u00a7", "merges": "\u00e7\u00a6 \u00a7", "raw_count": 1958485, "count": 1958485, "decode_str": "\u79a7"} -{"id": 1687, "token": "cript", "merges": "c ript", "raw_count": 86183, "count": 1959506, "decode_str": "cript"} -{"id": 5564, "token": "title", "merges": "t itle", "raw_count": 1959523, "count": 1959523, "decode_str": "title"} -{"id": 50910, "token": "\u00e5\u0130\u00a5", "merges": "\u00e5\u0130 \u00a5", "raw_count": 1959579, "count": 1959579, "decode_str": "\u53a5"} -{"id": 5070, "token": "place", "merges": "pl ace", "raw_count": 540359, "count": 1959986, "decode_str": "place"} -{"id": 904, "token": ".,", "merges": ". ,", "raw_count": 1527495, "count": 1964432, "decode_str": ".,"} -{"id": 53292, "token": "\u00e7\u00b4\u012c", "merges": "\u00e7\u00b4 \u012c", "raw_count": 1965858, "count": 1965858, "decode_str": "\u7d0a"} -{"id": 878, "token": "\u0120need", "merges": "\u0120ne ed", "raw_count": 1102172, "count": 1966052, "decode_str": " need"} -{"id": 53795, "token": "\u00e8\u00ae\u00b3", "merges": "\u00e8\u00ae \u00b3", "raw_count": 1966186, "count": 1966186, "decode_str": "\u8bb3"} -{"id": 1265, "token": "\u0120start", "merges": "\u0120st art", "raw_count": 1517795, "count": 1966961, "decode_str": " start"} -{"id": 2679, "token": "ache", "merges": "ac he", "raw_count": 185996, "count": 1967673, "decode_str": "ache"} -{"id": 1304, "token": "\u0120report", "merges": "\u0120re port", "raw_count": 1182731, "count": 1973199, "decode_str": " report"} -{"id": 3227, "token": "ha", "merges": "h a", "raw_count": 1644534, "count": 1973246, "decode_str": "ha"} -{"id": 12787, "token": "pred", "merges": "p red", "raw_count": 1571484, "count": 1973439, "decode_str": "pred"} -{"id": 497, "token": "\u0120were", "merges": "\u0120we re", "raw_count": 1974047, "count": 1974047, "decode_str": " were"} -{"id": 52910, "token": "\u00e7\u0138\u00a1", "merges": "\u00e7\u0138 \u00a1", "raw_count": 1974976, "count": 1974976, "decode_str": "\u75a1"} -{"id": 52563, "token": "\u00e6\u00b4\u00b1", "merges": "\u00e6\u00b4 \u00b1", "raw_count": 1975415, "count": 1975415, "decode_str": "\u6d31"} -{"id": 54489, "token": "\u00e9\u00aa\u0123", "merges": "\u00e9\u00aa \u0123", "raw_count": 1975822, "count": 1975822, "decode_str": "\u9a81"} -{"id": 13724, "token": "!)", "merges": "! )", "raw_count": 1982317, "count": 1982317, "decode_str": "!)"} -{"id": 52750, "token": "\u00e7\u0126\u013b", "merges": "\u00e7\u0126 \u013b", "raw_count": 1988311, "count": 1988311, "decode_str": "\u7119"} -{"id": 12347, "token": "108", "merges": "10 8", "raw_count": 1989615, "count": 1989615, "decode_str": "108"} -{"id": 7404, "token": "process", "merges": "pro cess", "raw_count": 1485174, "count": 1989808, "decode_str": "process"} -{"id": 51551, "token": "\u00e5\u00b9\u00a2", "merges": "\u00e5\u00b9 \u00a2", "raw_count": 1991145, "count": 1991145, "decode_str": "\u5e62"} -{"id": 9312, "token": "125", "merges": "12 5", "raw_count": 1993907, "count": 1993907, "decode_str": "125"} -{"id": 866, "token": "\u0120exp", "merges": "\u0120ex p", "raw_count": 359018, "count": 1994048, "decode_str": " exp"} -{"id": 51057, "token": "\u00e5\u0135\u012b", "merges": "\u00e5\u0135 \u012b", "raw_count": 1995295, "count": 1995295, "decode_str": "\u54c9"} -{"id": 10201, "token": "PV", "merges": "P V", "raw_count": 1994356, "count": 1995312, "decode_str": "PV"} -{"id": 52331, "token": "\u00e6\u00a3\u00b1", "merges": "\u00e6\u00a3 \u00b1", "raw_count": 1995995, "count": 1995995, "decode_str": "\u68f1"} -{"id": 6986, "token": "default", "merges": "def ault", "raw_count": 1816695, "count": 1997009, "decode_str": "default"} -{"id": 25116, "token": "Facebook", "merges": "F acebook", "raw_count": 1997263, "count": 1997263, "decode_str": "Facebook"} -{"id": 828, "token": "\u0120inv", "merges": "\u0120in v", "raw_count": 107226, "count": 1997864, "decode_str": " inv"} -{"id": 23405, "token": "'])", "merges": "' ])", "raw_count": 1999510, "count": 1999510, "decode_str": "'])"} -{"id": 1498, "token": "serv", "merges": "s erv", "raw_count": 112519, "count": 2000324, "decode_str": "serv"} -{"id": 51867, "token": "\u00e6\u012c\u0134", "merges": "\u00e6\u012c \u0134", "raw_count": 2005083, "count": 2005083, "decode_str": "\u6292"} -{"id": 14340, "token": "cn", "merges": "c n", "raw_count": 2006967, "count": 2006967, "decode_str": "cn"} -{"id": 51384, "token": "\u00e5\u0143\u013e", "merges": "\u00e5\u0143 \u013e", "raw_count": 2007278, "count": 2007278, "decode_str": "\u5b5c"} -{"id": 50711, "token": "\u00e5\u0128\u012b", "merges": "\u00e5\u0128 \u012b", "raw_count": 2009633, "count": 2009633, "decode_str": "\u5189"} -{"id": 46289, "token": ".\"\"\"", "merges": ".\" \"\"", "raw_count": 2011194, "count": 2011194, "decode_str": ".\"\"\""} -{"id": 689, "token": "\u0120over", "merges": "\u0120o ver", "raw_count": 1195701, "count": 2013491, "decode_str": " over"} -{"id": 758, "token": "ced", "merges": "c ed", "raw_count": 111568, "count": 2013877, "decode_str": "ced"} -{"id": 6145, "token": "acebook", "merges": "ace book", "raw_count": 2050, "count": 2014655, "decode_str": "acebook"} -{"id": 54201, "token": "\u00e9\u0127\u00ae", "merges": "\u00e9\u0127 \u00ae", "raw_count": 2015703, "count": 2015703, "decode_str": "\u916e"} -{"id": 1075, "token": "ention", "merges": "ent ion", "raw_count": 120549, "count": 2018681, "decode_str": "ention"} -{"id": 53485, "token": "\u00e8\u0124\u013a", "merges": "\u00e8\u0124 \u013a", "raw_count": 2019749, "count": 2019749, "decode_str": "\u8098"} -{"id": 1748, "token": "vert", "merges": "ver t", "raw_count": 364831, "count": 2020231, "decode_str": "vert"} -{"id": 9723, "token": "root", "merges": "ro ot", "raw_count": 2023773, "count": 2023773, "decode_str": "root"} -{"id": 51896, "token": "\u00e6\u012d\u0129", "merges": "\u00e6\u012d \u0129", "raw_count": 2023823, "count": 2023823, "decode_str": "\u62c7"} -{"id": 6081, "token": "izer", "merges": "iz er", "raw_count": 1877387, "count": 2027216, "decode_str": "izer"} -{"id": 2066, "token": "uff", "merges": "u ff", "raw_count": 158396, "count": 2027326, "decode_str": "uff"} -{"id": 52374, "token": "\u00e6\u00a9\u0126", "merges": "\u00e6\u00a9 \u0126", "raw_count": 2029923, "count": 2029923, "decode_str": "\u6a44"} -{"id": 10029, "token": "urns", "merges": "urn s", "raw_count": 50494, "count": 2032353, "decode_str": "urns"} -{"id": 52189, "token": "\u00e6\u013e\u0136", "merges": "\u00e6\u013e \u0136", "raw_count": 2033471, "count": 2033471, "decode_str": "\u6714"} -{"id": 1668, "token": "\u012016", "merges": "\u01201 6", "raw_count": 1766933, "count": 2033845, "decode_str": " 16"} -{"id": 4636, "token": "ample", "merges": "am ple", "raw_count": 140169, "count": 2034816, "decode_str": "ample"} -{"id": 1081, "token": "\u0120bu", "merges": "\u0120b u", "raw_count": 39003, "count": 2035581, "decode_str": " bu"} -{"id": 54085, "token": "\u00e8\u00bf\u00a6", "merges": "\u00e8\u00bf \u00a6", "raw_count": 2036110, "count": 2036110, "decode_str": "\u8fe6"} -{"id": 14028, "token": "240", "merges": "24 0", "raw_count": 2040956, "count": 2040956, "decode_str": "240"} -{"id": 1017, "token": "ower", "merges": "ow er", "raw_count": 187661, "count": 2040967, "decode_str": "ower"} -{"id": 2140, "token": "sw", "merges": "s w", "raw_count": 1057241, "count": 2044029, "decode_str": "sw"} -{"id": 2146, "token": "ler", "merges": "l er", "raw_count": 536810, "count": 2047260, "decode_str": "ler"} -{"id": 2633, "token": "rix", "merges": "ri x", "raw_count": 83508, "count": 2049180, "decode_str": "rix"} -{"id": 3351, "token": "Im", "merges": "I m", "raw_count": 677843, "count": 2050385, "decode_str": "Im"} -{"id": 1105, "token": "ym", "merges": "y m", "raw_count": 539033, "count": 2051025, "decode_str": "ym"} -{"id": 2023, "token": "},", "merges": "} ,", "raw_count": 1473577, "count": 2051170, "decode_str": "},"} -{"id": 53631, "token": "\u00e8\u012c\u00b8", "merges": "\u00e8\u012c \u00b8", "raw_count": 2053615, "count": 2053615, "decode_str": "\u82b8"} -{"id": 52680, "token": "\u00e6\u00ba\u013e", "merges": "\u00e6\u00ba \u013e", "raw_count": 2055540, "count": 2055540, "decode_str": "\u6e9c"} -{"id": 52148, "token": "\u00e6\u013a\u00bc", "merges": "\u00e6\u013a \u00bc", "raw_count": 2057415, "count": 2057415, "decode_str": "\u663c"} -{"id": 826, "token": "\u0120la", "merges": "\u0120l a", "raw_count": 395517, "count": 2061397, "decode_str": " la"} -{"id": 1767, "token": "yt", "merges": "y t", "raw_count": 1613714, "count": 2063764, "decode_str": "yt"} -{"id": 54199, "token": "\u00e9\u0127\u00aa", "merges": "\u00e9\u0127 \u00aa", "raw_count": 2064817, "count": 2064817, "decode_str": "\u916a"} -{"id": 6113, "token": "cs", "merges": "c s", "raw_count": 1147680, "count": 2067387, "decode_str": "cs"} -{"id": 2003, "token": "part", "merges": "p art", "raw_count": 921914, "count": 2068867, "decode_str": "part"} -{"id": 52363, "token": "\u00e6\u00a8\u012c", "merges": "\u00e6\u00a8 \u012c", "raw_count": 2069419, "count": 2069419, "decode_str": "\u6a0a"} -{"id": 3207, "token": "CL", "merges": "C L", "raw_count": 1745613, "count": 2073548, "decode_str": "CL"} -{"id": 1664, "token": "face", "merges": "f ace", "raw_count": 440791, "count": 2074188, "decode_str": "face"} -{"id": 53744, "token": "\u00e8\u00a3\u00b4", "merges": "\u00e8\u00a3 \u00b4", "raw_count": 2075041, "count": 2075041, "decode_str": "\u88f4"} -{"id": 1067, "token": "\u0120call", "merges": "\u0120c all", "raw_count": 839835, "count": 2076183, "decode_str": " call"} -{"id": 34691, "token": "1600", "merges": "16 00", "raw_count": 2076690, "count": 2076690, "decode_str": "1600"} -{"id": 1696, "token": "htt", "merges": "ht t", "raw_count": 34143, "count": 2076984, "decode_str": "htt"} -{"id": 7332, "token": "gt", "merges": "g t", "raw_count": 2020995, "count": 2077260, "decode_str": "gt"} -{"id": 53632, "token": "\u00e8\u012c\u00b9", "merges": "\u00e8\u012c \u00b9", "raw_count": 2077641, "count": 2077641, "decode_str": "\u82b9"} -{"id": 762, "token": "\u0120under", "merges": "\u0120un der", "raw_count": 1327482, "count": 2080075, "decode_str": " under"} -{"id": 15565, "token": "items", "merges": "it ems", "raw_count": 2080717, "count": 2080717, "decode_str": "items"} -{"id": 1154, "token": "cent", "merges": "c ent", "raw_count": 586003, "count": 2084314, "decode_str": "cent"} -{"id": 574, "token": "\u0120had", "merges": "\u0120h ad", "raw_count": 2076347, "count": 2085560, "decode_str": " had"} -{"id": 51959, "token": "\u00e6\u012f\u0124", "merges": "\u00e6\u012f \u0124", "raw_count": 2087008, "count": 2087008, "decode_str": "\u6342"} -{"id": 53480, "token": "\u00e8\u0124\u012d", "merges": "\u00e8\u0124 \u012d", "raw_count": 2087908, "count": 2087908, "decode_str": "\u808b"} -{"id": 51432, "token": "\u00e5\u00af\u0127", "merges": "\u00e5\u00af \u0127", "raw_count": 2091057, "count": 2091057, "decode_str": "\u5bc5"} -{"id": 54343, "token": "\u00e9\u013c\u012d", "merges": "\u00e9\u013c \u012d", "raw_count": 2092220, "count": 2092220, "decode_str": "\u968b"} -{"id": 2412, "token": "\u0120log", "merges": "\u0120l og", "raw_count": 996861, "count": 2092855, "decode_str": " log"} -{"id": 5983, "token": "'.", "merges": "' .", "raw_count": 2098030, "count": 2098030, "decode_str": "'."} -{"id": 52985, "token": "\u00e7\u013d\u0130", "merges": "\u00e7\u013d \u0130", "raw_count": 2099161, "count": 2099161, "decode_str": "\u76ce"} -{"id": 53276, "token": "\u00e7\u00b2\u00bd", "merges": "\u00e7\u00b2 \u00bd", "raw_count": 2099163, "count": 2099163, "decode_str": "\u7cbd"} -{"id": 50790, "token": "\u00e5\u012b\u0125", "merges": "\u00e5\u012b \u0125", "raw_count": 2099763, "count": 2099763, "decode_str": "\u5243"} -{"id": 53528, "token": "\u00e8\u0125\u00b3", "merges": "\u00e8\u0125 \u00b3", "raw_count": 2100802, "count": 2100802, "decode_str": "\u80f3"} -{"id": 2184, "token": "go", "merges": "g o", "raw_count": 947253, "count": 2104998, "decode_str": "go"} -{"id": 53108, "token": "\u00e7\u00a5\u0123", "merges": "\u00e7\u00a5 \u0123", "raw_count": 2106190, "count": 2106190, "decode_str": "\u7941"} -{"id": 1593, "token": "ional", "merges": "ion al", "raw_count": 185595, "count": 2108421, "decode_str": "ional"} -{"id": 51336, "token": "\u00e5\u00a6\u0134", "merges": "\u00e5\u00a6 \u0134", "raw_count": 2112283, "count": 2112283, "decode_str": "\u5992"} -{"id": 857, "token": "ond", "merges": "on d", "raw_count": 278731, "count": 2112587, "decode_str": "ond"} -{"id": 52410, "token": "\u00e6\u0143\u00bc", "merges": "\u00e6\u0143 \u00bc", "raw_count": 2112780, "count": 2112780, "decode_str": "\u6b7c"} -{"id": 54407, "token": "\u00e9\u013f\u00a1", "merges": "\u00e9\u013f \u00a1", "raw_count": 2113303, "count": 2113303, "decode_str": "\u9761"} -{"id": 51146, "token": "\u00e5\u013b\u00ac", "merges": "\u00e5\u013b \u00ac", "raw_count": 2114846, "count": 2114846, "decode_str": "\u566c"} -{"id": 874, "token": "ility", "merges": "il ity", "raw_count": 180880, "count": 2116124, "decode_str": "ility"} -{"id": 51224, "token": "\u00e5\u0140\u00a6", "merges": "\u00e5\u0140 \u00a6", "raw_count": 2116744, "count": 2116744, "decode_str": "\u57a6"} -{"id": 53185, "token": "\u00e7\u00a9\u0139", "merges": "\u00e7\u00a9 \u0139", "raw_count": 2117339, "count": 2117339, "decode_str": "\u7a57"} -{"id": 47227, "token": "2500", "merges": "25 00", "raw_count": 2118007, "count": 2118007, "decode_str": "2500"} -{"id": 600, "token": "ely", "merges": "el y", "raw_count": 175259, "count": 2118390, "decode_str": "ely"} -{"id": 2654, "token": "\u0120id", "merges": "\u0120 id", "raw_count": 1547761, "count": 2119690, "decode_str": " id"} -{"id": 13763, "token": "token", "merges": "t oken", "raw_count": 2120598, "count": 2120598, "decode_str": "token"} -{"id": 666, "token": "aus", "merges": "a us", "raw_count": 153403, "count": 2121066, "decode_str": "aus"} -{"id": 52179, "token": "\u00e6\u013d\u00a6", "merges": "\u00e6\u013d \u00a6", "raw_count": 2122202, "count": 2122202, "decode_str": "\u66e6"} -{"id": 53300, "token": "\u00e7\u00b5\u00ae", "merges": "\u00e7\u00b5 \u00ae", "raw_count": 2122390, "count": 2122390, "decode_str": "\u7d6e"} -{"id": 10294, "token": "km", "merges": "k m", "raw_count": 2123789, "count": 2123789, "decode_str": "km"} -{"id": 2856, "token": "\u0120dat", "merges": "\u0120d at", "raw_count": 309005, "count": 2124378, "decode_str": " dat"} -{"id": 6050, "token": "while", "merges": "wh ile", "raw_count": 2110124, "count": 2124990, "decode_str": "while"} -{"id": 51564, "token": "\u00e5\u00ba\u0132", "merges": "\u00e5\u00ba \u0132", "raw_count": 2125410, "count": 2125410, "decode_str": "\u5e90"} -{"id": 50544, "token": "\u00e4\u00bc\u00ba", "merges": "\u00e4\u00bc \u00ba", "raw_count": 2125936, "count": 2125936, "decode_str": "\u4f3a"} -{"id": 52030, "token": "\u00e6\u0134\u0129", "merges": "\u00e6\u0134 \u0129", "raw_count": 2126048, "count": 2126048, "decode_str": "\u6487"} -{"id": 1196, "token": "rence", "merges": "ren ce", "raw_count": 124420, "count": 2126201, "decode_str": "rence"} -{"id": 54411, "token": "\u00e9\u013f\u00b4", "merges": "\u00e9\u013f \u00b4", "raw_count": 2126222, "count": 2126222, "decode_str": "\u9774"} -{"id": 54307, "token": "\u00e9\u013a\u00ae", "merges": "\u00e9\u013a \u00ae", "raw_count": 2127390, "count": 2127390, "decode_str": "\u962e"} -{"id": 51163, "token": "\u00e5\u013d\u00a4", "merges": "\u00e5\u013d \u00a4", "raw_count": 2129342, "count": 2129342, "decode_str": "\u56e4"} -{"id": 1478, "token": "\u0120opt", "merges": "\u0120o pt", "raw_count": 279506, "count": 2133215, "decode_str": " opt"} -{"id": 975, "token": "ublic", "merges": "ub lic", "raw_count": 7118, "count": 2134000, "decode_str": "ublic"} -{"id": 51094, "token": "\u00e5\u0137\u00aa", "merges": "\u00e5\u0137 \u00aa", "raw_count": 2134711, "count": 2134711, "decode_str": "\u556a"} -{"id": 54154, "token": "\u00e9\u0124\u00a2", "merges": "\u00e9\u0124 \u00a2", "raw_count": 2135334, "count": 2135334, "decode_str": "\u90a2"} -{"id": 12185, "token": "super", "merges": "su per", "raw_count": 2118562, "count": 2135682, "decode_str": "super"} -{"id": 867, "token": "\u0120rem", "merges": "\u0120re m", "raw_count": 90344, "count": 2136830, "decode_str": " rem"} -{"id": 1938, "token": "opy", "merges": "op y", "raw_count": 70025, "count": 2137363, "decode_str": "opy"} -{"id": 3229, "token": "des", "merges": "d es", "raw_count": 592441, "count": 2138101, "decode_str": "des"} -{"id": 53816, "token": "\u00e8\u00af\u0131", "merges": "\u00e8\u00af \u0131", "raw_count": 2138207, "count": 2138207, "decode_str": "\u8bcf"} -{"id": 5902, "token": "pc", "merges": "p c", "raw_count": 1986978, "count": 2138435, "decode_str": "pc"} -{"id": 53048, "token": "\u00e7\u0141\u00b6", "merges": "\u00e7\u0141 \u00b6", "raw_count": 2138457, "count": 2138457, "decode_str": "\u77f6"} -{"id": 52841, "token": "\u00e7\u0132\u0127", "merges": "\u00e7\u0132 \u0127", "raw_count": 2141548, "count": 2141548, "decode_str": "\u7405"} -{"id": 2447, "token": "Un", "merges": "U n", "raw_count": 805631, "count": 2143205, "decode_str": "Un"} -{"id": 770, "token": "itt", "merges": "it t", "raw_count": 329175, "count": 2144402, "decode_str": "itt"} -{"id": 704, "token": "\u0120fe", "merges": "\u0120f e", "raw_count": 213869, "count": 2145203, "decode_str": " fe"} -{"id": 51465, "token": "\u00e5\u00b0\u00a7", "merges": "\u00e5\u00b0 \u00a7", "raw_count": 2146070, "count": 2146070, "decode_str": "\u5c27"} -{"id": 52328, "token": "\u00e6\u00a3\u0142", "merges": "\u00e6\u00a3 \u0142", "raw_count": 2147297, "count": 2147297, "decode_str": "\u68e0"} -{"id": 1903, "token": "\u012011", "merges": "\u01201 1", "raw_count": 2113464, "count": 2147559, "decode_str": " 11"} -{"id": 711, "token": "\u0120des", "merges": "\u0120d es", "raw_count": 200344, "count": 2149220, "decode_str": " des"} -{"id": 52190, "token": "\u00e6\u013e\u0137", "merges": "\u00e6\u013e \u0137", "raw_count": 2150436, "count": 2150436, "decode_str": "\u6715"} -{"id": 54304, "token": "\u00e9\u013a\u013e", "merges": "\u00e9\u013a \u013e", "raw_count": 2150604, "count": 2150604, "decode_str": "\u961c"} -{"id": 54237, "token": "\u00e9\u0136\u00a5", "merges": "\u00e9\u0136 \u00a5", "raw_count": 2153275, "count": 2153275, "decode_str": "\u9525"} -{"id": 1369, "token": "amb", "merges": "am b", "raw_count": 368365, "count": 2156240, "decode_str": "amb"} -{"id": 50626, "token": "\u00e5\u0122\u013c", "merges": "\u00e5\u0122 \u013c", "raw_count": 2156469, "count": 2156469, "decode_str": "\u501a"} -{"id": 4528, "token": "dim", "merges": "d im", "raw_count": 1980615, "count": 2158297, "decode_str": "dim"} -{"id": 2781, "token": "\u0120max", "merges": "\u0120m ax", "raw_count": 1882142, "count": 2158749, "decode_str": " max"} -{"id": 3456, "token": "pre", "merges": "p re", "raw_count": 963595, "count": 2159854, "decode_str": "pre"} -{"id": 982, "token": "ics", "merges": "ic s", "raw_count": 731920, "count": 2160741, "decode_str": "ics"} -{"id": 3018, "token": "plement", "merges": "ple ment", "raw_count": 78283, "count": 2161151, "decode_str": "plement"} -{"id": 1395, "token": "\u0120import", "merges": "\u0120im port", "raw_count": 1314688, "count": 2162338, "decode_str": " import"} -{"id": 1025, "token": "ized", "merges": "iz ed", "raw_count": 971438, "count": 2163809, "decode_str": "ized"} -{"id": 1566, "token": "\u0120model", "merges": "\u0120mod el", "raw_count": 2148238, "count": 2166477, "decode_str": " model"} -{"id": 52344, "token": "\u00e6\u00a5\u00b7", "merges": "\u00e6\u00a5 \u00b7", "raw_count": 2167079, "count": 2167079, "decode_str": "\u6977"} -{"id": 2446, "token": "AA", "merges": "A A", "raw_count": 1167019, "count": 2168247, "decode_str": "AA"} -{"id": 1898, "token": "And", "merges": "An d", "raw_count": 659233, "count": 2168297, "decode_str": "And"} -{"id": 738, "token": "fect", "merges": "fe ct", "raw_count": 43508, "count": 2170309, "decode_str": "fect"} -{"id": 25463, "token": "10000", "merges": "1 0000", "raw_count": 2170833, "count": 2170833, "decode_str": "10000"} -{"id": 47337, "token": "\u0120isinstance", "merges": "\u0120is instance", "raw_count": 2171002, "count": 2171002, "decode_str": " isinstance"} -{"id": 51067, "token": "\u00e5\u0135\u0139", "merges": "\u00e5\u0135 \u0139", "raw_count": 2171475, "count": 2171475, "decode_str": "\u54d7"} -{"id": 12430, "token": "1997", "merges": "199 7", "raw_count": 2171526, "count": 2171526, "decode_str": "1997"} -{"id": 990, "token": "\u0120end", "merges": "\u0120 end", "raw_count": 1675918, "count": 2172503, "decode_str": " end"} -{"id": 2653, "token": "ey", "merges": "e y", "raw_count": 278008, "count": 2172597, "decode_str": "ey"} -{"id": 1180, "token": "\u0120number", "merges": "\u0120num ber", "raw_count": 2173418, "count": 2173418, "decode_str": " number"} -{"id": 1283, "token": "\u012018", "merges": "\u01201 8", "raw_count": 1419107, "count": 2173513, "decode_str": " 18"} -{"id": 1338, "token": "lement", "merges": "le ment", "raw_count": 94303, "count": 2174136, "decode_str": "lement"} -{"id": 1854, "token": "\u0120path", "merges": "\u0120p ath", "raw_count": 1975554, "count": 2175133, "decode_str": " path"} -{"id": 1040, "token": "\u0120|", "merges": "\u0120 |", "raw_count": 1982637, "count": 2175897, "decode_str": " |"} -{"id": 53041, "token": "\u00e7\u0141\u00a2", "merges": "\u00e7\u0141 \u00a2", "raw_count": 2176860, "count": 2176860, "decode_str": "\u77e2"} -{"id": 1538, "token": "ission", "merges": "iss ion", "raw_count": 52230, "count": 2178263, "decode_str": "ission"} -{"id": 53107, "token": "\u00e7\u00a5\u0122", "merges": "\u00e7\u00a5 \u0122", "raw_count": 2179079, "count": 2179079, "decode_str": "\u7940"} -{"id": 52216, "token": "\u00e6\u013f\u0138", "merges": "\u00e6\u013f \u0138", "raw_count": 2179744, "count": 2179744, "decode_str": "\u6756"} -{"id": 52099, "token": "\u00e6\u0138\u00a7", "merges": "\u00e6\u0138 \u00a7", "raw_count": 2180364, "count": 2180364, "decode_str": "\u65a7"} -{"id": 54392, "token": "\u00e9\u013e\u0138", "merges": "\u00e9\u013e \u0138", "raw_count": 2180971, "count": 2180971, "decode_str": "\u9716"} -{"id": 6682, "token": "api", "merges": "ap i", "raw_count": 2171648, "count": 2180986, "decode_str": "api"} -{"id": 54381, "token": "\u00e9\u013e\u0126", "merges": "\u00e9\u013e \u0126", "raw_count": 2182303, "count": 2182303, "decode_str": "\u9704"} -{"id": 127, "token": "\u00c3", "merges": "NULL", "raw_count": 25147, "count": 2183759, "decode_str": "\ufffd"} -{"id": 54308, "token": "\u00e9\u013a\u00b1", "merges": "\u00e9\u013a \u00b1", "raw_count": 2186196, "count": 2186196, "decode_str": "\u9631"} -{"id": 1658, "token": "rop", "merges": "ro p", "raw_count": 314381, "count": 2188458, "decode_str": "rop"} -{"id": 51022, "token": "\u00e5\u0134\u0131", "merges": "\u00e5\u0134 \u0131", "raw_count": 2190738, "count": 2190738, "decode_str": "\u548f"} -{"id": 51334, "token": "\u00e5\u00a6\u012c", "merges": "\u00e5\u00a6 \u012c", "raw_count": 2191062, "count": 2191062, "decode_str": "\u598a"} -{"id": 839, "token": "ating", "merges": "at ing", "raw_count": 615045, "count": 2191112, "decode_str": "ating"} -{"id": 53644, "token": "\u00e8\u012d\u0136", "merges": "\u00e8\u012d \u0136", "raw_count": 2193216, "count": 2193216, "decode_str": "\u82d4"} -{"id": 917, "token": "ible", "merges": "ib le", "raw_count": 302196, "count": 2193884, "decode_str": "ible"} -{"id": 2267, "token": "II", "merges": "I I", "raw_count": 1768009, "count": 2196479, "decode_str": "II"} -{"id": 52474, "token": "\u00e6\u00b1\u0137", "merges": "\u00e6\u00b1 \u0137", "raw_count": 2197604, "count": 2197604, "decode_str": "\u6c55"} -{"id": 51313, "token": "\u00e5\u00a5\u0130", "merges": "\u00e5\u00a5 \u0130", "raw_count": 2203056, "count": 2203056, "decode_str": "\u594e"} -{"id": 8882, "token": "context", "merges": "con text", "raw_count": 2205927, "count": 2205927, "decode_str": "context"} -{"id": 54522, "token": "\u00e9\u00ab\u00a6", "merges": "\u00e9\u00ab \u00a6", "raw_count": 2205970, "count": 2205970, "decode_str": "\u9ae6"} -{"id": 50738, "token": "\u00e5\u0129\u0126", "merges": "\u00e5\u0129 \u0126", "raw_count": 2206199, "count": 2206199, "decode_str": "\u51c4"} -{"id": 53053, "token": "\u00e7\u0142\u012e", "merges": "\u00e7\u0142 \u012e", "raw_count": 2208329, "count": 2208329, "decode_str": "\u780c"} -{"id": 7267, "token": "query", "merges": "qu ery", "raw_count": 2189422, "count": 2208545, "decode_str": "query"} -{"id": 1231, "token": "We", "merges": "W e", "raw_count": 850192, "count": 2208682, "decode_str": "We"} -{"id": 53213, "token": "\u00e7\u00ac\u013d", "merges": "\u00e7\u00ac \u013d", "raw_count": 2209689, "count": 2209689, "decode_str": "\u7b1b"} -{"id": 52973, "token": "\u00e7\u013c\u0135", "merges": "\u00e7\u013c \u0135", "raw_count": 2211209, "count": 2211209, "decode_str": "\u7693"} -{"id": 957, "token": "ruct", "merges": "ru ct", "raw_count": 23833, "count": 2211424, "decode_str": "ruct"} -{"id": 2521, "token": "eters", "merges": "et ers", "raw_count": 79215, "count": 2213100, "decode_str": "eters"} -{"id": 1377, "token": "anc", "merges": "an c", "raw_count": 450857, "count": 2215959, "decode_str": "anc"} -{"id": 52326, "token": "\u00e6\u00a3\u013a", "merges": "\u00e6\u00a3 \u013a", "raw_count": 2216171, "count": 2216171, "decode_str": "\u68d8"} -{"id": 5213, "token": "\u0120international", "merges": "\u0120intern ational", "raw_count": 2218594, "count": 2218594, "decode_str": " international"} -{"id": 573, "token": "----------------", "merges": "-------- --------", "raw_count": 52832, "count": 2220366, "decode_str": "----------------"} -{"id": 52252, "token": "\u00e6\u0140\u00b8", "merges": "\u00e6\u0140 \u00b8", "raw_count": 2220588, "count": 2220588, "decode_str": "\u67b8"} -{"id": 927, "token": "\u0120includ", "merges": "\u0120in clud", "raw_count": 2221, "count": 2221368, "decode_str": " includ"} -{"id": 1028, "token": "uc", "merges": "u c", "raw_count": 533311, "count": 2222554, "decode_str": "uc"} -{"id": 51595, "token": "\u00e5\u00bc\u012a", "merges": "\u00e5\u00bc \u012a", "raw_count": 2223383, "count": 2223383, "decode_str": "\u5f08"} -{"id": 51570, "token": "\u00e5\u00ba\u013c", "merges": "\u00e5\u00ba \u013c", "raw_count": 2224315, "count": 2224315, "decode_str": "\u5e9a"} -{"id": 50616, "token": "\u00e4\u00bf\u00ba", "merges": "\u00e4\u00bf \u00ba", "raw_count": 2224384, "count": 2224384, "decode_str": "\u4ffa"} -{"id": 8858, "token": "values", "merges": "val ues", "raw_count": 2213789, "count": 2224446, "decode_str": "values"} -{"id": 9122, "token": "PM", "merges": "P M", "raw_count": 2224930, "count": 2224930, "decode_str": "PM"} -{"id": 3118, "token": "comp", "merges": "com p", "raw_count": 545742, "count": 2225826, "decode_str": "comp"} -{"id": 50417, "token": "\u00e4\u00b8\u0140", "merges": "\u00e4\u00b8 \u0140", "raw_count": 2231561, "count": 2231561, "decode_str": "\u4e1e"} -{"id": 53554, "token": "\u00e8\u0129\u0122", "merges": "\u00e8\u0129 \u0122", "raw_count": 2238512, "count": 2238512, "decode_str": "\u81c0"} -{"id": 24382, "token": "train", "merges": "t rain", "raw_count": 2238788, "count": 2238788, "decode_str": "train"} -{"id": 51031, "token": "\u00e5\u0134\u013c", "merges": "\u00e5\u0134 \u013c", "raw_count": 2239077, "count": 2239077, "decode_str": "\u549a"} -{"id": 2764, "token": "umber", "merges": "um ber", "raw_count": 67488, "count": 2239453, "decode_str": "umber"} -{"id": 680, "token": "wo", "merges": "w o", "raw_count": 264341, "count": 2239844, "decode_str": "wo"} -{"id": 52690, "token": "\u00e6\u00ba\u00ba", "merges": "\u00e6\u00ba \u00ba", "raw_count": 2239855, "count": 2239855, "decode_str": "\u6eba"} -{"id": 50845, "token": "\u00e5\u012e\u012a", "merges": "\u00e5\u012e \u012a", "raw_count": 2240052, "count": 2240052, "decode_str": "\u5308"} -{"id": 3528, "token": "SS", "merges": "S S", "raw_count": 1627067, "count": 2240323, "decode_str": "SS"} -{"id": 897, "token": "\u0120use", "merges": "\u0120us e", "raw_count": 2241031, "count": 2241031, "decode_str": " use"} -{"id": 1006, "token": "\u0120gener", "merges": "\u0120gen er", "raw_count": 21243, "count": 2241541, "decode_str": " gener"} -{"id": 54189, "token": "\u00e9\u0127\u012e", "merges": "\u00e9\u0127 \u012e", "raw_count": 2242169, "count": 2242169, "decode_str": "\u914c"} -{"id": 4856, "token": "msg", "merges": "ms g", "raw_count": 2224952, "count": 2242741, "decode_str": "msg"} -{"id": 51533, "token": "\u00e5\u00b8\u013e", "merges": "\u00e5\u00b8 \u013e", "raw_count": 2243276, "count": 2243276, "decode_str": "\u5e1c"} -{"id": 53931, "token": "\u00e8\u00b4\u00b1", "merges": "\u00e8\u00b4 \u00b1", "raw_count": 2244481, "count": 2244481, "decode_str": "\u8d31"} -{"id": 1098, "token": "\u0120stat", "merges": "\u0120st at", "raw_count": 128254, "count": 2247011, "decode_str": " stat"} -{"id": 1346, "token": "ists", "merges": "ist s", "raw_count": 263792, "count": 2248952, "decode_str": "ists"} -{"id": 21343, "token": "quo", "merges": "qu o", "raw_count": 2211231, "count": 2249470, "decode_str": "quo"} -{"id": 6259, "token": "current", "merges": "cur rent", "raw_count": 2174914, "count": 2251093, "decode_str": "current"} -{"id": 51335, "token": "\u00e5\u00a6\u012f", "merges": "\u00e5\u00a6 \u012f", "raw_count": 2252548, "count": 2252548, "decode_str": "\u598d"} -{"id": 2311, "token": "})", "merges": "} )", "raw_count": 2138665, "count": 2253595, "decode_str": "})"} -{"id": 774, "token": "\u0120rel", "merges": "\u0120re l", "raw_count": 188131, "count": 2255337, "decode_str": " rel"} -{"id": 836, "token": "ood", "merges": "o od", "raw_count": 202943, "count": 2260524, "decode_str": "ood"} -{"id": 1678, "token": "dd", "merges": "d d", "raw_count": 948435, "count": 2261274, "decode_str": "dd"} -{"id": 50566, "token": "\u00e4\u00bd\u00ac", "merges": "\u00e4\u00bd \u00ac", "raw_count": 2262358, "count": 2262358, "decode_str": "\u4f6c"} -{"id": 1197, "token": "ody", "merges": "od y", "raw_count": 128372, "count": 2262696, "decode_str": "ody"} -{"id": 1251, "token": "ng", "merges": "n g", "raw_count": 963536, "count": 2264130, "decode_str": "ng"} -{"id": 52493, "token": "\u00e6\u00b2\u0123", "merges": "\u00e6\u00b2 \u0123", "raw_count": 2269120, "count": 2269120, "decode_str": "\u6c81"} -{"id": 4350, "token": "SP", "merges": "S P", "raw_count": 2191828, "count": 2270064, "decode_str": "SP"} -{"id": 2577, "token": "my", "merges": "m y", "raw_count": 1650666, "count": 2270492, "decode_str": "my"} -{"id": 5501, "token": "conne", "merges": "con ne", "raw_count": 14679, "count": 2271951, "decode_str": "conne"} -{"id": 53894, "token": "\u00e8\u00b1\u0123", "merges": "\u00e8\u00b1 \u0123", "raw_count": 2272638, "count": 2272638, "decode_str": "\u8c41"} -{"id": 52789, "token": "\u00e7\u012c\u0122", "merges": "\u00e7\u012c \u0122", "raw_count": 2275162, "count": 2275162, "decode_str": "\u7280"} -{"id": 54021, "token": "\u00e8\u00bd\u00a7", "merges": "\u00e8\u00bd \u00a7", "raw_count": 2276175, "count": 2276175, "decode_str": "\u8f67"} -{"id": 644, "token": "\u0120been", "merges": "\u0120be en", "raw_count": 2278382, "count": 2278382, "decode_str": " been"} -{"id": 2388, "token": "inter", "merges": "in ter", "raw_count": 1210610, "count": 2280544, "decode_str": "inter"} -{"id": 595, "token": "ally", "merges": "al ly", "raw_count": 277579, "count": 2281377, "decode_str": "ally"} -{"id": 1814, "token": "mb", "merges": "m b", "raw_count": 939687, "count": 2287898, "decode_str": "mb"} -{"id": 1240, "token": "ah", "merges": "a h", "raw_count": 1361442, "count": 2288821, "decode_str": "ah"} -{"id": 9332, "token": "arser", "merges": "ars er", "raw_count": 55893, "count": 2288923, "decode_str": "arser"} -{"id": 51541, "token": "\u00e5\u00b8\u00b7", "merges": "\u00e5\u00b8 \u00b7", "raw_count": 2290260, "count": 2290260, "decode_str": "\u5e37"} -{"id": 50610, "token": "\u00e4\u00bf\u0143", "merges": "\u00e4\u00bf \u0143", "raw_count": 2292425, "count": 2292425, "decode_str": "\u4fed"} -{"id": 54442, "token": "\u00e9\u00a2\u012c", "merges": "\u00e9\u00a2 \u012c", "raw_count": 2292955, "count": 2292955, "decode_str": "\u988a"} -{"id": 1297, "token": "ision", "merges": "is ion", "raw_count": 352532, "count": 2293232, "decode_str": "ision"} -{"id": 52630, "token": "\u00e6\u00b7\u0129", "merges": "\u00e6\u00b7 \u0129", "raw_count": 2295827, "count": 2295827, "decode_str": "\u6dc7"} -{"id": 671, "token": "\u0120also", "merges": "\u0120al so", "raw_count": 2298108, "count": 2298108, "decode_str": " also"} -{"id": 888, "token": "ident", "merges": "id ent", "raw_count": 274135, "count": 2301270, "decode_str": "ident"} -{"id": 4120, "token": "Mod", "merges": "M od", "raw_count": 305423, "count": 2302254, "decode_str": "Mod"} -{"id": 52897, "token": "\u00e7\u0137\u00b8", "merges": "\u00e7\u0137 \u00b8", "raw_count": 2303375, "count": 2303375, "decode_str": "\u7578"} -{"id": 1288, "token": "br", "merges": "b r", "raw_count": 1339996, "count": 2304044, "decode_str": "br"} -{"id": 3620, "token": "dev", "merges": "de v", "raw_count": 715701, "count": 2304083, "decode_str": "dev"} -{"id": 51110, "token": "\u00e5\u0138\u0125", "merges": "\u00e5\u0138 \u0125", "raw_count": 2305555, "count": 2305555, "decode_str": "\u5583"} -{"id": 54493, "token": "\u00e9\u00aa\u0128", "merges": "\u00e9\u00aa \u0128", "raw_count": 2308516, "count": 2308516, "decode_str": "\u9a86"} -{"id": 10683, "token": "123", "merges": "12 3", "raw_count": 2308855, "count": 2308855, "decode_str": "123"} -{"id": 3519, "token": "OD", "merges": "O D", "raw_count": 1160280, "count": 2309950, "decode_str": "OD"} -{"id": 1553, "token": "pec", "merges": "pe c", "raw_count": 283207, "count": 2311096, "decode_str": "pec"} -{"id": 16445, "token": "'],", "merges": "' ],", "raw_count": 2312058, "count": 2312058, "decode_str": "'],"} -{"id": 53463, "token": "\u00e8\u0123\u0124", "merges": "\u00e8\u0123 \u0124", "raw_count": 2313477, "count": 2313477, "decode_str": "\u8042"} -{"id": 53537, "token": "\u00e8\u0126\u012c", "merges": "\u00e8\u0126 \u012c", "raw_count": 2315066, "count": 2315066, "decode_str": "\u810a"} -{"id": 51367, "token": "\u00e5\u00a7\u00a5", "merges": "\u00e5\u00a7 \u00a5", "raw_count": 2315090, "count": 2315090, "decode_str": "\u59e5"} -{"id": 6873, "token": "XX", "merges": "X X", "raw_count": 1332266, "count": 2315411, "decode_str": "XX"} -{"id": 7831, "token": "target", "merges": "t arget", "raw_count": 2038194, "count": 2315779, "decode_str": "target"} -{"id": 50884, "token": "\u00e5\u012f\u00a4", "merges": "\u00e5\u012f \u00a4", "raw_count": 2315998, "count": 2315998, "decode_str": "\u5364"} -{"id": 53031, "token": "\u00e7\u013f\u00ab", "merges": "\u00e7\u013f \u00ab", "raw_count": 2317463, "count": 2317463, "decode_str": "\u776b"} -{"id": 3801, "token": "IF", "merges": "I F", "raw_count": 1837076, "count": 2317681, "decode_str": "IF"} -{"id": 2634, "token": "\u0120`", "merges": "\u0120 `", "raw_count": 1633521, "count": 2319265, "decode_str": " `"} -{"id": 54468, "token": "\u00e9\u00a3\u013b", "merges": "\u00e9\u00a3 \u013b", "raw_count": 2320820, "count": 2320820, "decode_str": "\u98d9"} -{"id": 1789, "token": "\u0120object", "merges": "\u0120ob ject", "raw_count": 1629101, "count": 2323099, "decode_str": " object"} -{"id": 17664, "token": "Google", "merges": "Go ogle", "raw_count": 2323269, "count": 2323269, "decode_str": "Google"} -{"id": 51856, "token": "\u00e6\u012b\u00b3", "merges": "\u00e6\u012b \u00b3", "raw_count": 2323925, "count": 2323925, "decode_str": "\u6273"} -{"id": 51026, "token": "\u00e5\u0134\u0137", "merges": "\u00e5\u0134 \u0137", "raw_count": 2324104, "count": 2324104, "decode_str": "\u5495"} -{"id": 1424, "token": "\u0120cre", "merges": "\u0120c re", "raw_count": 37037, "count": 2326257, "decode_str": " cre"} -{"id": 4399, "token": "group", "merges": "gr oup", "raw_count": 2312950, "count": 2326364, "decode_str": "group"} -{"id": 25536, "token": "\u0120united", "merges": "\u0120un ited", "raw_count": 2328220, "count": 2328220, "decode_str": " united"} -{"id": 2431, "token": "IG", "merges": "I G", "raw_count": 1342516, "count": 2329342, "decode_str": "IG"} -{"id": 717, "token": "\u0120am", "merges": "\u0120a m", "raw_count": 692599, "count": 2332596, "decode_str": " am"} -{"id": 52494, "token": "\u00e6\u00b2\u0124", "merges": "\u00e6\u00b2 \u0124", "raw_count": 2332951, "count": 2332951, "decode_str": "\u6c82"} -{"id": 533, "token": "\u0120but", "merges": "\u0120b ut", "raw_count": 2022424, "count": 2333352, "decode_str": " but"} -{"id": 52645, "token": "\u00e6\u00b7\u00b3", "merges": "\u00e6\u00b7 \u00b3", "raw_count": 2333651, "count": 2333651, "decode_str": "\u6df3"} -{"id": 1375, "token": "\u0120state", "merges": "\u0120st ate", "raw_count": 2333330, "count": 2333969, "decode_str": " state"} -{"id": 53140, "token": "\u00e7\u00a6\u00b9", "merges": "\u00e7\u00a6 \u00b9", "raw_count": 2338197, "count": 2338197, "decode_str": "\u79b9"} -{"id": 54323, "token": "\u00e9\u013b\u012d", "merges": "\u00e9\u013b \u012d", "raw_count": 2339643, "count": 2339643, "decode_str": "\u964b"} -{"id": 51124, "token": "\u00e5\u0138\u00a7", "merges": "\u00e5\u0138 \u00a7", "raw_count": 2340427, "count": 2340427, "decode_str": "\u55a7"} -{"id": 21700, "token": "\u00e7\u00b5", "merges": "\u00e7 \u00b5", "raw_count": 192099, "count": 2340443, "decode_str": "\ufffd"} -{"id": 1320, "token": "ization", "merges": "iz ation", "raw_count": 1019940, "count": 2340786, "decode_str": "ization"} -{"id": 1189, "token": "over", "merges": "o ver", "raw_count": 1029270, "count": 2340902, "decode_str": "over"} -{"id": 50633, "token": "\u00e5\u0122\u00aa", "merges": "\u00e5\u0122 \u00aa", "raw_count": 2341109, "count": 2341109, "decode_str": "\u502a"} -{"id": 3446, "token": "\".", "merges": "\" .", "raw_count": 2341140, "count": 2341140, "decode_str": "\"."} -{"id": 1234, "token": "\u0120rep", "merges": "\u0120re p", "raw_count": 142665, "count": 2345315, "decode_str": " rep"} -{"id": 53464, "token": "\u00e8\u0123\u0128", "merges": "\u00e8\u0123 \u0128", "raw_count": 2345546, "count": 2345546, "decode_str": "\u8046"} -{"id": 2527, "token": "lete", "merges": "le te", "raw_count": 25760, "count": 2346491, "decode_str": "lete"} -{"id": 51204, "token": "\u00e5\u013f\u0141", "merges": "\u00e5\u013f \u0141", "raw_count": 2349041, "count": 2349041, "decode_str": "\u575f"} -{"id": 1710, "token": "gram", "merges": "gr am", "raw_count": 326065, "count": 2349917, "decode_str": "gram"} -{"id": 54365, "token": "\u00e9\u013d\u012f", "merges": "\u00e9\u013d \u012f", "raw_count": 2349943, "count": 2349943, "decode_str": "\u96cd"} -{"id": 1641, "token": "ts", "merges": "t s", "raw_count": 1263584, "count": 2350169, "decode_str": "ts"} -{"id": 4184, "token": "\u0120intern", "merges": "\u0120inter n", "raw_count": 20142, "count": 2353844, "decode_str": " intern"} -{"id": 2765, "token": "List", "merges": "L ist", "raw_count": 2268611, "count": 2356381, "decode_str": "List"} -{"id": 3288, "token": "oo", "merges": "o o", "raw_count": 840278, "count": 2362678, "decode_str": "oo"} -{"id": 3051, "token": "obal", "merges": "ob al", "raw_count": 14239, "count": 2363210, "decode_str": "obal"} -{"id": 602, "token": "ough", "merges": "oug h", "raw_count": 77106, "count": 2364901, "decode_str": "ough"} -{"id": 1248, "token": "formation", "merges": "form ation", "raw_count": 100101, "count": 2368785, "decode_str": "formation"} -{"id": 2402, "token": "Name", "merges": "N ame", "raw_count": 2164875, "count": 2370874, "decode_str": "Name"} -{"id": 2202, "token": "idth", "merges": "id th", "raw_count": 6292, "count": 2371931, "decode_str": "idth"} -{"id": 2838, "token": "Val", "merges": "V al", "raw_count": 458160, "count": 2372688, "decode_str": "Val"} -{"id": 2013, "token": "rem", "merges": "re m", "raw_count": 598547, "count": 2373891, "decode_str": "rem"} -{"id": 1296, "token": "\u0120serv", "merges": "\u0120s erv", "raw_count": 49928, "count": 2374154, "decode_str": " serv"} -{"id": 53155, "token": "\u00e7\u00a7\u00a4", "merges": "\u00e7\u00a7 \u00a4", "raw_count": 2374677, "count": 2374677, "decode_str": "\u79e4"} -{"id": 51712, "token": "\u00e6\u0123\u012f", "merges": "\u00e6\u0123 \u012f", "raw_count": 2374697, "count": 2374697, "decode_str": "\u604d"} -{"id": 53526, "token": "\u00e8\u0125\u00b0", "merges": "\u00e8\u0125 \u00b0", "raw_count": 2376149, "count": 2376149, "decode_str": "\u80f0"} -{"id": 51774, "token": "\u00e6\u0125\u00ab", "merges": "\u00e6\u0125 \u00ab", "raw_count": 2377576, "count": 2377576, "decode_str": "\u60eb"} -{"id": 1177, "token": "ature", "merges": "at ure", "raw_count": 84327, "count": 2378381, "decode_str": "ature"} -{"id": 54175, "token": "\u00e9\u0125\u013f", "merges": "\u00e9\u0125 \u013f", "raw_count": 2379346, "count": 2379346, "decode_str": "\u90dd"} -{"id": 3280, "token": "\u0120input", "merges": "\u0120in put", "raw_count": 1998057, "count": 2380850, "decode_str": " input"} -{"id": 2204, "token": "sum", "merges": "s um", "raw_count": 1813781, "count": 2380949, "decode_str": "sum"} -{"id": 1299, "token": "ton", "merges": "t on", "raw_count": 486214, "count": 2381144, "decode_str": "ton"} -{"id": 50899, "token": "\u00e5\u0130\u0126", "merges": "\u00e5\u0130 \u0126", "raw_count": 2382369, "count": 2382369, "decode_str": "\u5384"} -{"id": 1111, "token": "\u0120mat", "merges": "\u0120m at", "raw_count": 264497, "count": 2382395, "decode_str": " mat"} -{"id": 52718, "token": "\u00e7\u0123\u00bc", "merges": "\u00e7\u0123 \u00bc", "raw_count": 2384111, "count": 2384111, "decode_str": "\u707c"} -{"id": 635, "token": "very", "merges": "ver y", "raw_count": 114335, "count": 2384764, "decode_str": "very"} -{"id": 3233, "token": "Data", "merges": "D ata", "raw_count": 2366220, "count": 2386160, "decode_str": "Data"} -{"id": 698, "token": "ays", "merges": "ay s", "raw_count": 319140, "count": 2387488, "decode_str": "ays"} -{"id": 51076, "token": "\u00e5\u0135\u00ae", "merges": "\u00e5\u0135 \u00ae", "raw_count": 2388525, "count": 2388525, "decode_str": "\u54ee"} -{"id": 51203, "token": "\u00e5\u013f\u0140", "merges": "\u00e5\u013f \u0140", "raw_count": 2391667, "count": 2391667, "decode_str": "\u575e"} -{"id": 52598, "token": "\u00e6\u00b6\u0127", "merges": "\u00e6\u00b6 \u0127", "raw_count": 2392729, "count": 2392729, "decode_str": "\u6d85"} -{"id": 54212, "token": "\u00e9\u0129\u012b", "merges": "\u00e9\u0129 \u012b", "raw_count": 2394298, "count": 2394298, "decode_str": "\u91c9"} -{"id": 6481, "token": "win", "merges": "w in", "raw_count": 2372392, "count": 2395699, "decode_str": "win"} -{"id": 53625, "token": "\u00e8\u012c\u0143", "merges": "\u00e8\u012c \u0143", "raw_count": 2398175, "count": 2398175, "decode_str": "\u82ad"} -{"id": 3338, "token": "MS", "merges": "M S", "raw_count": 2055926, "count": 2400812, "decode_str": "MS"} -{"id": 53170, "token": "\u00e7\u00a8\u013c", "merges": "\u00e7\u00a8 \u013c", "raw_count": 2403984, "count": 2403984, "decode_str": "\u7a1a"} -{"id": 53371, "token": "\u00e7\u00bb\u00b7", "merges": "\u00e7\u00bb \u00b7", "raw_count": 2404771, "count": 2404771, "decode_str": "\u7ef7"} -{"id": 50957, "token": "\u00e5\u0132\u0131", "merges": "\u00e5\u0132 \u0131", "raw_count": 2405494, "count": 2405494, "decode_str": "\u540f"} -{"id": 53616, "token": "\u00e8\u012c\u013e", "merges": "\u00e8\u012c \u013e", "raw_count": 2406374, "count": 2406374, "decode_str": "\u829c"} -{"id": 54149, "token": "\u00e9\u0124\u0133", "merges": "\u00e9\u0124 \u0133", "raw_count": 2407718, "count": 2407718, "decode_str": "\u9091"} -{"id": 1257, "token": "be", "merges": "b e", "raw_count": 1255281, "count": 2408788, "decode_str": "be"} -{"id": 50632, "token": "\u00e5\u0122\u00a9", "merges": "\u00e5\u0122 \u00a9", "raw_count": 2410017, "count": 2410017, "decode_str": "\u5029"} -{"id": 994, "token": "\u0120ent", "merges": "\u0120 ent", "raw_count": 99311, "count": 2411083, "decode_str": " ent"} -{"id": 1321, "token": "ier", "merges": "i er", "raw_count": 797270, "count": 2417810, "decode_str": "ier"} -{"id": 10655, "token": "105", "merges": "10 5", "raw_count": 2418838, "count": 2418838, "decode_str": "105"} -{"id": 2573, "token": "DE", "merges": "D E", "raw_count": 941710, "count": 2419061, "decode_str": "DE"} -{"id": 772, "token": "\u0120cons", "merges": "\u0120con s", "raw_count": 87502, "count": 2419549, "decode_str": " cons"} -{"id": 53647, "token": "\u00e8\u012d\u013d", "merges": "\u00e8\u012d \u013d", "raw_count": 2419715, "count": 2419715, "decode_str": "\u82db"} -{"id": 51098, "token": "\u00e5\u0137\u00b0", "merges": "\u00e5\u0137 \u00b0", "raw_count": 2420619, "count": 2420619, "decode_str": "\u5570"} -{"id": 1507, "token": "ets", "merges": "et s", "raw_count": 1095012, "count": 2421098, "decode_str": "ets"} -{"id": 1440, "token": "tt", "merges": "t t", "raw_count": 630903, "count": 2421692, "decode_str": "tt"} -{"id": 2548, "token": "Type", "merges": "T ype", "raw_count": 2409793, "count": 2421983, "decode_str": "Type"} -{"id": 2703, "token": "string", "merges": "st ring", "raw_count": 2396612, "count": 2423377, "decode_str": "string"} -{"id": 51456, "token": "\u00e5\u00b0\u012b", "merges": "\u00e5\u00b0 \u012b", "raw_count": 2423531, "count": 2423531, "decode_str": "\u5c09"} -{"id": 51001, "token": "\u00e5\u0133\u013e", "merges": "\u00e5\u0133 \u013e", "raw_count": 2426805, "count": 2426805, "decode_str": "\u545c"} -{"id": 1968, "token": "label", "merges": "l abel", "raw_count": 2380446, "count": 2428225, "decode_str": "label"} -{"id": 2246, "token": "ries", "merges": "ri es", "raw_count": 478130, "count": 2430517, "decode_str": "ries"} -{"id": 53966, "token": "\u00e8\u00b5\u00a3", "merges": "\u00e8\u00b5 \u00a3", "raw_count": 2431345, "count": 2431345, "decode_str": "\u8d63"} -{"id": 2696, "token": "AG", "merges": "A G", "raw_count": 1510959, "count": 2431781, "decode_str": "AG"} -{"id": 51946, "token": "\u00e6\u012e\u0142", "merges": "\u00e6\u012e \u0142", "raw_count": 2432224, "count": 2432224, "decode_str": "\u6320"} -{"id": 51961, "token": "\u00e6\u012f\u0128", "merges": "\u00e6\u012f \u0128", "raw_count": 2435386, "count": 2435386, "decode_str": "\u6346"} -{"id": 39919, "token": "\u00e2\u0122\u013f:", "merges": "\u00e2\u0122\u013f :", "raw_count": 2437089, "count": 2437089, "decode_str": "\u201d:"} -{"id": 54249, "token": "\u00e9\u0137\u0123", "merges": "\u00e9\u0137 \u0123", "raw_count": 2437470, "count": 2437470, "decode_str": "\u9541"} -{"id": 1458, "token": "\u012015", "merges": "\u01201 5", "raw_count": 2085440, "count": 2437847, "decode_str": " 15"} -{"id": 594, "token": "\u0120so", "merges": "\u0120s o", "raw_count": 1704480, "count": 2445587, "decode_str": " so"} -{"id": 2352, "token": "ids", "merges": "id s", "raw_count": 1968248, "count": 2446799, "decode_str": "ids"} -{"id": 52141, "token": "\u00e6\u013a\u00a7", "merges": "\u00e6\u013a \u00a7", "raw_count": 2448475, "count": 2448475, "decode_str": "\u6627"} -{"id": 52696, "token": "\u00e6\u00bc\u0135", "merges": "\u00e6\u00bc \u0135", "raw_count": 2448866, "count": 2448866, "decode_str": "\u6f13"} -{"id": 5509, "token": "indows", "merges": "indow s", "raw_count": 2988, "count": 2450421, "decode_str": "indows"} -{"id": 1247, "token": "gan", "merges": "g an", "raw_count": 138216, "count": 2450944, "decode_str": "gan"} -{"id": 54327, "token": "\u00e9\u013b\u013d", "merges": "\u00e9\u013b \u013d", "raw_count": 2453356, "count": 2453356, "decode_str": "\u965b"} -{"id": 9573, "token": "attr", "merges": "at tr", "raw_count": 2078703, "count": 2454453, "decode_str": "attr"} -{"id": 1044, "token": "Th", "merges": "T h", "raw_count": 594252, "count": 2454530, "decode_str": "Th"} -{"id": 1161, "token": "\u0120che", "merges": "\u0120c he", "raw_count": 75250, "count": 2455062, "decode_str": " che"} -{"id": 4251, "token": "map", "merges": "m ap", "raw_count": 2405021, "count": 2456692, "decode_str": "map"} -{"id": 52920, "token": "\u00e7\u0138\u00b5", "merges": "\u00e7\u0138 \u00b5", "raw_count": 2457145, "count": 2457145, "decode_str": "\u75b5"} -{"id": 51974, "token": "\u00e6\u012f\u00a3", "merges": "\u00e6\u012f \u00a3", "raw_count": 2457146, "count": 2457146, "decode_str": "\u6363"} -{"id": 1386, "token": "\u0120line", "merges": "\u0120l ine", "raw_count": 2341368, "count": 2462908, "decode_str": " line"} -{"id": 1758, "token": "ina", "merges": "in a", "raw_count": 1740140, "count": 2465321, "decode_str": "ina"} -{"id": 51699, "token": "\u00e6\u0122\u0142", "merges": "\u00e6\u0122 \u0142", "raw_count": 2468631, "count": 2468631, "decode_str": "\u6020"} -{"id": 18104, "token": "900", "merges": "9 00", "raw_count": 2469155, "count": 2469155, "decode_str": "900"} -{"id": 51825, "token": "\u00e6\u012a\u00b3", "merges": "\u00e6\u012a \u00b3", "raw_count": 2469371, "count": 2469371, "decode_str": "\u6233"} -{"id": 1484, "token": "\u0120u", "merges": "\u0120 u", "raw_count": 1763231, "count": 2469793, "decode_str": " u"} -{"id": 52990, "token": "\u00e7\u013d\u0136", "merges": "\u00e7\u013d \u0136", "raw_count": 2470260, "count": 2470260, "decode_str": "\u76d4"} -{"id": 2369, "token": "no", "merges": "n o", "raw_count": 2093751, "count": 2472628, "decode_str": "no"} -{"id": 54267, "token": "\u00e9\u0137\u00b6", "merges": "\u00e9\u0137 \u00b6", "raw_count": 2473862, "count": 2473862, "decode_str": "\u9576"} -{"id": 53095, "token": "\u00e7\u00a2\u0141", "merges": "\u00e7\u00a2 \u0141", "raw_count": 2474048, "count": 2474048, "decode_str": "\u789f"} -{"id": 52159, "token": "\u00e6\u013b\u0138", "merges": "\u00e6\u013b \u0138", "raw_count": 2474970, "count": 2474970, "decode_str": "\u6656"} -{"id": 12101, "token": "TV", "merges": "T V", "raw_count": 2473585, "count": 2475050, "decode_str": "TV"} -{"id": 50453, "token": "\u00e4\u00b9\u0140", "merges": "\u00e4\u00b9 \u0140", "raw_count": 2475443, "count": 2475443, "decode_str": "\u4e5e"} -{"id": 53388, "token": "\u00e7\u00bc\u0137", "merges": "\u00e7\u00bc \u0137", "raw_count": 2476454, "count": 2476454, "decode_str": "\u7f15"} -{"id": 877, "token": "\u0120pol", "merges": "\u0120p ol", "raw_count": 117696, "count": 2477899, "decode_str": " pol"} -{"id": 626, "token": "'t", "merges": "' t", "raw_count": 2478414, "count": 2478414, "decode_str": "'t"} -{"id": 2809, "token": "Sh", "merges": "S h", "raw_count": 1380095, "count": 2479311, "decode_str": "Sh"} -{"id": 53144, "token": "\u00e7\u00a6\u00be", "merges": "\u00e7\u00a6 \u00be", "raw_count": 2481764, "count": 2481764, "decode_str": "\u79be"} -{"id": 3129, "token": "gl", "merges": "g l", "raw_count": 936087, "count": 2485468, "decode_str": "gl"} -{"id": 2115, "token": "Com", "merges": "C om", "raw_count": 623596, "count": 2487624, "decode_str": "Com"} -{"id": 53181, "token": "\u00e7\u00a8\u00bd", "merges": "\u00e7\u00a8 \u00bd", "raw_count": 2487904, "count": 2487904, "decode_str": "\u7a3d"} -{"id": 53173, "token": "\u00e7\u00a8\u0142", "merges": "\u00e7\u00a8 \u0142", "raw_count": 2488522, "count": 2488522, "decode_str": "\u7a20"} -{"id": 1038, "token": "cond", "merges": "con d", "raw_count": 227671, "count": 2488806, "decode_str": "cond"} -{"id": 50604, "token": "\u00e4\u00bf\u0140", "merges": "\u00e4\u00bf \u0140", "raw_count": 2489642, "count": 2489642, "decode_str": "\u4fde"} -{"id": 54330, "token": "\u00e9\u013b\u00a1", "merges": "\u00e9\u013b \u00a1", "raw_count": 2490128, "count": 2490128, "decode_str": "\u9661"} -{"id": 1140, "token": "\u0120tra", "merges": "\u0120t ra", "raw_count": 68549, "count": 2493748, "decode_str": " tra"} -{"id": 581, "token": "\u0120one", "merges": "\u0120on e", "raw_count": 2495686, "count": 2495686, "decode_str": " one"} -{"id": 992, "token": "ateg", "merges": "ate g", "raw_count": 220323, "count": 2498982, "decode_str": "ateg"} -{"id": 54241, "token": "\u00e9\u0136\u00af", "merges": "\u00e9\u0136 \u00af", "raw_count": 2500260, "count": 2500260, "decode_str": "\u952f"} -{"id": 52647, "token": "\u00e6\u00b7\u00b9", "merges": "\u00e6\u00b7 \u00b9", "raw_count": 2501132, "count": 2501132, "decode_str": "\u6df9"} -{"id": 28157, "token": "usb", "merges": "us b", "raw_count": 2501273, "count": 2501273, "decode_str": "usb"} -{"id": 8196, "token": "128", "merges": "12 8", "raw_count": 2502114, "count": 2502114, "decode_str": "128"} -{"id": 8428, "token": "img", "merges": "im g", "raw_count": 2491046, "count": 2505986, "decode_str": "img"} -{"id": 53208, "token": "\u00e7\u00ac\u012d", "merges": "\u00e7\u00ac \u012d", "raw_count": 2506018, "count": 2506018, "decode_str": "\u7b0b"} -{"id": 18297, "token": "[:", "merges": "[ :", "raw_count": 2508950, "count": 2508950, "decode_str": "[:"} -{"id": 50598, "token": "\u00e4\u00bf\u0131", "merges": "\u00e4\u00bf \u0131", "raw_count": 2512438, "count": 2512438, "decode_str": "\u4fcf"} -{"id": 915, "token": "\u0120supp", "merges": "\u0120su pp", "raw_count": 11125, "count": 2514715, "decode_str": " supp"} -{"id": 2224, "token": "ns", "merges": "n s", "raw_count": 1263375, "count": 2516189, "decode_str": "ns"} -{"id": 51327, "token": "\u00e5\u00a5\u00b8", "merges": "\u00e5\u00a5 \u00b8", "raw_count": 2516701, "count": 2516701, "decode_str": "\u5978"} -{"id": 727, "token": "ater", "merges": "at er", "raw_count": 254711, "count": 2517010, "decode_str": "ater"} -{"id": 26443, "token": "\u00ef\u00bc\u0141", "merges": "\u00ef\u00bc \u0141", "raw_count": 2517062, "count": 2517062, "decode_str": "\uff1f"} -{"id": 53686, "token": "\u00e8\u013b\u0140", "merges": "\u00e8\u013b \u0140", "raw_count": 2517887, "count": 2517887, "decode_str": "\u865e"} -{"id": 52986, "token": "\u00e7\u013d\u0131", "merges": "\u00e7\u013d \u0131", "raw_count": 2523094, "count": 2523094, "decode_str": "\u76cf"} -{"id": 3364, "token": "box", "merges": "b ox", "raw_count": 2081975, "count": 2524231, "decode_str": "box"} -{"id": 51720, "token": "\u00e6\u0123\u00a4", "merges": "\u00e6\u0123 \u00a4", "raw_count": 2528258, "count": 2528258, "decode_str": "\u6064"} -{"id": 2056, "token": "mat", "merges": "m at", "raw_count": 1014610, "count": 2529468, "decode_str": "mat"} -{"id": 52273, "token": "\u00e6\u0141\u00bf", "merges": "\u00e6\u0141 \u00bf", "raw_count": 2529818, "count": 2529818, "decode_str": "\u67ff"} -{"id": 52849, "token": "\u00e7\u0132\u00a2", "merges": "\u00e7\u0132 \u00a2", "raw_count": 2531514, "count": 2531514, "decode_str": "\u7422"} -{"id": 51623, "token": "\u00e5\u00bd\u00a4", "merges": "\u00e5\u00bd \u00a4", "raw_count": 2532888, "count": 2532888, "decode_str": "\u5f64"} -{"id": 1527, "token": "\u0120open", "merges": "\u0120op en", "raw_count": 2287085, "count": 2534245, "decode_str": " open"} -{"id": 1792, "token": "ari", "merges": "ar i", "raw_count": 434802, "count": 2536002, "decode_str": "ari"} -{"id": 3231, "token": "OC", "merges": "O C", "raw_count": 1812221, "count": 2536189, "decode_str": "OC"} -{"id": 51108, "token": "\u00e5\u0138\u0122", "merges": "\u00e5\u0138 \u0122", "raw_count": 2536980, "count": 2536980, "decode_str": "\u5580"} -{"id": 11496, "token": "1998", "merges": "199 8", "raw_count": 2538728, "count": 2538728, "decode_str": "1998"} -{"id": 53235, "token": "\u00e7\u0143\u00b7", "merges": "\u00e7\u0143 \u00b7", "raw_count": 2539458, "count": 2539458, "decode_str": "\u7b77"} -{"id": 53015, "token": "\u00e7\u013e\u00b7", "merges": "\u00e7\u013e \u00b7", "raw_count": 2539551, "count": 2539551, "decode_str": "\u7737"} -{"id": 51072, "token": "\u00e5\u0135\u00a8", "merges": "\u00e5\u0135 \u00a8", "raw_count": 2541658, "count": 2541658, "decode_str": "\u54e8"} -{"id": 759, "token": "\u0120pe", "merges": "\u0120p e", "raw_count": 160570, "count": 2542223, "decode_str": " pe"} -{"id": 50573, "token": "\u00e4\u00be\u0125", "merges": "\u00e4\u00be \u0125", "raw_count": 2546278, "count": 2546278, "decode_str": "\u4f83"} -{"id": 53757, "token": "\u00e8\u00a7\u0127", "merges": "\u00e8\u00a7 \u0127", "raw_count": 2546922, "count": 2546922, "decode_str": "\u89c5"} -{"id": 1913, "token": "action", "merges": "a ction", "raw_count": 1766145, "count": 2547471, "decode_str": "action"} -{"id": 54071, "token": "\u00e8\u00bf\u0126", "merges": "\u00e8\u00bf \u0126", "raw_count": 2548404, "count": 2548404, "decode_str": "\u8fc4"} -{"id": 51440, "token": "\u00e5\u00af\u013f", "merges": "\u00e5\u00af \u013f", "raw_count": 2548663, "count": 2548663, "decode_str": "\u5bdd"} -{"id": 52576, "token": "\u00e6\u00b5\u012c", "merges": "\u00e6\u00b5 \u012c", "raw_count": 2550228, "count": 2550228, "decode_str": "\u6d4a"} -{"id": 634, "token": "\u0120your", "merges": "\u0120you r", "raw_count": 2443809, "count": 2551461, "decode_str": " your"} -{"id": 53011, "token": "\u00e7\u013e\u00a8", "merges": "\u00e7\u013e \u00a8", "raw_count": 2551568, "count": 2551568, "decode_str": "\u7728"} -{"id": 6321, "token": "run", "merges": "r un", "raw_count": 2060985, "count": 2552181, "decode_str": "run"} -{"id": 1216, "token": "ner", "merges": "n er", "raw_count": 811915, "count": 2554188, "decode_str": "ner"} -{"id": 3493, "token": "Pl", "merges": "P l", "raw_count": 487247, "count": 2556344, "decode_str": "Pl"} -{"id": 15046, "token": "170", "merges": "17 0", "raw_count": 2559966, "count": 2559966, "decode_str": "170"} -{"id": 3423, "token": "field", "merges": "f ield", "raw_count": 1619727, "count": 2563401, "decode_str": "field"} -{"id": 7693, "token": "cp", "merges": "c p", "raw_count": 989551, "count": 2563499, "decode_str": "cp"} -{"id": 811, "token": "\u0120trans", "merges": "\u0120tr ans", "raw_count": 286725, "count": 2565916, "decode_str": " trans"} -{"id": 54632, "token": "\u00e3\u0122\u00bf", "merges": "\u00e3\u0122 \u00bf", "raw_count": 2566039, "count": 2566039, "decode_str": " "} -{"id": 52218, "token": "\u00e6\u013f\u0140", "merges": "\u00e6\u013f \u0140", "raw_count": 2567690, "count": 2567690, "decode_str": "\u675e"} -{"id": 667, "token": "\u0120any", "merges": "\u0120an y", "raw_count": 2237722, "count": 2568166, "decode_str": " any"} -{"id": 52123, "token": "\u00e6\u0139\u00b7", "merges": "\u00e6\u0139 \u00b7", "raw_count": 2574760, "count": 2574760, "decode_str": "\u65f7"} -{"id": 54373, "token": "\u00e9\u013d\u00af", "merges": "\u00e9\u013d \u00af", "raw_count": 2577014, "count": 2577014, "decode_str": "\u96ef"} -{"id": 803, "token": "\u0120pos", "merges": "\u0120p os", "raw_count": 588919, "count": 2577029, "decode_str": " pos"} -{"id": 51317, "token": "\u00e5\u00a5\u0137", "merges": "\u00e5\u00a5 \u0137", "raw_count": 2577162, "count": 2577162, "decode_str": "\u5955"} -{"id": 2632, "token": "Res", "merges": "R es", "raw_count": 533983, "count": 2577719, "decode_str": "Res"} -{"id": 27905, "token": "pk", "merges": "p k", "raw_count": 2577834, "count": 2577834, "decode_str": "pk"} -{"id": 50861, "token": "\u00e5\u012e\u00bf", "merges": "\u00e5\u012e \u00bf", "raw_count": 2579374, "count": 2579374, "decode_str": "\u533f"} -{"id": 800, "token": "ative", "merges": "at ive", "raw_count": 316055, "count": 2581655, "decode_str": "ative"} -{"id": 761, "token": "\u0120rec", "merges": "\u0120re c", "raw_count": 255800, "count": 2582326, "decode_str": " rec"} -{"id": 54534, "token": "\u00e9\u00bb\u013d", "merges": "\u00e9\u00bb \u013d", "raw_count": 2584044, "count": 2584044, "decode_str": "\u9edb"} -{"id": 51300, "token": "\u00e5\u00a4\u00af", "merges": "\u00e5\u00a4 \u00af", "raw_count": 2587387, "count": 2587387, "decode_str": "\u592f"} -{"id": 50866, "token": "\u00e5\u012f\u012b", "merges": "\u00e5\u012f \u012b", "raw_count": 2587983, "count": 2587983, "decode_str": "\u5349"} -{"id": 1079, "token": "ale", "merges": "al e", "raw_count": 482536, "count": 2591745, "decode_str": "ale"} -{"id": 54166, "token": "\u00e9\u0124\u00b9", "merges": "\u00e9\u0124 \u00b9", "raw_count": 2594148, "count": 2594148, "decode_str": "\u90b9"} -{"id": 53984, "token": "\u00e8\u00b6\u00b4", "merges": "\u00e8\u00b6 \u00b4", "raw_count": 2594447, "count": 2594447, "decode_str": "\u8db4"} -{"id": 52085, "token": "\u00e6\u0138\u012d", "merges": "\u00e6\u0138 \u012d", "raw_count": 2594489, "count": 2594489, "decode_str": "\u658b"} -{"id": 53459, "token": "\u00e8\u0122\u00b8", "merges": "\u00e8\u0122 \u00b8", "raw_count": 2594923, "count": 2594923, "decode_str": "\u8038"} -{"id": 1419, "token": "ify", "merges": "if y", "raw_count": 1146415, "count": 2597132, "decode_str": "ify"} -{"id": 618, "token": "\u0120sa", "merges": "\u0120s a", "raw_count": 367320, "count": 2599011, "decode_str": " sa"} -{"id": 1164, "token": "ank", "merges": "an k", "raw_count": 434645, "count": 2599149, "decode_str": "ank"} -{"id": 50937, "token": "\u00e5\u0131\u0143", "merges": "\u00e5\u0131 \u0143", "raw_count": 2600488, "count": 2600488, "decode_str": "\u53ed"} -{"id": 1091, "token": "\u0120return", "merges": "\u0120ret urn", "raw_count": 1661872, "count": 2602131, "decode_str": " return"} -{"id": 1054, "token": "\u0120min", "merges": "\u0120m in", "raw_count": 1098430, "count": 2606725, "decode_str": " min"} -{"id": 12928, "token": "params", "merges": "par ams", "raw_count": 2608426, "count": 2608426, "decode_str": "params"} -{"id": 52888, "token": "\u00e7\u0137\u0136", "merges": "\u00e7\u0137 \u0136", "raw_count": 2610743, "count": 2610743, "decode_str": "\u7554"} -{"id": 974, "token": "ract", "merges": "ra ct", "raw_count": 133898, "count": 2611687, "decode_str": "ract"} -{"id": 2040, "token": "raw", "merges": "ra w", "raw_count": 1096372, "count": 2611941, "decode_str": "raw"} -{"id": 1045, "token": "\u0120el", "merges": "\u0120 el", "raw_count": 385406, "count": 2613625, "decode_str": " el"} -{"id": 388, "token": "\u0120H", "merges": "\u0120 H", "raw_count": 754992, "count": 2614456, "decode_str": " H"} -{"id": 53392, "token": "\u00e7\u00bc\u013c", "merges": "\u00e7\u00bc \u013c", "raw_count": 2615756, "count": 2615756, "decode_str": "\u7f1a"} -{"id": 1301, "token": "amp", "merges": "am p", "raw_count": 1112636, "count": 2618461, "decode_str": "amp"} -{"id": 1362, "token": "yn", "merges": "y n", "raw_count": 479644, "count": 2621986, "decode_str": "yn"} -{"id": 51023, "token": "\u00e5\u0134\u0132", "merges": "\u00e5\u0134 \u0132", "raw_count": 2622194, "count": 2622194, "decode_str": "\u5490"} -{"id": 1452, "token": "que", "merges": "qu e", "raw_count": 385772, "count": 2625650, "decode_str": "que"} -{"id": 1003, "token": "ement", "merges": "em ent", "raw_count": 84682, "count": 2626359, "decode_str": "ement"} -{"id": 35033, "token": "'''", "merges": "'' '", "raw_count": 2628173, "count": 2628173, "decode_str": "'''"} -{"id": 53828, "token": "\u00e8\u00af\u00a1", "merges": "\u00e8\u00af \u00a1", "raw_count": 2630914, "count": 2630914, "decode_str": "\u8be1"} -{"id": 5964, "token": "PO", "merges": "P O", "raw_count": 1887474, "count": 2631682, "decode_str": "PO"} -{"id": 946, "token": "\u0120spec", "merges": "\u0120spe c", "raw_count": 188359, "count": 2638418, "decode_str": " spec"} -{"id": 52851, "token": "\u00e7\u0132\u00a6", "merges": "\u00e7\u0132 \u00a6", "raw_count": 2641280, "count": 2641280, "decode_str": "\u7426"} -{"id": 863, "token": "\u0120att", "merges": "\u0120at t", "raw_count": 341031, "count": 2643562, "decode_str": " att"} -{"id": 51916, "token": "\u00e6\u012d\u00a3", "merges": "\u00e6\u012d \u00a3", "raw_count": 2644535, "count": 2644535, "decode_str": "\u62e3"} -{"id": 943, "token": "\u0120should", "merges": "\u0120sh ould", "raw_count": 2576321, "count": 2647658, "decode_str": " should"} -{"id": 9344, "token": "obj", "merges": "ob j", "raw_count": 2652574, "count": 2652574, "decode_str": "obj"} -{"id": 22359, "token": "365", "merges": "36 5", "raw_count": 2652881, "count": 2652881, "decode_str": "365"} -{"id": 33038, "token": "8000", "merges": "8 000", "raw_count": 2653388, "count": 2653388, "decode_str": "8000"} -{"id": 52451, "token": "\u00e6\u00b0\u0141", "merges": "\u00e6\u00b0 \u0141", "raw_count": 2653819, "count": 2653819, "decode_str": "\u6c1f"} -{"id": 53462, "token": "\u00e8\u0122\u00bf", "merges": "\u00e8\u0122 \u00bf", "raw_count": 2657146, "count": 2657146, "decode_str": "\u803f"} -{"id": 16742, "token": "999", "merges": "99 9", "raw_count": 2661295, "count": 2661295, "decode_str": "999"} -{"id": 1479, "token": "ik", "merges": "i k", "raw_count": 1278015, "count": 2661414, "decode_str": "ik"} -{"id": 2422, "token": "Al", "merges": "A l", "raw_count": 1483773, "count": 2665890, "decode_str": "Al"} -{"id": 693, "token": "erm", "merges": "er m", "raw_count": 317551, "count": 2668904, "decode_str": "erm"} -{"id": 3788, "token": "MA", "merges": "M A", "raw_count": 1802065, "count": 2669099, "decode_str": "MA"} -{"id": 1397, "token": "ds", "merges": "d s", "raw_count": 1701406, "count": 2669156, "decode_str": "ds"} -{"id": 789, "token": "\u0120work", "merges": "\u0120wor k", "raw_count": 1447051, "count": 2673791, "decode_str": " work"} -{"id": 909, "token": "eg", "merges": "e g", "raw_count": 621380, "count": 2674363, "decode_str": "eg"} -{"id": 9148, "token": "split", "merges": "s plit", "raw_count": 2677559, "count": 2677559, "decode_str": "split"} -{"id": 50756, "token": "\u00e5\u0129\u00b3", "merges": "\u00e5\u0129 \u00b3", "raw_count": 2677798, "count": 2677798, "decode_str": "\u51f3"} -{"id": 616, "token": "\u0120their", "merges": "\u0120the ir", "raw_count": 2678677, "count": 2683260, "decode_str": " their"} -{"id": 51843, "token": "\u00e6\u012b\u013d", "merges": "\u00e6\u012b \u013d", "raw_count": 2683766, "count": 2683766, "decode_str": "\u625b"} -{"id": 411, "token": "\u0120W", "merges": "\u0120 W", "raw_count": 722569, "count": 2684023, "decode_str": " W"} -{"id": 1584, "token": "ote", "merges": "ot e", "raw_count": 210929, "count": 2684155, "decode_str": "ote"} -{"id": 53078, "token": "\u00e7\u00a1\u013f", "merges": "\u00e7\u00a1 \u013f", "raw_count": 2687856, "count": 2687856, "decode_str": "\u785d"} -{"id": 2399, "token": "bo", "merges": "b o", "raw_count": 872425, "count": 2689795, "decode_str": "bo"} -{"id": 52278, "token": "\u00e6\u0142\u012a", "merges": "\u00e6\u0142 \u012a", "raw_count": 2692513, "count": 2692513, "decode_str": "\u6808"} -{"id": 1059, "token": "let", "merges": "le t", "raw_count": 916833, "count": 2693105, "decode_str": "let"} -{"id": 1193, "token": "\u0120fil", "merges": "\u0120f il", "raw_count": 141943, "count": 2693790, "decode_str": " fil"} -{"id": 2823, "token": "comm", "merges": "com m", "raw_count": 275789, "count": 2700582, "decode_str": "comm"} -{"id": 6091, "token": "sf", "merges": "s f", "raw_count": 2702408, "count": 2702685, "decode_str": "sf"} -{"id": 16552, "token": "350", "merges": "3 50", "raw_count": 2702895, "count": 2702895, "decode_str": "350"} -{"id": 4625, "token": "EC", "merges": "E C", "raw_count": 2646195, "count": 2703507, "decode_str": "EC"} -{"id": 14256, "token": "220", "merges": "2 20", "raw_count": 2707926, "count": 2707926, "decode_str": "220"} -{"id": 728, "token": "ied", "merges": "i ed", "raw_count": 274489, "count": 2708254, "decode_str": "ied"} -{"id": 11183, "token": "update", "merges": "up date", "raw_count": 2712409, "count": 2712409, "decode_str": "update"} -{"id": 989, "token": "inal", "merges": "in al", "raw_count": 355667, "count": 2712480, "decode_str": "inal"} -{"id": 8559, "token": "message", "merges": "m essage", "raw_count": 2713200, "count": 2713200, "decode_str": "message"} -{"id": 965, "token": "li", "merges": "l i", "raw_count": 834289, "count": 2716713, "decode_str": "li"} -{"id": 52535, "token": "\u00e6\u00b3\u00a3", "merges": "\u00e6\u00b3 \u00a3", "raw_count": 2716935, "count": 2716935, "decode_str": "\u6ce3"} -{"id": 1511, "token": "\u0120type", "merges": "\u0120ty pe", "raw_count": 2715474, "count": 2717144, "decode_str": " type"} -{"id": 5903, "token": "check", "merges": "che ck", "raw_count": 2575780, "count": 2719153, "decode_str": "check"} -{"id": 54402, "token": "\u00e9\u013f\u0135", "merges": "\u00e9\u013f \u0135", "raw_count": 2720757, "count": 2720757, "decode_str": "\u9753"} -{"id": 50624, "token": "\u00e5\u0122\u013a", "merges": "\u00e5\u0122 \u013a", "raw_count": 2722349, "count": 2722349, "decode_str": "\u5018"} -{"id": 53317, "token": "\u00e7\u00ba\u00ac", "merges": "\u00e7\u00ba \u00ac", "raw_count": 2726698, "count": 2726698, "decode_str": "\u7eac"} -{"id": 53352, "token": "\u00e7\u00bb\u0140", "merges": "\u00e7\u00bb \u0140", "raw_count": 2732046, "count": 2732046, "decode_str": "\u7ede"} -{"id": 51498, "token": "\u00e5\u00b1\u00bf", "merges": "\u00e5\u00b1 \u00bf", "raw_count": 2732819, "count": 2732819, "decode_str": "\u5c7f"} -{"id": 51994, "token": "\u00e6\u0130\u0142", "merges": "\u00e6\u0130 \u0142", "raw_count": 2734934, "count": 2734934, "decode_str": "\u63a0"} -{"id": 54256, "token": "\u00e9\u0137\u0133", "merges": "\u00e9\u0137 \u0133", "raw_count": 2737125, "count": 2737125, "decode_str": "\u9551"} -{"id": 50575, "token": "\u00e4\u00be\u012a", "merges": "\u00e4\u00be \u012a", "raw_count": 2740440, "count": 2740440, "decode_str": "\u4f88"} -{"id": 51078, "token": "\u00e5\u0135\u00ba", "merges": "\u00e5\u0135 \u00ba", "raw_count": 2741662, "count": 2741662, "decode_str": "\u54fa"} -{"id": 52717, "token": "\u00e7\u0123\u00b8", "merges": "\u00e7\u0123 \u00b8", "raw_count": 2742042, "count": 2742042, "decode_str": "\u7078"} -{"id": 51233, "token": "\u00e5\u0141\u0136", "merges": "\u00e5\u0141 \u0136", "raw_count": 2742272, "count": 2742272, "decode_str": "\u57d4"} -{"id": 3175, "token": "PR", "merges": "P R", "raw_count": 1968263, "count": 2745838, "decode_str": "PR"} -{"id": 53952, "token": "\u00e8\u00b5\u0130", "merges": "\u00e8\u00b5 \u0130", "raw_count": 2748503, "count": 2748503, "decode_str": "\u8d4e"} -{"id": 54286, "token": "\u00e9\u0139\u00bd", "merges": "\u00e9\u0139 \u00bd", "raw_count": 2749900, "count": 2749900, "decode_str": "\u95fd"} -{"id": 51586, "token": "\u00e5\u00bb\u0135", "merges": "\u00e5\u00bb \u0135", "raw_count": 2751028, "count": 2751028, "decode_str": "\u5ed3"} -{"id": 54127, "token": "\u00e9\u0123\u0131", "merges": "\u00e9\u0123 \u0131", "raw_count": 2751747, "count": 2751747, "decode_str": "\u904f"} -{"id": 3613, "token": "\u0120!=", "merges": "\u0120! =", "raw_count": 2763294, "count": 2763294, "decode_str": " !="} -{"id": 653, "token": "\u0120sp", "merges": "\u0120s p", "raw_count": 474880, "count": 2766722, "decode_str": " sp"} -{"id": 2284, "token": "ai", "merges": "a i", "raw_count": 2345154, "count": 2767024, "decode_str": "ai"} -{"id": 5097, "token": "oken", "merges": "ok en", "raw_count": 82089, "count": 2768904, "decode_str": "oken"} -{"id": 3859, "token": "PL", "merges": "P L", "raw_count": 1770634, "count": 2769850, "decode_str": "PL"} -{"id": 726, "token": "\u0120sy", "merges": "\u0120s y", "raw_count": 214194, "count": 2773326, "decode_str": " sy"} -{"id": 51915, "token": "\u00e6\u012d\u00a2", "merges": "\u00e6\u012d \u00a2", "raw_count": 2773453, "count": 2773453, "decode_str": "\u62e2"} -{"id": 52509, "token": "\u00e6\u00b2\u00a6", "merges": "\u00e6\u00b2 \u00a6", "raw_count": 2773883, "count": 2773883, "decode_str": "\u6ca6"} -{"id": 2465, "token": "dex", "merges": "de x", "raw_count": 70067, "count": 2775698, "decode_str": "dex"} -{"id": 902, "token": "rit", "merges": "r it", "raw_count": 321987, "count": 2777764, "decode_str": "rit"} -{"id": 53928, "token": "\u00e8\u00b4\u00ae", "merges": "\u00e8\u00b4 \u00ae", "raw_count": 2777996, "count": 2777996, "decode_str": "\u8d2e"} -{"id": 53478, "token": "\u00e8\u0124\u0129", "merges": "\u00e8\u0124 \u0129", "raw_count": 2788860, "count": 2788860, "decode_str": "\u8087"} -{"id": 1182, "token": "\u0120z", "merges": "\u0120 z", "raw_count": 1605391, "count": 2789601, "decode_str": " z"} -{"id": 530, "token": "\u0120U", "merges": "\u0120 U", "raw_count": 504991, "count": 2792781, "decode_str": " U"} -{"id": 3775, "token": "error", "merges": "err or", "raw_count": 2522082, "count": 2792931, "decode_str": "error"} -{"id": 830, "token": "\u0120form", "merges": "\u0120for m", "raw_count": 1052679, "count": 2794529, "decode_str": " form"} -{"id": 1746, "token": "ength", "merges": "eng th", "raw_count": 21929, "count": 2801105, "decode_str": "ength"} -{"id": 1303, "token": "ument", "merges": "um ent", "raw_count": 136169, "count": 2804701, "decode_str": "ument"} -{"id": 33109, "token": "%-", "merges": "% -", "raw_count": 2805401, "count": 2805401, "decode_str": "%-"} -{"id": 54115, "token": "\u00e9\u0122\u00ae", "merges": "\u00e9\u0122 \u00ae", "raw_count": 2810399, "count": 2810399, "decode_str": "\u902e"} -{"id": 802, "token": "\u0120em", "merges": "\u0120e m", "raw_count": 272513, "count": 2811626, "decode_str": " em"} -{"id": 2845, "token": "rec", "merges": "re c", "raw_count": 809183, "count": 2812518, "decode_str": "rec"} -{"id": 2906, "token": "Ar", "merges": "A r", "raw_count": 615903, "count": 2812596, "decode_str": "Ar"} -{"id": 5142, "token": "tem", "merges": "t em", "raw_count": 177443, "count": 2813246, "decode_str": "tem"} -{"id": 1034, "token": "ward", "merges": "w ard", "raw_count": 577918, "count": 2814393, "decode_str": "ward"} -{"id": 6343, "token": "write", "merges": "w rite", "raw_count": 2738631, "count": 2819635, "decode_str": "write"} -{"id": 675, "token": "reat", "merges": "re at", "raw_count": 60967, "count": 2820328, "decode_str": "reat"} -{"id": 53204, "token": "\u00e7\u00ab\u00bf", "merges": "\u00e7\u00ab \u00bf", "raw_count": 2821970, "count": 2821970, "decode_str": "\u7aff"} -{"id": 53013, "token": "\u00e7\u013e\u00af", "merges": "\u00e7\u013e \u00af", "raw_count": 2824144, "count": 2824144, "decode_str": "\u772f"} -{"id": 2976, "token": "andom", "merges": "and om", "raw_count": 28590, "count": 2826933, "decode_str": "andom"} -{"id": 7210, "token": "valid", "merges": "val id", "raw_count": 1188266, "count": 2827550, "decode_str": "valid"} -{"id": 51739, "token": "\u00e6\u0124\u012f", "merges": "\u00e6\u0124 \u012f", "raw_count": 2827662, "count": 2827662, "decode_str": "\u608d"} -{"id": 2337, "token": "fun", "merges": "f un", "raw_count": 388468, "count": 2828240, "decode_str": "fun"} -{"id": 53290, "token": "\u00e7\u00b3\u00af", "merges": "\u00e7\u00b3 \u00af", "raw_count": 2831683, "count": 2831683, "decode_str": "\u7cef"} -{"id": 6953, "token": "create", "merges": "cre ate", "raw_count": 2812474, "count": 2832184, "decode_str": "create"} -{"id": 9900, "token": "bet", "merges": "b et", "raw_count": 2694200, "count": 2835439, "decode_str": "bet"} -{"id": 30291, "token": "xl", "merges": "x l", "raw_count": 2835711, "count": 2835711, "decode_str": "xl"} -{"id": 54476, "token": "\u00e9\u00a6\u0127", "merges": "\u00e9\u00a6 \u0127", "raw_count": 2835744, "count": 2835744, "decode_str": "\u9985"} -{"id": 809, "token": "\u0120def", "merges": "\u0120de f", "raw_count": 168117, "count": 2840368, "decode_str": " def"} -{"id": 3172, "token": "EM", "merges": "E M", "raw_count": 2031765, "count": 2853388, "decode_str": "EM"} -{"id": 730, "token": "\u0120gen", "merges": "\u0120g en", "raw_count": 316824, "count": 2856537, "decode_str": " gen"} -{"id": 51053, "token": "\u00e5\u0135\u0126", "merges": "\u00e5\u0135 \u0126", "raw_count": 2861354, "count": 2861354, "decode_str": "\u54c4"} -{"id": 1311, "token": "CR", "merges": "C R", "raw_count": 2023929, "count": 2863101, "decode_str": "CR"} -{"id": 54426, "token": "\u00e9\u00a1\u00b7", "merges": "\u00e9\u00a1 \u00b7", "raw_count": 2863427, "count": 2863427, "decode_str": "\u9877"} -{"id": 53130, "token": "\u00e7\u00a5\u00b7", "merges": "\u00e7\u00a5 \u00b7", "raw_count": 2863866, "count": 2863866, "decode_str": "\u7977"} -{"id": 2083, "token": "enc", "merges": "en c", "raw_count": 605282, "count": 2869778, "decode_str": "enc"} -{"id": 864, "token": "hen", "merges": "he n", "raw_count": 575821, "count": 2870902, "decode_str": "hen"} -{"id": 1473, "token": "da", "merges": "d a", "raw_count": 1194167, "count": 2877066, "decode_str": "da"} -{"id": 2727, "token": "off", "merges": "o ff", "raw_count": 803350, "count": 2877382, "decode_str": "off"} -{"id": 52744, "token": "\u00e7\u0126\u012b", "merges": "\u00e7\u0126 \u012b", "raw_count": 2881111, "count": 2881111, "decode_str": "\u7109"} -{"id": 52504, "token": "\u00e6\u00b2\u013d", "merges": "\u00e6\u00b2 \u013d", "raw_count": 2885921, "count": 2885921, "decode_str": "\u6c9b"} -{"id": 1747, "token": "reg", "merges": "re g", "raw_count": 880031, "count": 2885934, "decode_str": "reg"} -{"id": 1532, "token": "---", "merges": "-- -", "raw_count": 2112959, "count": 2889749, "decode_str": "---"} -{"id": 7913, "token": "mg", "merges": "m g", "raw_count": 2890556, "count": 2890556, "decode_str": "mg"} -{"id": 801, "token": "\u0120ind", "merges": "\u0120in d", "raw_count": 442307, "count": 2891857, "decode_str": " ind"} -{"id": 2648, "token": "CC", "merges": "C C", "raw_count": 2538296, "count": 2895018, "decode_str": "CC"} -{"id": 798, "token": "igh", "merges": "ig h", "raw_count": 139492, "count": 2897567, "decode_str": "igh"} -{"id": 54400, "token": "\u00e9\u013e\u00be", "merges": "\u00e9\u013e \u00be", "raw_count": 2898963, "count": 2898963, "decode_str": "\u973e"} -{"id": 52075, "token": "\u00e6\u0137\u013d", "merges": "\u00e6\u0137 \u013d", "raw_count": 2900656, "count": 2900656, "decode_str": "\u655b"} -{"id": 2608, "token": "\u0120user", "merges": "\u0120us er", "raw_count": 2523617, "count": 2902067, "decode_str": " user"} -{"id": 50444, "token": "\u00e4\u00b9\u0134", "merges": "\u00e4\u00b9 \u0134", "raw_count": 2905862, "count": 2905862, "decode_str": "\u4e52"} -{"id": 2490, "token": "\u0120\u010a", "merges": "\u0120 \u010a", "raw_count": 2914239, "count": 2914239, "decode_str": " \n"} -{"id": 54499, "token": "\u00e9\u00aa\u0131", "merges": "\u00e9\u00aa \u0131", "raw_count": 2915096, "count": 2915096, "decode_str": "\u9a8f"} -{"id": 745, "token": "\u0120off", "merges": "\u0120of f", "raw_count": 452326, "count": 2915124, "decode_str": " off"} -{"id": 9795, "token": "Ret", "merges": "R et", "raw_count": 216497, "count": 2915253, "decode_str": "Ret"} -{"id": 4464, "token": "((", "merges": "( (", "raw_count": 2801107, "count": 2916767, "decode_str": "(("} -{"id": 2404, "token": "itle", "merges": "it le", "raw_count": 112437, "count": 2921413, "decode_str": "itle"} -{"id": 1183, "token": "\u0120resp", "merges": "\u0120res p", "raw_count": 300047, "count": 2925426, "decode_str": " resp"} -{"id": 54054, "token": "\u00e8\u00be\u013e", "merges": "\u00e8\u00be \u013e", "raw_count": 2927196, "count": 2927196, "decode_str": "\u8f9c"} -{"id": 52476, "token": "\u00e6\u00b1\u013d", "merges": "\u00e6\u00b1 \u013d", "raw_count": 2931925, "count": 2931925, "decode_str": "\u6c5b"} -{"id": 53257, "token": "\u00e7\u00b1\u00bd", "merges": "\u00e7\u00b1 \u00bd", "raw_count": 2933162, "count": 2933162, "decode_str": "\u7c7d"} -{"id": 718, "token": "\u0120ass", "merges": "\u0120as s", "raw_count": 71269, "count": 2938643, "decode_str": " ass"} -{"id": 4989, "token": "df", "merges": "d f", "raw_count": 2354277, "count": 2940014, "decode_str": "df"} -{"id": 7684, "token": "\u0120os", "merges": "\u0120o s", "raw_count": 2942262, "count": 2942262, "decode_str": " os"} -{"id": 960, "token": "ctions", "merges": "ction s", "raw_count": 99332, "count": 2943946, "decode_str": "ctions"} -{"id": 51587, "token": "\u00e5\u00bb\u0138", "merges": "\u00e5\u00bb \u0138", "raw_count": 2948758, "count": 2948758, "decode_str": "\u5ed6"} -{"id": 8581, "token": "status", "merges": "st atus", "raw_count": 2948759, "count": 2948759, "decode_str": "status"} -{"id": 8780, "token": "client", "merges": "cl ient", "raw_count": 2949773, "count": 2949773, "decode_str": "client"} -{"id": 6223, "token": "~~~", "merges": "~~ ~", "raw_count": 2951827, "count": 2951827, "decode_str": "~~~"} -{"id": 962, "token": "ull", "merges": "ul l", "raw_count": 243760, "count": 2951878, "decode_str": "ull"} -{"id": 951, "token": "cy", "merges": "c y", "raw_count": 430960, "count": 2952219, "decode_str": "cy"} -{"id": 53197, "token": "\u00e7\u00ab\u00a3", "merges": "\u00e7\u00ab \u00a3", "raw_count": 2953230, "count": 2953230, "decode_str": "\u7ae3"} -{"id": 4065, "token": "call", "merges": "c all", "raw_count": 1941417, "count": 2960782, "decode_str": "call"} -{"id": 52872, "token": "\u00e7\u0136\u00ab", "merges": "\u00e7\u0136 \u00ab", "raw_count": 2966763, "count": 2966763, "decode_str": "\u752b"} -{"id": 10249, "token": "OK", "merges": "O K", "raw_count": 2973527, "count": 2973527, "decode_str": "OK"} -{"id": 1920, "token": "aut", "merges": "a ut", "raw_count": 640054, "count": 2978338, "decode_str": "aut"} -{"id": 1949, "token": "rain", "merges": "ra in", "raw_count": 340407, "count": 2989306, "decode_str": "rain"} -{"id": 53656, "token": "\u00e8\u012d\u00af", "merges": "\u00e8\u012d \u00af", "raw_count": 2993866, "count": 2993866, "decode_str": "\u82ef"} -{"id": 52477, "token": "\u00e6\u00b1\u013f", "merges": "\u00e6\u00b1 \u013f", "raw_count": 2997602, "count": 2997602, "decode_str": "\u6c5d"} -{"id": 53615, "token": "\u00e8\u012c\u013b", "merges": "\u00e8\u012c \u013b", "raw_count": 3013326, "count": 3013326, "decode_str": "\u8299"} -{"id": 52863, "token": "\u00e7\u0136\u0126", "merges": "\u00e7\u0136 \u0126", "raw_count": 3018841, "count": 3018841, "decode_str": "\u7504"} -{"id": 52780, "token": "\u00e7\u012b\u00a1", "merges": "\u00e7\u012b \u00a1", "raw_count": 3022828, "count": 3022828, "decode_str": "\u7261"} -{"id": 1094, "token": "air", "merges": "a ir", "raw_count": 931908, "count": 3024239, "decode_str": "air"} -{"id": 1657, "token": "ule", "merges": "u le", "raw_count": 187505, "count": 3025585, "decode_str": "ule"} -{"id": 4548, "token": "MP", "merges": "M P", "raw_count": 2585355, "count": 3027960, "decode_str": "MP"} -{"id": 51728, "token": "\u00e6\u0123\u00b3", "merges": "\u00e6\u0123 \u00b3", "raw_count": 3035118, "count": 3035118, "decode_str": "\u6073"} -{"id": 3024, "token": "net", "merges": "n et", "raw_count": 2116016, "count": 3040503, "decode_str": "net"} -{"id": 8456, "token": "json", "merges": "j son", "raw_count": 3041034, "count": 3041034, "decode_str": "json"} -{"id": 529, "token": "oug", "merges": "ou g", "raw_count": 61062, "count": 3042330, "decode_str": "oug"} -{"id": 50997, "token": "\u00e5\u0133\u0137", "merges": "\u00e5\u0133 \u0137", "raw_count": 3044465, "count": 3044465, "decode_str": "\u5455"} -{"id": 52966, "token": "\u00e7\u013c\u0124", "merges": "\u00e7\u013c \u0124", "raw_count": 3049865, "count": 3049865, "decode_str": "\u7682"} -{"id": 1785, "token": "Re", "merges": "R e", "raw_count": 1340471, "count": 3050031, "decode_str": "Re"} -{"id": 53571, "token": "\u00e8\u012a\u0127", "merges": "\u00e8\u012a \u0127", "raw_count": 3052367, "count": 3052367, "decode_str": "\u8205"} -{"id": 3675, "token": "trans", "merges": "tr ans", "raw_count": 1083356, "count": 3053752, "decode_str": "trans"} -{"id": 769, "token": "\u0120act", "merges": "\u0120a ct", "raw_count": 409834, "count": 3055470, "decode_str": " act"} -{"id": 1541, "token": "gen", "merges": "g en", "raw_count": 895245, "count": 3056514, "decode_str": "gen"} -{"id": 54412, "token": "\u00e9\u013f\u00b6", "merges": "\u00e9\u013f \u00b6", "raw_count": 3059721, "count": 3059721, "decode_str": "\u9776"} -{"id": 637, "token": "\u0120man", "merges": "\u0120m an", "raw_count": 437832, "count": 3062485, "decode_str": " man"} -{"id": 12166, "token": "\u0120{}", "merges": "\u0120{ }", "raw_count": 3065062, "count": 3065062, "decode_str": " {}"} -{"id": 53174, "token": "\u00e7\u00a8\u00a3", "merges": "\u00e7\u00a8 \u00a3", "raw_count": 3065551, "count": 3065551, "decode_str": "\u7a23"} -{"id": 52661, "token": "\u00e6\u00b8\u013f", "merges": "\u00e6\u00b8 \u013f", "raw_count": 3067744, "count": 3067744, "decode_str": "\u6e1d"} -{"id": 51925, "token": "\u00e6\u012d\u00af", "merges": "\u00e6\u012d \u00af", "raw_count": 3069814, "count": 3069814, "decode_str": "\u62ef"} -{"id": 9595, "token": "1999", "merges": "19 99", "raw_count": 3071327, "count": 3071327, "decode_str": "1999"} -{"id": 50499, "token": "\u00e4\u00bb\u0133", "merges": "\u00e4\u00bb \u0133", "raw_count": 3078607, "count": 3078607, "decode_str": "\u4ed1"} -{"id": 987, "token": "\u0120right", "merges": "\u0120r ight", "raw_count": 1372779, "count": 3078637, "decode_str": " right"} -{"id": 1287, "token": "\u0120develop", "merges": "\u0120de velop", "raw_count": 209992, "count": 3084756, "decode_str": " develop"} -{"id": 51410, "token": "\u00e5\u00ae\u013d", "merges": "\u00e5\u00ae \u013d", "raw_count": 3085277, "count": 3085277, "decode_str": "\u5b9b"} -{"id": 52175, "token": "\u00e6\u013b\u00be", "merges": "\u00e6\u013b \u00be", "raw_count": 3086973, "count": 3086973, "decode_str": "\u667e"} -{"id": 2484, "token": "wh", "merges": "w h", "raw_count": 501914, "count": 3089180, "decode_str": "wh"} -{"id": 3581, "token": "ogle", "merges": "og le", "raw_count": 11694, "count": 3091536, "decode_str": "ogle"} -{"id": 52340, "token": "\u00e6\u00a5\u0142", "merges": "\u00e6\u00a5 \u0142", "raw_count": 3093323, "count": 3093323, "decode_str": "\u6960"} -{"id": 12434, "token": "140", "merges": "14 0", "raw_count": 3093756, "count": 3093756, "decode_str": "140"} -{"id": 52277, "token": "\u00e6\u0142\u0127", "merges": "\u00e6\u0142 \u0127", "raw_count": 3094592, "count": 3094592, "decode_str": "\u6805"} -{"id": 54284, "token": "\u00e9\u0139\u00ba", "merges": "\u00e9\u0139 \u00ba", "raw_count": 3095284, "count": 3095284, "decode_str": "\u95fa"} -{"id": 15659, "token": "PK", "merges": "P K", "raw_count": 3100956, "count": 3100956, "decode_str": "PK"} -{"id": 50612, "token": "\u00e4\u00bf\u00af", "merges": "\u00e4\u00bf \u00af", "raw_count": 3102693, "count": 3102693, "decode_str": "\u4fef"} -{"id": 3246, "token": "PE", "merges": "P E", "raw_count": 2292307, "count": 3106660, "decode_str": "PE"} -{"id": 872, "token": "\u0120prov", "merges": "\u0120pro v", "raw_count": 25692, "count": 3107154, "decode_str": " prov"} -{"id": 53591, "token": "\u00e8\u012a\u00b6", "merges": "\u00e8\u012a \u00b6", "raw_count": 3111398, "count": 3111398, "decode_str": "\u8236"} -{"id": 51104, "token": "\u00e5\u0137\u00b8", "merges": "\u00e5\u0137 \u00b8", "raw_count": 3117761, "count": 3117761, "decode_str": "\u5578"} -{"id": 4789, "token": "py", "merges": "p y", "raw_count": 2049778, "count": 3118175, "decode_str": "py"} -{"id": 47017, "token": "618", "merges": "6 18", "raw_count": 3118963, "count": 3118963, "decode_str": "618"} -{"id": 52847, "token": "\u00e7\u0132\u0132", "merges": "\u00e7\u0132 \u0132", "raw_count": 3120373, "count": 3120373, "decode_str": "\u7410"} -{"id": 53875, "token": "\u00e8\u00b0\u013e", "merges": "\u00e8\u00b0 \u013e", "raw_count": 3123643, "count": 3123643, "decode_str": "\u8c1c"} -{"id": 2409, "token": "ception", "merges": "cept ion", "raw_count": 83536, "count": 3125079, "decode_str": "ception"} -{"id": 51941, "token": "\u00e6\u012e\u013c", "merges": "\u00e6\u012e \u013c", "raw_count": 3126049, "count": 3126049, "decode_str": "\u631a"} -{"id": 50796, "token": "\u00e5\u012b\u0136", "merges": "\u00e5\u012b \u0136", "raw_count": 3127982, "count": 3127982, "decode_str": "\u5254"} -{"id": 53827, "token": "\u00e8\u00af\u0142", "merges": "\u00e8\u00af \u0142", "raw_count": 3129579, "count": 3129579, "decode_str": "\u8be0"} -{"id": 50551, "token": "\u00e4\u00bd\u0133", "merges": "\u00e4\u00bd \u0133", "raw_count": 3130267, "count": 3130267, "decode_str": "\u4f51"} -{"id": 925, "token": "fr", "merges": "f r", "raw_count": 571829, "count": 3130853, "decode_str": "fr"} -{"id": 1848, "token": "RE", "merges": "R E", "raw_count": 1229359, "count": 3142651, "decode_str": "RE"} -{"id": 51113, "token": "\u00e5\u0138\u0129", "merges": "\u00e5\u0138 \u0129", "raw_count": 3142956, "count": 3142956, "decode_str": "\u5587"} -{"id": 50695, "token": "\u00e5\u0127\u00ae", "merges": "\u00e5\u0127 \u00ae", "raw_count": 3150078, "count": 3150078, "decode_str": "\u516e"} -{"id": 1354, "token": "raph", "merges": "ra ph", "raw_count": 56036, "count": 3150483, "decode_str": "raph"} -{"id": 1095, "token": "\u0120cur", "merges": "\u0120c ur", "raw_count": 631390, "count": 3151249, "decode_str": " cur"} -{"id": 932, "token": "als", "merges": "al s", "raw_count": 1126120, "count": 3153328, "decode_str": "als"} -{"id": 892, "token": "\u0120fl", "merges": "\u0120f l", "raw_count": 227161, "count": 3154629, "decode_str": " fl"} -{"id": 54435, "token": "\u00e9\u00a2\u0124", "merges": "\u00e9\u00a2 \u0124", "raw_count": 3157599, "count": 3157599, "decode_str": "\u9882"} -{"id": 52633, "token": "\u00e6\u00b7\u0133", "merges": "\u00e6\u00b7 \u0133", "raw_count": 3158279, "count": 3158279, "decode_str": "\u6dd1"} -{"id": 692, "token": "ific", "merges": "if ic", "raw_count": 244322, "count": 3159373, "decode_str": "ific"} -{"id": 52286, "token": "\u00e6\u0142\u0139", "merges": "\u00e6\u0142 \u0139", "raw_count": 3163308, "count": 3163308, "decode_str": "\u6817"} -{"id": 1116, "token": "arch", "merges": "ar ch", "raw_count": 353796, "count": 3165766, "decode_str": "arch"} -{"id": 5260, "token": "xx", "merges": "x x", "raw_count": 2079795, "count": 3165864, "decode_str": "xx"} -{"id": 1374, "token": "view", "merges": "v iew", "raw_count": 1667018, "count": 3167053, "decode_str": "view"} -{"id": 741, "token": "clud", "merges": "cl ud", "raw_count": 10077, "count": 3176030, "decode_str": "clud"} -{"id": 50493, "token": "\u00e4\u00bb\u0128", "merges": "\u00e4\u00bb \u0128", "raw_count": 3176312, "count": 3176312, "decode_str": "\u4ec6"} -{"id": 50722, "token": "\u00e5\u0128\u00a4", "merges": "\u00e5\u0128 \u00a4", "raw_count": 3177731, "count": 3177731, "decode_str": "\u51a4"} -{"id": 54015, "token": "\u00e8\u00ba\u00af", "merges": "\u00e8\u00ba \u00af", "raw_count": 3177762, "count": 3177762, "decode_str": "\u8eaf"} -{"id": 53375, "token": "\u00e7\u00bb\u00bd", "merges": "\u00e7\u00bb \u00bd", "raw_count": 3178188, "count": 3178188, "decode_str": "\u7efd"} -{"id": 1121, "token": "\u0120op", "merges": "\u0120o p", "raw_count": 475974, "count": 3178208, "decode_str": " op"} -{"id": 50478, "token": "\u00e4\u00ba\u00a8", "merges": "\u00e4\u00ba \u00a8", "raw_count": 3179697, "count": 3179697, "decode_str": "\u4ea8"} -{"id": 54089, "token": "\u00e8\u00bf\u0143", "merges": "\u00e8\u00bf \u0143", "raw_count": 3179765, "count": 3179765, "decode_str": "\u8fed"} -{"id": 4835, "token": "item", "merges": "it em", "raw_count": 3183284, "count": 3183284, "decode_str": "item"} -{"id": 642, "token": "\u0120no", "merges": "\u0120n o", "raw_count": 2911501, "count": 3183840, "decode_str": " no"} -{"id": 50691, "token": "\u00e5\u0127\u013e", "merges": "\u00e5\u0127 \u013e", "raw_count": 3185727, "count": 3185727, "decode_str": "\u515c"} -{"id": 763, "token": "ish", "merges": "is h", "raw_count": 792319, "count": 3200086, "decode_str": "ish"} -{"id": 53135, "token": "\u00e7\u00a6\u0126", "merges": "\u00e7\u00a6 \u0126", "raw_count": 3200736, "count": 3200736, "decode_str": "\u7984"} -{"id": 742, "token": "hed", "merges": "he d", "raw_count": 212339, "count": 3202284, "decode_str": "hed"} -{"id": 32158, "token": "1200", "merges": "12 00", "raw_count": 3203170, "count": 3203170, "decode_str": "1200"} -{"id": 1100, "token": "ines", "merges": "in es", "raw_count": 404562, "count": 3203203, "decode_str": "ines"} -{"id": 54382, "token": "\u00e9\u013e\u0128", "merges": "\u00e9\u013e \u0128", "raw_count": 3207056, "count": 3207056, "decode_str": "\u9706"} -{"id": 2522, "token": "head", "merges": "he ad", "raw_count": 863191, "count": 3207553, "decode_str": "head"} -{"id": 4403, "token": "plit", "merges": "pl it", "raw_count": 72517, "count": 3210559, "decode_str": "plit"} -{"id": 54164, "token": "\u00e9\u0124\u00b5", "merges": "\u00e9\u0124 \u00b5", "raw_count": 3211484, "count": 3211484, "decode_str": "\u90b5"} -{"id": 50655, "token": "\u00e5\u0124\u012f", "merges": "\u00e5\u0124 \u012f", "raw_count": 3214281, "count": 3214281, "decode_str": "\u508d"} -{"id": 52285, "token": "\u00e6\u0142\u0138", "merges": "\u00e6\u0142 \u0138", "raw_count": 3214394, "count": 3214394, "decode_str": "\u6816"} -{"id": 53217, "token": "\u00e7\u00ac\u00a8", "merges": "\u00e7\u00ac \u00a8", "raw_count": 3217350, "count": 3217350, "decode_str": "\u7b28"} -{"id": 5116, "token": "ename", "merges": "en ame", "raw_count": 432760, "count": 3221074, "decode_str": "ename"} -{"id": 51629, "token": "\u00e5\u00bd\u00ac", "merges": "\u00e5\u00bd \u00ac", "raw_count": 3226452, "count": 3226452, "decode_str": "\u5f6c"} -{"id": 2234, "token": "\u0120key", "merges": "\u0120ke y", "raw_count": 2972351, "count": 3227324, "decode_str": " key"} -{"id": 899, "token": "oy", "merges": "o y", "raw_count": 629395, "count": 3231372, "decode_str": "oy"} -{"id": 54359, "token": "\u00e9\u013d\u0123", "merges": "\u00e9\u013d \u0123", "raw_count": 3231380, "count": 3231380, "decode_str": "\u96c1"} -{"id": 6826, "token": "Go", "merges": "G o", "raw_count": 899435, "count": 3233314, "decode_str": "Go"} -{"id": 5715, "token": "(),", "merges": "( ),", "raw_count": 3234122, "count": 3234122, "decode_str": "(),"} -{"id": 51926, "token": "\u00e6\u012d\u00b1", "merges": "\u00e6\u012d \u00b1", "raw_count": 3238072, "count": 3238072, "decode_str": "\u62f1"} -{"id": 890, "token": "ution", "merges": "ut ion", "raw_count": 38698, "count": 3238267, "decode_str": "ution"} -{"id": 51252, "token": "\u00e5\u0142\u00a4", "merges": "\u00e5\u0142 \u00a4", "raw_count": 3244237, "count": 3244237, "decode_str": "\u5824"} -{"id": 657, "token": "\u0120V", "merges": "\u0120 V", "raw_count": 812277, "count": 3245896, "decode_str": " V"} -{"id": 53803, "token": "\u00e8\u00ae\u00bd", "merges": "\u00e8\u00ae \u00bd", "raw_count": 3247109, "count": 3247109, "decode_str": "\u8bbd"} -{"id": 1439, "token": "not", "merges": "n ot", "raw_count": 1507236, "count": 3247692, "decode_str": "not"} -{"id": 3659, "token": "point", "merges": "p oint", "raw_count": 1521054, "count": 3248355, "decode_str": "point"} -{"id": 1385, "token": "\u0120count", "merges": "\u0120c ount", "raw_count": 816407, "count": 3248425, "decode_str": " count"} -{"id": 709, "token": "ref", "merges": "re f", "raw_count": 1364466, "count": 3248800, "decode_str": "ref"} -{"id": 12812, "token": "email", "merges": "em ail", "raw_count": 3250427, "count": 3250427, "decode_str": "email"} -{"id": 50502, "token": "\u00e4\u00bb\u0137", "merges": "\u00e4\u00bb \u0137", "raw_count": 3254567, "count": 3254567, "decode_str": "\u4ed5"} -{"id": 2277, "token": "OM", "merges": "O M", "raw_count": 1400104, "count": 3256142, "decode_str": "OM"} -{"id": 50938, "token": "\u00e5\u0131\u00ae", "merges": "\u00e5\u0131 \u00ae", "raw_count": 3256347, "count": 3256347, "decode_str": "\u53ee"} -{"id": 978, "token": "\u0120inst", "merges": "\u0120in st", "raw_count": 139972, "count": 3262082, "decode_str": " inst"} -{"id": 4875, "token": "oat", "merges": "o at", "raw_count": 47414, "count": 3263223, "decode_str": "oat"} -{"id": 50631, "token": "\u00e5\u0122\u00a6", "merges": "\u00e5\u0122 \u00a6", "raw_count": 3265128, "count": 3265128, "decode_str": "\u5026"} -{"id": 51441, "token": "\u00e5\u00af\u0140", "merges": "\u00e5\u00af \u0140", "raw_count": 3267127, "count": 3267127, "decode_str": "\u5bde"} -{"id": 51396, "token": "\u00e5\u0143\u00b5", "merges": "\u00e5\u0143 \u00b5", "raw_count": 3267222, "count": 3267222, "decode_str": "\u5b75"} -{"id": 1130, "token": "ethod", "merges": "eth od", "raw_count": 23495, "count": 3269053, "decode_str": "ethod"} -{"id": 18650, "token": "np", "merges": "n p", "raw_count": 3271629, "count": 3271629, "decode_str": "np"} -{"id": 794, "token": "\u0120fun", "merges": "\u0120f un", "raw_count": 157001, "count": 3273076, "decode_str": " fun"} -{"id": 1736, "token": "\u0120arg", "merges": "\u0120ar g", "raw_count": 677873, "count": 3275315, "decode_str": " arg"} -{"id": 141, "token": "\u00d1", "merges": "NULL", "raw_count": 1298, "count": 3279442, "decode_str": "\ufffd"} -{"id": 53285, "token": "\u00e7\u00b3\u013b", "merges": "\u00e7\u00b3 \u013b", "raw_count": 3286597, "count": 3286597, "decode_str": "\u7cd9"} -{"id": 3852, "token": "rite", "merges": "r ite", "raw_count": 167758, "count": 3288240, "decode_str": "rite"} -{"id": 2415, "token": "OT", "merges": "O T", "raw_count": 1724127, "count": 3290939, "decode_str": "OT"} -{"id": 36830, "token": "kwargs", "merges": "kw args", "raw_count": 3301155, "count": 3301155, "decode_str": "kwargs"} -{"id": 817, "token": "##", "merges": "# #", "raw_count": 522030, "count": 3305894, "decode_str": "##"} -{"id": 796, "token": "ade", "merges": "ad e", "raw_count": 658689, "count": 3306193, "decode_str": "ade"} -{"id": 8971, "token": "2001", "merges": "200 1", "raw_count": 3311880, "count": 3311880, "decode_str": "2001"} -{"id": 931, "token": "tern", "merges": "ter n", "raw_count": 67347, "count": 3312254, "decode_str": "tern"} -{"id": 10927, "token": "response", "merges": "resp onse", "raw_count": 3312686, "count": 3312686, "decode_str": "response"} -{"id": 1843, "token": "LE", "merges": "L E", "raw_count": 1118985, "count": 3316297, "decode_str": "LE"} -{"id": 534, "token": "\u0120which", "merges": "\u0120wh ich", "raw_count": 3316305, "count": 3316305, "decode_str": " which"} -{"id": 52323, "token": "\u00e6\u00a3\u012f", "merges": "\u00e6\u00a3 \u012f", "raw_count": 3318337, "count": 3318337, "decode_str": "\u68cd"} -{"id": 8608, "token": "dat", "merges": "d at", "raw_count": 685683, "count": 3319099, "decode_str": "dat"} -{"id": 1131, "token": "ages", "merges": "ag es", "raw_count": 241681, "count": 3319242, "decode_str": "ages"} -{"id": 2135, "token": "back", "merges": "b ack", "raw_count": 1317967, "count": 3321969, "decode_str": "back"} -{"id": 510, "token": "The", "merges": "T he", "raw_count": 3086890, "count": 3323577, "decode_str": "The"} -{"id": 705, "token": "\u0120spe", "merges": "\u0120s pe", "raw_count": 11062, "count": 3324751, "decode_str": " spe"} -{"id": 52459, "token": "\u00e6\u00b0\u00ae", "merges": "\u00e6\u00b0 \u00ae", "raw_count": 3327795, "count": 3327795, "decode_str": "\u6c2e"} -{"id": 980, "token": "ures", "merges": "u res", "raw_count": 348961, "count": 3328133, "decode_str": "ures"} -{"id": 780, "token": "ual", "merges": "u al", "raw_count": 409924, "count": 3330339, "decode_str": "ual"} -{"id": 1155, "token": "velop", "merges": "vel op", "raw_count": 11793, "count": 3332044, "decode_str": "velop"} -{"id": 13956, "token": "join", "merges": "jo in", "raw_count": 3332573, "count": 3332573, "decode_str": "join"} -{"id": 591, "token": "\u0120per", "merges": "\u0120p er", "raw_count": 855645, "count": 3336021, "decode_str": " per"} -{"id": 852, "token": "stem", "merges": "st em", "raw_count": 121021, "count": 3337370, "decode_str": "stem"} -{"id": 53033, "token": "\u00e7\u013f\u00b9", "merges": "\u00e7\u013f \u00b9", "raw_count": 3338043, "count": 3338043, "decode_str": "\u7779"} -{"id": 54197, "token": "\u00e9\u0127\u00a5", "merges": "\u00e9\u0127 \u00a5", "raw_count": 3338142, "count": 3338142, "decode_str": "\u9165"} -{"id": 53460, "token": "\u00e8\u0122\u00bb", "merges": "\u00e8\u0122 \u00bb", "raw_count": 3349574, "count": 3349574, "decode_str": "\u803b"} -{"id": 48616, "token": "6000", "merges": "6 000", "raw_count": 3350662, "count": 3350662, "decode_str": "6000"} -{"id": 33021, "token": "......", "merges": ".... ..", "raw_count": 3356263, "count": 3356263, "decode_str": "......"} -{"id": 1249, "token": "\u012012", "merges": "\u01201 2", "raw_count": 2704816, "count": 3356709, "decode_str": " 12"} -{"id": 1595, "token": "att", "merges": "at t", "raw_count": 894434, "count": 3359549, "decode_str": "att"} -{"id": 51764, "token": "\u00e6\u0125\u0137", "merges": "\u00e6\u0125 \u0137", "raw_count": 3362559, "count": 3362559, "decode_str": "\u60d5"} -{"id": 51064, "token": "\u00e5\u0135\u0133", "merges": "\u00e5\u0135 \u0133", "raw_count": 3366974, "count": 3366974, "decode_str": "\u54d1"} -{"id": 52655, "token": "\u00e6\u00b8\u012f", "merges": "\u00e6\u00b8 \u012f", "raw_count": 3373433, "count": 3373433, "decode_str": "\u6e0d"} -{"id": 6267, "token": "''", "merges": "' '", "raw_count": 565254, "count": 3377030, "decode_str": "''"} -{"id": 953, "token": "its", "merges": "it s", "raw_count": 1299192, "count": 3381178, "decode_str": "its"} -{"id": 1601, "token": "work", "merges": "w ork", "raw_count": 701416, "count": 3383051, "decode_str": "work"} -{"id": 749, "token": "\u0120sub", "merges": "\u0120su b", "raw_count": 1366744, "count": 3384299, "decode_str": " sub"} -{"id": 942, "token": "ments", "merges": "ment s", "raw_count": 532357, "count": 3388297, "decode_str": "ments"} -{"id": 963, "token": "\u0120ty", "merges": "\u0120t y", "raw_count": 70334, "count": 3392765, "decode_str": " ty"} -{"id": 1070, "token": "led", "merges": "l ed", "raw_count": 1690398, "count": 3393179, "decode_str": "led"} -{"id": 964, "token": "\u0120.", "merges": "\u0120 .", "raw_count": 3369995, "count": 3393380, "decode_str": " ."} -{"id": 673, "token": "\u0120time", "merges": "\u0120t ime", "raw_count": 3049000, "count": 3394308, "decode_str": " time"} -{"id": 868, "token": "les", "merges": "l es", "raw_count": 705070, "count": 3396158, "decode_str": "les"} -{"id": 52508, "token": "\u00e6\u00b2\u00a5", "merges": "\u00e6\u00b2 \u00a5", "raw_count": 3397147, "count": 3397147, "decode_str": "\u6ca5"} -{"id": 51495, "token": "\u00e5\u00b1\u00af", "merges": "\u00e5\u00b1 \u00af", "raw_count": 3398448, "count": 3398448, "decode_str": "\u5c6f"} -{"id": 54162, "token": "\u00e9\u0124\u00b1", "merges": "\u00e9\u0124 \u00b1", "raw_count": 3400334, "count": 3400334, "decode_str": "\u90b1"} -{"id": 53378, "token": "\u00e7\u00bc\u0122", "merges": "\u00e7\u00bc \u0122", "raw_count": 3400759, "count": 3400759, "decode_str": "\u7f00"} -{"id": 819, "token": "\u0120pr", "merges": "\u0120p r", "raw_count": 259316, "count": 3401028, "decode_str": " pr"} -{"id": 488, "token": "\u0120whe", "merges": "\u0120w he", "raw_count": 8816, "count": 3402637, "decode_str": " whe"} -{"id": 1556, "token": "AL", "merges": "A L", "raw_count": 1440781, "count": 3405828, "decode_str": "AL"} -{"id": 18601, "token": "VR", "merges": "V R", "raw_count": 3407769, "count": 3407769, "decode_str": "VR"} -{"id": 920, "token": "ning", "merges": "n ing", "raw_count": 319786, "count": 3410356, "decode_str": "ning"} -{"id": 820, "token": "\u0120co", "merges": "\u0120c o", "raw_count": 599338, "count": 3414050, "decode_str": " co"} -{"id": 5858, "token": "pass", "merges": "p ass", "raw_count": 2078454, "count": 3419108, "decode_str": "pass"} -{"id": 443, "token": "\u0120G", "merges": "\u0120 G", "raw_count": 861196, "count": 3422736, "decode_str": " G"} -{"id": 906, "token": "\u0120result", "merges": "\u0120res ult", "raw_count": 2356503, "count": 3422914, "decode_str": " result"} -{"id": 50872, "token": "\u00e5\u012f\u0134", "merges": "\u00e5\u012f \u0134", "raw_count": 3424171, "count": 3424171, "decode_str": "\u5352"} -{"id": 52264, "token": "\u00e6\u0141\u0142", "merges": "\u00e6\u0141 \u0142", "raw_count": 3426185, "count": 3426185, "decode_str": "\u67e0"} -{"id": 893, "token": "ta", "merges": "t a", "raw_count": 1195442, "count": 3434259, "decode_str": "ta"} -{"id": 10016, "token": "2002", "merges": "200 2", "raw_count": 3434930, "count": 3434930, "decode_str": "2002"} -{"id": 53735, "token": "\u00e8\u00a3\u0136", "merges": "\u00e8\u00a3 \u0136", "raw_count": 3435520, "count": 3435520, "decode_str": "\u88d4"} -{"id": 473, "token": "\u0120O", "merges": "\u0120 O", "raw_count": 1008798, "count": 3435691, "decode_str": " O"} -{"id": 968, "token": "ins", "merges": "in s", "raw_count": 1442950, "count": 3435836, "decode_str": "ins"} -{"id": 832, "token": "ef", "merges": "e f", "raw_count": 718433, "count": 3438033, "decode_str": "ef"} -{"id": 3717, "token": "CD", "merges": "C D", "raw_count": 3270764, "count": 3441178, "decode_str": "CD"} -{"id": 1342, "token": "man", "merges": "m an", "raw_count": 1868455, "count": 3447340, "decode_str": "man"} -{"id": 53372, "token": "\u00e7\u00bb\u00b8", "merges": "\u00e7\u00bb \u00b8", "raw_count": 3448154, "count": 3448154, "decode_str": "\u7ef8"} -{"id": 2019, "token": "Cl", "merges": "C l", "raw_count": 900586, "count": 3448685, "decode_str": "Cl"} -{"id": 53380, "token": "\u00e7\u00bc\u0127", "merges": "\u00e7\u00bc \u0127", "raw_count": 3453586, "count": 3453586, "decode_str": "\u7f05"} -{"id": 790, "token": "ons", "merges": "on s", "raw_count": 740280, "count": 3454934, "decode_str": "ons"} -{"id": 6219, "token": "node", "merges": "n ode", "raw_count": 3461183, "count": 3461183, "decode_str": "node"} -{"id": 53532, "token": "\u00e8\u0125\u00ba", "merges": "\u00e8\u0125 \u00ba", "raw_count": 3463386, "count": 3463386, "decode_str": "\u80fa"} -{"id": 2503, "token": "mp", "merges": "m p", "raw_count": 1624089, "count": 3469906, "decode_str": "mp"} -{"id": 712, "token": "irst", "merges": "ir st", "raw_count": 36541, "count": 3473106, "decode_str": "irst"} -{"id": 1401, "token": "\u0120**", "merges": "\u0120 **", "raw_count": 3381645, "count": 3476987, "decode_str": " **"} -{"id": 612, "token": "\u0120ev", "merges": "\u0120e v", "raw_count": 224056, "count": 3478743, "decode_str": " ev"} -{"id": 5218, "token": "]:", "merges": "] :", "raw_count": 3483492, "count": 3483492, "decode_str": "]:"} -{"id": 52730, "token": "\u00e7\u0124\u0138", "merges": "\u00e7\u0124 \u0138", "raw_count": 3491276, "count": 3491276, "decode_str": "\u7096"} -{"id": 6903, "token": "101", "merges": "1 01", "raw_count": 3431356, "count": 3491988, "decode_str": "101"} -{"id": 6920, "token": "GB", "merges": "G B", "raw_count": 2963358, "count": 3492406, "decode_str": "GB"} -{"id": 5470, "token": "db", "merges": "d b", "raw_count": 3439679, "count": 3493349, "decode_str": "db"} -{"id": 15721, "token": "shape", "merges": "sh ape", "raw_count": 3493513, "count": 3493513, "decode_str": "shape"} -{"id": 3030, "token": "ems", "merges": "em s", "raw_count": 717181, "count": 3498010, "decode_str": "ems"} -{"id": 52759, "token": "\u00e7\u012a\u00aa", "merges": "\u00e7\u012a \u00aa", "raw_count": 3498752, "count": 3498752, "decode_str": "\u722a"} -{"id": 53682, "token": "\u00e8\u013b\u0132", "merges": "\u00e8\u013b \u0132", "raw_count": 3505754, "count": 3505754, "decode_str": "\u8650"} -{"id": 490, "token": "\u0120ab", "merges": "\u0120a b", "raw_count": 388308, "count": 3505953, "decode_str": " ab"} -{"id": 52912, "token": "\u00e7\u0138\u00a4", "merges": "\u00e7\u0138 \u00a4", "raw_count": 3506366, "count": 3506366, "decode_str": "\u75a4"} -{"id": 1123, "token": "ave", "merges": "a ve", "raw_count": 303159, "count": 3506825, "decode_str": "ave"} -{"id": 3305, "token": "book", "merges": "b ook", "raw_count": 1007420, "count": 3506904, "decode_str": "book"} -{"id": 53726, "token": "\u00e8\u00a2\u013e", "merges": "\u00e8\u00a2 \u013e", "raw_count": 3510045, "count": 3510045, "decode_str": "\u889c"} -{"id": 2925, "token": "AB", "merges": "A B", "raw_count": 2460647, "count": 3512717, "decode_str": "AB"} -{"id": 52915, "token": "\u00e7\u0138\u00ae", "merges": "\u00e7\u0138 \u00ae", "raw_count": 3514135, "count": 3514135, "decode_str": "\u75ae"} -{"id": 1122, "token": "ript", "merges": "ri pt", "raw_count": 10319, "count": 3519417, "decode_str": "ript"} -{"id": 11246, "token": "130", "merges": "13 0", "raw_count": 3520168, "count": 3520168, "decode_str": "130"} -{"id": 513, "token": "\u0120do", "merges": "\u0120d o", "raw_count": 1843661, "count": 3520687, "decode_str": " do"} -{"id": 52380, "token": "\u00e6\u00a9\u00b1", "merges": "\u00e6\u00a9 \u00b1", "raw_count": 3522313, "count": 3522313, "decode_str": "\u6a71"} -{"id": 51469, "token": "\u00e5\u00b0\u00b9", "merges": "\u00e5\u00b0 \u00b9", "raw_count": 3523969, "count": 3523969, "decode_str": "\u5c39"} -{"id": 52947, "token": "\u00e7\u0139\u00b0", "merges": "\u00e7\u0139 \u00b0", "raw_count": 3524246, "count": 3524246, "decode_str": "\u75f0"} -{"id": 605, "token": "//", "merges": "/ /", "raw_count": 934258, "count": 3526895, "decode_str": "//"} -{"id": 53942, "token": "\u00e8\u00b4\u00bf", "merges": "\u00e8\u00b4 \u00bf", "raw_count": 3529868, "count": 3529868, "decode_str": "\u8d3f"} -{"id": 52751, "token": "\u00e7\u0126\u013c", "merges": "\u00e7\u0126 \u013c", "raw_count": 3534787, "count": 3534787, "decode_str": "\u711a"} -{"id": 1271, "token": "ices", "merges": "ic es", "raw_count": 596710, "count": 3541218, "decode_str": "ices"} -{"id": 53269, "token": "\u00e7\u00b2\u00aa", "merges": "\u00e7\u00b2 \u00aa", "raw_count": 3543811, "count": 3543811, "decode_str": "\u7caa"} -{"id": 53913, "token": "\u00e8\u00b4\u0140", "merges": "\u00e8\u00b4 \u0140", "raw_count": 3554433, "count": 3554433, "decode_str": "\u8d1e"} -{"id": 53862, "token": "\u00e8\u00b0\u0130", "merges": "\u00e8\u00b0 \u0130", "raw_count": 3559235, "count": 3559235, "decode_str": "\u8c0e"} -{"id": 5695, "token": "image", "merges": "im age", "raw_count": 3560937, "count": 3560937, "decode_str": "image"} -{"id": 50855, "token": "\u00e5\u012e\u00aa", "merges": "\u00e5\u012e \u00aa", "raw_count": 3561502, "count": 3561502, "decode_str": "\u532a"} -{"id": 54353, "token": "\u00e9\u013c\u00a7", "merges": "\u00e9\u013c \u00a7", "raw_count": 3569075, "count": 3569075, "decode_str": "\u96a7"} -{"id": 51425, "token": "\u00e5\u00ae\u00b5", "merges": "\u00e5\u00ae \u00b5", "raw_count": 3580774, "count": 3580774, "decode_str": "\u5bb5"} -{"id": 3144, "token": "atus", "merges": "at us", "raw_count": 94336, "count": 3591654, "decode_str": "atus"} -{"id": 1873, "token": "\u0120file", "merges": "\u0120f ile", "raw_count": 3596792, "count": 3596792, "decode_str": " file"} -{"id": 5309, "token": "jo", "merges": "j o", "raw_count": 250406, "count": 3605238, "decode_str": "jo"} -{"id": 50546, "token": "\u00e4\u00bc\u00bd", "merges": "\u00e4\u00bc \u00bd", "raw_count": 3606355, "count": 3606355, "decode_str": "\u4f3d"} -{"id": 697, "token": "\u0120its", "merges": "\u0120it s", "raw_count": 3401408, "count": 3608784, "decode_str": " its"} -{"id": 2738, "token": "ession", "merges": "ess ion", "raw_count": 74048, "count": 3610143, "decode_str": "ession"} -{"id": 51217, "token": "\u00e5\u0140\u0126", "merges": "\u00e5\u0140 \u0126", "raw_count": 3616366, "count": 3616366, "decode_str": "\u5784"} -{"id": 54202, "token": "\u00e9\u0127\u00af", "merges": "\u00e9\u0127 \u00af", "raw_count": 3616392, "count": 3616392, "decode_str": "\u916f"} -{"id": 50830, "token": "\u00e5\u012d\u012d", "merges": "\u00e5\u012d \u012d", "raw_count": 3617073, "count": 3617073, "decode_str": "\u52cb"} -{"id": 52612, "token": "\u00e6\u00b6\u00a1", "merges": "\u00e6\u00b6 \u00a1", "raw_count": 3627272, "count": 3627272, "decode_str": "\u6da1"} -{"id": 2673, "token": "%)", "merges": "% )", "raw_count": 3622976, "count": 3628494, "decode_str": "%)"} -{"id": 51499, "token": "\u00e5\u00b7\u0127", "merges": "\u00e5\u00b7 \u0127", "raw_count": 3631083, "count": 3631083, "decode_str": "\u5dc5"} -{"id": 51285, "token": "\u00e5\u00a3\u00b9", "merges": "\u00e5\u00a3 \u00b9", "raw_count": 3633860, "count": 3633860, "decode_str": "\u58f9"} -{"id": 53926, "token": "\u00e8\u00b4\u00ac", "merges": "\u00e8\u00b4 \u00ac", "raw_count": 3637904, "count": 3637904, "decode_str": "\u8d2c"} -{"id": 1005, "token": "ities", "merges": "it ies", "raw_count": 493332, "count": 3644792, "decode_str": "ities"} -{"id": 4739, "token": "91", "merges": "9 1", "raw_count": 3640946, "count": 3651886, "decode_str": "91"} -{"id": 14966, "token": "instance", "merges": "in stance", "raw_count": 1481273, "count": 3652275, "decode_str": "instance"} -{"id": 51510, "token": "\u00e5\u00b7\u00ab", "merges": "\u00e5\u00b7 \u00ab", "raw_count": 3654250, "count": 3654250, "decode_str": "\u5deb"} -{"id": 643, "token": "\u0120other", "merges": "\u0120o ther", "raw_count": 3115806, "count": 3663926, "decode_str": " other"} -{"id": 52131, "token": "\u00e6\u013a\u012c", "merges": "\u00e6\u013a \u012c", "raw_count": 3666251, "count": 3666251, "decode_str": "\u660a"} -{"id": 6649, "token": "())", "merges": "() )", "raw_count": 3678123, "count": 3678123, "decode_str": "())"} -{"id": 1940, "token": "co", "merges": "c o", "raw_count": 2142580, "count": 3680599, "decode_str": "co"} -{"id": 2178, "token": "opt", "merges": "op t", "raw_count": 690074, "count": 3683857, "decode_str": "opt"} -{"id": 851, "token": "\u0120ret", "merges": "\u0120re t", "raw_count": 602705, "count": 3688037, "decode_str": " ret"} -{"id": 5560, "token": "count", "merges": "c ount", "raw_count": 3470265, "count": 3697091, "decode_str": "count"} -{"id": 810, "token": "\u0120reg", "merges": "\u0120re g", "raw_count": 155425, "count": 3698632, "decode_str": " reg"} -{"id": 16829, "token": "except", "merges": "ex cept", "raw_count": 3700171, "count": 3700171, "decode_str": "except"} -{"id": 756, "token": "\u0120acc", "merges": "\u0120a cc", "raw_count": 207890, "count": 3710413, "decode_str": " acc"} -{"id": 52746, "token": "\u00e7\u0126\u0137", "merges": "\u00e7\u0126 \u0137", "raw_count": 3714971, "count": 3714971, "decode_str": "\u7115"} -{"id": 14626, "token": "try", "merges": "t ry", "raw_count": 3708313, "count": 3715519, "decode_str": "try"} -{"id": 1773, "token": "Con", "merges": "C on", "raw_count": 714362, "count": 3715653, "decode_str": "Con"} -{"id": 50885, "token": "\u00e5\u012f\u00a6", "merges": "\u00e5\u012f \u00a6", "raw_count": 3715696, "count": 3715696, "decode_str": "\u5366"} -{"id": 51989, "token": "\u00e6\u0130\u0131", "merges": "\u00e6\u0130 \u0131", "raw_count": 3718294, "count": 3718294, "decode_str": "\u638f"} -{"id": 572, "token": "\u0120qu", "merges": "\u0120 qu", "raw_count": 133097, "count": 3723859, "decode_str": " qu"} -{"id": 3728, "token": "array", "merges": "ar ray", "raw_count": 3727008, "count": 3727360, "decode_str": "array"} -{"id": 3271, "token": "OL", "merges": "O L", "raw_count": 2630138, "count": 3727955, "decode_str": "OL"} -{"id": 51919, "token": "\u00e6\u012d\u00a7", "merges": "\u00e6\u012d \u00a7", "raw_count": 3735823, "count": 3735823, "decode_str": "\u62e7"} -{"id": 5023, "token": "().", "merges": "( ).", "raw_count": 3738321, "count": 3738321, "decode_str": "()."} -{"id": 51222, "token": "\u00e5\u0140\u00a2", "merges": "\u00e5\u0140 \u00a2", "raw_count": 3741742, "count": 3741742, "decode_str": "\u57a2"} -{"id": 3409, "token": "state", "merges": "st ate", "raw_count": 3736379, "count": 3743613, "decode_str": "state"} -{"id": 3953, "token": "94", "merges": "9 4", "raw_count": 3728158, "count": 3744926, "decode_str": "94"} -{"id": 1400, "token": "EN", "merges": "E N", "raw_count": 1161969, "count": 3745597, "decode_str": "EN"} -{"id": 4590, "token": "93", "merges": "9 3", "raw_count": 3736131, "count": 3747795, "decode_str": "93"} -{"id": 52377, "token": "\u00e6\u00a9\u013a", "merges": "\u00e6\u00a9 \u013a", "raw_count": 3751454, "count": 3751454, "decode_str": "\u6a58"} -{"id": 53021, "token": "\u00e7\u013f\u0132", "merges": "\u00e7\u013f \u0132", "raw_count": 3751695, "count": 3751695, "decode_str": "\u7750"} -{"id": 5653, "token": "False", "merges": "F alse", "raw_count": 3758530, "count": 3758530, "decode_str": "False"} -{"id": 9686, "token": "\"]", "merges": "\" ]", "raw_count": 3759690, "count": 3759690, "decode_str": "\"]"} -{"id": 51330, "token": "\u00e5\u00a6\u0126", "merges": "\u00e5\u00a6 \u0126", "raw_count": 3760594, "count": 3760594, "decode_str": "\u5984"} -{"id": 52922, "token": "\u00e7\u0138\u00b9", "merges": "\u00e7\u0138 \u00b9", "raw_count": 3760981, "count": 3760981, "decode_str": "\u75b9"} -{"id": 6082, "token": "object", "merges": "ob ject", "raw_count": 1965899, "count": 3772108, "decode_str": "object"} -{"id": 52425, "token": "\u00e6\u00ae\u00b7", "merges": "\u00e6\u00ae \u00b7", "raw_count": 3775503, "count": 3775503, "decode_str": "\u6bb7"} -{"id": 598, "token": "\u0120up", "merges": "\u0120 up", "raw_count": 1620827, "count": 3777555, "decode_str": " up"} -{"id": 1771, "token": "ery", "merges": "er y", "raw_count": 205775, "count": 3790092, "decode_str": "ery"} -{"id": 2748, "token": "\u0120request", "merges": "\u0120requ est", "raw_count": 2686864, "count": 3791104, "decode_str": " request"} -{"id": 28455, "token": "\u00e2\u0122\u013f),", "merges": "\u00e2\u0122\u013f ),", "raw_count": 3792644, "count": 3792644, "decode_str": "\u201d),"} -{"id": 9308, "token": "DP", "merges": "D P", "raw_count": 3779739, "count": 3798107, "decode_str": "DP"} -{"id": 50562, "token": "\u00e4\u00bd\u00a3", "merges": "\u00e4\u00bd \u00a3", "raw_count": 3802052, "count": 3802052, "decode_str": "\u4f63"} -{"id": 53046, "token": "\u00e7\u0141\u00ae", "merges": "\u00e7\u0141 \u00ae", "raw_count": 3809469, "count": 3809469, "decode_str": "\u77ee"} -{"id": 1962, "token": "che", "merges": "c he", "raw_count": 356200, "count": 3811302, "decode_str": "che"} -{"id": 52404, "token": "\u00e6\u0143\u00aa", "merges": "\u00e6\u0143 \u00aa", "raw_count": 3818231, "count": 3818231, "decode_str": "\u6b6a"} -{"id": 50967, "token": "\u00e5\u0132\u0141", "merges": "\u00e5\u0132 \u0141", "raw_count": 3823214, "count": 3823214, "decode_str": "\u541f"} -{"id": 823, "token": "\u0120add", "merges": "\u0120ad d", "raw_count": 1442847, "count": 3833989, "decode_str": " add"} -{"id": 51371, "token": "\u00e5\u00a7\u00ac", "merges": "\u00e5\u00a7 \u00ac", "raw_count": 3839992, "count": 3839992, "decode_str": "\u59ec"} -{"id": 52077, "token": "\u00e6\u0137\u0140", "merges": "\u00e6\u0137 \u0140", "raw_count": 3845981, "count": 3845981, "decode_str": "\u655e"} -{"id": 959, "token": "ited", "merges": "it ed", "raw_count": 592814, "count": 3849854, "decode_str": "ited"} -{"id": 2377, "token": "sub", "merges": "s ub", "raw_count": 3104749, "count": 3862812, "decode_str": "sub"} -{"id": 2068, "token": "ext", "merges": "e xt", "raw_count": 776053, "count": 3864850, "decode_str": "ext"} -{"id": 638, "token": "\u0120pre", "merges": "\u0120p re", "raw_count": 621635, "count": 3866233, "decode_str": " pre"} -{"id": 52122, "token": "\u00e6\u0139\u00b1", "merges": "\u00e6\u0139 \u00b1", "raw_count": 3867150, "count": 3867150, "decode_str": "\u65f1"} -{"id": 50985, "token": "\u00e5\u0132\u00bc", "merges": "\u00e5\u0132 \u00bc", "raw_count": 3869678, "count": 3869678, "decode_str": "\u543c"} -{"id": 1993, "token": "play", "merges": "pl ay", "raw_count": 1458735, "count": 3873059, "decode_str": "play"} -{"id": 51443, "token": "\u00e5\u00af\u00a1", "merges": "\u00e5\u00af \u00a1", "raw_count": 3873620, "count": 3873620, "decode_str": "\u5be1"} -{"id": 14744, "token": "700", "merges": "7 00", "raw_count": 3875051, "count": 3875051, "decode_str": "700"} -{"id": 51790, "token": "\u00e6\u0126\u013c", "merges": "\u00e6\u0126 \u013c", "raw_count": 3884324, "count": 3884324, "decode_str": "\u611a"} -{"id": 51972, "token": "\u00e6\u012f\u00a1", "merges": "\u00e6\u012f \u00a1", "raw_count": 3884333, "count": 3884333, "decode_str": "\u6361"} -{"id": 847, "token": "\u0120col", "merges": "\u0120c ol", "raw_count": 759105, "count": 3887030, "decode_str": " col"} -{"id": 9913, "token": "160", "merges": "16 0", "raw_count": 3890425, "count": 3890425, "decode_str": "160"} -{"id": 1225, "token": "ash", "merges": "as h", "raw_count": 1185271, "count": 3891536, "decode_str": "ash"} -{"id": 50765, "token": "\u00e5\u012a\u0125", "merges": "\u00e5\u012a \u0125", "raw_count": 3891828, "count": 3891828, "decode_str": "\u5203"} -{"id": 52824, "token": "\u00e7\u0131\u012c", "merges": "\u00e7\u0131 \u012c", "raw_count": 3904825, "count": 3904825, "decode_str": "\u73ca"} -{"id": 393, "token": "\u0120\\", "merges": "\u0120 \\", "raw_count": 1921843, "count": 3907322, "decode_str": " \\"} -{"id": 50710, "token": "\u00e5\u0128\u012a", "merges": "\u00e5\u0128 \u012a", "raw_count": 3910791, "count": 3910791, "decode_str": "\u5188"} -{"id": 528, "token": "ous", "merges": "ou s", "raw_count": 307129, "count": 3914726, "decode_str": "ous"} -{"id": 51923, "token": "\u00e6\u012d\u0143", "merges": "\u00e6\u012d \u0143", "raw_count": 3916199, "count": 3916199, "decode_str": "\u62ed"} -{"id": 5204, "token": "\u0120->", "merges": "\u0120- >", "raw_count": 3920230, "count": 3920230, "decode_str": " ->"} -{"id": 1719, "token": "AS", "merges": "A S", "raw_count": 2180186, "count": 3922802, "decode_str": "AS"} -{"id": 639, "token": "\u0120ag", "merges": "\u0120a g", "raw_count": 151488, "count": 3923309, "decode_str": " ag"} -{"id": 53666, "token": "\u00e8\u0130\u0135", "merges": "\u00e8\u0130 \u0135", "raw_count": 3931120, "count": 3931120, "decode_str": "\u8393"} -{"id": 52614, "token": "\u00e6\u00b6\u00a4", "merges": "\u00e6\u00b6 \u00a4", "raw_count": 3932648, "count": 3932648, "decode_str": "\u6da4"} -{"id": 1080, "token": "ator", "merges": "at or", "raw_count": 1431413, "count": 3936970, "decode_str": "ator"} -{"id": 650, "token": "\u0120gr", "merges": "\u0120g r", "raw_count": 155091, "count": 3941925, "decode_str": " gr"} -{"id": 9252, "token": "output", "merges": "out put", "raw_count": 3410849, "count": 3949518, "decode_str": "output"} -{"id": 52284, "token": "\u00e6\u0142\u0135", "merges": "\u00e6\u0142 \u0135", "raw_count": 3950016, "count": 3950016, "decode_str": "\u6813"} -{"id": 53905, "token": "\u00e8\u00b1\u00b9", "merges": "\u00e8\u00b1 \u00b9", "raw_count": 3952378, "count": 3952378, "decode_str": "\u8c79"} -{"id": 564, "token": "\u0120go", "merges": "\u0120g o", "raw_count": 591149, "count": 3955549, "decode_str": " go"} -{"id": 51043, "token": "\u00e5\u0134\u00af", "merges": "\u00e5\u0134 \u00af", "raw_count": 3968478, "count": 3968478, "decode_str": "\u54af"} -{"id": 988, "token": "\u010a\u0109\u0109", "merges": "\u010a \u0109\u0109", "raw_count": 2514850, "count": 3974786, "decode_str": "\n\t\t"} -{"id": 52853, "token": "\u00e7\u0132\u00aa", "merges": "\u00e7\u0132 \u00aa", "raw_count": 3978437, "count": 3978437, "decode_str": "\u742a"} -{"id": 53341, "token": "\u00e7\u00bb\u0130", "merges": "\u00e7\u00bb \u0130", "raw_count": 3990660, "count": 3990660, "decode_str": "\u7ece"} -{"id": 622, "token": "\u0120app", "merges": "\u0120a pp", "raw_count": 730887, "count": 4000251, "decode_str": " app"} -{"id": 54206, "token": "\u00e9\u0127\u00b6", "merges": "\u00e9\u0127 \u00b6", "raw_count": 4002024, "count": 4002024, "decode_str": "\u9176"} -{"id": 54108, "token": "\u00e9\u0122\u0139", "merges": "\u00e9\u0122 \u0139", "raw_count": 4007352, "count": 4007352, "decode_str": "\u9017"} -{"id": 378, "token": "\u0120B", "merges": "\u0120 B", "raw_count": 1515816, "count": 4008150, "decode_str": " B"} -{"id": 35764, "token": "!(", "merges": "! (", "raw_count": 4009045, "count": 4009045, "decode_str": "!("} -{"id": 52304, "token": "\u00e6\u00a1\u0132", "merges": "\u00e6\u00a1 \u0132", "raw_count": 4011317, "count": 4011317, "decode_str": "\u6850"} -{"id": 3211, "token": "code", "merges": "c ode", "raw_count": 3260828, "count": 4015876, "decode_str": "code"} -{"id": 52460, "token": "\u00e6\u00b0\u00af", "merges": "\u00e6\u00b0 \u00af", "raw_count": 4017707, "count": 4017707, "decode_str": "\u6c2f"} -{"id": 19791, "token": "1978", "merges": "19 78", "raw_count": 4026535, "count": 4026535, "decode_str": "1978"} -{"id": 1672, "token": "Ex", "merges": "E x", "raw_count": 839330, "count": 4028930, "decode_str": "Ex"} -{"id": 476, "token": "\u0120can", "merges": "\u0120c an", "raw_count": 3275330, "count": 4032035, "decode_str": " can"} -{"id": 51024, "token": "\u00e5\u0134\u0134", "merges": "\u00e5\u0134 \u0134", "raw_count": 4034948, "count": 4034948, "decode_str": "\u5492"} -{"id": 32215, "token": "?,", "merges": "? ,", "raw_count": 4042101, "count": 4042101, "decode_str": "?,"} -{"id": 3016, "token": "US", "merges": "U S", "raw_count": 1897237, "count": 4048670, "decode_str": "US"} -{"id": 4064, "token": "from", "merges": "f rom", "raw_count": 4045764, "count": 4049338, "decode_str": "from"} -{"id": 53887, "token": "\u00e8\u00b0\u0143", "merges": "\u00e8\u00b0 \u0143", "raw_count": 4050163, "count": 4050163, "decode_str": "\u8c2d"} -{"id": 53641, "token": "\u00e8\u012d\u0133", "merges": "\u00e8\u012d \u0133", "raw_count": 4052042, "count": 4052042, "decode_str": "\u82d1"} -{"id": 52443, "token": "\u00e6\u00af\u00af", "merges": "\u00e6\u00af \u00af", "raw_count": 4061608, "count": 4061608, "decode_str": "\u6bef"} -{"id": 2894, "token": "IM", "merges": "I M", "raw_count": 2715056, "count": 4066519, "decode_str": "IM"} -{"id": 22525, "token": "raise", "merges": "ra ise", "raw_count": 4071408, "count": 4071586, "decode_str": "raise"} -{"id": 50723, "token": "\u00e5\u0128\u00a5", "merges": "\u00e5\u0128 \u00a5", "raw_count": 4073687, "count": 4073687, "decode_str": "\u51a5"} -{"id": 588, "token": "\u0120will", "merges": "\u0120w ill", "raw_count": 4012751, "count": 4075757, "decode_str": " will"} -{"id": 557, "token": "\u0120dis", "merges": "\u0120d is", "raw_count": 380313, "count": 4076371, "decode_str": " dis"} -{"id": 52325, "token": "\u00e6\u00a3\u0137", "merges": "\u00e6\u00a3 \u0137", "raw_count": 4083284, "count": 4083284, "decode_str": "\u68d5"} -{"id": 53016, "token": "\u00e7\u013e\u00b8", "merges": "\u00e7\u013e \u00b8", "raw_count": 4086827, "count": 4086827, "decode_str": "\u7738"} -{"id": 54521, "token": "\u00e9\u00ab\u0135", "merges": "\u00e9\u00ab \u0135", "raw_count": 4088929, "count": 4088929, "decode_str": "\u9ad3"} -{"id": 5478, "token": "start", "merges": "st art", "raw_count": 3921246, "count": 4095168, "decode_str": "start"} -{"id": 51902, "token": "\u00e6\u012d\u0132", "merges": "\u00e6\u012d \u0132", "raw_count": 4102048, "count": 4102048, "decode_str": "\u62d0"} -{"id": 51599, "token": "\u00e5\u00bc\u0135", "merges": "\u00e5\u00bc \u0135", "raw_count": 4106141, "count": 4106141, "decode_str": "\u5f13"} -{"id": 52896, "token": "\u00e7\u0137\u00b4", "merges": "\u00e7\u0137 \u00b4", "raw_count": 4117240, "count": 4117240, "decode_str": "\u7574"} -{"id": 1443, "token": "ames", "merges": "am es", "raw_count": 477162, "count": 4119276, "decode_str": "ames"} -{"id": 50731, "token": "\u00e5\u0128\u00b6", "merges": "\u00e5\u0128 \u00b6", "raw_count": 4127640, "count": 4127640, "decode_str": "\u51b6"} -{"id": 1505, "token": "ource", "merges": "our ce", "raw_count": 106402, "count": 4130431, "decode_str": "ource"} -{"id": 52881, "token": "\u00e7\u0136\u00b8", "merges": "\u00e7\u0136 \u00b8", "raw_count": 4131811, "count": 4131811, "decode_str": "\u7538"} -{"id": 1692, "token": "ype", "merges": "y pe", "raw_count": 863722, "count": 4132484, "decode_str": "ype"} -{"id": 52210, "token": "\u00e6\u013f\u012b", "merges": "\u00e6\u013f \u012b", "raw_count": 4133287, "count": 4133287, "decode_str": "\u6749"} -{"id": 1063, "token": "ger", "merges": "g er", "raw_count": 472495, "count": 4136483, "decode_str": "ger"} -{"id": 50759, "token": "\u00e5\u0129\u00b9", "merges": "\u00e5\u0129 \u00b9", "raw_count": 4139260, "count": 4139260, "decode_str": "\u51f9"} -{"id": 1492, "token": "abel", "merges": "ab el", "raw_count": 294710, "count": 4141021, "decode_str": "abel"} -{"id": 52332, "token": "\u00e6\u00a3\u00b5", "merges": "\u00e6\u00a3 \u00b5", "raw_count": 4142840, "count": 4142840, "decode_str": "\u68f5"} -{"id": 1615, "token": "by", "merges": "b y", "raw_count": 2852176, "count": 4151203, "decode_str": "by"} -{"id": 53111, "token": "\u00e7\u00a5\u012a", "merges": "\u00e7\u00a5 \u012a", "raw_count": 4152480, "count": 4152480, "decode_str": "\u7948"} -{"id": 859, "token": "ss", "merges": "s s", "raw_count": 1193300, "count": 4153821, "decode_str": "ss"} -{"id": 52733, "token": "\u00e7\u0124\u00ab", "merges": "\u00e7\u0124 \u00ab", "raw_count": 4156888, "count": 4156888, "decode_str": "\u70ab"} -{"id": 660, "token": "\u0120sc", "merges": "\u0120s c", "raw_count": 396576, "count": 4159979, "decode_str": " sc"} -{"id": 51055, "token": "\u00e5\u0135\u0129", "merges": "\u00e5\u0135 \u0129", "raw_count": 4160844, "count": 4160844, "decode_str": "\u54c7"} -{"id": 51608, "token": "\u00e5\u00bc\u00a7", "merges": "\u00e5\u00bc \u00a7", "raw_count": 4170202, "count": 4170202, "decode_str": "\u5f27"} -{"id": 613, "token": "ear", "merges": "e ar", "raw_count": 401821, "count": 4170970, "decode_str": "ear"} -{"id": 750, "token": "ink", "merges": "in k", "raw_count": 601174, "count": 4172635, "decode_str": "ink"} -{"id": 54004, "token": "\u00e8\u00b7\u00aa", "merges": "\u00e8\u00b7 \u00aa", "raw_count": 4175249, "count": 4175249, "decode_str": "\u8dea"} -{"id": 1372, "token": "OR", "merges": "O R", "raw_count": 1301504, "count": 4179471, "decode_str": "OR"} -{"id": 53387, "token": "\u00e7\u00bc\u0136", "merges": "\u00e7\u00bc \u0136", "raw_count": 4179604, "count": 4179604, "decode_str": "\u7f14"} -{"id": 44779, "token": "elif", "merges": "el if", "raw_count": 4179757, "count": 4179757, "decode_str": "elif"} -{"id": 52045, "token": "\u00e6\u0134\u00bc", "merges": "\u00e6\u0134 \u00bc", "raw_count": 4182279, "count": 4182279, "decode_str": "\u64bc"} -{"id": 4792, "token": "stance", "merges": "st ance", "raw_count": 67561, "count": 4183612, "decode_str": "stance"} -{"id": 9629, "token": "request", "merges": "requ est", "raw_count": 4185094, "count": 4185094, "decode_str": "request"} -{"id": 51218, "token": "\u00e5\u0140\u0134", "merges": "\u00e5\u0140 \u0134", "raw_count": 4186031, "count": 4186031, "decode_str": "\u5792"} -{"id": 4529, "token": "92", "merges": "9 2", "raw_count": 4174895, "count": 4186924, "decode_str": "92"} -{"id": 747, "token": "\u0120new", "merges": "\u0120ne w", "raw_count": 3880036, "count": 4196023, "decode_str": " new"} -{"id": 1064, "token": "ork", "merges": "or k", "raw_count": 239610, "count": 4197622, "decode_str": "ork"} -{"id": 53044, "token": "\u00e7\u0141\u00ab", "merges": "\u00e7\u0141 \u00ab", "raw_count": 4199821, "count": 4199821, "decode_str": "\u77eb"} -{"id": 53477, "token": "\u00e8\u0124\u0128", "merges": "\u00e8\u0124 \u0128", "raw_count": 4202728, "count": 4202728, "decode_str": "\u8086"} -{"id": 6971, "token": "SU", "merges": "S U", "raw_count": 4062739, "count": 4209013, "decode_str": "SU"} -{"id": 54354, "token": "\u00e9\u013c\u00b6", "merges": "\u00e9\u013c \u00b6", "raw_count": 4214976, "count": 4214976, "decode_str": "\u96b6"} -{"id": 54629, "token": "\u00e3\u0122\u0141", "merges": "\u00e3\u0122 \u0141", "raw_count": 4218615, "count": 4218615, "decode_str": " "} -{"id": 2437, "token": "class", "merges": "cl ass", "raw_count": 3340686, "count": 4220128, "decode_str": "class"} -{"id": 52618, "token": "\u00e6\u00b6\u00a9", "merges": "\u00e6\u00b6 \u00a9", "raw_count": 4221893, "count": 4221893, "decode_str": "\u6da9"} -{"id": 40853, "token": "1949", "merges": "19 49", "raw_count": 4223427, "count": 4223427, "decode_str": "1949"} -{"id": 1061, "token": "\u0120par", "merges": "\u0120p ar", "raw_count": 243232, "count": 4225314, "decode_str": " par"} -{"id": 418, "token": "\u0120L", "merges": "\u0120 L", "raw_count": 1062203, "count": 4231188, "decode_str": " L"} -{"id": 51624, "token": "\u00e5\u00bd\u00a6", "merges": "\u00e5\u00bd \u00a6", "raw_count": 4232409, "count": 4232409, "decode_str": "\u5f66"} -{"id": 52862, "token": "\u00e7\u0132\u00bc", "merges": "\u00e7\u0132 \u00bc", "raw_count": 4233379, "count": 4233379, "decode_str": "\u743c"} -{"id": 51951, "token": "\u00e6\u012e\u00a8", "merges": "\u00e6\u012e \u00a8", "raw_count": 4239421, "count": 4239421, "decode_str": "\u6328"} -{"id": 1730, "token": "oss", "merges": "os s", "raw_count": 1544625, "count": 4242259, "decode_str": "oss"} -{"id": 52788, "token": "\u00e7\u012b\u00ba", "merges": "\u00e7\u012b \u00ba", "raw_count": 4244972, "count": 4244972, "decode_str": "\u727a"} -{"id": 1816, "token": "arget", "merges": "ar get", "raw_count": 49118, "count": 4244991, "decode_str": "arget"} -{"id": 54615, "token": "\u00ef\u00bc\u00bb", "merges": "\u00ef\u00bc \u00bb", "raw_count": 4249516, "count": 4249516, "decode_str": " "} -{"id": 51492, "token": "\u00e5\u00b1\u0142", "merges": "\u00e5\u00b1 \u0142", "raw_count": 4249910, "count": 4249910, "decode_str": "\u5c60"} -{"id": 52510, "token": "\u00e6\u00b2\u00a7", "merges": "\u00e6\u00b2 \u00a7", "raw_count": 4250835, "count": 4250835, "decode_str": "\u6ca7"} -{"id": 54431, "token": "\u00e9\u00a1\u00bd", "merges": "\u00e9\u00a1 \u00bd", "raw_count": 4251404, "count": 4251404, "decode_str": "\u987d"} -{"id": 452, "token": "\u0120have", "merges": "\u0120ha ve", "raw_count": 4254813, "count": 4254813, "decode_str": " have"} -{"id": 52569, "token": "\u00e6\u00b4\u00bd", "merges": "\u00e6\u00b4 \u00bd", "raw_count": 4260232, "count": 4260232, "decode_str": "\u6d3d"} -{"id": 5, "token": "$", "merges": "NULL", "raw_count": 2689546, "count": 4264213, "decode_str": "$"} -{"id": 3467, "token": "su", "merges": "s u", "raw_count": 1195012, "count": 4266364, "decode_str": "su"} -{"id": 53191, "token": "\u00e7\u00ab\u0138", "merges": "\u00e7\u00ab \u0138", "raw_count": 4267686, "count": 4267686, "decode_str": "\u7ad6"} -{"id": 9519, "token": "250", "merges": "25 0", "raw_count": 4274406, "count": 4274406, "decode_str": "250"} -{"id": 54503, "token": "\u00e9\u00aa\u013c", "merges": "\u00e9\u00aa \u013c", "raw_count": 4279070, "count": 4279070, "decode_str": "\u9a9a"} -{"id": 716, "token": "\u0120te", "merges": "\u0120t e", "raw_count": 160478, "count": 4284316, "decode_str": " te"} -{"id": 1137, "token": "ute", "merges": "ut e", "raw_count": 291214, "count": 4284389, "decode_str": "ute"} -{"id": 1923, "token": "ault", "merges": "a ult", "raw_count": 200049, "count": 4286056, "decode_str": "ault"} -{"id": 24856, "token": ".__", "merges": ". __", "raw_count": 4287031, "count": 4287031, "decode_str": ".__"} -{"id": 51195, "token": "\u00e5\u013f\u0130", "merges": "\u00e5\u013f \u0130", "raw_count": 4288513, "count": 4288513, "decode_str": "\u574e"} -{"id": 5025, "token": "len", "merges": "l en", "raw_count": 4288948, "count": 4292272, "decode_str": "len"} -{"id": 9430, "token": "2004", "merges": "200 4", "raw_count": 4292829, "count": 4292829, "decode_str": "2004"} -{"id": 53981, "token": "\u00e8\u00b6\u0141", "merges": "\u00e8\u00b6 \u0141", "raw_count": 4294524, "count": 4294524, "decode_str": "\u8d9f"} -{"id": 2350, "token": "AD", "merges": "A D", "raw_count": 1818632, "count": 4300769, "decode_str": "AD"} -{"id": 2300, "token": "AM", "merges": "A M", "raw_count": 2373056, "count": 4302896, "decode_str": "AM"} -{"id": 50707, "token": "\u00e5\u0128\u0122", "merges": "\u00e5\u0128 \u0122", "raw_count": 4305070, "count": 4305070, "decode_str": "\u5180"} -{"id": 50424, "token": "\u00e4\u00b8\u00ab", "merges": "\u00e4\u00b8 \u00ab", "raw_count": 4306400, "count": 4306400, "decode_str": "\u4e2b"} -{"id": 53805, "token": "\u00e8\u00af\u0122", "merges": "\u00e8\u00af \u0122", "raw_count": 4306648, "count": 4306648, "decode_str": "\u8bc0"} -{"id": 53143, "token": "\u00e7\u00a6\u00bd", "merges": "\u00e7\u00a6 \u00bd", "raw_count": 4309582, "count": 4309582, "decode_str": "\u79bd"} -{"id": 51983, "token": "\u00e6\u0130\u0122", "merges": "\u00e6\u0130 \u0122", "raw_count": 4311750, "count": 4311750, "decode_str": "\u6380"} -{"id": 53036, "token": "\u00e7\u013f\u00bf", "merges": "\u00e7\u013f \u00bf", "raw_count": 4317145, "count": 4317145, "decode_str": "\u777f"} -{"id": 51303, "token": "\u00e5\u00a4\u00b7", "merges": "\u00e5\u00a4 \u00b7", "raw_count": 4318025, "count": 4318025, "decode_str": "\u5937"} -{"id": 54282, "token": "\u00e9\u0139\u00b8", "merges": "\u00e9\u0139 \u00b8", "raw_count": 4323671, "count": 4323671, "decode_str": "\u95f8"} -{"id": 744, "token": "old", "merges": "ol d", "raw_count": 1033527, "count": 4324213, "decode_str": "old"} -{"id": 25851, "token": "4000", "merges": "4 000", "raw_count": 4324818, "count": 4324818, "decode_str": "4000"} -{"id": 1058, "token": "\u0120ke", "merges": "\u0120 ke", "raw_count": 95849, "count": 4336510, "decode_str": " ke"} -{"id": 1539, "token": "AN", "merges": "A N", "raw_count": 2048214, "count": 4345726, "decode_str": "AN"} -{"id": 834, "token": "ont", "merges": "on t", "raw_count": 333516, "count": 4348952, "decode_str": "ont"} -{"id": 1852, "token": "\u0120#", "merges": "\u0120 #", "raw_count": 4334346, "count": 4350325, "decode_str": " #"} -{"id": 1384, "token": "\u012020", "merges": "\u01202 0", "raw_count": 3318550, "count": 4357599, "decode_str": " 20"} -{"id": 51831, "token": "\u00e6\u012b\u0123", "merges": "\u00e6\u012b \u0123", "raw_count": 4361114, "count": 4361114, "decode_str": "\u6241"} -{"id": 40887, "token": "iPhone", "merges": "i Phone", "raw_count": 4370357, "count": 4370357, "decode_str": "iPhone"} -{"id": 2174, "token": "indow", "merges": "ind ow", "raw_count": 3018, "count": 4370615, "decode_str": "indow"} -{"id": 1205, "token": "eng", "merges": "en g", "raw_count": 787545, "count": 4372083, "decode_str": "eng"} -{"id": 707, "token": "ces", "merges": "c es", "raw_count": 159746, "count": 4373228, "decode_str": "ces"} -{"id": 20168, "token": "kw", "merges": "k w", "raw_count": 1091705, "count": 4392860, "decode_str": "kw"} -{"id": 2195, "token": "\u0120!", "merges": "\u0120 !", "raw_count": 1554792, "count": 4396059, "decode_str": " !"} -{"id": 732, "token": "lect", "merges": "le ct", "raw_count": 80539, "count": 4405057, "decode_str": "lect"} -{"id": 1318, "token": "\u0120value", "merges": "\u0120val ue", "raw_count": 4414579, "count": 4414579, "decode_str": " value"} -{"id": 4148, "token": "97", "merges": "9 7", "raw_count": 4412721, "count": 4428582, "decode_str": "97"} -{"id": 900, "token": "io", "merges": "i o", "raw_count": 1861430, "count": 4437276, "decode_str": "io"} -{"id": 1322, "token": "NA", "merges": "N A", "raw_count": 1836573, "count": 4440205, "decode_str": "NA"} -{"id": 5374, "token": "info", "merges": "inf o", "raw_count": 4453200, "count": 4453200, "decode_str": "info"} -{"id": 52686, "token": "\u00e6\u00ba\u00af", "merges": "\u00e6\u00ba \u00af", "raw_count": 4455052, "count": 4455052, "decode_str": "\u6eaf"} -{"id": 53878, "token": "\u00e8\u00b0\u00a3", "merges": "\u00e8\u00b0 \u00a3", "raw_count": 4463856, "count": 4463856, "decode_str": "\u8c23"} -{"id": 1062, "token": "ool", "merges": "o ol", "raw_count": 197335, "count": 4474423, "decode_str": "ool"} -{"id": 5423, "token": "input", "merges": "in put", "raw_count": 3622808, "count": 4478222, "decode_str": "input"} -{"id": 2076, "token": "resp", "merges": "res p", "raw_count": 657457, "count": 4491970, "decode_str": "resp"} -{"id": 52767, "token": "\u00e7\u012a\u00b9", "merges": "\u00e7\u012a \u00b9", "raw_count": 4494322, "count": 4494322, "decode_str": "\u7239"} -{"id": 1845, "token": "Pro", "merges": "P ro", "raw_count": 2020277, "count": 4494622, "decode_str": "Pro"} -{"id": 654, "token": "\u0120<", "merges": "\u0120 <", "raw_count": 3134628, "count": 4496590, "decode_str": " <"} -{"id": 51079, "token": "\u00e5\u0135\u00bc", "merges": "\u00e5\u0135 \u00bc", "raw_count": 4505104, "count": 4505104, "decode_str": "\u54fc"} -{"id": 34046, "token": "assertEqual", "merges": "assert Equal", "raw_count": 4506049, "count": 4506049, "decode_str": "assertEqual"} -{"id": 54540, "token": "\u00e4\u00b9\u00be", "merges": "\u00e4\u00b9 \u00be", "raw_count": 4507072, "count": 4507072, "decode_str": "\u4e7e"} -{"id": 50834, "token": "\u00e5\u012d\u013a", "merges": "\u00e5\u012d \u013a", "raw_count": 4507658, "count": 4507658, "decode_str": "\u52d8"} -{"id": 53124, "token": "\u00e7\u00a5\u0142", "merges": "\u00e7\u00a5 \u0142", "raw_count": 4507869, "count": 4507869, "decode_str": "\u7960"} -{"id": 1405, "token": "me", "merges": "m e", "raw_count": 1490666, "count": 4518815, "decode_str": "me"} -{"id": 5840, "token": "kg", "merges": "k g", "raw_count": 4203415, "count": 4530934, "decode_str": "kg"} -{"id": 54171, "token": "\u00e9\u0125\u012c", "merges": "\u00e9\u0125 \u012c", "raw_count": 4541542, "count": 4541542, "decode_str": "\u90ca"} -{"id": 52135, "token": "\u00e6\u013a\u0136", "merges": "\u00e6\u013a \u0136", "raw_count": 4560640, "count": 4560640, "decode_str": "\u6614"} -{"id": 52871, "token": "\u00e7\u0136\u00a9", "merges": "\u00e7\u0136 \u00a9", "raw_count": 4560760, "count": 4560760, "decode_str": "\u7529"} -{"id": 52012, "token": "\u00e6\u0131\u012b", "merges": "\u00e6\u0131 \u012b", "raw_count": 4562128, "count": 4562128, "decode_str": "\u63c9"} -{"id": 695, "token": "ric", "merges": "r ic", "raw_count": 305337, "count": 4567128, "decode_str": "ric"} -{"id": 53797, "token": "\u00e8\u00ae\u00b6", "merges": "\u00e8\u00ae \u00b6", "raw_count": 4568135, "count": 4568135, "decode_str": "\u8bb6"} -{"id": 53086, "token": "\u00e7\u00a2\u012e", "merges": "\u00e7\u00a2 \u012e", "raw_count": 4568955, "count": 4568955, "decode_str": "\u788c"} -{"id": 628, "token": "own", "merges": "ow n", "raw_count": 307942, "count": 4579418, "decode_str": "own"} -{"id": 678, "token": "eth", "merges": "et h", "raw_count": 452677, "count": 4594537, "decode_str": "eth"} -{"id": 607, "token": "ach", "merges": "ac h", "raw_count": 866689, "count": 4598446, "decode_str": "ach"} -{"id": 8168, "token": "\u0120[]", "merges": "\u0120[ ]", "raw_count": 4598841, "count": 4598841, "decode_str": " []"} -{"id": 4090, "token": "max", "merges": "ma x", "raw_count": 4472929, "count": 4599282, "decode_str": "max"} -{"id": 1559, "token": "bl", "merges": "b l", "raw_count": 1070019, "count": 4605115, "decode_str": "bl"} -{"id": 53447, "token": "\u00e8\u0122\u012f", "merges": "\u00e8\u0122 \u012f", "raw_count": 4605826, "count": 4605826, "decode_str": "\u800d"} -{"id": 5077, "token": "PC", "merges": "P C", "raw_count": 4303680, "count": 4607393, "decode_str": "PC"} -{"id": 54403, "token": "\u00e9\u013f\u0138", "merges": "\u00e9\u013f \u0138", "raw_count": 4611629, "count": 4611629, "decode_str": "\u9756"} -{"id": 9755, "token": "2003", "merges": "200 3", "raw_count": 4611635, "count": 4611635, "decode_str": "2003"} -{"id": 50909, "token": "\u00e5\u0130\u00a2", "merges": "\u00e5\u0130 \u00a2", "raw_count": 4612610, "count": 4612610, "decode_str": "\u53a2"} -{"id": 1136, "token": "ann", "merges": "an n", "raw_count": 482888, "count": 4618272, "decode_str": "ann"} -{"id": 33856, "token": "1500", "merges": "15 00", "raw_count": 4620270, "count": 4620270, "decode_str": "1500"} -{"id": 53589, "token": "\u00e8\u012a\u00b1", "merges": "\u00e8\u012a \u00b1", "raw_count": 4623006, "count": 4623006, "decode_str": "\u8231"} -{"id": 51422, "token": "\u00e5\u00ae\u00b0", "merges": "\u00e5\u00ae \u00b0", "raw_count": 4627176, "count": 4627176, "decode_str": "\u5bb0"} -{"id": 2239, "token": "\u0120>", "merges": "\u0120 >", "raw_count": 3307434, "count": 4629488, "decode_str": " >"} -{"id": 1416, "token": "\u0120name", "merges": "\u0120n ame", "raw_count": 4629911, "count": 4629911, "decode_str": " name"} -{"id": 50839, "token": "\u00e5\u012d\u00ba", "merges": "\u00e5\u012d \u00ba", "raw_count": 4632444, "count": 4632444, "decode_str": "\u52fa"} -{"id": 52212, "token": "\u00e6\u013f\u0131", "merges": "\u00e6\u013f \u0131", "raw_count": 4639153, "count": 4639153, "decode_str": "\u674f"} -{"id": 566, "token": "ence", "merges": "en ce", "raw_count": 389869, "count": 4639624, "decode_str": "ence"} -{"id": 1282, "token": "line", "merges": "l ine", "raw_count": 3520390, "count": 4640244, "decode_str": "line"} -{"id": 18279, "token": "ifi", "merges": "if i", "raw_count": 4499875, "count": 4640267, "decode_str": "ifi"} -{"id": 5073, "token": "fil", "merges": "f il", "raw_count": 325157, "count": 4641299, "decode_str": "fil"} -{"id": 10504, "token": "Phone", "merges": "Ph one", "raw_count": 232149, "count": 4650141, "decode_str": "Phone"} -{"id": 479, "token": "\u0120me", "merges": "\u0120m e", "raw_count": 1066889, "count": 4653167, "decode_str": " me"} -{"id": 50871, "token": "\u00e5\u012f\u0133", "merges": "\u00e5\u012f \u0133", "raw_count": 4653620, "count": 4653620, "decode_str": "\u5351"} -{"id": 51967, "token": "\u00e6\u012f\u0131", "merges": "\u00e6\u012f \u0131", "raw_count": 4658732, "count": 4658732, "decode_str": "\u634f"} -{"id": 53543, "token": "\u00e8\u0126\u0138", "merges": "\u00e8\u0126 \u0138", "raw_count": 4668261, "count": 4668261, "decode_str": "\u8116"} -{"id": 25075, "token": ",(", "merges": ", (", "raw_count": 4668773, "count": 4668773, "decode_str": ",("} -{"id": 6870, "token": "result", "merges": "res ult", "raw_count": 4679624, "count": 4679624, "decode_str": "result"} -{"id": 51202, "token": "\u00e5\u013f\u013f", "merges": "\u00e5\u013f \u013f", "raw_count": 4681085, "count": 4681085, "decode_str": "\u575d"} -{"id": 808, "token": "pect", "merges": "pe ct", "raw_count": 188401, "count": 4684246, "decode_str": "pect"} -{"id": 556, "token": "\u0120has", "merges": "\u0120h as", "raw_count": 4298686, "count": 4688049, "decode_str": " has"} -{"id": 53431, "token": "\u00e7\u00be\u00a1", "merges": "\u00e7\u00be \u00a1", "raw_count": 4690181, "count": 4690181, "decode_str": "\u7fa1"} -{"id": 53843, "token": "\u00e8\u00af\u00b5", "merges": "\u00e8\u00af \u00b5", "raw_count": 4692363, "count": 4692363, "decode_str": "\u8bf5"} -{"id": 52378, "token": "\u00e6\u00a9\u013b", "merges": "\u00e6\u00a9 \u013b", "raw_count": 4693785, "count": 4693785, "decode_str": "\u6a59"} -{"id": 52547, "token": "\u00e6\u00b3\u00bb", "merges": "\u00e6\u00b3 \u00bb", "raw_count": 4697219, "count": 4697219, "decode_str": "\u6cfb"} -{"id": 8124, "token": "format", "merges": "form at", "raw_count": 4693495, "count": 4699229, "decode_str": "format"} -{"id": 7645, "token": "model", "merges": "mod el", "raw_count": 4710122, "count": 4710122, "decode_str": "model"} -{"id": 53676, "token": "\u00e8\u0130\u00b9", "merges": "\u00e8\u0130 \u00b9", "raw_count": 4712902, "count": 4712902, "decode_str": "\u83b9"} -{"id": 16236, "token": "\u00e2\u0122\u013b,", "merges": "\u00e2\u0122\u013b ,", "raw_count": 4718296, "count": 4718296, "decode_str": "\u2019,"} -{"id": 52949, "token": "\u00e7\u0139\u00b4", "merges": "\u00e7\u0139 \u00b4", "raw_count": 4730764, "count": 4730764, "decode_str": "\u75f4"} -{"id": 52356, "token": "\u00e6\u00a7\u013d", "merges": "\u00e6\u00a7 \u013d", "raw_count": 4733089, "count": 4733089, "decode_str": "\u69db"} -{"id": 781, "token": "ick", "merges": "ic k", "raw_count": 363977, "count": 4733794, "decode_str": "ick"} -{"id": 54236, "token": "\u00e9\u0136\u00a4", "merges": "\u00e9\u0136 \u00a4", "raw_count": 4734432, "count": 4734432, "decode_str": "\u9524"} -{"id": 2795, "token": "OP", "merges": "O P", "raw_count": 2956335, "count": 4735552, "decode_str": "OP"} -{"id": 4196, "token": "96", "merges": "9 6", "raw_count": 4731042, "count": 4748070, "decode_str": "96"} -{"id": 725, "token": "rib", "merges": "ri b", "raw_count": 289634, "count": 4757142, "decode_str": "rib"} -{"id": 601, "token": "so", "merges": "s o", "raw_count": 1066560, "count": 4758889, "decode_str": "so"} -{"id": 16708, "token": "\u0120False", "merges": "\u0120F alse", "raw_count": 4762263, "count": 4762263, "decode_str": " False"} -{"id": 4785, "token": "PP", "merges": "P P", "raw_count": 4671414, "count": 4765006, "decode_str": "PP"} -{"id": 1241, "token": "els", "merges": "el s", "raw_count": 579436, "count": 4767572, "decode_str": "els"} -{"id": 734, "token": "\u0120inter", "merges": "\u0120in ter", "raw_count": 549995, "count": 4770366, "decode_str": " inter"} -{"id": 1647, "token": "CT", "merges": "C T", "raw_count": 2346650, "count": 4779971, "decode_str": "CT"} -{"id": 1317, "token": "ams", "merges": "am s", "raw_count": 504468, "count": 4783392, "decode_str": "ams"} -{"id": 509, "token": "\u0120comp", "merges": "\u0120com p", "raw_count": 153279, "count": 4783444, "decode_str": " comp"} -{"id": 782, "token": "ark", "merges": "ar k", "raw_count": 550508, "count": 4788823, "decode_str": "ark"} -{"id": 474, "token": "ical", "merges": "ic al", "raw_count": 500822, "count": 4793122, "decode_str": "ical"} -{"id": 53745, "token": "\u00e8\u00a3\u00b8", "merges": "\u00e8\u00a3 \u00b8", "raw_count": 4793977, "count": 4793977, "decode_str": "\u88f8"} -{"id": 2152, "token": "ser", "merges": "s er", "raw_count": 298198, "count": 4794209, "decode_str": "ser"} -{"id": 7341, "token": "dir", "merges": "d ir", "raw_count": 4296720, "count": 4795547, "decode_str": "dir"} -{"id": 51791, "token": "\u00e6\u0126\u00a3", "merges": "\u00e6\u0126 \u00a3", "raw_count": 4798240, "count": 4798240, "decode_str": "\u6123"} -{"id": 7079, "token": "\u0120+=", "merges": "\u0120+ =", "raw_count": 4799489, "count": 4799489, "decode_str": " +="} -{"id": 757, "token": "ian", "merges": "i an", "raw_count": 2009433, "count": 4803308, "decode_str": "ian"} -{"id": 54219, "token": "\u00e9\u0136\u0124", "merges": "\u00e9\u0136 \u0124", "raw_count": 4806414, "count": 4806414, "decode_str": "\u9502"} -{"id": 955, "token": "ues", "merges": "u es", "raw_count": 230917, "count": 4808176, "decode_str": "ues"} -{"id": 736, "token": "row", "merges": "ro w", "raw_count": 2189172, "count": 4808281, "decode_str": "row"} -{"id": 51958, "token": "\u00e6\u012e\u00bd", "merges": "\u00e6\u012e \u00bd", "raw_count": 4809936, "count": 4809936, "decode_str": "\u633d"} -{"id": 51793, "token": "\u00e6\u0126\u00a7", "merges": "\u00e6\u0126 \u00a7", "raw_count": 4812277, "count": 4812277, "decode_str": "\u6127"} -{"id": 3566, "token": "74", "merges": "7 4", "raw_count": 4240508, "count": 4817033, "decode_str": "74"} -{"id": 5305, "token": "CP", "merges": "C P", "raw_count": 2991181, "count": 4825605, "decode_str": "CP"} -{"id": 2799, "token": "load", "merges": "l oad", "raw_count": 2439257, "count": 4828129, "decode_str": "load"} -{"id": 691, "token": "\u0120ob", "merges": "\u0120o b", "raw_count": 151853, "count": 4832500, "decode_str": " ob"} -{"id": 3593, "token": "81", "merges": "8 1", "raw_count": 3946195, "count": 4847397, "decode_str": "81"} -{"id": 1050, "token": "ational", "merges": "ation al", "raw_count": 204937, "count": 4853353, "decode_str": "ational"} -{"id": 1145, "token": "An", "merges": "A n", "raw_count": 921324, "count": 4856687, "decode_str": "An"} -{"id": 43820, "token": "\u00e2\u0122\u013f?", "merges": "\u00e2\u0122\u013f ?", "raw_count": 4857200, "count": 4857200, "decode_str": "\u201d?"} -{"id": 51768, "token": "\u00e6\u0125\u0141", "merges": "\u00e6\u0125 \u0141", "raw_count": 4857642, "count": 4857642, "decode_str": "\u60df"} -{"id": 50926, "token": "\u00e5\u0131\u013d", "merges": "\u00e5\u0131 \u013d", "raw_count": 4862327, "count": 4862327, "decode_str": "\u53db"} -{"id": 623, "token": "\u0109\u0109", "merges": "\u0109 \u0109", "raw_count": 90597, "count": 4869362, "decode_str": "\t\t"} -{"id": 663, "token": "lic", "merges": "l ic", "raw_count": 267849, "count": 4873049, "decode_str": "lic"} -{"id": 4663, "token": "index", "merges": "ind ex", "raw_count": 4869617, "count": 4877697, "decode_str": "index"} -{"id": 1826, "token": "new", "merges": "ne w", "raw_count": 4253873, "count": 4883166, "decode_str": "new"} -{"id": 1618, "token": "\u0120list", "merges": "\u0120l ist", "raw_count": 4569268, "count": 4899280, "decode_str": " list"} -{"id": 53042, "token": "\u00e7\u0141\u00a3", "merges": "\u00e7\u0141 \u00a3", "raw_count": 4901784, "count": 4901784, "decode_str": "\u77e3"} -{"id": 51061, "token": "\u00e5\u0135\u0130", "merges": "\u00e5\u0135 \u0130", "raw_count": 4904014, "count": 4904014, "decode_str": "\u54ce"} -{"id": 8850, "token": "([", "merges": "( [", "raw_count": 4906643, "count": 4906643, "decode_str": "(["} -{"id": 771, "token": "\u0120mod", "merges": "\u0120m od", "raw_count": 238546, "count": 4908381, "decode_str": " mod"} -{"id": 54460, "token": "\u00e9\u00a2\u00a4", "merges": "\u00e9\u00a2 \u00a4", "raw_count": 4911065, "count": 4911065, "decode_str": "\u98a4"} -{"id": 51207, "token": "\u00e5\u013f\u00a4", "merges": "\u00e5\u013f \u00a4", "raw_count": 4911788, "count": 4911788, "decode_str": "\u5764"} -{"id": 3655, "token": "73", "merges": "7 3", "raw_count": 4339418, "count": 4912054, "decode_str": "73"} -{"id": 3832, "token": "61", "merges": "6 1", "raw_count": 4360633, "count": 4913930, "decode_str": "61"} -{"id": 50447, "token": "\u00e4\u00b9\u0138", "merges": "\u00e4\u00b9 \u0138", "raw_count": 4914930, "count": 4914930, "decode_str": "\u4e56"} -{"id": 2482, "token": "essage", "merges": "ess age", "raw_count": 58513, "count": 4917598, "decode_str": "essage"} -{"id": 629, "token": "\u0120part", "merges": "\u0120p art", "raw_count": 973054, "count": 4919540, "decode_str": " part"} -{"id": 51322, "token": "\u00e5\u00a5\u0142", "merges": "\u00e5\u00a5 \u0142", "raw_count": 4919773, "count": 4919773, "decode_str": "\u5960"} -{"id": 2491, "token": "\u0120range", "merges": "\u0120r ange", "raw_count": 4920842, "count": 4920842, "decode_str": " range"} -{"id": 2769, "token": ")(", "merges": ") (", "raw_count": 4922310, "count": 4922310, "decode_str": ")("} -{"id": 53274, "token": "\u00e7\u00b2\u00b9", "merges": "\u00e7\u00b2 \u00b9", "raw_count": 4922739, "count": 4922739, "decode_str": "\u7cb9"} -{"id": 52720, "token": "\u00e7\u0123\u00bf", "merges": "\u00e7\u0123 \u00bf", "raw_count": 4928243, "count": 4928243, "decode_str": "\u707f"} -{"id": 52755, "token": "\u00e7\u0126\u00b0", "merges": "\u00e7\u0126 \u00b0", "raw_count": 4934181, "count": 4934181, "decode_str": "\u7130"} -{"id": 51803, "token": "\u00e6\u0127\u00a8", "merges": "\u00e6\u0127 \u00a8", "raw_count": 4934517, "count": 4934517, "decode_str": "\u6168"} -{"id": 1171, "token": "of", "merges": "o f", "raw_count": 4446620, "count": 4944670, "decode_str": "of"} -{"id": 51580, "token": "\u00e5\u00ba\u00b8", "merges": "\u00e5\u00ba \u00b8", "raw_count": 4947115, "count": 4947115, "decode_str": "\u5eb8"} -{"id": 51970, "token": "\u00e6\u012f\u0140", "merges": "\u00e6\u012f \u0140", "raw_count": 4954748, "count": 4954748, "decode_str": "\u635e"} -{"id": 52933, "token": "\u00e7\u0139\u0134", "merges": "\u00e7\u0139 \u0134", "raw_count": 4960371, "count": 4960371, "decode_str": "\u75d2"} -{"id": 51260, "token": "\u00e5\u00a2\u0127", "merges": "\u00e5\u00a2 \u0127", "raw_count": 4976390, "count": 4976390, "decode_str": "\u5885"} -{"id": 1945, "token": "ask", "merges": "as k", "raw_count": 397108, "count": 4985025, "decode_str": "ask"} -{"id": 444, "token": "\u0120E", "merges": "\u0120 E", "raw_count": 970914, "count": 4986679, "decode_str": " E"} -{"id": 53723, "token": "\u00e8\u00a2\u012f", "merges": "\u00e8\u00a2 \u012f", "raw_count": 4989121, "count": 4989121, "decode_str": "\u888d"} -{"id": 8102, "token": "dict", "merges": "d ict", "raw_count": 4985705, "count": 4993356, "decode_str": "dict"} -{"id": 51607, "token": "\u00e5\u00bc\u00a6", "merges": "\u00e5\u00bc \u00a6", "raw_count": 4994315, "count": 4994315, "decode_str": "\u5f26"} -{"id": 51090, "token": "\u00e5\u0137\u00a4", "merges": "\u00e5\u0137 \u00a4", "raw_count": 4999853, "count": 4999853, "decode_str": "\u5564"} -{"id": 12827, "token": "Equal", "merges": "Equ al", "raw_count": 496049, "count": 5002098, "decode_str": "Equal"} -{"id": 51039, "token": "\u00e5\u0134\u00aa", "merges": "\u00e5\u0134 \u00aa", "raw_count": 5003500, "count": 5003500, "decode_str": "\u54aa"} -{"id": 54316, "token": "\u00e9\u013b\u0122", "merges": "\u00e9\u013b \u0122", "raw_count": 5003768, "count": 5003768, "decode_str": "\u9640"} -{"id": 658, "token": "ree", "merges": "re e", "raw_count": 453237, "count": 5009159, "decode_str": "ree"} -{"id": 51114, "token": "\u00e5\u0138\u012b", "merges": "\u00e5\u0138 \u012b", "raw_count": 5012482, "count": 5012482, "decode_str": "\u5589"} -{"id": 52517, "token": "\u00e6\u00b2\u00b8", "merges": "\u00e6\u00b2 \u00b8", "raw_count": 5021320, "count": 5021320, "decode_str": "\u6cb8"} -{"id": 53414, "token": "\u00e7\u00bd\u0137", "merges": "\u00e7\u00bd \u0137", "raw_count": 5029016, "count": 5029016, "decode_str": "\u7f55"} -{"id": 50412, "token": "\u00e4\u00b8\u013b", "merges": "\u00e4\u00b8 \u013b", "raw_count": 5029662, "count": 5029662, "decode_str": "\u4e19"} -{"id": 51596, "token": "\u00e5\u00bc\u012c", "merges": "\u00e5\u00bc \u012c", "raw_count": 5029924, "count": 5029924, "decode_str": "\u5f0a"} -{"id": 827, "token": "iew", "merges": "ie w", "raw_count": 41683, "count": 5038248, "decode_str": "iew"} -{"id": 52317, "token": "\u00e6\u00a1\u00a9", "merges": "\u00e6\u00a1 \u00a9", "raw_count": 5038558, "count": 5038558, "decode_str": "\u6869"} -{"id": 51489, "token": "\u00e5\u00b1\u0133", "merges": "\u00e5\u00b1 \u0133", "raw_count": 5040266, "count": 5040266, "decode_str": "\u5c51"} -{"id": 53954, "token": "\u00e8\u00b5\u0132", "merges": "\u00e8\u00b5 \u0132", "raw_count": 5042096, "count": 5042096, "decode_str": "\u8d50"} -{"id": 7749, "token": "110", "merges": "1 10", "raw_count": 4986674, "count": 5045412, "decode_str": "110"} -{"id": 53019, "token": "\u00e7\u013f\u0123", "merges": "\u00e7\u013f \u0123", "raw_count": 5047258, "count": 5047258, "decode_str": "\u7741"} -{"id": 5397, "token": "config", "merges": "con fig", "raw_count": 4598365, "count": 5047702, "decode_str": "config"} -{"id": 52453, "token": "\u00e6\u00b0\u00a2", "merges": "\u00e6\u00b0 \u00a2", "raw_count": 5056140, "count": 5056140, "decode_str": "\u6c22"} -{"id": 723, "token": "ings", "merges": "ing s", "raw_count": 1138204, "count": 5059315, "decode_str": "ings"} -{"id": 53266, "token": "\u00e7\u00b2\u00a4", "merges": "\u00e7\u00b2 \u00a4", "raw_count": 5061022, "count": 5061022, "decode_str": "\u7ca4"} -{"id": 1004, "token": "ox", "merges": "o x", "raw_count": 601154, "count": 5061854, "decode_str": "ox"} -{"id": 1032, "token": "ars", "merges": "ar s", "raw_count": 651005, "count": 5062794, "decode_str": "ars"} -{"id": 3575, "token": "param", "merges": "par am", "raw_count": 3912952, "count": 5066896, "decode_str": "param"} -{"id": 873, "token": "\u0120set", "merges": "\u0120s et", "raw_count": 3695665, "count": 5090465, "decode_str": " set"} -{"id": 416, "token": "\u0120R", "merges": "\u0120 R", "raw_count": 915573, "count": 5106653, "decode_str": " R"} -{"id": 53054, "token": "\u00e7\u0142\u012f", "merges": "\u00e7\u0142 \u012f", "raw_count": 5110125, "count": 5110125, "decode_str": "\u780d"} -{"id": 53771, "token": "\u00e8\u00a9\u00b9", "merges": "\u00e8\u00a9 \u00b9", "raw_count": 5113845, "count": 5113845, "decode_str": "\u8a79"} -{"id": 687, "token": "\u0120ro", "merges": "\u0120 ro", "raw_count": 418357, "count": 5120133, "decode_str": " ro"} -{"id": 51817, "token": "\u00e6\u012a\u013c", "merges": "\u00e6\u012a \u013c", "raw_count": 5121954, "count": 5121954, "decode_str": "\u621a"} -{"id": 1934, "token": "AC", "merges": "A C", "raw_count": 2526988, "count": 5122330, "decode_str": "AC"} -{"id": 11793, "token": "\u0120True", "merges": "\u0120Tr ue", "raw_count": 5134542, "count": 5134542, "decode_str": " True"} -{"id": 51700, "token": "\u00e6\u0122\u00a1", "merges": "\u00e6\u0122 \u00a1", "raw_count": 5134720, "count": 5134720, "decode_str": "\u6021"} -{"id": 9204, "token": "2005", "merges": "200 5", "raw_count": 5136574, "count": 5136574, "decode_str": "2005"} -{"id": 469, "token": "ich", "merges": "ic h", "raw_count": 443132, "count": 5137321, "decode_str": "ich"} -{"id": 52501, "token": "\u00e6\u00b2\u0132", "merges": "\u00e6\u00b2 \u0132", "raw_count": 5138558, "count": 5138558, "decode_str": "\u6c90"} -{"id": 710, "token": "ove", "merges": "o ve", "raw_count": 242944, "count": 5139749, "decode_str": "ove"} -{"id": 53119, "token": "\u00e7\u00a5\u013d", "merges": "\u00e7\u00a5 \u013d", "raw_count": 5141816, "count": 5141816, "decode_str": "\u795b"} -{"id": 2050, "token": "inf", "merges": "in f", "raw_count": 634712, "count": 5142995, "decode_str": "inf"} -{"id": 729, "token": "ov", "merges": "o v", "raw_count": 936620, "count": 5155237, "decode_str": "ov"} -{"id": 50531, "token": "\u00e4\u00bc\u0140", "merges": "\u00e4\u00bc \u0140", "raw_count": 5158684, "count": 5158684, "decode_str": "\u4f1e"} -{"id": 51467, "token": "\u00e5\u00b0\u00b4", "merges": "\u00e5\u00b0 \u00b4", "raw_count": 5159961, "count": 5159961, "decode_str": "\u5c34"} -{"id": 739, "token": "iss", "merges": "is s", "raw_count": 653405, "count": 5166218, "decode_str": "iss"} -{"id": 1779, "token": "Ch", "merges": "C h", "raw_count": 1960208, "count": 5174944, "decode_str": "Ch"} -{"id": 353, "token": "\u0120M", "merges": "\u0120 M", "raw_count": 1140083, "count": 5178267, "decode_str": " M"} -{"id": 52241, "token": "\u00e6\u0140\u00a2", "merges": "\u00e6\u0140 \u00a2", "raw_count": 5179393, "count": 5179393, "decode_str": "\u67a2"} -{"id": 54226, "token": "\u00e9\u0136\u012e", "merges": "\u00e9\u0136 \u012e", "raw_count": 5184383, "count": 5184383, "decode_str": "\u950c"} -{"id": 53356, "token": "\u00e7\u00bb\u00a3", "merges": "\u00e7\u00bb \u00a3", "raw_count": 5199420, "count": 5199420, "decode_str": "\u7ee3"} -{"id": 54529, "token": "\u00e9\u00bb\u0131", "merges": "\u00e9\u00bb \u0131", "raw_count": 5205089, "count": 5205089, "decode_str": "\u9ecf"} -{"id": 51205, "token": "\u00e5\u013f\u0142", "merges": "\u00e5\u013f \u0142", "raw_count": 5217099, "count": 5217099, "decode_str": "\u5760"} -{"id": 50576, "token": "\u00e4\u00be\u012f", "merges": "\u00e4\u00be \u012f", "raw_count": 5217807, "count": 5217807, "decode_str": "\u4f8d"} -{"id": 54358, "token": "\u00e9\u013d\u0122", "merges": "\u00e9\u013d \u0122", "raw_count": 5217830, "count": 5217830, "decode_str": "\u96c0"} -{"id": 52785, "token": "\u00e7\u012b\u00b2", "merges": "\u00e7\u012b \u00b2", "raw_count": 5218427, "count": 5218427, "decode_str": "\u7272"} -{"id": 50671, "token": "\u00e5\u0125\u00b5", "merges": "\u00e5\u0125 \u00b5", "raw_count": 5218552, "count": 5218552, "decode_str": "\u50f5"} -{"id": 51119, "token": "\u00e5\u0138\u013a", "merges": "\u00e5\u0138 \u013a", "raw_count": 5225846, "count": 5225846, "decode_str": "\u5598"} -{"id": 50950, "token": "\u00e5\u0132\u0123", "merges": "\u00e5\u0132 \u0123", "raw_count": 5226620, "count": 5226620, "decode_str": "\u5401"} -{"id": 1033, "token": "sp", "merges": "s p", "raw_count": 2924635, "count": 5228147, "decode_str": "sp"} -{"id": 735, "token": "vers", "merges": "ver s", "raw_count": 391162, "count": 5234227, "decode_str": "vers"} -{"id": 676, "token": "low", "merges": "l ow", "raw_count": 688056, "count": 5234955, "decode_str": "low"} -{"id": 52244, "token": "\u00e6\u0140\u00ab", "merges": "\u00e6\u0140 \u00ab", "raw_count": 5236824, "count": 5236824, "decode_str": "\u67ab"} -{"id": 51953, "token": "\u00e6\u012e\u00ab", "merges": "\u00e6\u012e \u00ab", "raw_count": 5237986, "count": 5237986, "decode_str": "\u632b"} -{"id": 50998, "token": "\u00e5\u0133\u0139", "merges": "\u00e5\u0133 \u0139", "raw_count": 5238414, "count": 5238414, "decode_str": "\u5457"} -{"id": 3245, "token": "83", "merges": "8 3", "raw_count": 4177457, "count": 5241564, "decode_str": "83"} -{"id": 419, "token": "\u0120ha", "merges": "\u0120h a", "raw_count": 223109, "count": 5245605, "decode_str": " ha"} -{"id": 3418, "token": "word", "merges": "w ord", "raw_count": 1795587, "count": 5246781, "decode_str": "word"} -{"id": 52041, "token": "\u00e6\u0134\u00b0", "merges": "\u00e6\u0134 \u00b0", "raw_count": 5249081, "count": 5249081, "decode_str": "\u64b0"} -{"id": 38904, "token": "\u00e2\u0122\u013f;", "merges": "\u00e2\u0122\u013f ;", "raw_count": 5253474, "count": 5253474, "decode_str": "\u201d;"} -{"id": 52120, "token": "\u00e6\u0139\u0143", "merges": "\u00e6\u0139 \u0143", "raw_count": 5258378, "count": 5258378, "decode_str": "\u65ed"} -{"id": 53923, "token": "\u00e8\u00b4\u00a9", "merges": "\u00e8\u00b4 \u00a9", "raw_count": 5258636, "count": 5258636, "decode_str": "\u8d29"} -{"id": 52392, "token": "\u00e6\u0143\u0129", "merges": "\u00e6\u0143 \u0129", "raw_count": 5272760, "count": 5272760, "decode_str": "\u6b47"} -{"id": 1410, "token": "ES", "merges": "E S", "raw_count": 2552748, "count": 5273868, "decode_str": "ES"} -{"id": 28812, "token": "\u00e8\u00a9", "merges": "\u00e8 \u00a9", "raw_count": 164461, "count": 5278306, "decode_str": "\ufffd"} -{"id": 641, "token": "ors", "merges": "or s", "raw_count": 1047239, "count": 5282369, "decode_str": "ors"} -{"id": 53599, "token": "\u00e8\u012b\u013a", "merges": "\u00e8\u012b \u013a", "raw_count": 5288031, "count": 5288031, "decode_str": "\u8258"} -{"id": 53773, "token": "\u00e8\u00aa\u0135", "merges": "\u00e8\u00aa \u0135", "raw_count": 5289619, "count": 5289619, "decode_str": "\u8a93"} -{"id": 53267, "token": "\u00e7\u00b2\u00a5", "merges": "\u00e7\u00b2 \u00a5", "raw_count": 5299270, "count": 5299270, "decode_str": "\u7ca5"} -{"id": 499, "token": "\u0120pl", "merges": "\u0120p l", "raw_count": 510684, "count": 5303113, "decode_str": " pl"} -{"id": 53668, "token": "\u00e8\u0130\u0140", "merges": "\u00e8\u0130 \u0140", "raw_count": 5307950, "count": 5307950, "decode_str": "\u839e"} -{"id": 2606, "token": "time", "merges": "t ime", "raw_count": 4713453, "count": 5315541, "decode_str": "time"} -{"id": 684, "token": "ates", "merges": "at es", "raw_count": 648725, "count": 5326628, "decode_str": "ates"} -{"id": 53620, "token": "\u00e8\u012c\u00a6", "merges": "\u00e8\u012c \u00a6", "raw_count": 5327391, "count": 5327391, "decode_str": "\u82a6"} -{"id": 930, "token": "\u0120num", "merges": "\u0120n um", "raw_count": 2149759, "count": 5329742, "decode_str": " num"} -{"id": 53461, "token": "\u00e8\u0122\u00bd", "merges": "\u00e8\u0122 \u00bd", "raw_count": 5331145, "count": 5331145, "decode_str": "\u803d"} -{"id": 54491, "token": "\u00e9\u00aa\u0126", "merges": "\u00e9\u00aa \u0126", "raw_count": 5332001, "count": 5332001, "decode_str": "\u9a84"} -{"id": 997, "token": "\u0120requ", "merges": "\u0120re qu", "raw_count": 25972, "count": 5333494, "decode_str": " requ"} -{"id": 53429, "token": "\u00e7\u00be\u0140", "merges": "\u00e7\u00be \u0140", "raw_count": 5335278, "count": 5335278, "decode_str": "\u7f9e"} -{"id": 1830, "token": "IS", "merges": "I S", "raw_count": 2222860, "count": 5336509, "decode_str": "IS"} -{"id": 50797, "token": "\u00e5\u012b\u0138", "merges": "\u00e5\u012b \u0138", "raw_count": 5349721, "count": 5349721, "decode_str": "\u5256"} -{"id": 562, "token": "\u0120out", "merges": "\u0120o ut", "raw_count": 2672231, "count": 5350116, "decode_str": " out"} -{"id": 52143, "token": "\u00e6\u013a\u0143", "merges": "\u00e6\u013a \u0143", "raw_count": 5361040, "count": 5361040, "decode_str": "\u662d"} -{"id": 52548, "token": "\u00e6\u00b3\u00bc", "merges": "\u00e6\u00b3 \u00bc", "raw_count": 5362055, "count": 5362055, "decode_str": "\u6cfc"} -{"id": 51466, "token": "\u00e5\u00b0\u00ac", "merges": "\u00e5\u00b0 \u00ac", "raw_count": 5366159, "count": 5366159, "decode_str": "\u5c2c"} -{"id": 52253, "token": "\u00e6\u0141\u0126", "merges": "\u00e6\u0141 \u0126", "raw_count": 5370262, "count": 5370262, "decode_str": "\u67c4"} -{"id": 63, "token": "^", "merges": "NULL", "raw_count": 2762971, "count": 5370627, "decode_str": "^"} -{"id": 983, "token": "ms", "merges": "m s", "raw_count": 1942185, "count": 5371531, "decode_str": "ms"} -{"id": 50801, "token": "\u00e5\u012b\u00a5", "merges": "\u00e5\u012b \u00a5", "raw_count": 5373636, "count": 5373636, "decode_str": "\u5265"} -{"id": 485, "token": "ome", "merges": "om e", "raw_count": 508818, "count": 5378069, "decode_str": "ome"} -{"id": 54176, "token": "\u00e9\u0125\u00a1", "merges": "\u00e9\u0125 \u00a1", "raw_count": 5379449, "count": 5379449, "decode_str": "\u90e1"} -{"id": 11336, "token": "None", "merges": "N one", "raw_count": 5388200, "count": 5388200, "decode_str": "None"} -{"id": 50503, "token": "\u00e4\u00bb\u0139", "merges": "\u00e4\u00bb \u0139", "raw_count": 5390079, "count": 5390079, "decode_str": "\u4ed7"} -{"id": 369, "token": "\u0120was", "merges": "\u0120w as", "raw_count": 5141679, "count": 5391363, "decode_str": " was"} -{"id": 52653, "token": "\u00e6\u00b8\u012c", "merges": "\u00e6\u00b8 \u012c", "raw_count": 5394645, "count": 5394645, "decode_str": "\u6e0a"} -{"id": 51493, "token": "\u00e5\u00b1\u00a1", "merges": "\u00e5\u00b1 \u00a1", "raw_count": 5406564, "count": 5406564, "decode_str": "\u5c61"} -{"id": 3677, "token": "71", "merges": "7 1", "raw_count": 3932100, "count": 5419996, "decode_str": "71"} -{"id": 54248, "token": "\u00e9\u0137\u0122", "merges": "\u00e9\u0137 \u0122", "raw_count": 5425850, "count": 5425850, "decode_str": "\u9540"} -{"id": 52242, "token": "\u00e6\u0140\u00a3", "merges": "\u00e6\u0140 \u00a3", "raw_count": 5435019, "count": 5435019, "decode_str": "\u67a3"} -{"id": 1535, "token": "\u0120Tr", "merges": "\u0120T r", "raw_count": 66860, "count": 5435689, "decode_str": " Tr"} -{"id": 54277, "token": "\u00e9\u0139\u00af", "merges": "\u00e9\u0139 \u00af", "raw_count": 5444803, "count": 5444803, "decode_str": "\u95ef"} -{"id": 1476, "token": "!\"", "merges": "! \"", "raw_count": 5409479, "count": 5452219, "decode_str": "!\""} -{"id": 50829, "token": "\u00e5\u012d\u012b", "merges": "\u00e5\u012d \u012b", "raw_count": 5454623, "count": 5454623, "decode_str": "\u52c9"} -{"id": 53069, "token": "\u00e7\u0142\u00b8", "merges": "\u00e7\u0142 \u00b8", "raw_count": 5456143, "count": 5456143, "decode_str": "\u7838"} -{"id": 508, "token": "ther", "merges": "t her", "raw_count": 121315, "count": 5458465, "decode_str": "ther"} -{"id": 3763, "token": "62", "merges": "6 2", "raw_count": 4830625, "count": 5461168, "decode_str": "62"} -{"id": 50897, "token": "\u00e5\u012f\u00bf", "merges": "\u00e5\u012f \u00bf", "raw_count": 5465612, "count": 5465612, "decode_str": "\u537f"} -{"id": 1227, "token": "\u0120/", "merges": "\u0120 /", "raw_count": 5402746, "count": 5467268, "decode_str": " /"} -{"id": 898, "token": "\u01209", "merges": "\u0120 9", "raw_count": 3764079, "count": 5467700, "decode_str": " 9"} -{"id": 579, "token": "ru", "merges": "r u", "raw_count": 521000, "count": 5470602, "decode_str": "ru"} -{"id": 54062, "token": "\u00e8\u00be\u00b1", "merges": "\u00e8\u00be \u00b1", "raw_count": 5471358, "count": 5471358, "decode_str": "\u8fb1"} -{"id": 54011, "token": "\u00e8\u00ba\u0123", "merges": "\u00e8\u00ba \u0123", "raw_count": 5471702, "count": 5471702, "decode_str": "\u8e81"} -{"id": 1052, "token": "\u0120200", "merges": "\u01202 00", "raw_count": 991680, "count": 5478354, "decode_str": " 200"} -{"id": 4339, "token": "CE", "merges": "C E", "raw_count": 5170172, "count": 5478794, "decode_str": "CE"} -{"id": 50550, "token": "\u00e4\u00bd\u0132", "merges": "\u00e4\u00bd \u0132", "raw_count": 5483064, "count": 5483064, "decode_str": "\u4f50"} -{"id": 54415, "token": "\u00e9\u0141\u00a7", "merges": "\u00e9\u0141 \u00a7", "raw_count": 5487729, "count": 5487729, "decode_str": "\u97e7"} -{"id": 3507, "token": "82", "merges": "8 2", "raw_count": 4364810, "count": 5488425, "decode_str": "82"} -{"id": 7008, "token": "Equ", "merges": "E qu", "raw_count": 103934, "count": 5490040, "decode_str": "Equ"} -{"id": 51782, "token": "\u00e6\u0125\u00b9", "merges": "\u00e6\u0125 \u00b9", "raw_count": 5494256, "count": 5494256, "decode_str": "\u60f9"} -{"id": 52522, "token": "\u00e6\u00b2\u00be", "merges": "\u00e6\u00b2 \u00be", "raw_count": 5501420, "count": 5501420, "decode_str": "\u6cbe"} -{"id": 1011, "token": "oup", "merges": "ou p", "raw_count": 540974, "count": 5505393, "decode_str": "oup"} -{"id": 52811, "token": "\u00e7\u0130\u00ab", "merges": "\u00e7\u0130 \u00ab", "raw_count": 5530356, "count": 5530356, "decode_str": "\u73ab"} -{"id": 8603, "token": "2006", "merges": "200 6", "raw_count": 5530448, "count": 5530448, "decode_str": "2006"} -{"id": 23167, "token": "LED", "merges": "L ED", "raw_count": 5532980, "count": 5532980, "decode_str": "LED"} -{"id": 865, "token": "?\"", "merges": "? \"", "raw_count": 5352833, "count": 5533650, "decode_str": "?\""} -{"id": 16587, "token": "360", "merges": "3 60", "raw_count": 5537407, "count": 5537407, "decode_str": "360"} -{"id": 9855, "token": "[\"", "merges": "[ \"", "raw_count": 5531590, "count": 5537658, "decode_str": "[\""} -{"id": 1665, "token": "son", "merges": "s on", "raw_count": 613418, "count": 5539558, "decode_str": "son"} -{"id": 397, "token": "--------", "merges": "---- ----", "raw_count": 141527, "count": 5540042, "decode_str": "--------"} -{"id": 1173, "token": "ev", "merges": "e v", "raw_count": 643985, "count": 5547591, "decode_str": "ev"} -{"id": 52890, "token": "\u00e7\u0137\u013e", "merges": "\u00e7\u0137 \u013e", "raw_count": 5556357, "count": 5556357, "decode_str": "\u755c"} -{"id": 3571, "token": "63", "merges": "6 3", "raw_count": 4927202, "count": 5558556, "decode_str": "63"} -{"id": 609, "token": "are", "merges": "a re", "raw_count": 791329, "count": 5566050, "decode_str": "are"} -{"id": 1139, "token": "ON", "merges": "O N", "raw_count": 1466082, "count": 5571311, "decode_str": "ON"} -{"id": 2259, "token": "ape", "merges": "a pe", "raw_count": 839423, "count": 5578273, "decode_str": "ape"} -{"id": 51477, "token": "\u00e5\u00b1\u0123", "merges": "\u00e5\u00b1 \u0123", "raw_count": 5581970, "count": 5581970, "decode_str": "\u5c41"} -{"id": 54035, "token": "\u00e8\u00bd\u00bf", "merges": "\u00e8\u00bd \u00bf", "raw_count": 5582425, "count": 5582425, "decode_str": "\u8f7f"} -{"id": 52026, "token": "\u00e6\u0131\u00bd", "merges": "\u00e6\u0131 \u00bd", "raw_count": 5583787, "count": 5583787, "decode_str": "\u63fd"} -{"id": 1864, "token": "IC", "merges": "I C", "raw_count": 3311665, "count": 5589117, "decode_str": "IC"} -{"id": 53881, "token": "\u00e8\u00b0\u00a6", "merges": "\u00e8\u00b0 \u00a6", "raw_count": 5597955, "count": 5597955, "decode_str": "\u8c26"} -{"id": 50984, "token": "\u00e5\u0132\u00bb", "merges": "\u00e5\u0132 \u00bb", "raw_count": 5622505, "count": 5622505, "decode_str": "\u543b"} -{"id": 592, "token": "ents", "merges": "ent s", "raw_count": 363391, "count": 5634490, "decode_str": "ents"} -{"id": 50675, "token": "\u00e5\u0126\u0134", "merges": "\u00e5\u0126 \u0134", "raw_count": 5644991, "count": 5644991, "decode_str": "\u5112"} -{"id": 50583, "token": "\u00e4\u00be\u00a3", "merges": "\u00e4\u00be \u00a3", "raw_count": 5647626, "count": 5647626, "decode_str": "\u4fa3"} -{"id": 51505, "token": "\u00e5\u00b7\u00a2", "merges": "\u00e5\u00b7 \u00a2", "raw_count": 5651162, "count": 5651162, "decode_str": "\u5de2"} -{"id": 1844, "token": "requ", "merges": "re qu", "raw_count": 151066, "count": 5655862, "decode_str": "requ"} -{"id": 1258, "token": "fl", "merges": "f l", "raw_count": 1004256, "count": 5656959, "decode_str": "fl"} -{"id": 53709, "token": "\u00e8\u00a1\u00ab", "merges": "\u00e8\u00a1 \u00ab", "raw_count": 5667903, "count": 5667903, "decode_str": "\u886b"} -{"id": 52575, "token": "\u00e6\u00b5\u0129", "merges": "\u00e6\u00b5 \u0129", "raw_count": 5671420, "count": 5671420, "decode_str": "\u6d47"} -{"id": 53940, "token": "\u00e8\u00b4\u00bc", "merges": "\u00e8\u00b4 \u00bc", "raw_count": 5684047, "count": 5684047, "decode_str": "\u8d3c"} -{"id": 51509, "token": "\u00e5\u00b7\u00a9", "merges": "\u00e5\u00b7 \u00a9", "raw_count": 5686281, "count": 5686281, "decode_str": "\u5de9"} -{"id": 3736, "token": "\u0120?", "merges": "\u0120 ?", "raw_count": 5697686, "count": 5703400, "decode_str": " ?"} -{"id": 886, "token": "ec", "merges": "e c", "raw_count": 1096614, "count": 5715406, "decode_str": "ec"} -{"id": 1402, "token": "ray", "merges": "r ay", "raw_count": 416108, "count": 5716796, "decode_str": "ray"} -{"id": 563, "token": "du", "merges": "d u", "raw_count": 680878, "count": 5718544, "decode_str": "du"} -{"id": 54056, "token": "\u00e8\u00be\u0141", "merges": "\u00e8\u00be \u0141", "raw_count": 5729987, "count": 5729987, "decode_str": "\u8f9f"} -{"id": 1987, "token": "cont", "merges": "con t", "raw_count": 659583, "count": 5736769, "decode_str": "cont"} -{"id": 3299, "token": "PS", "merges": "P S", "raw_count": 5483363, "count": 5743237, "decode_str": "PS"} -{"id": 52246, "token": "\u00e6\u0140\u00af", "merges": "\u00e6\u0140 \u00af", "raw_count": 5748535, "count": 5748535, "decode_str": "\u67af"} -{"id": 829, "token": "cess", "merges": "c ess", "raw_count": 121584, "count": 5752687, "decode_str": "cess"} -{"id": 3071, "token": "06", "merges": "0 6", "raw_count": 5598874, "count": 5757018, "decode_str": "06"} -{"id": 18128, "token": "AI", "merges": "A I", "raw_count": 5760293, "count": 5760293, "decode_str": "AI"} -{"id": 51348, "token": "\u00e5\u00a6\u00ae", "merges": "\u00e5\u00a6 \u00ae", "raw_count": 5774172, "count": 5774172, "decode_str": "\u59ae"} -{"id": 2641, "token": "Ph", "merges": "P h", "raw_count": 400740, "count": 5778539, "decode_str": "Ph"} -{"id": 11395, "token": "180", "merges": "18 0", "raw_count": 5782129, "count": 5782129, "decode_str": "180"} -{"id": 52763, "token": "\u00e7\u012a\u00b5", "merges": "\u00e7\u012a \u00b5", "raw_count": 5787257, "count": 5787257, "decode_str": "\u7235"} -{"id": 50894, "token": "\u00e5\u012f\u00b5", "merges": "\u00e5\u012f \u00b5", "raw_count": 5796595, "count": 5796595, "decode_str": "\u5375"} -{"id": 51962, "token": "\u00e6\u012f\u012b", "merges": "\u00e6\u012f \u012b", "raw_count": 5797713, "count": 5797713, "decode_str": "\u6349"} -{"id": 8472, "token": "\u0120len", "merges": "\u0120l en", "raw_count": 5798994, "count": 5798994, "decode_str": " len"} -{"id": 51049, "token": "\u00e5\u0134\u00bd", "merges": "\u00e5\u0134 \u00bd", "raw_count": 5799345, "count": 5799345, "decode_str": "\u54bd"} -{"id": 50755, "token": "\u00e5\u0129\u00b0", "merges": "\u00e5\u0129 \u00b0", "raw_count": 5810204, "count": 5810204, "decode_str": "\u51f0"} -{"id": 568, "token": "=\"", "merges": "= \"", "raw_count": 5378039, "count": 5815721, "decode_str": "=\""} -{"id": 53148, "token": "\u00e7\u00a7\u012b", "merges": "\u00e7\u00a7 \u012b", "raw_count": 5821938, "count": 5821938, "decode_str": "\u79c9"} -{"id": 51975, "token": "\u00e6\u012f\u00a7", "merges": "\u00e6\u012f \u00a7", "raw_count": 5827055, "count": 5827055, "decode_str": "\u6367"} -{"id": 993, "token": "pos", "merges": "p os", "raw_count": 2386737, "count": 5836568, "decode_str": "pos"} -{"id": 399, "token": "\u0120D", "merges": "\u0120 D", "raw_count": 1807916, "count": 5837480, "decode_str": " D"} -{"id": 51515, "token": "\u00e5\u00b7\u00b7", "merges": "\u00e5\u00b7 \u00b7", "raw_count": 5840379, "count": 5840379, "decode_str": "\u5df7"} -{"id": 54362, "token": "\u00e9\u013d\u0129", "merges": "\u00e9\u013d \u0129", "raw_count": 5848019, "count": 5848019, "decode_str": "\u96c7"} -{"id": 51142, "token": "\u00e5\u013b\u00a2", "merges": "\u00e5\u013b \u00a2", "raw_count": 5862170, "count": 5862170, "decode_str": "\u5662"} -{"id": 2025, "token": "ET", "merges": "E T", "raw_count": 3327319, "count": 5873568, "decode_str": "ET"} -{"id": 2387, "token": "\u0120)", "merges": "\u0120 )", "raw_count": 5860588, "count": 5874955, "decode_str": " )"} -{"id": 51051, "token": "\u00e5\u0135\u0122", "merges": "\u00e5\u0135 \u0122", "raw_count": 5878125, "count": 5878125, "decode_str": "\u54c0"} -{"id": 52370, "token": "\u00e6\u00a8\u00b1", "merges": "\u00e6\u00a8 \u00b1", "raw_count": 5886280, "count": 5886280, "decode_str": "\u6a31"} -{"id": 804, "token": "ring", "merges": "r ing", "raw_count": 342161, "count": 5892622, "decode_str": "ring"} -{"id": 50667, "token": "\u00e5\u0125\u00a7", "merges": "\u00e5\u0125 \u00a7", "raw_count": 5896965, "count": 5896965, "decode_str": "\u50e7"} -{"id": 52086, "token": "\u00e6\u0138\u012e", "merges": "\u00e6\u0138 \u012e", "raw_count": 5900412, "count": 5900412, "decode_str": "\u658c"} -{"id": 884, "token": "\u012010", "merges": "\u01201 0", "raw_count": 5176158, "count": 5902715, "decode_str": " 10"} -{"id": 677, "token": "erv", "merges": "er v", "raw_count": 178111, "count": 5912460, "decode_str": "erv"} -{"id": 54297, "token": "\u00e9\u013a\u0132", "merges": "\u00e9\u013a \u0132", "raw_count": 5912501, "count": 5912501, "decode_str": "\u9610"} -{"id": 1570, "token": "].", "merges": "] .", "raw_count": 4381554, "count": 5915845, "decode_str": "]."} -{"id": 54209, "token": "\u00e9\u0127\u00bf", "merges": "\u00e9\u0127 \u00bf", "raw_count": 5923521, "count": 5923521, "decode_str": "\u917f"} -{"id": 5088, "token": "True", "merges": "Tr ue", "raw_count": 5925025, "count": 5925025, "decode_str": "True"} -{"id": 2922, "token": "07", "merges": "0 7", "raw_count": 5618841, "count": 5927663, "decode_str": "07"} -{"id": 512, "token": "\u0120all", "merges": "\u0120al l", "raw_count": 4875243, "count": 5930116, "decode_str": " all"} -{"id": 814, "token": "ug", "merges": "u g", "raw_count": 877080, "count": 5940382, "decode_str": "ug"} -{"id": 50587, "token": "\u00e4\u00be\u00a8", "merges": "\u00e4\u00be \u00a8", "raw_count": 5948339, "count": 5948339, "decode_str": "\u4fa8"} -{"id": 53079, "token": "\u00e7\u00a1\u00ab", "merges": "\u00e7\u00a1 \u00ab", "raw_count": 5965812, "count": 5965812, "decode_str": "\u786b"} -{"id": 51853, "token": "\u00e6\u012b\u00af", "merges": "\u00e6\u012b \u00af", "raw_count": 5984764, "count": 5984764, "decode_str": "\u626f"} -{"id": 52486, "token": "\u00e6\u00b1\u00b0", "merges": "\u00e6\u00b1 \u00b0", "raw_count": 5992122, "count": 5992122, "decode_str": "\u6c70"} -{"id": 996, "token": "\u010a\u0109", "merges": "\u010a \u0109", "raw_count": 5913303, "count": 5995065, "decode_str": "\n\t"} -{"id": 548, "token": "\u0120wor", "merges": "\u0120w or", "raw_count": 10424, "count": 5995878, "decode_str": " wor"} -{"id": 51134, "token": "\u00e5\u0138\u00bb", "merges": "\u00e5\u0138 \u00bb", "raw_count": 6002805, "count": 6002805, "decode_str": "\u55bb"} -{"id": 51863, "token": "\u00e6\u012c\u0126", "merges": "\u00e6\u012c \u0126", "raw_count": 6003555, "count": 6003555, "decode_str": "\u6284"} -{"id": 54385, "token": "\u00e9\u013e\u012b", "merges": "\u00e9\u013e \u012b", "raw_count": 6007266, "count": 6007266, "decode_str": "\u9709"} -{"id": 2941, "token": "03", "merges": "0 3", "raw_count": 5951452, "count": 6008799, "decode_str": "03"} -{"id": 640, "token": "ake", "merges": "a ke", "raw_count": 864968, "count": 6035112, "decode_str": "ake"} -{"id": 2640, "token": "02", "merges": "0 2", "raw_count": 6007900, "count": 6041588, "decode_str": "02"} -{"id": 2946, "token": "App", "merges": "A pp", "raw_count": 4553888, "count": 6043436, "decode_str": "App"} -{"id": 492, "token": "\u0120tr", "merges": "\u0120t r", "raw_count": 266693, "count": 6044084, "decode_str": " tr"} -{"id": 661, "token": "ks", "merges": "k s", "raw_count": 687388, "count": 6046882, "decode_str": "ks"} -{"id": 51363, "token": "\u00e5\u00a7\u013c", "merges": "\u00e5\u00a7 \u013c", "raw_count": 6055922, "count": 6055922, "decode_str": "\u59da"} -{"id": 434, "token": "'s", "merges": "' s", "raw_count": 6060945, "count": 6060945, "decode_str": "'s"} -{"id": 3113, "token": "with", "merges": "w ith", "raw_count": 5797976, "count": 6064261, "decode_str": "with"} -{"id": 53099, "token": "\u00e7\u00a2\u00b1", "merges": "\u00e7\u00a2 \u00b1", "raw_count": 6065628, "count": 6065628, "decode_str": "\u78b1"} -{"id": 649, "token": "ft", "merges": "f t", "raw_count": 820662, "count": 6074300, "decode_str": "ft"} -{"id": 450, "token": "ould", "merges": "ou ld", "raw_count": 34219, "count": 6080101, "decode_str": "ould"} -{"id": 51530, "token": "\u00e5\u00b8\u013a", "merges": "\u00e5\u00b8 \u013a", "raw_count": 6080147, "count": 6080147, "decode_str": "\u5e18"} -{"id": 54205, "token": "\u00e9\u0127\u00b5", "merges": "\u00e9\u0127 \u00b5", "raw_count": 6096828, "count": 6096828, "decode_str": "\u9175"} -{"id": 53597, "token": "\u00e8\u012b\u0129", "merges": "\u00e8\u012b \u0129", "raw_count": 6097047, "count": 6097047, "decode_str": "\u8247"} -{"id": 53280, "token": "\u00e7\u00b3\u012c", "merges": "\u00e7\u00b3 \u012c", "raw_count": 6097113, "count": 6097113, "decode_str": "\u7cca"} -{"id": 52098, "token": "\u00e6\u0138\u00a5", "merges": "\u00e6\u0138 \u00a5", "raw_count": 6097537, "count": 6097537, "decode_str": "\u65a5"} -{"id": 8602, "token": "2007", "merges": "200 7", "raw_count": 6110025, "count": 6110025, "decode_str": "2007"} -{"id": 1001, "token": "ield", "merges": "iel d", "raw_count": 102451, "count": 6115572, "decode_str": "ield"} -{"id": 52402, "token": "\u00e6\u0143\u00a7", "merges": "\u00e6\u0143 \u00a7", "raw_count": 6117691, "count": 6117691, "decode_str": "\u6b67"} -{"id": 2125, "token": "04", "merges": "0 4", "raw_count": 5612905, "count": 6119049, "decode_str": "04"} -{"id": 2566, "token": "test", "merges": "t est", "raw_count": 5486177, "count": 6128282, "decode_str": "test"} -{"id": 436, "token": "\u0120this", "merges": "\u0120th is", "raw_count": 6134355, "count": 6134355, "decode_str": " this"} -{"id": 655, "token": "\u012019", "merges": "\u01201 9", "raw_count": 999781, "count": 6139840, "decode_str": " 19"} -{"id": 764, "token": "\u0120comm", "merges": "\u0120com m", "raw_count": 121170, "count": 6141310, "decode_str": " comm"} -{"id": 53136, "token": "\u00e7\u00a6\u0127", "merges": "\u00e7\u00a6 \u0127", "raw_count": 6147538, "count": 6147538, "decode_str": "\u7985"} -{"id": 51808, "token": "\u00e6\u012a\u012a", "merges": "\u00e6\u012a \u012a", "raw_count": 6150170, "count": 6150170, "decode_str": "\u6208"} -{"id": 3357, "token": "53", "merges": "5 3", "raw_count": 5615501, "count": 6151904, "decode_str": "53"} -{"id": 4756, "token": "Error", "merges": "Err or", "raw_count": 6158400, "count": 6158421, "decode_str": "Error"} -{"id": 50414, "token": "\u00e4\u00b8\u013d", "merges": "\u00e4\u00b8 \u013d", "raw_count": 6165348, "count": 6165348, "decode_str": "\u4e1b"} -{"id": 6327, "token": "BA", "merges": "B A", "raw_count": 6156999, "count": 6165482, "decode_str": "BA"} -{"id": 52675, "token": "\u00e6\u00ba\u0125", "merges": "\u00e6\u00ba \u0125", "raw_count": 6172011, "count": 6172011, "decode_str": "\u6e83"} -{"id": 1088, "token": "read", "merges": "re ad", "raw_count": 2899751, "count": 6174157, "decode_str": "read"} -{"id": 523, "token": "\u0120cont", "merges": "\u0120con t", "raw_count": 95746, "count": 6176181, "decode_str": " cont"} -{"id": 15749, "token": "\u0120np", "merges": "\u0120n p", "raw_count": 6176595, "count": 6176595, "decode_str": " np"} -{"id": 51908, "token": "\u00e6\u012d\u013a", "merges": "\u00e6\u012d \u013a", "raw_count": 6177330, "count": 6177330, "decode_str": "\u62d8"} -{"id": 51698, "token": "\u00e6\u0122\u013e", "merges": "\u00e6\u0122 \u013e", "raw_count": 6181911, "count": 6181911, "decode_str": "\u601c"} -{"id": 52886, "token": "\u00e7\u0137\u0131", "merges": "\u00e7\u0137 \u0131", "raw_count": 6188813, "count": 6188813, "decode_str": "\u754f"} -{"id": 4772, "token": "\u0120__", "merges": "\u0120_ _", "raw_count": 6190007, "count": 6190007, "decode_str": " __"} -{"id": 22418, "token": "?!", "merges": "? !", "raw_count": 6190745, "count": 6190745, "decode_str": "?!"} -{"id": 53572, "token": "\u00e8\u012a\u0128", "merges": "\u00e8\u012a \u0128", "raw_count": 6191696, "count": 6191696, "decode_str": "\u8206"} -{"id": 1910, "token": "onse", "merges": "on se", "raw_count": 27780, "count": 6192113, "decode_str": "onse"} -{"id": 2052, "token": "col", "merges": "c ol", "raw_count": 1500022, "count": 6205812, "decode_str": "col"} -{"id": 604, "token": "\u0120if", "merges": "\u0120 if", "raw_count": 6205191, "count": 6216803, "decode_str": " if"} -{"id": 51523, "token": "\u00e5\u00b8\u0128", "merges": "\u00e5\u00b8 \u0128", "raw_count": 6216935, "count": 6216935, "decode_str": "\u5e06"} -{"id": 51329, "token": "\u00e5\u00a6\u0125", "merges": "\u00e5\u00a6 \u0125", "raw_count": 6227730, "count": 6227730, "decode_str": "\u5983"} -{"id": 3439, "token": "54", "merges": "5 4", "raw_count": 5690760, "count": 6234667, "decode_str": "54"} -{"id": 2759, "token": "84", "merges": "8 4", "raw_count": 4501279, "count": 6235312, "decode_str": "84"} -{"id": 7082, "token": "][", "merges": "] [", "raw_count": 6235666, "count": 6235666, "decode_str": "]["} -{"id": 941, "token": "\u0120data", "merges": "\u0120d ata", "raw_count": 6236070, "count": 6236070, "decode_str": " data"} -{"id": 52100, "token": "\u00e6\u0138\u00a9", "merges": "\u00e6\u0138 \u00a9", "raw_count": 6238897, "count": 6238897, "decode_str": "\u65a9"} -{"id": 54457, "token": "\u00e9\u00a2\u0142", "merges": "\u00e9\u00a2 \u0142", "raw_count": 6242650, "count": 6242650, "decode_str": "\u98a0"} -{"id": 309, "token": "\u0120I", "merges": "\u0120 I", "raw_count": 904718, "count": 6246404, "decode_str": " I"} -{"id": 54110, "token": "\u00e9\u0122\u013f", "merges": "\u00e9\u0122 \u013f", "raw_count": 6253235, "count": 6253235, "decode_str": "\u901d"} -{"id": 3810, "token": "Err", "merges": "E rr", "raw_count": 51025, "count": 6257679, "decode_str": "Err"} -{"id": 773, "token": "\u0120\u00e2\u0122\u013e", "merges": "\u0120\u00e2\u0122 \u013e", "raw_count": 6260482, "count": 6260824, "decode_str": " \u201c"} -{"id": 52716, "token": "\u00e7\u0123\u00b6", "merges": "\u00e7\u0123 \u00b6", "raw_count": 6271107, "count": 6271107, "decode_str": "\u7076"} -{"id": 50981, "token": "\u00e5\u0132\u00b5", "merges": "\u00e5\u0132 \u00b5", "raw_count": 6275553, "count": 6275553, "decode_str": "\u5435"} -{"id": 786, "token": "ild", "merges": "il d", "raw_count": 82897, "count": 6278363, "decode_str": "ild"} -{"id": 4185, "token": "98", "merges": "9 8", "raw_count": 6246915, "count": 6283101, "decode_str": "98"} -{"id": 1418, "token": "0000", "merges": "00 00", "raw_count": 3245607, "count": 6285801, "decode_str": "0000"} -{"id": 51368, "token": "\u00e5\u00a7\u00a8", "merges": "\u00e5\u00a7 \u00a8", "raw_count": 6292030, "count": 6292030, "decode_str": "\u59e8"} -{"id": 53491, "token": "\u00e8\u0124\u00a2", "merges": "\u00e8\u0124 \u00a2", "raw_count": 6300556, "count": 6300556, "decode_str": "\u80a2"} -{"id": 54123, "token": "\u00e9\u0123\u0124", "merges": "\u00e9\u0123 \u0124", "raw_count": 6305390, "count": 6305390, "decode_str": "\u9042"} -{"id": 53407, "token": "\u00e7\u00bc\u00b8", "merges": "\u00e7\u00bc \u00b8", "raw_count": 6314360, "count": 6314360, "decode_str": "\u7f38"} -{"id": 53287, "token": "\u00e7\u00b3\u0141", "merges": "\u00e7\u00b3 \u0141", "raw_count": 6326349, "count": 6326349, "decode_str": "\u7cdf"} -{"id": 51325, "token": "\u00e5\u00a5\u00b4", "merges": "\u00e5\u00a5 \u00b4", "raw_count": 6327048, "count": 6327048, "decode_str": "\u5974"} -{"id": 52527, "token": "\u00e6\u00b3\u012e", "merges": "\u00e6\u00b3 \u012e", "raw_count": 6327267, "count": 6327267, "decode_str": "\u6ccc"} -{"id": 3121, "token": "76", "merges": "7 6", "raw_count": 5309982, "count": 6329208, "decode_str": "76"} -{"id": 1000, "token": "err", "merges": "er r", "raw_count": 846939, "count": 6332090, "decode_str": "err"} -{"id": 850, "token": "ient", "merges": "i ent", "raw_count": 275809, "count": 6340305, "decode_str": "ient"} -{"id": 53001, "token": "\u00e7\u013d\u00bc", "merges": "\u00e7\u013d \u00bc", "raw_count": 6342965, "count": 6342965, "decode_str": "\u76fc"} -{"id": 50784, "token": "\u00e5\u012a\u00b9", "merges": "\u00e5\u012a \u00b9", "raw_count": 6351658, "count": 6351658, "decode_str": "\u5239"} -{"id": 854, "token": "\u01208", "merges": "\u0120 8", "raw_count": 4625785, "count": 6351863, "decode_str": " 8"} -{"id": 50850, "token": "\u00e5\u012e\u013b", "merges": "\u00e5\u012e \u013b", "raw_count": 6367112, "count": 6367112, "decode_str": "\u5319"} -{"id": 53381, "token": "\u00e7\u00bc\u0128", "merges": "\u00e7\u00bc \u0128", "raw_count": 6368740, "count": 6368740, "decode_str": "\u7f06"} -{"id": 842, "token": "oint", "merges": "o int", "raw_count": 97313, "count": 6370192, "decode_str": "oint"} -{"id": 502, "token": "\u0120cl", "merges": "\u0120c l", "raw_count": 1057068, "count": 6376509, "decode_str": " cl"} -{"id": 620, "token": "ll", "merges": "l l", "raw_count": 814845, "count": 6379086, "decode_str": "ll"} -{"id": 53699, "token": "\u00e8\u00a1\u012f", "merges": "\u00e8\u00a1 \u012f", "raw_count": 6379398, "count": 6379398, "decode_str": "\u884d"} -{"id": 52289, "token": "\u00e6\u0142\u00aa", "merges": "\u00e6\u0142 \u00aa", "raw_count": 6380630, "count": 6380630, "decode_str": "\u682a"} -{"id": 458, "token": "\u0120le", "merges": "\u0120 le", "raw_count": 476137, "count": 6381016, "decode_str": " le"} -{"id": 54134, "token": "\u00e9\u0123\u00a3", "merges": "\u00e9\u0123 \u00a3", "raw_count": 6387160, "count": 6387160, "decode_str": "\u9063"} -{"id": 50429, "token": "\u00e4\u00b8\u00b8", "merges": "\u00e4\u00b8 \u00b8", "raw_count": 6387483, "count": 6387483, "decode_str": "\u4e38"} -{"id": 2697, "token": "OS", "merges": "O S", "raw_count": 3396591, "count": 6391061, "decode_str": "OS"} -{"id": 51210, "token": "\u00e5\u013f\u00aa", "merges": "\u00e5\u013f \u00aa", "raw_count": 6392352, "count": 6392352, "decode_str": "\u576a"} -{"id": 517, "token": "ound", "merges": "oun d", "raw_count": 170863, "count": 6405296, "decode_str": "ound"} -{"id": 51323, "token": "\u00e5\u00a5\u00a2", "merges": "\u00e5\u00a5 \u00a2", "raw_count": 6411662, "count": 6411662, "decode_str": "\u5962"} -{"id": 51726, "token": "\u00e6\u0123\u0143", "merges": "\u00e6\u0123 \u0143", "raw_count": 6416657, "count": 6416657, "decode_str": "\u606d"} -{"id": 51784, "token": "\u00e6\u0126\u0123", "merges": "\u00e6\u0126 \u0123", "raw_count": 6417435, "count": 6417435, "decode_str": "\u6101"} -{"id": 50852, "token": "\u00e5\u012e\u0142", "merges": "\u00e5\u012e \u0142", "raw_count": 6431594, "count": 6431594, "decode_str": "\u5320"} -{"id": 54045, "token": "\u00e8\u00be\u0132", "merges": "\u00e8\u00be \u0132", "raw_count": 6441445, "count": 6441445, "decode_str": "\u8f90"} -{"id": 2754, "token": "date", "merges": "d ate", "raw_count": 2104713, "count": 6443865, "decode_str": "date"} -{"id": 50844, "token": "\u00e5\u012e\u0128", "merges": "\u00e5\u012e \u0128", "raw_count": 6450799, "count": 6450799, "decode_str": "\u5306"} -{"id": 583, "token": "ose", "merges": "o se", "raw_count": 470509, "count": 6468589, "decode_str": "ose"} -{"id": 53179, "token": "\u00e7\u00a8\u00bb", "merges": "\u00e7\u00a8 \u00bb", "raw_count": 6470094, "count": 6470094, "decode_str": "\u7a3b"} -{"id": 3712, "token": "51", "merges": "5 1", "raw_count": 6012887, "count": 6483418, "decode_str": "51"} -{"id": 54394, "token": "\u00e9\u013e\u0140", "merges": "\u00e9\u013e \u0140", "raw_count": 6488717, "count": 6488717, "decode_str": "\u971e"} -{"id": 50905, "token": "\u00e5\u0130\u0137", "merges": "\u00e5\u0130 \u0137", "raw_count": 6495678, "count": 6495678, "decode_str": "\u5395"} -{"id": 51047, "token": "\u00e5\u0134\u00b8", "merges": "\u00e5\u0134 \u00b8", "raw_count": 6503746, "count": 6503746, "decode_str": "\u54b8"} -{"id": 52485, "token": "\u00e6\u00b1\u00aa", "merges": "\u00e6\u00b1 \u00aa", "raw_count": 6512313, "count": 6512313, "decode_str": "\u6c6a"} -{"id": 895, "token": "ix", "merges": "i x", "raw_count": 1490599, "count": 6517752, "decode_str": "ix"} -{"id": 928, "token": "iel", "merges": "i el", "raw_count": 189511, "count": 6521040, "decode_str": "iel"} -{"id": 52664, "token": "\u00e6\u00b8\u00a3", "merges": "\u00e6\u00b8 \u00a3", "raw_count": 6534303, "count": 6534303, "decode_str": "\u6e23"} -{"id": 52033, "token": "\u00e6\u0134\u0137", "merges": "\u00e6\u0134 \u0137", "raw_count": 6536272, "count": 6536272, "decode_str": "\u6495"} -{"id": 2511, "token": "89", "merges": "8 9", "raw_count": 4817108, "count": 6537454, "decode_str": "89"} -{"id": 52292, "token": "\u00e6\u0142\u00bd", "merges": "\u00e6\u0142 \u00bd", "raw_count": 6541726, "count": 6541726, "decode_str": "\u683d"} -{"id": 2787, "token": "79", "merges": "7 9", "raw_count": 4640023, "count": 6544965, "decode_str": "79"} -{"id": 52957, "token": "\u00e7\u013b\u013e", "merges": "\u00e7\u013b \u013e", "raw_count": 6552408, "count": 6552408, "decode_str": "\u765c"} -{"id": 5473, "token": "='", "merges": "= '", "raw_count": 6563400, "count": 6563400, "decode_str": "='"} -{"id": 53633, "token": "\u00e8\u012c\u00bd", "merges": "\u00e8\u012c \u00bd", "raw_count": 6573030, "count": 6573030, "decode_str": "\u82bd"} -{"id": 52237, "token": "\u00e6\u0140\u0137", "merges": "\u00e6\u0140 \u0137", "raw_count": 6573854, "count": 6573854, "decode_str": "\u6795"} -{"id": 1915, "token": "cur", "merges": "c ur", "raw_count": 1076426, "count": 6576671, "decode_str": "cur"} -{"id": 54109, "token": "\u00e9\u0122\u013d", "merges": "\u00e9\u0122 \u013d", "raw_count": 6576799, "count": 6576799, "decode_str": "\u901b"} -{"id": 1222, "token": "min", "merges": "m in", "raw_count": 3469338, "count": 6588804, "decode_str": "min"} -{"id": 50581, "token": "\u00e4\u00be\u0142", "merges": "\u00e4\u00be \u0142", "raw_count": 6614218, "count": 6614218, "decode_str": "\u4fa0"} -{"id": 2904, "token": "08", "merges": "0 8", "raw_count": 6448804, "count": 6620683, "decode_str": "08"} -{"id": 50841, "token": "\u00e5\u012d\u00bf", "merges": "\u00e5\u012d \u00bf", "raw_count": 6620733, "count": 6620733, "decode_str": "\u52ff"} -{"id": 50411, "token": "\u00e4\u00b8\u013a", "merges": "\u00e4\u00b8 \u013a", "raw_count": 6635026, "count": 6635026, "decode_str": "\u4e18"} -{"id": 2354, "token": "SE", "merges": "S E", "raw_count": 5194558, "count": 6638716, "decode_str": "SE"} -{"id": 53858, "token": "\u00e8\u00b0\u012c", "merges": "\u00e8\u00b0 \u012c", "raw_count": 6648524, "count": 6648524, "decode_str": "\u8c0a"} -{"id": 53714, "token": "\u00e8\u00a1\u00b7", "merges": "\u00e8\u00a1 \u00b7", "raw_count": 6676861, "count": 6676861, "decode_str": "\u8877"} -{"id": 1277, "token": "AR", "merges": "A R", "raw_count": 2811778, "count": 6686679, "decode_str": "AR"} -{"id": 53736, "token": "\u00e8\u00a3\u0137", "merges": "\u00e8\u00a3 \u0137", "raw_count": 6692982, "count": 6692982, "decode_str": "\u88d5"} -{"id": 52457, "token": "\u00e6\u00b0\u00a8", "merges": "\u00e6\u00b0 \u00a8", "raw_count": 6694796, "count": 6694796, "decode_str": "\u6c28"} -{"id": 367, "token": "\u0120P", "merges": "\u0120 P", "raw_count": 1250335, "count": 6704157, "decode_str": " P"} -{"id": 818, "token": "\u01207", "merges": "\u0120 7", "raw_count": 5048634, "count": 6706966, "decode_str": " 7"} -{"id": 2693, "token": "09", "merges": "0 9", "raw_count": 6280475, "count": 6728501, "decode_str": "09"} -{"id": 3583, "token": "52", "merges": "5 2", "raw_count": 6163638, "count": 6732338, "decode_str": "52"} -{"id": 51409, "token": "\u00e5\u00ae\u013b", "merges": "\u00e5\u00ae \u013b", "raw_count": 6732523, "count": 6732523, "decode_str": "\u5b99"} -{"id": 53395, "token": "\u00e7\u00bc\u0142", "merges": "\u00e7\u00bc \u0142", "raw_count": 6742355, "count": 6742355, "decode_str": "\u7f20"} -{"id": 53131, "token": "\u00e7\u00a5\u00b8", "merges": "\u00e7\u00a5 \u00b8", "raw_count": 6748196, "count": 6748196, "decode_str": "\u7978"} -{"id": 50987, "token": "\u00e5\u0132\u00be", "merges": "\u00e5\u0132 \u00be", "raw_count": 6755561, "count": 6755561, "decode_str": "\u543e"} -{"id": 1506, "token": "atch", "merges": "at ch", "raw_count": 353241, "count": 6768319, "decode_str": "atch"} -{"id": 52643, "token": "\u00e6\u00b7\u00ae", "merges": "\u00e6\u00b7 \u00ae", "raw_count": 6772053, "count": 6772053, "decode_str": "\u6dee"} -{"id": 9691, "token": "append", "merges": "app end", "raw_count": 6772812, "count": 6790817, "decode_str": "append"} -{"id": 10695, "token": "800", "merges": "8 00", "raw_count": 6794680, "count": 6794680, "decode_str": "800"} -{"id": 2391, "token": "....", "merges": ".. ..", "raw_count": 1996576, "count": 6798493, "decode_str": "...."} -{"id": 53700, "token": "\u00e8\u00a1\u0136", "merges": "\u00e8\u00a1 \u0136", "raw_count": 6800759, "count": 6800759, "decode_str": "\u8854"} -{"id": 50703, "token": "\u00e5\u0127\u00b9", "merges": "\u00e5\u0127 \u00b9", "raw_count": 6804774, "count": 6804774, "decode_str": "\u5179"} -{"id": 52084, "token": "\u00e6\u0137\u00b7", "merges": "\u00e6\u0137 \u00b7", "raw_count": 6814986, "count": 6814986, "decode_str": "\u6577"} -{"id": 51932, "token": "\u00e6\u012d\u00be", "merges": "\u00e6\u012d \u00be", "raw_count": 6816951, "count": 6816951, "decode_str": "\u62fe"} -{"id": 53977, "token": "\u00e8\u00b6\u0123", "merges": "\u00e8\u00b6 \u0123", "raw_count": 6831718, "count": 6831718, "decode_str": "\u8d81"} -{"id": 52151, "token": "\u00e6\u013b\u0125", "merges": "\u00e6\u013b \u0125", "raw_count": 6839831, "count": 6839831, "decode_str": "\u6643"} -{"id": 54349, "token": "\u00e9\u013c\u013b", "merges": "\u00e9\u013c \u013b", "raw_count": 6842372, "count": 6842372, "decode_str": "\u9699"} -{"id": 19396, "token": ",,", "merges": ", ,", "raw_count": 6844411, "count": 6844411, "decode_str": ",,"} -{"id": 656, "token": "ys", "merges": "y s", "raw_count": 992326, "count": 6845126, "decode_str": "ys"} -{"id": 21920, "token": "__(", "merges": "__ (", "raw_count": 6846349, "count": 6846349, "decode_str": "__("} -{"id": 52057, "token": "\u00e6\u0136\u0122", "merges": "\u00e6\u0136 \u0122", "raw_count": 6853038, "count": 6853038, "decode_str": "\u6500"} -{"id": 52268, "token": "\u00e6\u0141\u00af", "merges": "\u00e6\u0141 \u00af", "raw_count": 6856143, "count": 6856143, "decode_str": "\u67ef"} -{"id": 53329, "token": "\u00e7\u00ba\u00ba", "merges": "\u00e7\u00ba \u00ba", "raw_count": 6858337, "count": 6858337, "decode_str": "\u7eba"} -{"id": 3156, "token": "41", "merges": "4 1", "raw_count": 6365241, "count": 6858445, "decode_str": "41"} -{"id": 51952, "token": "\u00e6\u012e\u00aa", "merges": "\u00e6\u012e \u00aa", "raw_count": 6861111, "count": 6861111, "decode_str": "\u632a"} -{"id": 2597, "token": "87", "merges": "8 7", "raw_count": 4578984, "count": 6884553, "decode_str": "87"} -{"id": 2877, "token": "value", "merges": "val ue", "raw_count": 6877287, "count": 6886887, "decode_str": "value"} -{"id": 50407, "token": "\u00e4\u00b8\u0133", "merges": "\u00e4\u00b8 \u0133", "raw_count": 6918813, "count": 6918813, "decode_str": "\u4e11"} -{"id": 51840, "token": "\u00e6\u012b\u0136", "merges": "\u00e6\u012b \u0136", "raw_count": 6940364, "count": 6940364, "decode_str": "\u6254"} -{"id": 51430, "token": "\u00e5\u00af\u0124", "merges": "\u00e5\u00af \u0124", "raw_count": 6941746, "count": 6941746, "decode_str": "\u5bc2"} -{"id": 52526, "token": "\u00e6\u00b3\u012c", "merges": "\u00e6\u00b3 \u012c", "raw_count": 6943014, "count": 6943014, "decode_str": "\u6cca"} -{"id": 504, "token": "ide", "merges": "id e", "raw_count": 666813, "count": 6944061, "decode_str": "ide"} -{"id": 590, "token": "ory", "merges": "or y", "raw_count": 345397, "count": 6952745, "decode_str": "ory"} -{"id": 52239, "token": "\u00e6\u0140\u013c", "merges": "\u00e6\u0140 \u013c", "raw_count": 6958256, "count": 6958256, "decode_str": "\u679a"} -{"id": 2676, "token": "rr", "merges": "r r", "raw_count": 198012, "count": 6964210, "decode_str": "rr"} -{"id": 1163, "token": "\u0120:", "merges": "\u0120 :", "raw_count": 6778364, "count": 6971175, "decode_str": " :"} -{"id": 3547, "token": "72", "merges": "7 2", "raw_count": 6391273, "count": 7000306, "decode_str": "72"} -{"id": 437, "token": "ell", "merges": "el l", "raw_count": 811181, "count": 7001735, "decode_str": "ell"} -{"id": 52814, "token": "\u00e7\u0130\u00b2", "merges": "\u00e7\u0130 \u00b2", "raw_count": 7014291, "count": 7014291, "decode_str": "\u73b2"} -{"id": 3281, "token": "size", "merges": "s ize", "raw_count": 6992211, "count": 7018231, "decode_str": "size"} -{"id": 52858, "token": "\u00e7\u0132\u00b3", "merges": "\u00e7\u0132 \u00b3", "raw_count": 7021797, "count": 7021797, "decode_str": "\u7433"} -{"id": 52119, "token": "\u00e6\u0139\u00ac", "merges": "\u00e6\u0139 \u00ac", "raw_count": 7037889, "count": 7037889, "decode_str": "\u65ec"} -{"id": 2364, "token": "key", "merges": "ke y", "raw_count": 6599011, "count": 7052270, "decode_str": "key"} -{"id": 52133, "token": "\u00e6\u013a\u0131", "merges": "\u00e6\u013a \u0131", "raw_count": 7061647, "count": 7061647, "decode_str": "\u660f"} -{"id": 364, "token": "\u0120wh", "merges": "\u0120w h", "raw_count": 52135, "count": 7062511, "decode_str": " wh"} -{"id": 52580, "token": "\u00e6\u00b5\u0133", "merges": "\u00e6\u00b5 \u0133", "raw_count": 7070467, "count": 7070467, "decode_str": "\u6d51"} -{"id": 525, "token": "ign", "merges": "ig n", "raw_count": 314302, "count": 7073469, "decode_str": "ign"} -{"id": 540, "token": "\u0120int", "merges": "\u0120in t", "raw_count": 4273405, "count": 7074845, "decode_str": " int"} -{"id": 50817, "token": "\u00e5\u012c\u00ab", "merges": "\u00e5\u012c \u00ab", "raw_count": 7085948, "count": 7085948, "decode_str": "\u52ab"} -{"id": 53691, "token": "\u00e8\u013b\u00b9", "merges": "\u00e8\u013b \u00b9", "raw_count": 7087904, "count": 7087904, "decode_str": "\u8679"} -{"id": 52997, "token": "\u00e7\u013d\u00af", "merges": "\u00e7\u013d \u00af", "raw_count": 7098581, "count": 7098581, "decode_str": "\u76ef"} -{"id": 885, "token": "ise", "merges": "is e", "raw_count": 665035, "count": 7102844, "decode_str": "ise"} -{"id": 54414, "token": "\u00e9\u0141\u00a6", "merges": "\u00e9\u0141 \u00a6", "raw_count": 7112113, "count": 7112113, "decode_str": "\u97e6"} -{"id": 52048, "token": "\u00e6\u0135\u0127", "merges": "\u00e6\u0135 \u0127", "raw_count": 7112720, "count": 7112720, "decode_str": "\u64c5"} -{"id": 2691, "token": "86", "merges": "8 6", "raw_count": 5214922, "count": 7130637, "decode_str": "86"} -{"id": 1344, "token": "str", "merges": "st r", "raw_count": 6223651, "count": 7158371, "decode_str": "str"} -{"id": 50758, "token": "\u00e5\u0129\u00b8", "merges": "\u00e5\u0129 \u00b8", "raw_count": 7160353, "count": 7160353, "decode_str": "\u51f8"} -{"id": 53664, "token": "\u00e8\u0130\u0130", "merges": "\u00e8\u0130 \u0130", "raw_count": 7161523, "count": 7161523, "decode_str": "\u838e"} -{"id": 1213, "token": "\u0120str", "merges": "\u0120st r", "raw_count": 5613117, "count": 7166245, "decode_str": " str"} -{"id": 432, "token": "\u0120from", "merges": "\u0120f rom", "raw_count": 7176294, "count": 7176294, "decode_str": " from"} -{"id": 51046, "token": "\u00e5\u0134\u00b3", "merges": "\u00e5\u0134 \u00b3", "raw_count": 7181352, "count": 7181352, "decode_str": "\u54b3"} -{"id": 603, "token": "ire", "merges": "i re", "raw_count": 542320, "count": 7185344, "decode_str": "ire"} -{"id": 51345, "token": "\u00e5\u00a6\u00a8", "merges": "\u00e5\u00a6 \u00a8", "raw_count": 7208750, "count": 7208750, "decode_str": "\u59a8"} -{"id": 52699, "token": "\u00e6\u00bc\u0142", "merges": "\u00e6\u00bc \u0142", "raw_count": 7238558, "count": 7238558, "decode_str": "\u6f20"} -{"id": 1042, "token": "IN", "merges": "I N", "raw_count": 1752323, "count": 7244861, "decode_str": "IN"} -{"id": 52795, "token": "\u00e7\u012c\u00ac", "merges": "\u00e7\u012c \u00ac", "raw_count": 7254610, "count": 7254610, "decode_str": "\u72ac"} -{"id": 51948, "token": "\u00e6\u012e\u00a3", "merges": "\u00e6\u012e \u00a3", "raw_count": 7258025, "count": 7258025, "decode_str": "\u6323"} -{"id": 456, "token": "ated", "merges": "at ed", "raw_count": 823376, "count": 7262121, "decode_str": "ated"} -{"id": 51797, "token": "\u00e6\u0127\u012e", "merges": "\u00e6\u0127 \u012e", "raw_count": 7270392, "count": 7270392, "decode_str": "\u614c"} -{"id": 560, "token": "ress", "merges": "res s", "raw_count": 268834, "count": 7270899, "decode_str": "ress"} -{"id": 50745, "token": "\u00e5\u0129\u0133", "merges": "\u00e5\u0129 \u0133", "raw_count": 7282074, "count": 7282074, "decode_str": "\u51d1"} -{"id": 991, "token": "ax", "merges": "a x", "raw_count": 1657530, "count": 7283047, "decode_str": "ax"} -{"id": 50585, "token": "\u00e4\u00be\u00a6", "merges": "\u00e4\u00be \u00a6", "raw_count": 7288724, "count": 7288724, "decode_str": "\u4fa6"} -{"id": 1838, "token": "ID", "merges": "I D", "raw_count": 5737749, "count": 7311636, "decode_str": "ID"} -{"id": 52327, "token": "\u00e6\u00a3\u013c", "merges": "\u00e6\u00a3 \u013c", "raw_count": 7341429, "count": 7341429, "decode_str": "\u68da"} -{"id": 10477, "token": ":(", "merges": ": (", "raw_count": 7359967, "count": 7359967, "decode_str": ":("} -{"id": 51630, "token": "\u00e5\u00bd\u0143", "merges": "\u00e5\u00bd \u0143", "raw_count": 7360471, "count": 7360471, "decode_str": "\u5f6d"} -{"id": 52379, "token": "\u00e6\u00a9\u00a1", "merges": "\u00e6\u00a9 \u00a1", "raw_count": 7370813, "count": 7370813, "decode_str": "\u6a61"} -{"id": 4537, "token": "user", "merges": "us er", "raw_count": 6177726, "count": 7387082, "decode_str": "user"} -{"id": 50494, "token": "\u00e4\u00bb\u0129", "merges": "\u00e4\u00bb \u0129", "raw_count": 7394014, "count": 7394014, "decode_str": "\u4ec7"} -{"id": 52220, "token": "\u00e6\u013f\u0142", "merges": "\u00e6\u013f \u0142", "raw_count": 7400859, "count": 7400859, "decode_str": "\u6760"} -{"id": 54150, "token": "\u00e9\u0124\u0135", "merges": "\u00e9\u0124 \u0135", "raw_count": 7402368, "count": 7402368, "decode_str": "\u9093"} -{"id": 33, "token": "@", "merges": "NULL", "raw_count": 5578165, "count": 7404568, "decode_str": "@"} -{"id": 3079, "token": "43", "merges": "4 3", "raw_count": 6895308, "count": 7409644, "decode_str": "43"} -{"id": 51792, "token": "\u00e6\u0126\u00a4", "merges": "\u00e6\u0126 \u00a4", "raw_count": 7421941, "count": 7421941, "decode_str": "\u6124"} -{"id": 54023, "token": "\u00e8\u00bd\u00a9", "merges": "\u00e8\u00bd \u00a9", "raw_count": 7423994, "count": 7423994, "decode_str": "\u8f69"} -{"id": 51696, "token": "\u00e6\u0122\u0138", "merges": "\u00e6\u0122 \u0138", "raw_count": 7428003, "count": 7428003, "decode_str": "\u6016"} -{"id": 329, "token": "\u0120A", "merges": "\u0120 A", "raw_count": 1732958, "count": 7434994, "decode_str": " A"} -{"id": 3208, "token": "56", "merges": "5 6", "raw_count": 6438588, "count": 7463009, "decode_str": "56"} -{"id": 2357, "token": "77", "merges": "7 7", "raw_count": 5038336, "count": 7474256, "decode_str": "77"} -{"id": 52171, "token": "\u00e6\u013b\u00b4", "merges": "\u00e6\u013b \u00b4", "raw_count": 7474891, "count": 7474891, "decode_str": "\u6674"} -{"id": 713, "token": "ple", "merges": "p le", "raw_count": 216924, "count": 7476283, "decode_str": "ple"} -{"id": 3011, "token": "57", "merges": "5 7", "raw_count": 6098396, "count": 7480429, "decode_str": "57"} -{"id": 947, "token": "ER", "merges": "E R", "raw_count": 2532191, "count": 7481301, "decode_str": "ER"} -{"id": 18137, "token": "APP", "merges": "AP P", "raw_count": 7484650, "count": 7484650, "decode_str": "APP"} -{"id": 50995, "token": "\u00e5\u0133\u0132", "merges": "\u00e5\u0133 \u0132", "raw_count": 7493395, "count": 7493395, "decode_str": "\u5450"} -{"id": 53343, "token": "\u00e7\u00bb\u0134", "merges": "\u00e7\u00bb \u0134", "raw_count": 7502843, "count": 7502843, "decode_str": "\u7ed2"} -{"id": 14850, "token": "():", "merges": "() :", "raw_count": 7504072, "count": 7504072, "decode_str": "():"} -{"id": 519, "token": "\u0120ad", "merges": "\u0120a d", "raw_count": 318147, "count": 7507604, "decode_str": " ad"} -{"id": 539, "token": "ition", "merges": "it ion", "raw_count": 177896, "count": 7513656, "decode_str": "ition"} -{"id": 51529, "token": "\u00e5\u00b8\u0138", "merges": "\u00e5\u00b8 \u0138", "raw_count": 7518004, "count": 7518004, "decode_str": "\u5e16"} -{"id": 51773, "token": "\u00e6\u0125\u00a9", "merges": "\u00e6\u0125 \u00a9", "raw_count": 7531777, "count": 7531777, "decode_str": "\u60e9"} -{"id": 53710, "token": "\u00e8\u00a1\u00ac", "merges": "\u00e8\u00a1 \u00ac", "raw_count": 7533132, "count": 7533132, "decode_str": "\u886c"} -{"id": 52579, "token": "\u00e6\u00b5\u0131", "merges": "\u00e6\u00b5 \u0131", "raw_count": 7564801, "count": 7564801, "decode_str": "\u6d4f"} -{"id": 1194, "token": "AT", "merges": "A T", "raw_count": 3463654, "count": 7565258, "decode_str": "AT"} -{"id": 53624, "token": "\u00e8\u012c\u00ac", "merges": "\u00e8\u012c \u00ac", "raw_count": 7579480, "count": 7579480, "decode_str": "\u82ac"} -{"id": 52158, "token": "\u00e6\u013b\u0137", "merges": "\u00e6\u013b \u0137", "raw_count": 7581255, "count": 7581255, "decode_str": "\u6655"} -{"id": 359, "token": "\u0120we", "merges": "\u0120w e", "raw_count": 3262754, "count": 7590484, "decode_str": " we"} -{"id": 403, "token": "\u0120are", "merges": "\u0120a re", "raw_count": 6365596, "count": 7594469, "decode_str": " are"} -{"id": 50682, "token": "\u00e5\u0127\u0128", "merges": "\u00e5\u0127 \u0128", "raw_count": 7596394, "count": 7596394, "decode_str": "\u5146"} -{"id": 719, "token": "cre", "merges": "c re", "raw_count": 161135, "count": 7601493, "decode_str": "cre"} -{"id": 53229, "token": "\u00e7\u0143\u013d", "merges": "\u00e7\u0143 \u013d", "raw_count": 7602591, "count": 7602591, "decode_str": "\u7b5b"} -{"id": 54200, "token": "\u00e9\u0127\u00ac", "merges": "\u00e9\u0127 \u00ac", "raw_count": 7606992, "count": 7606992, "decode_str": "\u916c"} -{"id": 53584, "token": "\u00e8\u012a\u0141", "merges": "\u00e8\u012a \u0141", "raw_count": 7617348, "count": 7617348, "decode_str": "\u821f"} -{"id": 1433, "token": "IT", "merges": "I T", "raw_count": 5797669, "count": 7618334, "decode_str": "IT"} -{"id": 449, "token": ".\"", "merges": ". \"", "raw_count": 2832468, "count": 7623432, "decode_str": ".\""} -{"id": 53322, "token": "\u00e7\u00ba\u00b2", "merges": "\u00e7\u00ba \u00b2", "raw_count": 7625200, "count": 7625200, "decode_str": "\u7eb2"} -{"id": 52429, "token": "\u00e6\u00af\u0127", "merges": "\u00e6\u00af \u0127", "raw_count": 7625226, "count": 7625226, "decode_str": "\u6bc5"} -{"id": 664, "token": "we", "merges": "w e", "raw_count": 2296680, "count": 7634637, "decode_str": "we"} -{"id": 52671, "token": "\u00e6\u00b8\u00b4", "merges": "\u00e6\u00b8 \u00b4", "raw_count": 7642647, "count": 7642647, "decode_str": "\u6e34"} -{"id": 53184, "token": "\u00e7\u00a9\u0128", "merges": "\u00e7\u00a9 \u0128", "raw_count": 7645316, "count": 7645316, "decode_str": "\u7a46"} -{"id": 52511, "token": "\u00e6\u00b2\u00aa", "merges": "\u00e6\u00b2 \u00aa", "raw_count": 7648299, "count": 7648299, "decode_str": "\u6caa"} -{"id": 53573, "token": "\u00e8\u012a\u012e", "merges": "\u00e8\u012a \u012e", "raw_count": 7658491, "count": 7658491, "decode_str": "\u820c"} -{"id": 51445, "token": "\u00e5\u00af\u00a8", "merges": "\u00e5\u00af \u00a8", "raw_count": 7659420, "count": 7659420, "decode_str": "\u5be8"} -{"id": 518, "token": "ak", "merges": "a k", "raw_count": 1504273, "count": 7683875, "decode_str": "ak"} -{"id": 28306, "token": "5000", "merges": "5 000", "raw_count": 7692281, "count": 7692281, "decode_str": "5000"} -{"id": 552, "token": "ary", "merges": "ar y", "raw_count": 721259, "count": 7693696, "decode_str": "ary"} -{"id": 580, "token": "av", "merges": "a v", "raw_count": 1461288, "count": 7701545, "decode_str": "av"} -{"id": 54016, "token": "\u00e8\u00ba\u00b2", "merges": "\u00e8\u00ba \u00b2", "raw_count": 7706537, "count": 7706537, "decode_str": "\u8eb2"} -{"id": 546, "token": "\u0120en", "merges": "\u0120 en", "raw_count": 401849, "count": 7709047, "decode_str": " en"} -{"id": 51118, "token": "\u00e5\u0138\u0136", "merges": "\u00e5\u0138 \u0136", "raw_count": 7716447, "count": 7716447, "decode_str": "\u5594"} -{"id": 51999, "token": "\u00e6\u0130\u00a9", "merges": "\u00e6\u0130 \u00a9", "raw_count": 7727235, "count": 7727235, "decode_str": "\u63a9"} -{"id": 50827, "token": "\u00e5\u012d\u0125", "merges": "\u00e5\u012d \u0125", "raw_count": 7747429, "count": 7747429, "decode_str": "\u52c3"} -{"id": 3046, "token": "59", "merges": "5 9", "raw_count": 6255774, "count": 7756897, "decode_str": "59"} -{"id": 621, "token": "ions", "merges": "ion s", "raw_count": 412996, "count": 7757892, "decode_str": "ions"} -{"id": 7857, "token": "2009", "merges": "200 9", "raw_count": 7759902, "count": 7759902, "decode_str": "2009"} -{"id": 50688, "token": "\u00e5\u0127\u0136", "merges": "\u00e5\u0127 \u0136", "raw_count": 7763456, "count": 7763456, "decode_str": "\u5154"} -{"id": 3680, "token": "58", "merges": "5 8", "raw_count": 6839098, "count": 7808083, "decode_str": "58"} -{"id": 2290, "token": "Tr", "merges": "T r", "raw_count": 581266, "count": 7826666, "decode_str": "Tr"} -{"id": 54114, "token": "\u00e9\u0122\u00a2", "merges": "\u00e9\u0122 \u00a2", "raw_count": 7828634, "count": 7828634, "decode_str": "\u9022"} -{"id": 54017, "token": "\u00e8\u00ba\u00ba", "merges": "\u00e8\u00ba \u00ba", "raw_count": 7837365, "count": 7837365, "decode_str": "\u8eba"} -{"id": 51528, "token": "\u00e5\u00b8\u0137", "merges": "\u00e5\u00b8 \u0137", "raw_count": 7842309, "count": 7842309, "decode_str": "\u5e15"} -{"id": 51585, "token": "\u00e5\u00bb\u012c", "merges": "\u00e5\u00bb \u012c", "raw_count": 7846983, "count": 7846983, "decode_str": "\u5eca"} -{"id": 53158, "token": "\u00e7\u00a7\u00a9", "merges": "\u00e7\u00a7 \u00a9", "raw_count": 7851473, "count": 7851473, "decode_str": "\u79e9"} -{"id": 652, "token": "vel", "merges": "v el", "raw_count": 487744, "count": 7860894, "decode_str": "vel"} -{"id": 53924, "token": "\u00e8\u00b4\u00aa", "merges": "\u00e8\u00b4 \u00aa", "raw_count": 7871882, "count": 7871882, "decode_str": "\u8d2a"} -{"id": 51277, "token": "\u00e5\u00a3\u00a4", "merges": "\u00e5\u00a3 \u00a4", "raw_count": 7876598, "count": 7876598, "decode_str": "\u58e4"} -{"id": 52607, "token": "\u00e6\u00b6\u013d", "merges": "\u00e6\u00b6 \u013d", "raw_count": 7885435, "count": 7885435, "decode_str": "\u6d9b"} -{"id": 52512, "token": "\u00e6\u00b2\u00ab", "merges": "\u00e6\u00b2 \u00ab", "raw_count": 7899930, "count": 7899930, "decode_str": "\u6cab"} -{"id": 1376, "token": "oad", "merges": "o ad", "raw_count": 219339, "count": 7906098, "decode_str": "oad"} -{"id": 368, "token": "\u0120you", "merges": "\u0120y ou", "raw_count": 5004849, "count": 7908161, "decode_str": " you"} -{"id": 15440, "token": "\u00e2\u0122\u013f)", "merges": "\u00e2\u0122\u013f )", "raw_count": 7922555, "count": 7922555, "decode_str": "\u201d)"} -{"id": 52999, "token": "\u00e7\u013d\u00b2", "merges": "\u00e7\u013d \u00b2", "raw_count": 7934392, "count": 7934392, "decode_str": "\u76f2"} -{"id": 50777, "token": "\u00e5\u012a\u0142", "merges": "\u00e5\u012a \u0142", "raw_count": 7937482, "count": 7937482, "decode_str": "\u5220"} -{"id": 793, "token": "ps", "merges": "p s", "raw_count": 3757000, "count": 7939018, "decode_str": "ps"} -{"id": 53186, "token": "\u00e7\u00a9\u00b4", "merges": "\u00e7\u00a9 \u00b4", "raw_count": 7957156, "count": 7957156, "decode_str": "\u7a74"} -{"id": 53220, "token": "\u00e7\u00ac\u00bc", "merges": "\u00e7\u00ac \u00bc", "raw_count": 7962125, "count": 7962125, "decode_str": "\u7b3c"} -{"id": 53717, "token": "\u00e8\u00a2\u0123", "merges": "\u00e8\u00a2 \u0123", "raw_count": 7964513, "count": 7964513, "decode_str": "\u8881"} -{"id": 50761, "token": "\u00e5\u0129\u00bd", "merges": "\u00e5\u0129 \u00bd", "raw_count": 7967916, "count": 7967916, "decode_str": "\u51fd"} -{"id": 387, "token": "\u0120at", "merges": "\u0120a t", "raw_count": 5005666, "count": 7971604, "decode_str": " at"} -{"id": 52621, "token": "\u00e6\u00b6\u00af", "merges": "\u00e6\u00b6 \u00af", "raw_count": 7983071, "count": 7983071, "decode_str": "\u6daf"} -{"id": 50878, "token": "\u00e5\u012f\u013e", "merges": "\u00e5\u012f \u013e", "raw_count": 7983818, "count": 7983818, "decode_str": "\u535c"} -{"id": 140, "token": "\u00d0", "merges": "NULL", "raw_count": 59341, "count": 7997604, "decode_str": "\ufffd"} -{"id": 50792, "token": "\u00e5\u012b\u012c", "merges": "\u00e5\u012b \u012c", "raw_count": 8003875, "count": 8003875, "decode_str": "\u524a"} -{"id": 4478, "token": "init", "merges": "in it", "raw_count": 7200643, "count": 8043063, "decode_str": "init"} -{"id": 1686, "token": "ml", "merges": "m l", "raw_count": 4798666, "count": 8045695, "decode_str": "ml"} -{"id": 52050, "token": "\u00e6\u0135\u0130", "merges": "\u00e6\u0135 \u0130", "raw_count": 8052335, "count": 8052335, "decode_str": "\u64ce"} -{"id": 2950, "token": "46", "merges": "4 6", "raw_count": 6852724, "count": 8069985, "decode_str": "46"} -{"id": 998, "token": "St", "merges": "S t", "raw_count": 1415389, "count": 8075333, "decode_str": "St"} -{"id": 645, "token": "ook", "merges": "o ok", "raw_count": 155995, "count": 8075558, "decode_str": "ook"} -{"id": 821, "token": "\u0120val", "merges": "\u0120v al", "raw_count": 999762, "count": 8085443, "decode_str": " val"} -{"id": 51420, "token": "\u00e5\u00ae\u00aa", "merges": "\u00e5\u00ae \u00aa", "raw_count": 8093094, "count": 8093094, "decode_str": "\u5baa"} -{"id": 505, "token": "ast", "merges": "as t", "raw_count": 1271652, "count": 8117201, "decode_str": "ast"} -{"id": 51284, "token": "\u00e5\u00a3\u00b6", "merges": "\u00e5\u00a3 \u00b6", "raw_count": 8132568, "count": 8132568, "decode_str": "\u58f6"} -{"id": 755, "token": "\u0120get", "merges": "\u0120g et", "raw_count": 7900639, "count": 8134618, "decode_str": " get"} -{"id": 2251, "token": "67", "merges": "6 7", "raw_count": 5646496, "count": 8136105, "decode_str": "67"} -{"id": 26990, "token": "3000", "merges": "3 000", "raw_count": 8137643, "count": 8137643, "decode_str": "3000"} -{"id": 52280, "token": "\u00e6\u0142\u012d", "merges": "\u00e6\u0142 \u012d", "raw_count": 8140701, "count": 8140701, "decode_str": "\u680b"} -{"id": 52543, "token": "\u00e6\u00b3\u00b3", "merges": "\u00e6\u00b3 \u00b3", "raw_count": 8141880, "count": 8141880, "decode_str": "\u6cf3"} -{"id": 439, "token": "\u0120sh", "merges": "\u0120s h", "raw_count": 537420, "count": 8147691, "decode_str": " sh"} -{"id": 50726, "token": "\u00e5\u0128\u00af", "merges": "\u00e5\u0128 \u00af", "raw_count": 8150543, "count": 8150543, "decode_str": "\u51af"} -{"id": 50482, "token": "\u00e4\u00ba\u0143", "merges": "\u00e4\u00ba \u0143", "raw_count": 8172566, "count": 8172566, "decode_str": "\u4ead"} -{"id": 50663, "token": "\u00e5\u0124\u00bb", "merges": "\u00e5\u0124 \u00bb", "raw_count": 8174420, "count": 8174420, "decode_str": "\u50bb"} -{"id": 53128, "token": "\u00e7\u00a5\u0143", "merges": "\u00e7\u00a5 \u0143", "raw_count": 8183482, "count": 8183482, "decode_str": "\u796d"} -{"id": 1267, "token": "ST", "merges": "S T", "raw_count": 3627709, "count": 8183509, "decode_str": "ST"} -{"id": 514, "token": "act", "merges": "a ct", "raw_count": 662462, "count": 8186911, "decode_str": "act"} -{"id": 2090, "token": "69", "merges": "6 9", "raw_count": 5889131, "count": 8202578, "decode_str": "69"} -{"id": 52936, "token": "\u00e7\u0139\u013a", "merges": "\u00e7\u0139 \u013a", "raw_count": 8224469, "count": 8224469, "decode_str": "\u75d8"} -{"id": 53321, "token": "\u00e7\u00ba\u00b1", "merges": "\u00e7\u00ba \u00b1", "raw_count": 8226697, "count": 8226697, "decode_str": "\u7eb1"} -{"id": 561, "token": "ens", "merges": "en s", "raw_count": 880533, "count": 8228732, "decode_str": "ens"} -{"id": 10487, "token": "600", "merges": "6 00", "raw_count": 8244959, "count": 8244959, "decode_str": "600"} -{"id": 51602, "token": "\u00e5\u00bc\u013a", "merges": "\u00e5\u00bc \u013a", "raw_count": 8258738, "count": 8258738, "decode_str": "\u5f18"} -{"id": 52682, "token": "\u00e6\u00ba\u00a2", "merges": "\u00e6\u00ba \u00a2", "raw_count": 8272033, "count": 8272033, "decode_str": "\u6ea2"} -{"id": 407, "token": "\u0120by", "merges": "\u0120b y", "raw_count": 7650256, "count": 8291082, "decode_str": " by"} -{"id": 52946, "token": "\u00e7\u0139\u00ab", "merges": "\u00e7\u0139 \u00ab", "raw_count": 8296742, "count": 8296742, "decode_str": "\u75eb"} -{"id": 465, "token": "\u0120k", "merges": "\u0120 k", "raw_count": 3664052, "count": 8304678, "decode_str": " k"} -{"id": 8012, "token": "2008", "merges": "200 8", "raw_count": 8312335, "count": 8312335, "decode_str": "2008"} -{"id": 624, "token": "rent", "merges": "ren t", "raw_count": 285348, "count": 8321495, "decode_str": "rent"} -{"id": 51424, "token": "\u00e5\u00ae\u00b4", "merges": "\u00e5\u00ae \u00b4", "raw_count": 8341581, "count": 8341581, "decode_str": "\u5bb4"} -{"id": 52254, "token": "\u00e6\u0141\u0131", "merges": "\u00e6\u0141 \u0131", "raw_count": 8347236, "count": 8347236, "decode_str": "\u67cf"} -{"id": 50514, "token": "\u00e4\u00bb\u00b2", "merges": "\u00e4\u00bb \u00b2", "raw_count": 8350398, "count": 8350398, "decode_str": "\u4ef2"} -{"id": 53367, "token": "\u00e7\u00bb\u00b3", "merges": "\u00e7\u00bb \u00b3", "raw_count": 8357360, "count": 8357360, "decode_str": "\u7ef3"} -{"id": 2945, "token": "42", "merges": "4 2", "raw_count": 7784929, "count": 8359993, "decode_str": "42"} -{"id": 614, "token": "ite", "merges": "it e", "raw_count": 1041219, "count": 8360131, "decode_str": "ite"} -{"id": 777, "token": "ck", "merges": "c k", "raw_count": 681630, "count": 8378029, "decode_str": "ck"} -{"id": 1026, "token": "sc", "merges": "s c", "raw_count": 1651829, "count": 8378467, "decode_str": "sc"} -{"id": 53738, "token": "\u00e8\u00a3\u013b", "merges": "\u00e8\u00a3 \u013b", "raw_count": 8378503, "count": 8378503, "decode_str": "\u88d9"} -{"id": 2504, "token": "47", "merges": "4 7", "raw_count": 6637259, "count": 8382143, "decode_str": "47"} -{"id": 51291, "token": "\u00e5\u00a4\u0137", "merges": "\u00e5\u00a4 \u0137", "raw_count": 8383168, "count": 8383168, "decode_str": "\u5915"} -{"id": 54102, "token": "\u00e9\u0122\u012c", "merges": "\u00e9\u0122 \u012c", "raw_count": 8407107, "count": 8407107, "decode_str": "\u900a"} -{"id": 53904, "token": "\u00e8\u00b1\u00ab", "merges": "\u00e8\u00b1 \u00ab", "raw_count": 8411969, "count": 8411969, "decode_str": "\u8c6b"} -{"id": 53097, "token": "\u00e7\u00a2\u00a7", "merges": "\u00e7\u00a2 \u00a7", "raw_count": 8435965, "count": 8435965, "decode_str": "\u78a7"} -{"id": 52082, "token": "\u00e6\u0137\u00b2", "merges": "\u00e6\u0137 \u00b2", "raw_count": 8438767, "count": 8438767, "decode_str": "\u6572"} -{"id": 2307, "token": "mod", "merges": "m od", "raw_count": 1034902, "count": 8451076, "decode_str": "mod"} -{"id": 571, "token": "ia", "merges": "i a", "raw_count": 3601972, "count": 8463280, "decode_str": "ia"} -{"id": 54233, "token": "\u00e9\u0136\u00a1", "merges": "\u00e9\u0136 \u00a1", "raw_count": 8469035, "count": 8469035, "decode_str": "\u9521"} -{"id": 1911, "token": "add", "merges": "ad d", "raw_count": 5595499, "count": 8475790, "decode_str": "add"} -{"id": 322, "token": "\u0120S", "merges": "\u0120 S", "raw_count": 1380910, "count": 8477912, "decode_str": " S"} -{"id": 50811, "token": "\u00e5\u012c\u013f", "merges": "\u00e5\u012c \u013f", "raw_count": 8482356, "count": 8482356, "decode_str": "\u529d"} -{"id": 54324, "token": "\u00e9\u013b\u012e", "merges": "\u00e9\u013b \u012e", "raw_count": 8500873, "count": 8500873, "decode_str": "\u964c"} -{"id": 52626, "token": "\u00e6\u00b7\u0122", "merges": "\u00e6\u00b7 \u0122", "raw_count": 8510780, "count": 8510780, "decode_str": "\u6dc0"} -{"id": 50781, "token": "\u00e5\u012a\u00ae", "merges": "\u00e5\u012a \u00ae", "raw_count": 8511398, "count": 8511398, "decode_str": "\u522e"} -{"id": 487, "token": "ib", "merges": "i b", "raw_count": 1681176, "count": 8514594, "decode_str": "ib"} -{"id": 50524, "token": "\u00e4\u00bc\u0132", "merges": "\u00e4\u00bc \u0132", "raw_count": 8536041, "count": 8536041, "decode_str": "\u4f10"} -{"id": 53802, "token": "\u00e8\u00ae\u00bc", "merges": "\u00e8\u00ae \u00bc", "raw_count": 8561026, "count": 8561026, "decode_str": "\u8bbc"} -{"id": 51304, "token": "\u00e5\u00a4\u00b8", "merges": "\u00e5\u00a4 \u00b8", "raw_count": 8572656, "count": 8572656, "decode_str": "\u5938"} -{"id": 549, "token": "\u0120ar", "merges": "\u0120a r", "raw_count": 592966, "count": 8591520, "decode_str": " ar"} -{"id": 65, "token": "`", "merges": "NULL", "raw_count": 2089319, "count": 8592317, "decode_str": "`"} -{"id": 52658, "token": "\u00e6\u00b8\u0136", "merges": "\u00e6\u00b8 \u0136", "raw_count": 8597384, "count": 8597384, "decode_str": "\u6e14"} -{"id": 50904, "token": "\u00e5\u0130\u012e", "merges": "\u00e5\u0130 \u012e", "raw_count": 8600418, "count": 8600418, "decode_str": "\u538c"} -{"id": 53614, "token": "\u00e8\u012c\u0134", "merges": "\u00e8\u012c \u0134", "raw_count": 8607862, "count": 8607862, "decode_str": "\u8292"} -{"id": 606, "token": "ang", "merges": "an g", "raw_count": 2088790, "count": 8626975, "decode_str": "ang"} -{"id": 15844, "token": "!!!", "merges": "!! !", "raw_count": 8632410, "count": 8632410, "decode_str": "!!!"} -{"id": 54138, "token": "\u00e9\u0123\u00ae", "merges": "\u00e9\u0123 \u00ae", "raw_count": 8648960, "count": 8648960, "decode_str": "\u906e"} -{"id": 2526, "token": "66", "merges": "6 6", "raw_count": 6703038, "count": 8660886, "decode_str": "66"} -{"id": 54611, "token": "\u00ef\u00bc\u013e", "merges": "\u00ef\u00bc \u013e", "raw_count": 8665764, "count": 8665764, "decode_str": " "} -{"id": 50925, "token": "\u00e5\u0131\u013b", "merges": "\u00e5\u0131 \u013b", "raw_count": 8669728, "count": 8669728, "decode_str": "\u53d9"} -{"id": 916, "token": "cept", "merges": "ce pt", "raw_count": 188878, "count": 8685488, "decode_str": "cept"} -{"id": 51385, "token": "\u00e5\u0143\u013f", "merges": "\u00e5\u0143 \u013f", "raw_count": 8704809, "count": 8704809, "decode_str": "\u5b5d"} -{"id": 52201, "token": "\u00e6\u013e\u00b4", "merges": "\u00e6\u013e \u00b4", "raw_count": 8707788, "count": 8707788, "decode_str": "\u6734"} -{"id": 926, "token": "fig", "merges": "f ig", "raw_count": 508571, "count": 8710087, "decode_str": "fig"} -{"id": 53663, "token": "\u00e8\u0130\u012b", "merges": "\u00e8\u0130 \u012b", "raw_count": 8731231, "count": 8731231, "decode_str": "\u8389"} -{"id": 53941, "token": "\u00e8\u00b4\u00be", "merges": "\u00e8\u00b4 \u00be", "raw_count": 8732342, "count": 8732342, "decode_str": "\u8d3e"} -{"id": 461, "token": "ust", "merges": "u st", "raw_count": 532312, "count": 8740207, "decode_str": "ust"} -{"id": 53694, "token": "\u00e8\u013b\u00be", "merges": "\u00e8\u013b \u00be", "raw_count": 8766233, "count": 8766233, "decode_str": "\u867e"} -{"id": 569, "token": "ations", "merges": "ation s", "raw_count": 1235721, "count": 8780678, "decode_str": "ations"} -{"id": 7271, "token": "else", "merges": "el se", "raw_count": 8783465, "count": 8783465, "decode_str": "else"} -{"id": 558, "token": ");", "merges": ") ;", "raw_count": 8106053, "count": 8807679, "decode_str": ");"} -{"id": 54028, "token": "\u00e8\u00bd\u00b0", "merges": "\u00e8\u00bd \u00b0", "raw_count": 8807837, "count": 8807837, "decode_str": "\u8f70"} -{"id": 936, "token": "to", "merges": "t o", "raw_count": 7548728, "count": 8809215, "decode_str": "to"} -{"id": 52961, "token": "\u00e7\u013b\u00ab", "merges": "\u00e7\u013b \u00ab", "raw_count": 8841510, "count": 8841510, "decode_str": "\u766b"} -{"id": 52554, "token": "\u00e6\u00b4\u0134", "merges": "\u00e6\u00b4 \u0134", "raw_count": 8875339, "count": 8875339, "decode_str": "\u6d12"} -{"id": 2018, "token": "alse", "merges": "al se", "raw_count": 7513, "count": 8879802, "decode_str": "alse"} -{"id": 1381, "token": "\":", "merges": "\" :", "raw_count": 8526301, "count": 8892574, "decode_str": "\":"} -{"id": 330, "token": "\u0120C", "merges": "\u0120 C", "raw_count": 1964604, "count": 8971138, "decode_str": " C"} -{"id": 50840, "token": "\u00e5\u012d\u00be", "merges": "\u00e5\u012d \u00be", "raw_count": 8977719, "count": 8977719, "decode_str": "\u52fe"} -{"id": 53639, "token": "\u00e8\u012d\u012f", "merges": "\u00e8\u012d \u012f", "raw_count": 8998385, "count": 8998385, "decode_str": "\u82cd"} -{"id": 516, "token": "\u0120im", "merges": "\u0120 im", "raw_count": 416940, "count": 8999578, "decode_str": " im"} -{"id": 50662, "token": "\u00e5\u0124\u00b2", "merges": "\u00e5\u0124 \u00b2", "raw_count": 9012135, "count": 9012135, "decode_str": "\u50b2"} -{"id": 51109, "token": "\u00e5\u0138\u0124", "merges": "\u00e5\u0138 \u0124", "raw_count": 9018408, "count": 9018408, "decode_str": "\u5582"} -{"id": 51569, "token": "\u00e5\u00ba\u013b", "merges": "\u00e5\u00ba \u013b", "raw_count": 9025680, "count": 9025680, "decode_str": "\u5e99"} -{"id": 51852, "token": "\u00e6\u012b\u00ae", "merges": "\u00e6\u012b \u00ae", "raw_count": 9032709, "count": 9032709, "decode_str": "\u626e"} -{"id": 53725, "token": "\u00e8\u00a2\u0138", "merges": "\u00e8\u00a2 \u0138", "raw_count": 9046809, "count": 9046809, "decode_str": "\u8896"} -{"id": 52127, "token": "\u00e6\u013a\u0124", "merges": "\u00e6\u013a \u0124", "raw_count": 9051257, "count": 9051257, "decode_str": "\u6602"} -{"id": 51771, "token": "\u00e6\u0125\u00a7", "merges": "\u00e6\u0125 \u00a7", "raw_count": 9053521, "count": 9053521, "decode_str": "\u60e7"} -{"id": 53855, "token": "\u00e8\u00b0\u0127", "merges": "\u00e8\u00b0 \u0127", "raw_count": 9058236, "count": 9058236, "decode_str": "\u8c05"} -{"id": 52977, "token": "\u00e7\u013c\u00b1", "merges": "\u00e7\u013c \u00b1", "raw_count": 9058682, "count": 9058682, "decode_str": "\u76b1"} -{"id": 54281, "token": "\u00e9\u0139\u00b7", "merges": "\u00e9\u0139 \u00b7", "raw_count": 9092360, "count": 9092360, "decode_str": "\u95f7"} -{"id": 475, "token": "\u0120*", "merges": "\u0120 *", "raw_count": 8653848, "count": 9095719, "decode_str": " *"} -{"id": 51740, "token": "\u00e6\u0124\u0136", "merges": "\u00e6\u0124 \u0136", "raw_count": 9122003, "count": 9122003, "decode_str": "\u6094"} -{"id": 54449, "token": "\u00e9\u00a2\u0138", "merges": "\u00e9\u00a2 \u0138", "raw_count": 9125869, "count": 9125869, "decode_str": "\u9896"} -{"id": 401, "token": "\u0120F", "merges": "\u0120 F", "raw_count": 1323590, "count": 9143763, "decode_str": " F"} -{"id": 3550, "token": "list", "merges": "l ist", "raw_count": 8787700, "count": 9144052, "decode_str": "list"} -{"id": 51263, "token": "\u00e5\u00a2\u0135", "merges": "\u00e5\u00a2 \u0135", "raw_count": 9153467, "count": 9153467, "decode_str": "\u5893"} -{"id": 53043, "token": "\u00e7\u0141\u00a9", "merges": "\u00e7\u0141 \u00a9", "raw_count": 9154550, "count": 9154550, "decode_str": "\u77e9"} -{"id": 912, "token": "ange", "merges": "an ge", "raw_count": 490158, "count": 9159676, "decode_str": "ange"} -{"id": 2808, "token": "log", "merges": "l og", "raw_count": 4300414, "count": 9159679, "decode_str": "log"} -{"id": 848, "token": "\u0120201", "merges": "\u01202 01", "raw_count": 145521, "count": 9169312, "decode_str": " 201"} -{"id": 1156, "token": "text", "merges": "te xt", "raw_count": 5098279, "count": 9181994, "decode_str": "text"} -{"id": 51020, "token": "\u00e5\u0134\u012d", "merges": "\u00e5\u0134 \u012d", "raw_count": 9206712, "count": 9206712, "decode_str": "\u548b"} -{"id": 53222, "token": "\u00e7\u0143\u012d", "merges": "\u00e7\u0143 \u012d", "raw_count": 9212495, "count": 9212495, "decode_str": "\u7b4b"} -{"id": 51481, "token": "\u00e5\u00b1\u012a", "merges": "\u00e5\u00b1 \u012a", "raw_count": 9219224, "count": 9219224, "decode_str": "\u5c48"} -{"id": 53199, "token": "\u00e7\u00ab\u0143", "merges": "\u00e7\u00ab \u0143", "raw_count": 9221159, "count": 9221159, "decode_str": "\u7aed"} -{"id": 51631, "token": "\u00e5\u00bd\u00b0", "merges": "\u00e5\u00bd \u00b0", "raw_count": 9222452, "count": 9222452, "decode_str": "\u5f70"} -{"id": 51772, "token": "\u00e6\u0125\u00a8", "merges": "\u00e6\u0125 \u00a8", "raw_count": 9226634, "count": 9226634, "decode_str": "\u60e8"} -{"id": 2462, "token": "\u0120%", "merges": "\u0120 %", "raw_count": 9094417, "count": 9236414, "decode_str": " %"} -{"id": 50757, "token": "\u00e5\u0129\u00b6", "merges": "\u00e5\u0129 \u00b6", "raw_count": 9252897, "count": 9252897, "decode_str": "\u51f6"} -{"id": 550, "token": "cc", "merges": "c c", "raw_count": 1966389, "count": 9263013, "decode_str": "cc"} -{"id": 51736, "token": "\u00e6\u0124\u0126", "merges": "\u00e6\u0124 \u0126", "raw_count": 9267685, "count": 9267685, "decode_str": "\u6084"} -{"id": 53617, "token": "\u00e8\u012c\u013f", "merges": "\u00e8\u012c \u013f", "raw_count": 9272223, "count": 9272223, "decode_str": "\u829d"} -{"id": 2358, "token": "68", "merges": "6 8", "raw_count": 6540884, "count": 9280518, "decode_str": "68"} -{"id": 50919, "token": "\u00e5\u0131\u012b", "merges": "\u00e5\u0131 \u012b", "raw_count": 9290224, "count": 9290224, "decode_str": "\u53c9"} -{"id": 3141, "token": "78", "merges": "7 8", "raw_count": 4851534, "count": 9321467, "decode_str": "78"} -{"id": 8193, "token": "120", "merges": "12 0", "raw_count": 9326233, "count": 9326233, "decode_str": "120"} -{"id": 480, "token": "\u0120j", "merges": "\u0120 j", "raw_count": 3793445, "count": 9334483, "decode_str": " j"} -{"id": 10543, "token": "%;", "merges": "% ;", "raw_count": 9335230, "count": 9335230, "decode_str": "%;"} -{"id": 441, "token": "\u0120us", "merges": "\u0120 us", "raw_count": 923075, "count": 9357795, "decode_str": " us"} -{"id": 51870, "token": "\u00e6\u012c\u0138", "merges": "\u00e6\u012c \u0138", "raw_count": 9363395, "count": 9363395, "decode_str": "\u6296"} -{"id": 53495, "token": "\u00e8\u0124\u00aa", "merges": "\u00e8\u0124 \u00aa", "raw_count": 9376585, "count": 9376585, "decode_str": "\u80aa"} -{"id": 2031, "token": "44", "merges": "4 4", "raw_count": 7307734, "count": 9386460, "decode_str": "44"} -{"id": 1269, "token": "\u0120x", "merges": "\u0120 x", "raw_count": 8977352, "count": 9386546, "decode_str": " x"} -{"id": 589, "token": "ber", "merges": "b er", "raw_count": 1557718, "count": 9399186, "decode_str": "ber"} -{"id": 511, "token": "ase", "merges": "as e", "raw_count": 416421, "count": 9422572, "decode_str": "ase"} -{"id": 721, "token": "\u01206", "merges": "\u0120 6", "raw_count": 6422670, "count": 9426183, "decode_str": " 6"} -{"id": 52080, "token": "\u00e6\u0137\u00a6", "merges": "\u00e6\u0137 \u00a6", "raw_count": 9428144, "count": 9428144, "decode_str": "\u6566"} -{"id": 53450, "token": "\u00e8\u0122\u0137", "merges": "\u00e8\u0122 \u0137", "raw_count": 9431774, "count": 9431774, "decode_str": "\u8015"} -{"id": 51837, "token": "\u00e6\u012b\u0133", "merges": "\u00e6\u012b \u0133", "raw_count": 9449931, "count": 9449931, "decode_str": "\u6251"} -{"id": 54490, "token": "\u00e9\u00aa\u0124", "merges": "\u00e9\u00aa \u0124", "raw_count": 9487683, "count": 9487683, "decode_str": "\u9a82"} -{"id": 51873, "token": "\u00e6\u012c\u013c", "merges": "\u00e6\u012c \u013c", "raw_count": 9491547, "count": 9491547, "decode_str": "\u629a"} -{"id": 51253, "token": "\u00e5\u0142\u00aa", "merges": "\u00e5\u0142 \u00aa", "raw_count": 9502052, "count": 9502052, "decode_str": "\u582a"} -{"id": 50961, "token": "\u00e5\u0132\u0137", "merges": "\u00e5\u0132 \u0137", "raw_count": 9518259, "count": 9518259, "decode_str": "\u5415"} -{"id": 51518, "token": "\u00e5\u00b7\u00be", "merges": "\u00e5\u00b7 \u00be", "raw_count": 9538559, "count": 9538559, "decode_str": "\u5dfe"} -{"id": 53226, "token": "\u00e7\u0143\u0134", "merges": "\u00e7\u0143 \u0134", "raw_count": 9539263, "count": 9539263, "decode_str": "\u7b52"} -{"id": 54118, "token": "\u00e9\u0122\u00b8", "merges": "\u00e9\u0122 \u00b8", "raw_count": 9550926, "count": 9550926, "decode_str": "\u9038"} -{"id": 448, "token": "\u0120ch", "merges": "\u0120c h", "raw_count": 1452930, "count": 9556415, "decode_str": " ch"} -{"id": 53553, "token": "\u00e8\u0126\u00be", "merges": "\u00e8\u0126 \u00be", "raw_count": 9560098, "count": 9560098, "decode_str": "\u813e"} -{"id": 7199, "token": "2010", "merges": "201 0", "raw_count": 9560946, "count": 9560946, "decode_str": "2010"} -{"id": 54289, "token": "\u00e9\u013a\u0123", "merges": "\u00e9\u013a \u0123", "raw_count": 9582520, "count": 9582520, "decode_str": "\u9601"} -{"id": 53811, "token": "\u00e8\u00af\u012a", "merges": "\u00e8\u00af \u012a", "raw_count": 9587009, "count": 9587009, "decode_str": "\u8bc8"} -{"id": 51438, "token": "\u00e5\u00af\u0135", "merges": "\u00e5\u00af \u0135", "raw_count": 9622024, "count": 9622024, "decode_str": "\u5bd3"} -{"id": 425, "token": "\u0120ne", "merges": "\u0120n e", "raw_count": 199892, "count": 9623964, "decode_str": " ne"} -{"id": 54157, "token": "\u00e9\u0124\u00aa", "merges": "\u00e9\u0124 \u00aa", "raw_count": 9629326, "count": 9629326, "decode_str": "\u90aa"} -{"id": 51734, "token": "\u00e6\u0123\u00bc", "merges": "\u00e6\u0123 \u00bc", "raw_count": 9637160, "count": 9637160, "decode_str": "\u607c"} -{"id": 51572, "token": "\u00e5\u00ba\u0140", "merges": "\u00e5\u00ba \u0140", "raw_count": 9643178, "count": 9643178, "decode_str": "\u5e9e"} -{"id": 54204, "token": "\u00e9\u0127\u00b1", "merges": "\u00e9\u0127 \u00b1", "raw_count": 9657146, "count": 9657146, "decode_str": "\u9171"} -{"id": 50607, "token": "\u00e4\u00bf\u00a9", "merges": "\u00e4\u00bf \u00a9", "raw_count": 9676753, "count": 9676753, "decode_str": "\u4fe9"} -{"id": 52178, "token": "\u00e6\u013d\u013f", "merges": "\u00e6\u013d \u013f", "raw_count": 9677775, "count": 9677775, "decode_str": "\u66dd"} -{"id": 51589, "token": "\u00e5\u00bb\u00b7", "merges": "\u00e5\u00bb \u00b7", "raw_count": 9692789, "count": 9692789, "decode_str": "\u5ef7"} -{"id": 8970, "token": "150", "merges": "15 0", "raw_count": 9698415, "count": 9698415, "decode_str": "150"} -{"id": 50883, "token": "\u00e5\u012f\u00a2", "merges": "\u00e5\u012f \u00a2", "raw_count": 9701945, "count": 9701945, "decode_str": "\u5362"} -{"id": 51899, "token": "\u00e6\u012d\u012e", "merges": "\u00e6\u012d \u012e", "raw_count": 9707407, "count": 9707407, "decode_str": "\u62cc"} -{"id": 50814, "token": "\u00e5\u012c\u00a3", "merges": "\u00e5\u012c \u00a3", "raw_count": 9712458, "count": 9712458, "decode_str": "\u52a3"} -{"id": 53506, "token": "\u00e8\u0125\u0123", "merges": "\u00e8\u0125 \u0123", "raw_count": 9719741, "count": 9719741, "decode_str": "\u80c1"} -{"id": 1762, "token": "05", "merges": "0 5", "raw_count": 8663066, "count": 9733146, "decode_str": "05"} -{"id": 53074, "token": "\u00e7\u00a1\u0127", "merges": "\u00e7\u00a1 \u0127", "raw_count": 9738632, "count": 9738632, "decode_str": "\u7845"} -{"id": 344, "token": "\u0120he", "merges": "\u0120 he", "raw_count": 1982255, "count": 9745413, "decode_str": " he"} -{"id": 53918, "token": "\u00e8\u00b4\u00a4", "merges": "\u00e8\u00b4 \u00a4", "raw_count": 9753451, "count": 9753451, "decode_str": "\u8d24"} -{"id": 52271, "token": "\u00e6\u0141\u00b4", "merges": "\u00e6\u0141 \u00b4", "raw_count": 9764614, "count": 9764614, "decode_str": "\u67f4"} -{"id": 541, "token": "\u0120\u00e2\u0122", "merges": "\u0120 \u00e2\u0122", "raw_count": 18527, "count": 9767845, "decode_str": " \ufffd"} -{"id": 51193, "token": "\u00e5\u013f\u012c", "merges": "\u00e5\u013f \u012c", "raw_count": 9768573, "count": 9768573, "decode_str": "\u574a"} -{"id": 51468, "token": "\u00e5\u00b0\u00b8", "merges": "\u00e5\u00b0 \u00b8", "raw_count": 9793670, "count": 9793670, "decode_str": "\u5c38"} -{"id": 53418, "token": "\u00e7\u00bd\u00a2", "merges": "\u00e7\u00bd \u00a2", "raw_count": 9853446, "count": 9853446, "decode_str": "\u7f62"} -{"id": 14236, "token": "\u00ef\u00bc\u012a", "merges": "\u00ef\u00bc \u012a", "raw_count": 9860104, "count": 9860104, "decode_str": "\uff08"} -{"id": 825, "token": "ock", "merges": "oc k", "raw_count": 322414, "count": 9863318, "decode_str": "ock"} -{"id": 3845, "token": "print", "merges": "pr int", "raw_count": 9745383, "count": 9865068, "decode_str": "print"} -{"id": 53938, "token": "\u00e8\u00b4\u00ba", "merges": "\u00e8\u00b4 \u00ba", "raw_count": 9867535, "count": 9867535, "decode_str": "\u8d3a"} -{"id": 1071, "token": "\u0120test", "merges": "\u0120t est", "raw_count": 9359031, "count": 9868449, "decode_str": " test"} -{"id": 53943, "token": "\u00e8\u00b5\u0123", "merges": "\u00e8\u00b5 \u0123", "raw_count": 9869665, "count": 9869665, "decode_str": "\u8d41"} -{"id": 51386, "token": "\u00e5\u0143\u0141", "merges": "\u00e5\u0143 \u0141", "raw_count": 9869729, "count": 9869729, "decode_str": "\u5b5f"} -{"id": 7330, "token": "2011", "merges": "201 1", "raw_count": 9875939, "count": 9875939, "decode_str": "2011"} -{"id": 50629, "token": "\u00e5\u0122\u00a1", "merges": "\u00e5\u0122 \u00a1", "raw_count": 9898887, "count": 9898887, "decode_str": "\u5021"} -{"id": 52305, "token": "\u00e6\u00a1\u0133", "merges": "\u00e6\u00a1 \u0133", "raw_count": 9899045, "count": 9899045, "decode_str": "\u6851"} -{"id": 51601, "token": "\u00e5\u00bc\u0139", "merges": "\u00e5\u00bc \u0139", "raw_count": 9904917, "count": 9904917, "decode_str": "\u5f17"} -{"id": 438, "token": "ud", "merges": "u d", "raw_count": 729845, "count": 9911747, "decode_str": "ud"} -{"id": 52707, "token": "\u00e7\u0123\u012e", "merges": "\u00e7\u0123 \u012e", "raw_count": 9916918, "count": 9916918, "decode_str": "\u704c"} -{"id": 8854, "token": "args", "merges": "arg s", "raw_count": 6618359, "count": 9919514, "decode_str": "args"} -{"id": 51606, "token": "\u00e5\u00bc\u00a5", "merges": "\u00e5\u00bc \u00a5", "raw_count": 9925046, "count": 9925046, "decode_str": "\u5f25"} -{"id": 51145, "token": "\u00e5\u013b\u00aa", "merges": "\u00e5 \u013b\u00aa", "raw_count": 9942439, "count": 9942439, "decode_str": "\u566a"} -{"id": 6038, "token": "']", "merges": "' ]", "raw_count": 8812676, "count": 9947464, "decode_str": "']"} -{"id": 1206, "token": "tr", "merges": "t r", "raw_count": 1177736, "count": 9948121, "decode_str": "tr"} -{"id": 1703, "token": "ED", "merges": "E D", "raw_count": 3739352, "count": 9953694, "decode_str": "ED"} -{"id": 53563, "token": "\u00e8\u0129\u0143", "merges": "\u00e8\u0129 \u0143", "raw_count": 9955035, "count": 9955035, "decode_str": "\u81ed"} -{"id": 51041, "token": "\u00e5\u0134\u00ac", "merges": "\u00e5\u0134 \u00ac", "raw_count": 9959206, "count": 9959206, "decode_str": "\u54ac"} -{"id": 52631, "token": "\u00e6\u00b7\u012d", "merges": "\u00e6\u00b7 \u012d", "raw_count": 9968829, "count": 9968829, "decode_str": "\u6dcb"} -{"id": 53369, "token": "\u00e7\u00bb\u00b5", "merges": "\u00e7\u00bb \u00b5", "raw_count": 9979555, "count": 9979555, "decode_str": "\u7ef5"} -{"id": 50960, "token": "\u00e5\u0132\u0135", "merges": "\u00e5\u0132 \u0135", "raw_count": 9984111, "count": 9984111, "decode_str": "\u5413"} -{"id": 53951, "token": "\u00e8\u00b5\u012e", "merges": "\u00e8\u00b5 \u012e", "raw_count": 9990724, "count": 9990724, "decode_str": "\u8d4c"} -{"id": 3140, "token": "file", "merges": "f ile", "raw_count": 9143392, "count": 9996466, "decode_str": "file"} -{"id": 52659, "token": "\u00e6\u00b8\u0139", "merges": "\u00e6\u00b8 \u0139", "raw_count": 10012381, "count": 10012381, "decode_str": "\u6e17"} -{"id": 54387, "token": "\u00e9\u013e\u012f", "merges": "\u00e9\u013e \u012f", "raw_count": 10026737, "count": 10026737, "decode_str": "\u970d"} -{"id": 52735, "token": "\u00e7\u0124\u0143", "merges": "\u00e7\u0124 \u0143", "raw_count": 10037821, "count": 10037821, "decode_str": "\u70ad"} -{"id": 51231, "token": "\u00e5\u0141\u012d", "merges": "\u00e5\u0141 \u012d", "raw_count": 10044477, "count": 10044477, "decode_str": "\u57cb"} -{"id": 51338, "token": "\u00e5\u00a6\u0138", "merges": "\u00e5\u00a6 \u0138", "raw_count": 10050572, "count": 10050572, "decode_str": "\u5996"} -{"id": 53967, "token": "\u00e8\u00b5\u00a4", "merges": "\u00e8\u00b5 \u00a4", "raw_count": 10051074, "count": 10051074, "decode_str": "\u8d64"} -{"id": 14106, "token": "\u00ef\u00bc\u012b", "merges": "\u00ef\u00bc \u012b", "raw_count": 10058656, "count": 10058656, "decode_str": "\uff09"} -{"id": 631, "token": "port", "merges": "p ort", "raw_count": 1747480, "count": 10069505, "decode_str": "port"} -{"id": 50966, "token": "\u00e5\u0132\u0140", "merges": "\u00e5\u0132 \u0140", "raw_count": 10094166, "count": 10094166, "decode_str": "\u541e"} -{"id": 50590, "token": "\u00e4\u00be\u00af", "merges": "\u00e4\u00be \u00af", "raw_count": 10094950, "count": 10094950, "decode_str": "\u4faf"} -{"id": 53970, "token": "\u00e8\u00b5\u00ab", "merges": "\u00e8\u00b5 \u00ab", "raw_count": 10107190, "count": 10107190, "decode_str": "\u8d6b"} -{"id": 52588, "token": "\u00e6\u00b5\u00a6", "merges": "\u00e6\u00b5 \u00a6", "raw_count": 10113702, "count": 10113702, "decode_str": "\u6d66"} -{"id": 54439, "token": "\u00e9\u00a2\u0129", "merges": "\u00e9\u00a2 \u0129", "raw_count": 10114789, "count": 10114789, "decode_str": "\u9887"} -{"id": 50896, "token": "\u00e5\u012f\u00b8", "merges": "\u00e5\u012f \u00b8", "raw_count": 10128331, "count": 10128331, "decode_str": "\u5378"} -{"id": 50422, "token": "\u00e4\u00b8\u00a7", "merges": "\u00e4\u00b8 \u00a7", "raw_count": 10128496, "count": 10128496, "decode_str": "\u4e27"} -{"id": 51373, "token": "\u00e5\u00a7\u00bb", "merges": "\u00e5\u00a7 \u00bb", "raw_count": 10130576, "count": 10130576, "decode_str": "\u59fb"} -{"id": 50990, "token": "\u00e5\u0133\u0128", "merges": "\u00e5\u0133 \u0128", "raw_count": 10155531, "count": 10155531, "decode_str": "\u5446"} -{"id": 54228, "token": "\u00e9\u0136\u0132", "merges": "\u00e9\u0136 \u0132", "raw_count": 10157010, "count": 10157010, "decode_str": "\u9510"} -{"id": 386, "token": "ant", "merges": "an t", "raw_count": 1327999, "count": 10159153, "decode_str": "ant"} -{"id": 53555, "token": "\u00e8\u0129\u0124", "merges": "\u00e8\u0129 \u0124", "raw_count": 10160361, "count": 10160361, "decode_str": "\u81c2"} -{"id": 54247, "token": "\u00e9\u0136\u00bb", "merges": "\u00e9\u0136 \u00bb", "raw_count": 10191104, "count": 10191104, "decode_str": "\u953b"} -{"id": 891, "token": "\u0120i", "merges": "\u0120 i", "raw_count": 9616875, "count": 10198712, "decode_str": " i"} -{"id": 52032, "token": "\u00e6\u0134\u0134", "merges": "\u00e6\u0134 \u0134", "raw_count": 10204499, "count": 10204499, "decode_str": "\u6492"} -{"id": 52596, "token": "\u00e6\u00b5\u00b8", "merges": "\u00e6\u00b5 \u00b8", "raw_count": 10208486, "count": 10208486, "decode_str": "\u6d78"} -{"id": 52389, "token": "\u00e6\u00ac\u00ba", "merges": "\u00e6\u00ac \u00ba", "raw_count": 10211900, "count": 10211900, "decode_str": "\u6b3a"} -{"id": 545, "token": "ph", "merges": "p h", "raw_count": 1037267, "count": 10240871, "decode_str": "ph"} -{"id": 51526, "token": "\u00e5\u00b8\u0132", "merges": "\u00e5\u00b8 \u0132", "raw_count": 10271437, "count": 10271437, "decode_str": "\u5e10"} -{"id": 54059, "token": "\u00e8\u00be\u00a9", "merges": "\u00e8\u00be \u00a9", "raw_count": 10366718, "count": 10366718, "decode_str": "\u8fa9"} -{"id": 507, "token": "ans", "merges": "an s", "raw_count": 1540862, "count": 10368239, "decode_str": "ans"} -{"id": 51344, "token": "\u00e5\u00a6\u00a5", "merges": "\u00e5\u00a6 \u00a5", "raw_count": 10368574, "count": 10368574, "decode_str": "\u59a5"} -{"id": 52094, "token": "\u00e6\u0138\u013e", "merges": "\u00e6\u0138 \u013e", "raw_count": 10380229, "count": 10380229, "decode_str": "\u659c"} -{"id": 453, "token": "fe", "merges": "f e", "raw_count": 907201, "count": 10395187, "decode_str": "fe"} -{"id": 54326, "token": "\u00e9\u013b\u0137", "merges": "\u00e9\u013b \u0137", "raw_count": 10403337, "count": 10403337, "decode_str": "\u9655"} -{"id": 785, "token": "ma", "merges": "m a", "raw_count": 2945314, "count": 10428052, "decode_str": "ma"} -{"id": 54172, "token": "\u00e9\u0125\u0130", "merges": "\u00e9\u0125 \u0130", "raw_count": 10430126, "count": 10430126, "decode_str": "\u90ce"} -{"id": 51543, "token": "\u00e5\u00b8\u00bd", "merges": "\u00e5\u00b8 \u00bd", "raw_count": 10447203, "count": 10447203, "decode_str": "\u5e3d"} -{"id": 50831, "token": "\u00e5\u012d\u0132", "merges": "\u00e5\u012d \u0132", "raw_count": 10456604, "count": 10456604, "decode_str": "\u52d0"} -{"id": 50687, "token": "\u00e5\u0127\u0133", "merges": "\u00e5\u0127 \u0133", "raw_count": 10459725, "count": 10459725, "decode_str": "\u5151"} -{"id": 52322, "token": "\u00e6\u00a3\u012d", "merges": "\u00e6\u00a3 \u012d", "raw_count": 10464141, "count": 10464141, "decode_str": "\u68cb"} -{"id": 53534, "token": "\u00e8\u0126\u0128", "merges": "\u00e8\u0126 \u0128", "raw_count": 10491557, "count": 10491557, "decode_str": "\u8106"} -{"id": 54119, "token": "\u00e9\u0122\u00bb", "merges": "\u00e9\u0122 \u00bb", "raw_count": 10527203, "count": 10527203, "decode_str": "\u903b"} -{"id": 51851, "token": "\u00e6\u012b\u0143", "merges": "\u00e6\u012b \u0143", "raw_count": 10529649, "count": 10529649, "decode_str": "\u626d"} -{"id": 52574, "token": "\u00e6\u00b5\u0128", "merges": "\u00e6\u00b5 \u0128", "raw_count": 10539344, "count": 10539344, "decode_str": "\u6d46"} -{"id": 53841, "token": "\u00e8\u00af\u00b1", "merges": "\u00e8\u00af \u00b1", "raw_count": 10548330, "count": 10548330, "decode_str": "\u8bf1"} -{"id": 52745, "token": "\u00e7\u0126\u012c", "merges": "\u00e7\u0126 \u012c", "raw_count": 10562179, "count": 10562179, "decode_str": "\u710a"} -{"id": 408, "token": "ill", "merges": "il l", "raw_count": 684651, "count": 10579602, "decode_str": "ill"} -{"id": 52760, "token": "\u00e7\u012a\u00ac", "merges": "\u00e7\u012a \u00ac", "raw_count": 10611399, "count": 10611399, "decode_str": "\u722c"} -{"id": 459, "token": "ure", "merges": "u re", "raw_count": 880647, "count": 10622278, "decode_str": "ure"} -{"id": 53282, "token": "\u00e7\u00b3\u0137", "merges": "\u00e7\u00b3 \u0137", "raw_count": 10630638, "count": 10630638, "decode_str": "\u7cd5"} -{"id": 53486, "token": "\u00e8\u0124\u013c", "merges": "\u00e8\u0124 \u013c", "raw_count": 10649825, "count": 10649825, "decode_str": "\u809a"} -{"id": 737, "token": "gr", "merges": "g r", "raw_count": 939626, "count": 10666736, "decode_str": "gr"} -{"id": 493, "token": "ost", "merges": "o st", "raw_count": 495343, "count": 10672963, "decode_str": "ost"} -{"id": 50426, "token": "\u00e4\u00b8\u00b2", "merges": "\u00e4\u00b8 \u00b2", "raw_count": 10674775, "count": 10674775, "decode_str": "\u4e32"} -{"id": 51152, "token": "\u00e5\u013d\u012c", "merges": "\u00e5\u013d \u012c", "raw_count": 10688693, "count": 10688693, "decode_str": "\u56ca"} -{"id": 54434, "token": "\u00e9\u00a2\u0123", "merges": "\u00e9\u00a2 \u0123", "raw_count": 10732097, "count": 10732097, "decode_str": "\u9881"} -{"id": 51804, "token": "\u00e6\u0127\u00b0", "merges": "\u00e6\u0127 \u00b0", "raw_count": 10744853, "count": 10744853, "decode_str": "\u6170"} -{"id": 53472, "token": "\u00e8\u0123\u00aa", "merges": "\u00e8\u0123 \u00aa", "raw_count": 10804006, "count": 10804006, "decode_str": "\u806a"} -{"id": 396, "token": "\u0120se", "merges": "\u0120s e", "raw_count": 408025, "count": 10822364, "decode_str": " se"} -{"id": 51703, "token": "\u00e6\u0122\u00a8", "merges": "\u00e6\u0122 \u00a8", "raw_count": 10824875, "count": 10824875, "decode_str": "\u6028"} -{"id": 52524, "token": "\u00e6\u00b3\u0126", "merges": "\u00e6\u00b3 \u0126", "raw_count": 10826799, "count": 10826799, "decode_str": "\u6cc4"} -{"id": 52918, "token": "\u00e7\u0138\u00b2", "merges": "\u00e7\u0138 \u00b2", "raw_count": 10881598, "count": 10881598, "decode_str": "\u75b2"} -{"id": 53484, "token": "\u00e8\u0124\u0138", "merges": "\u00e8\u0124 \u0138", "raw_count": 10882386, "count": 10882386, "decode_str": "\u8096"} -{"id": 54467, "token": "\u00e9\u00a3\u013a", "merges": "\u00e9\u00a3 \u013a", "raw_count": 10883479, "count": 10883479, "decode_str": "\u98d8"} -{"id": 554, "token": "ep", "merges": "e p", "raw_count": 2196844, "count": 10889695, "decode_str": "ep"} -{"id": 1148, "token": "par", "merges": "p ar", "raw_count": 526128, "count": 10892770, "decode_str": "par"} -{"id": 53505, "token": "\u00e8\u0125\u0122", "merges": "\u00e8\u0125 \u0122", "raw_count": 10892928, "count": 10892928, "decode_str": "\u80c0"} -{"id": 51198, "token": "\u00e5\u013f\u0133", "merges": "\u00e5\u013f \u0133", "raw_count": 10895077, "count": 10895077, "decode_str": "\u5751"} -{"id": 688, "token": "In", "merges": "I n", "raw_count": 2441811, "count": 10897370, "decode_str": "In"} -{"id": 1200, "token": "sh", "merges": "s h", "raw_count": 2418719, "count": 10922114, "decode_str": "sh"} -{"id": 51918, "token": "\u00e6\u012d\u00a6", "merges": "\u00e6\u012d \u00a6", "raw_count": 10930617, "count": 10930617, "decode_str": "\u62e6"} -{"id": 491, "token": "der", "merges": "d er", "raw_count": 475390, "count": 10932265, "decode_str": "der"} -{"id": 52601, "token": "\u00e6\u00b6\u012e", "merges": "\u00e6\u00b6 \u012e", "raw_count": 10935020, "count": 10935020, "decode_str": "\u6d8c"} -{"id": 440, "token": "\u0120un", "merges": "\u0120 un", "raw_count": 1744387, "count": 10953035, "decode_str": " un"} -{"id": 53457, "token": "\u00e8\u0122\u00b6", "merges": "\u00e8\u0122 \u00b6", "raw_count": 10976521, "count": 10976521, "decode_str": "\u8036"} -{"id": 54440, "token": "\u00e9\u00a2\u012a", "merges": "\u00e9\u00a2 \u012a", "raw_count": 10988382, "count": 10988382, "decode_str": "\u9888"} -{"id": 54336, "token": "\u00e9\u013b\u00b5", "merges": "\u00e9\u013b \u00b5", "raw_count": 10993772, "count": 10993772, "decode_str": "\u9675"} -{"id": 422, "token": "ive", "merges": "i ve", "raw_count": 1185408, "count": 11000989, "decode_str": "ive"} -{"id": 783, "token": "the", "merges": "t he", "raw_count": 8271814, "count": 11004599, "decode_str": "the"} -{"id": 50906, "token": "\u00e5\u0130\u013a", "merges": "\u00e5\u0130 \u013a", "raw_count": 11008475, "count": 11008475, "decode_str": "\u5398"} -{"id": 52495, "token": "\u00e6\u00b2\u0125", "merges": "\u00e6\u00b2 \u0125", "raw_count": 11013988, "count": 11013988, "decode_str": "\u6c83"} -{"id": 51721, "token": "\u00e6\u0123\u00a8", "merges": "\u00e6\u0123 \u00a8", "raw_count": 11017978, "count": 11017978, "decode_str": "\u6068"} -{"id": 50537, "token": "\u00e4\u00bc\u00aa", "merges": "\u00e4\u00bc \u00aa", "raw_count": 11022500, "count": 11022500, "decode_str": "\u4f2a"} -{"id": 27806, "token": "mobile", "merges": "m obile", "raw_count": 11036085, "count": 11036085, "decode_str": "mobile"} -{"id": 51832, "token": "\u00e6\u012b\u0129", "merges": "\u00e6\u012b \u0129", "raw_count": 11040492, "count": 11040492, "decode_str": "\u6247"} -{"id": 51251, "token": "\u00e5\u0142\u00a1", "merges": "\u00e5\u0142 \u00a1", "raw_count": 11051096, "count": 11051096, "decode_str": "\u5821"} -{"id": 51315, "token": "\u00e5\u00a5\u0133", "merges": "\u00e5\u00a5 \u0133", "raw_count": 11052488, "count": 11052488, "decode_str": "\u5951"} -{"id": 51993, "token": "\u00e6\u0130\u013a", "merges": "\u00e6\u0130 \u013a", "raw_count": 11064261, "count": 11064261, "decode_str": "\u6398"} -{"id": 51068, "token": "\u00e5\u0135\u0141", "merges": "\u00e5\u0135 \u0141", "raw_count": 11074605, "count": 11074605, "decode_str": "\u54df"} -{"id": 53089, "token": "\u00e7\u00a2\u0133", "merges": "\u00e7\u00a2 \u0133", "raw_count": 11079222, "count": 11079222, "decode_str": "\u7891"} -{"id": 54488, "token": "\u00e9\u00a6\u00a8", "merges": "\u00e9\u00a6 \u00a8", "raw_count": 11081426, "count": 11081426, "decode_str": "\u99a8"} -{"id": 51413, "token": "\u00e5\u00ae\u0142", "merges": "\u00e5\u00ae \u0142", "raw_count": 11094010, "count": 11094010, "decode_str": "\u5ba0"} -{"id": 402, "token": "\u0120su", "merges": "\u0120s u", "raw_count": 261514, "count": 11107803, "decode_str": " su"} -{"id": 3123, "token": "IP", "merges": "I P", "raw_count": 10387565, "count": 11110658, "decode_str": "IP"} -{"id": 720, "token": "ject", "merges": "j ect", "raw_count": 178508, "count": 11117141, "decode_str": "ject"} -{"id": 51556, "token": "\u00e5\u00b9\u00bd", "merges": "\u00e5\u00b9 \u00bd", "raw_count": 11121466, "count": 11121466, "decode_str": "\u5e7d"} -{"id": 54509, "token": "\u00e9\u00aa\u00a4", "merges": "\u00e9\u00aa \u00a4", "raw_count": 11152444, "count": 11152444, "decode_str": "\u9aa4"} -{"id": 54061, "token": "\u00e8\u00be\u00b0", "merges": "\u00e8\u00be \u00b0", "raw_count": 11172073, "count": 11172073, "decode_str": "\u8fb0"} -{"id": 8320, "token": "400", "merges": "4 00", "raw_count": 11189691, "count": 11189691, "decode_str": "400"} -{"id": 59, "token": "Z", "merges": "NULL", "raw_count": 7791471, "count": 11203560, "decode_str": "Z"} -{"id": 937, "token": ",\"", "merges": ", \"", "raw_count": 9913232, "count": 11273019, "decode_str": ",\""} -{"id": 1540, "token": "64", "merges": "6 4", "raw_count": 8075682, "count": 11274420, "decode_str": "64"} -{"id": 54049, "token": "\u00e8\u00be\u0138", "merges": "\u00e8\u00be \u0138", "raw_count": 11274985, "count": 11274985, "decode_str": "\u8f96"} -{"id": 466, "token": "ie", "merges": "i e", "raw_count": 2197854, "count": 11316576, "decode_str": "ie"} -{"id": 53629, "token": "\u00e8\u012c\u00b3", "merges": "\u00e8\u012c \u00b3", "raw_count": 11329383, "count": 11329383, "decode_str": "\u82b3"} -{"id": 50513, "token": "\u00e4\u00bb\u00b0", "merges": "\u00e4\u00bb \u00b0", "raw_count": 11345853, "count": 11345853, "decode_str": "\u4ef0"} -{"id": 881, "token": "type", "merges": "ty pe", "raw_count": 10368246, "count": 11348319, "decode_str": "type"} -{"id": 53746, "token": "\u00e8\u00a3\u00b9", "merges": "\u00e8\u00a3 \u00b9", "raw_count": 11350114, "count": 11350114, "decode_str": "\u88f9"} -{"id": 54067, "token": "\u00e8\u00be\u00bd", "merges": "\u00e8\u00be \u00bd", "raw_count": 11374851, "count": 11374851, "decode_str": "\u8fbd"} -{"id": 52128, "token": "\u00e6\u013a\u0128", "merges": "\u00e6\u013a \u0128", "raw_count": 11379494, "count": 11379494, "decode_str": "\u6606"} -{"id": 702, "token": "ount", "merges": "oun t", "raw_count": 191196, "count": 11383660, "decode_str": "ount"} -{"id": 51255, "token": "\u00e5\u0142\u00b5", "merges": "\u00e5\u0142 \u00b5", "raw_count": 11399776, "count": 11399776, "decode_str": "\u5835"} -{"id": 567, "token": "ff", "merges": "f f", "raw_count": 952342, "count": 11422622, "decode_str": "ff"} -{"id": 53039, "token": "\u00e7\u0141\u013d", "merges": "\u00e7\u0141 \u013d", "raw_count": 11439563, "count": 11439563, "decode_str": "\u77db"} -{"id": 51634, "token": "\u00e5\u00bd\u00b9", "merges": "\u00e5\u00bd \u00b9", "raw_count": 11443696, "count": 11443696, "decode_str": "\u5f79"} -{"id": 647, "token": "ail", "merges": "a il", "raw_count": 375534, "count": 11464643, "decode_str": "ail"} -{"id": 51664, "token": "\u00e5\u00bf\u012e", "merges": "\u00e5\u00bf \u012e", "raw_count": 11467273, "count": 11467273, "decode_str": "\u5fcc"} -{"id": 4252, "token": "obile", "merges": "ob ile", "raw_count": 35929, "count": 11498344, "decode_str": "obile"} -{"id": 593, "token": "ance", "merges": "an ce", "raw_count": 972405, "count": 11511616, "decode_str": "ance"} -{"id": 53342, "token": "\u00e7\u00bb\u0133", "merges": "\u00e7\u00bb \u0133", "raw_count": 11515272, "count": 11515272, "decode_str": "\u7ed1"} -{"id": 52689, "token": "\u00e6\u00ba\u00b6", "merges": "\u00e6\u00ba \u00b6", "raw_count": 11528021, "count": 11528021, "decode_str": "\u6eb6"} -{"id": 50309, "token": "\u00e2\u0126\u0125", "merges": "\u00e2\u0126 \u0125", "raw_count": 11536652, "count": 11536652, "decode_str": "\u2103"} -{"id": 13262, "token": "\u00e2\u0126", "merges": "\u00e2 \u0126", "raw_count": 1429, "count": 11539858, "decode_str": "\ufffd"} -{"id": 52916, "token": "\u00e7\u0138\u00af", "merges": "\u00e7\u0138 \u00af", "raw_count": 11551956, "count": 11551956, "decode_str": "\u75af"} -{"id": 53602, "token": "\u00e8\u012b\u00b0", "merges": "\u00e8\u012b \u00b0", "raw_count": 11557777, "count": 11557777, "decode_str": "\u8270"} -{"id": 54168, "token": "\u00e9\u0124\u00bb", "merges": "\u00e9\u0124 \u00bb", "raw_count": 11564134, "count": 11564134, "decode_str": "\u90bb"} -{"id": 494, "token": "able", "merges": "ab le", "raw_count": 2204527, "count": 11569262, "decode_str": "able"} -{"id": 472, "token": "ard", "merges": "ar d", "raw_count": 1011940, "count": 11604427, "decode_str": "ard"} -{"id": 3591, "token": "cm", "merges": "c m", "raw_count": 10317388, "count": 11610624, "decode_str": "cm"} -{"id": 882, "token": "ict", "merges": "ic t", "raw_count": 589702, "count": 11617468, "decode_str": "ict"} -{"id": 392, "token": "ld", "merges": "l d", "raw_count": 1848679, "count": 11633248, "decode_str": "ld"} -{"id": 52736, "token": "\u00e7\u0124\u00ae", "merges": "\u00e7\u0124 \u00ae", "raw_count": 11634279, "count": 11634279, "decode_str": "\u70ae"} -{"id": 50911, "token": "\u00e5\u0130\u00a6", "merges": "\u00e5\u0130 \u00a6", "raw_count": 11654435, "count": 11654435, "decode_str": "\u53a6"} -{"id": 52426, "token": "\u00e6\u00ae\u00bf", "merges": "\u00e6\u00ae \u00bf", "raw_count": 11664113, "count": 11664113, "decode_str": "\u6bbf"} -{"id": 501, "token": "\u0120res", "merges": "\u0120re s", "raw_count": 1196246, "count": 11677162, "decode_str": " res"} -{"id": 51796, "token": "\u00e6\u0127\u012a", "merges": "\u00e6\u0127 \u012a", "raw_count": 11720975, "count": 11720975, "decode_str": "\u6148"} -{"id": 54420, "token": "\u00e9\u0141\u00b5", "merges": "\u00e9\u0141 \u00b5", "raw_count": 11723872, "count": 11723872, "decode_str": "\u97f5"} -{"id": 29, "token": "<", "merges": "NULL", "raw_count": 3698059, "count": 11730299, "decode_str": "<"} -{"id": 53974, "token": "\u00e8\u00b5\u00b4", "merges": "\u00e8\u00b5 \u00b4", "raw_count": 11732668, "count": 11732668, "decode_str": "\u8d74"} -{"id": 1178, "token": "set", "merges": "s et", "raw_count": 7658374, "count": 11739775, "decode_str": "set"} -{"id": 50596, "token": "\u00e4\u00bf\u012c", "merges": "\u00e4\u00bf \u012c", "raw_count": 11745296, "count": 11745296, "decode_str": "\u4fca"} -{"id": 50886, "token": "\u00e5\u012f\u00a7", "merges": "\u00e5\u012f \u00a7", "raw_count": 11751641, "count": 11751641, "decode_str": "\u5367"} -{"id": 52361, "token": "\u00e6\u00a7\u00bd", "merges": "\u00e6\u00a7 \u00bd", "raw_count": 11752208, "count": 11752208, "decode_str": "\u69fd"} -{"id": 1806, "token": ",\u00e2\u0122\u013f", "merges": ", \u00e2\u0122\u013f", "raw_count": 11778548, "count": 11778548, "decode_str": ",\u201d"} -{"id": 54299, "token": "\u00e9\u013a\u0136", "merges": "\u00e9\u013a \u0136", "raw_count": 11795222, "count": 11795222, "decode_str": "\u9614"} -{"id": 52296, "token": "\u00e6\u00a1\u0124", "merges": "\u00e6\u00a1 \u0124", "raw_count": 11800741, "count": 11800741, "decode_str": "\u6842"} -{"id": 54393, "token": "\u00e9\u013e\u013e", "merges": "\u00e9\u013e \u013e", "raw_count": 11842424, "count": 11842424, "decode_str": "\u971c"} -{"id": 52635, "token": "\u00e6\u00b7\u013a", "merges": "\u00e6\u00b7 \u013a", "raw_count": 11859069, "count": 11859069, "decode_str": "\u6dd8"} -{"id": 53864, "token": "\u00e8\u00b0\u0132", "merges": "\u00e8\u00b0 \u0132", "raw_count": 11870496, "count": 11870496, "decode_str": "\u8c10"} -{"id": 6755, "token": "2012", "merges": "201 2", "raw_count": 11893374, "count": 11893374, "decode_str": "2012"} -{"id": 51744, "token": "\u00e6\u0124\u0142", "merges": "\u00e6\u0124 \u0142", "raw_count": 11923832, "count": 11923832, "decode_str": "\u60a0"} -{"id": 50479, "token": "\u00e4\u00ba\u00a9", "merges": "\u00e4\u00ba \u00a9", "raw_count": 11934718, "count": 11934718, "decode_str": "\u4ea9"} -{"id": 50924, "token": "\u00e5\u0131\u0136", "merges": "\u00e5\u0131 \u0136", "raw_count": 11949572, "count": 11949572, "decode_str": "\u53d4"} -{"id": 342, "token": "\u0120with", "merges": "\u0120w ith", "raw_count": 10371478, "count": 11951239, "decode_str": " with"} -{"id": 551, "token": "\u0120{", "merges": "\u0120 {", "raw_count": 6100952, "count": 11973391, "decode_str": " {"} -{"id": 50405, "token": "\u00e4\u00b8\u012a", "merges": "\u00e4\u00b8 \u012a", "raw_count": 11980340, "count": 11980340, "decode_str": "\u4e08"} -{"id": 53712, "token": "\u00e8\u00a1\u00b0", "merges": "\u00e8\u00a1 \u00b0", "raw_count": 11982108, "count": 11982108, "decode_str": "\u8870"} -{"id": 51949, "token": "\u00e6\u012e\u00a4", "merges": "\u00e6\u012e \u00a4", "raw_count": 11995035, "count": 11995035, "decode_str": "\u6324"} -{"id": 51884, "token": "\u00e6\u012c\u00ab", "merges": "\u00e6\u012c \u00ab", "raw_count": 12025366, "count": 12025366, "decode_str": "\u62ab"} -{"id": 52982, "token": "\u00e7\u013d\u0128", "merges": "\u00e7\u013d \u0128", "raw_count": 12049769, "count": 12049769, "decode_str": "\u76c6"} -{"id": 379, "token": "her", "merges": "he r", "raw_count": 594530, "count": 12066799, "decode_str": "her"} -{"id": 51230, "token": "\u00e5\u0141\u0125", "merges": "\u00e5\u0141 \u0125", "raw_count": 12067948, "count": 12067948, "decode_str": "\u57c3"} -{"id": 50928, "token": "\u00e5\u0131\u0142", "merges": "\u00e5\u0131 \u0142", "raw_count": 12072381, "count": 12072381, "decode_str": "\u53e0"} -{"id": 51743, "token": "\u00e6\u0124\u0141", "merges": "\u00e6\u0124 \u0141", "raw_count": 12072413, "count": 12072413, "decode_str": "\u609f"} -{"id": 52800, "token": "\u00e7\u0130\u0126", "merges": "\u00e7\u0130 \u0126", "raw_count": 12079593, "count": 12079593, "decode_str": "\u7384"} -{"id": 51215, "token": "\u00e5\u0140\u0124", "merges": "\u00e5\u0140 \u0124", "raw_count": 12089437, "count": 12089437, "decode_str": "\u5782"} -{"id": 454, "token": "our", "merges": "ou r", "raw_count": 793859, "count": 12092729, "decode_str": "our"} -{"id": 2088, "token": "AP", "merges": "A P", "raw_count": 3023562, "count": 12100947, "decode_str": "AP"} -{"id": 52992, "token": "\u00e7\u013d\u0139", "merges": "\u00e7\u013d \u0139", "raw_count": 12122907, "count": 12122907, "decode_str": "\u76d7"} -{"id": 51800, "token": "\u00e6\u0127\u0137", "merges": "\u00e6\u0127 \u0137", "raw_count": 12130838, "count": 12130838, "decode_str": "\u6155"} -{"id": 51968, "token": "\u00e6\u012f\u0132", "merges": "\u00e6\u012f \u0132", "raw_count": 12139762, "count": 12139762, "decode_str": "\u6350"} -{"id": 53503, "token": "\u00e8\u0124\u00be", "merges": "\u00e8\u0124 \u00be", "raw_count": 12152468, "count": 12152468, "decode_str": "\u80be"} -{"id": 52544, "token": "\u00e6\u00b3\u00b5", "merges": "\u00e6\u00b3 \u00b5", "raw_count": 12185674, "count": 12185674, "decode_str": "\u6cf5"} -{"id": 53603, "token": "\u00e8\u012b\u00b3", "merges": "\u00e8\u012b \u00b3", "raw_count": 12185872, "count": 12185872, "decode_str": "\u8273"} -{"id": 52036, "token": "\u00e6\u0134\u00a4", "merges": "\u00e6\u0134 \u00a4", "raw_count": 12219523, "count": 12219523, "decode_str": "\u64a4"} -{"id": 53513, "token": "\u00e8\u0125\u0138", "merges": "\u00e8\u0125 \u0138", "raw_count": 12241373, "count": 12241373, "decode_str": "\u80d6"} -{"id": 52383, "token": "\u00e6\u00ac\u0142", "merges": "\u00e6\u00ac \u0142", "raw_count": 12268455, "count": 12268455, "decode_str": "\u6b20"} -{"id": 447, "token": "ies", "merges": "i es", "raw_count": 1229656, "count": 12277005, "decode_str": "ies"} -{"id": 50835, "token": "\u00e5\u012d\u0141", "merges": "\u00e5\u012d \u0141", "raw_count": 12280218, "count": 12280218, "decode_str": "\u52df"} -{"id": 51763, "token": "\u00e6\u0125\u0133", "merges": "\u00e6\u0125 \u0133", "raw_count": 12314911, "count": 12314911, "decode_str": "\u60d1"} -{"id": 50450, "token": "\u00e4\u00b9\u013b", "merges": "\u00e4\u00b9 \u013b", "raw_count": 12317110, "count": 12317110, "decode_str": "\u4e59"} -{"id": 54058, "token": "\u00e8\u00be\u00a8", "merges": "\u00e8\u00be \u00a8", "raw_count": 12331951, "count": 12331951, "decode_str": "\u8fa8"} -{"id": 1867, "token": "39", "merges": "3 9", "raw_count": 9069899, "count": 12349539, "decode_str": "39"} -{"id": 355, "token": "\u0120al", "merges": "\u0120a l", "raw_count": 569117, "count": 12378581, "decode_str": " al"} -{"id": 326, "token": "\u0120that", "merges": "\u0120th at", "raw_count": 12380645, "count": 12385107, "decode_str": " that"} -{"id": 52183, "token": "\u00e6\u013d\u00b9", "merges": "\u00e6\u013d \u00b9", "raw_count": 12436984, "count": 12436984, "decode_str": "\u66f9"} -{"id": 610, "token": "ry", "merges": "r y", "raw_count": 1392639, "count": 12447530, "decode_str": "ry"} -{"id": 52021, "token": "\u00e6\u0131\u0143", "merges": "\u00e6\u0131 \u0143", "raw_count": 12452283, "count": 12452283, "decode_str": "\u63ed"} -{"id": 2807, "token": "\")", "merges": "\" )", "raw_count": 12063321, "count": 12454340, "decode_str": "\")"} -{"id": 52663, "token": "\u00e6\u00b8\u00a1", "merges": "\u00e6\u00b8 \u00a1", "raw_count": 12455845, "count": 12455845, "decode_str": "\u6e21"} -{"id": 646, "token": "ect", "merges": "e ct", "raw_count": 208125, "count": 12486335, "decode_str": "ect"} -{"id": 53883, "token": "\u00e8\u00b0\u00a8", "merges": "\u00e8\u00b0 \u00a8", "raw_count": 12489878, "count": 12489878, "decode_str": "\u8c28"} -{"id": 8256, "token": "\u0120None", "merges": "\u0120N one", "raw_count": 12507013, "count": 12507013, "decode_str": " None"} -{"id": 53091, "token": "\u00e7\u00a2\u0139", "merges": "\u00e7\u00a2 \u0139", "raw_count": 12511593, "count": 12511593, "decode_str": "\u7897"} -{"id": 52468, "token": "\u00e6\u00b1\u0123", "merges": "\u00e6\u00b1 \u0123", "raw_count": 12518765, "count": 12518765, "decode_str": "\u6c41"} -{"id": 51874, "token": "\u00e6\u012c\u013d", "merges": "\u00e6\u012c \u013d", "raw_count": 12521994, "count": 12521994, "decode_str": "\u629b"} -{"id": 2227, "token": "85", "merges": "8 5", "raw_count": 8974286, "count": 12554856, "decode_str": "85"} -{"id": 51750, "token": "\u00e6\u0124\u00ac", "merges": "\u00e6 \u0124\u00ac", "raw_count": 12566259, "count": 12566259, "decode_str": "\u60ac"} -{"id": 538, "token": "ub", "merges": "u b", "raw_count": 1242902, "count": 12591064, "decode_str": "ub"} -{"id": 52783, "token": "\u00e7\u012b\u00a7", "merges": "\u00e7\u012b \u00a7", "raw_count": 12605820, "count": 12605820, "decode_str": "\u7267"} -{"id": 51927, "token": "\u00e6\u012d\u00b3", "merges": "\u00e6\u012d \u00b3", "raw_count": 12618465, "count": 12618465, "decode_str": "\u62f3"} -{"id": 907, "token": "ize", "merges": "iz e", "raw_count": 1803007, "count": 12647620, "decode_str": "ize"} -{"id": 5295, "token": "':", "merges": "' :", "raw_count": 12438330, "count": 12650058, "decode_str": "':"} -{"id": 2082, "token": "65", "merges": "6 5", "raw_count": 9762022, "count": 12653623, "decode_str": "65"} -{"id": 52240, "token": "\u00e6\u0140\u013f", "merges": "\u00e6\u0140 \u013f", "raw_count": 12659129, "count": 12659129, "decode_str": "\u679d"} -{"id": 52685, "token": "\u00e6\u00ba\u00aa", "merges": "\u00e6\u00ba \u00aa", "raw_count": 12727317, "count": 12727317, "decode_str": "\u6eaa"} -{"id": 451, "token": "ial", "merges": "i al", "raw_count": 510030, "count": 12732411, "decode_str": "ial"} -{"id": 51364, "token": "\u00e5\u00a7\u013e", "merges": "\u00e5\u00a7 \u013e", "raw_count": 12739994, "count": 12739994, "decode_str": "\u59dc"} -{"id": 53673, "token": "\u00e8\u0130\u00b2", "merges": "\u00e8\u0130 \u00b2", "raw_count": 12744673, "count": 12744673, "decode_str": "\u83b2"} -{"id": 2537, "token": "49", "merges": "4 9", "raw_count": 7195812, "count": 12767093, "decode_str": "49"} -{"id": 433, "token": "red", "merges": "re d", "raw_count": 1031601, "count": 12778480, "decode_str": "red"} -{"id": 52806, "token": "\u00e7\u0130\u013d", "merges": "\u00e7\u0130 \u013d", "raw_count": 12787128, "count": 12787128, "decode_str": "\u739b"} -{"id": 54121, "token": "\u00e9\u0122\u00be", "merges": "\u00e9\u0122 \u00be", "raw_count": 12795879, "count": 12795879, "decode_str": "\u903e"} -{"id": 51888, "token": "\u00e6\u012c\u00b9", "merges": "\u00e6\u012c \u00b9", "raw_count": 12796961, "count": 12796961, "decode_str": "\u62b9"} -{"id": 54528, "token": "\u00e9\u00bb\u0130", "merges": "\u00e9\u00bb \u0130", "raw_count": 12800652, "count": 12800652, "decode_str": "\u9ece"} -{"id": 547, "token": "ice", "merges": "ic e", "raw_count": 887671, "count": 12800804, "decode_str": "ice"} -{"id": 53126, "token": "\u00e7\u00a5\u00a5", "merges": "\u00e7\u00a5 \u00a5", "raw_count": 12815375, "count": 12815375, "decode_str": "\u7965"} -{"id": 636, "token": "ord", "merges": "or d", "raw_count": 654881, "count": 12828877, "decode_str": "ord"} -{"id": 51310, "token": "\u00e5\u00a5\u012a", "merges": "\u00e5\u00a5 \u012a", "raw_count": 12836413, "count": 12836413, "decode_str": "\u5948"} -{"id": 51746, "token": "\u00e6\u0124\u00a6", "merges": "\u00e6\u0124 \u00a6", "raw_count": 12848077, "count": 12848077, "decode_str": "\u60a6"} -{"id": 52589, "token": "\u00e6\u00b5\u00a9", "merges": "\u00e6\u00b5 \u00a9", "raw_count": 12853747, "count": 12853747, "decode_str": "\u6d69"} -{"id": 54207, "token": "\u00e9\u0127\u00b7", "merges": "\u00e9\u0127 \u00b7", "raw_count": 12861073, "count": 12861073, "decode_str": "\u9177"} -{"id": 3291, "token": "])", "merges": "] )", "raw_count": 10007500, "count": 12861776, "decode_str": "])"} -{"id": 50446, "token": "\u00e4\u00b9\u0136", "merges": "\u00e4\u00b9 \u0136", "raw_count": 12874326, "count": 12874326, "decode_str": "\u4e54"} -{"id": 584, "token": "ace", "merges": "ac e", "raw_count": 533325, "count": 12885557, "decode_str": "ace"} -{"id": 54592, "token": "\u00ef\u00bc\u013d", "merges": "\u00ef\u00bc \u013d", "raw_count": 12885982, "count": 12885982, "decode_str": "\uff1b"} -{"id": 429, "token": "ight", "merges": "ig ht", "raw_count": 365384, "count": 12901754, "decode_str": "ight"} -{"id": 2417, "token": "55", "merges": "5 5", "raw_count": 10555044, "count": 12948250, "decode_str": "55"} -{"id": 3967, "token": "path", "merges": "p ath", "raw_count": 12426453, "count": 12954192, "decode_str": "path"} -{"id": 53052, "token": "\u00e7\u0142\u0124", "merges": "\u00e7\u0142 \u0124", "raw_count": 12957183, "count": 12957183, "decode_str": "\u7802"} -{"id": 52202, "token": "\u00e6\u013e\u00b5", "merges": "\u00e6\u013e \u00b5", "raw_count": 12969338, "count": 12969338, "decode_str": "\u6735"} -{"id": 51089, "token": "\u00e5\u0137\u00a1", "merges": "\u00e5\u0137 \u00a1", "raw_count": 12993099, "count": 12993099, "decode_str": "\u5561"} -{"id": 51969, "token": "\u00e6\u012f\u0137", "merges": "\u00e6\u012f \u0137", "raw_count": 13002496, "count": 13002496, "decode_str": "\u6355"} -{"id": 53475, "token": "\u00e8\u0124\u0125", "merges": "\u00e8\u0124 \u0125", "raw_count": 13005880, "count": 13005880, "decode_str": "\u8083"} -{"id": 352, "token": "\u0120it", "merges": "\u0120 it", "raw_count": 6509082, "count": 13022118, "decode_str": " it"} -{"id": 52935, "token": "\u00e7\u0139\u0137", "merges": "\u00e7\u0139 \u0137", "raw_count": 13022975, "count": 13022975, "decode_str": "\u75d5"} -{"id": 53411, "token": "\u00e7\u00bd\u0132", "merges": "\u00e7\u00bd \u0132", "raw_count": 13059198, "count": 13059198, "decode_str": "\u7f50"} -{"id": 51115, "token": "\u00e5\u0138\u012c", "merges": "\u00e5\u0138 \u012c", "raw_count": 13070490, "count": 13070490, "decode_str": "\u558a"} -{"id": 51374, "token": "\u00e5\u00a7\u00bf", "merges": "\u00e5\u00a7 \u00bf", "raw_count": 13073175, "count": 13073175, "decode_str": "\u59ff"} -{"id": 52594, "token": "\u00e6\u00b5\u00b4", "merges": "\u00e6\u00b5 \u00b4", "raw_count": 13073651, "count": 13073651, "decode_str": "\u6d74"} -{"id": 51077, "token": "\u00e5\u0135\u00b2", "merges": "\u00e5\u0135 \u00b2", "raw_count": 13077673, "count": 13077673, "decode_str": "\u54f2"} -{"id": 53950, "token": "\u00e8\u00b5\u012d", "merges": "\u00e8\u00b5 \u012d", "raw_count": 13078036, "count": 13078036, "decode_str": "\u8d4b"} -{"id": 51449, "token": "\u00e5\u00af\u00ba", "merges": "\u00e5\u00af \u00ba", "raw_count": 13079818, "count": 13079818, "decode_str": "\u5bfa"} -{"id": 51727, "token": "\u00e6\u0123\u00b0", "merges": "\u00e6\u0123 \u00b0", "raw_count": 13086763, "count": 13086763, "decode_str": "\u6070"} -{"id": 53165, "token": "\u00e7\u00a8\u0122", "merges": "\u00e7\u00a8 \u0122", "raw_count": 13090028, "count": 13090028, "decode_str": "\u7a00"} -{"id": 51611, "token": "\u00e5\u00bc\u00af", "merges": "\u00e5\u00bc \u00af", "raw_count": 13092112, "count": 13092112, "decode_str": "\u5f2f"} -{"id": 389, "token": "\u0120com", "merges": "\u0120c om", "raw_count": 161324, "count": 13099042, "decode_str": " com"} -{"id": 54073, "token": "\u00e8\u00bf\u012a", "merges": "\u00e8\u00bf \u012a", "raw_count": 13107615, "count": 13107615, "decode_str": "\u8fc8"} -{"id": 54223, "token": "\u00e9\u0136\u012a", "merges": "\u00e9\u0136 \u012a", "raw_count": 13142001, "count": 13142001, "decode_str": "\u9508"} -{"id": 52270, "token": "\u00e6\u0141\u00b3", "merges": "\u00e6\u0141 \u00b3", "raw_count": 13146599, "count": 13146599, "decode_str": "\u67f3"} -{"id": 53330, "token": "\u00e7\u00ba\u00bd", "merges": "\u00e7\u00ba \u00bd", "raw_count": 13150561, "count": 13150561, "decode_str": "\u7ebd"} -{"id": 630, "token": "form", "merges": "f orm", "raw_count": 1994760, "count": 13186931, "decode_str": "form"} -{"id": 51662, "token": "\u00e5\u00be\u00bd", "merges": "\u00e5\u00be \u00bd", "raw_count": 13190517, "count": 13190517, "decode_str": "\u5fbd"} -{"id": 51889, "token": "\u00e6\u012c\u00bc", "merges": "\u00e6\u012c \u00bc", "raw_count": 13222908, "count": 13222908, "decode_str": "\u62bc"} -{"id": 50946, "token": "\u00e5\u0131\u00b9", "merges": "\u00e5\u0131 \u00b9", "raw_count": 13240090, "count": 13240090, "decode_str": "\u53f9"} -{"id": 50842, "token": "\u00e5\u012e\u0122", "merges": "\u00e5\u012e \u0122", "raw_count": 13246823, "count": 13246823, "decode_str": "\u5300"} -{"id": 52117, "token": "\u00e6\u0139\u00a8", "merges": "\u00e6\u0139 \u00a8", "raw_count": 13250246, "count": 13250246, "decode_str": "\u65e8"} -{"id": 53440, "token": "\u00e7\u00be\u00bd", "merges": "\u00e7\u00be \u00bd", "raw_count": 13284111, "count": 13284111, "decode_str": "\u7fbd"} -{"id": 52901, "token": "\u00e7\u0138\u0131", "merges": "\u00e7\u0138 \u0131", "raw_count": 13306250, "count": 13306250, "decode_str": "\u758f"} -{"id": 385, "token": "\u0120ex", "merges": "\u0120e x", "raw_count": 371040, "count": 13308564, "decode_str": " ex"} -{"id": 54120, "token": "\u00e9\u0122\u00bc", "merges": "\u00e9\u0122 \u00bc", "raw_count": 13309848, "count": 13309848, "decode_str": "\u903c"} -{"id": 51866, "token": "\u00e6\u012c\u0133", "merges": "\u00e6\u012c \u0133", "raw_count": 13339881, "count": 13339881, "decode_str": "\u6291"} -{"id": 54288, "token": "\u00e9\u013a\u0122", "merges": "\u00e9\u013a \u0122", "raw_count": 13354271, "count": 13354271, "decode_str": "\u9600"} -{"id": 53188, "token": "\u00e7\u00a9\u00b7", "merges": "\u00e7\u00a9 \u00b7", "raw_count": 13359452, "count": 13359452, "decode_str": "\u7a77"} -{"id": 51653, "token": "\u00e5\u00be\u00a1", "merges": "\u00e5\u00be \u00a1", "raw_count": 13370785, "count": 13370785, "decode_str": "\u5fa1"} -{"id": 50804, "token": "\u00e5\u012b\u00aa", "merges": "\u00e5\u012b \u00aa", "raw_count": 13385329, "count": 13385329, "decode_str": "\u526a"} -{"id": 54370, "token": "\u00e9\u013d\u0137", "merges": "\u00e9\u013d \u0137", "raw_count": 13385835, "count": 13385835, "decode_str": "\u96d5"} -{"id": 50806, "token": "\u00e5\u012b\u00b2", "merges": "\u00e5\u012b \u00b2", "raw_count": 13395237, "count": 13395237, "decode_str": "\u5272"} -{"id": 1662, "token": "arg", "merges": "ar g", "raw_count": 1455290, "count": 13410344, "decode_str": "arg"} -{"id": 608, "token": "\u01205", "merges": "\u0120 5", "raw_count": 9447387, "count": 13446019, "decode_str": " 5"} -{"id": 53560, "token": "\u00e8\u0129\u00a3", "merges": "\u00e8\u0129 \u00a3", "raw_count": 13470294, "count": 13470294, "decode_str": "\u81e3"} -{"id": 54238, "token": "\u00e9\u0136\u00a6", "merges": "\u00e9\u0136 \u00a6", "raw_count": 13473382, "count": 13473382, "decode_str": "\u9526"} -{"id": 2222, "token": "95", "merges": "9 5", "raw_count": 10131229, "count": 13526526, "decode_str": "95"} -{"id": 52859, "token": "\u00e7\u0132\u00b4", "merges": "\u00e7\u0132 \u00b4", "raw_count": 13530852, "count": 13530852, "decode_str": "\u7434"} -{"id": 52900, "token": "\u00e7\u0138\u0128", "merges": "\u00e7\u0138 \u0128", "raw_count": 13543611, "count": 13543611, "decode_str": "\u7586"} -{"id": 53077, "token": "\u00e7\u00a1\u0137", "merges": "\u00e7\u00a1 \u0137", "raw_count": 13568044, "count": 13568044, "decode_str": "\u7855"} -{"id": 51305, "token": "\u00e5\u00a4\u00b9", "merges": "\u00e5\u00a4 \u00b9", "raw_count": 13616909, "count": 13616909, "decode_str": "\u5939"} -{"id": 51358, "token": "\u00e5\u00a7\u0133", "merges": "\u00e5\u00a7 \u0133", "raw_count": 13695713, "count": 13695713, "decode_str": "\u59d1"} -{"id": 471, "token": "ack", "merges": "ac k", "raw_count": 626952, "count": 13699233, "decode_str": "ack"} -{"id": 54619, "token": "\u00ef\u00bc\u00bf", "merges": "\u00ef\u00bc \u00bf", "raw_count": 13718539, "count": 13718539, "decode_str": " "} -{"id": 1976, "token": "75", "merges": "7 5", "raw_count": 10592117, "count": 13727059, "decode_str": "75"} -{"id": 52180, "token": "\u00e6\u013d\u00b0", "merges": "\u00e6\u013d \u00b0", "raw_count": 13734867, "count": 13734867, "decode_str": "\u66f0"} -{"id": 51814, "token": "\u00e6\u012a\u0134", "merges": "\u00e6\u012a \u0134", "raw_count": 13765164, "count": 13765164, "decode_str": "\u6212"} -{"id": 52427, "token": "\u00e6\u00af\u0123", "merges": "\u00e6\u00af \u0123", "raw_count": 13767250, "count": 13767250, "decode_str": "\u6bc1"} -{"id": 1706, "token": "34", "merges": "3 4", "raw_count": 9791266, "count": 13774415, "decode_str": "34"} -{"id": 409, "token": "rom", "merges": "ro m", "raw_count": 447915, "count": 13776393, "decode_str": "rom"} -{"id": 53889, "token": "\u00e8\u00b0\u00b1", "merges": "\u00e8\u00b0 \u00b1", "raw_count": 13798610, "count": 13798610, "decode_str": "\u8c31"} -{"id": 50873, "token": "\u00e5\u012f\u0135", "merges": "\u00e5\u012f \u0135", "raw_count": 13801207, "count": 13801207, "decode_str": "\u5353"} -{"id": 53470, "token": "\u00e8\u0123\u013a", "merges": "\u00e8\u0123 \u013a", "raw_count": 13819905, "count": 13819905, "decode_str": "\u8058"} -{"id": 1087, "token": "pr", "merges": "p r", "raw_count": 1562715, "count": 13822206, "decode_str": "pr"} -{"id": 468, "token": "per", "merges": "p er", "raw_count": 1577868, "count": 13822846, "decode_str": "per"} -{"id": 484, "token": "up", "merges": "u p", "raw_count": 2543540, "count": 13824168, "decode_str": "up"} -{"id": 21382, "token": ":[", "merges": ": [", "raw_count": 13852804, "count": 13852804, "decode_str": ":["} -{"id": 54398, "token": "\u00e9\u013e\u00b8", "merges": "\u00e9\u013e \u00b8", "raw_count": 13863017, "count": 13863017, "decode_str": "\u9738"} -{"id": 6914, "token": "2000", "merges": "2 000", "raw_count": 13875934, "count": 13875934, "decode_str": "2000"} -{"id": 404, "token": "ain", "merges": "a in", "raw_count": 793142, "count": 13894345, "decode_str": "ain"} -{"id": 553, "token": "ime", "merges": "im e", "raw_count": 747436, "count": 13908144, "decode_str": "ime"} -{"id": 410, "token": "ore", "merges": "o re", "raw_count": 817068, "count": 13933421, "decode_str": "ore"} -{"id": 308, "token": "\u0120T", "merges": "\u0120 T", "raw_count": 1528831, "count": 13940309, "decode_str": " T"} -{"id": 50613, "token": "\u00e4\u00bf\u00b1", "merges": "\u00e4\u00bf \u00b1", "raw_count": 13960137, "count": 13960137, "decode_str": "\u4ff1"} -{"id": 53825, "token": "\u00e8\u00af\u0140", "merges": "\u00e8\u00af \u0140", "raw_count": 14042199, "count": 14042199, "decode_str": "\u8bde"} -{"id": 1787, "token": "37", "merges": "3 7", "raw_count": 9450859, "count": 14051540, "decode_str": "37"} -{"id": 51798, "token": "\u00e6\u0127\u0130", "merges": "\u00e6\u0127 \u0130", "raw_count": 14052528, "count": 14052528, "decode_str": "\u614e"} -{"id": 2055, "token": "88", "merges": "8 8", "raw_count": 9291807, "count": 14056830, "decode_str": "88"} -{"id": 51522, "token": "\u00e5\u00b8\u0127", "merges": "\u00e5\u00b8 \u0127", "raw_count": 14089696, "count": 14089696, "decode_str": "\u5e05"} -{"id": 52124, "token": "\u00e6\u0139\u00ba", "merges": "\u00e6\u0139 \u00ba", "raw_count": 14092286, "count": 14092286, "decode_str": "\u65fa"} -{"id": 390, "token": "\u0120or", "merges": "\u0120o r", "raw_count": 9661788, "count": 14121053, "decode_str": " or"} -{"id": 414, "token": "ity", "merges": "it y", "raw_count": 1039588, "count": 14128774, "decode_str": "ity"} -{"id": 93, "token": "|", "merges": "NULL", "raw_count": 9310599, "count": 14154986, "decode_str": "|"} -{"id": 400, "token": "iv", "merges": "i v", "raw_count": 1002841, "count": 14170764, "decode_str": "iv"} -{"id": 51885, "token": "\u00e6\u012c\u00ac", "merges": "\u00e6\u012c \u00ac", "raw_count": 14199171, "count": 14199171, "decode_str": "\u62ac"} -{"id": 54169, "token": "\u00e9\u0125\u0123", "merges": "\u00e9\u0125 \u0123", "raw_count": 14219503, "count": 14219503, "decode_str": "\u90c1"} -{"id": 53182, "token": "\u00e7\u00a8\u00bf", "merges": "\u00e7\u00a8 \u00bf", "raw_count": 14316119, "count": 14316119, "decode_str": "\u7a3f"} -{"id": 54057, "token": "\u00e8\u00be\u00a3", "merges": "\u00e8\u00be \u00a3", "raw_count": 14346642, "count": 14346642, "decode_str": "\u8fa3"} -{"id": 460, "token": "ine", "merges": "in e", "raw_count": 1356691, "count": 14373685, "decode_str": "ine"} -{"id": 50955, "token": "\u00e5\u0132\u012c", "merges": "\u00e5\u0132 \u012c", "raw_count": 14393010, "count": 14393010, "decode_str": "\u540a"} -{"id": 50706, "token": "\u00e5\u0127\u00bd", "merges": "\u00e5\u0127 \u00bd", "raw_count": 14420462, "count": 14420462, "decode_str": "\u517d"} -{"id": 52573, "token": "\u00e6\u00b5\u0127", "merges": "\u00e6\u00b5 \u0127", "raw_count": 14457927, "count": 14457927, "decode_str": "\u6d45"} -{"id": 53057, "token": "\u00e7\u0142\u0138", "merges": "\u00e7\u0142 \u0138", "raw_count": 14460386, "count": 14460386, "decode_str": "\u7816"} -{"id": 50857, "token": "\u00e5\u012e\u00b9", "merges": "\u00e5\u012e \u00b9", "raw_count": 14474667, "count": 14474667, "decode_str": "\u5339"} -{"id": 53419, "token": "\u00e7\u00bd\u00a9", "merges": "\u00e7\u00bd \u00a9", "raw_count": 14479353, "count": 14479353, "decode_str": "\u7f69"} -{"id": 53002, "token": "\u00e7\u013d\u00be", "merges": "\u00e7\u013d \u00be", "raw_count": 14484939, "count": 14484939, "decode_str": "\u76fe"} -{"id": 2650, "token": "~~", "merges": "~ ~", "raw_count": 9512274, "count": 14494967, "decode_str": "~~"} -{"id": 54182, "token": "\u00e9\u0125\u0143", "merges": "\u00e9\u0125 \u0143", "raw_count": 14496907, "count": 14496907, "decode_str": "\u90ed"} -{"id": 1839, "token": "38", "merges": "3 8", "raw_count": 10932542, "count": 14504641, "decode_str": "38"} -{"id": 53247, "token": "\u00e7\u00ae\u0143", "merges": "\u00e7\u00ae \u0143", "raw_count": 14516974, "count": 14516974, "decode_str": "\u7bad"} -{"id": 481, "token": ").", "merges": ") .", "raw_count": 7949075, "count": 14542132, "decode_str": ")."} -{"id": 51389, "token": "\u00e5\u0143\u00a4", "merges": "\u00e5\u0143 \u00a4", "raw_count": 14611602, "count": 14611602, "decode_str": "\u5b64"} -{"id": 52170, "token": "\u00e6\u013b\u00b0", "merges": "\u00e6\u013b \u00b0", "raw_count": 14621316, "count": 14621316, "decode_str": "\u6670"} -{"id": 315, "token": "----", "merges": "-- --", "raw_count": 1275780, "count": 14627177, "decode_str": "----"} -{"id": 50679, "token": "\u00e5\u0127\u0123", "merges": "\u00e5\u0127 \u0123", "raw_count": 14667915, "count": 14667915, "decode_str": "\u5141"} -{"id": 35199, "token": "\u00e2\u0122\u0137", "merges": "\u00e2\u0122 \u0137", "raw_count": 14678131, "count": 14678131, "decode_str": "\u2015"} -{"id": 7, "token": "&", "merges": "NULL", "raw_count": 10437833, "count": 14687921, "decode_str": "&"} -{"id": 52787, "token": "\u00e7\u012b\u00b5", "merges": "\u00e7\u012b \u00b5", "raw_count": 14703534, "count": 14703534, "decode_str": "\u7275"} -{"id": 53729, "token": "\u00e8\u00a2\u0143", "merges": "\u00e8\u00a2 \u0143", "raw_count": 14708645, "count": 14708645, "decode_str": "\u88ad"} -{"id": 5013, "token": "['", "merges": "[ '", "raw_count": 12756871, "count": 14752095, "decode_str": "['"} -{"id": 3031, "token": "199", "merges": "19 9", "raw_count": 1887045, "count": 14755298, "decode_str": "199"} -{"id": 53009, "token": "\u00e7\u013e\u0142", "merges": "\u00e7\u013e \u0142", "raw_count": 14761357, "count": 14761357, "decode_str": "\u7720"} -{"id": 9138, "token": "1000", "merges": "1 000", "raw_count": 14767569, "count": 14767569, "decode_str": "1000"} -{"id": 54135, "token": "\u00e9\u0123\u00a5", "merges": "\u00e9\u0123 \u00a5", "raw_count": 14789687, "count": 14789687, "decode_str": "\u9065"} -{"id": 424, "token": "**", "merges": "* *", "raw_count": 4319523, "count": 14811735, "decode_str": "**"} -{"id": 51013, "token": "\u00e5\u0133\u00bc", "merges": "\u00e5\u0133 \u00bc", "raw_count": 14841224, "count": 14841224, "decode_str": "\u547c"} -{"id": 856, "token": "pro", "merges": "p ro", "raw_count": 3757500, "count": 14848351, "decode_str": "pro"} -{"id": 52321, "token": "\u00e6\u00a3\u012b", "merges": "\u00e6\u00a3 \u012b", "raw_count": 14863051, "count": 14863051, "decode_str": "\u68c9"} -{"id": 795, "token": "\u0120_", "merges": "\u0120 _", "raw_count": 8421042, "count": 14895616, "decode_str": " _"} -{"id": 51311, "token": "\u00e5\u00a5\u012b", "merges": "\u00e5\u00a5 \u012b", "raw_count": 14946050, "count": 14946050, "decode_str": "\u5949"} -{"id": 53442, "token": "\u00e8\u0122\u0122", "merges": "\u00e8\u0122 \u0122", "raw_count": 15016341, "count": 15016341, "decode_str": "\u8000"} -{"id": 52537, "token": "\u00e6\u00b3\u00aa", "merges": "\u00e6\u00b3 \u00aa", "raw_count": 15028094, "count": 15028094, "decode_str": "\u6cea"} -{"id": 51584, "token": "\u00e5\u00bb\u012b", "merges": "\u00e5\u00bb \u012b", "raw_count": 15041591, "count": 15041591, "decode_str": "\u5ec9"} -{"id": 54055, "token": "\u00e8\u00be\u0140", "merges": "\u00e8\u00be \u0140", "raw_count": 15088426, "count": 15088426, "decode_str": "\u8f9e"} -{"id": 52318, "token": "\u00e6\u00a1\u00b6", "merges": "\u00e6\u00a1 \u00b6", "raw_count": 15125385, "count": 15125385, "decode_str": "\u6876"} -{"id": 52693, "token": "\u00e6\u00bc\u0128", "merges": "\u00e6\u00bc \u0128", "raw_count": 15160022, "count": 15160022, "decode_str": "\u6f06"} -{"id": 51636, "token": "\u00e5\u00bd\u00bc", "merges": "\u00e5\u00bd \u00bc", "raw_count": 15163803, "count": 15163803, "decode_str": "\u5f7c"} -{"id": 52420, "token": "\u00e6\u00ae\u0138", "merges": "\u00e6\u00ae \u0138", "raw_count": 15164294, "count": 15164294, "decode_str": "\u6b96"} -{"id": 483, "token": "out", "merges": "ou t", "raw_count": 5276355, "count": 15167982, "decode_str": "out"} -{"id": 51283, "token": "\u00e5\u00a3\u00b3", "merges": "\u00e5\u00a3 \u00b3", "raw_count": 15169064, "count": 15169064, "decode_str": "\u58f3"} -{"id": 51009, "token": "\u00e5\u0133\u00b5", "merges": "\u00e5\u0133 \u00b5", "raw_count": 15178086, "count": 15178086, "decode_str": "\u5475"} -{"id": 1610, "token": "33", "merges": "3 3", "raw_count": 10996166, "count": 15186823, "decode_str": "33"} -{"id": 52152, "token": "\u00e6\u013b\u012d", "merges": "\u00e6\u013b \u012d", "raw_count": 15195715, "count": 15195715, "decode_str": "\u664b"} -{"id": 51554, "token": "\u00e5\u00b9\u00bb", "merges": "\u00e5\u00b9 \u00bb", "raw_count": 15215141, "count": 15215141, "decode_str": "\u5e7b"} -{"id": 52623, "token": "\u00e6\u00b6\u00b5", "merges": "\u00e6\u00b6 \u00b5", "raw_count": 15215614, "count": 15215614, "decode_str": "\u6db5"} -{"id": 52282, "token": "\u00e6\u0142\u0131", "merges": "\u00e6\u0142 \u0131", "raw_count": 15218180, "count": 15218180, "decode_str": "\u680f"} -{"id": 54337, "token": "\u00e9\u013b\u00b6", "merges": "\u00e9\u013b \u00b6", "raw_count": 15238426, "count": 15238426, "decode_str": "\u9676"} -{"id": 61, "token": "\\", "merges": "NULL", "raw_count": 4778466, "count": 15238691, "decode_str": "\\"} -{"id": 5136, "token": ":\"", "merges": ": \"", "raw_count": 15280845, "count": 15280845, "decode_str": ":\""} -{"id": 50958, "token": "\u00e5\u0132\u0132", "merges": "\u00e5\u0132 \u0132", "raw_count": 15284594, "count": 15284594, "decode_str": "\u5410"} -{"id": 53494, "token": "\u00e8\u0124\u00a9", "merges": "\u00e8\u0124 \u00a9", "raw_count": 15318060, "count": 15318060, "decode_str": "\u80a9"} -{"id": 52799, "token": "\u00e7\u012c\u00b9", "merges": "\u00e7\u012c \u00b9", "raw_count": 15328949, "count": 15328949, "decode_str": "\u72b9"} -{"id": 3401, "token": "')", "merges": "' )", "raw_count": 15061481, "count": 15332870, "decode_str": "')"} -{"id": 53346, "token": "\u00e7\u00bb\u013a", "merges": "\u00e7\u00bb \u013a", "raw_count": 15341038, "count": 15341038, "decode_str": "\u7ed8"} -{"id": 51947, "token": "\u00e6\u012e\u00a1", "merges": "\u00e6\u012e \u00a1", "raw_count": 15411933, "count": 15411933, "decode_str": "\u6321"} -{"id": 51939, "token": "\u00e6\u012e\u0138", "merges": "\u00e6\u012e \u0138", "raw_count": 15429593, "count": 15429593, "decode_str": "\u6316"} -{"id": 53100, "token": "\u00e7\u00a2\u00b3", "merges": "\u00e7\u00a2 \u00b3", "raw_count": 15436450, "count": 15436450, "decode_str": "\u78b3"} -{"id": 2203, "token": "data", "merges": "d ata", "raw_count": 15475394, "count": 15475394, "decode_str": "data"} -{"id": 1208, "token": "val", "merges": "v al", "raw_count": 2606201, "count": 15484885, "decode_str": "val"} -{"id": 1065, "token": "put", "merges": "p ut", "raw_count": 537825, "count": 15492491, "decode_str": "put"} -{"id": 570, "token": "ne", "merges": "n e", "raw_count": 1498962, "count": 15516890, "decode_str": "ne"} -{"id": 52893, "token": "\u00e7\u0137\u00aa", "merges": "\u00e7\u0137 \u00aa", "raw_count": 15523864, "count": 15523864, "decode_str": "\u756a"} -{"id": 340, "token": "\u0120y", "merges": "\u0120 y", "raw_count": 5122026, "count": 15578221, "decode_str": " y"} -{"id": 50468, "token": "\u00e4\u00ba\u0137", "merges": "\u00e4\u00ba \u0137", "raw_count": 15586809, "count": 15586809, "decode_str": "\u4e95"} -{"id": 51027, "token": "\u00e5\u0134\u0138", "merges": "\u00e5\u0134 \u0138", "raw_count": 15589895, "count": 15589895, "decode_str": "\u5496"} -{"id": 53087, "token": "\u00e7\u00a2\u012f", "merges": "\u00e7\u00a2 \u012f", "raw_count": 15633830, "count": 15633830, "decode_str": "\u788d"} -{"id": 372, "token": "\u0120de", "merges": "\u0120d e", "raw_count": 1124909, "count": 15651208, "decode_str": " de"} -{"id": 52475, "token": "\u00e6\u00b1\u0139", "merges": "\u00e6\u00b1 \u0139", "raw_count": 15689483, "count": 15689483, "decode_str": "\u6c57"} -{"id": 53324, "token": "\u00e7\u00ba\u00b5", "merges": "\u00e7\u00ba \u00b5", "raw_count": 15699597, "count": 15699597, "decode_str": "\u7eb5"} -{"id": 53308, "token": "\u00e7\u00ba\u0142", "merges": "\u00e7\u00ba \u0142", "raw_count": 15732512, "count": 15732512, "decode_str": "\u7ea0"} -{"id": 2188, "token": "mm", "merges": "m m", "raw_count": 15323737, "count": 15762715, "decode_str": "mm"} -{"id": 51314, "token": "\u00e5\u00a5\u0131", "merges": "\u00e5\u00a5 \u0131", "raw_count": 15784797, "count": 15784797, "decode_str": "\u594f"} -{"id": 52269, "token": "\u00e6\u0141\u00b1", "merges": "\u00e6\u0141 \u00b1", "raw_count": 15785594, "count": 15785594, "decode_str": "\u67f1"} -{"id": 52089, "token": "\u00e6\u0138\u0133", "merges": "\u00e6\u0138 \u0133", "raw_count": 15797560, "count": 15797560, "decode_str": "\u6591"} -{"id": 52769, "token": "\u00e7\u012a\u00bd", "merges": "\u00e7\u012a \u00bd", "raw_count": 15801979, "count": 15801979, "decode_str": "\u723d"} -{"id": 53504, "token": "\u00e8\u0124\u00bf", "merges": "\u00e8\u0124 \u00bf", "raw_count": 15807289, "count": 15807289, "decode_str": "\u80bf"} -{"id": 52222, "token": "\u00e6\u013f\u0143", "merges": "\u00e6\u013f \u0143", "raw_count": 15827133, "count": 15827133, "decode_str": "\u676d"} -{"id": 51920, "token": "\u00e6\u012d\u00a8", "merges": "\u00e6\u012d \u00a8", "raw_count": 15844437, "count": 15844437, "decode_str": "\u62e8"} -{"id": 53394, "token": "\u00e7\u00bc\u013f", "merges": "\u00e7\u00bc \u013f", "raw_count": 15852664, "count": 15852664, "decode_str": "\u7f1d"} -{"id": 53005, "token": "\u00e7\u013e\u012b", "merges": "\u00e7\u013e \u012b", "raw_count": 15870314, "count": 15870314, "decode_str": "\u7709"} -{"id": 53909, "token": "\u00e8\u00b2\u012e", "merges": "\u00e8\u00b2 \u012e", "raw_count": 15883080, "count": 15883080, "decode_str": "\u8c8c"} -{"id": 6622, "token": "2013", "merges": "201 3", "raw_count": 15925410, "count": 15925410, "decode_str": "2013"} -{"id": 522, "token": "ap", "merges": "a p", "raw_count": 2821217, "count": 15949404, "decode_str": "ap"} -{"id": 51246, "token": "\u00e5\u0142\u0128", "merges": "\u00e5\u0142 \u0128", "raw_count": 15957092, "count": 15957092, "decode_str": "\u5806"} -{"id": 50419, "token": "\u00e4\u00b8\u00a2", "merges": "\u00e4\u00b8 \u00a2", "raw_count": 15959369, "count": 15959369, "decode_str": "\u4e22"} -{"id": 50768, "token": "\u00e5\u012a\u012c", "merges": "\u00e5\u012a \u012c", "raw_count": 15982550, "count": 15982550, "decode_str": "\u520a"} -{"id": 347, "token": "\u0120as", "merges": "\u0120a s", "raw_count": 11332646, "count": 15984743, "decode_str": " as"} -{"id": 53264, "token": "\u00e7\u00b2\u013a", "merges": "\u00e7\u00b2 \u013a", "raw_count": 15990833, "count": 15990833, "decode_str": "\u7c98"} -{"id": 50733, "token": "\u00e5\u0128\u00bb", "merges": "\u00e5\u0128 \u00bb", "raw_count": 16013662, "count": 16013662, "decode_str": "\u51bb"} -{"id": 54101, "token": "\u00e9\u0122\u0128", "merges": "\u00e9\u0122 \u0128", "raw_count": 16036742, "count": 16036742, "decode_str": "\u9006"} -{"id": 51693, "token": "\u00e6\u0122\u0134", "merges": "\u00e6\u0122 \u0134", "raw_count": 16090475, "count": 16090475, "decode_str": "\u6012"} -{"id": 50464, "token": "\u00e4\u00ba\u0131", "merges": "\u00e4\u00ba \u0131", "raw_count": 16091117, "count": 16091117, "decode_str": "\u4e8f"} -{"id": 53311, "token": "\u00e7\u00ba\u00a4", "merges": "\u00e7\u00ba \u00a4", "raw_count": 16145722, "count": 16145722, "decode_str": "\u7ea4"} -{"id": 445, "token": "ren", "merges": "re n", "raw_count": 806812, "count": 16195902, "decode_str": "ren"} -{"id": 54042, "token": "\u00e8\u00be\u012b", "merges": "\u00e8\u00be \u012b", "raw_count": 16206106, "count": 16206106, "decode_str": "\u8f89"} -{"id": 51753, "token": "\u00e6\u0124\u00b2", "merges": "\u00e6\u0124 \u00b2", "raw_count": 16233700, "count": 16233700, "decode_str": "\u60b2"} -{"id": 555, "token": "ty", "merges": "t y", "raw_count": 975271, "count": 16242712, "decode_str": "ty"} -{"id": 853, "token": "ode", "merges": "od e", "raw_count": 440894, "count": 16261701, "decode_str": "ode"} -{"id": 6759, "token": "2014", "merges": "201 4", "raw_count": 16264080, "count": 16264080, "decode_str": "2014"} -{"id": 50650, "token": "\u00e5\u0123\u00b7", "merges": "\u00e5\u0123 \u00b7", "raw_count": 16302859, "count": 16302859, "decode_str": "\u5077"} -{"id": 51494, "token": "\u00e5\u00b1\u00a5", "merges": "\u00e5\u00b1 \u00a5", "raw_count": 16349578, "count": 16349578, "decode_str": "\u5c65"} -{"id": 53606, "token": "\u00e8\u012b\u00be", "merges": "\u00e8\u012b \u00be", "raw_count": 16351615, "count": 16351615, "decode_str": "\u827e"} -{"id": 54283, "token": "\u00e9\u0139\u00b9", "merges": "\u00e9\u0139 \u00b9", "raw_count": 16391841, "count": 16391841, "decode_str": "\u95f9"} -{"id": 53740, "token": "\u00e8\u00a3\u00a4", "merges": "\u00e8\u00a3 \u00a4", "raw_count": 16403820, "count": 16403820, "decode_str": "\u88e4"} -{"id": 50902, "token": "\u00e5\u0130\u012b", "merges": "\u00e5\u0130 \u012b", "raw_count": 16405890, "count": 16405890, "decode_str": "\u5389"} -{"id": 463, "token": "ge", "merges": "g e", "raw_count": 1199302, "count": 16411480, "decode_str": "ge"} -{"id": 54379, "token": "\u00e9\u013d\u00be", "merges": "\u00e9\u013d \u00be", "raw_count": 16438913, "count": 16438913, "decode_str": "\u96fe"} -{"id": 327, "token": "\u0120on", "merges": "\u0120 on", "raw_count": 11321494, "count": 16473396, "decode_str": " on"} -{"id": 577, "token": "\u01204", "merges": "\u0120 4", "raw_count": 11863712, "count": 16516814, "decode_str": " 4"} -{"id": 2295, "token": "\u0120==", "merges": "\u0120 ==", "raw_count": 16534407, "count": 16546082, "decode_str": " =="} -{"id": 320, "token": "\u0120be", "merges": "\u0120b e", "raw_count": 9691328, "count": 16548946, "decode_str": " be"} -{"id": 54140, "token": "\u00e9\u0123\u00b5", "merges": "\u00e9\u0123 \u00b5", "raw_count": 16619772, "count": 16619772, "decode_str": "\u9075"} -{"id": 52450, "token": "\u00e6\u00b0\u013d", "merges": "\u00e6\u00b0 \u013d", "raw_count": 16642180, "count": 16642180, "decode_str": "\u6c1b"} -{"id": 52035, "token": "\u00e6\u0134\u0140", "merges": "\u00e6\u0134 \u0140", "raw_count": 16647416, "count": 16647416, "decode_str": "\u649e"} -{"id": 51075, "token": "\u00e5\u0135\u0143", "merges": "\u00e5\u0135 \u0143", "raw_count": 16673032, "count": 16673032, "decode_str": "\u54ed"} -{"id": 51206, "token": "\u00e5\u013f\u00a1", "merges": "\u00e5\u013f \u00a1", "raw_count": 16714046, "count": 16714046, "decode_str": "\u5761"} -{"id": 427, "token": "\u0120N", "merges": "\u0120 N", "raw_count": 1161974, "count": 16763109, "decode_str": " N"} -{"id": 50754, "token": "\u00e5\u0129\u00af", "merges": "\u00e5\u0129 \u00af", "raw_count": 16782305, "count": 16782305, "decode_str": "\u51ef"} -{"id": 51316, "token": "\u00e5\u00a5\u0136", "merges": "\u00e5\u00a5 \u0136", "raw_count": 16802864, "count": 16802864, "decode_str": "\u5954"} -{"id": 455, "token": "all", "merges": "al l", "raw_count": 4608995, "count": 16805433, "decode_str": "all"} -{"id": 2385, "token": "48", "merges": "4 8", "raw_count": 15078307, "count": 16815944, "decode_str": "48"} -{"id": 5056, "token": "long", "merges": "l ong", "raw_count": 16804184, "count": 16822016, "decode_str": "long"} -{"id": 52299, "token": "\u00e6\u00a1\u0128", "merges": "\u00e6\u00a1 \u0128", "raw_count": 16827286, "count": 16827286, "decode_str": "\u6846"} -{"id": 3333, "token": "._", "merges": ". _", "raw_count": 16857247, "count": 16857247, "decode_str": "._"} -{"id": 8271, "token": "assert", "merges": "ass ert", "raw_count": 12043217, "count": 16896899, "decode_str": "assert"} -{"id": 53201, "token": "\u00e7\u00ab\u00b9", "merges": "\u00e7\u00ab \u00b9", "raw_count": 16913120, "count": 16913120, "decode_str": "\u7af9"} -{"id": 50436, "token": "\u00e4\u00b9\u0125", "merges": "\u00e4\u00b9 \u0125", "raw_count": 16934168, "count": 16934168, "decode_str": "\u4e43"} -{"id": 51767, "token": "\u00e6\u0125\u013e", "merges": "\u00e6\u0125 \u013e", "raw_count": 16958377, "count": 16958377, "decode_str": "\u60dc"} -{"id": 52561, "token": "\u00e6\u00b4\u00aa", "merges": "\u00e6\u00b4 \u00aa", "raw_count": 16973172, "count": 16973172, "decode_str": "\u6d2a"} -{"id": 50565, "token": "\u00e4\u00bd\u00a9", "merges": "\u00e4\u00bd \u00a9", "raw_count": 16984471, "count": 16984471, "decode_str": "\u4f69"} -{"id": 50750, "token": "\u00e5\u0129\u00a4", "merges": "\u00e5\u0129 \u00a4", "raw_count": 16990700, "count": 16990700, "decode_str": "\u51e4"} -{"id": 7554, "token": "300", "merges": "3 00", "raw_count": 17007360, "count": 17007360, "decode_str": "300"} -{"id": 53488, "token": "\u00e8\u0124\u013f", "merges": "\u00e8\u0124 \u013f", "raw_count": 17063236, "count": 17063236, "decode_str": "\u809d"} -{"id": 52967, "token": "\u00e7\u013c\u0128", "merges": "\u00e7\u013c \u0128", "raw_count": 17068250, "count": 17068250, "decode_str": "\u7686"} -{"id": 52781, "token": "\u00e7\u012b\u00a2", "merges": "\u00e7\u012b \u00a2", "raw_count": 17091697, "count": 17091697, "decode_str": "\u7262"} -{"id": 1157, "token": "\u0120,", "merges": "\u0120 ,", "raw_count": 17149739, "count": 17150571, "decode_str": " ,"} -{"id": 54030, "token": "\u00e8\u00bd\u00b4", "merges": "\u00e8\u00bd \u00b4", "raw_count": 17194886, "count": 17194886, "decode_str": "\u8f74"} -{"id": 52954, "token": "\u00e7\u013b\u012e", "merges": "\u00e7\u013b \u012e", "raw_count": 17225866, "count": 17225866, "decode_str": "\u764c"} -{"id": 1092, "token": "],", "merges": "] ,", "raw_count": 12688335, "count": 17258229, "decode_str": "],"} -{"id": 53263, "token": "\u00e7\u00b2\u0139", "merges": "\u00e7\u00b2 \u0139", "raw_count": 17283381, "count": 17283381, "decode_str": "\u7c97"} -{"id": 50912, "token": "\u00e5\u0130\u00a8", "merges": "\u00e5\u0130 \u00a8", "raw_count": 17308274, "count": 17308274, "decode_str": "\u53a8"} -{"id": 50983, "token": "\u00e5\u0132\u00b9", "merges": "\u00e5\u0132 \u00b9", "raw_count": 17354669, "count": 17354669, "decode_str": "\u5439"} -{"id": 681, "token": "com", "merges": "c om", "raw_count": 8183229, "count": 17358106, "decode_str": "com"} -{"id": 51400, "token": "\u00e5\u00ae\u0127", "merges": "\u00e5\u00ae \u0127", "raw_count": 17416093, "count": 17416093, "decode_str": "\u5b85"} -{"id": 52497, "token": "\u00e6\u00b2\u012a", "merges": "\u00e6\u00b2 \u012a", "raw_count": 17423369, "count": 17423369, "decode_str": "\u6c88"} -{"id": 54041, "token": "\u00e8\u00be\u012a", "merges": "\u00e8\u00be \u012a", "raw_count": 17450089, "count": 17450089, "decode_str": "\u8f88"} -{"id": 52217, "token": "\u00e6\u013f\u013e", "merges": "\u00e6\u013f \u013e", "raw_count": 17459940, "count": 17459940, "decode_str": "\u675c"} -{"id": 54022, "token": "\u00e8\u00bd\u00a8", "merges": "\u00e8\u00bd \u00a8", "raw_count": 17479681, "count": 17479681, "decode_str": "\u8f68"} -{"id": 51306, "token": "\u00e5\u00a4\u00ba", "merges": "\u00e5\u00a4 \u00ba", "raw_count": 17504377, "count": 17504377, "decode_str": "\u593a"} -{"id": 51647, "token": "\u00e5\u00be\u0134", "merges": "\u00e5\u00be \u0134", "raw_count": 17506000, "count": 17506000, "decode_str": "\u5f92"} -{"id": 314, "token": "ly", "merges": "l y", "raw_count": 1341369, "count": 17561529, "decode_str": "ly"} -{"id": 532, "token": "ip", "merges": "i p", "raw_count": 6425994, "count": 17571577, "decode_str": "ip"} -{"id": 51280, "token": "\u00e5\u00a3\u00ae", "merges": "\u00e5\u00a3 \u00ae", "raw_count": 17574055, "count": 17574055, "decode_str": "\u58ee"} -{"id": 52324, "token": "\u00e6\u00a3\u0134", "merges": "\u00e6\u00a3 \u0134", "raw_count": 17598279, "count": 17598279, "decode_str": "\u68d2"} -{"id": 50523, "token": "\u00e4\u00bc\u0131", "merges": "\u00e4\u00bc \u0131", "raw_count": 17623268, "count": 17623268, "decode_str": "\u4f0f"} -{"id": 52184, "token": "\u00e6\u013d\u00bc", "merges": "\u00e6\u013d \u00bc", "raw_count": 17669605, "count": 17669605, "decode_str": "\u66fc"} -{"id": 52923, "token": "\u00e7\u0138\u00bc", "merges": "\u00e7\u0138 \u00bc", "raw_count": 17672597, "count": 17672597, "decode_str": "\u75bc"} -{"id": 51786, "token": "\u00e6\u0126\u012a", "merges": "\u00e6\u0126 \u012a", "raw_count": 17697167, "count": 17697167, "decode_str": "\u6108"} -{"id": 417, "token": "\u0120not", "merges": "\u0120n ot", "raw_count": 16088325, "count": 17697636, "decode_str": " not"} -{"id": 51404, "token": "\u00e5\u00ae\u0131", "merges": "\u00e5\u00ae \u0131", "raw_count": 17712401, "count": 17712401, "decode_str": "\u5b8f"} -{"id": 51354, "token": "\u00e5\u00a7\u0128", "merges": "\u00e5\u00a7 \u0128", "raw_count": 17802542, "count": 17802542, "decode_str": "\u59c6"} -{"id": 53688, "token": "\u00e8\u013b\u00ab", "merges": "\u00e8\u013b \u00ab", "raw_count": 17823953, "count": 17823953, "decode_str": "\u866b"} -{"id": 354, "token": "\u0120pro", "merges": "\u0120p ro", "raw_count": 371326, "count": 17843852, "decode_str": " pro"} -{"id": 51226, "token": "\u00e5\u0140\u00ab", "merges": "\u00e5\u0140 \u00ab", "raw_count": 17847888, "count": 17847888, "decode_str": "\u57ab"} -{"id": 32363, "token": "\u00e8\u00b2", "merges": "\u00e8 \u00b2", "raw_count": 292115, "count": 17879630, "decode_str": "\ufffd"} -{"id": 52385, "token": "\u00e6\u00ac\u00a3", "merges": "\u00e6\u00ac \u00a3", "raw_count": 17888334, "count": 17888334, "decode_str": "\u6b23"} -{"id": 53501, "token": "\u00e8\u0124\u00ba", "merges": "\u00e8\u0124 \u00ba", "raw_count": 17905538, "count": 17905538, "decode_str": "\u80ba"} -{"id": 526, "token": "orm", "merges": "or m", "raw_count": 322101, "count": 17942527, "decode_str": "orm"} -{"id": 54155, "token": "\u00e9\u0124\u00a6", "merges": "\u00e9\u0124 \u00a6", "raw_count": 17969421, "count": 17969421, "decode_str": "\u90a6"} -{"id": 527, "token": "ind", "merges": "in d", "raw_count": 1256658, "count": 17975214, "decode_str": "ind"} -{"id": 51675, "token": "\u00e5\u00bf\u0142", "merges": "\u00e5\u00bf \u0142", "raw_count": 17978111, "count": 17978111, "decode_str": "\u5fe0"} -{"id": 52132, "token": "\u00e6\u013a\u012e", "merges": "\u00e6\u013a \u012e", "raw_count": 17996249, "count": 17996249, "decode_str": "\u660c"} -{"id": 1542, "token": "for", "merges": "f or", "raw_count": 16865721, "count": 18086994, "decode_str": "for"} -{"id": 50501, "token": "\u00e4\u00bb\u0136", "merges": "\u00e4\u00bb \u0136", "raw_count": 18118866, "count": 18118866, "decode_str": "\u4ed4"} -{"id": 51340, "token": "\u00e5\u00a6\u013b", "merges": "\u00e5\u00a6 \u013b", "raw_count": 18125685, "count": 18125685, "decode_str": "\u5999"} -{"id": 1812, "token": "36", "merges": "3 6", "raw_count": 12387701, "count": 18192756, "decode_str": "36"} -{"id": 1587, "token": "(\"", "merges": "( \"", "raw_count": 16741601, "count": 18215056, "decode_str": "(\""} -{"id": 53270, "token": "\u00e7\u00b2\u00ae", "merges": "\u00e7\u00b2 \u00ae", "raw_count": 18250428, "count": 18250428, "decode_str": "\u7cae"} -{"id": 384, "token": "ht", "merges": "h t", "raw_count": 481371, "count": 18288637, "decode_str": "ht"} -{"id": 51460, "token": "\u00e5\u00b0\u0138", "merges": "\u00e5\u00b0 \u0138", "raw_count": 18325795, "count": 18325795, "decode_str": "\u5c16"} -{"id": 52724, "token": "\u00e7\u0124\u012b", "merges": "\u00e7\u0124 \u012b", "raw_count": 18353949, "count": 18353949, "decode_str": "\u7089"} -{"id": 53859, "token": "\u00e8\u00b0\u012d", "merges": "\u00e8\u00b0 \u012d", "raw_count": 18356612, "count": 18356612, "decode_str": "\u8c0b"} -{"id": 51906, "token": "\u00e6\u012d\u0138", "merges": "\u00e6\u012d \u0138", "raw_count": 18357581, "count": 18357581, "decode_str": "\u62d6"} -{"id": 51189, "token": "\u00e5\u013e\u00be", "merges": "\u00e5\u013e \u00be", "raw_count": 18378056, "count": 18378056, "decode_str": "\u573e"} -{"id": 53989, "token": "\u00e8\u00b7\u0125", "merges": "\u00e8\u00b7 \u0125", "raw_count": 18395977, "count": 18395977, "decode_str": "\u8dc3"} -{"id": 51216, "token": "\u00e5\u0140\u0125", "merges": "\u00e5\u0140 \u0125", "raw_count": 18400057, "count": 18400057, "decode_str": "\u5783"} -{"id": 51331, "token": "\u00e5\u00a6\u0128", "merges": "\u00e5\u00a6 \u0128", "raw_count": 18428678, "count": 18428678, "decode_str": "\u5986"} -{"id": 54225, "token": "\u00e9\u0136\u012d", "merges": "\u00e9\u0136 \u012d", "raw_count": 18476406, "count": 18476406, "decode_str": "\u950b"} -{"id": 53509, "token": "\u00e8\u0125\u0128", "merges": "\u00e8\u0125 \u0128", "raw_count": 18487510, "count": 18487510, "decode_str": "\u80c6"} -{"id": 53672, "token": "\u00e8\u0130\u00b1", "merges": "\u00e8\u0130 \u00b1", "raw_count": 18527045, "count": 18527045, "decode_str": "\u83b1"} -{"id": 52727, "token": "\u00e7\u0124\u0134", "merges": "\u00e7\u0124 \u0134", "raw_count": 18534442, "count": 18534442, "decode_str": "\u7092"} -{"id": 503, "token": "ult", "merges": "ul t", "raw_count": 318766, "count": 18538327, "decode_str": "ult"} -{"id": 53531, "token": "\u00e8\u0125\u00b8", "merges": "\u00e8\u0125 \u00b8", "raw_count": 18573556, "count": 18573556, "decode_str": "\u80f8"} -{"id": 51065, "token": "\u00e5\u0135\u0134", "merges": "\u00e5\u0135 \u0134", "raw_count": 18646379, "count": 18646379, "decode_str": "\u54d2"} -{"id": 421, "token": "ction", "merges": "ct ion", "raw_count": 111285, "count": 18654139, "decode_str": "ction"} -{"id": 51711, "token": "\u00e6\u0123\u012d", "merges": "\u00e6\u0123 \u012d", "raw_count": 18660829, "count": 18660829, "decode_str": "\u604b"} -{"id": 2405, "token": "31", "merges": "3 1", "raw_count": 18526240, "count": 18743245, "decode_str": "31"} -{"id": 1857, "token": "45", "merges": "4 5", "raw_count": 15470588, "count": 18746468, "decode_str": "45"} -{"id": 52692, "token": "\u00e6\u00bc\u0124", "merges": "\u00e6\u00bc \u0124", "raw_count": 18839255, "count": 18839255, "decode_str": "\u6f02"} -{"id": 50832, "token": "\u00e5\u012d\u0134", "merges": "\u00e5\u012d \u0134", "raw_count": 18857240, "count": 18857240, "decode_str": "\u52d2"} -{"id": 51475, "token": "\u00e5\u00b0\u00bf", "merges": "\u00e5\u00b0 \u00bf", "raw_count": 18866581, "count": 18866581, "decode_str": "\u5c3f"} -{"id": 51504, "token": "\u00e5\u00b7\u00a1", "merges": "\u00e5\u00b7 \u00a1", "raw_count": 18867706, "count": 18867706, "decode_str": "\u5de1"} -{"id": 506, "token": "ath", "merges": "at h", "raw_count": 609353, "count": 18918780, "decode_str": "ath"} -{"id": 50743, "token": "\u00e5\u0129\u012e", "merges": "\u00e5\u0129 \u012e", "raw_count": 18983500, "count": 18983500, "decode_str": "\u51cc"} -{"id": 50442, "token": "\u00e4\u00b9\u0131", "merges": "\u00e4\u00b9 \u0131", "raw_count": 19023773, "count": 19023773, "decode_str": "\u4e4f"} -{"id": 54501, "token": "\u00e9\u00aa\u0133", "merges": "\u00e9\u00aa \u0133", "raw_count": 19056224, "count": 19056224, "decode_str": "\u9a91"} -{"id": 52108, "token": "\u00e6\u0139\u012d", "merges": "\u00e6\u0139 \u012d", "raw_count": 19099859, "count": 19099859, "decode_str": "\u65cb"} -{"id": 51678, "token": "\u00e5\u00bf\u00a7", "merges": "\u00e5\u00bf \u00a7", "raw_count": 19110932, "count": 19110932, "decode_str": "\u5fe7"} -{"id": 54334, "token": "\u00e9\u013b\u00aa", "merges": "\u00e9 \u013b\u00aa", "raw_count": 19134189, "count": 19134189, "decode_str": "\u966a"} -{"id": 52740, "token": "\u00e7\u0124\u00b8", "merges": "\u00e7\u0124 \u00b8", "raw_count": 19138116, "count": 19138116, "decode_str": "\u70b8"} -{"id": 5388, "token": "500", "merges": "5 00", "raw_count": 19197568, "count": 19197568, "decode_str": "500"} -{"id": 50649, "token": "\u00e5\u0123\u00b6", "merges": "\u00e5\u0123 \u00b6", "raw_count": 19211246, "count": 19211246, "decode_str": "\u5076"} -{"id": 53489, "token": "\u00e8\u0124\u0142", "merges": "\u00e8\u0124 \u0142", "raw_count": 19260320, "count": 19260320, "decode_str": "\u80a0"} -{"id": 52297, "token": "\u00e6\u00a1\u0125", "merges": "\u00e6\u00a1 \u0125", "raw_count": 19262981, "count": 19262981, "decode_str": "\u6843"} -{"id": 54088, "token": "\u00e8\u00bf\u00ab", "merges": "\u00e8\u00bf \u00ab", "raw_count": 19284221, "count": 19284221, "decode_str": "\u8feb"} -{"id": 53098, "token": "\u00e7\u00a2\u00b0", "merges": "\u00e7\u00a2 \u00b0", "raw_count": 19310584, "count": 19310584, "decode_str": "\u78b0"} -{"id": 51854, "token": "\u00e6\u012b\u00b0", "merges": "\u00e6\u012b \u00b0", "raw_count": 19322291, "count": 19322291, "decode_str": "\u6270"} -{"id": 54144, "token": "\u00e9\u0124\u0122", "merges": "\u00e9\u0124 \u0122", "raw_count": 19324365, "count": 19324365, "decode_str": "\u9080"} -{"id": 51208, "token": "\u00e5\u013f\u00a6", "merges": "\u00e5\u013f \u00a6", "raw_count": 19344030, "count": 19344030, "decode_str": "\u5766"} -{"id": 50591, "token": "\u00e4\u00be\u00b5", "merges": "\u00e4\u00be \u00b5", "raw_count": 19397261, "count": 19397261, "decode_str": "\u4fb5"} -{"id": 52155, "token": "\u00e6\u013b\u0134", "merges": "\u00e6\u013b \u0134", "raw_count": 19409298, "count": 19409298, "decode_str": "\u6652"} -{"id": 54069, "token": "\u00e8\u00bf\u0123", "merges": "\u00e8\u00bf \u0123", "raw_count": 19418908, "count": 19418908, "decode_str": "\u8fc1"} -{"id": 50803, "token": "\u00e5\u012b\u00a9", "merges": "\u00e5\u012b \u00a9", "raw_count": 19448410, "count": 19448410, "decode_str": "\u5269"} -{"id": 52172, "token": "\u00e6\u013b\u00b6", "merges": "\u00e6\u013b \u00b6", "raw_count": 19475930, "count": 19475930, "decode_str": "\u6676"} -{"id": 53406, "token": "\u00e7\u00bc\u00b4", "merges": "\u00e7\u00bc \u00b4", "raw_count": 19479963, "count": 19479963, "decode_str": "\u7f34"} -{"id": 50714, "token": "\u00e5\u0128\u0134", "merges": "\u00e5 \u0128\u0134", "raw_count": 19513348, "count": 19513348, "decode_str": "\u5192"} -{"id": 58, "token": "Y", "merges": "NULL", "raw_count": 9179150, "count": 19516557, "decode_str": "Y"} -{"id": 43, "token": "J", "merges": "NULL", "raw_count": 9100241, "count": 19555353, "decode_str": "J"} -{"id": 52983, "token": "\u00e7\u013d\u012a", "merges": "\u00e7\u013d \u012a", "raw_count": 19579084, "count": 19579084, "decode_str": "\u76c8"} -{"id": 435, "token": "art", "merges": "ar t", "raw_count": 1244194, "count": 19638294, "decode_str": "art"} -{"id": 54099, "token": "\u00e9\u0122\u0125", "merges": "\u00e9\u0122 \u0125", "raw_count": 19661219, "count": 19661219, "decode_str": "\u9003"} -{"id": 398, "token": "ers", "merges": "er s", "raw_count": 2340878, "count": 19670529, "decode_str": "ers"} -{"id": 394, "token": "th", "merges": "t h", "raw_count": 1684038, "count": 19673446, "decode_str": "th"} -{"id": 53957, "token": "\u00e8\u00b5\u0138", "merges": "\u00e8\u00b5 \u0138", "raw_count": 19679011, "count": 19679011, "decode_str": "\u8d56"} -{"id": 50680, "token": "\u00e5\u0127\u0126", "merges": "\u00e5\u0127 \u0126", "raw_count": 19693841, "count": 19693841, "decode_str": "\u5144"} -{"id": 51905, "token": "\u00e6\u012d\u0136", "merges": "\u00e6\u012d \u0136", "raw_count": 19796283, "count": 19796283, "decode_str": "\u62d4"} -{"id": 51428, "token": "\u00e5\u00ae\u00be", "merges": "\u00e5\u00ae \u00be", "raw_count": 19944147, "count": 19944147, "decode_str": "\u5bbe"} -{"id": 536, "token": "ok", "merges": "o k", "raw_count": 6829205, "count": 19955398, "decode_str": "ok"} -{"id": 53512, "token": "\u00e8\u0125\u0130", "merges": "\u00e8\u0125 \u0130", "raw_count": 19955683, "count": 19955683, "decode_str": "\u80ce"} -{"id": 50638, "token": "\u00e5\u0122\u00be", "merges": "\u00e5\u0122 \u00be", "raw_count": 19974791, "count": 19974791, "decode_str": "\u503e"} -{"id": 54341, "token": "\u00e9\u013c\u0128", "merges": "\u00e9\u013c \u0128", "raw_count": 20016589, "count": 20016589, "decode_str": "\u9686"} -{"id": 53252, "token": "\u00e7\u00b1\u012f", "merges": "\u00e7\u00b1 \u012f", "raw_count": 20040353, "count": 20040353, "decode_str": "\u7c4d"} -{"id": 52662, "token": "\u00e6\u00b8\u0142", "merges": "\u00e6\u00b8 \u0142", "raw_count": 20065629, "count": 20065629, "decode_str": "\u6e20"} -{"id": 53424, "token": "\u00e7\u00be\u012c", "merges": "\u00e7\u00be \u012c", "raw_count": 20091971, "count": 20091971, "decode_str": "\u7f8a"} -{"id": 430, "token": "ort", "merges": "or t", "raw_count": 653377, "count": 20101502, "decode_str": "ort"} -{"id": 420, "token": "ment", "merges": "m ent", "raw_count": 1020221, "count": 20116274, "decode_str": "ment"} -{"id": 53659, "token": "\u00e8\u012d\u00b9", "merges": "\u00e8\u012d \u00b9", "raw_count": 20152684, "count": 20152684, "decode_str": "\u82f9"} -{"id": 362, "token": "\u0120v", "merges": "\u0120 v", "raw_count": 3279014, "count": 20171309, "decode_str": " v"} -{"id": 51980, "token": "\u00e6\u012f\u00b7", "merges": "\u00e6\u012f \u00b7", "raw_count": 20175858, "count": 20175858, "decode_str": "\u6377"} -{"id": 53507, "token": "\u00e8\u0125\u0125", "merges": "\u00e8\u0125 \u0125", "raw_count": 20191861, "count": 20191861, "decode_str": "\u80c3"} -{"id": 53646, "token": "\u00e8\u012d\u0139", "merges": "\u00e8\u012d \u0139", "raw_count": 20204319, "count": 20204319, "decode_str": "\u82d7"} -{"id": 1237, "token": "32", "merges": "3 2", "raw_count": 15331541, "count": 20253358, "decode_str": "32"} -{"id": 498, "token": "cl", "merges": "c l", "raw_count": 1885239, "count": 20340228, "decode_str": "cl"} -{"id": 334, "token": "ith", "merges": "it h", "raw_count": 863231, "count": 20345993, "decode_str": "ith"} -{"id": 1051, "token": "...", "merges": ".. .", "raw_count": 17820254, "count": 20403581, "decode_str": "..."} -{"id": 52243, "token": "\u00e6\u0140\u00aa", "merges": "\u00e6\u0140 \u00aa", "raw_count": 20409448, "count": 20409448, "decode_str": "\u67aa"} -{"id": 50820, "token": "\u00e5\u012c\u00b2", "merges": "\u00e5\u012c \u00b2", "raw_count": 20418371, "count": 20418371, "decode_str": "\u52b2"} -{"id": 53915, "token": "\u00e8\u00b4\u00a1", "merges": "\u00e8\u00b4 \u00a1", "raw_count": 20435102, "count": 20435102, "decode_str": "\u8d21"} -{"id": 52987, "token": "\u00e7\u013d\u0132", "merges": "\u00e7\u013d \u0132", "raw_count": 20466483, "count": 20466483, "decode_str": "\u76d0"} -{"id": 52592, "token": "\u00e6\u00b5\u00ae", "merges": "\u00e6\u00b5 \u00ae", "raw_count": 20476905, "count": 20476905, "decode_str": "\u6d6e"} -{"id": 381, "token": "==", "merges": "= =", "raw_count": 1387197, "count": 20505678, "decode_str": "=="} -{"id": 51429, "token": "\u00e5\u00ae\u00bf", "merges": "\u00e5\u00ae \u00bf", "raw_count": 20518548, "count": 20518548, "decode_str": "\u5bbf"} -{"id": 50439, "token": "\u00e4\u00b9\u012e", "merges": "\u00e4\u00b9 \u012e", "raw_count": 20552092, "count": 20552092, "decode_str": "\u4e4c"} -{"id": 50836, "token": "\u00e5\u012d\u00a4", "merges": "\u00e5\u012d \u00a4", "raw_count": 20559568, "count": 20559568, "decode_str": "\u52e4"} -{"id": 559, "token": "\u0120+", "merges": "\u0120 +", "raw_count": 15800385, "count": 20629244, "decode_str": " +"} -{"id": 51714, "token": "\u00e6\u0123\u0134", "merges": "\u00e6\u0123 \u0134", "raw_count": 20646246, "count": 20646246, "decode_str": "\u6052"} -{"id": 633, "token": "xt", "merges": "x t", "raw_count": 799737, "count": 20653623, "decode_str": "xt"} -{"id": 52056, "token": "\u00e6\u0135\u00a6", "merges": "\u00e6\u0135 \u00a6", "raw_count": 20659271, "count": 20659271, "decode_str": "\u64e6"} -{"id": 50517, "token": "\u00e4\u00bb\u00bf", "merges": "\u00e4\u00bb \u00bf", "raw_count": 20662711, "count": 20662711, "decode_str": "\u4eff"} -{"id": 51904, "token": "\u00e6\u012d\u0135", "merges": "\u00e6\u012d \u0135", "raw_count": 20680402, "count": 20680402, "decode_str": "\u62d3"} -{"id": 797, "token": "ert", "merges": "er t", "raw_count": 431860, "count": 20720238, "decode_str": "ert"} -{"id": 391, "token": "\u0120r", "merges": "\u0120 r", "raw_count": 4074379, "count": 20767591, "decode_str": " r"} -{"id": 50601, "token": "\u00e4\u00bf\u0139", "merges": "\u00e4\u00bf \u0139", "raw_count": 20806827, "count": 20806827, "decode_str": "\u4fd7"} -{"id": 52166, "token": "\u00e6\u013b\u00a8", "merges": "\u00e6\u013b \u00a8", "raw_count": 20808600, "count": 20808600, "decode_str": "\u6668"} -{"id": 53518, "token": "\u00e8\u0125\u0140", "merges": "\u00e8\u0125 \u0140", "raw_count": 20826833, "count": 20826833, "decode_str": "\u80de"} -{"id": 53261, "token": "\u00e7\u00b2\u0134", "merges": "\u00e7\u00b2 \u0134", "raw_count": 20856961, "count": 20856961, "decode_str": "\u7c92"} -{"id": 415, "token": "oun", "merges": "ou n", "raw_count": 155833, "count": 20866485, "decode_str": "oun"} -{"id": 52865, "token": "\u00e7\u0136\u013a", "merges": "\u00e7\u0136 \u013a", "raw_count": 20875078, "count": 20875078, "decode_str": "\u7518"} -{"id": 49650, "token": "\u00e6\u00b0\u0131", "merges": "\u00e6\u00b0 \u0131", "raw_count": 20908711, "count": 20908711, "decode_str": "\u6c0f"} -{"id": 470, "token": "\u01200", "merges": "\u0120 0", "raw_count": 18825327, "count": 20923062, "decode_str": " 0"} -{"id": 50771, "token": "\u00e5\u012a\u0133", "merges": "\u00e5\u012a \u0133", "raw_count": 20923726, "count": 20923726, "decode_str": "\u5211"} -{"id": 53732, "token": "\u00e8\u00a3\u0124", "merges": "\u00e8\u00a3 \u0124", "raw_count": 20932329, "count": 20932329, "decode_str": "\u88c2"} -{"id": 52825, "token": "\u00e7\u0131\u012f", "merges": "\u00e7\u0131 \u012f", "raw_count": 20946275, "count": 20946275, "decode_str": "\u73cd"} -{"id": 1590, "token": "name", "merges": "n ame", "raw_count": 18940522, "count": 20961607, "decode_str": "name"} -{"id": 54338, "token": "\u00e9\u013b\u00b7", "merges": "\u00e9\u013b \u00b7", "raw_count": 20963575, "count": 20963575, "decode_str": "\u9677"} -{"id": 486, "token": "age", "merges": "ag e", "raw_count": 1503944, "count": 20993238, "decode_str": "age"} -{"id": 52549, "token": "\u00e6\u00b3\u00bd", "merges": "\u00e6\u00b3 \u00bd", "raw_count": 20996631, "count": 20996631, "decode_str": "\u6cfd"} -{"id": 50705, "token": "\u00e5\u0127\u00bc", "merges": "\u00e5\u0127 \u00bc", "raw_count": 20999583, "count": 20999583, "decode_str": "\u517c"} -{"id": 2073, "token": "('", "merges": "( '", "raw_count": 19671084, "count": 21002011, "decode_str": "('"} -{"id": 52584, "token": "\u00e6\u00b5\u013b", "merges": "\u00e6\u00b5 \u013b", "raw_count": 21031854, "count": 21031854, "decode_str": "\u6d59"} -{"id": 53574, "token": "\u00e8\u012a\u012f", "merges": "\u00e8\u012a \u012f", "raw_count": 21037321, "count": 21037321, "decode_str": "\u820d"} -{"id": 53361, "token": "\u00e7\u00bb\u00aa", "merges": "\u00e7\u00bb \u00aa", "raw_count": 21043790, "count": 21043790, "decode_str": "\u7eea"} -{"id": 52525, "token": "\u00e6\u00b3\u012b", "merges": "\u00e6\u00b3 \u012b", "raw_count": 21047695, "count": 21047695, "decode_str": "\u6cc9"} -{"id": 50539, "token": "\u00e4\u00bc\u00af", "merges": "\u00e4\u00bc \u00af", "raw_count": 21061750, "count": 21061750, "decode_str": "\u4f2f"} -{"id": 51665, "token": "\u00e5\u00bf\u012f", "merges": "\u00e5\u00bf \u012f", "raw_count": 21062553, "count": 21062553, "decode_str": "\u5fcd"} -{"id": 53151, "token": "\u00e7\u00a7\u0134", "merges": "\u00e7\u00a7 \u0134", "raw_count": 21088021, "count": 21088021, "decode_str": "\u79d2"} -{"id": 53959, "token": "\u00e8\u00b5\u013c", "merges": "\u00e8\u00b5 \u013c", "raw_count": 21108754, "count": 21108754, "decode_str": "\u8d5a"} -{"id": 6370, "token": "num", "merges": "n um", "raw_count": 20744027, "count": 21114647, "decode_str": "num"} -{"id": 50489, "token": "\u00e4\u00bb\u0123", "merges": "\u00e4\u00bb \u0123", "raw_count": 21140185, "count": 21140185, "decode_str": "\u4ec1"} -{"id": 428, "token": "\u0120-", "merges": "\u0120 -", "raw_count": 16589959, "count": 21156709, "decode_str": " -"} -{"id": 52200, "token": "\u00e6\u013e\u00b1", "merges": "\u00e6\u013e \u00b1", "raw_count": 21260581, "count": 21260581, "decode_str": "\u6731"} -{"id": 52367, "token": "\u00e6\u00a8\u00aa", "merges": "\u00e6\u00a8 \u00aa", "raw_count": 21302234, "count": 21302234, "decode_str": "\u6a2a"} -{"id": 54633, "token": "\u00e2\u0122\u013d", "merges": "\u00e2\u0122 \u013d", "raw_count": 21322808, "count": 21322808, "decode_str": " "} -{"id": 53539, "token": "\u00e8\u0126\u0131", "merges": "\u00e8\u0126 \u0131", "raw_count": 21340139, "count": 21340139, "decode_str": "\u810f"} -{"id": 52885, "token": "\u00e7\u0137\u0127", "merges": "\u00e7\u0137 \u0127", "raw_count": 21383470, "count": 21383470, "decode_str": "\u7545"} -{"id": 51912, "token": "\u00e6\u012d\u013e", "merges": "\u00e6\u012d \u013e", "raw_count": 21412110, "count": 21412110, "decode_str": "\u62dc"} -{"id": 53465, "token": "\u00e8\u0123\u012c", "merges": "\u00e8\u0123 \u012c", "raw_count": 21462619, "count": 21462619, "decode_str": "\u804a"} -{"id": 51930, "token": "\u00e6\u012d\u00bc", "merges": "\u00e6\u012d \u00bc", "raw_count": 21465122, "count": 21465122, "decode_str": "\u62fc"} -{"id": 50521, "token": "\u00e4\u00bc\u012f", "merges": "\u00e4\u00bc \u012f", "raw_count": 21487606, "count": 21487606, "decode_str": "\u4f0d"} -{"id": 50543, "token": "\u00e4\u00bc\u00b8", "merges": "\u00e4\u00bc \u00b8", "raw_count": 21516222, "count": 21516222, "decode_str": "\u4f38"} -{"id": 50402, "token": "\u00e4\u00b8\u0123", "merges": "\u00e4\u00b8 \u0123", "raw_count": 21621571, "count": 21621571, "decode_str": "\u4e01"} -{"id": 53772, "token": "\u00e8\u00aa\u012b", "merges": "\u00e8\u00aa \u012b", "raw_count": 21629086, "count": 21629086, "decode_str": "\u8a89"} -{"id": 51655, "token": "\u00e5\u00be\u00aa", "merges": "\u00e5\u00be \u00aa", "raw_count": 21632399, "count": 21632399, "decode_str": "\u5faa"} -{"id": 911, "token": "ex", "merges": "e x", "raw_count": 2198921, "count": 21651965, "decode_str": "ex"} -{"id": 52208, "token": "\u00e6\u013f\u0128", "merges": "\u00e6\u013f \u0128", "raw_count": 21678393, "count": 21678393, "decode_str": "\u6746"} -{"id": 53627, "token": "\u00e8\u012c\u00af", "merges": "\u00e8\u012c \u00af", "raw_count": 21712737, "count": 21712737, "decode_str": "\u82af"} -{"id": 6620, "token": "2015", "merges": "201 5", "raw_count": 21756160, "count": 21756160, "decode_str": "2015"} -{"id": 32488, "token": "\"\"\"", "merges": "\"\" \"", "raw_count": 21768405, "count": 21768405, "decode_str": "\"\"\""} -{"id": 52097, "token": "\u00e6\u0138\u00a4", "merges": "\u00e6\u0138 \u00a4", "raw_count": 21773349, "count": 21773349, "decode_str": "\u65a4"} -{"id": 52818, "token": "\u00e7\u0130\u00bb", "merges": "\u00e7\u0130 \u00bb", "raw_count": 21849147, "count": 21849147, "decode_str": "\u73bb"} -{"id": 52068, "token": "\u00e6\u0137\u012e", "merges": "\u00e6\u0137 \u012e", "raw_count": 21941947, "count": 21941947, "decode_str": "\u654c"} -{"id": 53588, "token": "\u00e8\u012a\u00b0", "merges": "\u00e8\u012a \u00b0", "raw_count": 21944123, "count": 21944123, "decode_str": "\u8230"} -{"id": 51836, "token": "\u00e6\u012b\u0130", "merges": "\u00e6\u012b \u0130", "raw_count": 22054289, "count": 22054289, "decode_str": "\u624e"} -{"id": 51271, "token": "\u00e5\u00a3\u0123", "merges": "\u00e5\u00a3 \u0123", "raw_count": 22065681, "count": 22065681, "decode_str": "\u58c1"} -{"id": 43033, "token": "\u00e6\u00a7", "merges": "\u00e6 \u00a7", "raw_count": 276545, "count": 22068336, "decode_str": "\ufffd"} -{"id": 345, "token": "\u0120con", "merges": "\u0120c on", "raw_count": 334443, "count": 22085322, "decode_str": " con"} -{"id": 37794, "token": "\u00e6\u00a9", "merges": "\u00e6 \u00a9", "raw_count": 210770, "count": 22246888, "decode_str": "\ufffd"} -{"id": 50972, "token": "\u00e5\u0132\u00a8", "merges": "\u00e5\u0132 \u00a8", "raw_count": 22269360, "count": 22269360, "decode_str": "\u5428"} -{"id": 423, "token": "end", "merges": "en d", "raw_count": 2881132, "count": 22317027, "decode_str": "end"} -{"id": 54279, "token": "\u00e9\u0139\u00b2", "merges": "\u00e9\u0139 \u00b2", "raw_count": 22345488, "count": 22345488, "decode_str": "\u95f2"} -{"id": 876, "token": "__", "merges": "_ _", "raw_count": 6143029, "count": 22378124, "decode_str": "__"} -{"id": 543, "token": "ong", "merges": "on g", "raw_count": 1769792, "count": 22417739, "decode_str": "ong"} -{"id": 52224, "token": "\u00e6\u013f\u00b0", "merges": "\u00e6\u013f \u00b0", "raw_count": 22452064, "count": 22452064, "decode_str": "\u6770"} -{"id": 51452, "token": "\u00e5\u00af\u00bf", "merges": "\u00e5\u00af \u00bf", "raw_count": 22480737, "count": 22480737, "decode_str": "\u5bff"} -{"id": 52387, "token": "\u00e6\u00ac\u00b2", "merges": "\u00e6\u00ac \u00b2", "raw_count": 22538927, "count": 22538927, "decode_str": "\u6b32"} -{"id": 52022, "token": "\u00e6\u0131\u00b4", "merges": "\u00e6\u0131 \u00b4", "raw_count": 22572824, "count": 22572824, "decode_str": "\u63f4"} -{"id": 51403, "token": "\u00e5\u00ae\u012d", "merges": "\u00e5\u00ae \u012d", "raw_count": 22580924, "count": 22580924, "decode_str": "\u5b8b"} -{"id": 1671, "token": "35", "merges": "3 5", "raw_count": 18766587, "count": 22581784, "decode_str": "35"} -{"id": 52536, "token": "\u00e6\u00b3\u00a5", "merges": "\u00e6\u00b3 \u00a5", "raw_count": 22705170, "count": 22705170, "decode_str": "\u6ce5"} -{"id": 1228, "token": "))", "merges": ") )", "raw_count": 14509901, "count": 22731164, "decode_str": "))"} -{"id": 52712, "token": "\u00e7\u0123\u0143", "merges": "\u00e7\u0123 \u0143", "raw_count": 22741549, "count": 22741549, "decode_str": "\u706d"} -{"id": 53929, "token": "\u00e8\u00b4\u00af", "merges": "\u00e8\u00b4 \u00af", "raw_count": 22746303, "count": 22746303, "decode_str": "\u8d2f"} -{"id": 14952, "token": "2020", "merges": "20 20", "raw_count": 22754833, "count": 22754833, "decode_str": "2020"} -{"id": 51594, "token": "\u00e5\u00bc\u0126", "merges": "\u00e5\u00bc \u0126", "raw_count": 22768419, "count": 22768419, "decode_str": "\u5f04"} -{"id": 53156, "token": "\u00e7\u00a7\u00a6", "merges": "\u00e7\u00a7 \u00a6", "raw_count": 22776076, "count": 22776076, "decode_str": "\u79e6"} -{"id": 52115, "token": "\u00e6\u0139\u00a6", "merges": "\u00e6\u0139 \u00a6", "raw_count": 22798818, "count": 22798818, "decode_str": "\u65e6"} -{"id": 1717, "token": "29", "merges": "2 9", "raw_count": 19173237, "count": 22855267, "decode_str": "29"} -{"id": 51201, "token": "\u00e5\u013f\u013d", "merges": "\u00e5\u013f \u013d", "raw_count": 22896779, "count": 22896779, "decode_str": "\u575b"} -{"id": 53903, "token": "\u00e8\u00b1\u00aa", "merges": "\u00e8\u00b1 \u00aa", "raw_count": 22904561, "count": 22904561, "decode_str": "\u8c6a"} -{"id": 52031, "token": "\u00e6\u0134\u0133", "merges": "\u00e6\u0134 \u0133", "raw_count": 22911082, "count": 22911082, "decode_str": "\u6491"} -{"id": 50, "token": "Q", "merges": "NULL", "raw_count": 13850620, "count": 22927835, "decode_str": "Q"} -{"id": 50741, "token": "\u00e5\u0129\u012b", "merges": "\u00e5\u0129 \u012b", "raw_count": 22963179, "count": 22963179, "decode_str": "\u51c9"} -{"id": 53680, "token": "\u00e8\u013b\u0130", "merges": "\u00e8\u013b \u0130", "raw_count": 22991816, "count": 22991816, "decode_str": "\u864e"} -{"id": 478, "token": "iz", "merges": "i z", "raw_count": 754870, "count": 22992049, "decode_str": "iz"} -{"id": 431, "token": "pt", "merges": "p t", "raw_count": 1683072, "count": 23022419, "decode_str": "pt"} -{"id": 53953, "token": "\u00e8\u00b5\u0131", "merges": "\u00e8\u00b5 \u0131", "raw_count": 23023424, "count": 23023424, "decode_str": "\u8d4f"} -{"id": 462, "token": "og", "merges": "o g", "raw_count": 1195137, "count": 23044810, "decode_str": "og"} -{"id": 53536, "token": "\u00e8\u0126\u012b", "merges": "\u00e8\u0126 \u012b", "raw_count": 23072566, "count": 23072566, "decode_str": "\u8109"} -{"id": 54450, "token": "\u00e9\u00a2\u0139", "merges": "\u00e9\u00a2 \u0139", "raw_count": 23108476, "count": 23108476, "decode_str": "\u9897"} -{"id": 52302, "token": "\u00e6\u00a1\u012e", "merges": "\u00e6\u00a1 \u012e", "raw_count": 23145157, "count": 23145157, "decode_str": "\u684c"} -{"id": 52714, "token": "\u00e7\u0123\u00b0", "merges": "\u00e7\u0123 \u00b0", "raw_count": 23175860, "count": 23175860, "decode_str": "\u7070"} -{"id": 53956, "token": "\u00e8\u00b5\u0136", "merges": "\u00e8\u00b5 \u0136", "raw_count": 23194060, "count": 23194060, "decode_str": "\u8d54"} -{"id": 54173, "token": "\u00e9\u0125\u0133", "merges": "\u00e9\u0125 \u0133", "raw_count": 23203463, "count": 23203463, "decode_str": "\u90d1"} -{"id": 54502, "token": "\u00e9\u00aa\u0139", "merges": "\u00e9\u00aa \u0139", "raw_count": 23216732, "count": 23216732, "decode_str": "\u9a97"} -{"id": 51352, "token": "\u00e5\u00a6\u00bb", "merges": "\u00e5\u00a6 \u00bb", "raw_count": 23262672, "count": 23262672, "decode_str": "\u59bb"} -{"id": 52695, "token": "\u00e6\u00bc\u0131", "merges": "\u00e6\u00bc \u0131", "raw_count": 23280263, "count": 23280263, "decode_str": "\u6f0f"} -{"id": 54046, "token": "\u00e8\u00be\u0133", "merges": "\u00e8\u00be \u0133", "raw_count": 23406377, "count": 23406377, "decode_str": "\u8f91"} -{"id": 1383, "token": "',", "merges": "' ,", "raw_count": 21938093, "count": 23422199, "decode_str": "',"} -{"id": 53295, "token": "\u00e7\u00b4\u00ab", "merges": "\u00e7\u00b4 \u00ab", "raw_count": 23450141, "count": 23450141, "decode_str": "\u7d2b"} -{"id": 53088, "token": "\u00e7\u00a2\u0130", "merges": "\u00e7\u00a2 \u0130", "raw_count": 23488254, "count": 23488254, "decode_str": "\u788e"} -{"id": 50753, "token": "\u00e5\u0129\u0143", "merges": "\u00e5\u0129 \u0143", "raw_count": 23489668, "count": 23489668, "decode_str": "\u51ed"} -{"id": 52014, "token": "\u00e6\u0131\u0131", "merges": "\u00e6\u0131 \u0131", "raw_count": 23511359, "count": 23511359, "decode_str": "\u63cf"} -{"id": 94, "token": "}", "merges": "NULL", "raw_count": 7660215, "count": 23587418, "decode_str": "}"} -{"id": 51401, "token": "\u00e5\u00ae\u0129", "merges": "\u00e5\u00ae \u0129", "raw_count": 23598547, "count": 23598547, "decode_str": "\u5b87"} -{"id": 92, "token": "{", "merges": "NULL", "raw_count": 3754129, "count": 23634031, "decode_str": "{"} -{"id": 52523, "token": "\u00e6\u00b2\u00bf", "merges": "\u00e6\u00b2 \u00bf", "raw_count": 23663512, "count": 23663512, "decode_str": "\u6cbf"} -{"id": 54081, "token": "\u00e8\u00bf\u0141", "merges": "\u00e8\u00bf \u0141", "raw_count": 23688419, "count": 23688419, "decode_str": "\u8fdf"} -{"id": 51379, "token": "\u00e5\u0143\u0137", "merges": "\u00e5\u0143 \u0137", "raw_count": 23716314, "count": 23716314, "decode_str": "\u5b55"} -{"id": 51663, "token": "\u00e5\u00bf\u0128", "merges": "\u00e5\u00bf \u0128", "raw_count": 23722877, "count": 23722877, "decode_str": "\u5fc6"} -{"id": 31, "token": ">", "merges": "NULL", "raw_count": 5872710, "count": 23765216, "decode_str": ">"} -{"id": 442, "token": "te", "merges": "t e", "raw_count": 1250965, "count": 23775755, "decode_str": "te"} -{"id": 51954, "token": "\u00e6\u012e\u00af", "merges": "\u00e6\u012e \u00af", "raw_count": 23845313, "count": 23845313, "decode_str": "\u632f"} -{"id": 50747, "token": "\u00e5\u0129\u013f", "merges": "\u00e5\u0129 \u013f", "raw_count": 23897526, "count": 23897526, "decode_str": "\u51dd"} -{"id": 51646, "token": "\u00e5\u00be\u0132", "merges": "\u00e5\u00be \u0132", "raw_count": 24057307, "count": 24057307, "decode_str": "\u5f90"} -{"id": 413, "token": "ke", "merges": "k e", "raw_count": 832110, "count": 24108269, "decode_str": "ke"} -{"id": 53023, "token": "\u00e7\u013f\u013d", "merges": "\u00e7\u013f \u013d", "raw_count": 24310810, "count": 24310810, "decode_str": "\u775b"} -{"id": 395, "token": "and", "merges": "an d", "raw_count": 3919314, "count": 24322837, "decode_str": "and"} -{"id": 565, "token": "int", "merges": "in t", "raw_count": 4704580, "count": 24410801, "decode_str": "int"} -{"id": 52868, "token": "\u00e7\u0136\u013e", "merges": "\u00e7\u0136 \u013e", "raw_count": 24433631, "count": 24433631, "decode_str": "\u751c"} -{"id": 52558, "token": "\u00e6\u00b4\u0140", "merges": "\u00e6\u00b4 \u0140", "raw_count": 24439882, "count": 24439882, "decode_str": "\u6d1e"} -{"id": 52456, "token": "\u00e6\u00b0\u00a7", "merges": "\u00e6\u00b0 \u00a7", "raw_count": 24446956, "count": 24446956, "decode_str": "\u6c27"} -{"id": 51186, "token": "\u00e5\u013e\u00b3", "merges": "\u00e5\u013e \u00b3", "raw_count": 24459097, "count": 24459097, "decode_str": "\u5733"} -{"id": 405, "token": "ess", "merges": "es s", "raw_count": 772118, "count": 24549603, "decode_str": "ess"} -{"id": 52557, "token": "\u00e6\u00b4\u013d", "merges": "\u00e6\u00b4 \u013d", "raw_count": 24563325, "count": 24563325, "decode_str": "\u6d1b"} -{"id": 50505, "token": "\u00e4\u00bb\u013b", "merges": "\u00e4\u00bb \u013b", "raw_count": 24629738, "count": 24629738, "decode_str": "\u4ed9"} -{"id": 51684, "token": "\u00e5\u00bf\u00bd", "merges": "\u00e5\u00bf \u00bd", "raw_count": 24807533, "count": 24807533, "decode_str": "\u5ffd"} -{"id": 52482, "token": "\u00e6\u00b1\u00a4", "merges": "\u00e6\u00b1 \u00a4", "raw_count": 24834913, "count": 24834913, "decode_str": "\u6c64"} -{"id": 52156, "token": "\u00e6\u013b\u0135", "merges": "\u00e6\u013b \u0135", "raw_count": 24851613, "count": 24851613, "decode_str": "\u6653"} -{"id": 51269, "token": "\u00e5\u00a2\u00a8", "merges": "\u00e5\u00a2 \u00a8", "raw_count": 24905296, "count": 24905296, "decode_str": "\u58a8"} -{"id": 495, "token": "\u01203", "merges": "\u0120 3", "raw_count": 17898927, "count": 24914660, "decode_str": " 3"} -{"id": 1967, "token": "70", "merges": "7 0", "raw_count": 20896666, "count": 24952336, "decode_str": "70"} -{"id": 52741, "token": "\u00e7\u0124\u00bc", "merges": "\u00e7\u0124 \u00bc", "raw_count": 24983596, "count": 24983596, "decode_str": "\u70bc"} -{"id": 53749, "token": "\u00e8\u00a6\u0128", "merges": "\u00e8\u00a6 \u0128", "raw_count": 25006307, "count": 25006307, "decode_str": "\u8986"} -{"id": 51131, "token": "\u00e5\u0138\u00b7", "merges": "\u00e5\u0138 \u00b7", "raw_count": 25028392, "count": 25028392, "decode_str": "\u55b7"} -{"id": 50536, "token": "\u00e4\u00bc\u00a6", "merges": "\u00e4\u00bc \u00a6", "raw_count": 25068524, "count": 25068524, "decode_str": "\u4f26"} -{"id": 54072, "token": "\u00e8\u00bf\u0127", "merges": "\u00e8\u00bf \u0127", "raw_count": 25096305, "count": 25096305, "decode_str": "\u8fc5"} -{"id": 50430, "token": "\u00e4\u00b8\u00b9", "merges": "\u00e4\u00b8 \u00b9", "raw_count": 25107638, "count": 25107638, "decode_str": "\u4e39"} -{"id": 52186, "token": "\u00e6\u013d\u00bf", "merges": "\u00e6\u013d \u00bf", "raw_count": 25119659, "count": 25119659, "decode_str": "\u66ff"} -{"id": 51312, "token": "\u00e5\u00a5\u012d", "merges": "\u00e5\u00a5 \u012d", "raw_count": 25218730, "count": 25218730, "decode_str": "\u594b"} -{"id": 54038, "token": "\u00e8\u00be\u0127", "merges": "\u00e8\u00be \u0127", "raw_count": 25292460, "count": 25292460, "decode_str": "\u8f85"} -{"id": 51787, "token": "\u00e6\u0126\u012b", "merges": "\u00e6\u0126 \u012b", "raw_count": 25306700, "count": 25306700, "decode_str": "\u6109"} -{"id": 54087, "token": "\u00e8\u00bf\u00aa", "merges": "\u00e8\u00bf \u00aa", "raw_count": 25312522, "count": 25312522, "decode_str": "\u8fea"} -{"id": 53533, "token": "\u00e8\u0126\u0124", "merges": "\u00e8\u0126 \u0124", "raw_count": 25346776, "count": 25346776, "decode_str": "\u8102"} -{"id": 52417, "token": "\u00e6\u00ae\u012d", "merges": "\u00e6\u00ae \u012d", "raw_count": 25363265, "count": 25363265, "decode_str": "\u6b8b"} -{"id": 52105, "token": "\u00e6\u0139\u0123", "merges": "\u00e6\u0139 \u0123", "raw_count": 25373841, "count": 25373841, "decode_str": "\u65c1"} -{"id": 52765, "token": "\u00e7\u012a\u00b7", "merges": "\u00e7\u012a \u00b7", "raw_count": 25379493, "count": 25379493, "decode_str": "\u7237"} -{"id": 54274, "token": "\u00e9\u0139\u00aa", "merges": "\u00e9\u0139 \u00aa", "raw_count": 25409644, "count": 25409644, "decode_str": "\u95ea"} -{"id": 53759, "token": "\u00e8\u00a7\u012a", "merges": "\u00e8\u00a7 \u012a", "raw_count": 25425517, "count": 25425517, "decode_str": "\u89c8"} -{"id": 54093, "token": "\u00e8\u00bf\u00b9", "merges": "\u00e8\u00bf \u00b9", "raw_count": 25479020, "count": 25479020, "decode_str": "\u8ff9"} -{"id": 50595, "token": "\u00e4\u00bf\u0126", "merges": "\u00e4\u00bf \u0126", "raw_count": 25527270, "count": 25527270, "decode_str": "\u4fc4"} -{"id": 788, "token": "get", "merges": "g et", "raw_count": 18835423, "count": 25538829, "decode_str": "get"} -{"id": 53845, "token": "\u00e8\u00af\u00b8", "merges": "\u00e8\u00af \u00b8", "raw_count": 25549888, "count": 25549888, "decode_str": "\u8bf8"} -{"id": 2270, "token": "90", "merges": "9 0", "raw_count": 22164547, "count": 25652458, "decode_str": "90"} -{"id": 51461, "token": "\u00e5\u00b0\u013a", "merges": "\u00e5\u00b0 \u013a", "raw_count": 25744572, "count": 25744572, "decode_str": "\u5c18"} -{"id": 1212, "token": "app", "merges": "a pp", "raw_count": 16067572, "count": 25771439, "decode_str": "app"} -{"id": 50964, "token": "\u00e5\u0132\u013d", "merges": "\u00e5\u0132 \u013d", "raw_count": 25907732, "count": 25907732, "decode_str": "\u541b"} -{"id": 53116, "token": "\u00e7\u00a5\u0138", "merges": "\u00e7\u00a5 \u0138", "raw_count": 25950605, "count": 25950605, "decode_str": "\u7956"} -{"id": 42522, "token": "\u00e6\u0138\u0129\u00e4\u00bb\u00b6", "merges": "\u00e6\u0138\u0129 \u00e4\u00bb\u00b6", "raw_count": 25950648, "count": 25950648, "decode_str": "\u6587\u4ef6"} -{"id": 363, "token": "ri", "merges": "r i", "raw_count": 941465, "count": 25954259, "decode_str": "ri"} -{"id": 51474, "token": "\u00e5\u00b0\u00be", "merges": "\u00e5\u00b0 \u00be", "raw_count": 25963526, "count": 25963526, "decode_str": "\u5c3e"} -{"id": 50460, "token": "\u00e4\u00b9\u00b3", "merges": "\u00e4\u00b9 \u00b3", "raw_count": 26084094, "count": 26084094, "decode_str": "\u4e73"} -{"id": 1630, "token": "27", "merges": "2 7", "raw_count": 21329264, "count": 26095356, "decode_str": "27"} -{"id": 53328, "token": "\u00e7\u00ba\u00b9", "merges": "\u00e7\u00ba \u00b9", "raw_count": 26122936, "count": 26122936, "decode_str": "\u7eb9"} -{"id": 53345, "token": "\u00e7\u00bb\u0137", "merges": "\u00e7\u00bb \u0137", "raw_count": 26149991, "count": 26149991, "decode_str": "\u7ed5"} -{"id": 54002, "token": "\u00e8\u00b7\u00a8", "merges": "\u00e8\u00b7 \u00a8", "raw_count": 26175807, "count": 26175807, "decode_str": "\u8de8"} -{"id": 323, "token": "\u0120for", "merges": "\u0120f or", "raw_count": 21341516, "count": 26223801, "decode_str": " for"} -{"id": 52262, "token": "\u00e6\u0141\u013e", "merges": "\u00e6\u0141 \u013e", "raw_count": 26227032, "count": 26227032, "decode_str": "\u67dc"} -{"id": 289, "token": "\u0120th", "merges": "\u0120t h", "raw_count": 333639, "count": 26287977, "decode_str": " th"} -{"id": 50795, "token": "\u00e5\u012b\u0133", "merges": "\u00e5\u012b \u0133", "raw_count": 26291465, "count": 26291465, "decode_str": "\u5251"} -{"id": 53236, "token": "\u00e7\u0143\u00b9", "merges": "\u00e7\u0143 \u00b9", "raw_count": 26428738, "count": 26428738, "decode_str": "\u7b79"} -{"id": 1731, "token": "26", "merges": "2 6", "raw_count": 22834853, "count": 26508536, "decode_str": "26"} -{"id": 50473, "token": "\u00e4\u00ba\u00a1", "merges": "\u00e4\u00ba \u00a1", "raw_count": 26534490, "count": 26534490, "decode_str": "\u4ea1"} -{"id": 51360, "token": "\u00e5\u00a7\u0135", "merges": "\u00e5\u00a7 \u0135", "raw_count": 26544343, "count": 26544343, "decode_str": "\u59d3"} -{"id": 53893, "token": "\u00e8\u00b0\u00b7", "merges": "\u00e8\u00b0 \u00b7", "raw_count": 26550564, "count": 26550564, "decode_str": "\u8c37"} -{"id": 682, "token": "ata", "merges": "at a", "raw_count": 917594, "count": 26581180, "decode_str": "ata"} -{"id": 52719, "token": "\u00e7\u0123\u00be", "merges": "\u00e7\u0123 \u00be", "raw_count": 26619339, "count": 26619339, "decode_str": "\u707e"} -{"id": 53451, "token": "\u00e8\u0122\u0139", "merges": "\u00e8\u0122 \u0139", "raw_count": 26654845, "count": 26654845, "decode_str": "\u8017"} -{"id": 51887, "token": "\u00e6\u012c\u00b5", "merges": "\u00e6\u012c \u00b5", "raw_count": 26678451, "count": 26678451, "decode_str": "\u62b5"} -{"id": 4672, "token": "!!", "merges": "! !", "raw_count": 14609047, "count": 26732615, "decode_str": "!!"} -{"id": 585, "token": "con", "merges": "c on", "raw_count": 1338414, "count": 26744596, "decode_str": "con"} -{"id": 52831, "token": "\u00e7\u0131\u0142", "merges": "\u00e7\u0131 \u0142", "raw_count": 26841644, "count": 26841644, "decode_str": "\u73e0"} -{"id": 52530, "token": "\u00e6\u00b3\u013d", "merges": "\u00e6\u00b3 \u013d", "raw_count": 26856307, "count": 26856307, "decode_str": "\u6cdb"} -{"id": 53416, "token": "\u00e7\u00bd\u013c", "merges": "\u00e7\u00bd \u013c", "raw_count": 26915902, "count": 26915902, "decode_str": "\u7f5a"} -{"id": 50476, "token": "\u00e4\u00ba\u00a6", "merges": "\u00e4\u00ba \u00a6", "raw_count": 26992855, "count": 26992855, "decode_str": "\u4ea6"} -{"id": 310, "token": "\u0120is", "merges": "\u0120 is", "raw_count": 23215618, "count": 27094003, "decode_str": " is"} -{"id": 51849, "token": "\u00e6\u012b\u00ab", "merges": "\u00e6\u012b \u00ab", "raw_count": 27115047, "count": 27115047, "decode_str": "\u626b"} -{"id": 50532, "token": "\u00e4\u00bc\u0141", "merges": "\u00e4\u00bc \u0141", "raw_count": 27136041, "count": 27136041, "decode_str": "\u4f1f"} -{"id": 9739, "token": "\"\"", "merges": "\" \"", "raw_count": 3376957, "count": 27156556, "decode_str": "\"\""} -{"id": 52259, "token": "\u00e6\u0141\u0136", "merges": "\u00e6\u0141 \u0136", "raw_count": 27171201, "count": 27171201, "decode_str": "\u67d4"} -{"id": 50828, "token": "\u00e5\u012d\u0129", "merges": "\u00e5\u012d \u0129", "raw_count": 27175013, "count": 27175013, "decode_str": "\u52c7"} -{"id": 52559, "token": "\u00e6\u00b4\u00a5", "merges": "\u00e6\u00b4 \u00a5", "raw_count": 27192275, "count": 27192275, "decode_str": "\u6d25"} -{"id": 19119, "token": "\u00e8\u00aa", "merges": "\u00e8 \u00aa", "raw_count": 104685, "count": 27198967, "decode_str": "\ufffd"} -{"id": 52702, "token": "\u00e6\u00bc\u00ab", "merges": "\u00e6\u00bc \u00ab", "raw_count": 27210840, "count": 27210840, "decode_str": "\u6f2b"} -{"id": 1525, "token": "99", "merges": "9 9", "raw_count": 14575580, "count": 27236759, "decode_str": "99"} -{"id": 446, "token": "pl", "merges": "p l", "raw_count": 1672304, "count": 27302115, "decode_str": "pl"} -{"id": 51463, "token": "\u00e5\u00b0\u013f", "merges": "\u00e5\u00b0 \u013f", "raw_count": 27313283, "count": 27313283, "decode_str": "\u5c1d"} -{"id": 51560, "token": "\u00e5\u00ba\u0126", "merges": "\u00e5\u00ba \u0126", "raw_count": 27390061, "count": 27390061, "decode_str": "\u5e84"} -{"id": 51903, "token": "\u00e6\u012d\u0134", "merges": "\u00e6\u012d \u0134", "raw_count": 27423058, "count": 27423058, "decode_str": "\u62d2"} -{"id": 52597, "token": "\u00e6\u00b6\u0124", "merges": "\u00e6\u00b6 \u0124", "raw_count": 27462470, "count": 27462470, "decode_str": "\u6d82"} -{"id": 51718, "token": "\u00e6\u0123\u00a2", "merges": "\u00e6\u0123 \u00a2", "raw_count": 27547069, "count": 27547069, "decode_str": "\u6062"} -{"id": 52582, "token": "\u00e6\u00b5\u0135", "merges": "\u00e6\u00b5 \u0135", "raw_count": 27563895, "count": 27563895, "decode_str": "\u6d53"} -{"id": 706, "token": "ob", "merges": "o b", "raw_count": 1585177, "count": 27711382, "decode_str": "ob"} -{"id": 51913, "token": "\u00e6\u012d\u0141", "merges": "\u00e6\u012d \u0141", "raw_count": 27729233, "count": 27729233, "decode_str": "\u62df"} -{"id": 50749, "token": "\u00e5\u0129\u00a1", "merges": "\u00e5\u0129 \u00a1", "raw_count": 27736497, "count": 27736497, "decode_str": "\u51e1"} -{"id": 54478, "token": "\u00e9\u00a6\u012a", "merges": "\u00e9\u00a6 \u012a", "raw_count": 27841544, "count": 27841544, "decode_str": "\u9988"} -{"id": 51802, "token": "\u00e6\u0127\u00a7", "merges": "\u00e6\u0127 \u00a7", "raw_count": 27854966, "count": 27854966, "decode_str": "\u6167"} -{"id": 343, "token": "ir", "merges": "i r", "raw_count": 1759846, "count": 27859995, "decode_str": "ir"} -{"id": 51957, "token": "\u00e6\u012e\u00ba", "merges": "\u00e6\u012e \u00ba", "raw_count": 27873079, "count": 27873079, "decode_str": "\u633a"} -{"id": 52753, "token": "\u00e7\u0126\u00a6", "merges": "\u00e7\u0126 \u00a6", "raw_count": 27901397, "count": 27901397, "decode_str": "\u7126"} -{"id": 53731, "token": "\u00e8\u00a3\u0123", "merges": "\u00e8\u00a3 \u0123", "raw_count": 27956310, "count": 27956310, "decode_str": "\u88c1"} -{"id": 375, "token": "os", "merges": "o s", "raw_count": 6795334, "count": 27973221, "decode_str": "os"} -{"id": 406, "token": "oc", "merges": "o c", "raw_count": 1753009, "count": 28083139, "decode_str": "oc"} -{"id": 53965, "token": "\u00e8\u00b5\u00a2", "merges": "\u00e8\u00b5 \u00a2", "raw_count": 28084572, "count": 28084572, "decode_str": "\u8d62"} -{"id": 332, "token": "ver", "merges": "v er", "raw_count": 795117, "count": 28106835, "decode_str": "ver"} -{"id": 51635, "token": "\u00e5\u00bd\u00bb", "merges": "\u00e5\u00bd \u00bb", "raw_count": 28153758, "count": 28153758, "decode_str": "\u5f7b"} -{"id": 50449, "token": "\u00e4\u00b9\u013a", "merges": "\u00e4\u00b9 \u013a", "raw_count": 28212656, "count": 28212656, "decode_str": "\u4e58"} -{"id": 51555, "token": "\u00e5\u00b9\u00bc", "merges": "\u00e5\u00b9 \u00bc", "raw_count": 28269730, "count": 28269730, "decode_str": "\u5e7c"} -{"id": 1619, "token": "28", "merges": "2 8", "raw_count": 23785921, "count": 28299059, "decode_str": "28"} -{"id": 52330, "token": "\u00e6\u00a3\u00ae", "merges": "\u00e6\u00a3 \u00ae", "raw_count": 28343242, "count": 28343242, "decode_str": "\u68ee"} -{"id": 50991, "token": "\u00e5\u0133\u012a", "merges": "\u00e5\u0133 \u012a", "raw_count": 28358238, "count": 28358238, "decode_str": "\u5448"} -{"id": 412, "token": "op", "merges": "o p", "raw_count": 2430148, "count": 28400774, "decode_str": "op"} -{"id": 51381, "token": "\u00e5\u0143\u013b", "merges": "\u00e5\u0143 \u013b", "raw_count": 28437815, "count": 28437815, "decode_str": "\u5b59"} -{"id": 52416, "token": "\u00e6\u00ae\u012c", "merges": "\u00e6\u00ae \u012c", "raw_count": 28472401, "count": 28472401, "decode_str": "\u6b8a"} -{"id": 53704, "token": "\u00e8\u00a1\u00a1", "merges": "\u00e8\u00a1 \u00a1", "raw_count": 28488921, "count": 28488921, "decode_str": "\u8861"} -{"id": 51713, "token": "\u00e6\u0123\u0132", "merges": "\u00e6\u0123 \u0132", "raw_count": 28497062, "count": 28497062, "decode_str": "\u6050"} -{"id": 6961, "token": "2016", "merges": "201 6", "raw_count": 28500343, "count": 28500343, "decode_str": "2016"} -{"id": 51880, "token": "\u00e6\u012c\u00a2", "merges": "\u00e6\u012c \u00a2", "raw_count": 28509393, "count": 28509393, "decode_str": "\u62a2"} -{"id": 53421, "token": "\u00e7\u00bd\u00b2", "merges": "\u00e7\u00bd \u00b2", "raw_count": 28576650, "count": 28576650, "decode_str": "\u7f72"} -{"id": 53975, "token": "\u00e8\u00b5\u00b5", "merges": "\u00e8\u00b5 \u00b5", "raw_count": 28610275, "count": 28610275, "decode_str": "\u8d75"} -{"id": 51826, "token": "\u00e6\u012a\u00b4", "merges": "\u00e6\u012a \u00b4", "raw_count": 28739711, "count": 28739711, "decode_str": "\u6234"} -{"id": 51437, "token": "\u00e5\u00af\u0134", "merges": "\u00e5\u00af \u0134", "raw_count": 28797006, "count": 28797006, "decode_str": "\u5bd2"} -{"id": 54314, "token": "\u00e9\u013a\u00bb", "merges": "\u00e9\u013a \u00bb", "raw_count": 28809453, "count": 28809453, "decode_str": "\u963b"} -{"id": 53390, "token": "\u00e7\u00bc\u013a", "merges": "\u00e7\u00bc \u013a", "raw_count": 28809974, "count": 28809974, "decode_str": "\u7f18"} -{"id": 51844, "token": "\u00e6\u012b\u00a3", "merges": "\u00e6\u012b \u00a3", "raw_count": 28811218, "count": 28811218, "decode_str": "\u6263"} -{"id": 53671, "token": "\u00e8\u0130\u00ab", "merges": "\u00e8\u0130 \u00ab", "raw_count": 28889639, "count": 28889639, "decode_str": "\u83ab"} -{"id": 54006, "token": "\u00e8\u00b7\u00b5", "merges": "\u00e8\u00b7 \u00b5", "raw_count": 29044211, "count": 29044211, "decode_str": "\u8df5"} -{"id": 9638, "token": "2019", "merges": "201 9", "raw_count": 29062669, "count": 29062669, "decode_str": "2019"} -{"id": 8318, "token": "\u013b\u00aa", "merges": "\u013b \u00aa", "raw_count": 1698, "count": 29078951, "decode_str": "\ufffd\ufffd"} -{"id": 52648, "token": "\u00e6\u00b7\u00bb", "merges": "\u00e6\u00b7 \u00bb", "raw_count": 29079336, "count": 29079336, "decode_str": "\u6dfb"} -{"id": 53980, "token": "\u00e8\u00b6\u012d", "merges": "\u00e8\u00b6 \u012d", "raw_count": 29110330, "count": 29110330, "decode_str": "\u8d8b"} -{"id": 331, "token": "\u0120st", "merges": "\u0120s t", "raw_count": 745536, "count": 29154969, "decode_str": " st"} -{"id": 53051, "token": "\u00e7\u0141\u00bf", "merges": "\u00e7\u0141 \u00bf", "raw_count": 29215058, "count": 29215058, "decode_str": "\u77ff"} -{"id": 51573, "token": "\u00e5\u00ba\u0141", "merges": "\u00e5\u00ba \u0141", "raw_count": 29301516, "count": 29301516, "decode_str": "\u5e9f"} -{"id": 52541, "token": "\u00e6\u00b3\u00b0", "merges": "\u00e6\u00b3 \u00b0", "raw_count": 29320949, "count": 29320949, "decode_str": "\u6cf0"} -{"id": 319, "token": "ow", "merges": "o w", "raw_count": 827913, "count": 29349538, "decode_str": "ow"} -{"id": 350, "token": "ter", "merges": "t er", "raw_count": 1117545, "count": 29407240, "decode_str": "ter"} -{"id": 50980, "token": "\u00e5\u0132\u00b4", "merges": "\u00e5\u0132 \u00b4", "raw_count": 29574148, "count": 29574148, "decode_str": "\u5434"} -{"id": 54005, "token": "\u00e8\u00b7\u00b3", "merges": "\u00e8\u00b7 \u00b3", "raw_count": 29685151, "count": 29685151, "decode_str": "\u8df3"} -{"id": 51704, "token": "\u00e6\u0122\u00aa", "merges": "\u00e6\u0122 \u00aa", "raw_count": 29760810, "count": 29760810, "decode_str": "\u602a"} -{"id": 53962, "token": "\u00e8\u00b5\u0140", "merges": "\u00e8\u00b5 \u0140", "raw_count": 29863374, "count": 29863374, "decode_str": "\u8d5e"} -{"id": 50520, "token": "\u00e4\u00bc\u012c", "merges": "\u00e4\u00bc \u012c", "raw_count": 29921203, "count": 29921203, "decode_str": "\u4f0a"} -{"id": 54218, "token": "\u00e9\u0136\u0123", "merges": "\u00e9\u0136 \u0123", "raw_count": 29959988, "count": 29959988, "decode_str": "\u9501"} -{"id": 53813, "token": "\u00e8\u00af\u012c", "merges": "\u00e8\u00af \u012c", "raw_count": 29981792, "count": 29981792, "decode_str": "\u8bca"} -{"id": 51778, "token": "\u00e6\u0125\u00af", "merges": "\u00e6\u0125 \u00af", "raw_count": 29996738, "count": 29996738, "decode_str": "\u60ef"} -{"id": 51890, "token": "\u00e6\u012c\u00bd", "merges": "\u00e6\u012c \u00bd", "raw_count": 30048291, "count": 30048291, "decode_str": "\u62bd"} -{"id": 53519, "token": "\u00e8\u0125\u00a1", "merges": "\u00e8\u0125 \u00a1", "raw_count": 30051058, "count": 30051058, "decode_str": "\u80e1"} -{"id": 51351, "token": "\u00e5\u00a6\u00b9", "merges": "\u00e5\u00a6 \u00b9", "raw_count": 30152833, "count": 30152833, "decode_str": "\u59b9"} -{"id": 54053, "token": "\u00e8\u00be\u013d", "merges": "\u00e8\u00be \u013d", "raw_count": 30156465, "count": 30156465, "decode_str": "\u8f9b"} -{"id": 54311, "token": "\u00e9\u013a\u00b4", "merges": "\u00e9\u013a \u00b4", "raw_count": 30191737, "count": 30191737, "decode_str": "\u9634"} -{"id": 51640, "token": "\u00e5\u00be\u0126", "merges": "\u00e5\u00be \u0126", "raw_count": 30367759, "count": 30367759, "decode_str": "\u5f84"} -{"id": 52442, "token": "\u00e6\u00af\u00ab", "merges": "\u00e6\u00af \u00ab", "raw_count": 30433454, "count": 30433454, "decode_str": "\u6beb"} -{"id": 53722, "token": "\u00e8\u00a2\u012d", "merges": "\u00e8\u00a2 \u012d", "raw_count": 30439321, "count": 30439321, "decode_str": "\u888b"} -{"id": 52139, "token": "\u00e6\u013a\u0142", "merges": "\u00e6\u013a \u0142", "raw_count": 30490102, "count": 30490102, "decode_str": "\u6620"} -{"id": 50936, "token": "\u00e5\u0131\u00ac", "merges": "\u00e5\u0131 \u00ac", "raw_count": 30631639, "count": 30631639, "decode_str": "\u53ec"} -{"id": 8924, "token": "\u00e2\u0122\u013a", "merges": "\u00e2\u0122 \u013a", "raw_count": 30650525, "count": 30650525, "decode_str": "\u2018"} -{"id": 51091, "token": "\u00e5\u0137\u00a5", "merges": "\u00e5\u0137 \u00a5", "raw_count": 30842989, "count": 30842989, "decode_str": "\u5565"} -{"id": 50652, "token": "\u00e5\u0123\u00bf", "merges": "\u00e5\u0123 \u00bf", "raw_count": 30875979, "count": 30875979, "decode_str": "\u507f"} -{"id": 53867, "token": "\u00e8\u00b0\u0135", "merges": "\u00e8\u00b0 \u0135", "raw_count": 30901811, "count": 30901811, "decode_str": "\u8c13"} -{"id": 47397, "token": "\u00e8\u00bf\u0136", "merges": "\u00e8\u00bf \u0136", "raw_count": 30966178, "count": 30966178, "decode_str": "\u8fd4"} -{"id": 53895, "token": "\u00e8\u00b1\u0128", "merges": "\u00e8\u00b1 \u0128", "raw_count": 31126823, "count": 31126823, "decode_str": "\u8c46"} -{"id": 51593, "token": "\u00e5\u00bc\u0125", "merges": "\u00e5\u00bc \u0125", "raw_count": 31136829, "count": 31136829, "decode_str": "\u5f03"} -{"id": 376, "token": "ra", "merges": "r a", "raw_count": 2186910, "count": 31229366, "decode_str": "ra"} -{"id": 51895, "token": "\u00e6\u012d\u0128", "merges": "\u00e6\u012d \u0128", "raw_count": 31256288, "count": 31256288, "decode_str": "\u62c6"} -{"id": 52071, "token": "\u00e6\u0137\u0131", "merges": "\u00e6\u0137 \u0131", "raw_count": 31347674, "count": 31347674, "decode_str": "\u654f"} -{"id": 50763, "token": "\u00e5\u012a\u0122", "merges": "\u00e5\u012a \u0122", "raw_count": 31428195, "count": 31428195, "decode_str": "\u5200"} -{"id": 54291, "token": "\u00e9\u013a\u0127", "merges": "\u00e9\u013a \u0127", "raw_count": 31470530, "count": 31470530, "decode_str": "\u9605"} -{"id": 51332, "token": "\u00e5\u00a6\u0129", "merges": "\u00e5\u00a6 \u0129", "raw_count": 31510621, "count": 31510621, "decode_str": "\u5987"} -{"id": 50895, "token": "\u00e5\u012f\u00b7", "merges": "\u00e5\u012f \u00b7", "raw_count": 31523551, "count": 31523551, "decode_str": "\u5377"} -{"id": 53481, "token": "\u00e8\u0124\u012e", "merges": "\u00e8\u0124 \u012e", "raw_count": 31587676, "count": 31587676, "decode_str": "\u808c"} -{"id": 52191, "token": "\u00e6\u013e\u0139", "merges": "\u00e6\u013e \u0139", "raw_count": 31608932, "count": 31608932, "decode_str": "\u6717"} -{"id": 51507, "token": "\u00e5\u00b7\u00a7", "merges": "\u00e5\u00b7 \u00a7", "raw_count": 31609274, "count": 31609274, "decode_str": "\u5de7"} -{"id": 53846, "token": "\u00e8\u00af\u00ba", "merges": "\u00e8\u00af \u00ba", "raw_count": 31615013, "count": 31615013, "decode_str": "\u8bfa"} -{"id": 54533, "token": "\u00e9\u00bb\u013a", "merges": "\u00e9\u00bb \u013a", "raw_count": 31840256, "count": 31840256, "decode_str": "\u9ed8"} -{"id": 531, "token": "one", "merges": "on e", "raw_count": 3288278, "count": 31881394, "decode_str": "one"} -{"id": 515, "token": "ass", "merges": "as s", "raw_count": 1029347, "count": 31916821, "decode_str": "ass"} -{"id": 51092, "token": "\u00e5\u0137\u00a6", "merges": "\u00e5\u0137 \u00a6", "raw_count": 31929696, "count": 31929696, "decode_str": "\u5566"} -{"id": 457, "token": "\u00e2\u0122\u013b", "merges": "\u00e2\u0122 \u013b", "raw_count": 25569312, "count": 31950407, "decode_str": "\u2019"} -{"id": 54126, "token": "\u00e9\u0123\u012f", "merges": "\u00e9\u0123 \u012f", "raw_count": 32061447, "count": 32061447, "decode_str": "\u904d"} -{"id": 306, "token": "ve", "merges": "v e", "raw_count": 990258, "count": 32315739, "decode_str": "ve"} -{"id": 54360, "token": "\u00e9\u013d\u0126", "merges": "\u00e9\u013d \u0126", "raw_count": 32325049, "count": 32325049, "decode_str": "\u96c4"} -{"id": 52197, "token": "\u00e6\u013e\u00ab", "merges": "\u00e6\u013e \u00ab", "raw_count": 32353134, "count": 32353134, "decode_str": "\u672b"} -{"id": 587, "token": "ile", "merges": "i le", "raw_count": 1082994, "count": 32373917, "decode_str": "ile"} -{"id": 50619, "token": "\u00e5\u0122\u012f", "merges": "\u00e5\u0122 \u012f", "raw_count": 32378938, "count": 32378938, "decode_str": "\u500d"} -{"id": 288, "token": "\u0120h", "merges": "\u0120 h", "raw_count": 2803743, "count": 32461386, "decode_str": " h"} -{"id": 1508, "token": "23", "merges": "2 3", "raw_count": 28073010, "count": 32476114, "decode_str": "23"} -{"id": 52726, "token": "\u00e7\u0124\u0130", "merges": "\u00e7\u0124 \u0130", "raw_count": 32492003, "count": 32492003, "decode_str": "\u708e"} -{"id": 57, "token": "X", "merges": "NULL", "raw_count": 17276018, "count": 32500007, "decode_str": "X"} -{"id": 52989, "token": "\u00e7\u013d\u0134", "merges": "\u00e7\u013d \u0134", "raw_count": 32617520, "count": 32617520, "decode_str": "\u76d2"} -{"id": 54433, "token": "\u00e9\u00a1\u00bf", "merges": "\u00e9\u00a1 \u00bf", "raw_count": 32780708, "count": 32780708, "decode_str": "\u987f"} -{"id": 489, "token": "ue", "merges": "u e", "raw_count": 881862, "count": 32793693, "decode_str": "ue"} -{"id": 53493, "token": "\u00e8\u0124\u00a5", "merges": "\u00e8\u0124 \u00a5", "raw_count": 32836320, "count": 32836320, "decode_str": "\u80a5"} -{"id": 51737, "token": "\u00e6\u0124\u012b", "merges": "\u00e6\u0124 \u012b", "raw_count": 32842527, "count": 32842527, "decode_str": "\u6089"} -{"id": 333, "token": "ay", "merges": "a y", "raw_count": 1590104, "count": 32933443, "decode_str": "ay"} -{"id": 53833, "token": "\u00e8\u00af\u00a6", "merges": "\u00e8\u00af \u00a6", "raw_count": 32962867, "count": 32962867, "decode_str": "\u8be6"} -{"id": 52081, "token": "\u00e6\u0137\u00ac", "merges": "\u00e6\u0137 \u00ac", "raw_count": 32977955, "count": 32977955, "decode_str": "\u656c"} -{"id": 52505, "token": "\u00e6\u00b2\u0141", "merges": "\u00e6\u00b2 \u0141", "raw_count": 33026792, "count": 33026792, "decode_str": "\u6c9f"} -{"id": 51672, "token": "\u00e5\u00bf\u013a", "merges": "\u00e5\u00bf \u013a", "raw_count": 33121940, "count": 33121940, "decode_str": "\u5fd8"} -{"id": 52313, "token": "\u00e6\u00a1\u00a5", "merges": "\u00e6\u00a1 \u00a5", "raw_count": 33176702, "count": 33176702, "decode_str": "\u6865"} -{"id": 995, "token": "\",", "merges": "\" ,", "raw_count": 32319448, "count": 33192759, "decode_str": "\","} -{"id": 52533, "token": "\u00e6\u00b3\u00a1", "merges": "\u00e6\u00b3 \u00a1", "raw_count": 33298611, "count": 33298611, "decode_str": "\u6ce1"} -{"id": 52015, "token": "\u00e6\u0131\u0134", "merges": "\u00e6\u0131 \u0134", "raw_count": 33379751, "count": 33379751, "decode_str": "\u63d2"} -{"id": 51857, "token": "\u00e6\u012b\u00b6", "merges": "\u00e6\u012b \u00b6", "raw_count": 33427413, "count": 33427413, "decode_str": "\u6276"} -{"id": 53594, "token": "\u00e8\u012a\u00b9", "merges": "\u00e8\u012a \u00b9", "raw_count": 33435607, "count": 33435607, "decode_str": "\u8239"} -{"id": 50654, "token": "\u00e5\u0124\u0127", "merges": "\u00e5\u0124 \u0127", "raw_count": 33547708, "count": 33547708, "decode_str": "\u5085"} -{"id": 54137, "token": "\u00e9\u0123\u0143", "merges": "\u00e9\u0123 \u0143", "raw_count": 33634672, "count": 33634672, "decode_str": "\u906d"} -{"id": 305, "token": "\u0120g", "merges": "\u0120 g", "raw_count": 3075002, "count": 33665708, "decode_str": " g"} -{"id": 54276, "token": "\u00e9\u0139\u0143", "merges": "\u00e9\u0139 \u0143", "raw_count": 33695023, "count": 33695023, "decode_str": "\u95ed"} -{"id": 54221, "token": "\u00e9\u0136\u0127", "merges": "\u00e9\u0136 \u0127", "raw_count": 33695170, "count": 33695170, "decode_str": "\u9505"} -{"id": 54361, "token": "\u00e9\u013d\u0127", "merges": "\u00e9\u013d \u0127", "raw_count": 33839628, "count": 33839628, "decode_str": "\u96c5"} -{"id": 53976, "token": "\u00e8\u00b5\u00b6", "merges": "\u00e8\u00b5 \u00b6", "raw_count": 34044851, "count": 34044851, "decode_str": "\u8d76"} -{"id": 54383, "token": "\u00e9\u013e\u0129", "merges": "\u00e9\u013e \u0129", "raw_count": 34046631, "count": 34046631, "decode_str": "\u9707"} -{"id": 686, "token": "\u0120'", "merges": "\u0120 '", "raw_count": 27586967, "count": 34146292, "decode_str": " '"} -{"id": 52553, "token": "\u00e6\u00b4\u012d", "merges": "\u00e6\u00b4 \u012d", "raw_count": 34149730, "count": 34149730, "decode_str": "\u6d0b"} -{"id": 382, "token": "ist", "merges": "is t", "raw_count": 1832931, "count": 34272731, "decode_str": "ist"} -{"id": 52113, "token": "\u00e6\u0139\u0139", "merges": "\u00e6\u0139 \u0139", "raw_count": 34300307, "count": 34300307, "decode_str": "\u65d7"} -{"id": 53963, "token": "\u00e8\u00b5\u0142", "merges": "\u00e8\u00b5 \u0142", "raw_count": 34393787, "count": 34393787, "decode_str": "\u8d60"} -{"id": 52766, "token": "\u00e7\u012a\u00b8", "merges": "\u00e7\u012a \u00b8", "raw_count": 34413736, "count": 34413736, "decode_str": "\u7238"} -{"id": 373, "token": "res", "merges": "re s", "raw_count": 3215313, "count": 34423473, "decode_str": "res"} -{"id": 357, "token": "ab", "merges": "a b", "raw_count": 3344445, "count": 34438959, "decode_str": "ab"} -{"id": 51182, "token": "\u00e5\u013e\u00a3", "merges": "\u00e5\u013e \u00a3", "raw_count": 34444354, "count": 34444354, "decode_str": "\u5723"} -{"id": 53283, "token": "\u00e7\u00b3\u0138", "merges": "\u00e7\u00b3 \u0138", "raw_count": 34465952, "count": 34465952, "decode_str": "\u7cd6"} -{"id": 51934, "token": "\u00e6\u012e\u0124", "merges": "\u00e6\u012e \u0124", "raw_count": 34691006, "count": 34691006, "decode_str": "\u6302"} -{"id": 50529, "token": "\u00e4\u00bc\u013b", "merges": "\u00e4\u00bc \u013b", "raw_count": 34700001, "count": 34700001, "decode_str": "\u4f19"} -{"id": 50725, "token": "\u00e5\u0128\u00ac", "merges": "\u00e5\u0128 \u00ac", "raw_count": 34780723, "count": 34780723, "decode_str": "\u51ac"} -{"id": 51378, "token": "\u00e5\u0143\u0136", "merges": "\u00e5\u0143 \u0136", "raw_count": 34787163, "count": 34787163, "decode_str": "\u5b54"} -{"id": 50785, "token": "\u00e5\u012a\u00ba", "merges": "\u00e5\u012a \u00ba", "raw_count": 34882818, "count": 34882818, "decode_str": "\u523a"} -{"id": 54091, "token": "\u00e8\u00bf\u00b7", "merges": "\u00e8\u00bf \u00b7", "raw_count": 34943324, "count": 34943324, "decode_str": "\u8ff7"} -{"id": 52590, "token": "\u00e6\u00b5\u00aa", "merges": "\u00e6\u00b5 \u00aa", "raw_count": 34989859, "count": 34989859, "decode_str": "\u6d6a"} -{"id": 54214, "token": "\u00e9\u0129\u0130", "merges": "\u00e9\u0129 \u0130", "raw_count": 35082833, "count": 35082833, "decode_str": "\u91ce"} -{"id": 1797, "token": "21", "merges": "2 1", "raw_count": 33358029, "count": 35104057, "decode_str": "21"} -{"id": 50782, "token": "\u00e5\u012a\u00b7", "merges": "\u00e5\u012a \u00b7", "raw_count": 35170392, "count": 35170392, "decode_str": "\u5237"} -{"id": 53149, "token": "\u00e7\u00a7\u012d", "merges": "\u00e7\u00a7 \u012d", "raw_count": 35235327, "count": 35235327, "decode_str": "\u79cb"} -{"id": 51850, "token": "\u00e6\u012b\u00ac", "merges": "\u00e6\u012b \u00ac", "raw_count": 35313586, "count": 35313586, "decode_str": "\u626c"} -{"id": 52312, "token": "\u00e6\u00a1\u00a3", "merges": "\u00e6\u00a1 \u00a3", "raw_count": 35324171, "count": 35324171, "decode_str": "\u6863"} -{"id": 335, "token": "ul", "merges": "u l", "raw_count": 1193297, "count": 35339033, "decode_str": "ul"} -{"id": 52142, "token": "\u00e6\u013a\u00a8", "merges": "\u00e6\u013a \u00a8", "raw_count": 35361057, "count": 35361057, "decode_str": "\u6628"} -{"id": 52638, "token": "\u00e6\u00b7\u00a1", "merges": "\u00e6\u00b7 \u00a1", "raw_count": 35366423, "count": 35366423, "decode_str": "\u6de1"} -{"id": 51421, "token": "\u00e5\u00ae\u00ab", "merges": "\u00e5\u00ae \u00ab", "raw_count": 35391045, "count": 35391045, "decode_str": "\u5bab"} -{"id": 50712, "token": "\u00e5\u0128\u012e", "merges": "\u00e5\u0128 \u012e", "raw_count": 35439408, "count": 35439408, "decode_str": "\u518c"} -{"id": 52796, "token": "\u00e7\u012c\u00af", "merges": "\u00e7\u012c \u00af", "raw_count": 35440312, "count": 35440312, "decode_str": "\u72af"} -{"id": 299, "token": "\u0120e", "merges": "\u0120 e", "raw_count": 3522447, "count": 35458313, "decode_str": " e"} -{"id": 54131, "token": "\u00e9\u0123\u0139", "merges": "\u00e9\u0123 \u0139", "raw_count": 35486742, "count": 35486742, "decode_str": "\u9057"} -{"id": 53583, "token": "\u00e8\u012a\u0140", "merges": "\u00e8\u012a \u0140", "raw_count": 35582587, "count": 35582587, "decode_str": "\u821e"} -{"id": 54347, "token": "\u00e9\u013c\u0136", "merges": "\u00e9\u013c \u0136", "raw_count": 35612250, "count": 35612250, "decode_str": "\u9694"} -{"id": 50661, "token": "\u00e5\u0124\u00ac", "merges": "\u00e5 \u0124\u00ac", "raw_count": 35698196, "count": 35698196, "decode_str": "\u50ac"} -{"id": 51730, "token": "\u00e6\u0123\u00b6", "merges": "\u00e6\u0123 \u00b6", "raw_count": 35812212, "count": 35812212, "decode_str": "\u6076"} -{"id": 54107, "token": "\u00e9\u0122\u0136", "merges": "\u00e9\u0122 \u0136", "raw_count": 35855157, "count": 35855157, "decode_str": "\u9014"} -{"id": 51448, "token": "\u00e5\u00af\u00b8", "merges": "\u00e5\u00af \u00b8", "raw_count": 35870928, "count": 35870928, "decode_str": "\u5bf8"} -{"id": 53400, "token": "\u00e7\u00bc\u00a9", "merges": "\u00e7\u00bc \u00a9", "raw_count": 36065295, "count": 36065295, "decode_str": "\u7f29"} -{"id": 52223, "token": "\u00e6\u013f\u00af", "merges": "\u00e6\u013f \u00af", "raw_count": 36238531, "count": 36238531, "decode_str": "\u676f"} -{"id": 51266, "token": "\u00e5\u00a2\u013b", "merges": "\u00e5\u00a2 \u013b", "raw_count": 36249358, "count": 36249358, "decode_str": "\u5899"} -{"id": 51044, "token": "\u00e5\u0134\u00b1", "merges": "\u00e5\u0134 \u00b1", "raw_count": 36345684, "count": 36345684, "decode_str": "\u54b1"} -{"id": 50954, "token": "\u00e5\u0132\u012b", "merges": "\u00e5\u0132 \u012b", "raw_count": 36504695, "count": 36504695, "decode_str": "\u5409"} -{"id": 52078, "token": "\u00e6\u0137\u00a2", "merges": "\u00e6\u0137 \u00a2", "raw_count": 36534482, "count": 36534482, "decode_str": "\u6562"} -{"id": 53993, "token": "\u00e8\u00b7\u012e", "merges": "\u00e8\u00b7 \u012e", "raw_count": 36575203, "count": 36575203, "decode_str": "\u8dcc"} -{"id": 53822, "token": "\u00e8\u00af\u013c", "merges": "\u00e8\u00af \u013c", "raw_count": 36598767, "count": 36598767, "decode_str": "\u8bda"} -{"id": 51612, "token": "\u00e5\u00bc\u00b1", "merges": "\u00e5\u00bc \u00b1", "raw_count": 36713747, "count": 36713747, "decode_str": "\u5f31"} -{"id": 52925, "token": "\u00e7\u0138\u00be", "merges": "\u00e7\u0138 \u00be", "raw_count": 36766787, "count": 36766787, "decode_str": "\u75be"} -{"id": 53819, "token": "\u00e8\u00af\u0139", "merges": "\u00e8\u00af \u0139", "raw_count": 36795833, "count": 36795833, "decode_str": "\u8bd7"} -{"id": 50586, "token": "\u00e4\u00be\u00a7", "merges": "\u00e4\u00be \u00a7", "raw_count": 36867567, "count": 36867567, "decode_str": "\u4fa7"} -{"id": 54210, "token": "\u00e9\u0128\u0134", "merges": "\u00e9 \u0128\u0134", "raw_count": 36962958, "count": 36962958, "decode_str": "\u9192"} -{"id": 53152, "token": "\u00e7\u00a7\u013a", "merges": "\u00e7\u00a7 \u013a", "raw_count": 37052765, "count": 37052765, "decode_str": "\u79d8"} -{"id": 51450, "token": "\u00e5\u00af\u00bb", "merges": "\u00e5\u00af \u00bb", "raw_count": 37091799, "count": 37091799, "decode_str": "\u5bfb"} -{"id": 52393, "token": "\u00e6\u0143\u012b", "merges": "\u00e6\u0143 \u012b", "raw_count": 37138641, "count": 37138641, "decode_str": "\u6b49"} -{"id": 53420, "token": "\u00e7\u00bd\u00aa", "merges": "\u00e7\u00bd \u00aa", "raw_count": 37185962, "count": 37185962, "decode_str": "\u7f6a"} -{"id": 51502, "token": "\u00e5\u00b7\u013f", "merges": "\u00e5\u00b7 \u013f", "raw_count": 37319642, "count": 37319642, "decode_str": "\u5ddd"} -{"id": 358, "token": "em", "merges": "e m", "raw_count": 1994138, "count": 37354701, "decode_str": "em"} -{"id": 1438, "token": "80", "merges": "8 0", "raw_count": 27019513, "count": 37449209, "decode_str": "80"} -{"id": 52877, "token": "\u00e7\u0136\u00b2", "merges": "\u00e7\u0136 \u00b2", "raw_count": 37466761, "count": 37466761, "decode_str": "\u7532"} -{"id": 54416, "token": "\u00e9\u0141\u00a9", "merges": "\u00e9\u0141 \u00a9", "raw_count": 37511837, "count": 37511837, "decode_str": "\u97e9"} -{"id": 51604, "token": "\u00e5\u00bc\u0141", "merges": "\u00e5\u00bc \u0141", "raw_count": 37520551, "count": 37520551, "decode_str": "\u5f1f"} -{"id": 54312, "token": "\u00e9\u013a\u00b5", "merges": "\u00e9\u013a \u00b5", "raw_count": 37567579, "count": 37567579, "decode_str": "\u9635"} -{"id": 52646, "token": "\u00e6\u00b7\u00b7", "merges": "\u00e6\u00b7 \u00b7", "raw_count": 37587205, "count": 37587205, "decode_str": "\u6df7"} -{"id": 51470, "token": "\u00e5\u00b0\u00ba", "merges": "\u00e5\u00b0 \u00ba", "raw_count": 37655490, "count": 37655490, "decode_str": "\u5c3a"} -{"id": 50659, "token": "\u00e5\u0124\u00a8", "merges": "\u00e5\u0124 \u00a8", "raw_count": 37699949, "count": 37699949, "decode_str": "\u50a8"} -{"id": 53530, "token": "\u00e8\u0125\u00b6", "merges": "\u00e8\u0125 \u00b6", "raw_count": 37764259, "count": 37764259, "decode_str": "\u80f6"} -{"id": 54261, "token": "\u00e9\u0137\u013e", "merges": "\u00e9\u0137 \u013e", "raw_count": 37792143, "count": 37792143, "decode_str": "\u955c"} -{"id": 53936, "token": "\u00e8\u00b4\u00b8", "merges": "\u00e8\u00b4 \u00b8", "raw_count": 37887174, "count": 37887174, "decode_str": "\u8d38"} -{"id": 53319, "token": "\u00e7\u00ba\u00af", "merges": "\u00e7\u00ba \u00af", "raw_count": 37913704, "count": 37913704, "decode_str": "\u7eaf"} -{"id": 53326, "token": "\u00e7\u00ba\u00b7", "merges": "\u00e7\u00ba \u00b7", "raw_count": 37965266, "count": 37965266, "decode_str": "\u7eb7"} -{"id": 53134, "token": "\u00e7\u00a6\u0123", "merges": "\u00e7\u00a6 \u0123", "raw_count": 37970677, "count": 37970677, "decode_str": "\u7981"} -{"id": 51464, "token": "\u00e5\u00b0\u00a4", "merges": "\u00e5\u00b0 \u00a4", "raw_count": 38203816, "count": 38203816, "decode_str": "\u5c24"} -{"id": 50789, "token": "\u00e5\u012b\u0124", "merges": "\u00e5\u012b \u0124", "raw_count": 38209473, "count": 38209473, "decode_str": "\u5242"} -{"id": 371, "token": "qu", "merges": "q u", "raw_count": 1109773, "count": 38216933, "decode_str": "qu"} -{"id": 544, "token": "\u0120[", "merges": "\u0120 [", "raw_count": 30317439, "count": 38402632, "decode_str": " ["} -{"id": 50459, "token": "\u00e4\u00b9\u00b1", "merges": "\u00e4\u00b9 \u00b1", "raw_count": 38407641, "count": 38407641, "decode_str": "\u4e71"} -{"id": 53685, "token": "\u00e8\u013b\u013c", "merges": "\u00e8\u013b \u013c", "raw_count": 38420557, "count": 38420557, "decode_str": "\u865a"} -{"id": 51457, "token": "\u00e5\u00b0\u012c", "merges": "\u00e5\u00b0 \u012c", "raw_count": 38423391, "count": 38423391, "decode_str": "\u5c0a"} -{"id": 54346, "token": "\u00e9\u013c\u0132", "merges": "\u00e9\u013c \u0132", "raw_count": 38438086, "count": 38438086, "decode_str": "\u9690"} -{"id": 45804, "token": "\u00e7\u00a7\u0123", "merges": "\u00e7\u00a7 \u0123", "raw_count": 38599694, "count": 38599694, "decode_str": "\u79c1"} -{"id": 2309, "token": "return", "merges": "ret urn", "raw_count": 38244516, "count": 38639749, "decode_str": "return"} -{"id": 52994, "token": "\u00e7\u013d\u013d", "merges": "\u00e7\u013d \u013d", "raw_count": 38780423, "count": 38780423, "decode_str": "\u76db"} -{"id": 51938, "token": "\u00e6\u012e\u0133", "merges": "\u00e6\u012e \u0133", "raw_count": 38801915, "count": 38801915, "decode_str": "\u6311"} -{"id": 50720, "token": "\u00e5\u0128\u0142", "merges": "\u00e5\u0128 \u0142", "raw_count": 38813880, "count": 38813880, "decode_str": "\u51a0"} -{"id": 51484, "token": "\u00e5\u00b1\u012d", "merges": "\u00e5\u00b1 \u012d", "raw_count": 38846947, "count": 38846947, "decode_str": "\u5c4b"} -{"id": 51722, "token": "\u00e6\u0123\u00a9", "merges": "\u00e6\u0123 \u00a9", "raw_count": 38872968, "count": 38872968, "decode_str": "\u6069"} -{"id": 53919, "token": "\u00e8\u00b4\u00a5", "merges": "\u00e8\u00b4 \u00a5", "raw_count": 38916753, "count": 38916753, "decode_str": "\u8d25"} -{"id": 50637, "token": "\u00e5\u0122\u00ba", "merges": "\u00e5\u0122 \u00ba", "raw_count": 39011092, "count": 39011092, "decode_str": "\u503a"} -{"id": 51534, "token": "\u00e5\u00b8\u013f", "merges": "\u00e5\u00b8 \u013f", "raw_count": 39054587, "count": 39054587, "decode_str": "\u5e1d"} -{"id": 52968, "token": "\u00e7\u013c\u0129", "merges": "\u00e7\u013c \u0129", "raw_count": 39118236, "count": 39118236, "decode_str": "\u7687"} -{"id": 53386, "token": "\u00e7\u00bc\u0135", "merges": "\u00e7\u00bc \u0135", "raw_count": 39228516, "count": 39228516, "decode_str": "\u7f13"} -{"id": 51407, "token": "\u00e5\u00ae\u0139", "merges": "\u00e5\u00ae \u0139", "raw_count": 39339293, "count": 39339293, "decode_str": "\u5b97"} -{"id": 482, "token": "ame", "merges": "am e", "raw_count": 573356, "count": 39344351, "decode_str": "ame"} -{"id": 50511, "token": "\u00e4\u00bb\u00aa", "merges": "\u00e4\u00bb \u00aa", "raw_count": 39345530, "count": 39345530, "decode_str": "\u4eea"} -{"id": 53982, "token": "\u00e8\u00b6\u00a3", "merges": "\u00e8\u00b6 \u00a3", "raw_count": 39371781, "count": 39371781, "decode_str": "\u8da3"} -{"id": 52600, "token": "\u00e6\u00b6\u012b", "merges": "\u00e6\u00b6 \u012b", "raw_count": 39388058, "count": 39388058, "decode_str": "\u6d89"} -{"id": 50819, "token": "\u00e5\u012c\u00b1", "merges": "\u00e5\u012c \u00b1", "raw_count": 39659551, "count": 39659551, "decode_str": "\u52b1"} -{"id": 336, "token": "ce", "merges": "c e", "raw_count": 1533110, "count": 39665791, "decode_str": "ce"} -{"id": 52498, "token": "\u00e6\u00b2\u012b", "merges": "\u00e6\u00b2 \u012b", "raw_count": 39689262, "count": 39689262, "decode_str": "\u6c89"} -{"id": 51673, "token": "\u00e5\u00bf\u013b", "merges": "\u00e5\u00bf \u013b", "raw_count": 39773849, "count": 39773849, "decode_str": "\u5fd9"} -{"id": 52995, "token": "\u00e7\u013d\u0141", "merges": "\u00e7\u013d \u0141", "raw_count": 39797011, "count": 39797011, "decode_str": "\u76df"} -{"id": 186, "token": "\u0109", "merges": "NULL", "raw_count": 23011751, "count": 39879737, "decode_str": "\t"} -{"id": 53577, "token": "\u00e8\u012a\u0134", "merges": "\u00e8\u012a \u0134", "raw_count": 39967956, "count": 39967956, "decode_str": "\u8212"} -{"id": 52564, "token": "\u00e6\u00b4\u00b2", "merges": "\u00e6\u00b4 \u00b2", "raw_count": 39998797, "count": 39998797, "decode_str": "\u6d32"} -{"id": 328, "token": "un", "merges": "u n", "raw_count": 3553664, "count": 40057213, "decode_str": "un"} -{"id": 54512, "token": "\u00e9\u00aa\u00a8", "merges": "\u00e9\u00aa \u00a8", "raw_count": 40244632, "count": 40244632, "decode_str": "\u9aa8"} -{"id": 51177, "token": "\u00e5\u013e\u0128", "merges": "\u00e5\u013e \u0128", "raw_count": 40384768, "count": 40384768, "decode_str": "\u5706"} -{"id": 51178, "token": "\u00e5\u013e\u012a", "merges": "\u00e5\u013e \u012a", "raw_count": 40388609, "count": 40388609, "decode_str": "\u5708"} -{"id": 52876, "token": "\u00e7\u0136\u00b0", "merges": "\u00e7\u0136 \u00b0", "raw_count": 40427295, "count": 40427295, "decode_str": "\u7530"} -{"id": 52017, "token": "\u00e6\u0131\u00a1", "merges": "\u00e6\u0131 \u00a1", "raw_count": 40494563, "count": 40494563, "decode_str": "\u63e1"} -{"id": 50644, "token": "\u00e5\u0123\u0131", "merges": "\u00e5\u0123 \u0131", "raw_count": 40562506, "count": 40562506, "decode_str": "\u504f"} -{"id": 51847, "token": "\u00e6\u012b\u00a9", "merges": "\u00e6\u012b \u00a9", "raw_count": 40568644, "count": 40568644, "decode_str": "\u6269"} -{"id": 52219, "token": "\u00e6\u013f\u0141", "merges": "\u00e6\u013f \u0141", "raw_count": 40638994, "count": 40638994, "decode_str": "\u675f"} -{"id": 53024, "token": "\u00e7\u013f\u00a1", "merges": "\u00e7\u013f \u00a1", "raw_count": 40672600, "count": 40672600, "decode_str": "\u7761"} -{"id": 346, "token": "\u0120\"", "merges": "\u0120 \"", "raw_count": 33418063, "count": 40710328, "decode_str": " \""} -{"id": 51549, "token": "\u00e5\u00b9\u0137", "merges": "\u00e5\u00b9 \u0137", "raw_count": 40729740, "count": 40729740, "decode_str": "\u5e55"} -{"id": 53121, "token": "\u00e7\u00a5\u013f", "merges": "\u00e7\u00a5 \u013f", "raw_count": 40824707, "count": 40824707, "decode_str": "\u795d"} -{"id": 51872, "token": "\u00e6\u012c\u013a", "merges": "\u00e6\u012c \u013a", "raw_count": 40843343, "count": 40843343, "decode_str": "\u6298"} -{"id": 54159, "token": "\u00e9\u0124\u00ae", "merges": "\u00e9\u0124 \u00ae", "raw_count": 40873429, "count": 40873429, "decode_str": "\u90ae"} -{"id": 1221, "token": "ret", "merges": "re t", "raw_count": 1498473, "count": 40904528, "decode_str": "ret"} -{"id": 52221, "token": "\u00e6\u013f\u00a8", "merges": "\u00e6\u013f \u00a8", "raw_count": 41042488, "count": 41042488, "decode_str": "\u6768"} -{"id": 313, "token": "\u0120(", "merges": "\u0120 (", "raw_count": 38217961, "count": 41061695, "decode_str": " ("} -{"id": 366, "token": "ate", "merges": "at e", "raw_count": 2743566, "count": 41087131, "decode_str": "ate"} -{"id": 51822, "token": "\u00e6\u012a\u00aa", "merges": "\u00e6\u012a \u00aa", "raw_count": 41091864, "count": 41091864, "decode_str": "\u622a"} -{"id": 1449, "token": "40", "merges": "4 0", "raw_count": 35175541, "count": 41179195, "decode_str": "40"} -{"id": 52470, "token": "\u00e6\u00b1\u0129", "merges": "\u00e6\u00b1 \u0129", "raw_count": 41261722, "count": 41261722, "decode_str": "\u6c47"} -{"id": 51427, "token": "\u00e5\u00ae\u00bd", "merges": "\u00e5\u00ae \u00bd", "raw_count": 41456791, "count": 41456791, "decode_str": "\u5bbd"} -{"id": 56, "token": "W", "merges": "NULL", "raw_count": 14816012, "count": 41492418, "decode_str": "W"} -{"id": 365, "token": "pe", "merges": "p e", "raw_count": 1649851, "count": 41505290, "decode_str": "pe"} -{"id": 51988, "token": "\u00e6\u0130\u012e", "merges": "\u00e6\u0130 \u012e", "raw_count": 41624271, "count": 41624271, "decode_str": "\u638c"} -{"id": 51487, "token": "\u00e5\u00b1\u0131", "merges": "\u00e5\u00b1 \u0131", "raw_count": 41647467, "count": 41647467, "decode_str": "\u5c4f"} -{"id": 51357, "token": "\u00e5\u00a7\u0132", "merges": "\u00e5\u00a7 \u0132", "raw_count": 41651267, "count": 41651267, "decode_str": "\u59d0"} -{"id": 348, "token": "ch", "merges": "c h", "raw_count": 3807743, "count": 41675296, "decode_str": "ch"} -{"id": 54377, "token": "\u00e9\u013d\u00b7", "merges": "\u00e9\u013d \u00b7", "raw_count": 41690683, "count": 41690683, "decode_str": "\u96f7"} -{"id": 53912, "token": "\u00e8\u00b4\u013f", "merges": "\u00e8\u00b4 \u013f", "raw_count": 41749293, "count": 41749293, "decode_str": "\u8d1d"} -{"id": 1423, "token": "22", "merges": "2 2", "raw_count": 37271935, "count": 41810866, "decode_str": "22"} -{"id": 6434, "token": "url", "merges": "ur l", "raw_count": 41820222, "count": 41820222, "decode_str": "url"} -{"id": 54213, "token": "\u00e9\u0129\u012c", "merges": "\u00e9\u0129 \u012c", "raw_count": 41823394, "count": 41823394, "decode_str": "\u91ca"} -{"id": 52551, "token": "\u00e6\u00b4\u0123", "merges": "\u00e6\u00b4 \u0123", "raw_count": 42047663, "count": 42047663, "decode_str": "\u6d01"} -{"id": 53999, "token": "\u00e8\u00b7\u013f", "merges": "\u00e8\u00b7 \u013f", "raw_count": 42048190, "count": 42048190, "decode_str": "\u8ddd"} -{"id": 7132, "token": "2017", "merges": "201 7", "raw_count": 42152001, "count": 42152001, "decode_str": "2017"} -{"id": 49868, "token": "\u00e6\u0139\u00a5\u00e6\u013e\u00ac", "merges": "\u00e6\u0139\u00a5 \u00e6\u013e\u00ac", "raw_count": 42170930, "count": 42170930, "decode_str": "\u65e5\u672c"} -{"id": 52758, "token": "\u00e7\u012a\u0128", "merges": "\u00e7\u012a \u0128", "raw_count": 42244990, "count": 42244990, "decode_str": "\u7206"} -{"id": 51483, "token": "\u00e5\u00b1\u012c", "merges": "\u00e5\u00b1 \u012c", "raw_count": 42299793, "count": 42299793, "decode_str": "\u5c4a"} -{"id": 53768, "token": "\u00e8\u00a7\u00a6", "merges": "\u00e8\u00a7 \u00a6", "raw_count": 42418649, "count": 42418649, "decode_str": "\u89e6"} -{"id": 383, "token": "est", "merges": "es t", "raw_count": 2816850, "count": 42450144, "decode_str": "est"} -{"id": 44, "token": "K", "merges": "NULL", "raw_count": 19335226, "count": 42517027, "decode_str": "K"} -{"id": 51431, "token": "\u00e5\u00af\u0126", "merges": "\u00e5\u00af \u0126", "raw_count": 42533626, "count": 42533626, "decode_str": "\u5bc4"} -{"id": 51324, "token": "\u00e5\u00a5\u00a5", "merges": "\u00e5\u00a5 \u00a5", "raw_count": 42563664, "count": 42563664, "decode_str": "\u5965"} -{"id": 52802, "token": "\u00e7\u0130\u012b", "merges": "\u00e7\u0130 \u012b", "raw_count": 42632326, "count": 42632326, "decode_str": "\u7389"} -{"id": 54623, "token": "\u00ef\u00bd\u0141", "merges": "\u00ef\u00bd \u0141", "raw_count": 42643974, "count": 42643974, "decode_str": " "} -{"id": 53216, "token": "\u00e7\u00ac\u00a6", "merges": "\u00e7\u00ac \u00a6", "raw_count": 42877720, "count": 42877720, "decode_str": "\u7b26"} -{"id": 356, "token": "ag", "merges": "a g", "raw_count": 2307205, "count": 42879071, "decode_str": "ag"} -{"id": 54039, "token": "\u00e8\u00be\u0128", "merges": "\u00e8\u00be \u0128", "raw_count": 42933334, "count": 42933334, "decode_str": "\u8f86"} -{"id": 1881, "token": "\u0120self", "merges": "\u0120s elf", "raw_count": 43032599, "count": 43038328, "decode_str": " self"} -{"id": 51037, "token": "\u00e5\u0134\u00a8", "merges": "\u00e5\u0134 \u00a8", "raw_count": 43229569, "count": 43229569, "decode_str": "\u54a8"} -{"id": 304, "token": "ig", "merges": "i g", "raw_count": 1672170, "count": 43239929, "decode_str": "ig"} -{"id": 50988, "token": "\u00e5\u0133\u0122", "merges": "\u00e5\u0133 \u0122", "raw_count": 43315997, "count": 43315997, "decode_str": "\u5440"} -{"id": 52181, "token": "\u00e6\u013d\u00b2", "merges": "\u00e6\u013d \u00b2", "raw_count": 43411898, "count": 43411898, "decode_str": "\u66f2"} -{"id": 53497, "token": "\u00e8\u0124\u00af", "merges": "\u00e8\u0124 \u00af", "raw_count": 43533640, "count": 43533640, "decode_str": "\u80af"} -{"id": 316, "token": "us", "merges": "u s", "raw_count": 2683861, "count": 43555569, "decode_str": "us"} -{"id": 52928, "token": "\u00e7\u0139\u0129", "merges": "\u00e7\u0139 \u0129", "raw_count": 43765272, "count": 43765272, "decode_str": "\u75c7"} -{"id": 52657, "token": "\u00e6\u00b8\u0132", "merges": "\u00e6\u00b8 \u0132", "raw_count": 43778355, "count": 43778355, "decode_str": "\u6e10"} -{"id": 50907, "token": "\u00e5\u0130\u013c", "merges": "\u00e5\u0130 \u013c", "raw_count": 43846904, "count": 43846904, "decode_str": "\u539a"} -{"id": 53297, "token": "\u00e7\u00b4\u00af", "merges": "\u00e7\u00b4 \u00af", "raw_count": 43849575, "count": 43849575, "decode_str": "\u7d2f"} -{"id": 51618, "token": "\u00e5\u00bd\u0134", "merges": "\u00e5\u00bd \u0134", "raw_count": 43873076, "count": 43873076, "decode_str": "\u5f52"} -{"id": 53815, "token": "\u00e8\u00af\u012f", "merges": "\u00e8\u00af \u012f", "raw_count": 43886861, "count": 43886861, "decode_str": "\u8bcd"} -{"id": 50540, "token": "\u00e4\u00bc\u00b0", "merges": "\u00e4\u00bc \u00b0", "raw_count": 43945495, "count": 43945495, "decode_str": "\u4f30"} -{"id": 1549, "token": "60", "merges": "6 0", "raw_count": 31093692, "count": 44173887, "decode_str": "60"} -{"id": 54208, "token": "\u00e9\u0127\u00b8", "merges": "\u00e9\u0127 \u00b8", "raw_count": 44179343, "count": 44179343, "decode_str": "\u9178"} -{"id": 52000, "token": "\u00e6\u0130\u00aa", "merges": "\u00e6\u0130 \u00aa", "raw_count": 44241519, "count": 44241519, "decode_str": "\u63aa"} -{"id": 52481, "token": "\u00e6\u00b1\u00a1", "merges": "\u00e6\u00b1 \u00a1", "raw_count": 44323287, "count": 44323287, "decode_str": "\u6c61"} -{"id": 53166, "token": "\u00e7\u00a8\u012f", "merges": "\u00e7\u00a8 \u012f", "raw_count": 44385691, "count": 44385691, "decode_str": "\u7a0d"} -{"id": 50541, "token": "\u00e4\u00bc\u00b4", "merges": "\u00e4\u00bc \u00b4", "raw_count": 44393944, "count": 44393944, "decode_str": "\u4f34"} -{"id": 54372, "token": "\u00e9\u013d\u00aa", "merges": "\u00e9\u013d \u00aa", "raw_count": 44403325, "count": 44403325, "decode_str": "\u96ea"} -{"id": 50569, "token": "\u00e4\u00bd\u00b3", "merges": "\u00e4\u00bd \u00b3", "raw_count": 44608715, "count": 44608715, "decode_str": "\u4f73"} -{"id": 53839, "token": "\u00e8\u00af\u00af", "merges": "\u00e8\u00af \u00af", "raw_count": 44676613, "count": 44676613, "decode_str": "\u8bef"} -{"id": 51613, "token": "\u00e5\u00bc\u00b9", "merges": "\u00e5\u00bc \u00b9", "raw_count": 44688319, "count": 44688319, "decode_str": "\u5f39"} -{"id": 50525, "token": "\u00e4\u00bc\u0133", "merges": "\u00e4\u00bc \u0133", "raw_count": 44837107, "count": 44837107, "decode_str": "\u4f11"} -{"id": 1166, "token": "17", "merges": "1 7", "raw_count": 34716304, "count": 44887160, "decode_str": "17"} -{"id": 53456, "token": "\u00e8\u0122\u00b3", "merges": "\u00e8\u0122 \u00b3", "raw_count": 44960193, "count": 44960193, "decode_str": "\u8033"} -{"id": 54424, "token": "\u00e9\u00a1\u00b5", "merges": "\u00e9\u00a1 \u00b5", "raw_count": 44999114, "count": 44999114, "decode_str": "\u9875"} -{"id": 1348, "token": "24", "merges": "2 4", "raw_count": 37283994, "count": 45002016, "decode_str": "24"} -{"id": 52091, "token": "\u00e6\u0138\u0139", "merges": "\u00e6\u0138 \u0139", "raw_count": 45099199, "count": 45099199, "decode_str": "\u6597"} -{"id": 50816, "token": "\u00e5\u012c\u00aa", "merges": "\u00e5\u012c \u00aa", "raw_count": 45102345, "count": 45102345, "decode_str": "\u52aa"} -{"id": 50891, "token": "\u00e5\u012f\u00b1", "merges": "\u00e5\u012f \u00b1", "raw_count": 45204252, "count": 45204252, "decode_str": "\u5371"} -{"id": 52114, "token": "\u00e6\u0139\u00a2", "merges": "\u00e6\u0139 \u00a2", "raw_count": 45297934, "count": 45297934, "decode_str": "\u65e2"} -{"id": 51537, "token": "\u00e5\u00b8\u0143", "merges": "\u00e5\u00b8 \u0143", "raw_count": 45434028, "count": 45434028, "decode_str": "\u5e2d"} -{"id": 662, "token": "urn", "merges": "ur n", "raw_count": 158561, "count": 45462394, "decode_str": "urn"} -{"id": 53786, "token": "\u00e8\u00ae\u00a8", "merges": "\u00e8\u00ae \u00a8", "raw_count": 45463720, "count": 45463720, "decode_str": "\u8ba8"} -{"id": 52615, "token": "\u00e6\u00b6\u00a6", "merges": "\u00e6\u00b6 \u00a6", "raw_count": 45620429, "count": 45620429, "decode_str": "\u6da6"} -{"id": 20422, "token": "\u00ef\u00bd", "merges": "\u00ef \u00bd", "raw_count": 6569, "count": 45630028, "decode_str": "\ufffd"} -{"id": 50900, "token": "\u00e5\u0130\u0127", "merges": "\u00e5\u0130 \u0127", "raw_count": 45646370, "count": 45646370, "decode_str": "\u5385"} -{"id": 51508, "token": "\u00e5\u00b7\u00a8", "merges": "\u00e5\u00b7 \u00a8", "raw_count": 45658493, "count": 45658493, "decode_str": "\u5de8"} -{"id": 51455, "token": "\u00e5\u00b0\u0126", "merges": "\u00e5\u00b0 \u0126", "raw_count": 45713472, "count": 45713472, "decode_str": "\u5c04"} -{"id": 52206, "token": "\u00e6\u013f\u0124", "merges": "\u00e6\u013f \u0124", "raw_count": 45800074, "count": 45800074, "decode_str": "\u6742"} -{"id": 54318, "token": "\u00e9\u013b\u0126", "merges": "\u00e9\u013b \u0126", "raw_count": 45868210, "count": 45868210, "decode_str": "\u9644"} -{"id": 53153, "token": "\u00e7\u00a7\u0141", "merges": "\u00e7\u00a7 \u0141", "raw_count": 45920556, "count": 45920556, "decode_str": "\u79df"} -{"id": 285, "token": "\u0120and", "merges": "\u0120an d", "raw_count": 45911239, "count": 45935589, "decode_str": " and"} -{"id": 318, "token": "ation", "merges": "at ion", "raw_count": 1901338, "count": 45950288, "decode_str": "ation"} -{"id": 51561, "token": "\u00e5\u00ba\u0128", "merges": "\u00e5\u00ba \u0128", "raw_count": 46060995, "count": 46060995, "decode_str": "\u5e86"} -{"id": 52116, "token": "\u00e6\u0139\u00a7", "merges": "\u00e6\u0139 \u00a7", "raw_count": 46068070, "count": 46068070, "decode_str": "\u65e7"} -{"id": 298, "token": "\u0120l", "merges": "\u0120 l", "raw_count": 3427783, "count": 46080768, "decode_str": " l"} -{"id": 51986, "token": "\u00e6\u0130\u012a", "merges": "\u00e6\u0130 \u012a", "raw_count": 46159356, "count": 46159356, "decode_str": "\u6388"} -{"id": 5294, "token": "%,", "merges": "% ,", "raw_count": 46283860, "count": 46283860, "decode_str": "%,"} -{"id": 51868, "token": "\u00e6\u012c\u0135", "merges": "\u00e6\u012c \u0135", "raw_count": 46296014, "count": 46296014, "decode_str": "\u6293"} -{"id": 53198, "token": "\u00e7\u00ab\u00a5", "merges": "\u00e7\u00ab \u00a5", "raw_count": 46316538, "count": 46316538, "decode_str": "\u7ae5"} -{"id": 51462, "token": "\u00e5\u00b0\u013c", "merges": "\u00e5\u00b0 \u013c", "raw_count": 46352004, "count": 46352004, "decode_str": "\u5c1a"} -{"id": 53925, "token": "\u00e8\u00b4\u00ab", "merges": "\u00e8\u00b4 \u00ab", "raw_count": 46370882, "count": 46370882, "decode_str": "\u8d2b"} -{"id": 51122, "token": "\u00e5\u0138\u013f", "merges": "\u00e5\u0138 \u013f", "raw_count": 46389340, "count": 46389340, "decode_str": "\u559d"} -{"id": 283, "token": "--", "merges": "- -", "raw_count": 10852295, "count": 46457289, "decode_str": "--"} -{"id": 53080, "token": "\u00e7\u00a1\u00ac", "merges": "\u00e7\u00a1 \u00ac", "raw_count": 46546939, "count": 46546939, "decode_str": "\u786c"} -{"id": 54376, "token": "\u00e9\u013d\u00b6", "merges": "\u00e9\u013d \u00b6", "raw_count": 46621618, "count": 46621618, "decode_str": "\u96f6"} -{"id": 53792, "token": "\u00e8\u00ae\u00af", "merges": "\u00e8\u00ae \u00af", "raw_count": 46628373, "count": 46628373, "decode_str": "\u8baf"} -{"id": 54079, "token": "\u00e8\u00bf\u013f", "merges": "\u00e8\u00bf \u013f", "raw_count": 47167253, "count": 47167253, "decode_str": "\u8fdd"} -{"id": 51244, "token": "\u00e5\u0142\u0124", "merges": "\u00e5\u0142 \u0124", "raw_count": 47203103, "count": 47203103, "decode_str": "\u5802"} -{"id": 51761, "token": "\u00e6\u0125\u012c", "merges": "\u00e6\u0125 \u012c", "raw_count": 47212877, "count": 47212877, "decode_str": "\u60ca"} -{"id": 51995, "token": "\u00e6\u0130\u00a2", "merges": "\u00e6\u0130 \u00a2", "raw_count": 47241213, "count": 47241213, "decode_str": "\u63a2"} -{"id": 51069, "token": "\u00e5\u0135\u00a5", "merges": "\u00e5\u0135 \u00a5", "raw_count": 47280611, "count": 47280611, "decode_str": "\u54e5"} -{"id": 52337, "token": "\u00e6\u00a5\u013c", "merges": "\u00e6\u00a5 \u013c", "raw_count": 47300826, "count": 47300826, "decode_str": "\u695a"} -{"id": 50727, "token": "\u00e5\u0128\u00b0", "merges": "\u00e5\u0128 \u00b0", "raw_count": 47318416, "count": 47318416, "decode_str": "\u51b0"} -{"id": 52480, "token": "\u00e6\u00b1\u0142", "merges": "\u00e6\u00b1 \u0142", "raw_count": 47407730, "count": 47407730, "decode_str": "\u6c60"} -{"id": 52775, "token": "\u00e7\u012b\u013b", "merges": "\u00e7\u012b \u013b", "raw_count": 47453687, "count": 47453687, "decode_str": "\u7259"} -{"id": 2313, "token": "100", "merges": "1 00", "raw_count": 46629829, "count": 47508550, "decode_str": "100"} -{"id": 51563, "token": "\u00e5\u00ba\u012c", "merges": "\u00e5\u00ba \u012c", "raw_count": 47604351, "count": 47604351, "decode_str": "\u5e8a"} -{"id": 377, "token": "pp", "merges": "p p", "raw_count": 2249030, "count": 47854568, "decode_str": "pp"} -{"id": 51472, "token": "\u00e5\u00b0\u00bc", "merges": "\u00e5\u00b0 \u00bc", "raw_count": 47862146, "count": 47862146, "decode_str": "\u5c3c"} -{"id": 54425, "token": "\u00e9\u00a1\u00b6", "merges": "\u00e9\u00a1 \u00b6", "raw_count": 48022762, "count": 48022762, "decode_str": "\u9876"} -{"id": 50931, "token": "\u00e5\u0131\u00a5", "merges": "\u00e5\u0131 \u00a5", "raw_count": 48029881, "count": 48029881, "decode_str": "\u53e5"} -{"id": 51546, "token": "\u00e5\u00b9\u0127", "merges": "\u00e5\u00b9 \u0127", "raw_count": 48111397, "count": 48111397, "decode_str": "\u5e45"} -{"id": 50557, "token": "\u00e4\u00bd\u013d", "merges": "\u00e4\u00bd \u013d", "raw_count": 48135385, "count": 48135385, "decode_str": "\u4f5b"} -{"id": 54454, "token": "\u00e9\u00a2\u013e", "merges": "\u00e9\u00a2 \u013e", "raw_count": 48231769, "count": 48231769, "decode_str": "\u989c"} -{"id": 53448, "token": "\u00e8\u0122\u0132", "merges": "\u00e8\u0122 \u0132", "raw_count": 48286046, "count": 48286046, "decode_str": "\u8010"} -{"id": 53995, "token": "\u00e8\u00b7\u0133", "merges": "\u00e8\u00b7 \u0133", "raw_count": 48372702, "count": 48372702, "decode_str": "\u8dd1"} -{"id": 53327, "token": "\u00e7\u00ba\u00b8", "merges": "\u00e7\u00ba \u00b8", "raw_count": 48546505, "count": 48546505, "decode_str": "\u7eb8"} -{"id": 281, "token": "\u0120to", "merges": "\u0120t o", "raw_count": 43285724, "count": 48699476, "decode_str": " to"} -{"id": 53804, "token": "\u00e8\u00ae\u00bf", "merges": "\u00e8\u00ae \u00bf", "raw_count": 48705345, "count": 48705345, "decode_str": "\u8bbf"} -{"id": 50778, "token": "\u00e5\u012a\u00a4", "merges": "\u00e5\u012a \u00a4", "raw_count": 48849676, "count": 48849676, "decode_str": "\u5224"} -{"id": 7798, "token": "2018", "merges": "201 8", "raw_count": 48885133, "count": 48885133, "decode_str": "2018"} -{"id": 50462, "token": "\u00e4\u00ba\u012a", "merges": "\u00e4\u00ba \u012a", "raw_count": 48891141, "count": 48891141, "decode_str": "\u4e88"} -{"id": 53701, "token": "\u00e8\u00a1\u0139", "merges": "\u00e8\u00a1 \u0139", "raw_count": 48923379, "count": 48923379, "decode_str": "\u8857"} -{"id": 311, "token": "ol", "merges": "o l", "raw_count": 2211911, "count": 49087044, "decode_str": "ol"} -{"id": 53026, "token": "\u00e7\u013f\u00a3", "merges": "\u00e7\u013f \u00a3", "raw_count": 49364935, "count": 49364935, "decode_str": "\u7763"} -{"id": 52622, "token": "\u00e6\u00b6\u00b2", "merges": "\u00e6\u00b6 \u00b2", "raw_count": 49495191, "count": 49495191, "decode_str": "\u6db2"} -{"id": 50702, "token": "\u00e5\u0127\u00b8", "merges": "\u00e5\u0127 \u00b8", "raw_count": 49567988, "count": 49567988, "decode_str": "\u5178"} -{"id": 1047, "token": "14", "merges": "1 4", "raw_count": 37990172, "count": 49688903, "decode_str": "14"} -{"id": 52464, "token": "\u00e6\u00b0\u00b8", "merges": "\u00e6\u00b0 \u00b8", "raw_count": 49734425, "count": 49734425, "decode_str": "\u6c38"} -{"id": 50700, "token": "\u00e5\u0127\u00b5", "merges": "\u00e5\u0127 \u00b5", "raw_count": 49789307, "count": 49789307, "decode_str": "\u5175"} -{"id": 51299, "token": "\u00e5\u00a4\u00ae", "merges": "\u00e5\u00a4 \u00ae", "raw_count": 49853110, "count": 49853110, "decode_str": "\u592e"} -{"id": 317, "token": "ac", "merges": "a c", "raw_count": 2452128, "count": 50018082, "decode_str": "ac"} -{"id": 54105, "token": "\u00e9\u0122\u0132", "merges": "\u00e9\u0122 \u0132", "raw_count": 50040080, "count": 50040080, "decode_str": "\u9010"} -{"id": 53683, "token": "\u00e8\u013b\u0133", "merges": "\u00e8\u013b \u0133", "raw_count": 50078938, "count": 50078938, "decode_str": "\u8651"} -{"id": 51950, "token": "\u00e6\u012e\u00a5", "merges": "\u00e6\u012e \u00a5", "raw_count": 50145785, "count": 50145785, "decode_str": "\u6325"} -{"id": 9223, "token": "\u0124\u00ac", "merges": "\u0124 \u00ac", "raw_count": 26613, "count": 50200691, "decode_str": "\ufffd\ufffd"} -{"id": 54143, "token": "\u00e9\u0123\u00bf", "merges": "\u00e9\u0123 \u00bf", "raw_count": 50324221, "count": 50324221, "decode_str": "\u907f"} -{"id": 54477, "token": "\u00e9\u00a6\u0128", "merges": "\u00e9\u00a6 \u0128", "raw_count": 50344794, "count": 50344794, "decode_str": "\u9986"} -{"id": 53225, "token": "\u00e7\u0143\u0133", "merges": "\u00e7\u0143 \u0133", "raw_count": 50480343, "count": 50480343, "decode_str": "\u7b51"} -{"id": 54, "token": "U", "merges": "NULL", "raw_count": 10782179, "count": 50599354, "decode_str": "U"} -{"id": 1082, "token": "()", "merges": "( )", "raw_count": 38036933, "count": 50727400, "decode_str": "()"} -{"id": 51553, "token": "\u00e5\u00b9\u00b8", "merges": "\u00e5\u00b9 \u00b8", "raw_count": 50829178, "count": 50829178, "decode_str": "\u5e78"} -{"id": 51686, "token": "\u00e6\u0122\u0122", "merges": "\u00e6\u0122 \u0122", "raw_count": 50868897, "count": 50868897, "decode_str": "\u6000"} -{"id": 54320, "token": "\u00e9\u013b\u0128", "merges": "\u00e9\u013b \u0128", "raw_count": 50948772, "count": 50948772, "decode_str": "\u9646"} -{"id": 52617, "token": "\u00e6\u00b6\u00a8", "merges": "\u00e6\u00b6 \u00a8", "raw_count": 50998792, "count": 50998792, "decode_str": "\u6da8"} -{"id": 52072, "token": "\u00e6\u0137\u0133", "merges": "\u00e6\u0137 \u0133", "raw_count": 51115381, "count": 51115381, "decode_str": "\u6551"} -{"id": 51411, "token": "\u00e5\u00ae\u013e", "merges": "\u00e5\u00ae \u013e", "raw_count": 51129736, "count": 51129736, "decode_str": "\u5b9c"} -{"id": 351, "token": "od", "merges": "o d", "raw_count": 1385889, "count": 51185368, "decode_str": "od"} -{"id": 51842, "token": "\u00e6\u012b\u013a", "merges": "\u00e6\u012b \u013a", "raw_count": 51201220, "count": 51201220, "decode_str": "\u6258"} -{"id": 91, "token": "z", "merges": "NULL", "raw_count": 8613519, "count": 51291782, "decode_str": "z"} -{"id": 54074, "token": "\u00e8\u00bf\u0130", "merges": "\u00e8\u00bf \u0130", "raw_count": 51403676, "count": 51403676, "decode_str": "\u8fce"} -{"id": 51196, "token": "\u00e5\u013f\u0131", "merges": "\u00e5\u013f \u0131", "raw_count": 51503974, "count": 51503974, "decode_str": "\u574f"} -{"id": 52937, "token": "\u00e7\u0139\u013d", "merges": "\u00e7\u0139 \u013d", "raw_count": 51722206, "count": 51722206, "decode_str": "\u75db"} -{"id": 53920, "token": "\u00e8\u00b4\u00a6", "merges": "\u00e8\u00b4 \u00a6", "raw_count": 51771294, "count": 51771294, "decode_str": "\u8d26"} -{"id": 51520, "token": "\u00e5\u00b8\u0123", "merges": "\u00e5\u00b8 \u0123", "raw_count": 51865128, "count": 51865128, "decode_str": "\u5e01"} -{"id": 53145, "token": "\u00e7\u00a7\u0122", "merges": "\u00e7\u00a7 \u0122", "raw_count": 51906210, "count": 51906210, "decode_str": "\u79c0"} -{"id": 50432, "token": "\u00e4\u00b8\u00bd", "merges": "\u00e4\u00b8 \u00bd", "raw_count": 52156861, "count": 52156861, "decode_str": "\u4e3d"} -{"id": 1099, "token": "25", "merges": "2 5", "raw_count": 37440563, "count": 52166610, "decode_str": "25"} -{"id": 51917, "token": "\u00e6\u012d\u00a5", "merges": "\u00e6\u012d \u00a5", "raw_count": 52195689, "count": 52195689, "decode_str": "\u62e5"} -{"id": 51326, "token": "\u00e5\u00a5\u00b6", "merges": "\u00e5\u00a5 \u00b6", "raw_count": 52197014, "count": 52197014, "decode_str": "\u5976"} -{"id": 53471, "token": "\u00e8\u0123\u013c", "merges": "\u00e8\u0123 \u013c", "raw_count": 52208279, "count": 52208279, "decode_str": "\u805a"} -{"id": 51402, "token": "\u00e5\u00ae\u012a", "merges": "\u00e5\u00ae \u012a", "raw_count": 52246694, "count": 52246694, "decode_str": "\u5b88"} -{"id": 374, "token": "\u01202", "merges": "\u0120 2", "raw_count": 23620742, "count": 52259668, "decode_str": " 2"} -{"id": 52079, "token": "\u00e6\u0137\u00a3", "merges": "\u00e6\u0137 \u00a3", "raw_count": 52338223, "count": 52338223, "decode_str": "\u6563"} -{"id": 302, "token": "ot", "merges": "o t", "raw_count": 1860354, "count": 52442878, "decode_str": "ot"} -{"id": 53516, "token": "\u00e8\u0125\u013e", "merges": "\u00e8\u0125 \u013e", "raw_count": 52501040, "count": 52501040, "decode_str": "\u80dc"} -{"id": 51289, "token": "\u00e5\u00a4\u0131", "merges": "\u00e5\u00a4 \u0131", "raw_count": 52646327, "count": 52646327, "decode_str": "\u590f"} -{"id": 53549, "token": "\u00e8\u0126\u00b1", "merges": "\u00e8\u0126 \u00b1", "raw_count": 52668665, "count": 52668665, "decode_str": "\u8131"} -{"id": 54313, "token": "\u00e9\u013a\u00b6", "merges": "\u00e9\u013a \u00b6", "raw_count": 52773860, "count": 52773860, "decode_str": "\u9636"} -{"id": 52258, "token": "\u00e6\u0141\u0135", "merges": "\u00e6\u0141 \u0135", "raw_count": 52819687, "count": 52819687, "decode_str": "\u67d3"} -{"id": 52503, "token": "\u00e6\u00b2\u013b", "merges": "\u00e6\u00b2 \u013b", "raw_count": 52826674, "count": 52826674, "decode_str": "\u6c99"} -{"id": 51871, "token": "\u00e6\u012c\u0139", "merges": "\u00e6\u012c \u0139", "raw_count": 52909867, "count": 52909867, "decode_str": "\u6297"} -{"id": 53545, "token": "\u00e8\u0126\u013c", "merges": "\u00e8\u0126 \u013c", "raw_count": 52994788, "count": 52994788, "decode_str": "\u811a"} -{"id": 307, "token": "ut", "merges": "u t", "raw_count": 1313233, "count": 53002197, "decode_str": "ut"} -{"id": 52440, "token": "\u00e6\u00af\u013d", "merges": "\u00e6\u00af \u013d", "raw_count": 53015623, "count": 53015623, "decode_str": "\u6bdb"} -{"id": 52394, "token": "\u00e6\u0143\u012e", "merges": "\u00e6\u0143 \u012e", "raw_count": 53241476, "count": 53241476, "decode_str": "\u6b4c"} -{"id": 54397, "token": "\u00e9\u013e\u00b2", "merges": "\u00e9\u013e \u00b2", "raw_count": 53291288, "count": 53291288, "decode_str": "\u9732"} -{"id": 41, "token": "H", "merges": "NULL", "raw_count": 15817836, "count": 53329895, "decode_str": "H"} -{"id": 537, "token": "..", "merges": ". .", "raw_count": 12595029, "count": 53376350, "decode_str": ".."} -{"id": 52065, "token": "\u00e6\u0136\u00bb", "merges": "\u00e6\u0136 \u00bb", "raw_count": 53399237, "count": 53399237, "decode_str": "\u653b"} -{"id": 8465, "token": "\u00e2\u0122\u0136\u00e2\u0122\u0136", "merges": "\u00e2\u0122\u0136 \u00e2\u0122\u0136", "raw_count": 52077116, "count": 53422244, "decode_str": "\u2014\u2014"} -{"id": 53374, "token": "\u00e7\u00bb\u00bc", "merges": "\u00e7\u00bb \u00bc", "raw_count": 53479954, "count": 53479954, "decode_str": "\u7efc"} -{"id": 54371, "token": "\u00e9\u013d\u00a8", "merges": "\u00e9\u013d \u00a8", "raw_count": 53845812, "count": 53845812, "decode_str": "\u96e8"} -{"id": 294, "token": "\u0120re", "merges": "\u0120 re", "raw_count": 1771515, "count": 53945398, "decode_str": " re"} -{"id": 50621, "token": "\u00e5\u0122\u0134", "merges": "\u00e5\u0122 \u0134", "raw_count": 54216395, "count": 54216395, "decode_str": "\u5012"} -{"id": 52776, "token": "\u00e7\u012b\u013d", "merges": "\u00e7\u012b \u013d", "raw_count": 54316713, "count": 54316713, "decode_str": "\u725b"} -{"id": 53492, "token": "\u00e8\u0124\u00a4", "merges": "\u00e8\u0124 \u00a4", "raw_count": 54391048, "count": 54391048, "decode_str": "\u80a4"} -{"id": 75, "token": "j", "merges": "NULL", "raw_count": 8424488, "count": 54465651, "decode_str": "j"} -{"id": 1012, "token": "13", "merges": "1 3", "raw_count": 41085742, "count": 54471478, "decode_str": "13"} -{"id": 52250, "token": "\u00e6\u0140\u00b6", "merges": "\u00e6\u0140 \u00b6", "raw_count": 54600749, "count": 54600749, "decode_str": "\u67b6"} -{"id": 51399, "token": "\u00e5\u00ae\u0123", "merges": "\u00e5\u00ae \u0123", "raw_count": 54693545, "count": 54693545, "decode_str": "\u5b81"} -{"id": 52713, "token": "\u00e7\u0123\u00af", "merges": "\u00e7\u0123 \u00af", "raw_count": 54951728, "count": 54951728, "decode_str": "\u706f"} -{"id": 53360, "token": "\u00e7\u00bb\u00a9", "merges": "\u00e7\u00bb \u00a9", "raw_count": 55121160, "count": 55121160, "decode_str": "\u7ee9"} -{"id": 53933, "token": "\u00e8\u00b4\u00b4", "merges": "\u00e8\u00b4 \u00b4", "raw_count": 55197204, "count": 55197204, "decode_str": "\u8d34"} -{"id": 360, "token": "um", "merges": "u m", "raw_count": 1749601, "count": 55413120, "decode_str": "um"} -{"id": 53195, "token": "\u00e7\u00ab\u0141", "merges": "\u00e7\u00ab \u0141", "raw_count": 55441017, "count": 55441017, "decode_str": "\u7adf"} -{"id": 53935, "token": "\u00e8\u00b4\u00b7", "merges": "\u00e8\u00b4 \u00b7", "raw_count": 55448873, "count": 55448873, "decode_str": "\u8d37"} -{"id": 52471, "token": "\u00e6\u00b1\u012b", "merges": "\u00e6\u00b1 \u012b", "raw_count": 55452385, "count": 55452385, "decode_str": "\u6c49"} -{"id": 50821, "token": "\u00e5\u012c\u00b3", "merges": "\u00e5\u012c \u00b3", "raw_count": 55509213, "count": 55509213, "decode_str": "\u52b3"} -{"id": 53340, "token": "\u00e7\u00bb\u012f", "merges": "\u00e7\u00bb \u012f", "raw_count": 55571786, "count": 55571786, "decode_str": "\u7ecd"} -{"id": 51695, "token": "\u00e6\u0122\u0137", "merges": "\u00e6\u0122 \u0137", "raw_count": 55593471, "count": 55593471, "decode_str": "\u6015"} -{"id": 52205, "token": "\u00e6\u013f\u0122", "merges": "\u00e6\u013f \u0122", "raw_count": 55632533, "count": 55632533, "decode_str": "\u6740"} -{"id": 52193, "token": "\u00e6\u013e\u013f", "merges": "\u00e6\u013e \u013f", "raw_count": 55657287, "count": 55657287, "decode_str": "\u671d"} -{"id": 50773, "token": "\u00e5\u012a\u013a", "merges": "\u00e5\u012a \u013a", "raw_count": 55741030, "count": 55741030, "decode_str": "\u5218"} -{"id": 52283, "token": "\u00e6\u0142\u0133", "merges": "\u00e6\u0142 \u0133", "raw_count": 55765660, "count": 55765660, "decode_str": "\u6811"} -{"id": 51453, "token": "\u00e5\u00b0\u0123", "merges": "\u00e5\u00b0 \u0123", "raw_count": 55817612, "count": 55817612, "decode_str": "\u5c01"} -{"id": 51987, "token": "\u00e6\u0130\u012b", "merges": "\u00e6\u0130 \u012b", "raw_count": 55982370, "count": 55982370, "decode_str": "\u6389"} -{"id": 52991, "token": "\u00e7\u013d\u0138", "merges": "\u00e7\u013d \u0138", "raw_count": 55992506, "count": 55992506, "decode_str": "\u76d6"} -{"id": 53852, "token": "\u00e8\u00b0\u0123", "merges": "\u00e8\u00b0 \u0123", "raw_count": 56182881, "count": 56182881, "decode_str": "\u8c01"} -{"id": 50944, "token": "\u00e5\u0131\u00b6", "merges": "\u00e5\u0131 \u00b6", "raw_count": 56211219, "count": 56211219, "decode_str": "\u53f6"} -{"id": 50978, "token": "\u00e5\u0132\u00af", "merges": "\u00e5\u0132 \u00af", "raw_count": 56372138, "count": 56372138, "decode_str": "\u542f"} -{"id": 324, "token": "ad", "merges": "a d", "raw_count": 3500688, "count": 56402106, "decode_str": "ad"} -{"id": 52434, "token": "\u00e6\u00af\u0134", "merges": "\u00e6\u00af \u0134", "raw_count": 56417623, "count": 56417623, "decode_str": "\u6bd2"} -{"id": 51886, "token": "\u00e6\u012c\u00b1", "merges": "\u00e6\u012c \u00b1", "raw_count": 56428501, "count": 56428501, "decode_str": "\u62b1"} -{"id": 13076, "token": "\u0128\u0134", "merges": "\u0128 \u0134", "raw_count": 2140, "count": 56514360, "decode_str": "\ufffd\ufffd"} -{"id": 51167, "token": "\u00e5\u013d\u00b0", "merges": "\u00e5\u013d \u00b0", "raw_count": 56546134, "count": 56546134, "decode_str": "\u56f0"} -{"id": 52436, "token": "\u00e6\u00af\u0137", "merges": "\u00e6\u00af \u0137", "raw_count": 56635413, "count": 56635413, "decode_str": "\u6bd5"} -{"id": 1036, "token": "16", "merges": "1 6", "raw_count": 40964514, "count": 56648616, "decode_str": "16"} -{"id": 52570, "token": "\u00e6\u00b4\u00be", "merges": "\u00e6\u00b4 \u00be", "raw_count": 56684407, "count": 56684407, "decode_str": "\u6d3e"} -{"id": 54406, "token": "\u00e9\u013f\u0142", "merges": "\u00e9\u013f \u0142", "raw_count": 56969531, "count": 56969531, "decode_str": "\u9760"} -{"id": 51576, "token": "\u00e5\u00ba\u0143", "merges": "\u00e5\u00ba \u0143", "raw_count": 57110866, "count": 57110866, "decode_str": "\u5ead"} -{"id": 55, "token": "V", "merges": "NULL", "raw_count": 22818341, "count": 57187083, "decode_str": "V"} -{"id": 273, "token": "\u0120of", "merges": "\u0120o f", "raw_count": 54071145, "count": 57325115, "decode_str": " of"} -{"id": 1545, "token": "def", "merges": "de f", "raw_count": 54879102, "count": 57341713, "decode_str": "def"} -{"id": 271, "token": "\u0120an", "merges": "\u0120a n", "raw_count": 5231173, "count": 57371566, "decode_str": " an"} -{"id": 339, "token": "se", "merges": "s e", "raw_count": 3308539, "count": 57421059, "decode_str": "se"} -{"id": 300, "token": "il", "merges": "i l", "raw_count": 1776812, "count": 57528528, "decode_str": "il"} -{"id": 51588, "token": "\u00e5\u00bb\u00b6", "merges": "\u00e5\u00bb \u00b6", "raw_count": 57570675, "count": 57570675, "decode_str": "\u5ef6"} -{"id": 54404, "token": "\u00e9\u013f\u013b", "merges": "\u00e9\u013f \u013b", "raw_count": 57630868, "count": 57630868, "decode_str": "\u9759"} -{"id": 303, "token": "im", "merges": "i m", "raw_count": 3347597, "count": 57707898, "decode_str": "im"} -{"id": 50416, "token": "\u00e4\u00b8\u013f", "merges": "\u00e4\u00b8 \u013f", "raw_count": 57861749, "count": 57861749, "decode_str": "\u4e1d"} -{"id": 51197, "token": "\u00e5\u013f\u0132", "merges": "\u00e5\u013f \u0132", "raw_count": 58003206, "count": 58003206, "decode_str": "\u5750"} -{"id": 53211, "token": "\u00e7\u00ac\u0136", "merges": "\u00e7\u00ac \u0136", "raw_count": 58024366, "count": 58024366, "decode_str": "\u7b14"} -{"id": 53377, "token": "\u00e7\u00bb\u00bf", "merges": "\u00e7\u00bb \u00bf", "raw_count": 58284466, "count": 58284466, "decode_str": "\u7eff"} -{"id": 54090, "token": "\u00e8\u00bf\u00b0", "merges": "\u00e8\u00bf \u00b0", "raw_count": 58339484, "count": 58339484, "decode_str": "\u8ff0"} -{"id": 50452, "token": "\u00e4\u00b9\u013f", "merges": "\u00e4\u00b9 \u013f", "raw_count": 58364378, "count": 58364378, "decode_str": "\u4e5d"} -{"id": 6256, "token": "\u00c2\u00b7", "merges": "\u00c2 \u00b7", "raw_count": 54530575, "count": 58372927, "decode_str": "\u00b7"} -{"id": 54285, "token": "\u00e9\u0139\u00bb", "merges": "\u00e9\u0139 \u00bb", "raw_count": 58612374, "count": 58612374, "decode_str": "\u95fb"} -{"id": 50500, "token": "\u00e4\u00bb\u0135", "merges": "\u00e4\u00bb \u0135", "raw_count": 58672877, "count": 58672877, "decode_str": "\u4ed3"} -{"id": 50628, "token": "\u00e5\u0122\u0141", "merges": "\u00e5\u0122 \u0141", "raw_count": 58682109, "count": 58682109, "decode_str": "\u501f"} -{"id": 53194, "token": "\u00e7\u00ab\u0140", "merges": "\u00e7\u00ab \u0140", "raw_count": 58751016, "count": 58751016, "decode_str": "\u7ade"} -{"id": 53106, "token": "\u00e7\u00a4\u00bc", "merges": "\u00e7\u00a4 \u00bc", "raw_count": 58841831, "count": 58841831, "decode_str": "\u793c"} -{"id": 54240, "token": "\u00e9\u0136\u00ae", "merges": "\u00e9\u0136 \u00ae", "raw_count": 58873271, "count": 58873271, "decode_str": "\u952e"} -{"id": 51173, "token": "\u00e5\u013d\u00ba", "merges": "\u00e5\u013d \u00ba", "raw_count": 58925517, "count": 58925517, "decode_str": "\u56fa"} -{"id": 52386, "token": "\u00e6\u00ac\u00a7", "merges": "\u00e6\u00ac \u00a7", "raw_count": 58973863, "count": 58973863, "decode_str": "\u6b27"} -{"id": 297, "token": "om", "merges": "o m", "raw_count": 1622628, "count": 58989166, "decode_str": "om"} -{"id": 53857, "token": "\u00e8\u00b0\u012a", "merges": "\u00e8\u00b0 \u012a", "raw_count": 59515672, "count": 59515672, "decode_str": "\u8c08"} -{"id": 54026, "token": "\u00e8\u00bd\u00ae", "merges": "\u00e8\u00bd \u00ae", "raw_count": 59803871, "count": 59803871, "decode_str": "\u8f6e"} -{"id": 51190, "token": "\u00e5\u013f\u0122", "merges": "\u00e5\u013f \u0122", "raw_count": 59887894, "count": 59887894, "decode_str": "\u5740"} -{"id": 52902, "token": "\u00e7\u0138\u0133", "merges": "\u00e7\u0138 \u0133", "raw_count": 59986235, "count": 59986235, "decode_str": "\u7591"} -{"id": 53408, "token": "\u00e7\u00bc\u00ba", "merges": "\u00e7\u00bc \u00ba", "raw_count": 60027454, "count": 60027454, "decode_str": "\u7f3a"} -{"id": 50696, "token": "\u00e5\u0127\u00b0", "merges": "\u00e5\u0127 \u00b0", "raw_count": 60100925, "count": 60100925, "decode_str": "\u5170"} -{"id": 126, "token": "\u00c2", "merges": "NULL", "raw_count": 0, "count": 60134287, "decode_str": "\ufffd"} -{"id": 53293, "token": "\u00e7\u00b4\u00a2", "merges": "\u00e7\u00b4 \u00a2", "raw_count": 60302135, "count": 60302135, "decode_str": "\u7d22"} -{"id": 51745, "token": "\u00e6\u0124\u00a3", "merges": "\u00e6\u0124 \u00a3", "raw_count": 60305989, "count": 60305989, "decode_str": "\u60a3"} -{"id": 51639, "token": "\u00e5\u00be\u0123", "merges": "\u00e5\u00be \u0123", "raw_count": 60472151, "count": 60472151, "decode_str": "\u5f81"} -{"id": 54095, "token": "\u00e8\u00bf\u00bd", "merges": "\u00e8\u00bf \u00bd", "raw_count": 60488893, "count": 60488893, "decode_str": "\u8ffd"} -{"id": 82, "token": "q", "merges": "NULL", "raw_count": 8850916, "count": 60537656, "decode_str": "q"} -{"id": 18780, "token": "\u00e2\u0122\u00a6\u00e2\u0122\u00a6", "merges": "\u00e2\u0122\u00a6 \u00e2\u0122\u00a6", "raw_count": 59932930, "count": 60722310, "decode_str": "\u2026\u2026"} -{"id": 54104, "token": "\u00e9\u0122\u0131", "merges": "\u00e9\u0122 \u0131", "raw_count": 60807657, "count": 60807657, "decode_str": "\u900f"} -{"id": 50496, "token": "\u00e4\u00bb\u012f", "merges": "\u00e4\u00bb \u012f", "raw_count": 60839668, "count": 60839668, "decode_str": "\u4ecd"} -{"id": 53817, "token": "\u00e8\u00af\u0133", "merges": "\u00e8\u00af \u0133", "raw_count": 61188960, "count": 61188960, "decode_str": "\u8bd1"} -{"id": 51293, "token": "\u00e5\u00a4\u013e", "merges": "\u00e5\u00a4 \u013e", "raw_count": 61196535, "count": 61196535, "decode_str": "\u591c"} -{"id": 4, "token": "#", "merges": "NULL", "raw_count": 47939986, "count": 61338192, "decode_str": "#"} -{"id": 52764, "token": "\u00e7\u012a\u00b6", "merges": "\u00e7\u012a \u00b6", "raw_count": 61553420, "count": 61553420, "decode_str": "\u7236"} -{"id": 270, "token": "\u0120b", "merges": "\u0120 b", "raw_count": 4841268, "count": 61595054, "decode_str": " b"} -{"id": 53585, "token": "\u00e8\u012a\u00aa", "merges": "\u00e8\u012a \u00aa", "raw_count": 61610917, "count": 61610917, "decode_str": "\u822a"} -{"id": 53479, "token": "\u00e8\u0124\u012b", "merges": "\u00e8\u0124 \u012b", "raw_count": 61740325, "count": 61740325, "decode_str": "\u8089"} -{"id": 50392, "token": "\u00e3\u0122\u0132", "merges": "\u00e3\u0122 \u0132", "raw_count": 61857962, "count": 61857962, "decode_str": "\u3010"} -{"id": 259, "token": "\u0120w", "merges": "\u0120 w", "raw_count": 2112389, "count": 62343156, "decode_str": " w"} -{"id": 50935, "token": "\u00e5\u0131\u00ab", "merges": "\u00e5\u0131 \u00ab", "raw_count": 62363859, "count": 62363859, "decode_str": "\u53eb"} -{"id": 50393, "token": "\u00e3\u0122\u0133", "merges": "\u00e3\u0122 \u0133", "raw_count": 62487989, "count": 62487989, "decode_str": "\u3011"} -{"id": 50802, "token": "\u00e5\u012b\u00a7", "merges": "\u00e5\u012b \u00a7", "raw_count": 62765897, "count": 62765897, "decode_str": "\u5267"} -{"id": 49056, "token": "\u00e5\u00ba\u0131", "merges": "\u00e5\u00ba \u0131", "raw_count": 62783920, "count": 62783920, "decode_str": "\u5e8f"} -{"id": 11602, "token": "!\u00e2\u0122\u013f", "merges": "! \u00e2\u0122\u013f", "raw_count": 62875408, "count": 62875408, "decode_str": "!\u201d"} -{"id": 50865, "token": "\u00e5\u012f\u012a", "merges": "\u00e5\u012f \u012a", "raw_count": 62982256, "count": 62982256, "decode_str": "\u5348"} -{"id": 53334, "token": "\u00e7\u00bb\u0125", "merges": "\u00e7\u00bb \u0125", "raw_count": 63121960, "count": 63121960, "decode_str": "\u7ec3"} -{"id": 50441, "token": "\u00e4\u00b9\u0130", "merges": "\u00e4\u00b9 \u0130", "raw_count": 63211877, "count": 63211877, "decode_str": "\u4e4e"} -{"id": 1235, "token": "50", "merges": "5 0", "raw_count": 48990081, "count": 63420867, "decode_str": "50"} -{"id": 50403, "token": "\u00e4\u00b8\u0125", "merges": "\u00e4\u00b8 \u0125", "raw_count": 64053939, "count": 64053939, "decode_str": "\u4e03"} -{"id": 52867, "token": "\u00e7\u0136\u013c", "merges": "\u00e7\u0136 \u013c", "raw_count": 64168950, "count": 64168950, "decode_str": "\u751a"} -{"id": 51813, "token": "\u00e6\u012a\u0131", "merges": "\u00e6\u012a \u0131", "raw_count": 64340471, "count": 64340471, "decode_str": "\u620f"} -{"id": 53073, "token": "\u00e7\u00a1\u0122", "merges": "\u00e7\u00a1 \u0122", "raw_count": 64530404, "count": 64530404, "decode_str": "\u7840"} -{"id": 52039, "token": "\u00e6\u0134\u0143", "merges": "\u00e6\u0134 \u0143", "raw_count": 64623896, "count": 64623896, "decode_str": "\u64ad"} -{"id": 50783, "token": "\u00e5\u012a\u00b8", "merges": "\u00e5\u012a \u00b8", "raw_count": 64706708, "count": 64706708, "decode_str": "\u5238"} -{"id": 53934, "token": "\u00e8\u00b4\u00b5", "merges": "\u00e8\u00b4 \u00b5", "raw_count": 64753945, "count": 64753945, "decode_str": "\u8d35"} -{"id": 50737, "token": "\u00e5\u0129\u0122", "merges": "\u00e5\u0129 \u0122", "raw_count": 64938263, "count": 64938263, "decode_str": "\u51c0"} -{"id": 54322, "token": "\u00e9\u013b\u012a", "merges": "\u00e9\u013b \u012a", "raw_count": 65007884, "count": 65007884, "decode_str": "\u9648"} -{"id": 52236, "token": "\u00e6\u0140\u0132", "merges": "\u00e6\u0140 \u0132", "raw_count": 65155713, "count": 65155713, "decode_str": "\u6790"} -{"id": 53654, "token": "\u00e8\u012d\u00a6", "merges": "\u00e8\u012d \u00a6", "raw_count": 65287339, "count": 65287339, "decode_str": "\u82e6"} -{"id": 54432, "token": "\u00e9\u00a1\u00be", "merges": "\u00e9\u00a1 \u00be", "raw_count": 65331823, "count": 65331823, "decode_str": "\u987e"} -{"id": 53552, "token": "\u00e8\u0126\u00b8", "merges": "\u00e8\u0126 \u00b8", "raw_count": 65441462, "count": 65441462, "decode_str": "\u8138"} -{"id": 54034, "token": "\u00e8\u00bd\u00bd", "merges": "\u00e8\u00bd \u00bd", "raw_count": 65445361, "count": 65445361, "decode_str": "\u8f7d"} -{"id": 52534, "token": "\u00e6\u00b3\u00a2", "merges": "\u00e6\u00b3 \u00a2", "raw_count": 65633446, "count": 65633446, "decode_str": "\u6ce2"} -{"id": 52229, "token": "\u00e6\u013f\u00be", "merges": "\u00e6\u013f \u00be", "raw_count": 65960895, "count": 65960895, "decode_str": "\u677e"} -{"id": 278, "token": "\u0120m", "merges": "\u0120 m", "raw_count": 4469986, "count": 66006541, "decode_str": " m"} -{"id": 1093, "token": "18", "merges": "1 8", "raw_count": 47012706, "count": 66045999, "decode_str": "18"} -{"id": 50455, "token": "\u00e4\u00b9\u00a1", "merges": "\u00e4\u00b9 \u00a1", "raw_count": 66149180, "count": 66149180, "decode_str": "\u4e61"} -{"id": 52715, "token": "\u00e7\u0123\u00b5", "merges": "\u00e7\u0123 \u00b5", "raw_count": 66227289, "count": 66227289, "decode_str": "\u7075"} -{"id": 2262, "token": "):", "merges": ") :", "raw_count": 63792135, "count": 66303318, "decode_str": "):"} -{"id": 51297, "token": "\u00e5\u00a4\u00ab", "merges": "\u00e5\u00a4 \u00ab", "raw_count": 66392681, "count": 66392681, "decode_str": "\u592b"} -{"id": 51911, "token": "\u00e6\u012d\u013d", "merges": "\u00e6\u012d \u013d", "raw_count": 66427722, "count": 66427722, "decode_str": "\u62db"} -{"id": 53510, "token": "\u00e8\u0125\u012e", "merges": "\u00e8\u0125 \u012e", "raw_count": 66462751, "count": 66462751, "decode_str": "\u80cc"} -{"id": 50728, "token": "\u00e5\u0128\u00b2", "merges": "\u00e5\u0128 \u00b2", "raw_count": 66568118, "count": 66568118, "decode_str": "\u51b2"} -{"id": 53248, "token": "\u00e7\u00ae\u00b1", "merges": "\u00e7\u00ae \u00b1", "raw_count": 66590534, "count": 66590534, "decode_str": "\u7bb1"} -{"id": 337, "token": "\u01201", "merges": "\u0120 1", "raw_count": 32931335, "count": 66607182, "decode_str": " 1"} -{"id": 54350, "token": "\u00e9\u013c\u013e", "merges": "\u00e9\u013c \u013e", "raw_count": 66692886, "count": 66692886, "decode_str": "\u969c"} -{"id": 53640, "token": "\u00e8\u012d\u0131", "merges": "\u00e8\u012d \u0131", "raw_count": 66853860, "count": 66853860, "decode_str": "\u82cf"} -{"id": 50881, "token": "\u00e5\u012f\u0142", "merges": "\u00e5\u012f \u0142", "raw_count": 67156800, "count": 67156800, "decode_str": "\u5360"} -{"id": 51801, "token": "\u00e6\u0127\u00a2", "merges": "\u00e6\u0127 \u00a2", "raw_count": 67226829, "count": 67226829, "decode_str": "\u6162"} -{"id": 51442, "token": "\u00e5\u00af\u0141", "merges": "\u00e5\u00af \u0141", "raw_count": 67719330, "count": 67719330, "decode_str": "\u5bdf"} -{"id": 53323, "token": "\u00e7\u00ba\u00b3", "merges": "\u00e7\u00ba \u00b3", "raw_count": 67792673, "count": 67792673, "decode_str": "\u7eb3"} -{"id": 50483, "token": "\u00e4\u00ba\u00ae", "merges": "\u00e4\u00ba \u00ae", "raw_count": 67916284, "count": 67916284, "decode_str": "\u4eae"} -{"id": 50509, "token": "\u00e4\u00bb\u00a4", "merges": "\u00e4\u00bb \u00a4", "raw_count": 67948922, "count": 67948922, "decode_str": "\u4ee4"} -{"id": 53163, "token": "\u00e7\u00a7\u00bb", "merges": "\u00e7\u00a7 \u00bb", "raw_count": 68056915, "count": 68056915, "decode_str": "\u79fb"} -{"id": 338, "token": "if", "merges": "i f", "raw_count": 36222098, "count": 68103940, "decode_str": "if"} -{"id": 52810, "token": "\u00e7\u0130\u00a9", "merges": "\u00e7\u0130 \u00a9", "raw_count": 68384068, "count": 68384068, "decode_str": "\u73a9"} -{"id": 53259, "token": "\u00e7\u00b2\u012b", "merges": "\u00e7\u00b2 \u012b", "raw_count": 68599576, "count": 68599576, "decode_str": "\u7c89"} -{"id": 52669, "token": "\u00e6\u00b8\u00af", "merges": "\u00e6\u00b8 \u00af", "raw_count": 68604017, "count": 68604017, "decode_str": "\u6e2f"} -{"id": 50545, "token": "\u00e4\u00bc\u00bc", "merges": "\u00e4\u00bc \u00bc", "raw_count": 68647556, "count": 68647556, "decode_str": "\u4f3c"} -{"id": 51971, "token": "\u00e6\u012f\u0141", "merges": "\u00e6\u012f \u0141", "raw_count": 69004469, "count": 69004469, "decode_str": "\u635f"} -{"id": 51592, "token": "\u00e5\u00bc\u0124", "merges": "\u00e5\u00bc \u0124", "raw_count": 69218117, "count": 69218117, "decode_str": "\u5f02"} -{"id": 54315, "token": "\u00e9\u013a\u00bf", "merges": "\u00e9\u013a \u00bf", "raw_count": 69289591, "count": 69289591, "decode_str": "\u963f"} -{"id": 11, "token": "*", "merges": "NULL", "raw_count": 22607472, "count": 69497979, "decode_str": "*"} -{"id": 51922, "token": "\u00e6\u012d\u00ac", "merges": "\u00e6\u012d \u00ac", "raw_count": 69586531, "count": 69586531, "decode_str": "\u62ec"} -{"id": 51575, "token": "\u00e5\u00ba\u00a7", "merges": "\u00e5\u00ba \u00a7", "raw_count": 69670262, "count": 69670262, "decode_str": "\u5ea7"} -{"id": 50594, "token": "\u00e4\u00bf\u0125", "merges": "\u00e4\u00bf \u0125", "raw_count": 69794651, "count": 69794651, "decode_str": "\u4fc3"} -{"id": 52347, "token": "\u00e6\u00a5\u00bc", "merges": "\u00e6\u00a5 \u00bc", "raw_count": 69990045, "count": 69990045, "decode_str": "\u697c"} -{"id": 50693, "token": "\u00e5\u0127\u00ab", "merges": "\u00e5\u0127 \u00ab", "raw_count": 70025829, "count": 70025829, "decode_str": "\u516b"} -{"id": 52401, "token": "\u00e6\u0143\u00a6", "merges": "\u00e6\u0143 \u00a6", "raw_count": 70110506, "count": 70110506, "decode_str": "\u6b66"} -{"id": 52111, "token": "\u00e6\u0139\u0131", "merges": "\u00e6\u0139 \u0131", "raw_count": 70138472, "count": 70138472, "decode_str": "\u65cf"} -{"id": 52963, "token": "\u00e7\u013b\u00bb", "merges": "\u00e7\u013b \u00bb", "raw_count": 70190596, "count": 70190596, "decode_str": "\u767b"} -{"id": 50425, "token": "\u00e4\u00b8\u00b0", "merges": "\u00e4\u00b8 \u00b0", "raw_count": 70326696, "count": 70326696, "decode_str": "\u4e30"} -{"id": 53389, "token": "\u00e7\u00bc\u0138", "merges": "\u00e7\u00bc \u0138", "raw_count": 70450133, "count": 70450133, "decode_str": "\u7f16"} -{"id": 44301, "token": "\u00e6\u0138\u00b9\u00e6\u00b3\u0137", "merges": "\u00e6\u0138\u00b9 \u00e6\u00b3\u0137", "raw_count": 70482801, "count": 70482801, "decode_str": "\u65b9\u6cd5"} -{"id": 277, "token": "\u0120d", "merges": "\u0120 d", "raw_count": 3840651, "count": 70531946, "decode_str": " d"} -{"id": 54047, "token": "\u00e8\u00be\u0135", "merges": "\u00e8\u00be \u0135", "raw_count": 70669734, "count": 70669734, "decode_str": "\u8f93"} -{"id": 52195, "token": "\u00e6\u013e\u00a8", "merges": "\u00e6\u013e \u00a8", "raw_count": 70694328, "count": 70694328, "decode_str": "\u6728"} -{"id": 54251, "token": "\u00e9\u0137\u0129", "merges": "\u00e9\u0137 \u0129", "raw_count": 70751579, "count": 70751579, "decode_str": "\u9547"} -{"id": 54027, "token": "\u00e8\u00bd\u00af", "merges": "\u00e8\u00bd \u00af", "raw_count": 70790577, "count": 70790577, "decode_str": "\u8f6f"} -{"id": 933, "token": "000", "merges": "00 0", "raw_count": 13233156, "count": 70813332, "decode_str": "000"} -{"id": 301, "token": "id", "merges": "i d", "raw_count": 22670005, "count": 70846254, "decode_str": "id"} -{"id": 295, "token": "\u0120n", "merges": "\u0120 n", "raw_count": 8165672, "count": 71088102, "decode_str": " n"} -{"id": 615, "token": "de", "merges": "d e", "raw_count": 1979007, "count": 71149554, "decode_str": "de"} -{"id": 53350, "token": "\u00e7\u00bb\u013e", "merges": "\u00e7\u00bb \u013e", "raw_count": 71271014, "count": 71271014, "decode_str": "\u7edc"} -{"id": 51309, "token": "\u00e5\u00a5\u0129", "merges": "\u00e5\u00a5 \u0129", "raw_count": 71567590, "count": 71567590, "decode_str": "\u5947"} -{"id": 53541, "token": "\u00e8\u0126\u0133", "merges": "\u00e8\u0126 \u0133", "raw_count": 71646531, "count": 71646531, "decode_str": "\u8111"} -{"id": 53167, "token": "\u00e7\u00a8\u0130", "merges": "\u00e7\u00a8 \u0130", "raw_count": 71868540, "count": 71868540, "decode_str": "\u7a0e"} -{"id": 53196, "token": "\u00e7\u00ab\u0142", "merges": "\u00e7\u00ab \u0142", "raw_count": 72238702, "count": 72238702, "decode_str": "\u7ae0"} -{"id": 51416, "token": "\u00e5\u00ae\u00a3", "merges": "\u00e5\u00ae \u00a3", "raw_count": 72254733, "count": 72254733, "decode_str": "\u5ba3"} -{"id": 53190, "token": "\u00e7\u00a9\u00bf", "merges": "\u00e7\u00a9 \u00bf", "raw_count": 72255748, "count": 72255748, "decode_str": "\u7a7f"} -{"id": 1518, "token": "200", "merges": "2 00", "raw_count": 24202137, "count": 72729938, "decode_str": "200"} -{"id": 7721, "token": "?\u00e2\u0122\u013f", "merges": "? \u00e2\u0122\u013f", "raw_count": 73121778, "count": 73121778, "decode_str": "?\u201d"} -{"id": 54409, "token": "\u00e9\u013f\u00a9", "merges": "\u00e9\u013f \u00a9", "raw_count": 73261707, "count": 73261707, "decode_str": "\u9769"} -{"id": 52187, "token": "\u00e6\u013e\u012d", "merges": "\u00e6\u013e \u012d", "raw_count": 73710459, "count": 73710459, "decode_str": "\u670b"} -{"id": 53200, "token": "\u00e7\u00ab\u00af", "merges": "\u00e7\u00ab \u00af", "raw_count": 73721654, "count": 73721654, "decode_str": "\u7aef"} -{"id": 51514, "token": "\u00e5\u00b7\u00b4", "merges": "\u00e5\u00b7 \u00b4", "raw_count": 73794517, "count": 73794517, "decode_str": "\u5df4"} -{"id": 53653, "token": "\u00e8\u012d\u00a5", "merges": "\u00e8\u012d \u00a5", "raw_count": 73883061, "count": 73883061, "decode_str": "\u82e5"} -{"id": 53706, "token": "\u00e8\u00a1\u00a3", "merges": "\u00e8\u00a1 \u00a3", "raw_count": 74117932, "count": 74117932, "decode_str": "\u8863"} -{"id": 290, "token": "ent", "merges": "en t", "raw_count": 1799103, "count": 74143516, "decode_str": "ent"} -{"id": 51795, "token": "\u00e6\u0126\u00bf", "merges": "\u00e6\u0126 \u00bf", "raw_count": 74491823, "count": 74491823, "decode_str": "\u613f"} -{"id": 52914, "token": "\u00e7\u0138\u00ab", "merges": "\u00e7\u0138 \u00ab", "raw_count": 74636489, "count": 74636489, "decode_str": "\u75ab"} -{"id": 50898, "token": "\u00e5\u0130\u0124", "merges": "\u00e5\u0130 \u0124", "raw_count": 74638951, "count": 74638951, "decode_str": "\u5382"} -{"id": 52049, "token": "\u00e6\u0135\u012f", "merges": "\u00e6\u0135 \u012f", "raw_count": 74788233, "count": 74788233, "decode_str": "\u64cd"} -{"id": 50874, "token": "\u00e5\u012f\u0138", "merges": "\u00e5\u012f \u0138", "raw_count": 74899030, "count": 74899030, "decode_str": "\u5356"} -{"id": 53176, "token": "\u00e7\u00a8\u00b3", "merges": "\u00e7\u00a8 \u00b3", "raw_count": 74955037, "count": 74955037, "decode_str": "\u7a33"} -{"id": 51701, "token": "\u00e6\u0122\u00a5", "merges": "\u00e6\u0122 \u00a5", "raw_count": 75111510, "count": 75111510, "decode_str": "\u6025"} -{"id": 50640, "token": "\u00e5\u0123\u0129", "merges": "\u00e5\u0123 \u0129", "raw_count": 75205046, "count": 75205046, "decode_str": "\u5047"} -{"id": 51769, "token": "\u00e6\u0125\u0142", "merges": "\u00e6\u0125 \u0142", "raw_count": 75288380, "count": 75288380, "decode_str": "\u60e0"} -{"id": 291, "token": "ct", "merges": "c t", "raw_count": 1917753, "count": 75333592, "decode_str": "ct"} -{"id": 51846, "token": "\u00e6\u012b\u00a7", "merges": "\u00e6\u012b \u00a7", "raw_count": 75433104, "count": 75433104, "decode_str": "\u6267"} -{"id": 53351, "token": "\u00e7\u00bb\u013f", "merges": "\u00e7\u00bb \u013f", "raw_count": 75472411, "count": 75472411, "decode_str": "\u7edd"} -{"id": 50805, "token": "\u00e5\u012b\u00af", "merges": "\u00e5\u012b \u00af", "raw_count": 75529312, "count": 75529312, "decode_str": "\u526f"} -{"id": 51199, "token": "\u00e5\u013f\u0139", "merges": "\u00e5\u013f \u0139", "raw_count": 75711519, "count": 75711519, "decode_str": "\u5757"} -{"id": 52491, "token": "\u00e6\u00b1\u00bd", "merges": "\u00e6\u00b1 \u00bd", "raw_count": 75771936, "count": 75771936, "decode_str": "\u6c7d"} -{"id": 50427, "token": "\u00e4\u00b8\u00b4", "merges": "\u00e4\u00b8 \u00b4", "raw_count": 75839103, "count": 75839103, "decode_str": "\u4e34"} -{"id": 53790, "token": "\u00e8\u00ae\u0143", "merges": "\u00e8\u00ae \u0143", "raw_count": 75930000, "count": 75930000, "decode_str": "\u8bad"} -{"id": 52891, "token": "\u00e7\u0137\u00a5", "merges": "\u00e7\u0137 \u00a5", "raw_count": 75958992, "count": 75958992, "decode_str": "\u7565"} -{"id": 50887, "token": "\u00e5\u012f\u00ab", "merges": "\u00e5\u012f \u00ab", "raw_count": 76035755, "count": 76035755, "decode_str": "\u536b"} -{"id": 52185, "token": "\u00e6\u013d\u00be", "merges": "\u00e6\u013d \u00be", "raw_count": 76110372, "count": 76110372, "decode_str": "\u66fe"} -{"id": 53829, "token": "\u00e8\u00af\u00a2", "merges": "\u00e8\u00af \u00a2", "raw_count": 76443234, "count": 76443234, "decode_str": "\u8be2"} -{"id": 53777, "token": "\u00e8\u0143\u00a6", "merges": "\u00e8\u0143 \u00a6", "raw_count": 76474955, "count": 76474955, "decode_str": "\u8b66"} -{"id": 50732, "token": "\u00e5\u0128\u00b7", "merges": "\u00e5\u0128 \u00b7", "raw_count": 76712191, "count": 76712191, "decode_str": "\u51b7"} -{"id": 50786, "token": "\u00e5\u012a\u00bb", "merges": "\u00e5\u012a \u00bb", "raw_count": 77198502, "count": 77198502, "decode_str": "\u523b"} -{"id": 50974, "token": "\u00e5\u0132\u00ab", "merges": "\u00e5\u0132 \u00ab", "raw_count": 77365633, "count": 77365633, "decode_str": "\u542b"} -{"id": 50694, "token": "\u00e5\u0127\u0143", "merges": "\u00e5\u0127 \u0143", "raw_count": 77370011, "count": 77370011, "decode_str": "\u516d"} -{"id": 272, "token": "ing", "merges": "in g", "raw_count": 6032267, "count": 77446060, "decode_str": "ing"} -{"id": 51333, "token": "\u00e5\u00a6\u012a", "merges": "\u00e5\u00a6 \u012a", "raw_count": 77553408, "count": 77553408, "decode_str": "\u5988"} -{"id": 52140, "token": "\u00e6\u013a\u00a5", "merges": "\u00e6\u013a \u00a5", "raw_count": 77593541, "count": 77593541, "decode_str": "\u6625"} -{"id": 54125, "token": "\u00e9\u0123\u0129", "merges": "\u00e9\u0123 \u0129", "raw_count": 77807471, "count": 77807471, "decode_str": "\u9047"} -{"id": 52431, "token": "\u00e6\u00af\u012f", "merges": "\u00e6\u00af \u012f", "raw_count": 78021239, "count": 78021239, "decode_str": "\u6bcd"} -{"id": 53237, "token": "\u00e7\u0143\u00be", "merges": "\u00e7\u0143 \u00be", "raw_count": 78114038, "count": 78114038, "decode_str": "\u7b7e"} -{"id": 53601, "token": "\u00e8\u012b\u00af", "merges": "\u00e8\u012b \u00af", "raw_count": 78165972, "count": 78165972, "decode_str": "\u826f"} -{"id": 52255, "token": "\u00e6\u0141\u0132", "merges": "\u00e6\u0141 \u0132", "raw_count": 78453406, "count": 78453406, "decode_str": "\u67d0"} -{"id": 32750, "token": "\u00e8\u0143", "merges": "\u00e8 \u0143", "raw_count": 24660, "count": 78457334, "decode_str": "\ufffd"} -{"id": 39, "token": "F", "merges": "NULL", "raw_count": 18792941, "count": 78469453, "decode_str": "F"} -{"id": 53415, "token": "\u00e7\u00bd\u0139", "merges": "\u00e7\u00bd \u0139", "raw_count": 78585619, "count": 78585619, "decode_str": "\u7f57"} -{"id": 53045, "token": "\u00e7\u0141\u0143", "merges": "\u00e7\u0141 \u0143", "raw_count": 78711492, "count": 78711492, "decode_str": "\u77ed"} -{"id": 50480, "token": "\u00e4\u00ba\u00ab", "merges": "\u00e4\u00ba \u00ab", "raw_count": 78971060, "count": 78971060, "decode_str": "\u4eab"} -{"id": 54428, "token": "\u00e9\u00a1\u00ba", "merges": "\u00e9\u00a1 \u00ba", "raw_count": 79654469, "count": 79654469, "decode_str": "\u987a"} -{"id": 53315, "token": "\u00e7\u00ba\u00aa", "merges": "\u00e7\u00ba \u00aa", "raw_count": 79791116, "count": 79791116, "decode_str": "\u7eaa"} -{"id": 50495, "token": "\u00e4\u00bb\u012d", "merges": "\u00e4\u00bb \u012d", "raw_count": 79808680, "count": 79808680, "decode_str": "\u4ecb"} -{"id": 51318, "token": "\u00e5\u00a5\u0138", "merges": "\u00e5\u00a5 \u0138", "raw_count": 79846610, "count": 79846610, "decode_str": "\u5956"} -{"id": 51626, "token": "\u00e5\u00bd\u00a9", "merges": "\u00e5\u00bd \u00a9", "raw_count": 80174629, "count": 80174629, "decode_str": "\u5f69"} -{"id": 53812, "token": "\u00e8\u00af\u012b", "merges": "\u00e8\u00af \u012b", "raw_count": 80247925, "count": 80247925, "decode_str": "\u8bc9"} -{"id": 12, "token": "+", "merges": "NULL", "raw_count": 53301951, "count": 80456227, "decode_str": "+"} -{"id": 50877, "token": "\u00e5\u012f\u013c", "merges": "\u00e5\u012f \u013c", "raw_count": 80777845, "count": 80777845, "decode_str": "\u535a"} -{"id": 52993, "token": "\u00e7\u013d\u013a", "merges": "\u00e7\u013d \u013a", "raw_count": 81789607, "count": 81789607, "decode_str": "\u76d8"} -{"id": 42930, "token": "\u00e7\u0136\u00bb", "merges": "\u00e7\u0136 \u00bb", "raw_count": 81865011, "count": 81865011, "decode_str": "\u753b"} -{"id": 51671, "token": "\u00e5\u00bf\u0139", "merges": "\u00e5\u00bf \u0139", "raw_count": 82001000, "count": 82001000, "decode_str": "\u5fd7"} -{"id": 50890, "token": "\u00e5\u012f\u00b0", "merges": "\u00e5\u012f \u00b0", "raw_count": 82143102, "count": 82143102, "decode_str": "\u5370"} -{"id": 51388, "token": "\u00e5\u0143\u00a3", "merges": "\u00e5\u0143 \u00a3", "raw_count": 82174264, "count": 82174264, "decode_str": "\u5b63"} -{"id": 50535, "token": "\u00e4\u00bc\u00a4", "merges": "\u00e4\u00bc \u00a4", "raw_count": 82418015, "count": 82418015, "decode_str": "\u4f24"} -{"id": 54446, "token": "\u00e9\u00a2\u0133", "merges": "\u00e9\u00a2 \u0133", "raw_count": 82574995, "count": 82574995, "decode_str": "\u9891"} -{"id": 51858, "token": "\u00e6\u012b\u00b9", "merges": "\u00e6\u012b \u00b9", "raw_count": 82612821, "count": 82612821, "decode_str": "\u6279"} -{"id": 51423, "token": "\u00e5\u00ae\u00b3", "merges": "\u00e5\u00ae \u00b3", "raw_count": 82693543, "count": 82693543, "decode_str": "\u5bb3"} -{"id": 54470, "token": "\u00e9\u00a3\u0140", "merges": "\u00e9\u00a3 \u0140", "raw_count": 82705407, "count": 82705407, "decode_str": "\u98de"} -{"id": 53359, "token": "\u00e7\u00bb\u00a7", "merges": "\u00e7\u00bb \u00a7", "raw_count": 82873807, "count": 82873807, "decode_str": "\u7ee7"} -{"id": 52555, "token": "\u00e6\u00b4\u0139", "merges": "\u00e6\u00b4 \u0139", "raw_count": 83041645, "count": 83041645, "decode_str": "\u6d17"} -{"id": 51933, "token": "\u00e6\u012d\u00bf", "merges": "\u00e6\u012d \u00bf", "raw_count": 83168387, "count": 83168387, "decode_str": "\u62ff"} -{"id": 269, "token": "\u0120f", "merges": "\u0120 f", "raw_count": 5384834, "count": 83337302, "decode_str": " f"} -{"id": 50555, "token": "\u00e4\u00bd\u013b", "merges": "\u00e4\u00bd \u013b", "raw_count": 83861532, "count": 83861532, "decode_str": "\u4f59"} -{"id": 51645, "token": "\u00e5\u00be\u012d", "merges": "\u00e5\u00be \u012d", "raw_count": 84137982, "count": 84137982, "decode_str": "\u5f8b"} -{"id": 883, "token": "11", "merges": "1 1", "raw_count": 70053047, "count": 84282765, "decode_str": "11"} -{"id": 50862, "token": "\u00e5\u012f\u0125", "merges": "\u00e5\u012f \u0125", "raw_count": 84290961, "count": 84290961, "decode_str": "\u5343"} -{"id": 53693, "token": "\u00e8\u013b\u00bd", "merges": "\u00e8\u013b \u00bd", "raw_count": 84394999, "count": 84394999, "decode_str": "\u867d"} -{"id": 40, "token": "G", "merges": "NULL", "raw_count": 34925511, "count": 85190887, "decode_str": "G"} -{"id": 51565, "token": "\u00e5\u00ba\u0135", "merges": "\u00e5\u00ba \u0135", "raw_count": 85231307, "count": 85231307, "decode_str": "\u5e93"} -{"id": 42697, "token": "\u00e7\u0142\u0123", "merges": "\u00e7\u0142 \u0123", "raw_count": 85335439, "count": 85335439, "decode_str": "\u7801"} -{"id": 287, "token": "ro", "merges": "r o", "raw_count": 2613554, "count": 85713784, "decode_str": "ro"} -{"id": 276, "token": "ou", "merges": "o u", "raw_count": 1322739, "count": 86018297, "decode_str": "ou"} -{"id": 312, "token": "am", "merges": "a m", "raw_count": 2980461, "count": 86211174, "decode_str": "am"} -{"id": 51435, "token": "\u00e5\u00af\u012e", "merges": "\u00e5\u00af \u012e", "raw_count": 86230594, "count": 86230594, "decode_str": "\u5bcc"} -{"id": 296, "token": "st", "merges": "s t", "raw_count": 3354763, "count": 86569018, "decode_str": "st"} -{"id": 50930, "token": "\u00e5\u0131\u00a4", "merges": "\u00e5\u0131 \u00a4", "raw_count": 86794466, "count": 86794466, "decode_str": "\u53e4"} -{"id": 1010, "token": "15", "merges": "1 5", "raw_count": 63215122, "count": 86840844, "decode_str": "15"} -{"id": 50982, "token": "\u00e5\u0132\u00b8", "merges": "\u00e5\u0132 \u00b8", "raw_count": 87005036, "count": 87005036, "decode_str": "\u5438"} -{"id": 51241, "token": "\u00e5\u0141\u00b9", "merges": "\u00e5\u0141 \u00b9", "raw_count": 87052440, "count": 87052440, "decode_str": "\u57f9"} -{"id": 50647, "token": "\u00e5\u0123\u013e", "merges": "\u00e5\u0123 \u013e", "raw_count": 87094704, "count": 87094704, "decode_str": "\u505c"} -{"id": 53210, "token": "\u00e7\u00ac\u0133", "merges": "\u00e7\u00ac \u0133", "raw_count": 87098177, "count": 87098177, "decode_str": "\u7b11"} -{"id": 52516, "token": "\u00e6\u00b2\u00b3", "merges": "\u00e6\u00b2 \u00b3", "raw_count": 87125789, "count": 87125789, "decode_str": "\u6cb3"} -{"id": 53847, "token": "\u00e8\u00af\u00bb", "merges": "\u00e8\u00af \u00bb", "raw_count": 87239318, "count": 87239318, "decode_str": "\u8bfb"} -{"id": 51894, "token": "\u00e6\u012d\u0127", "merges": "\u00e6\u012d \u0127", "raw_count": 87737870, "count": 87737870, "decode_str": "\u62c5"} -{"id": 54429, "token": "\u00e9\u00a1\u00bb", "merges": "\u00e9\u00a1 \u00bb", "raw_count": 87781115, "count": 87781115, "decode_str": "\u987b"} -{"id": 50941, "token": "\u00e5\u0131\u00b2", "merges": "\u00e5\u0131 \u00b2", "raw_count": 88286782, "count": 88286782, "decode_str": "\u53f2"} -{"id": 50470, "token": "\u00e4\u00ba\u013c", "merges": "\u00e4\u00ba \u013c", "raw_count": 88444040, "count": 88444040, "decode_str": "\u4e9a"} -{"id": 51414, "token": "\u00e5\u00ae\u00a1", "merges": "\u00e5\u00ae \u00a1", "raw_count": 88517771, "count": 88517771, "decode_str": "\u5ba1"} -{"id": 1229, "token": "30", "merges": "3 0", "raw_count": 77360791, "count": 88546859, "decode_str": "30"} -{"id": 51433, "token": "\u00e5\u00af\u0128", "merges": "\u00e5\u00af \u0128", "raw_count": 88577201, "count": 88577201, "decode_str": "\u5bc6"} -{"id": 280, "token": "ic", "merges": "i c", "raw_count": 3025949, "count": 88692499, "decode_str": "ic"} -{"id": 51525, "token": "\u00e5\u00b8\u012e", "merges": "\u00e5\u00b8 \u012e", "raw_count": 88708728, "count": 88708728, "decode_str": "\u5e0c"} -{"id": 45, "token": "L", "merges": "NULL", "raw_count": 18985121, "count": 88903993, "decode_str": "L"} -{"id": 51319, "token": "\u00e5\u00a5\u0139", "merges": "\u00e5\u00a5 \u0139", "raw_count": 89064214, "count": 89064214, "decode_str": "\u5957"} -{"id": 275, "token": "\u0120in", "merges": "\u0120 in", "raw_count": 52009337, "count": 89127336, "decode_str": " in"} -{"id": 52836, "token": "\u00e7\u0131\u0143", "merges": "\u00e7\u0131 \u0143", "raw_count": 89229030, "count": 89229030, "decode_str": "\u73ed"} -{"id": 53794, "token": "\u00e8\u00ae\u00b2", "merges": "\u00e8\u00ae \u00b2", "raw_count": 89265181, "count": 89265181, "decode_str": "\u8bb2"} -{"id": 50932, "token": "\u00e5\u0131\u00a6", "merges": "\u00e5\u0131 \u00a6", "raw_count": 89623437, "count": 89623437, "decode_str": "\u53e6"} -{"id": 52107, "token": "\u00e6\u0139\u0127", "merges": "\u00e6\u0139 \u0127", "raw_count": 89701198, "count": 89701198, "decode_str": "\u65c5"} -{"id": 50942, "token": "\u00e5\u0131\u00b3", "merges": "\u00e5\u0131 \u00b3", "raw_count": 90133406, "count": 90133406, "decode_str": "\u53f3"} -{"id": 51682, "token": "\u00e5\u00bf\u00b5", "merges": "\u00e5\u00bf \u00b5", "raw_count": 90565765, "count": 90565765, "decode_str": "\u5ff5"} -{"id": 52771, "token": "\u00e7\u012b\u012a", "merges": "\u00e7\u012b \u012a", "raw_count": 90834025, "count": 90834025, "decode_str": "\u7248"} -{"id": 51506, "token": "\u00e5\u00b7\u00a6", "merges": "\u00e5\u00b7 \u00a6", "raw_count": 91366022, "count": 91366022, "decode_str": "\u5de6"} -{"id": 53294, "token": "\u00e7\u00b4\u00a7", "merges": "\u00e7\u00b4 \u00a7", "raw_count": 91419876, "count": 91419876, "decode_str": "\u7d27"} -{"id": 268, "token": "\u0120p", "merges": "\u0120 p", "raw_count": 5078282, "count": 91427698, "decode_str": " p"} -{"id": 52211, "token": "\u00e6\u013f\u0130", "merges": "\u00e6\u013f \u0130", "raw_count": 91442011, "count": 91442011, "decode_str": "\u674e"} -{"id": 51181, "token": "\u00e5\u013e\u0141", "merges": "\u00e5\u013e \u0141", "raw_count": 91570433, "count": 91570433, "decode_str": "\u571f"} -{"id": 52399, "token": "\u00e6\u0143\u00a2", "merges": "\u00e6\u0143 \u00a2", "raw_count": 91634257, "count": 91634257, "decode_str": "\u6b62"} -{"id": 52976, "token": "\u00e7\u013c\u00ae", "merges": "\u00e7\u013c \u00ae", "raw_count": 91673924, "count": 91673924, "decode_str": "\u76ae"} -{"id": 47754, "token": "\u00e5\u012a\u013f", "merges": "\u00e5\u012a \u013f", "raw_count": 91809715, "count": 91809715, "decode_str": "\u521d"} -{"id": 53782, "token": "\u00e8\u00ae\u00a2", "merges": "\u00e8\u00ae \u00a2", "raw_count": 91881685, "count": 91881685, "decode_str": "\u8ba2"} -{"id": 53067, "token": "\u00e7\u0142\u00b4", "merges": "\u00e7\u0142 \u00b4", "raw_count": 91925422, "count": 91925422, "decode_str": "\u7834"} -{"id": 51111, "token": "\u00e5\u0138\u0126", "merges": "\u00e5\u0138 \u0126", "raw_count": 91928394, "count": 91928394, "decode_str": "\u5584"} -{"id": 50437, "token": "\u00e4\u00b9\u0127", "merges": "\u00e4\u00b9 \u0127", "raw_count": 92634642, "count": 92634642, "decode_str": "\u4e45"} -{"id": 53137, "token": "\u00e7\u00a6\u0131", "merges": "\u00e7\u00a6 \u0131", "raw_count": 92893959, "count": 92893959, "decode_str": "\u798f"} -{"id": 53849, "token": "\u00e8\u00af\u00be", "merges": "\u00e8\u00af \u00be", "raw_count": 92942366, "count": 92942366, "decode_str": "\u8bfe"} -{"id": 50699, "token": "\u00e5\u0127\u00b4", "merges": "\u00e5\u0127 \u00b4", "raw_count": 92985778, "count": 92985778, "decode_str": "\u5174"} -{"id": 53765, "token": "\u00e8\u00a7\u0134", "merges": "\u00e8\u00a7 \u0134", "raw_count": 93307200, "count": 93307200, "decode_str": "\u89d2"} -{"id": 44246, "token": "\u00e5\u0124", "merges": "\u00e5 \u0124", "raw_count": 324792, "count": 93452912, "decode_str": "\ufffd"} -{"id": 50465, "token": "\u00e4\u00ba\u0133", "merges": "\u00e4\u00ba \u0133", "raw_count": 93880128, "count": 93880128, "decode_str": "\u4e91"} -{"id": 35, "token": "B", "merges": "NULL", "raw_count": 33373255, "count": 93996036, "decode_str": "B"} -{"id": 52066, "token": "\u00e6\u0137\u0127", "merges": "\u00e6\u0137 \u0127", "raw_count": 94122991, "count": 94122991, "decode_str": "\u6545"} -{"id": 52161, "token": "\u00e6\u013b\u013c", "merges": "\u00e6\u013b \u013c", "raw_count": 94371879, "count": 94371879, "decode_str": "\u665a"} -{"id": 51619, "token": "\u00e5\u00bd\u0137", "merges": "\u00e5\u00bd \u0137", "raw_count": 94942562, "count": 94942562, "decode_str": "\u5f55"} -{"id": 50463, "token": "\u00e4\u00ba\u012b", "merges": "\u00e4\u00ba \u012b", "raw_count": 95229547, "count": 95229547, "decode_str": "\u4e89"} -{"id": 36998, "token": "\u00e6\u0137\u00b0\u00e6\u012f\u00ae", "merges": "\u00e6\u0137\u00b0 \u00e6\u012f\u00ae", "raw_count": 95312270, "count": 95312270, "decode_str": "\u6570\u636e"} -{"id": 51200, "token": "\u00e5\u013f\u013c", "merges": "\u00e5\u013f \u013c", "raw_count": 95354768, "count": 95354768, "decode_str": "\u575a"} -{"id": 582, "token": "),", "merges": ") ,", "raw_count": 81087341, "count": 95441203, "decode_str": "),"} -{"id": 51, "token": "R", "merges": "NULL", "raw_count": 14943767, "count": 95685600, "decode_str": "R"} -{"id": 54191, "token": "\u00e9\u0127\u0134", "merges": "\u00e9\u0127 \u0134", "raw_count": 95929496, "count": 95929496, "decode_str": "\u9152"} -{"id": 284, "token": "as", "merges": "a s", "raw_count": 4776928, "count": 95974430, "decode_str": "as"} -{"id": 52880, "token": "\u00e7\u0136\u00b7", "merges": "\u00e7\u0136 \u00b7", "raw_count": 96142143, "count": 96142143, "decode_str": "\u7537"} -{"id": 52905, "token": "\u00e7\u0138\u0139", "merges": "\u00e7\u0138 \u0139", "raw_count": 96463744, "count": 96463744, "decode_str": "\u7597"} -{"id": 51480, "token": "\u00e5\u00b1\u0127", "merges": "\u00e5\u00b1 \u0127", "raw_count": 96505212, "count": 96505212, "decode_str": "\u5c45"} -{"id": 52409, "token": "\u00e6\u0143\u00bb", "merges": "\u00e6\u0143 \u00bb", "raw_count": 96578647, "count": 96578647, "decode_str": "\u6b7b"} -{"id": 54530, "token": "\u00e9\u00bb\u0133", "merges": "\u00e9\u00bb \u0133", "raw_count": 96694706, "count": 96694706, "decode_str": "\u9ed1"} -{"id": 53696, "token": "\u00e8\u00a1\u0122", "merges": "\u00e8\u00a1 \u0122", "raw_count": 96788849, "count": 96788849, "decode_str": "\u8840"} -{"id": 264, "token": "ed", "merges": "e d", "raw_count": 5430801, "count": 96938212, "decode_str": "ed"} -{"id": 51417, "token": "\u00e5\u00ae\u00a4", "merges": "\u00e5\u00ae \u00a4", "raw_count": 97720791, "count": 97720791, "decode_str": "\u5ba4"} -{"id": 50466, "token": "\u00e4\u00ba\u0134", "merges": "\u00e4\u00ba \u0134", "raw_count": 97794358, "count": 97794358, "decode_str": "\u4e92"} -{"id": 51579, "token": "\u00e5\u00ba\u00b7", "merges": "\u00e5\u00ba \u00b7", "raw_count": 98723802, "count": 98723802, "decode_str": "\u5eb7"} -{"id": 53605, "token": "\u00e8\u012b\u00ba", "merges": "\u00e8\u012b \u00ba", "raw_count": 99177685, "count": 99177685, "decode_str": "\u827a"} -{"id": 50717, "token": "\u00e5\u0128\u013b", "merges": "\u00e5\u0128 \u013b", "raw_count": 99371597, "count": 99371597, "decode_str": "\u5199"} -{"id": 54486, "token": "\u00e9\u00a6\u013b", "merges": "\u00e9\u00a6 \u013b", "raw_count": 99562126, "count": 99562126, "decode_str": "\u9999"} -{"id": 47, "token": "N", "merges": "NULL", "raw_count": 18037605, "count": 99674715, "decode_str": "N"} -{"id": 51192, "token": "\u00e5\u013f\u0129", "merges": "\u00e5\u013f \u0129", "raw_count": 100031578, "count": 100031578, "decode_str": "\u5747"} -{"id": 53433, "token": "\u00e7\u00be\u00a4", "merges": "\u00e7\u00be \u00a4", "raw_count": 100031730, "count": 100031730, "decode_str": "\u7fa4"} -{"id": 44157, "token": "\u00e5\u012a\u0139", "merges": "\u00e5\u012a \u0139", "raw_count": 101030574, "count": 101030574, "decode_str": "\u5217"} -{"id": 51861, "token": "\u00e6\u012b\u00bf", "merges": "\u00e6\u012b \u00bf", "raw_count": 101045438, "count": 101045438, "decode_str": "\u627f"} -{"id": 50916, "token": "\u00e5\u0130\u00bf", "merges": "\u00e5\u0130 \u00bf", "raw_count": 101088588, "count": 101088588, "decode_str": "\u53bf"} -{"id": 50970, "token": "\u00e5\u0132\u00a6", "merges": "\u00e5\u0132 \u00a6", "raw_count": 101098515, "count": 101098515, "decode_str": "\u5426"} -{"id": 53337, "token": "\u00e7\u00bb\u0129", "merges": "\u00e7\u00bb \u0129", "raw_count": 101283051, "count": 101283051, "decode_str": "\u7ec7"} -{"id": 32378, "token": "\u00e4\u00be\u012d", "merges": "\u00e4\u00be \u012d", "raw_count": 101360496, "count": 101360496, "decode_str": "\u4f8b"} -{"id": 51166, "token": "\u00e5\u013d\u0143", "merges": "\u00e5\u013d \u0143", "raw_count": 101374244, "count": 101374244, "decode_str": "\u56ed"} -{"id": 52697, "token": "\u00e6\u00bc\u0136", "merges": "\u00e6\u00bc \u0136", "raw_count": 101741423, "count": 101741423, "decode_str": "\u6f14"} -{"id": 51171, "token": "\u00e5\u013d\u00b4", "merges": "\u00e5\u013d \u00b4", "raw_count": 102013355, "count": 102013355, "decode_str": "\u56f4"} -{"id": 51408, "token": "\u00e5\u00ae\u013a", "merges": "\u00e5\u00ae \u013a", "raw_count": 102022671, "count": 102022671, "decode_str": "\u5b98"} -{"id": 53916, "token": "\u00e8\u00b4\u00a2", "merges": "\u00e8\u00b4 \u00a2", "raw_count": 102269168, "count": 102269168, "decode_str": "\u8d22"} -{"id": 50744, "token": "\u00e5\u0129\u0131", "merges": "\u00e5\u0129 \u0131", "raw_count": 102598488, "count": 102598488, "decode_str": "\u51cf"} -{"id": 50775, "token": "\u00e5\u012a\u013c", "merges": "\u00e5\u012a \u013c", "raw_count": 103233648, "count": 103233648, "decode_str": "\u521a"} -{"id": 54526, "token": "\u00e9\u00bb\u0126", "merges": "\u00e9\u00bb \u0126", "raw_count": 103244140, "count": 103244140, "decode_str": "\u9ec4"} -{"id": 22150, "token": "\u00e5\u0142", "merges": "\u00e5 \u0142", "raw_count": 267909, "count": 103351065, "decode_str": "\ufffd"} -{"id": 52168, "token": "\u00e6\u013b\u00ae", "merges": "\u00e6\u013b \u00ae", "raw_count": 104274120, "count": 104274120, "decode_str": "\u666e"} -{"id": 51641, "token": "\u00e5\u00be\u0127", "merges": "\u00e5\u00be \u0127", "raw_count": 104276488, "count": 104276488, "decode_str": "\u5f85"} -{"id": 54325, "token": "\u00e9\u013b\u012f", "merges": "\u00e9\u013b \u012f", "raw_count": 104616371, "count": 104616371, "decode_str": "\u964d"} -{"id": 50760, "token": "\u00e5\u0129\u00bb", "merges": "\u00e5\u0129 \u00bb", "raw_count": 105206199, "count": 105206199, "decode_str": "\u51fb"} -{"id": 258, "token": "\u0120o", "merges": "\u0120 o", "raw_count": 1962944, "count": 105317257, "decode_str": " o"} -{"id": 50433, "token": "\u00e4\u00b8\u00be", "merges": "\u00e4\u00b8 \u00be", "raw_count": 105452775, "count": 105452775, "decode_str": "\u4e3e"} -{"id": 53047, "token": "\u00e7\u0141\u00b3", "merges": "\u00e7\u0141 \u00b3", "raw_count": 105532994, "count": 105532994, "decode_str": "\u77f3"} -{"id": 50685, "token": "\u00e5\u0127\u012f", "merges": "\u00e5\u0127 \u012f", "raw_count": 105877219, "count": 105877219, "decode_str": "\u514d"} -{"id": 43397, "token": "\u00e7\u012c\u00b6", "merges": "\u00e7\u012c \u00b6", "raw_count": 106651801, "count": 106651801, "decode_str": "\u72b6"} -{"id": 253, "token": "\u0120the", "merges": "\u0120t he", "raw_count": 96681552, "count": 106871236, "decode_str": " the"} -{"id": 48, "token": "O", "merges": "NULL", "raw_count": 24359690, "count": 107367526, "decode_str": "O"} -{"id": 52889, "token": "\u00e7\u0137\u013b", "merges": "\u00e7\u0137 \u013b", "raw_count": 107430665, "count": 107430665, "decode_str": "\u7559"} -{"id": 53228, "token": "\u00e7\u0143\u0138", "merges": "\u00e7\u0143 \u0138", "raw_count": 107459471, "count": 107459471, "decode_str": "\u7b56"} -{"id": 50504, "token": "\u00e4\u00bb\u013a", "merges": "\u00e4\u00bb \u013a", "raw_count": 107721034, "count": 107721034, "decode_str": "\u4ed8"} -{"id": 50648, "token": "\u00e5\u0123\u00a5", "merges": "\u00e5\u0123 \u00a5", "raw_count": 108139878, "count": 108139878, "decode_str": "\u5065"} -{"id": 53238, "token": "\u00e7\u00ae\u0122", "merges": "\u00e7\u00ae \u0122", "raw_count": 108424739, "count": 108424739, "decode_str": "\u7b80"} -{"id": 52984, "token": "\u00e7\u013d\u012c", "merges": "\u00e7\u013d \u012c", "raw_count": 108734333, "count": 108734333, "decode_str": "\u76ca"} -{"id": 51008, "token": "\u00e5\u0133\u00b3", "merges": "\u00e5\u0133 \u00b3", "raw_count": 109087425, "count": 109087425, "decode_str": "\u5473"} -{"id": 52174, "token": "\u00e6\u013b\u00ba", "merges": "\u00e6\u013b \u00ba", "raw_count": 109164517, "count": 109164517, "decode_str": "\u667a"} -{"id": 50421, "token": "\u00e4\u00b8\u00a5", "merges": "\u00e4\u00b8 \u00a5", "raw_count": 109345467, "count": 109345467, "decode_str": "\u4e25"} -{"id": 50867, "token": "\u00e5\u012f\u012c", "merges": "\u00e5\u012f \u012c", "raw_count": 109787439, "count": 109787439, "decode_str": "\u534a"} -{"id": 53707, "token": "\u00e8\u00a1\u00a5", "merges": "\u00e8\u00a1 \u00a5", "raw_count": 109795555, "count": 109795555, "decode_str": "\u8865"} -{"id": 46, "token": "M", "merges": "NULL", "raw_count": 23229984, "count": 110037783, "decode_str": "M"} -{"id": 53338, "token": "\u00e7\u00bb\u012a", "merges": "\u00e7\u00bb \u012a", "raw_count": 110348021, "count": 110348021, "decode_str": "\u7ec8"} -{"id": 54310, "token": "\u00e9\u013a\u00b3", "merges": "\u00e9\u013a \u00b3", "raw_count": 110550571, "count": 110550571, "decode_str": "\u9633"} -{"id": 53914, "token": "\u00e8\u00b4\u0141", "merges": "\u00e8\u00b4 \u0141", "raw_count": 110665620, "count": 110665620, "decode_str": "\u8d1f"} -{"id": 52138, "token": "\u00e6\u013a\u0141", "merges": "\u00e6\u013a \u0141", "raw_count": 110683651, "count": 110683651, "decode_str": "\u661f"} -{"id": 54401, "token": "\u00e9\u013f\u0134", "merges": "\u00e9\u013f \u0134", "raw_count": 110832578, "count": 110832578, "decode_str": "\u9752"} -{"id": 53127, "token": "\u00e7\u00a5\u00a8", "merges": "\u00e7\u00a5 \u00a8", "raw_count": 111094134, "count": 111094134, "decode_str": "\u7968"} -{"id": 1286, "token": "self", "merges": "s elf", "raw_count": 111073880, "count": 111359736, "decode_str": "self"} -{"id": 746, "token": "19", "merges": "1 9", "raw_count": 34128159, "count": 111438890, "decode_str": "19"} -{"id": 54455, "token": "\u00e9\u00a2\u013f", "merges": "\u00e9\u00a2 \u013f", "raw_count": 111655941, "count": 111655941, "decode_str": "\u989d"} -{"id": 292, "token": "et", "merges": "e t", "raw_count": 2842187, "count": 111673401, "decode_str": "et"} -{"id": 51236, "token": "\u00e5\u0141\u0141", "merges": "\u00e5\u0141 \u0141", "raw_count": 112319251, "count": 112319251, "decode_str": "\u57df"} -{"id": 51491, "token": "\u00e5\u00b1\u0140", "merges": "\u00e5\u00b1 \u0140", "raw_count": 112352469, "count": 112352469, "decode_str": "\u5c5e"} -{"id": 51511, "token": "\u00e5\u00b7\u00ae", "merges": "\u00e5\u00b7 \u00ae", "raw_count": 112798215, "count": 112798215, "decode_str": "\u5dee"} -{"id": 51900, "token": "\u00e6\u012d\u012f", "merges": "\u00e6\u012d \u012f", "raw_count": 112931660, "count": 112931660, "decode_str": "\u62cd"} -{"id": 260, "token": "\u0120c", "merges": "\u0120 c", "raw_count": 4882555, "count": 113249940, "decode_str": " c"} -{"id": 50487, "token": "\u00e4\u00ba\u00bf", "merges": "\u00e4\u00ba \u00bf", "raw_count": 113686360, "count": 113686360, "decode_str": "\u4ebf"} -{"id": 50580, "token": "\u00e4\u00be\u013f", "merges": "\u00e4\u00be \u013f", "raw_count": 113818351, "count": 113818351, "decode_str": "\u4f9d"} -{"id": 50492, "token": "\u00e4\u00bb\u0127", "merges": "\u00e4\u00bb \u0127", "raw_count": 113915627, "count": 113915627, "decode_str": "\u4ec5"} -{"id": 53587, "token": "\u00e8\u012a\u00ac", "merges": "\u00e8\u012a \u00ac", "raw_count": 114517764, "count": 114517764, "decode_str": "\u822c"} -{"id": 44508, "token": "\u00e6\u0135", "merges": "\u00e6 \u0135", "raw_count": 138429, "count": 114853576, "decode_str": "\ufffd"} -{"id": 54230, "token": "\u00e9\u0136\u013b", "merges": "\u00e9\u0136 \u013b", "raw_count": 115017512, "count": 115017512, "decode_str": "\u9519"} -{"id": 54078, "token": "\u00e8\u00bf\u013e", "merges": "\u00e8\u00bf \u013e", "raw_count": 115121612, "count": 115121612, "decode_str": "\u8fdc"} -{"id": 54627, "token": "\u00e3\u0122\u013c", "merges": "\u00e3\u0122 \u013c", "raw_count": 115980906, "count": 115980906, "decode_str": " "} -{"id": 50975, "token": "\u00e5\u0132\u00ac", "merges": "\u00e5\u0132 \u00ac", "raw_count": 115982786, "count": 115982786, "decode_str": "\u542c"} -{"id": 52238, "token": "\u00e6\u0140\u0139", "merges": "\u00e6\u0140 \u0139", "raw_count": 115990291, "count": 115990291, "decode_str": "\u6797"} -{"id": 279, "token": "ion", "merges": "i on", "raw_count": 1361826, "count": 116216737, "decode_str": "ion"} -{"id": 37, "token": "D", "merges": "NULL", "raw_count": 27406328, "count": 116462635, "decode_str": "D"} -{"id": 52169, "token": "\u00e6\u013b\u00af", "merges": "\u00e6\u013b \u00af", "raw_count": 116468162, "count": 116468162, "decode_str": "\u666f"} -{"id": 50870, "token": "\u00e5\u012f\u0131", "merges": "\u00e5\u012f \u0131", "raw_count": 116571045, "count": 116571045, "decode_str": "\u534f"} -{"id": 54106, "token": "\u00e9\u0122\u0134", "merges": "\u00e9\u0122 \u0134", "raw_count": 116608678, "count": 116608678, "decode_str": "\u9012"} -{"id": 50766, "token": "\u00e5\u012a\u0129", "merges": "\u00e5\u012a \u0129", "raw_count": 116856787, "count": 116856787, "decode_str": "\u5207"} -{"id": 321, "token": "ur", "merges": "u r", "raw_count": 1575076, "count": 116942132, "decode_str": "ur"} -{"id": 51860, "token": "\u00e6\u012b\u00be", "merges": "\u00e6\u012b \u00be", "raw_count": 118406298, "count": 118406298, "decode_str": "\u627e"} -{"id": 51478, "token": "\u00e5\u00b1\u0124", "merges": "\u00e5\u00b1 \u0124", "raw_count": 118524560, "count": 118524560, "decode_str": "\u5c42"} -{"id": 805, "token": "12", "merges": "1 2", "raw_count": 88520904, "count": 118571908, "decode_str": "12"} -{"id": 51898, "token": "\u00e6\u012d\u012b", "merges": "\u00e6\u012d \u012b", "raw_count": 118792307, "count": 118792307, "decode_str": "\u62c9"} -{"id": 16, "token": "/", "merges": "NULL", "raw_count": 96986984, "count": 119247830, "decode_str": "/"} -{"id": 50901, "token": "\u00e5\u0130\u0128", "merges": "\u00e5\u0130 \u0128", "raw_count": 119274286, "count": 119274286, "decode_str": "\u5386"} -{"id": 53838, "token": "\u00e8\u00af\u0143", "merges": "\u00e8\u00af \u0143", "raw_count": 119638588, "count": 119638588, "decode_str": "\u8bed"} -{"id": 48815, "token": "\u00e7\u00b4\u0142", "merges": "\u00e7\u00b4 \u0142", "raw_count": 119706887, "count": 119706887, "decode_str": "\u7d20"} -{"id": 51473, "token": "\u00e5\u00b0\u00bd", "merges": "\u00e5\u00b0 \u00bd", "raw_count": 119777719, "count": 119777719, "decode_str": "\u5c3d"} -{"id": 52479, "token": "\u00e6\u00b1\u0141", "merges": "\u00e6\u00b1 \u0141", "raw_count": 120237829, "count": 120237829, "decode_str": "\u6c5f"} -{"id": 52118, "token": "\u00e6\u0139\u00a9", "merges": "\u00e6\u0139 \u00a9", "raw_count": 120262303, "count": 120262303, "decode_str": "\u65e9"} -{"id": 51921, "token": "\u00e6\u012d\u00a9", "merges": "\u00e6\u012d \u00a9", "raw_count": 120281834, "count": 120281834, "decode_str": "\u62e9"} -{"id": 52988, "token": "\u00e7\u013d\u0133", "merges": "\u00e7\u013d \u0133", "raw_count": 120503082, "count": 120503082, "decode_str": "\u76d1"} -{"id": 44795, "token": "\u00e8\u00b1\u00a1", "merges": "\u00e8\u00b1 \u00a1", "raw_count": 120552980, "count": 120552980, "decode_str": "\u8c61"} -{"id": 50882, "token": "\u00e5\u012f\u00a1", "merges": "\u00e5\u012f \u00a1", "raw_count": 120586364, "count": 120586364, "decode_str": "\u5361"} -{"id": 51571, "token": "\u00e5\u00ba\u013e", "merges": "\u00e5\u00ba \u013e", "raw_count": 121041764, "count": 121041764, "decode_str": "\u5e9c"} -{"id": 54032, "token": "\u00e8\u00bd\u00bb", "merges": "\u00e8\u00bd \u00bb", "raw_count": 121160353, "count": 121160353, "decode_str": "\u8f7b"} -{"id": 51458, "token": "\u00e5\u00b0\u0136", "merges": "\u00e5\u00b0 \u0136", "raw_count": 121499480, "count": 121499480, "decode_str": "\u5c14"} -{"id": 51014, "token": "\u00e5\u0133\u00bd", "merges": "\u00e5\u0133 \u00bd", "raw_count": 121566210, "count": 121566210, "decode_str": "\u547d"} -{"id": 50516, "token": "\u00e4\u00bb\u00bd", "merges": "\u00e4\u00bb \u00bd", "raw_count": 121938510, "count": 121938510, "decode_str": "\u4efd"} -{"id": 51085, "token": "\u00e5\u0137\u012c", "merges": "\u00e5\u0137 \u012c", "raw_count": 121969836, "count": 121969836, "decode_str": "\u554a"} -{"id": 50684, "token": "\u00e5\u0127\u012d", "merges": "\u00e5\u0127 \u012d", "raw_count": 122195747, "count": 122195747, "decode_str": "\u514b"} -{"id": 50719, "token": "\u00e5\u0128\u013e", "merges": "\u00e5\u0128 \u013e", "raw_count": 122238721, "count": 122238721, "decode_str": "\u519c"} -{"id": 52214, "token": "\u00e6\u013f\u0133", "merges": "\u00e6\u013f \u0133", "raw_count": 123036252, "count": 123036252, "decode_str": "\u6751"} -{"id": 53336, "token": "\u00e7\u00bb\u0128", "merges": "\u00e7\u00bb \u0128", "raw_count": 123249129, "count": 123249129, "decode_str": "\u7ec6"} -{"id": 50921, "token": "\u00e5\u0131\u012e", "merges": "\u00e5\u0131 \u012e", "raw_count": 123283956, "count": 123283956, "decode_str": "\u53cc"} -{"id": 46180, "token": "\u00e7\u00a2", "merges": "\u00e7 \u00a2", "raw_count": 243303, "count": 123476336, "decode_str": "\ufffd"} -{"id": 51566, "token": "\u00e5\u00ba\u0137", "merges": "\u00e5\u00ba \u0137", "raw_count": 124283205, "count": 124283205, "decode_str": "\u5e95"} -{"id": 1128, "token": "\u00e2\u0122\u0136", "merges": "\u00e2\u0122 \u0136", "raw_count": 16942258, "count": 124285128, "decode_str": "\u2014"} -{"id": 282, "token": "le", "merges": "l e", "raw_count": 2894509, "count": 124338872, "decode_str": "le"} -{"id": 53675, "token": "\u00e8\u0130\u00b7", "merges": "\u00e8\u0130 \u00b7", "raw_count": 124343522, "count": 124343522, "decode_str": "\u83b7"} -{"id": 52710, "token": "\u00e7\u0123\u00ab", "merges": "\u00e7\u0123 \u00ab", "raw_count": 124838485, "count": 124838485, "decode_str": "\u706b"} -{"id": 50438, "token": "\u00e4\u00b9\u012b", "merges": "\u00e4\u00b9 \u012b", "raw_count": 124927187, "count": 124927187, "decode_str": "\u4e49"} -{"id": 54000, "token": "\u00e8\u00b7\u0141", "merges": "\u00e8\u00b7 \u0141", "raw_count": 125159640, "count": 125159640, "decode_str": "\u8ddf"} -{"id": 51301, "token": "\u00e5\u00a4\u00b1", "merges": "\u00e5\u00a4 \u00b1", "raw_count": 125182034, "count": 125182034, "decode_str": "\u5931"} -{"id": 50690, "token": "\u00e5\u0127\u013c", "merges": "\u00e5\u0127 \u013c", "raw_count": 125375943, "count": 125375943, "decode_str": "\u515a"} -{"id": 52384, "token": "\u00e6\u00ac\u00a2", "merges": "\u00e6\u00ac \u00a2", "raw_count": 125809260, "count": 125809260, "decode_str": "\u6b22"} -{"id": 52290, "token": "\u00e6\u0142\u00b8", "merges": "\u00e6\u0142 \u00b8", "raw_count": 126307386, "count": 126307386, "decode_str": "\u6838"} -{"id": 52577, "token": "\u00e6\u00b5\u012d", "merges": "\u00e6\u00b5 \u012d", "raw_count": 126407706, "count": 126407706, "decode_str": "\u6d4b"} -{"id": 31982, "token": "\u00e8\u00a8\u0122", "merges": "\u00e8\u00a8 \u0122", "raw_count": 126538421, "count": 126538421, "decode_str": "\u8a00"} -{"id": 51660, "token": "\u00e5\u00be\u00b7", "merges": "\u00e5\u00be \u00b7", "raw_count": 126557607, "count": 126557607, "decode_str": "\u5fb7"} -{"id": 28492, "token": "\u00e6\u00a5", "merges": "\u00e6 \u00a5", "raw_count": 149672, "count": 126762308, "decode_str": "\ufffd"} -{"id": 52213, "token": "\u00e6\u013f\u0132", "merges": "\u00e6\u013f \u0132", "raw_count": 126768983, "count": 126768983, "decode_str": "\u6750"} -{"id": 14945, "token": "\u00e8\u00a8", "merges": "\u00e8 \u00a8", "raw_count": 233584, "count": 126785957, "decode_str": "\ufffd"} -{"id": 52518, "token": "\u00e6\u00b2\u00b9", "merges": "\u00e6\u00b2 \u00b9", "raw_count": 127410836, "count": 127410836, "decode_str": "\u6cb9"} -{"id": 52230, "token": "\u00e6\u013f\u00bf", "merges": "\u00e6\u013f \u00bf", "raw_count": 127577676, "count": 127577676, "decode_str": "\u677f"} -{"id": 50903, "token": "\u00e5\u0130\u012d", "merges": "\u00e5\u0130 \u012d", "raw_count": 127589775, "count": 127589775, "decode_str": "\u538b"} -{"id": 51657, "token": "\u00e5\u00be\u00ae", "merges": "\u00e5\u00be \u00ae", "raw_count": 127800454, "count": 127800454, "decode_str": "\u5fae"} -{"id": 261, "token": "is", "merges": "i s", "raw_count": 7598841, "count": 128181593, "decode_str": "is"} -{"id": 51638, "token": "\u00e5\u00be\u0122", "merges": "\u00e5\u00be \u0122", "raw_count": 129099982, "count": 129099982, "decode_str": "\u5f80"} -{"id": 51294, "token": "\u00e5\u00a4\u0141", "merges": "\u00e5\u00a4 \u0141", "raw_count": 129382577, "count": 129382577, "decode_str": "\u591f"} -{"id": 51121, "token": "\u00e5\u0138\u013e", "merges": "\u00e5\u0138 \u013e", "raw_count": 129814900, "count": 129814900, "decode_str": "\u559c"} -{"id": 52878, "token": "\u00e7\u0136\u00b3", "merges": "\u00e7\u0136 \u00b3", "raw_count": 130143662, "count": 130143662, "decode_str": "\u7533"} -{"id": 53309, "token": "\u00e7\u00ba\u00a2", "merges": "\u00e7\u00ba \u00a2", "raw_count": 130151179, "count": 130151179, "decode_str": "\u7ea2"} -{"id": 52424, "token": "\u00e6\u00ae\u00b5", "merges": "\u00e6\u00ae \u00b5", "raw_count": 130260715, "count": 130260715, "decode_str": "\u6bb5"} -{"id": 52772, "token": "\u00e7\u012b\u012e", "merges": "\u00e7\u012b \u012e", "raw_count": 130331742, "count": 130331742, "decode_str": "\u724c"} -{"id": 53160, "token": "\u00e7\u00a7\u00af", "merges": "\u00e7\u00a7 \u00af", "raw_count": 130483788, "count": 130483788, "decode_str": "\u79ef"} -{"id": 7521, "token": "\u00e2\u0122\u013f,", "merges": "\u00e2\u0122\u013f ,", "raw_count": 130679608, "count": 130679608, "decode_str": "\u201d,"} -{"id": 42, "token": "I", "merges": "NULL", "raw_count": 13002353, "count": 130879144, "decode_str": "I"} -{"id": 50893, "token": "\u00e5\u012f\u00b4", "merges": "\u00e5\u012f \u00b4", "raw_count": 131151834, "count": 131151834, "decode_str": "\u5374"} -{"id": 21163, "token": "\u00e5\u012d", "merges": "\u00e5 \u012d", "raw_count": 354207, "count": 131372792, "decode_str": "\ufffd"} -{"id": 2866, "token": "\u00e2\u0122\u00a6", "merges": "\u00e2\u0122 \u00a6", "raw_count": 8402130, "count": 131418197, "decode_str": "\u2026"} -{"id": 51278, "token": "\u00e5\u00a3\u00ab", "merges": "\u00e5\u00a3 \u00ab", "raw_count": 131928724, "count": 131928724, "decode_str": "\u58eb"} -{"id": 54217, "token": "\u00e9\u0136\u0122", "merges": "\u00e9\u0136 \u0122", "raw_count": 132001882, "count": 132001882, "decode_str": "\u9500"} -{"id": 53799, "token": "\u00e8\u00ae\u00b8", "merges": "\u00e8\u00ae \u00b8", "raw_count": 132686497, "count": 132686497, "decode_str": "\u8bb8"} -{"id": 53657, "token": "\u00e8\u012d\u00b1", "merges": "\u00e8\u012d \u00b1", "raw_count": 132803490, "count": 132803490, "decode_str": "\u82f1"} -{"id": 50772, "token": "\u00e5\u012a\u0134", "merges": "\u00e5\u012a \u0134", "raw_count": 133149443, "count": 133149443, "decode_str": "\u5212"} -{"id": 52965, "token": "\u00e7\u013b\u00be", "merges": "\u00e7\u013b \u00be", "raw_count": 133833687, "count": 133833687, "decode_str": "\u767e"} -{"id": 54419, "token": "\u00e9\u0141\u00b3", "merges": "\u00e9\u0141 \u00b3", "raw_count": 133858155, "count": 133858155, "decode_str": "\u97f3"} -{"id": 53983, "token": "\u00e8\u00b6\u00b3", "merges": "\u00e8\u00b6 \u00b3", "raw_count": 133960366, "count": 133960366, "decode_str": "\u8db3"} -{"id": 52667, "token": "\u00e6\u00b8\u00a9", "merges": "\u00e6\u00b8 \u00a9", "raw_count": 134038394, "count": 134038394, "decode_str": "\u6e29"} -{"id": 53368, "token": "\u00e7\u00bb\u00b4", "merges": "\u00e7\u00bb \u00b4", "raw_count": 134130671, "count": 134130671, "decode_str": "\u7ef4"} -{"id": 54333, "token": "\u00e9\u013b\u00a9", "merges": "\u00e9\u013b \u00a9", "raw_count": 134903288, "count": 134903288, "decode_str": "\u9669"} -{"id": 53142, "token": "\u00e7\u00a6\u00bb", "merges": "\u00e7\u00a6 \u00bb", "raw_count": 135209068, "count": 135209068, "decode_str": "\u79bb"} -{"id": 53565, "token": "\u00e8\u0129\u00b4", "merges": "\u00e8\u0129 \u00b4", "raw_count": 135952724, "count": 135952724, "decode_str": "\u81f4"} -{"id": 53467, "token": "\u00e8\u0123\u012e", "merges": "\u00e8\u0123 \u012e", "raw_count": 136161370, "count": 136161370, "decode_str": "\u804c"} -{"id": 52319, "token": "\u00e6\u00a3\u0122", "merges": "\u00e6\u00a3 \u0122", "raw_count": 136297100, "count": 136297100, "decode_str": "\u68c0"} -{"id": 30886, "token": "\u00e5\u0143\u0139", "merges": "\u00e5\u0143 \u0139", "raw_count": 136639973, "count": 136639973, "decode_str": "\u5b57"} -{"id": 38, "token": "E", "merges": "NULL", "raw_count": 14224359, "count": 136694188, "decode_str": "E"} -{"id": 54211, "token": "\u00e9\u0129\u0129", "merges": "\u00e9\u0129 \u0129", "raw_count": 137320164, "count": 137320164, "decode_str": "\u91c7"} -{"id": 53255, "token": "\u00e7\u00b1\u00b3", "merges": "\u00e7\u00b1 \u00b3", "raw_count": 137813674, "count": 137813674, "decode_str": "\u7c73"} -{"id": 50826, "token": "\u00e5\u012c\u00bf", "merges": "\u00e5\u012c \u00bf", "raw_count": 138384013, "count": 138384013, "decode_str": "\u52bf"} -{"id": 51503, "token": "\u00e5\u00b7\u0140", "merges": "\u00e5\u00b7 \u0140", "raw_count": 138570794, "count": 138570794, "decode_str": "\u5dde"} -{"id": 274, "token": "ar", "merges": "a r", "raw_count": 3362724, "count": 138598525, "decode_str": "ar"} -{"id": 50681, "token": "\u00e5\u0127\u0127", "merges": "\u00e5\u0127 \u0127", "raw_count": 139033215, "count": 139033215, "decode_str": "\u5145"} -{"id": 52231, "token": "\u00e6\u0140\u0123", "merges": "\u00e6\u0140 \u0123", "raw_count": 139189940, "count": 139189940, "decode_str": "\u6781"} -{"id": 51538, "token": "\u00e5\u00b8\u00ae", "merges": "\u00e5\u00b8 \u00ae", "raw_count": 139239990, "count": 139239990, "decode_str": "\u5e2e"} -{"id": 266, "token": "an", "merges": "a n", "raw_count": 4470278, "count": 140493223, "decode_str": "an"} -{"id": 51936, "token": "\u00e6\u012e\u012b", "merges": "\u00e6\u012e \u012b", "raw_count": 140804185, "count": 140804185, "decode_str": "\u6309"} -{"id": 53960, "token": "\u00e8\u00b5\u013d", "merges": "\u00e8\u00b5 \u013d", "raw_count": 141053960, "count": 141053960, "decode_str": "\u8d5b"} -{"id": 262, "token": "it", "merges": "i t", "raw_count": 4749664, "count": 141452482, "decode_str": "it"} -{"id": 53192, "token": "\u00e7\u00ab\u013b", "merges": "\u00e7\u00ab \u013b", "raw_count": 141922550, "count": 141922550, "decode_str": "\u7ad9"} -{"id": 52102, "token": "\u00e6\u0138\u0143", "merges": "\u00e6\u0138 \u0143", "raw_count": 142122344, "count": 142122344, "decode_str": "\u65ad"} -{"id": 48889, "token": "\u00e9\u013b\u0132", "merges": "\u00e9\u013b \u0132", "raw_count": 142564132, "count": 142564132, "decode_str": "\u9650"} -{"id": 50527, "token": "\u00e4\u00bc\u0139", "merges": "\u00e4\u00bc \u0139", "raw_count": 142623185, "count": 142623185, "decode_str": "\u4f17"} -{"id": 41202, "token": "\u00e6\u00a8\u00a1", "merges": "\u00e6\u00a8 \u00a1", "raw_count": 142749438, "count": 142749438, "decode_str": "\u6a21"} -{"id": 42951, "token": "\u00e9\u013b\u00a4", "merges": "\u00e9\u013b \u00a4", "raw_count": 143535515, "count": 143535515, "decode_str": "\u9664"} -{"id": 53917, "token": "\u00e8\u00b4\u00a3", "merges": "\u00e8\u00b4 \u00a3", "raw_count": 143916725, "count": 143916725, "decode_str": "\u8d23"} -{"id": 52803, "token": "\u00e7\u0130\u012d", "merges": "\u00e7\u0130 \u012d", "raw_count": 145019751, "count": 145019751, "decode_str": "\u738b"} -{"id": 52578, "token": "\u00e6\u00b5\u0130", "merges": "\u00e6\u00b5 \u0130", "raw_count": 145020594, "count": 145020594, "decode_str": "\u6d4e"} -{"id": 51997, "token": "\u00e6\u0130\u00a7", "merges": "\u00e6\u0130 \u00a7", "raw_count": 145051370, "count": 145051370, "decode_str": "\u63a7"} -{"id": 51259, "token": "\u00e5\u00a2\u0125", "merges": "\u00e5\u00a2 \u0125", "raw_count": 145105380, "count": 145105380, "decode_str": "\u5883"} -{"id": 52192, "token": "\u00e6\u013e\u013d", "merges": "\u00e6\u013e \u013d", "raw_count": 145139774, "count": 145139774, "decode_str": "\u671b"} -{"id": 54080, "token": "\u00e8\u00bf\u0140", "merges": "\u00e8\u00bf \u0140", "raw_count": 145621027, "count": 145621027, "decode_str": "\u8fde"} -{"id": 44314, "token": "\u00e5\u0125\u0131", "merges": "\u00e5\u0125 \u0131", "raw_count": 145928023, "count": 145928023, "decode_str": "\u50cf"} -{"id": 51281, "token": "\u00e5\u00a3\u00b0", "merges": "\u00e5\u00a3 \u00b0", "raw_count": 145950823, "count": 145950823, "decode_str": "\u58f0"} -{"id": 53810, "token": "\u00e8\u00af\u0128", "merges": "\u00e8\u00af \u0128", "raw_count": 146509793, "count": 146509793, "decode_str": "\u8bc6"} -{"id": 53161, "token": "\u00e7\u00a7\u00b0", "merges": "\u00e7\u00a7 \u00b0", "raw_count": 146851567, "count": 146851567, "decode_str": "\u79f0"} -{"id": 50704, "token": "\u00e5\u0127\u00bb", "merges": "\u00e5\u0127 \u00bb", "raw_count": 146986583, "count": 146986583, "decode_str": "\u517b"} -{"id": 50718, "token": "\u00e5\u0128\u013d", "merges": "\u00e5\u0128 \u013d", "raw_count": 147011354, "count": 147011354, "decode_str": "\u519b"} -{"id": 52103, "token": "\u00e6\u0138\u00af", "merges": "\u00e6\u0138 \u00af", "raw_count": 147105496, "count": 147105496, "decode_str": "\u65af"} -{"id": 44290, "token": "\u00e5\u00bc\u0137", "merges": "\u00e5\u00bc \u0137", "raw_count": 147354530, "count": 147354530, "decode_str": "\u5f15"} -{"id": 426, "token": "\u0120=", "merges": "\u0120 =", "raw_count": 147796173, "count": 147885320, "decode_str": " ="} -{"id": 53187, "token": "\u00e7\u00a9\u00b6", "merges": "\u00e7\u00a9 \u00b6", "raw_count": 148163037, "count": 148163037, "decode_str": "\u7a76"} -{"id": 54484, "token": "\u00e9\u00a6\u0138", "merges": "\u00e9\u00a6 \u0138", "raw_count": 148209167, "count": 148209167, "decode_str": "\u9996"} -{"id": 28791, "token": "\u00e7\u00bd\u00ae", "merges": "\u00e7\u00bd \u00ae", "raw_count": 148952113, "count": 148952113, "decode_str": "\u7f6e"} -{"id": 54471, "token": "\u00e9\u00a3\u0141", "merges": "\u00e9\u00a3 \u0141", "raw_count": 149270753, "count": 149270753, "decode_str": "\u98df"} -{"id": 50549, "token": "\u00e4\u00bd\u0131", "merges": "\u00e4\u00bd \u0131", "raw_count": 149286697, "count": 149286697, "decode_str": "\u4f4f"} -{"id": 50920, "token": "\u00e5\u0131\u012d", "merges": "\u00e5\u0131 \u012d", "raw_count": 149509389, "count": 149509389, "decode_str": "\u53cb"} -{"id": 35801, "token": "\u00e7\u0131", "merges": "\u00e7 \u0131", "raw_count": 179450, "count": 149936062, "decode_str": "\ufffd"} -{"id": 51687, "token": "\u00e6\u0122\u0123", "merges": "\u00e6\u0122 \u0123", "raw_count": 150219645, "count": 150219645, "decode_str": "\u6001"} -{"id": 51390, "token": "\u00e5\u0143\u00a9", "merges": "\u00e5\u0143 \u00a9", "raw_count": 150405771, "count": 150405771, "decode_str": "\u5b69"} -{"id": 45128, "token": "\u00e6\u0134", "merges": "\u00e6 \u0134", "raw_count": 189444, "count": 150794504, "decode_str": "\ufffd"} -{"id": 53, "token": "T", "merges": "NULL", "raw_count": 25933720, "count": 150819477, "decode_str": "T"} -{"id": 50454, "token": "\u00e4\u00b9\u0142", "merges": "\u00e4\u00b9 \u0142", "raw_count": 151739522, "count": 151739522, "decode_str": "\u4e60"} -{"id": 267, "token": "al", "merges": "a l", "raw_count": 3253722, "count": 152028149, "decode_str": "al"} -{"id": 51361, "token": "\u00e5\u00a7\u0136", "merges": "\u00e5\u00a7 \u0136", "raw_count": 152230774, "count": 152230774, "decode_str": "\u59d4"} -{"id": 50951, "token": "\u00e5\u0132\u0125", "merges": "\u00e5\u0132 \u0125", "raw_count": 152374913, "count": 152374913, "decode_str": "\u5403"} -{"id": 50815, "token": "\u00e5\u012c\u00a9", "merges": "\u00e5\u012c \u00a9", "raw_count": 152390406, "count": 152390406, "decode_str": "\u52a9"} -{"id": 51074, "token": "\u00e5\u0135\u00aa", "merges": "\u00e5\u0135 \u00aa", "raw_count": 152789552, "count": 152789552, "decode_str": "\u54ea"} -{"id": 50467, "token": "\u00e4\u00ba\u0136", "merges": "\u00e4\u00ba \u0136", "raw_count": 153018899, "count": 153018899, "decode_str": "\u4e94"} -{"id": 39249, "token": "\u00e5\u013d\u00be", "merges": "\u00e5\u013d \u00be", "raw_count": 153198622, "count": 153198622, "decode_str": "\u56fe"} -{"id": 50892, "token": "\u00e5\u012f\u00b3", "merges": "\u00e5\u012f \u00b3", "raw_count": 153958333, "count": 153958333, "decode_str": "\u5373"} -{"id": 47615, "token": "\u00e7\u00ae\u0139", "merges": "\u00e7\u00ae \u0139", "raw_count": 154324432, "count": 154324432, "decode_str": "\u7b97"} -{"id": 53312, "token": "\u00e7\u00ba\u00a6", "merges": "\u00e7\u00ba \u00a6", "raw_count": 154425696, "count": 154425696, "decode_str": "\u7ea6"} -{"id": 51568, "token": "\u00e5\u00ba\u0139", "merges": "\u00e5\u00ba \u0139", "raw_count": 154455521, "count": 154455521, "decode_str": "\u5e97"} -{"id": 51060, "token": "\u00e5\u0135\u012f", "merges": "\u00e5\u0135 \u012f", "raw_count": 154566531, "count": 154566531, "decode_str": "\u54cd"} -{"id": 53018, "token": "\u00e7\u013e\u00bc", "merges": "\u00e7\u013e \u00bc", "raw_count": 154606131, "count": 154606131, "decode_str": "\u773c"} -{"id": 52927, "token": "\u00e7\u0139\u0127", "merges": "\u00e7\u0139 \u0127", "raw_count": 154741033, "count": 154741033, "decode_str": "\u75c5"} -{"id": 813, "token": "elf", "merges": "el f", "raw_count": 127402, "count": 154921611, "decode_str": "elf"} -{"id": 52300, "token": "\u00e6\u00a1\u012a", "merges": "\u00e6\u00a1 \u012a", "raw_count": 154993433, "count": 154993433, "decode_str": "\u6848"} -{"id": 54345, "token": "\u00e9\u013c\u0131", "merges": "\u00e9\u013c \u0131", "raw_count": 155091972, "count": 155091972, "decode_str": "\u968f"} -{"id": 53978, "token": "\u00e8\u00b6\u0127", "merges": "\u00e8\u00b6 \u0127", "raw_count": 155748239, "count": 155748239, "decode_str": "\u8d85"} -{"id": 32938, "token": "\u00e5\u0143\u013a", "merges": "\u00e5\u0143 \u013a", "raw_count": 155960188, "count": 155960188, "decode_str": "\u5b58"} -{"id": 51973, "token": "\u00e6\u012f\u00a2", "merges": "\u00e6\u012f \u00a2", "raw_count": 156119067, "count": 156119067, "decode_str": "\u6362"} -{"id": 50774, "token": "\u00e5\u012a\u013b", "merges": "\u00e5\u012a \u013b", "raw_count": 156242519, "count": 156242519, "decode_str": "\u5219"} -{"id": 50443, "token": "\u00e4\u00b9\u0132", "merges": "\u00e4\u00b9 \u0132", "raw_count": 156968299, "count": 156968299, "decode_str": "\u4e50"} -{"id": 51881, "token": "\u00e6\u012c\u00a4", "merges": "\u00e6\u012c \u00a4", "raw_count": 157137878, "count": 157137878, "decode_str": "\u62a4"} -{"id": 52104, "token": "\u00e6\u0138\u00bd", "merges": "\u00e6\u0138 \u00bd", "raw_count": 157306563, "count": 157306563, "decode_str": "\u65bd"} -{"id": 95, "token": "~", "merges": "NULL", "raw_count": 121156576, "count": 157416677, "decode_str": "~"} -{"id": 41250, "token": "\u00e5\u00bf\u0127", "merges": "\u00e5\u00bf \u0127", "raw_count": 157448000, "count": 157448000, "decode_str": "\u5fc5"} -{"id": 54098, "token": "\u00e9\u0122\u0124", "merges": "\u00e9\u0122 \u0124", "raw_count": 157826662, "count": 157826662, "decode_str": "\u9002"} -{"id": 50611, "token": "\u00e4\u00bf\u00ae", "merges": "\u00e4\u00bf \u00ae", "raw_count": 158174197, "count": 158174197, "decode_str": "\u4fee"} -{"id": 54319, "token": "\u00e9\u013b\u0127", "merges": "\u00e9\u013b \u0127", "raw_count": 158419510, "count": 158419510, "decode_str": "\u9645"} -{"id": 50864, "token": "\u00e5\u012f\u0129", "merges": "\u00e5\u012f \u0129", "raw_count": 159267657, "count": 159267657, "decode_str": "\u5347"} -{"id": 54436, "token": "\u00e9\u00a2\u0126", "merges": "\u00e9\u00a2 \u0126", "raw_count": 159304749, "count": 159304749, "decode_str": "\u9884"} -{"id": 89, "token": "x", "merges": "NULL", "raw_count": 29727926, "count": 159637280, "decode_str": "x"} -{"id": 43251, "token": "\u00e5\u0131\u00af\u00e8\u0125\u00bd", "merges": "\u00e5\u0131\u00af \u00e8\u0125\u00bd", "raw_count": 159687724, "count": 159687724, "decode_str": "\u53ef\u80fd"} -{"id": 40969, "token": "\u00e5\u0122\u00bc", "merges": "\u00e5\u0122 \u00bc", "raw_count": 159917388, "count": 159917388, "decode_str": "\u503c"} -{"id": 46791, "token": "\u00e6\u0127", "merges": "\u00e6 \u0127", "raw_count": 191020, "count": 160017352, "decode_str": "\ufffd"} -{"id": 51552, "token": "\u00e5\u00b9\u00b2", "merges": "\u00e5\u00b9 \u00b2", "raw_count": 160698059, "count": 160698059, "decode_str": "\u5e72"} -{"id": 52207, "token": "\u00e6\u013f\u0125", "merges": "\u00e6\u013f \u0125", "raw_count": 160804174, "count": 160804174, "decode_str": "\u6743"} -{"id": 51605, "token": "\u00e5\u00bc\u0142", "merges": "\u00e5\u00bc \u0142", "raw_count": 161009258, "count": 161009258, "decode_str": "\u5f20"} -{"id": 52770, "token": "\u00e7\u012b\u0129", "merges": "\u00e7\u012b \u0129", "raw_count": 161119351, "count": 161119351, "decode_str": "\u7247"} -{"id": 52232, "token": "\u00e6\u0140\u0126", "merges": "\u00e6\u0140 \u0126", "raw_count": 161167707, "count": 161167707, "decode_str": "\u6784"} -{"id": 32653, "token": "\u00e5\u0125", "merges": "\u00e5 \u0125", "raw_count": 280280, "count": 161534311, "decode_str": "\ufffd"} -{"id": 54498, "token": "\u00e9\u00aa\u012e", "merges": "\u00e9\u00aa \u012e", "raw_count": 161629331, "count": 161629331, "decode_str": "\u9a8c"} -{"id": 52801, "token": "\u00e7\u0130\u0129", "merges": "\u00e7\u0130 \u0129", "raw_count": 161730376, "count": 161730376, "decode_str": "\u7387"} -{"id": 39295, "token": "\u00e5\u00a7\u012d", "merges": "\u00e5\u00a7 \u012d", "raw_count": 162793185, "count": 162793185, "decode_str": "\u59cb"} -{"id": 35636, "token": "\u00e6\u0122\u013f", "merges": "\u00e6\u0122 \u013f", "raw_count": 162973390, "count": 162973390, "decode_str": "\u601d"} -{"id": 50869, "token": "\u00e5\u012f\u0130", "merges": "\u00e5\u012f \u0130", "raw_count": 164058389, "count": 164058389, "decode_str": "\u534e"} -{"id": 51991, "token": "\u00e6\u0130\u0134", "merges": "\u00e6\u0130 \u0134", "raw_count": 164066544, "count": 164066544, "decode_str": "\u6392"} -{"id": 53927, "token": "\u00e8\u00b4\u0143", "merges": "\u00e8\u00b4 \u0143", "raw_count": 164496651, "count": 164496651, "decode_str": "\u8d2d"} -{"id": 51412, "token": "\u00e5\u00ae\u013f", "merges": "\u00e5\u00ae \u013f", "raw_count": 165257956, "count": 165257956, "decode_str": "\u5b9d"} -{"id": 50409, "token": "\u00e4\u00b8\u0136", "merges": "\u00e4\u00b8 \u0136", "raw_count": 165536065, "count": 165536065, "decode_str": "\u4e14"} -{"id": 51161, "token": "\u00e5\u013d\u00a2", "merges": "\u00e5\u013d \u00a2", "raw_count": 165661671, "count": 165661671, "decode_str": "\u56e2"} -{"id": 52196, "token": "\u00e6\u013e\u00aa", "merges": "\u00e6\u013e \u00aa", "raw_count": 165935639, "count": 165935639, "decode_str": "\u672a"} -{"id": 51476, "token": "\u00e5\u00b1\u0122", "merges": "\u00e5\u00b1 \u0122", "raw_count": 166939591, "count": 166939591, "decode_str": "\u5c40"} -{"id": 54112, "token": "\u00e9\u0122\u0141", "merges": "\u00e9\u0122 \u0141", "raw_count": 166980773, "count": 166980773, "decode_str": "\u901f"} -{"id": 52672, "token": "\u00e6\u00b8\u00b8", "merges": "\u00e6\u00b8 \u00b8", "raw_count": 167425213, "count": 167425213, "decode_str": "\u6e38"} -{"id": 53979, "token": "\u00e8\u00b6\u012c", "merges": "\u00e8\u00b6 \u012c", "raw_count": 167505969, "count": 167505969, "decode_str": "\u8d8a"} -{"id": 53877, "token": "\u00e8\u00b0\u00a2", "merges": "\u00e8\u00b0 \u00a2", "raw_count": 167986490, "count": 167986490, "decode_str": "\u8c22"} -{"id": 52291, "token": "\u00e6\u0142\u00b9", "merges": "\u00e6\u0142 \u00b9", "raw_count": 168350831, "count": 168350831, "decode_str": "\u6839"} -{"id": 938, "token": "20", "merges": "2 0", "raw_count": 108183580, "count": 168631417, "decode_str": "20"} -{"id": 256, "token": "\u0120s", "merges": "\u0120 s", "raw_count": 4186805, "count": 168753198, "decode_str": " s"} -{"id": 54357, "token": "\u00e9\u013c\u00be", "merges": "\u00e9\u013c \u00be", "raw_count": 169058435, "count": 169058435, "decode_str": "\u96be"} -{"id": 39573, "token": "\u00e5\u0131\u0124", "merges": "\u00e5\u0131 \u0124", "raw_count": 169247688, "count": 169247688, "decode_str": "\u53c2"} -{"id": 265, "token": "es", "merges": "e s", "raw_count": 4475090, "count": 169327788, "decode_str": "es"} -{"id": 52, "token": "S", "merges": "NULL", "raw_count": 27628080, "count": 169477323, "decode_str": "S"} -{"id": 36, "token": "C", "merges": "NULL", "raw_count": 37082725, "count": 169576741, "decode_str": "C"} -{"id": 36720, "token": "\u00e7\u012c", "merges": "\u00e7 \u012c", "raw_count": 313030, "count": 169999082, "decode_str": "\ufffd"} -{"id": 50548, "token": "\u00e4\u00bd\u0130", "merges": "\u00e4\u00bd \u0130", "raw_count": 170711586, "count": 170711586, "decode_str": "\u4f4e"} -{"id": 45261, "token": "\u00e7\u0137\u012e", "merges": "\u00e7\u0137 \u012e", "raw_count": 170821219, "count": 170821219, "decode_str": "\u754c"} -{"id": 51005, "token": "\u00e5\u0133\u00a8", "merges": "\u00e5\u0133 \u00a8", "raw_count": 172407642, "count": 172407642, "decode_str": "\u5468"} -{"id": 50992, "token": "\u00e5\u0133\u012c", "merges": "\u00e5\u0133 \u012c", "raw_count": 172417365, "count": 172417365, "decode_str": "\u544a"} -{"id": 53628, "token": "\u00e8\u012c\u00b1", "merges": "\u00e8\u012c \u00b1", "raw_count": 172869617, "count": 172869617, "decode_str": "\u82b1"} -{"id": 740, "token": "10", "merges": "1 0", "raw_count": 147913949, "count": 173127007, "decode_str": "10"} -{"id": 53760, "token": "\u00e8\u00a7\u012b", "merges": "\u00e8\u00a7 \u012b", "raw_count": 173395245, "count": 173395245, "decode_str": "\u89c9"} -{"id": 53755, "token": "\u00e8\u00a7\u0124", "merges": "\u00e8\u00a7 \u0124", "raw_count": 174404108, "count": 174404108, "decode_str": "\u89c2"} -{"id": 26487, "token": "\u00e6\u00a8", "merges": "\u00e6 \u00a8", "raw_count": 321033, "count": 174804337, "decode_str": "\ufffd"} -{"id": 54309, "token": "\u00e9\u013a\u00b2", "merges": "\u00e9\u013a \u00b2", "raw_count": 175274680, "count": 175274680, "decode_str": "\u9632"} -{"id": 49, "token": "P", "merges": "NULL", "raw_count": 23893996, "count": 176989036, "decode_str": "P"} -{"id": 53490, "token": "\u00e8\u0124\u00a1", "merges": "\u00e8\u0124 \u00a1", "raw_count": 178330665, "count": 178330665, "decode_str": "\u80a1"} -{"id": 52679, "token": "\u00e6\u00ba\u0132", "merges": "\u00e6\u00ba \u0132", "raw_count": 179452917, "count": 179452917, "decode_str": "\u6e90"} -{"id": 51056, "token": "\u00e5\u0135\u012a", "merges": "\u00e5\u0135 \u012a", "raw_count": 179725633, "count": 179725633, "decode_str": "\u54c8"} -{"id": 54097, "token": "\u00e9\u0122\u0123", "merges": "\u00e9\u0122 \u0123", "raw_count": 179901069, "count": 179901069, "decode_str": "\u9001"} -{"id": 50859, "token": "\u00e5\u012e\u00bb", "merges": "\u00e5\u012e \u00bb", "raw_count": 180024573, "count": 180024573, "decode_str": "\u533b"} -{"id": 53808, "token": "\u00e8\u00af\u0126", "merges": "\u00e8\u00af \u0126", "raw_count": 180509487, "count": 180509487, "decode_str": "\u8bc4"} -{"id": 53003, "token": "\u00e7\u013e\u0123", "merges": "\u00e7\u013e \u0123", "raw_count": 180652685, "count": 180652685, "decode_str": "\u7701"} -{"id": 39465, "token": "\u00e5\u00ae\u0125", "merges": "\u00e5\u00ae \u0125", "raw_count": 180682479, "count": 180682479, "decode_str": "\u5b83"} -{"id": 52149, "token": "\u00e6\u013a\u00be", "merges": "\u00e6\u013a \u00be", "raw_count": 180748644, "count": 180748644, "decode_str": "\u663e"} -{"id": 76, "token": "k", "merges": "NULL", "raw_count": 15612696, "count": 181600161, "decode_str": "k"} -{"id": 53122, "token": "\u00e7\u00a5\u0140", "merges": "\u00e7\u00a5 \u0140", "raw_count": 181665517, "count": 181665517, "decode_str": "\u795e"} -{"id": 263, "token": "or", "merges": "o r", "raw_count": 4025246, "count": 181961548, "decode_str": "or"} -{"id": 50730, "token": "\u00e5\u0128\u00b5", "merges": "\u00e5\u0128 \u00b5", "raw_count": 182146894, "count": 182146894, "decode_str": "\u51b5"} -{"id": 52092, "token": "\u00e6\u0138\u013b", "merges": "\u00e6\u0138 \u013b", "raw_count": 182451359, "count": 182451359, "decode_str": "\u6599"} -{"id": 52813, "token": "\u00e7\u0130\u00af", "merges": "\u00e7\u0130 \u00af", "raw_count": 182455731, "count": 182455731, "decode_str": "\u73af"} -{"id": 52519, "token": "\u00e6\u00b2\u00bb", "merges": "\u00e6\u00b2 \u00bb", "raw_count": 182456373, "count": 182456373, "decode_str": "\u6cbb"} -{"id": 247, "token": "\u0120a", "merges": "\u0120 a", "raw_count": 28651123, "count": 183051257, "decode_str": " a"} -{"id": 53972, "token": "\u00e8\u00b5\u00b0", "merges": "\u00e8\u00b5 \u00b0", "raw_count": 183606884, "count": 183606884, "decode_str": "\u8d70"} -{"id": 50677, "token": "\u00e5\u0126\u00bf", "merges": "\u00e5\u0126 \u00bf", "raw_count": 183705618, "count": 183705618, "decode_str": "\u513f"} -{"id": 248, "token": "he", "merges": "h e", "raw_count": 2192405, "count": 183772130, "decode_str": "he"} -{"id": 42165, "token": "\u00e9\u013d\u0128", "merges": "\u00e9\u013d \u0128", "raw_count": 184992845, "count": 184992845, "decode_str": "\u96c6"} -{"id": 47750, "token": "\u00e4\u00be\u013d", "merges": "\u00e4\u00be \u013d", "raw_count": 185622399, "count": 185622399, "decode_str": "\u4f9b"} -{"id": 50729, "token": "\u00e5\u0128\u00b3", "merges": "\u00e5\u0128 \u00b3", "raw_count": 185723538, "count": 185723538, "decode_str": "\u51b3"} -{"id": 40715, "token": "\u00e9\u0127\u012f", "merges": "\u00e9\u0127 \u012f", "raw_count": 185827418, "count": 185827418, "decode_str": "\u914d"} -{"id": 50813, "token": "\u00e5\u012c\u0141", "merges": "\u00e5\u012c \u0141", "raw_count": 186132642, "count": 186132642, "decode_str": "\u529f"} -{"id": 51521, "token": "\u00e5\u00b8\u0125", "merges": "\u00e5\u00b8 \u0125", "raw_count": 186225701, "count": 186225701, "decode_str": "\u5e03"} -{"id": 52287, "token": "\u00e6\u0142\u00a1", "merges": "\u00e6\u0142 \u00a1", "raw_count": 186336996, "count": 186336996, "decode_str": "\u6821"} -{"id": 50593, "token": "\u00e4\u00be\u00bf", "merges": "\u00e4\u00be \u00bf", "raw_count": 186986665, "count": 186986665, "decode_str": "\u4fbf"} -{"id": 53277, "token": "\u00e7\u00b2\u00be", "merges": "\u00e7\u00b2 \u00be", "raw_count": 187112786, "count": 187112786, "decode_str": "\u7cbe"} -{"id": 51557, "token": "\u00e5\u00b9\u00bf", "merges": "\u00e5\u00b9 \u00bf", "raw_count": 187145266, "count": 187145266, "decode_str": "\u5e7f"} -{"id": 54305, "token": "\u00e9\u013a\u0141", "merges": "\u00e9\u013a \u0141", "raw_count": 187330273, "count": 187330273, "decode_str": "\u961f"} -{"id": 50922, "token": "\u00e5\u0131\u012f", "merges": "\u00e5\u0131 \u012f", "raw_count": 187434617, "count": 187434617, "decode_str": "\u53cd"} -{"id": 52644, "token": "\u00e6\u00b7\u00b1", "merges": "\u00e6\u00b7 \u00b1", "raw_count": 187439943, "count": 187439943, "decode_str": "\u6df1"} -{"id": 51157, "token": "\u00e5\u013d\u013d", "merges": "\u00e5\u013d \u013d", "raw_count": 187555634, "count": 187555634, "decode_str": "\u56db"} -{"id": 35498, "token": "\u00e7\u00b1\u00bb", "merges": "\u00e7\u00b1 \u00bb", "raw_count": 187931107, "count": 187931107, "decode_str": "\u7c7b"} -{"id": 50697, "token": "\u00e5\u0127\u00b1", "merges": "\u00e5\u0127 \u00b1", "raw_count": 188164444, "count": 188164444, "decode_str": "\u5171"} -{"id": 34, "token": "A", "merges": "NULL", "raw_count": 41928850, "count": 188799486, "decode_str": "A"} -{"id": 53363, "token": "\u00e7\u00bb\u0143", "merges": "\u00e7\u00bb \u0143", "raw_count": 188812842, "count": 188812842, "decode_str": "\u7eed"} -{"id": 52840, "token": "\u00e7\u0132\u0125", "merges": "\u00e7\u0132 \u0125", "raw_count": 189596824, "count": 189596824, "decode_str": "\u7403"} -{"id": 52134, "token": "\u00e6\u013a\u0135", "merges": "\u00e6\u013a \u0135", "raw_count": 190429113, "count": 190429113, "decode_str": "\u6613"} -{"id": 52400, "token": "\u00e6\u0143\u00a5", "merges": "\u00e6\u0143 \u00a5", "raw_count": 190486460, "count": 190486460, "decode_str": "\u6b65"} -{"id": 53499, "token": "\u00e8\u0124\u00b2", "merges": "\u00e8\u0124 \u00b2", "raw_count": 190548933, "count": 190548933, "decode_str": "\u80b2"} -{"id": 48897, "token": "\u00e5\u0126", "merges": "\u00e5 \u0126", "raw_count": 106217, "count": 190636749, "decode_str": "\ufffd"} -{"id": 257, "token": "en", "merges": "e n", "raw_count": 3978703, "count": 191375552, "decode_str": "en"} -{"id": 62, "token": "]", "merges": "NULL", "raw_count": 113040238, "count": 192419572, "decode_str": "]"} -{"id": 37300, "token": "\u00e8\u00b1", "merges": "\u00e8 \u00b1", "raw_count": 282775, "count": 192505315, "decode_str": "\ufffd"} -{"id": 50971, "token": "\u00e5\u0132\u00a7", "merges": "\u00e5\u0132 \u00a7", "raw_count": 192709809, "count": 192709809, "decode_str": "\u5427"} -{"id": 60, "token": "[", "merges": "NULL", "raw_count": 95063068, "count": 192796090, "decode_str": "["} -{"id": 42848, "token": "\u00e4\u00b8\u0138", "merges": "\u00e4\u00b8 \u0138", "raw_count": 194838186, "count": 194838186, "decode_str": "\u4e16"} -{"id": 42055, "token": "\u00e5\u00a6\u0124\u00e6\u0140\u013e", "merges": "\u00e5\u00a6\u0124 \u00e6\u0140\u013e", "raw_count": 196270138, "count": 196270138, "decode_str": "\u5982\u679c"} -{"id": 54024, "token": "\u00e8\u00bd\u00ac", "merges": "\u00e8\u00bd \u00ac", "raw_count": 196327890, "count": 196327890, "decode_str": "\u8f6c"} -{"id": 50875, "token": "\u00e5\u012f\u0139", "merges": "\u00e5\u012f \u0139", "raw_count": 196839132, "count": 196839132, "decode_str": "\u5357"} -{"id": 51816, "token": "\u00e6\u012a\u013a", "merges": "\u00e6\u012a \u013a", "raw_count": 197491095, "count": 197491095, "decode_str": "\u6218"} -{"id": 53607, "token": "\u00e8\u012c\u0124", "merges": "\u00e8\u012c \u0124", "raw_count": 198309274, "count": 198309274, "decode_str": "\u8282"} -{"id": 54438, "token": "\u00e9\u00a2\u0128", "merges": "\u00e9\u00a2 \u0128", "raw_count": 198530125, "count": 198530125, "decode_str": "\u9886"} -{"id": 41683, "token": "\u00e5\u00ae\u00b9", "merges": "\u00e5\u00ae \u00b9", "raw_count": 199350788, "count": 199350788, "decode_str": "\u5bb9"} -{"id": 51296, "token": "\u00e5\u00a4\u00aa", "merges": "\u00e5\u00a4 \u00aa", "raw_count": 199680408, "count": 199680408, "decode_str": "\u592a"} -{"id": 51622, "token": "\u00e5\u00bd\u00a2", "merges": "\u00e5\u00bd \u00a2", "raw_count": 199939948, "count": 199939948, "decode_str": "\u5f62"} -{"id": 33499, "token": "\u00e5\u013b\u00a8", "merges": "\u00e5\u013b \u00a8", "raw_count": 199946358, "count": 199946358, "decode_str": "\u5668"} -{"id": 51830, "token": "\u00e6\u012a\u00bf", "merges": "\u00e6\u012a \u00bf", "raw_count": 199969398, "count": 199969398, "decode_str": "\u623f"} -{"id": 53818, "token": "\u00e8\u00af\u0137", "merges": "\u00e8\u00af \u0137", "raw_count": 200018551, "count": 200018551, "decode_str": "\u8bd5"} -{"id": 40153, "token": "\u00e9\u0141", "merges": "\u00e9 \u0141", "raw_count": 213867, "count": 200364518, "decode_str": "\ufffd"} -{"id": 45249, "token": "\u00e7\u00a9\u00ba", "merges": "\u00e7\u00a9 \u00ba", "raw_count": 201546729, "count": 201546729, "decode_str": "\u7a7a"} -{"id": 53056, "token": "\u00e7\u0142\u0136", "merges": "\u00e7\u0142 \u0136", "raw_count": 203413432, "count": 203413432, "decode_str": "\u7814"} -{"id": 45387, "token": "\u00e6\u00bc", "merges": "\u00e6 \u00bc", "raw_count": 469001, "count": 204125710, "decode_str": "\ufffd"} -{"id": 54076, "token": "\u00e8\u00bf\u0133", "merges": "\u00e8\u00bf \u0133", "raw_count": 205586698, "count": 205586698, "decode_str": "\u8fd1"} -{"id": 53791, "token": "\u00e8\u00ae\u00ae", "merges": "\u00e8\u00ae \u00ae", "raw_count": 205587606, "count": 205587606, "decode_str": "\u8bae"} -{"id": 51496, "token": "\u00e5\u00b1\u00b1", "merges": "\u00e5\u00b1 \u00b1", "raw_count": 205767310, "count": 205767310, "decode_str": "\u5c71"} -{"id": 53758, "token": "\u00e8\u00a7\u0128", "merges": "\u00e8\u00a7 \u0128", "raw_count": 205791636, "count": 205791636, "decode_str": "\u89c6"} -{"id": 54096, "token": "\u00e9\u0122\u0122", "merges": "\u00e9\u0122 \u0122", "raw_count": 205976680, "count": 205976680, "decode_str": "\u9000"} -{"id": 29463, "token": "\u00e4\u00bd\u00bf\u00e7\u0136\u00a8", "merges": "\u00e4\u00bd\u00bf \u00e7\u0136\u00a8", "raw_count": 206639243, "count": 206639243, "decode_str": "\u4f7f\u7528"} -{"id": 50849, "token": "\u00e5\u012e\u0139", "merges": "\u00e5\u012e \u0139", "raw_count": 207069215, "count": 207069215, "decode_str": "\u5317"} -{"id": 52599, "token": "\u00e6\u00b6\u012a", "merges": "\u00e6\u00b6 \u012a", "raw_count": 207856232, "count": 207856232, "decode_str": "\u6d88"} -{"id": 53801, "token": "\u00e8\u00ae\u00ba", "merges": "\u00e8\u00ae \u00ba", "raw_count": 208883069, "count": 208883069, "decode_str": "\u8bba"} -{"id": 50456, "token": "\u00e4\u00b9\u00a6", "merges": "\u00e4\u00b9 \u00a6", "raw_count": 209448829, "count": 209448829, "decode_str": "\u4e66"} -{"id": 51691, "token": "\u00e6\u0122\u0130", "merges": "\u00e6\u0122 \u0130", "raw_count": 210031310, "count": 210031310, "decode_str": "\u600e"} -{"id": 8, "token": "'", "merges": "NULL", "raw_count": 26885885, "count": 210433361, "decode_str": "'"} -{"id": 54036, "token": "\u00e8\u00be\u0125", "merges": "\u00e8\u00be \u0125", "raw_count": 212941745, "count": 212941745, "decode_str": "\u8f83"} -{"id": 52762, "token": "\u00e7\u012a\u00b1", "merges": "\u00e7\u012a \u00b1", "raw_count": 213046208, "count": 213046208, "decode_str": "\u7231"} -{"id": 41351, "token": "\u00e6\u013f\u00a1", "merges": "\u00e6\u013f \u00a1", "raw_count": 213549972, "count": 213549972, "decode_str": "\u6761"} -{"id": 34380, "token": "\u00e5\u0140\u012d", "merges": "\u00e5\u0140 \u012d", "raw_count": 213731472, "count": 213731472, "decode_str": "\u578b"} -{"id": 43136, "token": "\u00e6\u0123\u00af", "merges": "\u00e6\u0123 \u00af", "raw_count": 214160431, "count": 214160431, "decode_str": "\u606f"} -{"id": 41015, "token": "\u00e5\u0131\u00b7", "merges": "\u00e5\u0131 \u00b7", "raw_count": 214725981, "count": 214725981, "decode_str": "\u53f7"} -{"id": 53754, "token": "\u00e8\u00a7\u0123", "merges": "\u00e8\u00a7 \u0123", "raw_count": 214748234, "count": 214748234, "decode_str": "\u89c1"} -{"id": 51869, "token": "\u00e6\u012c\u0137", "merges": "\u00e6\u012c \u0137", "raw_count": 215408382, "count": 215408382, "decode_str": "\u6295"} -{"id": 50528, "token": "\u00e4\u00bc\u013a", "merges": "\u00e4\u00bc \u013a", "raw_count": 215563282, "count": 215563282, "decode_str": "\u4f18"} -{"id": 50739, "token": "\u00e5\u0129\u0128", "merges": "\u00e5\u0129 \u0128", "raw_count": 216130963, "count": 216130963, "decode_str": "\u51c6"} -{"id": 88, "token": "w", "merges": "NULL", "raw_count": 18822511, "count": 216347414, "decode_str": "w"} -{"id": 32053, "token": "\u00e5\u013b", "merges": "\u00e5 \u013b", "raw_count": 193771, "count": 216455210, "decode_str": "\ufffd"} -{"id": 51232, "token": "\u00e5\u0141\u0130", "merges": "\u00e5\u0141 \u0130", "raw_count": 216509305, "count": 216509305, "decode_str": "\u57ce"} -{"id": 50481, "token": "\u00e4\u00ba\u00ac", "merges": "\u00e4\u00ba \u00ac", "raw_count": 217549633, "count": 217549633, "decode_str": "\u4eac"} -{"id": 34811, "token": "\u00e6\u012e\u0129", "merges": "\u00e6\u012e \u0129", "raw_count": 217905831, "count": 217905831, "decode_str": "\u6307"} -{"id": 39811, "token": "\u00e7\u00a4\u00be", "merges": "\u00e7\u00a4 \u00be", "raw_count": 218169253, "count": 218169253, "decode_str": "\u793e"} -{"id": 6, "token": "%", "merges": "NULL", "raw_count": 139198669, "count": 218253956, "decode_str": "%"} -{"id": 52083, "token": "\u00e6\u0137\u00b4", "merges": "\u00e6\u0137 \u00b4", "raw_count": 218592040, "count": 218592040, "decode_str": "\u6574"} -{"id": 40007, "token": "\u00e5\u00a5\u00b3", "merges": "\u00e5\u00a5 \u00b3", "raw_count": 219207748, "count": 219207748, "decode_str": "\u5973"} -{"id": 50918, "token": "\u00e5\u0131\u012a", "merges": "\u00e5\u0131 \u012a", "raw_count": 219264825, "count": 219264825, "decode_str": "\u53c8"} -{"id": 51287, "token": "\u00e5\u00a4\u0129", "merges": "\u00e5\u00a4 \u0129", "raw_count": 219420837, "count": 219420837, "decode_str": "\u5907"} -{"id": 52964, "token": "\u00e7\u013b\u00bd", "merges": "\u00e7\u013b \u00bd", "raw_count": 219738848, "count": 219738848, "decode_str": "\u767d"} -{"id": 53081, "token": "\u00e7\u00a1\u00ae", "merges": "\u00e7\u00a1 \u00ae", "raw_count": 219784912, "count": 219784912, "decode_str": "\u786e"} -{"id": 51288, "token": "\u00e5\u00a4\u012f", "merges": "\u00e5\u00a4 \u012f", "raw_count": 220256612, "count": 220256612, "decode_str": "\u590d"} -{"id": 48950, "token": "\u00e6\u0141\u00a5", "merges": "\u00e6\u0141 \u00a5", "raw_count": 220364001, "count": 220364001, "decode_str": "\u67e5"} -{"id": 87, "token": "v", "merges": "NULL", "raw_count": 18586961, "count": 220936401, "decode_str": "v"} -{"id": 50625, "token": "\u00e5\u0122\u013b", "merges": "\u00e5\u0122 \u013b", "raw_count": 221304521, "count": 221304521, "decode_str": "\u5019"} -{"id": 33369, "token": "\u00e6\u00ae", "merges": "\u00e6 \u00ae", "raw_count": 500939, "count": 221553131, "decode_str": "\ufffd"} -{"id": 44966, "token": "\u00e8\u0130", "merges": "\u00e8 \u0130", "raw_count": 443289, "count": 221770851, "decode_str": "\ufffd"} -{"id": 54068, "token": "\u00e8\u00be\u00be", "merges": "\u00e8\u00be \u00be", "raw_count": 221779827, "count": 221779827, "decode_str": "\u8fbe"} -{"id": 50683, "token": "\u00e5\u0127\u012b", "merges": "\u00e5\u0127 \u012b", "raw_count": 222634311, "count": 222634311, "decode_str": "\u5149"} -{"id": 35201, "token": "\u00e4\u00bd\u0137", "merges": "\u00e4\u00bd \u0137", "raw_count": 223068663, "count": 223068663, "decode_str": "\u4f55"} -{"id": 51998, "token": "\u00e6\u0130\u00a8", "merges": "\u00e6\u0130 \u00a8", "raw_count": 223118036, "count": 223118036, "decode_str": "\u63a8"} -{"id": 51267, "token": "\u00e5\u00a2\u0140", "merges": "\u00e5\u00a2 \u0140", "raw_count": 224158228, "count": 224158228, "decode_str": "\u589e"} -{"id": 53313, "token": "\u00e7\u00ba\u00a7", "merges": "\u00e7\u00ba \u00a7", "raw_count": 224230059, "count": 224230059, "decode_str": "\u7ea7"} -{"id": 46136, "token": "\u00e6\u012a\u00b7", "merges": "\u00e6\u012a \u00b7", "raw_count": 224308757, "count": 224308757, "decode_str": "\u6237"} -{"id": 43316, "token": "\u00e6\u0136\u00b9", "merges": "\u00e6\u0136 \u00b9", "raw_count": 225426431, "count": 225426431, "decode_str": "\u6539"} -{"id": 27937, "token": "\u00e5\u0131\u0138", "merges": "\u00e5\u0131 \u0138", "raw_count": 225908718, "count": 225908718, "decode_str": "\u53d6"} -{"id": 54113, "token": "\u00e9\u0122\u0142", "merges": "\u00e9\u0122 \u0142", "raw_count": 226510898, "count": 226510898, "decode_str": "\u9020"} -{"id": 45466, "token": "\u00e8\u0122\u0125", "merges": "\u00e8\u0122 \u0125", "raw_count": 226966937, "count": 226966937, "decode_str": "\u8003"} -{"id": 41251, "token": "\u00e7\u00bb\u0126", "merges": "\u00e7\u00bb \u0126", "raw_count": 227125640, "count": 227125640, "decode_str": "\u7ec4"} -{"id": 44712, "token": "\u00e6\u00b3\u00a8", "merges": "\u00e6\u00b3 \u00a8", "raw_count": 227210339, "count": 227210339, "decode_str": "\u6ce8"} -{"id": 52650, "token": "\u00e6\u00b8\u0127", "merges": "\u00e6\u00b8 \u0127", "raw_count": 227365749, "count": 227365749, "decode_str": "\u6e05"} -{"id": 50533, "token": "\u00e4\u00bc\u0142", "merges": "\u00e4\u00bc \u0142", "raw_count": 227790330, "count": 227790330, "decode_str": "\u4f20"} -{"id": 53832, "token": "\u00e8\u00af\u00a5", "merges": "\u00e8\u00af \u00a5", "raw_count": 228951874, "count": 228951874, "decode_str": "\u8be5"} -{"id": 50776, "token": "\u00e5\u012a\u013d", "merges": "\u00e5\u012a \u013d", "raw_count": 229885206, "count": 229885206, "decode_str": "\u521b"} -{"id": 50748, "token": "\u00e5\u0129\u0142", "merges": "\u00e5\u0129 \u0142", "raw_count": 230560332, "count": 230560332, "decode_str": "\u51e0"} -{"id": 51632, "token": "\u00e5\u00bd\u00b1", "merges": "\u00e5\u00bd \u00b1", "raw_count": 230698782, "count": 230698782, "decode_str": "\u5f71"} -{"id": 50812, "token": "\u00e5\u012c\u0140", "merges": "\u00e5\u012c \u0140", "raw_count": 231957874, "count": 231957874, "decode_str": "\u529e"} -{"id": 47905, "token": "\u00e9\u013e\u0122\u00e8\u00a6\u0123", "merges": "\u00e9\u013e\u0122 \u00e8\u00a6\u0123", "raw_count": 232096114, "count": 232096114, "decode_str": "\u9700\u8981"} -{"id": 36337, "token": "\u00e6\u00ba", "merges": "\u00e6 \u00ba", "raw_count": 296915, "count": 232539114, "decode_str": "\ufffd"} -{"id": 50843, "token": "\u00e5\u012e\u0127", "merges": "\u00e5\u012e \u0127", "raw_count": 232953061, "count": 232953061, "decode_str": "\u5305"} -{"id": 51707, "token": "\u00e6\u0122\u00bb", "merges": "\u00e6\u0122 \u00bb", "raw_count": 234090677, "count": 234090677, "decode_str": "\u603b"} -{"id": 293, "token": "el", "merges": "e l", "raw_count": 3298008, "count": 234546301, "decode_str": "el"} -{"id": 53783, "token": "\u00e8\u00ae\u00a4", "merges": "\u00e8\u00ae \u00a4", "raw_count": 235841286, "count": 235841286, "decode_str": "\u8ba4"} -{"id": 46291, "token": "\u00e6\u00a3", "merges": "\u00e6 \u00a3", "raw_count": 225854, "count": 235893674, "decode_str": "\ufffd"} -{"id": 1252, "token": "201", "merges": "2 01", "raw_count": 2417884, "count": 236293939, "decode_str": "201"} -{"id": 48991, "token": "\u00e9\u013f\u0140", "merges": "\u00e9\u013f \u0140", "raw_count": 238306867, "count": 238306867, "decode_str": "\u975e"} -{"id": 53806, "token": "\u00e8\u00af\u0123", "merges": "\u00e8\u00af \u0123", "raw_count": 238341360, "count": 238341360, "decode_str": "\u8bc1"} -{"id": 53793, "token": "\u00e8\u00ae\u00b0", "merges": "\u00e8\u00ae \u00b0", "raw_count": 239229572, "count": 239229572, "decode_str": "\u8bb0"} -{"id": 46982, "token": "\u00e8\u013b", "merges": "\u00e8 \u013b", "raw_count": 212759, "count": 239326973, "decode_str": "\ufffd"} -{"id": 51451, "token": "\u00e5\u00af\u00bc", "merges": "\u00e5\u00af \u00bc", "raw_count": 239571739, "count": 239571739, "decode_str": "\u5bfc"} -{"id": 53564, "token": "\u00e8\u0129\u00b3", "merges": "\u00e8\u0129 \u00b3", "raw_count": 240571111, "count": 240571111, "decode_str": "\u81f3"} -{"id": 246, "token": "\u0120t", "merges": "\u0120 t", "raw_count": 4069373, "count": 241081370, "decode_str": " t"} -{"id": 52433, "token": "\u00e6\u00af\u0131", "merges": "\u00e6\u00af \u0131", "raw_count": 241629401, "count": 241629401, "decode_str": "\u6bcf"} -{"id": 54331, "token": "\u00e9\u013b\u00a2", "merges": "\u00e9\u013b \u00a2", "raw_count": 242453973, "count": 242453973, "decode_str": "\u9662"} -{"id": 50701, "token": "\u00e5\u0127\u00b7", "merges": "\u00e5\u0127 \u00b7", "raw_count": 242549539, "count": 242549539, "decode_str": "\u5177"} -{"id": 54427, "token": "\u00e9\u00a1\u00b9", "merges": "\u00e9\u00a1 \u00b9", "raw_count": 243130365, "count": 243130365, "decode_str": "\u9879"} -{"id": 41478, "token": "\u00e7\u00ab\u012d", "merges": "\u00e7\u00ab \u012d", "raw_count": 243644988, "count": 243644988, "decode_str": "\u7acb"} -{"id": 255, "token": "at", "merges": "a t", "raw_count": 3382666, "count": 243904969, "decode_str": "at"} -{"id": 37248, "token": "\u00e4\u00bb\u012c", "merges": "\u00e4\u00bb \u012c", "raw_count": 246265080, "count": 246265080, "decode_str": "\u4eca"} -{"id": 50518, "token": "\u00e4\u00bc\u0123", "merges": "\u00e4\u00bc \u0123", "raw_count": 247083541, "count": 247083541, "decode_str": "\u4f01"} -{"id": 47570, "token": "\u00e5\u0131\u013a", "merges": "\u00e5\u0131 \u013a", "raw_count": 247528644, "count": 247528644, "decode_str": "\u53d8"} -{"id": 51865, "token": "\u00e6\u012c\u012c", "merges": "\u00e6\u012c \u012c", "raw_count": 247894934, "count": 247894934, "decode_str": "\u628a"} -{"id": 45314, "token": "\u00e6\u0136\u00af", "merges": "\u00e6\u0136 \u00af", "raw_count": 248511043, "count": 248511043, "decode_str": "\u652f"} -{"id": 47961, "token": "\u00e5\u00ae\u012e", "merges": "\u00e5\u00ae \u012e", "raw_count": 251143742, "count": 251143742, "decode_str": "\u5b8c"} -{"id": 42292, "token": "\u00e6\u0142\u0129", "merges": "\u00e6\u0142 \u0129", "raw_count": 251442314, "count": 251442314, "decode_str": "\u6807"} -{"id": 53853, "token": "\u00e8\u00b0\u0125", "merges": "\u00e8\u00b0 \u0125", "raw_count": 252825844, "count": 252825844, "decode_str": "\u8c03"} -{"id": 6238, "token": "\u00ef\u00bc\u012e", "merges": "\u00ef\u00bc \u012e", "raw_count": 253132768, "count": 253132768, "decode_str": "\uff0c"} -{"id": 50408, "token": "\u00e4\u00b8\u0135", "merges": "\u00e4\u00b8 \u0135", "raw_count": 253601701, "count": 253601701, "decode_str": "\u4e13"} -{"id": 51535, "token": "\u00e5\u00b8\u00a6", "merges": "\u00e5\u00b8 \u00a6", "raw_count": 253686168, "count": 253686168, "decode_str": "\u5e26"} -{"id": 51524, "token": "\u00e5\u00b8\u012a", "merges": "\u00e5\u00b8 \u012a", "raw_count": 254259284, "count": 254259284, "decode_str": "\u5e08"} -{"id": 43741, "token": "\u00e6\u00b1\u0124", "merges": "\u00e6\u00b1 \u0124", "raw_count": 254633404, "count": 254633404, "decode_str": "\u6c42"} -{"id": 51835, "token": "\u00e6\u012b\u012f", "merges": "\u00e6\u012b \u012f", "raw_count": 255807018, "count": 255807018, "decode_str": "\u624d"} -{"id": 52067, "token": "\u00e6\u0137\u012a", "merges": "\u00e6\u0137 \u012a", "raw_count": 256853830, "count": 256853830, "decode_str": "\u6548"} -{"id": 53756, "token": "\u00e8\u00a7\u0126", "merges": "\u00e8\u00a7 \u0126", "raw_count": 257324911, "count": 257324911, "decode_str": "\u89c4"} -{"id": 51415, "token": "\u00e5\u00ae\u00a2", "merges": "\u00e5\u00ae \u00a2", "raw_count": 257559604, "count": 257559604, "decode_str": "\u5ba2"} -{"id": 51328, "token": "\u00e5\u00a5\u00b9", "merges": "\u00e5\u00a5 \u00b9", "raw_count": 257596561, "count": 257596561, "decode_str": "\u5979"} -{"id": 37215, "token": "\u00e9\u00bb", "merges": "\u00e9 \u00bb", "raw_count": 796560, "count": 257808422, "decode_str": "\ufffd"} -{"id": 53353, "token": "\u00e7\u00bb\u0141", "merges": "\u00e7\u00bb \u0141", "raw_count": 258850272, "count": 258850272, "decode_str": "\u7edf"} -{"id": 43368, "token": "\u00e5\u0131\u0139", "merges": "\u00e5\u0131 \u0139", "raw_count": 259408984, "count": 259408984, "decode_str": "\u53d7"} -{"id": 49037, "token": "\u00e9\u0122\u012b", "merges": "\u00e9\u0122 \u012b", "raw_count": 264247181, "count": 264247181, "decode_str": "\u9009"} -{"id": 52199, "token": "\u00e6\u013e\u00af", "merges": "\u00e6\u013e \u00af", "raw_count": 264340965, "count": 264340965, "decode_str": "\u672f"} -{"id": 49521, "token": "\u00e8\u00b7\u00af", "merges": "\u00e8\u00b7 \u00af", "raw_count": 264939351, "count": 264939351, "decode_str": "\u8def"} -{"id": 37657, "token": "\u00e5\u012f\u0123", "merges": "\u00e5\u012f \u0123", "raw_count": 265167328, "count": 265167328, "decode_str": "\u5341"} -{"id": 48561, "token": "\u00e7\u013e\u0141", "merges": "\u00e7\u013e \u0141", "raw_count": 265436516, "count": 265436516, "decode_str": "\u771f"} -{"id": 50458, "token": "\u00e4\u00b9\u00b0", "merges": "\u00e4\u00b9 \u00b0", "raw_count": 266018726, "count": 266018726, "decode_str": "\u4e70"} -{"id": 44002, "token": "\u00e5\u0131\u00a3", "merges": "\u00e5\u0131 \u00a3", "raw_count": 266061524, "count": 266061524, "decode_str": "\u53e3"} -{"id": 254, "token": "er", "merges": "e r", "raw_count": 5153085, "count": 266167677, "decode_str": "er"} -{"id": 54463, "token": "\u00e9\u00a3\u0130", "merges": "\u00e9\u00a3 \u0130", "raw_count": 266363714, "count": 266363714, "decode_str": "\u98ce"} -{"id": 520, "token": "01", "merges": "0 1", "raw_count": 9922222, "count": 266896669, "decode_str": "01"} -{"id": 52595, "token": "\u00e6\u00b5\u00b7", "merges": "\u00e6\u00b5 \u00b7", "raw_count": 266907979, "count": 266907979, "decode_str": "\u6d77"} -{"id": 43216, "token": "\u00e5\u0127\u012a", "merges": "\u00e5\u0127 \u012a", "raw_count": 267615918, "count": 267615918, "decode_str": "\u5148"} -{"id": 44573, "token": "\u00e4\u00bb\u00bb", "merges": "\u00e4\u00bb \u00bb", "raw_count": 268906481, "count": 268906481, "decode_str": "\u4efb"} -{"id": 39673, "token": "\u00e5\u0130\u0141", "merges": "\u00e5\u0130 \u0141", "raw_count": 269329082, "count": 269329082, "decode_str": "\u539f"} -{"id": 50939, "token": "\u00e5\u0131\u00b0", "merges": "\u00e5\u0131 \u00b0", "raw_count": 270782756, "count": 270782756, "decode_str": "\u53f0"} -{"id": 50404, "token": "\u00e4\u00b8\u0129", "merges": "\u00e4\u00b8 \u0129", "raw_count": 271296630, "count": 271296630, "decode_str": "\u4e07"} -{"id": 50952, "token": "\u00e5\u0132\u0126", "merges": "\u00e5\u0132 \u0126", "raw_count": 271502731, "count": 271502731, "decode_str": "\u5404"} -{"id": 54075, "token": "\u00e8\u00bf\u0132", "merges": "\u00e8\u00bf \u0132", "raw_count": 272180309, "count": 272180309, "decode_str": "\u8fd0"} -{"id": 34744, "token": "\u00e4\u00ba\u012e", "merges": "\u00e4\u00ba \u012e", "raw_count": 272291725, "count": 272291725, "decode_str": "\u4e8c"} -{"id": 45683, "token": "\u00e6\u0142\u00bc", "merges": "\u00e6\u0142 \u00bc", "raw_count": 272688722, "count": 272688722, "decode_str": "\u683c"} -{"id": 90, "token": "y", "merges": "NULL", "raw_count": 13493753, "count": 273611444, "decode_str": "y"} -{"id": 54631, "token": "\u00e3\u0122\u00be", "merges": "\u00e3\u0122 \u00be", "raw_count": 274209082, "count": 274209082, "decode_str": " "} -{"id": 30, "token": "=", "merges": "NULL", "raw_count": 56495557, "count": 275240377, "decode_str": "="} -{"id": 38155, "token": "\u00e5\u0132\u0133", "merges": "\u00e5\u0132 \u0133", "raw_count": 275806061, "count": 275806061, "decode_str": "\u5411"} -{"id": 50780, "token": "\u00e5\u012a\u00ab", "merges": "\u00e5\u012a \u00ab", "raw_count": 277225316, "count": 277225316, "decode_str": "\u522b"} -{"id": 30420, "token": "\u00e7\u00a4\u00ba", "merges": "\u00e7\u00a4 \u00ba", "raw_count": 277435108, "count": 277435108, "decode_str": "\u793a"} -{"id": 50037, "token": "\u00e4\u00ba\u00a4", "merges": "\u00e4\u00ba \u00a4", "raw_count": 278191248, "count": 278191248, "decode_str": "\u4ea4"} -{"id": 49218, "token": "\u00e5\u0128\u012f", "merges": "\u00e5\u0128 \u012f", "raw_count": 279345811, "count": 279345811, "decode_str": "\u518d"} -{"id": 29440, "token": "\u00e4\u00bb\u00a3", "merges": "\u00e4\u00bb \u00a3", "raw_count": 279971173, "count": 279971173, "decode_str": "\u4ee3"} -{"id": 45882, "token": "\u00e6\u0136\u00be", "merges": "\u00e6\u0136 \u00be", "raw_count": 280013644, "count": 280013644, "decode_str": "\u653e"} -{"id": 51862, "token": "\u00e6\u012c\u0122", "merges": "\u00e6\u012c \u0122", "raw_count": 280315647, "count": 280315647, "decode_str": "\u6280"} -{"id": 53332, "token": "\u00e7\u00ba\u00bf", "merges": "\u00e7\u00ba \u00bf", "raw_count": 280321870, "count": 280321870, "decode_str": "\u7ebf"} -{"id": 51882, "token": "\u00e6\u012c\u00a5", "merges": "\u00e6\u012c \u00a5", "raw_count": 280405374, "count": 280405374, "decode_str": "\u62a5"} -{"id": 43799, "token": "\u00e7\u00bb\u0135", "merges": "\u00e7\u00bb \u0135", "raw_count": 280472795, "count": 280472795, "decode_str": "\u7ed3"} -{"id": 44692, "token": "\u00e7\u0136\u00b1", "merges": "\u00e7\u0136 \u00b1", "raw_count": 280853548, "count": 280853548, "decode_str": "\u7531"} -{"id": 32120, "token": "\u00e5\u0140", "merges": "\u00e5 \u0140", "raw_count": 848979, "count": 281367384, "decode_str": "\ufffd"} -{"id": 53937, "token": "\u00e8\u00b4\u00b9", "merges": "\u00e8\u00b4 \u00b9", "raw_count": 282495322, "count": 282495322, "decode_str": "\u8d39"} -{"id": 53150, "token": "\u00e7\u00a7\u0133", "merges": "\u00e7\u00a7 \u0133", "raw_count": 282560734, "count": 282560734, "decode_str": "\u79d1"} -{"id": 54063, "token": "\u00e8\u00be\u00b9", "merges": "\u00e8\u00be \u00b9", "raw_count": 284960639, "count": 284960639, "decode_str": "\u8fb9"} -{"id": 53469, "token": "\u00e8\u0123\u0136", "merges": "\u00e8\u0123 \u0136", "raw_count": 285391065, "count": 285391065, "decode_str": "\u8054"} -{"id": 53824, "token": "\u00e8\u00af\u013f", "merges": "\u00e8\u00af \u013f", "raw_count": 285718289, "count": 285718289, "decode_str": "\u8bdd"} -{"id": 51302, "token": "\u00e5\u00a4\u00b4", "merges": "\u00e5\u00a4 \u00b4", "raw_count": 286898686, "count": 286898686, "decode_str": "\u5934"} -{"id": 51614, "token": "\u00e5\u00bc\u00ba", "merges": "\u00e5\u00bc \u00ba", "raw_count": 287084208, "count": 287084208, "decode_str": "\u5f3a"} -{"id": 53443, "token": "\u00e8\u0122\u0123", "merges": "\u00e8\u0122 \u0123", "raw_count": 287709365, "count": 287709365, "decode_str": "\u8001"} -{"id": 50391, "token": "\u00e3\u0122\u012d", "merges": "\u00e3\u0122 \u012d", "raw_count": 288016248, "count": 288016248, "decode_str": "\u300b"} -{"id": 50390, "token": "\u00e3\u0122\u012c", "merges": "\u00e3\u0122 \u012c", "raw_count": 288077878, "count": 288077878, "decode_str": "\u300a"} -{"id": 41140, "token": "\u00e5\u0141\u00ba", "merges": "\u00e5\u0141 \u00ba", "raw_count": 288666919, "count": 288666919, "decode_str": "\u57fa"} -{"id": 250, "token": "re", "merges": "r e", "raw_count": 4527511, "count": 289468323, "decode_str": "re"} -{"id": 44020, "token": "\u00e7\u00a6", "merges": "\u00e7 \u00a6", "raw_count": 318456, "count": 289499185, "decode_str": "\ufffd"} -{"id": 44673, "token": "\u00e8\u00af\u00b7", "merges": "\u00e8\u00af \u00b7", "raw_count": 290690822, "count": 290690822, "decode_str": "\u8bf7"} -{"id": 48604, "token": "\u00e9\u00aa", "merges": "\u00e9 \u00aa", "raw_count": 484095, "count": 292365232, "decode_str": "\ufffd"} -{"id": 46461, "token": "\u00e8\u012b\u00b2", "merges": "\u00e8\u012b \u00b2", "raw_count": 292806743, "count": 292806743, "decode_str": "\u8272"} -{"id": 45508, "token": "\u00e5\u00b0\u0133", "merges": "\u00e5\u00b0 \u0133", "raw_count": 294152696, "count": 294152696, "decode_str": "\u5c11"} -{"id": 32130, "token": "\u00e6\u012f\u00ae", "merges": "\u00e6\u012f \u00ae", "raw_count": 199924967, "count": 295237237, "decode_str": "\u636e"} -{"id": 46239, "token": "\u00e7\u013d\u00b4", "merges": "\u00e7\u013d \u00b4", "raw_count": 296474628, "count": 296474628, "decode_str": "\u76f4"} -{"id": 53733, "token": "\u00e8\u00a3\u0127", "merges": "\u00e8\u00a3 \u0127", "raw_count": 296665518, "count": 296665518, "decode_str": "\u88c5"} -{"id": 50039, "token": "\u00e6\u00b5\u0123", "merges": "\u00e6\u00b5 \u0123", "raw_count": 296942397, "count": 296942397, "decode_str": "\u6d41"} -{"id": 51286, "token": "\u00e5\u00a4\u0126", "merges": "\u00e5\u00a4 \u0126", "raw_count": 297577070, "count": 297577070, "decode_str": "\u5904"} -{"id": 51839, "token": "\u00e6\u012b\u0135", "merges": "\u00e6\u012b \u0135", "raw_count": 297877529, "count": 297877529, "decode_str": "\u6253"} -{"id": 67, "token": "b", "merges": "NULL", "raw_count": 21561457, "count": 299702919, "decode_str": "b"} -{"id": 251, "token": "on", "merges": "o n", "raw_count": 5315922, "count": 299781675, "decode_str": "on"} -{"id": 40162, "token": "\u00e7\u0139", "merges": "\u00e7 \u0139", "raw_count": 114082, "count": 304891127, "decode_str": "\ufffd"} -{"id": 51083, "token": "\u00e5\u0137\u0128", "merges": "\u00e5\u0137 \u0128", "raw_count": 305899475, "count": 305899475, "decode_str": "\u5546"} -{"id": 52447, "token": "\u00e6\u00b0\u0136", "merges": "\u00e6\u00b0 \u0136", "raw_count": 307671091, "count": 307671091, "decode_str": "\u6c14"} -{"id": 23366, "token": "\u00e4\u00bb\u00b6", "merges": "\u00e4\u00bb \u00b6", "raw_count": 281749087, "count": 307699735, "decode_str": "\u4ef6"} -{"id": 54273, "token": "\u00e9\u0139\u00a8", "merges": "\u00e9\u0139 \u00a8", "raw_count": 310221992, "count": 310221992, "decode_str": "\u95e8"} -{"id": 41873, "token": "\u00e8\u00a2\u00ab", "merges": "\u00e8\u00a2 \u00ab", "raw_count": 311454875, "count": 311454875, "decode_str": "\u88ab"} -{"id": 53787, "token": "\u00e8\u00ae\u00a9", "merges": "\u00e8\u00ae \u00a9", "raw_count": 316102506, "count": 316102506, "decode_str": "\u8ba9"} -{"id": 37661, "token": "\u00e7\u00bc", "merges": "\u00e7 \u00bc", "raw_count": 1190056, "count": 317966203, "decode_str": "\ufffd"} -{"id": 44360, "token": "\u00e6\u0136\u00bf", "merges": "\u00e6\u0136 \u00bf", "raw_count": 320301256, "count": 320301256, "decode_str": "\u653f"} -{"id": 30077, "token": "\u00e5\u00bc\u0131", "merges": "\u00e5\u00bc \u0131", "raw_count": 322766827, "count": 322766827, "decode_str": "\u5f0f"} -{"id": 33273, "token": "\u00e8\u00a7\u00a3", "merges": "\u00e8\u00a7 \u00a3", "raw_count": 323630193, "count": 323630193, "decode_str": "\u89e3"} -{"id": 53922, "token": "\u00e8\u00b4\u00a8", "merges": "\u00e8\u00b4 \u00a8", "raw_count": 324633677, "count": 324633677, "decode_str": "\u8d28"} -{"id": 51070, "token": "\u00e5\u0135\u00a6", "merges": "\u00e5\u0135 \u00a6", "raw_count": 325615998, "count": 325615998, "decode_str": "\u54e6"} -{"id": 36820, "token": "\u00e6\u012e\u0123", "merges": "\u00e6\u012e \u0123", "raw_count": 327461812, "count": 327461812, "decode_str": "\u6301"} -{"id": 31949, "token": "\u00e7\u00a8\u012d", "merges": "\u00e7\u00a8 \u012d", "raw_count": 327860224, "count": 327860224, "decode_str": "\u7a0b"} -{"id": 37208, "token": "\u00e5\u012a\u00a9", "merges": "\u00e5\u012a \u00a9", "raw_count": 329895369, "count": 329895369, "decode_str": "\u5229"} -{"id": 36114, "token": "\u00e7\u012b\u00b9", "merges": "\u00e7\u012b \u00b9", "raw_count": 330023098, "count": 330023098, "decode_str": "\u7279"} -{"id": 52390, "token": "\u00e6\u00ac\u00be", "merges": "\u00e6\u00ac \u00be", "raw_count": 331169553, "count": 331169553, "decode_str": "\u6b3e"} -{"id": 28610, "token": "\u00e5\u0132\u012f", "merges": "\u00e5\u0132 \u012f", "raw_count": 331208496, "count": 331208496, "decode_str": "\u540d"} -{"id": 38822, "token": "\u00e8\u0125", "merges": "\u00e8 \u0125", "raw_count": 288601, "count": 334055374, "decode_str": "\ufffd"} -{"id": 50415, "token": "\u00e4\u00b8\u013e", "merges": "\u00e4\u00b8 \u013e", "raw_count": 335047885, "count": 335047885, "decode_str": "\u4e1c"} -{"id": 37542, "token": "\u00e6\u012a\u0138", "merges": "\u00e6\u012a \u0138", "raw_count": 335355501, "count": 335355501, "decode_str": "\u6216"} -{"id": 50945, "token": "\u00e5\u0131\u00b8", "merges": "\u00e5\u0131 \u00b8", "raw_count": 336222870, "count": 336222870, "decode_str": "\u53f8"} -{"id": 35072, "token": "\u00e6\u00a1", "merges": "\u00e6 \u00a1", "raw_count": 238434, "count": 336740576, "decode_str": "\ufffd"} -{"id": 51512, "token": "\u00e5\u00b7\u00b1", "merges": "\u00e5\u00b7 \u00b1", "raw_count": 337157178, "count": 337157178, "decode_str": "\u5df1"} -{"id": 45748, "token": "\u00e8\u00ba\u00ab", "merges": "\u00e8\u00ba \u00ab", "raw_count": 338610896, "count": 338610896, "decode_str": "\u8eab"} -{"id": 44114, "token": "\u00e5\u0127\u0125", "merges": "\u00e5\u0127 \u0125", "raw_count": 339741249, "count": 339741249, "decode_str": "\u5143"} -{"id": 50484, "token": "\u00e4\u00ba\u00b2", "merges": "\u00e4\u00ba \u00b2", "raw_count": 340288044, "count": 340288044, "decode_str": "\u4eb2"} -{"id": 50515, "token": "\u00e4\u00bb\u00b7", "merges": "\u00e4\u00bb \u00b7", "raw_count": 340773343, "count": 340773343, "decode_str": "\u4ef7"} -{"id": 20557, "token": "\u00e7\u00b4", "merges": "\u00e7 \u00b4", "raw_count": 79611, "count": 340774146, "decode_str": "\ufffd"} -{"id": 46356, "token": "\u00e6\u00b0\u0133", "merges": "\u00e6\u00b0 \u0133", "raw_count": 341116524, "count": 341116524, "decode_str": "\u6c11"} -{"id": 50646, "token": "\u00e5\u0123\u013c", "merges": "\u00e5\u0123 \u013c", "raw_count": 341894253, "count": 341894253, "decode_str": "\u505a"} -{"id": 50420, "token": "\u00e4\u00b8\u00a4", "merges": "\u00e4\u00b8 \u00a4", "raw_count": 343601313, "count": 343601313, "decode_str": "\u4e24"} -{"id": 43641, "token": "\u00e8\u0126", "merges": "\u00e8 \u0126", "raw_count": 128052, "count": 344882966, "decode_str": "\ufffd"} -{"id": 34609, "token": "\u00e7\u0141\u00a5", "merges": "\u00e7\u0141 \u00a5", "raw_count": 344967931, "count": 344967931, "decode_str": "\u77e5"} -{"id": 48078, "token": "\u00e7\u0123", "merges": "\u00e7 \u0123", "raw_count": 54426, "count": 345590600, "decode_str": "\ufffd"} -{"id": 49873, "token": "\u00e6\u0137\u013b", "merges": "\u00e6\u0137 \u013b", "raw_count": 345690567, "count": 345690567, "decode_str": "\u6559"} -{"id": 40843, "token": "\u00e9\u00a6", "merges": "\u00e9 \u00a6", "raw_count": 334736, "count": 346399929, "decode_str": "\ufffd"} -{"id": 249, "token": "in", "merges": "i n", "raw_count": 11297348, "count": 347738929, "decode_str": "in"} -{"id": 53781, "token": "\u00e8\u00ae\u00a1", "merges": "\u00e8\u00ae \u00a1", "raw_count": 348090545, "count": 348090545, "decode_str": "\u8ba1"} -{"id": 36087, "token": "\u00e6\u00b7", "merges": "\u00e6 \u00b7", "raw_count": 247393, "count": 348127250, "decode_str": "\ufffd"} -{"id": 361, "token": "00", "merges": "0 0", "raw_count": 41238426, "count": 349325986, "decode_str": "00"} -{"id": 26844, "token": "\u00e7\u00b1", "merges": "\u00e7 \u00b1", "raw_count": 143322, "count": 349610128, "decode_str": "\ufffd"} -{"id": 38011, "token": "\u00e6\u0126\u0141", "merges": "\u00e6\u0126 \u0141", "raw_count": 350958516, "count": 350958516, "decode_str": "\u611f"} -{"id": 15531, "token": "\u00e6\u0137\u00b0", "merges": "\u00e6\u0137 \u00b0", "raw_count": 258219171, "count": 353531441, "decode_str": "\u6570"} -{"id": 24893, "token": "\u00e7\u00ac\u00ac", "merges": "\u00e7\u00ac \u00ac", "raw_count": 354032551, "count": 354032551, "decode_str": "\u7b2c"} -{"id": 53921, "token": "\u00e8\u00b4\u00a7", "merges": "\u00e8\u00b4 \u00a7", "raw_count": 354442649, "count": 354442649, "decode_str": "\u8d27"} -{"id": 48153, "token": "\u00e7\u00b2", "merges": "\u00e7 \u00b2", "raw_count": 179762, "count": 354459464, "decode_str": "\ufffd"} -{"id": 41085, "token": "\u00e9\u013e\u0122", "merges": "\u00e9\u013e \u0122", "raw_count": 122741000, "count": 354837114, "decode_str": "\u9700"} -{"id": 28917, "token": "\u00e5\u00a3", "merges": "\u00e5 \u00a3", "raw_count": 62970, "count": 355171922, "decode_str": "\ufffd"} -{"id": 39393, "token": "\u00e7\u0138", "merges": "\u00e7 \u0138", "raw_count": 375333, "count": 356408890, "decode_str": "\ufffd"} -{"id": 39429, "token": "\u00e5\u0138", "merges": "\u00e5 \u0138", "raw_count": 360065, "count": 356521578, "decode_str": "\ufffd"} -{"id": 43873, "token": "\u00e6\u0143\u00a4", "merges": "\u00e6\u0143 \u00a4", "raw_count": 357064438, "count": 357064438, "decode_str": "\u6b64"} -{"id": 42843, "token": "\u00e5\u00b9\u00b6", "merges": "\u00e5\u00b9 \u00b6", "raw_count": 359183359, "count": 359183359, "decode_str": "\u5e76"} -{"id": 49616, "token": "\u00e6\u013e\u012f", "merges": "\u00e6\u013e \u012f", "raw_count": 361233793, "count": 361233793, "decode_str": "\u670d"} -{"id": 53412, "token": "\u00e7\u00bd\u0133", "merges": "\u00e7\u00bd \u0133", "raw_count": 362125055, "count": 362125055, "decode_str": "\u7f51"} -{"id": 51680, "token": "\u00e5\u00bf\u00ab", "merges": "\u00e5\u00bf \u00ab", "raw_count": 363047691, "count": 363047691, "decode_str": "\u5feb"} -{"id": 26270, "token": "\u00e5\u013d\u0140", "merges": "\u00e5\u013d \u0140", "raw_count": 365136236, "count": 365136236, "decode_str": "\u56de"} -{"id": 41777, "token": "\u00e8\u00ba", "merges": "\u00e8 \u00ba", "raw_count": 119278, "count": 365357944, "decode_str": "\ufffd"} -{"id": 34372, "token": "\u00e8\u012a", "merges": "\u00e8 \u012a", "raw_count": 228414, "count": 366015298, "decode_str": "\ufffd"} -{"id": 46549, "token": "\u00e6\u00b4\u00bb", "merges": "\u00e6\u00b4 \u00bb", "raw_count": 366356258, "count": 366356258, "decode_str": "\u6d3b"} -{"id": 49835, "token": "\u00e7\u00a1", "merges": "\u00e7 \u00a1", "raw_count": 641996, "count": 366377333, "decode_str": "\ufffd"} -{"id": 46987, "token": "\u00e5\u0131\u00aa", "merges": "\u00e5\u0131 \u00aa", "raw_count": 367097182, "count": 367097182, "decode_str": "\u53ea"} -{"id": 44084, "token": "\u00e5\u00b9\u00b3", "merges": "\u00e5\u00b9 \u00b3", "raw_count": 368971973, "count": 368971973, "decode_str": "\u5e73"} -{"id": 33474, "token": "\u00e6\u0130\u00a5", "merges": "\u00e6\u0130 \u00a5", "raw_count": 369096031, "count": 369096031, "decode_str": "\u63a5"} -{"id": 54451, "token": "\u00e9\u00a2\u013a", "merges": "\u00e9\u00a2 \u013a", "raw_count": 369690884, "count": 369690884, "decode_str": "\u9898"} -{"id": 50999, "token": "\u00e5\u0133\u013a", "merges": "\u00e5\u0133 \u013a", "raw_count": 371303025, "count": 371303025, "decode_str": "\u5458"} -{"id": 50488, "token": "\u00e4\u00bb\u0122", "merges": "\u00e4\u00bb \u0122", "raw_count": 374967796, "count": 374967796, "decode_str": "\u4ec0"} -{"id": 48584, "token": "\u00e5\u00b7\u00b2", "merges": "\u00e5\u00b7 \u00b2", "raw_count": 375516390, "count": 375516390, "decode_str": "\u5df2"} -{"id": 24160, "token": "\u00e8\u00a1\u00a8", "merges": "\u00e8\u00a1 \u00a8", "raw_count": 377653228, "count": 377653228, "decode_str": "\u8868"} -{"id": 22160, "token": "\u00e4\u00bd\u00bf", "merges": "\u00e4\u00bd \u00bf", "raw_count": 171490340, "count": 378129583, "decode_str": "\u4f7f"} -{"id": 46419, "token": "\u00e7\u00ae\u00a1", "merges": "\u00e7\u00ae \u00a1", "raw_count": 378438865, "count": 378438865, "decode_str": "\u7ba1"} -{"id": 41197, "token": "\u00e6\u0125\u00b3", "merges": "\u00e6\u0125 \u00b3", "raw_count": 384512760, "count": 384512760, "decode_str": "\u60f3"} -{"id": 36666, "token": "\u00e4\u00bd\u012f", "merges": "\u00e4\u00bd \u012f", "raw_count": 385815509, "count": 385815509, "decode_str": "\u4f4d"} -{"id": 38053, "token": "\u00e8\u00a2", "merges": "\u00e8 \u00a2", "raw_count": 165500, "count": 386557622, "decode_str": "\ufffd"} -{"id": 32165, "token": "\u00e4\u00bf\u00a1", "merges": "\u00e4\u00bf \u00a1", "raw_count": 391947030, "count": 391947030, "decode_str": "\u4fe1"} -{"id": 50497, "token": "\u00e4\u00bb\u0130", "merges": "\u00e4\u00bb \u0130", "raw_count": 392183895, "count": 392183895, "decode_str": "\u4ece"} -{"id": 28154, "token": "\u00e7\u013d\u00ae", "merges": "\u00e7\u013d \u00ae", "raw_count": 392206421, "count": 392206421, "decode_str": "\u76ee"} -{"id": 52063, "token": "\u00e6\u0136\u00b6", "merges": "\u00e6\u0136 \u00b6", "raw_count": 393020028, "count": 393020028, "decode_str": "\u6536"} -{"id": 30088, "token": "\u00e9\u0127", "merges": "\u00e9 \u0127", "raw_count": 390275, "count": 394642527, "decode_str": "\ufffd"} -{"id": 32313, "token": "\u00e7\u013d\u00b8", "merges": "\u00e7\u013d \u00b8", "raw_count": 395183738, "count": 395183738, "decode_str": "\u76f8"} -{"id": 53426, "token": "\u00e7\u00be\u0130", "merges": "\u00e7\u00be \u0130", "raw_count": 395497640, "count": 395497640, "decode_str": "\u7f8e"} -{"id": 32594, "token": "\u00e6\u0143\u00a3", "merges": "\u00e6\u0143 \u00a3", "raw_count": 395680906, "count": 395680906, "decode_str": "\u6b63"} -{"id": 36168, "token": "\u00e4\u00b8\u012b", "merges": "\u00e4\u00b8 \u012b", "raw_count": 396069771, "count": 396069771, "decode_str": "\u4e09"} -{"id": 54020, "token": "\u00e8\u00bd\u00a6", "merges": "\u00e8\u00bd \u00a6", "raw_count": 398069360, "count": 398069360, "decode_str": "\u8f66"} -{"id": 14, "token": "-", "merges": "NULL", "raw_count": 263514617, "count": 398431683, "decode_str": "-"} -{"id": 44126, "token": "\u00e7\u00b3\u00bb", "merges": "\u00e7\u00b3 \u00bb", "raw_count": 399877105, "count": 399877105, "decode_str": "\u7cfb"} -{"id": 40951, "token": "\u00e4\u00ba\u013d", "merges": "\u00e4\u00ba \u013d", "raw_count": 402676959, "count": 402676959, "decode_str": "\u4e9b"} -{"id": 29626, "token": "\u00e8\u00a3", "merges": "\u00e8 \u00a3", "raw_count": 285303, "count": 402815168, "decode_str": "\ufffd"} -{"id": 36548, "token": "\u00e5\u00b8\u00b8", "merges": "\u00e5\u00b8 \u00b8", "raw_count": 403583161, "count": 403583161, "decode_str": "\u5e38"} -{"id": 40658, "token": "\u00e5\u0131\u012c", "merges": "\u00e5\u0131 \u012c", "raw_count": 404916296, "count": 404916296, "decode_str": "\u53ca"} -{"id": 38672, "token": "\u00e8\u012d", "merges": "\u00e8 \u012d", "raw_count": 430200, "count": 408256808, "decode_str": "\ufffd"} -{"id": 51002, "token": "\u00e5\u0133\u00a2", "merges": "\u00e5\u0133 \u00a2", "raw_count": 410055778, "count": 410055778, "decode_str": "\u5462"} -{"id": 42205, "token": "\u00e8\u00ae\u00be", "merges": "\u00e8\u00ae \u00be", "raw_count": 410523351, "count": 410523351, "decode_str": "\u8bbe"} -{"id": 34179, "token": "\u00e5\u012a\u00b6", "merges": "\u00e5\u012a \u00b6", "raw_count": 411233902, "count": 411233902, "decode_str": "\u5236"} -{"id": 50963, "token": "\u00e5\u0132\u0139", "merges": "\u00e5\u0132 \u0139", "raw_count": 411348117, "count": 411348117, "decode_str": "\u5417"} -{"id": 23956, "token": "\u00e7\u0137", "merges": "\u00e7 \u0137", "raw_count": 475424, "count": 413792428, "decode_str": "\ufffd"} -{"id": 44075, "token": "\u00e6\u00af\u0136", "merges": "\u00e6\u00af \u0136", "raw_count": 414162649, "count": 414162649, "decode_str": "\u6bd4"} -{"id": 23373, "token": "\u00e5\u0127\u00a5", "merges": "\u00e5\u0127 \u00a5", "raw_count": 414462805, "count": 414462805, "decode_str": "\u5165"} -{"id": 34389, "token": "\u00e7\u012b\u00a9", "merges": "\u00e7\u012b \u00a9", "raw_count": 414883690, "count": 414883690, "decode_str": "\u7269"} -{"id": 37769, "token": "\u00e7\u00a5", "merges": "\u00e7 \u00a5", "raw_count": 231028, "count": 415951592, "decode_str": "\ufffd"} -{"id": 29687, "token": "\u00e6\u013a\u0130", "merges": "\u00e6\u013a \u0130", "raw_count": 416266925, "count": 416266925, "decode_str": "\u660e"} -{"id": 43300, "token": "\u00e4\u00bd\u0128", "merges": "\u00e4\u00bd \u0128", "raw_count": 417640861, "count": 417640861, "decode_str": "\u4f46"} -{"id": 28, "token": ";", "merges": "NULL", "raw_count": 388868097, "count": 417696694, "decode_str": ";"} -{"id": 42025, "token": "\u00e7\u012a", "merges": "\u00e7 \u012a", "raw_count": 143592, "count": 417875933, "decode_str": "\ufffd"} -{"id": 38001, "token": "\u00e9\u0129\u0133", "merges": "\u00e9\u0129 \u0133", "raw_count": 422269395, "count": 422269395, "decode_str": "\u91d1"} -{"id": 43929, "token": "\u00e6\u0142\u00b7", "merges": "\u00e6\u0142 \u00b7", "raw_count": 423133128, "count": 423133128, "decode_str": "\u6837"} -{"id": 49288, "token": "\u00e7\u00a7\u012f", "merges": "\u00e7\u00a7 \u012f", "raw_count": 423287838, "count": 423287838, "decode_str": "\u79cd"} -{"id": 51490, "token": "\u00e5\u00b1\u0137", "merges": "\u00e5\u00b1 \u0137", "raw_count": 424271461, "count": 424271461, "decode_str": "\u5c55"} -{"id": 34175, "token": "\u00e6\u013e\u0141", "merges": "\u00e6\u013e \u0141", "raw_count": 424905468, "count": 424905468, "decode_str": "\u671f"} -{"id": 50858, "token": "\u00e5\u012e\u00ba", "merges": "\u00e5\u012e \u00ba", "raw_count": 426201310, "count": 426201310, "decode_str": "\u533a"} -{"id": 27374, "token": "\u00e7\u0142", "merges": "\u00e7 \u0142", "raw_count": 630175, "count": 429112335, "decode_str": "\ufffd"} -{"id": 47029, "token": "\u00e6\u0139\u0142", "merges": "\u00e6\u0139 \u0142", "raw_count": 430248608, "count": 430248608, "decode_str": "\u65e0"} -{"id": 33859, "token": "\u00e6\u013d\u00b4", "merges": "\u00e6\u013d \u00b4", "raw_count": 431149822, "count": 431149822, "decode_str": "\u66f4"} -{"id": 36361, "token": "\u00e5\u00ba\u0136", "merges": "\u00e5\u00ba \u0136", "raw_count": 431351905, "count": 431351905, "decode_str": "\u5e94"} -{"id": 44006, "token": "\u00e5\u012f\u0137", "merges": "\u00e5\u012f \u0137", "raw_count": 432068574, "count": 432068574, "decode_str": "\u5355"} -{"id": 45008, "token": "\u00e5\u012c\u00a1", "merges": "\u00e5\u012c \u00a1", "raw_count": 432090422, "count": 432090422, "decode_str": "\u52a1"} -{"id": 36213, "token": "\u00e5\u013d\u0142", "merges": "\u00e5\u013d \u0142", "raw_count": 432793462, "count": 432793462, "decode_str": "\u56e0"} -{"id": 39859, "token": "\u00e8\u00b5\u00b7", "merges": "\u00e8\u00b5 \u00b7", "raw_count": 432860310, "count": 432860310, "decode_str": "\u8d77"} -{"id": 35241, "token": "\u00e6\u00ac\u00a1", "merges": "\u00e6\u00ac \u00a1", "raw_count": 433840641, "count": 433840641, "decode_str": "\u6b21"} -{"id": 35489, "token": "\u00e5\u00a4\u0138", "merges": "\u00e5\u00a4 \u0138", "raw_count": 434718869, "count": 434718869, "decode_str": "\u5916"} -{"id": 53347, "token": "\u00e7\u00bb\u013b", "merges": "\u00e7\u00bb \u013b", "raw_count": 435718716, "count": 435718716, "decode_str": "\u7ed9"} -{"id": 26354, "token": "\u00e6\u0140\u013e", "merges": "\u00e6\u0140 \u013e", "raw_count": 240979288, "count": 437249426, "decode_str": "\u679c"} -{"id": 29785, "token": "\u00e6\u0123", "merges": "\u00e6 \u0123", "raw_count": 365111, "count": 441530110, "decode_str": "\ufffd"} -{"id": 40309, "token": "\u00e5\u00bb\u00ba", "merges": "\u00e5\u00bb \u00ba", "raw_count": 443550637, "count": 443550637, "decode_str": "\u5efa"} -{"id": 24, "token": "7", "merges": "NULL", "raw_count": 126970491, "count": 443590845, "decode_str": "7"} -{"id": 53946, "token": "\u00e8\u00b5\u0126", "merges": "\u00e8\u00b5 \u0126", "raw_count": 444853540, "count": 444853540, "decode_str": "\u8d44"} -{"id": 20855, "token": "\u00e6\u0138\u0129", "merges": "\u00e6\u0138 \u0129", "raw_count": 420642405, "count": 446593053, "decode_str": "\u6587"} -{"id": 38028, "token": "\u00e5\u00ae\u012b", "merges": "\u00e5\u00ae \u012b", "raw_count": 447462323, "count": 447462323, "decode_str": "\u5b89"} -{"id": 34693, "token": "\u00e5\u00a2", "merges": "\u00e5 \u00a2", "raw_count": 111985, "count": 448424188, "decode_str": "\ufffd"} -{"id": 26772, "token": "\u00e5\u00bd\u0135", "merges": "\u00e5\u00bd \u0135", "raw_count": 451119901, "count": 451119901, "decode_str": "\u5f53"} -{"id": 29554, "token": "\u00e6\u012b\u012d", "merges": "\u00e6\u012b \u012d", "raw_count": 451967837, "count": 451967837, "decode_str": "\u624b"} -{"id": 51187, "token": "\u00e5\u013e\u00ba", "merges": "\u00e5\u013e \u00ba", "raw_count": 452900159, "count": 452900159, "decode_str": "\u573a"} -{"id": 37079, "token": "\u00e9\u0129\u0131", "merges": "\u00e9\u0129 \u0131", "raw_count": 453106719, "count": 453106719, "decode_str": "\u91cf"} -{"id": 28215, "token": "\u00e7\u00a9", "merges": "\u00e7 \u00a9", "raw_count": 234252, "count": 454558132, "decode_str": "\ufffd"} -{"id": 44781, "token": "\u00e5\u0130\u00bb", "merges": "\u00e5\u0130 \u00bb", "raw_count": 456094786, "count": 456094786, "decode_str": "\u53bb"} -{"id": 72, "token": "g", "merges": "NULL", "raw_count": 28867472, "count": 456299856, "decode_str": "g"} -{"id": 31129, "token": "\u00e6\u0126\u0131", "merges": "\u00e6\u0126 \u0131", "raw_count": 457645878, "count": 457645878, "decode_str": "\u610f"} -{"id": 21734, "token": "\u00e6\u0122\u00a7", "merges": "\u00e6\u0122 \u00a7", "raw_count": 459496409, "count": 459496409, "decode_str": "\u6027"} -{"id": 19218, "token": "\u00e7\u013b", "merges": "\u00e7 \u013b", "raw_count": 313397, "count": 460511941, "decode_str": "\ufffd"} -{"id": 36387, "token": "\u00e8\u012c", "merges": "\u00e8 \u012c", "raw_count": 582357, "count": 463197906, "decode_str": "\ufffd"} -{"id": 37679, "token": "\u00e7\u00b3", "merges": "\u00e7 \u00b3", "raw_count": 178253, "count": 465877555, "decode_str": "\ufffd"} -{"id": 34671, "token": "\u00e6\u0131\u0132", "merges": "\u00e6\u0131 \u0132", "raw_count": 468577383, "count": 468577383, "decode_str": "\u63d0"} -{"id": 37373, "token": "\u00e5\u00b0\u0128", "merges": "\u00e5\u00b0 \u0128", "raw_count": 469584341, "count": 469584341, "decode_str": "\u5c06"} -{"id": 28327, "token": "\u00e5\u0128\u0127", "merges": "\u00e5\u0128 \u0127", "raw_count": 472911648, "count": 472911648, "decode_str": "\u5185"} -{"id": 39915, "token": "\u00e9\u0136", "merges": "\u00e9 \u0136", "raw_count": 1392411, "count": 473539632, "decode_str": "\ufffd"} -{"id": 28650, "token": "\u00e5\u00a7", "merges": "\u00e5 \u00a7", "raw_count": 239079, "count": 473676456, "decode_str": "\ufffd"} -{"id": 38908, "token": "\u00e4\u00bf\u013f", "merges": "\u00e4\u00bf \u013f", "raw_count": 474172861, "count": 474172861, "decode_str": "\u4fdd"} -{"id": 47937, "token": "\u00e6\u00b0\u00b4", "merges": "\u00e6\u00b0 \u00b4", "raw_count": 475836324, "count": 475836324, "decode_str": "\u6c34"} -{"id": 26974, "token": "\u00e6\u0141", "merges": "\u00e6 \u0141", "raw_count": 278748, "count": 476160929, "decode_str": "\ufffd"} -{"id": 34397, "token": "\u00e6\u0125\u0127", "merges": "\u00e6\u0125 \u0127", "raw_count": 483828823, "count": 483828823, "decode_str": "\u60c5"} -{"id": 38389, "token": "\u00e7\u0126\u00b6", "merges": "\u00e7\u0126 \u00b6", "raw_count": 486423261, "count": 486423261, "decode_str": "\u7136"} -{"id": 37933, "token": "\u00e6\u00b6", "merges": "\u00e6 \u00b6", "raw_count": 211596, "count": 486494237, "decode_str": "\ufffd"} -{"id": 27896, "token": "\u00e4\u00b8\u0122\u00e4\u00b8\u00aa", "merges": "\u00e4\u00b8\u0122 \u00e4\u00b8\u00aa", "raw_count": 489256112, "count": 489256112, "decode_str": "\u4e00\u4e2a"} -{"id": 20031, "token": "\u00e9\u013d", "merges": "\u00e9 \u013d", "raw_count": 244218, "count": 492255401, "decode_str": "\ufffd"} -{"id": 3, "token": "\"", "merges": "NULL", "raw_count": 218835264, "count": 493734597, "decode_str": "\""} -{"id": 27804, "token": "\u00e9\u0122\u013c", "merges": "\u00e9\u0122 \u013c", "raw_count": 495149034, "count": 495149034, "decode_str": "\u901a"} -{"id": 31486, "token": "\u00e6\u012a\u0133\u00e4\u00bb\u00ac", "merges": "\u00e6\u012a\u0133 \u00e4\u00bb\u00ac", "raw_count": 499381709, "count": 499381709, "decode_str": "\u6211\u4eec"} -{"id": 32790, "token": "\u00e9\u013e", "merges": "\u00e9 \u013e", "raw_count": 51221, "count": 504496355, "decode_str": "\ufffd"} -{"id": 26335, "token": "\u00e9\u013c", "merges": "\u00e9 \u013c", "raw_count": 263806, "count": 505007963, "decode_str": "\ufffd"} -{"id": 26552, "token": "\u00e6\u013e\u012a", "merges": "\u00e6\u013e \u012a", "raw_count": 505197221, "count": 505197221, "decode_str": "\u6708"} -{"id": 42013, "token": "\u00e9\u0129\u012e", "merges": "\u00e9\u0129 \u012e", "raw_count": 507695358, "count": 507695358, "decode_str": "\u91cc"} -{"id": 20012, "token": "\u00e8\u0122\u0127", "merges": "\u00e8\u0122 \u0127", "raw_count": 508632776, "count": 508632776, "decode_str": "\u8005"} -{"id": 23, "token": "6", "merges": "NULL", "raw_count": 143386279, "count": 509726401, "decode_str": "6"} -{"id": 22010, "token": "\u00e4\u00ba\u012d", "merges": "\u00e4\u00ba \u012d", "raw_count": 511959407, "count": 511959407, "decode_str": "\u4e8b"} -{"id": 34698, "token": "\u00e9\u0129\u012f", "merges": "\u00e9\u0129 \u012f", "raw_count": 514024637, "count": 514024637, "decode_str": "\u91cd"} -{"id": 33700, "token": "\u00e9\u00a3", "merges": "\u00e9 \u00a3", "raw_count": 171242, "count": 514374596, "decode_str": "\ufffd"} -{"id": 40500, "token": "\u00e5\u0127\u00b3", "merges": "\u00e5\u0127 \u00b3", "raw_count": 514433702, "count": 514433702, "decode_str": "\u5173"} -{"id": 26, "token": "9", "merges": "NULL", "raw_count": 101224540, "count": 516884559, "decode_str": "9"} -{"id": 29485, "token": "\u00e5\u00ba\u00a6", "merges": "\u00e5\u00ba \u00a6", "raw_count": 517873921, "count": 517873921, "decode_str": "\u5ea6"} -{"id": 27707, "token": "\u00e5\u012e\u0138", "merges": "\u00e5\u012e \u0138", "raw_count": 519026860, "count": 519026860, "decode_str": "\u5316"} -{"id": 32417, "token": "\u00e8\u012b", "merges": "\u00e8 \u012b", "raw_count": 330542, "count": 522590028, "decode_str": "\ufffd"} -{"id": 25276, "token": "\u00e6\u012b\u0122", "merges": "\u00e6\u012b \u0122", "raw_count": 522915046, "count": 522915046, "decode_str": "\u6240"} -{"id": 73, "token": "h", "merges": "NULL", "raw_count": 13350275, "count": 523824468, "decode_str": "h"} -{"id": 25538, "token": "\u00e6\u013e\u0122", "merges": "\u00e6\u013e \u0122", "raw_count": 524781586, "count": 524781586, "decode_str": "\u6700"} -{"id": 30676, "token": "\u00e5\u0137", "merges": "\u00e5 \u0137", "raw_count": 240281, "count": 524802487, "decode_str": "\ufffd"} -{"id": 37286, "token": "\u00e9\u0139\u00b4", "merges": "\u00e9\u0139 \u00b4", "raw_count": 526716159, "count": 526716159, "decode_str": "\u95f4"} -{"id": 30590, "token": "\u00e8\u0123", "merges": "\u00e8 \u0123", "raw_count": 291368, "count": 526782479, "decode_str": "\ufffd"} -{"id": 54268, "token": "\u00e9\u0137\u00bf", "merges": "\u00e9\u0137 \u00bf", "raw_count": 526942284, "count": 526942284, "decode_str": "\u957f"} -{"id": 25, "token": "8", "merges": "NULL", "raw_count": 125752070, "count": 528315527, "decode_str": "8"} -{"id": 36359, "token": "\u00e5\u0127\u00b6", "merges": "\u00e5\u0127 \u00b6", "raw_count": 532913682, "count": 532913682, "decode_str": "\u5176"} -{"id": 64, "token": "_", "merges": "NULL", "raw_count": 446236637, "count": 535231250, "decode_str": "_"} -{"id": 27727, "token": "\u00e5\u012c\u0142", "merges": "\u00e5\u012c \u0142", "raw_count": 535261771, "count": 535261771, "decode_str": "\u52a0"} -{"id": 32283, "token": "\u00e5\u00bb", "merges": "\u00e5 \u00bb", "raw_count": 390141, "count": 539796496, "decode_str": "\ufffd"} -{"id": 26795, "token": "\u00e9\u0125\u00a8", "merges": "\u00e9\u0125 \u00a8", "raw_count": 541380588, "count": 541380588, "decode_str": "\u90e8"} -{"id": 34138, "token": "\u00e8\u00b6", "merges": "\u00e8 \u00b6", "raw_count": 289961, "count": 541763808, "decode_str": "\ufffd"} -{"id": 34260, "token": "\u00e9\u0123\u0135", "merges": "\u00e9\u0123 \u0135", "raw_count": 542440775, "count": 542440775, "decode_str": "\u9053"} -{"id": 34204, "token": "\u00e4\u00b8\u00bb", "merges": "\u00e4\u00b8 \u00bb", "raw_count": 543384507, "count": 543384507, "decode_str": "\u4e3b"} -{"id": 26036, "token": "\u00e7\u0126", "merges": "\u00e7 \u0126", "raw_count": 191142, "count": 545199587, "decode_str": "\ufffd"} -{"id": 30255, "token": "\u00e7\u00be", "merges": "\u00e7 \u00be", "raw_count": 149948, "count": 548204643, "decode_str": "\ufffd"} -{"id": 45091, "token": "\u00e5\u00be\u012a", "merges": "\u00e5\u00be \u012a", "raw_count": 548833655, "count": 548833655, "decode_str": "\u5f88"} -{"id": 18957, "token": "\u00e6\u013e\u00ac", "merges": "\u00e6\u013e \u00ac", "raw_count": 507433338, "count": 549604268, "decode_str": "\u672c"} -{"id": 40693, "token": "\u00e9\u0124\u00a3", "merges": "\u00e9\u0124 \u00a3", "raw_count": 550680786, "count": 550680786, "decode_str": "\u90a3"} -{"id": 52879, "token": "\u00e7\u0136\u00b5", "merges": "\u00e7\u0136 \u00b5", "raw_count": 554305438, "count": 554305438, "decode_str": "\u7535"} -{"id": 21121, "token": "\u00e7\u00a4", "merges": "\u00e7 \u00a4", "raw_count": 162505, "count": 557112058, "decode_str": "\ufffd"} -{"id": 31902, "token": "\u00e5\u013f", "merges": "\u00e5 \u013f", "raw_count": 637645, "count": 557490417, "decode_str": "\ufffd"} -{"id": 40564, "token": "\u00e4\u00b8\u0130", "merges": "\u00e4\u00b8 \u0130", "raw_count": 561992512, "count": 561992512, "decode_str": "\u4e0e"} -{"id": 18947, "token": "\u00e7\u00ac", "merges": "\u00e7 \u00ac", "raw_count": 694748, "count": 563736827, "decode_str": "\ufffd"} -{"id": 29734, "token": "\u00e7\u0124\u00b9", "merges": "\u00e7\u0124 \u00b9", "raw_count": 564985180, "count": 564985180, "decode_str": "\u70b9"} -{"id": 22580, "token": "\u00e7\u00a8", "merges": "\u00e7 \u00a8", "raw_count": 68849, "count": 565751014, "decode_str": "\ufffd"} -{"id": 45111, "token": "\u00e7\u013f\u0122", "merges": "\u00e7\u013f \u0122", "raw_count": 567962241, "count": 567962241, "decode_str": "\u7740"} -{"id": 24168, "token": "\u00e5\u0132\u012a", "merges": "\u00e5\u0132 \u012a", "raw_count": 570818041, "count": 570818041, "decode_str": "\u5408"} -{"id": 21, "token": "4", "merges": "NULL", "raw_count": 185827946, "count": 573313216, "decode_str": "4"} -{"id": 37895, "token": "\u00e6\u013b", "merges": "\u00e6 \u013b", "raw_count": 175031, "count": 575313569, "decode_str": "\ufffd"} -{"id": 24412, "token": "\u00e5\u0132\u012e", "merges": "\u00e5\u0132 \u012e", "raw_count": 587076485, "count": 587076485, "decode_str": "\u540c"} -{"id": 20113, "token": "\u00e6\u00b3\u0137", "merges": "\u00e6\u00b3 \u0137", "raw_count": 516949138, "count": 587431939, "decode_str": "\u6cd5"} -{"id": 38328, "token": "\u00e8\u0122\u012e", "merges": "\u00e8\u0122 \u012e", "raw_count": 597150542, "count": 597150542, "decode_str": "\u800c"} -{"id": 25762, "token": "\u00e7\u0141", "merges": "\u00e7 \u0141", "raw_count": 372666, "count": 598373771, "decode_str": "\ufffd"} -{"id": 23823, "token": "\u00e6\u012f", "merges": "\u00e6 \u012f", "raw_count": 120390, "count": 603112009, "decode_str": "\ufffd"} -{"id": 41230, "token": "\u00e5\u0135\u0123", "merges": "\u00e5\u0135 \u0123", "raw_count": 604895375, "count": 604895375, "decode_str": "\u54c1"} -{"id": 17951, "token": "\u00e6\u0139\u00a5", "merges": "\u00e6\u0139 \u00a5", "raw_count": 565178364, "count": 607349294, "decode_str": "\u65e5"} -{"id": 50477, "token": "\u00e4\u00ba\u00a7", "merges": "\u00e4\u00ba \u00a7", "raw_count": 607392029, "count": 607392029, "decode_str": "\u4ea7"} -{"id": 19780, "token": "\u00e9\u00a1", "merges": "\u00e9 \u00a1", "raw_count": 77929, "count": 609063107, "decode_str": "\ufffd"} -{"id": 16849, "token": "\u00e5\u0122", "merges": "\u00e5 \u0122", "raw_count": 348512, "count": 611198757, "decode_str": "\ufffd"} -{"id": 32365, "token": "\u00e5\u012c\u013d", "merges": "\u00e5\u012c \u013d", "raw_count": 613708160, "count": 613708160, "decode_str": "\u529b"} -{"id": 29645, "token": "\u00e4\u00bd\u0135", "merges": "\u00e4\u00bd \u0135", "raw_count": 614291737, "count": 614291737, "decode_str": "\u4f53"} -{"id": 25434, "token": "\u00e5\u00a6\u0124", "merges": "\u00e5\u00a6 \u0124", "raw_count": 418987737, "count": 615257875, "decode_str": "\u5982"} -{"id": 22470, "token": "\u00e6\u0131", "merges": "\u00e6 \u0131", "raw_count": 374466, "count": 616703477, "decode_str": "\ufffd"} -{"id": 42335, "token": "\u00e5\u00b8\u0124", "merges": "\u00e5\u00b8 \u0124", "raw_count": 616836741, "count": 616836741, "decode_str": "\u5e02"} -{"id": 17576, "token": "\u00e5\u00ae\u013c", "merges": "\u00e5\u00ae \u013c", "raw_count": 618062980, "count": 618062980, "decode_str": "\u5b9a"} -{"id": 24299, "token": "\u00e9\u0125", "merges": "\u00e9 \u0125", "raw_count": 987897, "count": 620362277, "decode_str": "\ufffd"} -{"id": 22329, "token": "\u00e5\u012b\u012f", "merges": "\u00e5\u012b \u012f", "raw_count": 620874384, "count": 620874384, "decode_str": "\u524d"} -{"id": 31811, "token": "\u00e8\u00b7", "merges": "\u00e8 \u00b7", "raw_count": 542093, "count": 631832027, "decode_str": "\ufffd"} -{"id": 30423, "token": "\u00e5\u0127\u00a8", "merges": "\u00e5\u0127 \u00a8", "raw_count": 631911208, "count": 631911208, "decode_str": "\u5168"} -{"id": 36644, "token": "\u00e5\u00bf\u0125", "merges": "\u00e5\u00bf \u0125", "raw_count": 633251643, "count": 633251643, "decode_str": "\u5fc3"} -{"id": 30808, "token": "\u00e5\u00be\u0139", "merges": "\u00e5\u00be \u0139", "raw_count": 633941433, "count": 633941433, "decode_str": "\u5f97"} -{"id": 20286, "token": "\u00e6\u013d", "merges": "\u00e6 \u013d", "raw_count": 629420, "count": 635470066, "decode_str": "\ufffd"} -{"id": 38563, "token": "\u00e7\u0143\u012b", "merges": "\u00e7\u0143 \u012b", "raw_count": 639151157, "count": 639151157, "decode_str": "\u7b49"} -{"id": 71, "token": "f", "merges": "NULL", "raw_count": 18811650, "count": 644165976, "decode_str": "f"} -{"id": 29766, "token": "\u00e4\u00b9\u012d", "merges": "\u00e4\u00b9 \u012d", "raw_count": 650179487, "count": 650179487, "decode_str": "\u4e4b"} -{"id": 2, "token": "!", "merges": "NULL", "raw_count": 499330325, "count": 650785535, "decode_str": "!"} -{"id": 28607, "token": "\u00e9\u0137", "merges": "\u00e9 \u0137", "raw_count": 1650610, "count": 659094585, "decode_str": "\ufffd"} -{"id": 38242, "token": "\u00e7\u013e\u012d", "merges": "\u00e7\u013e \u012d", "raw_count": 660503903, "count": 660503903, "decode_str": "\u770b"} -{"id": 78, "token": "m", "merges": "NULL", "raw_count": 24013466, "count": 662514429, "decode_str": "m"} -{"id": 86, "token": "u", "merges": "NULL", "raw_count": 9253957, "count": 666505899, "decode_str": "u"} -{"id": 81, "token": "p", "merges": "NULL", "raw_count": 19468966, "count": 667453839, "decode_str": "p"} -{"id": 36750, "token": "\u00e5\u00ae\u0140", "merges": "\u00e5\u00ae \u0140", "raw_count": 671850037, "count": 671850037, "decode_str": "\u5b9e"} -{"id": 36778, "token": "\u00e8\u00bf\u013d", "merges": "\u00e8\u00bf \u013d", "raw_count": 673561354, "count": 673561354, "decode_str": "\u8fdb"} -{"id": 52203, "token": "\u00e6\u013e\u00ba", "merges": "\u00e6\u013e \u00ba", "raw_count": 674838515, "count": 674838515, "decode_str": "\u673a"} -{"id": 35601, "token": "\u00e5\u0127\u00ac", "merges": "\u00e5\u0127 \u00ac", "raw_count": 675723784, "count": 675723784, "decode_str": "\u516c"} -{"id": 30903, "token": "\u00e9\u00ab\u013a", "merges": "\u00e9\u00ab \u013a", "raw_count": 678126338, "count": 678126338, "decode_str": "\u9ad8"} -{"id": 30086, "token": "\u00e9\u0124", "merges": "\u00e9 \u0124", "raw_count": 604228, "count": 678525461, "decode_str": "\ufffd"} -{"id": 33018, "token": "\u00e5\u0131\u00af\u00e4\u00bb\u00a5", "merges": "\u00e5\u0131\u00af \u00e4\u00bb\u00a5", "raw_count": 678818611, "count": 678818611, "decode_str": "\u53ef\u4ee5"} -{"id": 41807, "token": "\u00e8\u00af\u00b4", "merges": "\u00e8\u00af \u00b4", "raw_count": 680134845, "count": 680134845, "decode_str": "\u8bf4"} -{"id": 29533, "token": "\u00e5\u00b0\u0131", "merges": "\u00e5\u00b0 \u0131", "raw_count": 680198990, "count": 680198990, "decode_str": "\u5c0f"} -{"id": 51747, "token": "\u00e6\u0124\u00a8", "merges": "\u00e6\u0124 \u00a8", "raw_count": 685859567, "count": 685859567, "decode_str": "\u60a8"} -{"id": 27712, "token": "\u00e9\u00ab", "merges": "\u00e9 \u00ab", "raw_count": 536427, "count": 687304374, "decode_str": "\ufffd"} -{"id": 46049, "token": "\u00e6\u00b2\u00a1", "merges": "\u00e6\u00b2 \u00a1", "raw_count": 692240844, "count": 692240844, "decode_str": "\u6ca1"} -{"id": 24017, "token": "\u00e7\u0132\u0128", "merges": "\u00e7\u0132 \u0128", "raw_count": 692287933, "count": 692287933, "decode_str": "\u7406"} -{"id": 16800, "token": "\u00e4\u00be", "merges": "\u00e4 \u00be", "raw_count": 550826, "count": 697009824, "decode_str": "\ufffd"} -{"id": 24308, "token": "\u00e6\u0138\u00b0", "merges": "\u00e6\u0138 \u00b0", "raw_count": 697215822, "count": 697215822, "decode_str": "\u65b0"} -{"id": 49344, "token": "\u00e7\u00bb\u0131", "merges": "\u00e7\u00bb \u0131", "raw_count": 698553893, "count": 698553893, "decode_str": "\u7ecf"} -{"id": 33656, "token": "\u00e8\u00b0", "merges": "\u00e8 \u00b0", "raw_count": 822984, "count": 703389375, "decode_str": "\ufffd"} -{"id": 37531, "token": "\u00e7\u013f", "merges": "\u00e7 \u013f", "raw_count": 227519, "count": 706731958, "decode_str": "\ufffd"} -{"id": 23371, "token": "\u00e5\u0143\u0132", "merges": "\u00e5\u0143 \u0132", "raw_count": 708573596, "count": 708573596, "decode_str": "\u5b50"} -{"id": 28305, "token": "\u00e9\u013f\u00a2", "merges": "\u00e9\u013f \u00a2", "raw_count": 709358365, "count": 709358365, "decode_str": "\u9762"} -{"id": 21944, "token": "\u00e7\u0124", "merges": "\u00e7 \u0124", "raw_count": 337177, "count": 717493707, "decode_str": "\ufffd"} -{"id": 18434, "token": "\u00e5\u012a\u0128", "merges": "\u00e5\u012a \u0128", "raw_count": 722177652, "count": 722177652, "decode_str": "\u5206"} -{"id": 28915, "token": "\u00e5\u0123", "merges": "\u00e5 \u0123", "raw_count": 158940, "count": 722196991, "decode_str": "\ufffd"} -{"id": 24545, "token": "\u00e6\u00b1", "merges": "\u00e6 \u00b1", "raw_count": 300698, "count": 724232340, "decode_str": "\ufffd"} -{"id": 25541, "token": "\u00e7\u00ae", "merges": "\u00e7 \u00ae", "raw_count": 633131, "count": 726589560, "decode_str": "\ufffd"} -{"id": 40120, "token": "\u00e5\u00a4\u00a9", "merges": "\u00e5\u00a4 \u00a9", "raw_count": 726654281, "count": 726654281, "decode_str": "\u5929"} -{"id": 26151, "token": "\u00e6\u00b8", "merges": "\u00e6 \u00b8", "raw_count": 351884, "count": 727244224, "decode_str": "\ufffd"} -{"id": 19957, "token": "\u00e7\u00bd", "merges": "\u00e7 \u00bd", "raw_count": 455398, "count": 728167062, "decode_str": "\ufffd"} -{"id": 22701, "token": "\u00e7\u00ab", "merges": "\u00e7 \u00ab", "raw_count": 203856, "count": 729226433, "decode_str": "\ufffd"} -{"id": 54077, "token": "\u00e8\u00bf\u013a", "merges": "\u00e8\u00bf \u013a", "raw_count": 731296495, "count": 731296495, "decode_str": "\u8fd8"} -{"id": 35930, "token": "\u00e5\u00bc\u0122", "merges": "\u00e5\u00bc \u0122", "raw_count": 733573064, "count": 733573064, "decode_str": "\u5f00"} -{"id": 26581, "token": "\u00e5\u0141", "merges": "\u00e5 \u0141", "raw_count": 1776264, "count": 733602059, "decode_str": "\ufffd"} -{"id": 30093, "token": "\u00e6\u00b4", "merges": "\u00e6 \u00b4", "raw_count": 388594, "count": 733651503, "decode_str": "\ufffd"} -{"id": 22, "token": "5", "merges": "NULL", "raw_count": 227832575, "count": 735165309, "decode_str": "5"} -{"id": 68, "token": "c", "merges": "NULL", "raw_count": 23600730, "count": 746177633, "decode_str": "c"} -{"id": 43244, "token": "\u00e4\u00b9\u012a", "merges": "\u00e4\u00b9 \u012a", "raw_count": 750035931, "count": 750035931, "decode_str": "\u4e48"} -{"id": 41869, "token": "\u00e5\u00b7\u00a5", "merges": "\u00e5\u00b7 \u00a5", "raw_count": 754764892, "count": 754764892, "decode_str": "\u5de5"} -{"id": 37062, "token": "\u00e5\u012c\u00a8", "merges": "\u00e5\u012c \u00a8", "raw_count": 757613631, "count": 757613631, "decode_str": "\u52a8"} -{"id": 32026, "token": "\u00e8\u0124", "merges": "\u00e8 \u0124", "raw_count": 210787, "count": 758023463, "decode_str": "\ufffd"} -{"id": 20, "token": "3", "merges": "NULL", "raw_count": 270906407, "count": 768315736, "decode_str": "3"} -{"id": 20005, "token": "\u00e6\u0138\u00b9", "merges": "\u00e6\u0138 \u00b9", "raw_count": 698883862, "count": 769366663, "decode_str": "\u65b9"} -{"id": 34446, "token": "\u00e9\u0125\u00bd", "merges": "\u00e9 \u0125\u00bd", "raw_count": 772673790, "count": 772673790, "decode_str": "\u90fd"} -{"id": 35321, "token": "\u00e7\u0130\u00b0", "merges": "\u00e7\u0130 \u00b0", "raw_count": 778010636, "count": 778010636, "decode_str": "\u73b0"} -{"id": 29852, "token": "\u00e9\u013a", "merges": "\u00e9 \u013a", "raw_count": 961898, "count": 778259619, "decode_str": "\ufffd"} -{"id": 30329, "token": "\u00e4\u00ba\u0130", "merges": "\u00e4\u00ba \u0130", "raw_count": 789514212, "count": 789514212, "decode_str": "\u4e8e"} -{"id": 24553, "token": "\u00e4\u00bd\u0142", "merges": "\u00e4\u00bd \u0142", "raw_count": 802824485, "count": 802824485, "decode_str": "\u4f60"} -{"id": 21232, "token": "\u00e8\u0129\u00aa", "merges": "\u00e8\u0129 \u00aa", "raw_count": 808323314, "count": 808323314, "decode_str": "\u81ea"} -{"id": 69, "token": "d", "merges": "NULL", "raw_count": 22590908, "count": 812277227, "decode_str": "d"} -{"id": 32004, "token": "\u00e8\u00bf\u0129", "merges": "\u00e8\u00bf \u0129", "raw_count": 829093067, "count": 829093067, "decode_str": "\u8fc7"} -{"id": 14378, "token": "\u00e9\u0123", "merges": "\u00e9 \u0123", "raw_count": 190057, "count": 833101960, "decode_str": "\ufffd"} -{"id": 32403, "token": "\u00e6\u0124", "merges": "\u00e6 \u0124", "raw_count": 361119, "count": 860027783, "decode_str": "\ufffd"} -{"id": 21683, "token": "\u00e5\u00a6", "merges": "\u00e5 \u00a6", "raw_count": 395389, "count": 869887901, "decode_str": "\ufffd"} -{"id": 21275, "token": "\u00e4\u00bd\u013e", "merges": "\u00e4\u00bd \u013e", "raw_count": 879408552, "count": 879408552, "decode_str": "\u4f5c"} -{"id": 24086, "token": "\u00e5\u013e\u00b0", "merges": "\u00e5\u013e \u00b0", "raw_count": 880741561, "count": 880741561, "decode_str": "\u5730"} -{"id": 24446, "token": "\u00e4\u00bb\u0138", "merges": "\u00e4\u00bb \u0138", "raw_count": 887666725, "count": 887666725, "decode_str": "\u4ed6"} -{"id": 34091, "token": "\u00e5\u00ae\u00b6", "merges": "\u00e5\u00ae \u00b6", "raw_count": 892972382, "count": 892972382, "decode_str": "\u5bb6"} -{"id": 16805, "token": "\u00e5\u012b", "merges": "\u00e5 \u012b", "raw_count": 151063, "count": 897534447, "decode_str": "\ufffd"} -{"id": 28586, "token": "\u00e5\u0143\u00a6", "merges": "\u00e5\u0143 \u00a6", "raw_count": 901424632, "count": 901424632, "decode_str": "\u5b66"} -{"id": 21991, "token": "\u00e6\u012a\u0132", "merges": "\u00e6\u012a \u0132", "raw_count": 912199298, "count": 912199298, "decode_str": "\u6210"} -{"id": 9, "token": "(", "merges": "NULL", "raw_count": 719369578, "count": 915576179, "decode_str": "("} -{"id": 32, "token": "?", "merges": "NULL", "raw_count": 817361271, "count": 921914254, "decode_str": "?"} -{"id": 10, "token": ")", "merges": "NULL", "raw_count": 548917521, "count": 925428047, "decode_str": ")"} -{"id": 21422, "token": "\u00e7\u0132", "merges": "\u00e7 \u0132", "raw_count": 236490, "count": 928927078, "decode_str": "\ufffd"} -{"id": 24899, "token": "\u00e5\u00a4\u013c", "merges": "\u00e5\u00a4 \u013c", "raw_count": 933663894, "count": 933663894, "decode_str": "\u591a"} -{"id": 35724, "token": "\u00e4\u00b9\u0141", "merges": "\u00e4\u00b9 \u0141", "raw_count": 937584750, "count": 937584750, "decode_str": "\u4e5f"} -{"id": 29427, "token": "\u00e5\u0132\u0130", "merges": "\u00e5\u0132 \u0130", "raw_count": 942238997, "count": 942238997, "decode_str": "\u540e"} -{"id": 18245, "token": "\u00e6\u012e", "merges": "\u00e6 \u012e", "raw_count": 82126, "count": 943276912, "decode_str": "\ufffd"} -{"id": 19597, "token": "\u00e6\u0126", "merges": "\u00e6 \u0126", "raw_count": 449089, "count": 955576591, "decode_str": "\ufffd"} -{"id": 22985, "token": "\u00e6\u00af", "merges": "\u00e6 \u00af", "raw_count": 214184, "count": 962924963, "decode_str": "\ufffd"} -{"id": 50413, "token": "\u00e4\u00b8\u013c", "merges": "\u00e4\u00b8 \u013c", "raw_count": 972168667, "count": 972168667, "decode_str": "\u4e1a"} -{"id": 27258, "token": "\u00e8\u00bd", "merges": "\u00e8 \u00bd", "raw_count": 365788, "count": 972906115, "decode_str": "\ufffd"} -{"id": 16677, "token": "\u00e8\u00a1\u012e", "merges": "\u00e8\u00a1 \u012e", "raw_count": 973123780, "count": 973123780, "decode_str": "\u884c"} -{"id": 25949, "token": "\u00e5\u00af\u00b9", "merges": "\u00e5\u00af \u00b9", "raw_count": 974594796, "count": 974594796, "decode_str": "\u5bf9"} -{"id": 23825, "token": "\u00e6\u012d", "merges": "\u00e6 \u012d", "raw_count": 121875, "count": 996935543, "decode_str": "\ufffd"} -{"id": 25715, "token": "\u00e6\u00ac", "merges": "\u00e6 \u00ac", "raw_count": 273968, "count": 1013147171, "decode_str": "\ufffd"} -{"id": 23788, "token": "\u00e4\u00bb\u00ac", "merges": "\u00e4\u00bb \u00ac", "raw_count": 529838326, "count": 1029220035, "decode_str": "\u4eec"} -{"id": 18678, "token": "\u00e5\u0129\u00ba", "merges": "\u00e5\u0129 \u00ba", "raw_count": 1030782510, "count": 1030782510, "decode_str": "\u51fa"} -{"id": 21998, "token": "\u00e6\u00b5", "merges": "\u00e6 \u00b5", "raw_count": 634824, "count": 1037006027, "decode_str": "\ufffd"} -{"id": 17321, "token": "\u00e6\u0140", "merges": "\u00e6 \u0140", "raw_count": 310495, "count": 1048253447, "decode_str": "\ufffd"} -{"id": 27107, "token": "\u00e9\u00a2", "merges": "\u00e9 \u00a2", "raw_count": 432258, "count": 1060031600, "decode_str": "\ufffd"} -{"id": 21365, "token": "\u00e8\u00be", "merges": "\u00e8 \u00be", "raw_count": 514847, "count": 1061836476, "decode_str": "\ufffd"} -{"id": 27, "token": ":", "merges": "NULL", "raw_count": 903877574, "count": 1064650325, "decode_str": ":"} -{"id": 20025, "token": "\u00e7\u0136\u0141", "merges": "\u00e7\u0136 \u0141", "raw_count": 1082285810, "count": 1082285810, "decode_str": "\u751f"} -{"id": 53227, "token": "\u00e7\u0143\u0136", "merges": "\u00e7\u0143 \u0136", "raw_count": 1091407147, "count": 1091407147, "decode_str": "\u7b54"} -{"id": 77, "token": "l", "merges": "NULL", "raw_count": 16013796, "count": 1095703157, "decode_str": "l"} -{"id": 21555, "token": "\u00e6\u0125", "merges": "\u00e6 \u0125", "raw_count": 91351, "count": 1103000772, "decode_str": "\ufffd"} -{"id": 29297, "token": "\u00e5\u00b0\u00b1", "merges": "\u00e5\u00b0 \u00b1", "raw_count": 1103703702, "count": 1103703702, "decode_str": "\u5c31"} -{"id": 34439, "token": "\u00e5\u00a5\u00bd", "merges": "\u00e5\u00a5 \u00bd", "raw_count": 1104455677, "count": 1104455677, "decode_str": "\u597d"} -{"id": 15, "token": ".", "merges": "NULL", "raw_count": 910962306, "count": 1110013221, "decode_str": "."} -{"id": 14670, "token": "\u00e6\u00b3", "merges": "\u00e6 \u00b3", "raw_count": 402096, "count": 1113381817, "decode_str": "\ufffd"} -{"id": 19144, "token": "\u00e5\u00b9\u00b4", "merges": "\u00e5\u00b9 \u00b4", "raw_count": 1115883781, "count": 1115883781, "decode_str": "\u5e74"} -{"id": 20720, "token": "\u00e4\u00b8\u012d", "merges": "\u00e4\u00b8 \u012d", "raw_count": 1123747545, "count": 1123747545, "decode_str": "\u4e0b"} -{"id": 23197, "token": "\u00e5\u013d\u00bd", "merges": "\u00e5\u013d \u00bd", "raw_count": 1149853902, "count": 1149853902, "decode_str": "\u56fd"} -{"id": 17783, "token": "\u00e9\u013b", "merges": "\u00e9 \u013b", "raw_count": 230274, "count": 1170684836, "decode_str": "\ufffd"} -{"id": 17598, "token": "\u00e6\u0130", "merges": "\u00e6 \u0130", "raw_count": 380602, "count": 1175485710, "decode_str": "\ufffd"} -{"id": 29268, "token": "\u00e7\u00ba", "merges": "\u00e7 \u00ba", "raw_count": 598230, "count": 1179341592, "decode_str": "\ufffd"} -{"id": 668, "token": "\u00e2\u0122\u013f", "merges": "\u00e2\u0122 \u013f", "raw_count": 877656731, "count": 1182559632, "decode_str": "\u201d"} -{"id": 1628, "token": "\u00e2\u0122\u013e", "merges": "\u00e2\u0122 \u013e", "raw_count": 1183077059, "count": 1184035528, "decode_str": "\u201c"} -{"id": 14318, "token": "\u00e5\u00bd", "merges": "\u00e5 \u00bd", "raw_count": 428557, "count": 1186663723, "decode_str": "\ufffd"} -{"id": 24370, "token": "\u00e6\u013f\u00a5", "merges": "\u00e6\u013f \u00a5", "raw_count": 1189930642, "count": 1189930642, "decode_str": "\u6765"} -{"id": 16818, "token": "\u00e4\u00bf", "merges": "\u00e4 \u00bf", "raw_count": 413214, "count": 1195940292, "decode_str": "\ufffd"} -{"id": 12335, "token": "\u00e7\u0136\u00a8", "merges": "\u00e7\u0136 \u00a8", "raw_count": 1002106647, "count": 1208745890, "decode_str": "\u7528"} -{"id": 16787, "token": "\u00e8\u0129", "merges": "\u00e8 \u0129", "raw_count": 129481, "count": 1225273936, "decode_str": "\ufffd"} -{"id": 20287, "token": "\u00e8\u0125\u00bd", "merges": "\u00e8 \u0125\u00bd", "raw_count": 1084329342, "count": 1244017066, "decode_str": "\u80fd"} -{"id": 19127, "token": "\u00e9\u013f", "merges": "\u00e9 \u013f", "raw_count": 87460, "count": 1262506271, "decode_str": "\ufffd"} -{"id": 17289, "token": "\u00e6\u00b0", "merges": "\u00e6 \u00b0", "raw_count": 578873, "count": 1262525262, "decode_str": "\ufffd"} -{"id": 29918, "token": "\u00e5\u0131\u0133", "merges": "\u00e5\u0131 \u0133", "raw_count": 1276108989, "count": 1276108989, "decode_str": "\u53d1"} -{"id": 20281, "token": "\u00e4\u00bc\u013c", "merges": "\u00e4\u00bc \u013c", "raw_count": 1280722699, "count": 1280722699, "decode_str": "\u4f1a"} -{"id": 15957, "token": "\u00e7\u012b", "merges": "\u00e7 \u012b", "raw_count": 244976, "count": 1289213373, "decode_str": "\ufffd"} -{"id": 17955, "token": "\u00e5\u00b1", "merges": "\u00e5 \u00b1", "raw_count": 371537, "count": 1304216149, "decode_str": "\ufffd"} -{"id": 20827, "token": "\u00e7\u013e", "merges": "\u00e7 \u013e", "raw_count": 257927, "count": 1309319424, "decode_str": "\ufffd"} -{"id": 18148, "token": "\u00e5\u0131\u00af", "merges": "\u00e5\u0131 \u00af", "raw_count": 471568195, "count": 1310074530, "decode_str": "\u53ef"} -{"id": 14486, "token": "\u00e6\u0143", "merges": "\u00e6 \u0143", "raw_count": 114004, "count": 1311965148, "decode_str": "\ufffd"} -{"id": 20647, "token": "\u00e5\u0130", "merges": "\u00e5 \u0130", "raw_count": 169166, "count": 1320346044, "decode_str": "\ufffd"} -{"id": 22044, "token": "\u00e5\u012a\u00b0", "merges": "\u00e5\u012a \u00b0", "raw_count": 1322609385, "count": 1322609385, "decode_str": "\u5230"} -{"id": 21458, "token": "\u00e5\u0134\u012e", "merges": "\u00e5\u0134 \u012e", "raw_count": 1323009740, "count": 1323009740, "decode_str": "\u548c"} -{"id": 22305, "token": "\u00e6\u00b2", "merges": "\u00e6 \u00b2", "raw_count": 911738, "count": 1325206000, "decode_str": "\ufffd"} -{"id": 16998, "token": "\u00e7\u00a7", "merges": "\u00e7 \u00a7", "raw_count": 159826, "count": 1326724910, "decode_str": "\ufffd"} -{"id": 22975, "token": "\u00e6\u0139\u00b6", "merges": "\u00e6\u0139 \u00b6", "raw_count": 1334169560, "count": 1334169560, "decode_str": "\u65f6"} -{"id": 187, "token": "\u010a", "merges": "NULL", "raw_count": 1324179378, "count": 1337088482, "decode_str": "\n"} -{"id": 18764, "token": "\u00e8\u00a6\u0123", "merges": "\u00e8\u00a6 \u0123", "raw_count": 1144092699, "count": 1376188813, "decode_str": "\u8981"} -{"id": 16740, "token": "\u00e4\u00b8\u012c", "merges": "\u00e4\u00b8 \u012c", "raw_count": 1398125777, "count": 1398125777, "decode_str": "\u4e0a"} -{"id": 11800, "token": "\u00e8\u00a6", "merges": "\u00e8 \u00a6", "raw_count": 72676, "count": 1401944873, "decode_str": "\ufffd"} -{"id": 19, "token": "2", "merges": "NULL", "raw_count": 295649853, "count": 1435774346, "decode_str": "2"} -{"id": 80, "token": "o", "merges": "NULL", "raw_count": 14857869, "count": 1439680876, "decode_str": "o"} -{"id": 20241, "token": "\u00e7\u0130", "merges": "\u00e7 \u0130", "raw_count": 397794, "count": 1443773308, "decode_str": "\ufffd"} -{"id": 79, "token": "n", "merges": "NULL", "raw_count": 20871357, "count": 1449749288, "decode_str": "n"} -{"id": 83, "token": "r", "merges": "NULL", "raw_count": 13694221, "count": 1456528640, "decode_str": "r"} -{"id": 13258, "token": "\u00e6\u0122", "merges": "\u00e6 \u0122", "raw_count": 268631, "count": 1483618159, "decode_str": "\ufffd"} -{"id": 74, "token": "i", "merges": "NULL", "raw_count": 25642595, "count": 1491085156, "decode_str": "i"} -{"id": 20345, "token": "\u00e5\u0134", "merges": "\u00e5 \u0134", "raw_count": 200573, "count": 1493579696, "decode_str": "\ufffd"} -{"id": 18617, "token": "\u00e5\u0133", "merges": "\u00e5 \u0133", "raw_count": 348911, "count": 1494313113, "decode_str": "\ufffd"} -{"id": 84, "token": "s", "merges": "NULL", "raw_count": 41901290, "count": 1503220976, "decode_str": "s"} -{"id": 17559, "token": "\u00e8\u00a7", "merges": "\u00e8 \u00a7", "raw_count": 280732, "count": 1515623193, "decode_str": "\ufffd"} -{"id": 16549, "token": "\u00e5\u00bf", "merges": "\u00e5 \u00bf", "raw_count": 574436, "count": 1524430689, "decode_str": "\ufffd"} -{"id": 23692, "token": "\u00e8\u00b5", "merges": "\u00e8 \u00b5", "raw_count": 636453, "count": 1527384710, "decode_str": "\ufffd"} -{"id": 20326, "token": "\u00e4\u00b8\u00ba", "merges": "\u00e4\u00b8 \u00ba", "raw_count": 1527881671, "count": 1527881671, "decode_str": "\u4e3a"} -{"id": 10962, "token": "\u00e6\u0137", "merges": "\u00e6 \u0137", "raw_count": 125094, "count": 1529078156, "decode_str": "\ufffd"} -{"id": 16127, "token": "\u00e6\u0136", "merges": "\u00e6 \u0136", "raw_count": 80540, "count": 1532083723, "decode_str": "\ufffd"} -{"id": 49271, "token": "\u00e9\u0139\u00ae", "merges": "\u00e9\u0139 \u00ae", "raw_count": 1532783320, "count": 1532783320, "decode_str": "\u95ee"} -{"id": 15756, "token": "\u00e6\u0142", "merges": "\u00e6 \u0142", "raw_count": 370109, "count": 1539713646, "decode_str": "\ufffd"} -{"id": 15962, "token": "\u00e5\u00a4\u00a7", "merges": "\u00e5\u00a4 \u00a7", "raw_count": 1551523298, "count": 1551523298, "decode_str": "\u5927"} -{"id": 20833, "token": "\u00e5\u0135", "merges": "\u00e5 \u0135", "raw_count": 594613, "count": 1567952380, "decode_str": "\ufffd"} -{"id": 18751, "token": "\u00e6\u012c", "merges": "\u00e6 \u012c", "raw_count": 99859, "count": 1572486131, "decode_str": "\ufffd"} -{"id": 13609, "token": "\u00e4\u00b8\u0143", "merges": "\u00e4\u00b8 \u0143", "raw_count": 1587128747, "count": 1587128747, "decode_str": "\u4e2d"} -{"id": 16877, "token": "\u00e4\u00bb\u00a5", "merges": "\u00e4\u00bb \u00a5", "raw_count": 910549339, "count": 1589367950, "decode_str": "\u4ee5"} -{"id": 66, "token": "a", "merges": "NULL", "raw_count": 28357289, "count": 1593025286, "decode_str": "a"} -{"id": 15899, "token": "\u00e5\u012e", "merges": "\u00e5 \u012e", "raw_count": 156162, "count": 1627046325, "decode_str": "\ufffd"} -{"id": 16401, "token": "\u00e4\u00b8\u00aa", "merges": "\u00e4\u00b8 \u00aa", "raw_count": 1150422684, "count": 1639678796, "decode_str": "\u4e2a"} -{"id": 13764, "token": "\u00e7\u013d", "merges": "\u00e7 \u013d", "raw_count": 105621, "count": 1670795333, "decode_str": "\ufffd"} -{"id": 13744, "token": "\u00e5\u00af", "merges": "\u00e5 \u00af", "raw_count": 249163, "count": 1679202806, "decode_str": "\ufffd"} -{"id": 10716, "token": "\u00e8\u00a1", "merges": "\u00e8 \u00a1", "raw_count": 188321, "count": 1759123667, "decode_str": "\ufffd"} -{"id": 20622, "token": "\u00e8\u00bf\u013b", "merges": "\u00e8\u00bf \u013b", "raw_count": 1784491655, "count": 1784491655, "decode_str": "\u8fd9"} -{"id": 85, "token": "t", "merges": "NULL", "raw_count": 17510730, "count": 1788196427, "decode_str": "t"} -{"id": 13180, "token": "\u00e8\u0122", "merges": "\u00e8 \u0122", "raw_count": 164496, "count": 1798171489, "decode_str": "\ufffd"} -{"id": 18, "token": "1", "merges": "NULL", "raw_count": 337703626, "count": 1800007470, "decode_str": "1"} -{"id": 14262, "token": "\u00e5\u0128", "merges": "\u00e5 \u0128", "raw_count": 134675, "count": 1838665321, "decode_str": "\ufffd"} -{"id": 15367, "token": "\u00e6\u012a\u0133", "merges": "\u00e6\u012a \u0133", "raw_count": 1370772254, "count": 1870153963, "decode_str": "\u6211"} -{"id": 12613, "token": "\u00e5\u00ba", "merges": "\u00e5 \u00ba", "raw_count": 299031, "count": 1906299570, "decode_str": "\ufffd"} -{"id": 12005, "token": "\u00e5\u00be", "merges": "\u00e5 \u00be", "raw_count": 294615, "count": 1942403946, "decode_str": "\ufffd"} -{"id": 13486, "token": "\u00e5\u0129", "merges": "\u00e5 \u0129", "raw_count": 303182, "count": 1952464287, "decode_str": "\ufffd"} -{"id": 17, "token": "0", "merges": "NULL", "raw_count": 93473482, "count": 1953409374, "decode_str": "0"} -{"id": 12811, "token": "\u00e5\u00bc", "merges": "\u00e5 \u00bc", "raw_count": 135125, "count": 1960490370, "decode_str": "\ufffd"} -{"id": 29832, "token": "\u00e8\u00b4", "merges": "\u00e8 \u00b4", "raw_count": 177222, "count": 1982813082, "decode_str": "\ufffd"} -{"id": 13484, "token": "\u00e4\u00ba\u00ba", "merges": "\u00e4\u00ba \u00ba", "raw_count": 2010476810, "count": 2010476810, "decode_str": "\u4eba"} -{"id": 15911, "token": "\u0125\u00bd", "merges": "\u0125 \u00bd", "raw_count": 2937, "count": 2017563542, "decode_str": "\ufffd\ufffd"} -{"id": 24379, "token": "\u00e7\u0143", "merges": "\u00e7 \u0143", "raw_count": 506233, "count": 2027814440, "decode_str": "\ufffd"} -{"id": 17474, "token": "\u00e5\u00a5", "merges": "\u00e5 \u00a5", "raw_count": 180696, "count": 2040652487, "decode_str": "\ufffd"} -{"id": 16385, "token": "\u00e5\u00b7", "merges": "\u00e5 \u00b7", "raw_count": 163786, "count": 2055083824, "decode_str": "\ufffd"} -{"id": 11016, "token": "\u00e9\u0122", "merges": "\u00e9 \u0122", "raw_count": 690455, "count": 2082383346, "decode_str": "\ufffd"} -{"id": 13499, "token": "\u00e9\u0129", "merges": "\u00e9 \u0129", "raw_count": 116052, "count": 2115050388, "decode_str": "\ufffd"} -{"id": 15446, "token": "\u00e5\u00b8", "merges": "\u00e5 \u00b8", "raw_count": 223217, "count": 2149691826, "decode_str": "\ufffd"} -{"id": 18140, "token": "\u00ef\u00bc\u013c", "merges": "\u00ef\u00bc \u013c", "raw_count": 2161095794, "count": 2161095794, "decode_str": "\uff1a"} -{"id": 11827, "token": "\u00e6\u012b", "merges": "\u00e6 \u012b", "raw_count": 205318, "count": 2231383007, "decode_str": "\ufffd"} -{"id": 10674, "token": "\u00e5\u0143", "merges": "\u00e5 \u0143", "raw_count": 156572, "count": 2266970045, "decode_str": "\ufffd"} -{"id": 12462, "token": "\u00e5\u00b9", "merges": "\u00e5 \u00b9", "raw_count": 2195636, "count": 2393692239, "decode_str": "\ufffd"} -{"id": 13610, "token": "\u00e5\u013e\u00a8", "merges": "\u00e5\u013e \u00a8", "raw_count": 2412671111, "count": 2412671111, "decode_str": "\u5728"} -{"id": 12676, "token": "\u00e6\u013f", "merges": "\u00e6 \u013f", "raw_count": 395269, "count": 2418660532, "decode_str": "\ufffd"} -{"id": 3193, "token": "\u00ef\u00bc", "merges": "\u00ef \u00bc", "raw_count": 206721, "count": 2481629575, "decode_str": "\ufffd"} -{"id": 14129, "token": "\u00e8\u00ae", "merges": "\u00e8 \u00ae", "raw_count": 302984, "count": 2517061267, "decode_str": "\ufffd"} -{"id": 171, "token": "\u00ef", "merges": "NULL", "raw_count": 896695, "count": 2528318238, "decode_str": "\ufffd"} -{"id": 12363, "token": "\u00e5\u012f", "merges": "\u00e5 \u012f", "raw_count": 180933, "count": 2538168386, "decode_str": "\ufffd"} -{"id": 20616, "token": "\u00e9\u0139", "merges": "\u00e9 \u0139", "raw_count": 672142, "count": 2555159794, "decode_str": "\ufffd"} -{"id": 13127, "token": "\u00e4\u00bc", "merges": "\u00e4 \u00bc", "raw_count": 257258, "count": 2629748584, "decode_str": "\ufffd"} -{"id": 14377, "token": "\u00e6\u013e\u012b", "merges": "\u00e6\u013e \u012b", "raw_count": 2631575175, "count": 2631575175, "decode_str": "\u6709"} -{"id": 70, "token": "e", "merges": "NULL", "raw_count": 13699767, "count": 2637865285, "decode_str": "e"} -{"id": 17492, "token": "\u00e4\u00ba\u0128", "merges": "\u00e4\u00ba \u0128", "raw_count": 2649584123, "count": 2649584123, "decode_str": "\u4e86"} -{"id": 8587, "token": "\u00e6\u0138", "merges": "\u00e6 \u0138", "raw_count": 179397, "count": 2663763917, "decode_str": "\ufffd"} -{"id": 4746, "token": "\u00e3\u0122\u0123", "merges": "\u00e3\u0122 \u0123", "raw_count": 2722587417, "count": 2722587417, "decode_str": "\u3001"} -{"id": 325, "token": "\u00e2\u0122", "merges": "\u00e2 \u0122", "raw_count": 11434, "count": 2730877246, "decode_str": "\ufffd"} -{"id": 158, "token": "\u00e2", "merges": "NULL", "raw_count": 584213, "count": 2744555149, "decode_str": "\ufffd"} -{"id": 10041, "token": "\u00e5\u013d", "merges": "\u00e5 \u013d", "raw_count": 307394, "count": 2790830828, "decode_str": "\ufffd"} -{"id": 14274, "token": "\u00e4\u00b8\u012f", "merges": "\u00e4\u00b8 \u012f", "raw_count": 2872892383, "count": 2872892383, "decode_str": "\u4e0d"} -{"id": 10460, "token": "\u00e6\u0139", "merges": "\u00e6 \u0139", "raw_count": 578002, "count": 2893310274, "decode_str": "\ufffd"} -{"id": 11894, "token": "\u00e8\u00af", "merges": "\u00e8 \u00af", "raw_count": 918656, "count": 3117094433, "decode_str": "\ufffd"} -{"id": 12755, "token": "\u00e7\u00bb", "merges": "\u00e7 \u00bb", "raw_count": 507390, "count": 3208901900, "decode_str": "\ufffd"} -{"id": 11043, "token": "\u00e5\u012c", "merges": "\u00e5 \u012c", "raw_count": 216141, "count": 3236745327, "decode_str": "\ufffd"} -{"id": 10673, "token": "\u00e5\u00b0", "merges": "\u00e5 \u00b0", "raw_count": 178315, "count": 3243939026, "decode_str": "\ufffd"} -{"id": 9850, "token": "\u00e4\u00b8\u0122", "merges": "\u00e4\u00b8 \u0122", "raw_count": 2974435622, "count": 3463691734, "decode_str": "\u4e00"} -{"id": 7297, "token": "\u00e7\u0136", "merges": "\u00e7 \u0136", "raw_count": 167888, "count": 3639280789, "decode_str": "\ufffd"} -{"id": 12105, "token": "\u00e6\u013a\u00af", "merges": "\u00e6\u013a \u00af", "raw_count": 3652717171, "count": 3652717171, "decode_str": "\u662f"} -{"id": 11871, "token": "\u00e4\u00b9", "merges": "\u00e4 \u00b9", "raw_count": 96000, "count": 3720242828, "decode_str": "\ufffd"} -{"id": 229, "token": "\u0134", "merges": "NULL", "raw_count": 601062984, "count": 3721763971, "decode_str": "\ufffd"} -{"id": 8650, "token": "\u00e6\u012a", "merges": "\u00e6 \u012a", "raw_count": 240575, "count": 3909459256, "decode_str": "\ufffd"} -{"id": 9504, "token": "\u00e5\u013e", "merges": "\u00e5 \u013e", "raw_count": 344020, "count": 3999735095, "decode_str": "\ufffd"} -{"id": 106, "token": "\u00ab", "merges": "NULL", "raw_count": 124173354, "count": 4025519116, "decode_str": "\ufffd"} -{"id": 115, "token": "\u00b5", "merges": "NULL", "raw_count": 25291860, "count": 4127459604, "decode_str": "\ufffd"} -{"id": 104, "token": "\u00a9", "merges": "NULL", "raw_count": 504692126, "count": 4221837691, "decode_str": "\ufffd"} -{"id": 7111, "token": "\u00e4\u00bd", "merges": "\u00e4 \u00bd", "raw_count": 287158, "count": 4236479813, "decode_str": "\ufffd"} -{"id": 112, "token": "\u00b2", "merges": "NULL", "raw_count": 349827826, "count": 4293748861, "decode_str": "\ufffd"} -{"id": 98, "token": "\u00a3", "merges": "NULL", "raw_count": 169908336, "count": 4309357520, "decode_str": "\ufffd"} -{"id": 241, "token": "\u0140", "merges": "NULL", "raw_count": 345779928, "count": 4371186657, "decode_str": "\ufffd"} -{"id": 7719, "token": "\u00e5\u0132", "merges": "\u00e5 \u0132", "raw_count": 230539, "count": 4405785700, "decode_str": "\ufffd"} -{"id": 6765, "token": "\u00e5\u012a", "merges": "\u00e5 \u012a", "raw_count": 250376, "count": 4410080798, "decode_str": "\ufffd"} -{"id": 6916, "token": "\u00e5\u00ae", "merges": "\u00e5 \u00ae", "raw_count": 97164, "count": 4572955274, "decode_str": "\ufffd"} -{"id": 8841, "token": "\u00e6\u013a", "merges": "\u00e6 \u013a", "raw_count": 273945, "count": 4763233343, "decode_str": "\ufffd"} -{"id": 105, "token": "\u00aa", "merges": "NULL", "raw_count": 302713624, "count": 4821010100, "decode_str": "\ufffd"} -{"id": 7056, "token": "\u00e5\u0127", "merges": "\u00e5 \u0127", "raw_count": 152817, "count": 5181640341, "decode_str": "\ufffd"} -{"id": 9078, "token": "\u00e8\u00bf", "merges": "\u00e8 \u00bf", "raw_count": 420317, "count": 5203524069, "decode_str": "\ufffd"} -{"id": 7249, "token": "\u00e5\u00a4", "merges": "\u00e5 \u00a4", "raw_count": 240662, "count": 5412273756, "decode_str": "\ufffd"} -{"id": 113, "token": "\u00b3", "merges": "NULL", "raw_count": 141232735, "count": 5417249187, "decode_str": "\ufffd"} -{"id": 230, "token": "\u0135", "merges": "NULL", "raw_count": 580328106, "count": 5475123678, "decode_str": "\ufffd"} -{"id": 107, "token": "\u00ac", "merges": "NULL", "raw_count": 352270980, "count": 5595639797, "decode_str": "\ufffd"} -{"id": 97, "token": "\u00a2", "merges": "NULL", "raw_count": 246546347, "count": 5735040652, "decode_str": "\ufffd"} -{"id": 4340, "token": "\u00e3\u0122\u0124", "merges": "\u00e3\u0122 \u0124", "raw_count": 5937041850, "count": 5937041850, "decode_str": "\u3002"} -{"id": 232, "token": "\u0137", "merges": "NULL", "raw_count": 58027574, "count": 6077305498, "decode_str": "\ufffd"} -{"id": 243, "token": "\u0142", "merges": "NULL", "raw_count": 55710557, "count": 6129329782, "decode_str": "\ufffd"} -{"id": 209, "token": "\u0120", "merges": "NULL", "raw_count": 3683673729, "count": 6420745310, "decode_str": " "} -{"id": 5690, "token": "\u00e4\u00bb", "merges": "\u00e4 \u00bb", "raw_count": 312561, "count": 6496501122, "decode_str": "\ufffd"} -{"id": 5959, "token": "\u00e6\u013e", "merges": "\u00e6 \u013e", "raw_count": 158330, "count": 6563158363, "decode_str": "\ufffd"} -{"id": 111, "token": "\u00b1", "merges": "NULL", "raw_count": 302448942, "count": 6605192535, "decode_str": "\ufffd"} -{"id": 117, "token": "\u00b7", "merges": "NULL", "raw_count": 55221819, "count": 6624925638, "decode_str": "\ufffd"} -{"id": 5941, "token": "\u00e5\u0131", "merges": "\u00e5 \u0131", "raw_count": 239089, "count": 6652432169, "decode_str": "\ufffd"} -{"id": 116, "token": "\u00b6", "merges": "NULL", "raw_count": 254050102, "count": 6985015295, "decode_str": "\ufffd"} -{"id": 233, "token": "\u0138", "merges": "NULL", "raw_count": 168597256, "count": 6998138359, "decode_str": "\ufffd"} -{"id": 236, "token": "\u013b", "merges": "NULL", "raw_count": 152323245, "count": 7111054997, "decode_str": "\ufffd"} -{"id": 101, "token": "\u00a6", "merges": "NULL", "raw_count": 268861703, "count": 7132600694, "decode_str": "\ufffd"} -{"id": 96, "token": "\u00a1", "merges": "NULL", "raw_count": 391290382, "count": 7764424811, "decode_str": "\ufffd"} -{"id": 102, "token": "\u00a7", "merges": "NULL", "raw_count": 231580085, "count": 7856133109, "decode_str": "\ufffd"} -{"id": 222, "token": "\u012d", "merges": "NULL", "raw_count": 306728910, "count": 7921444864, "decode_str": "\ufffd"} -{"id": 242, "token": "\u0141", "merges": "NULL", "raw_count": 216832774, "count": 8018451661, "decode_str": "\ufffd"} -{"id": 214, "token": "\u0125", "merges": "NULL", "raw_count": 611549351, "count": 8054594638, "decode_str": "\ufffd"} -{"id": 124, "token": "\u00be", "merges": "NULL", "raw_count": 373348362, "count": 8157167004, "decode_str": "\ufffd"} -{"id": 240, "token": "\u013f", "merges": "NULL", "raw_count": 107079434, "count": 8355095887, "decode_str": "\ufffd"} -{"id": 114, "token": "\u00b4", "merges": "NULL", "raw_count": 190455748, "count": 8492342699, "decode_str": "\ufffd"} -{"id": 99, "token": "\u00a4", "merges": "NULL", "raw_count": 244889271, "count": 8572111176, "decode_str": "\ufffd"} -{"id": 228, "token": "\u0133", "merges": "NULL", "raw_count": 424730549, "count": 8779771323, "decode_str": "\ufffd"} -{"id": 5494, "token": "\u00e4\u00ba", "merges": "\u00e4 \u00ba", "raw_count": 609814, "count": 9033807532, "decode_str": "\ufffd"} -{"id": 238, "token": "\u013d", "merges": "NULL", "raw_count": 184247074, "count": 9141868841, "decode_str": "\ufffd"} -{"id": 223, "token": "\u012e", "merges": "NULL", "raw_count": 418838752, "count": 9179079770, "decode_str": "\ufffd"} -{"id": 122, "token": "\u00bc", "merges": "NULL", "raw_count": 191020395, "count": 9187175346, "decode_str": "\ufffd"} -{"id": 244, "token": "\u0143", "merges": "NULL", "raw_count": 406848235, "count": 9200969305, "decode_str": "\ufffd"} -{"id": 221, "token": "\u012c", "merges": "NULL", "raw_count": 59161179, "count": 9293701798, "decode_str": "\ufffd"} -{"id": 218, "token": "\u0129", "merges": "NULL", "raw_count": 228069429, "count": 9311016245, "decode_str": "\ufffd"} -{"id": 217, "token": "\u0128", "merges": "NULL", "raw_count": 267961569, "count": 9404273942, "decode_str": "\ufffd"} -{"id": 225, "token": "\u0130", "merges": "NULL", "raw_count": 52150964, "count": 9410773797, "decode_str": "\ufffd"} -{"id": 235, "token": "\u013a", "merges": "NULL", "raw_count": 225209048, "count": 9576406006, "decode_str": "\ufffd"} -{"id": 234, "token": "\u0139", "merges": "NULL", "raw_count": 363764246, "count": 9687390995, "decode_str": "\ufffd"} -{"id": 2155, "token": "\u00e3\u0122", "merges": "\u00e3 \u0122", "raw_count": 409, "count": 9765951908, "decode_str": "\ufffd"} -{"id": 159, "token": "\u00e3", "merges": "NULL", "raw_count": 103764, "count": 9767304196, "decode_str": "\ufffd"} -{"id": 227, "token": "\u0132", "merges": "NULL", "raw_count": 776122916, "count": 9806403150, "decode_str": "\ufffd"} -{"id": 231, "token": "\u0136", "merges": "NULL", "raw_count": 424580919, "count": 10052098183, "decode_str": "\ufffd"} -{"id": 103, "token": "\u00a8", "merges": "NULL", "raw_count": 257010916, "count": 10065874801, "decode_str": "\ufffd"} -{"id": 216, "token": "\u0127", "merges": "NULL", "raw_count": 488718929, "count": 10324805365, "decode_str": "\ufffd"} -{"id": 5225, "token": "\u00e7\u013c\u0126", "merges": "\u00e7\u013c \u0126", "raw_count": 10567838918, "count": 10567838918, "decode_str": "\u7684"} -{"id": 100, "token": "\u00a5", "merges": "NULL", "raw_count": 686797694, "count": 10678616267, "decode_str": "\ufffd"} -{"id": 5138, "token": "\u00e7\u013c", "merges": "\u00e7 \u013c", "raw_count": 147771, "count": 10736204837, "decode_str": "\ufffd"} -{"id": 220, "token": "\u012b", "merges": "NULL", "raw_count": 144008498, "count": 11213895999, "decode_str": "\ufffd"} -{"id": 212, "token": "\u0123", "merges": "NULL", "raw_count": 414117950, "count": 11335881692, "decode_str": "\ufffd"} -{"id": 224, "token": "\u012f", "merges": "NULL", "raw_count": 511855183, "count": 11397438244, "decode_str": "\ufffd"} -{"id": 110, "token": "\u00b0", "merges": "NULL", "raw_count": 169156823, "count": 11429706031, "decode_str": "\ufffd"} -{"id": 119, "token": "\u00b9", "merges": "NULL", "raw_count": 285031824, "count": 11474464164, "decode_str": "\ufffd"} -{"id": 226, "token": "\u0131", "merges": "NULL", "raw_count": 232343667, "count": 12114562525, "decode_str": "\ufffd"} -{"id": 213, "token": "\u0124", "merges": "NULL", "raw_count": 224164285, "count": 12155002123, "decode_str": "\ufffd"} -{"id": 125, "token": "\u00bf", "merges": "NULL", "raw_count": 629694590, "count": 12211406635, "decode_str": "\ufffd"} -{"id": 108, "token": "\u00ae", "merges": "NULL", "raw_count": 316450372, "count": 12347130400, "decode_str": "\ufffd"} -{"id": 123, "token": "\u00bd", "merges": "NULL", "raw_count": 279201642, "count": 13126931115, "decode_str": "\ufffd"} -{"id": 109, "token": "\u00af", "merges": "NULL", "raw_count": 366032561, "count": 13707925554, "decode_str": "\ufffd"} -{"id": 219, "token": "\u012a", "merges": "NULL", "raw_count": 120061762, "count": 14081076269, "decode_str": "\ufffd"} -{"id": 121, "token": "\u00bb", "merges": "NULL", "raw_count": 548317365, "count": 15352869292, "decode_str": "\ufffd"} -{"id": 215, "token": "\u0126", "merges": "NULL", "raw_count": 165881945, "count": 15357920251, "decode_str": "\ufffd"} -{"id": 13, "token": ",", "merges": "NULL", "raw_count": 14950977748, "count": 15382517639, "decode_str": ","} -{"id": 239, "token": "\u013e", "merges": "NULL", "raw_count": 357654147, "count": 16754655257, "decode_str": "\ufffd"} -{"id": 3218, "token": "\u00e4\u00b8", "merges": "\u00e4 \u00b8", "raw_count": 147039, "count": 18322645039, "decode_str": "\ufffd"} -{"id": 237, "token": "\u013c", "merges": "NULL", "raw_count": 290457124, "count": 19566586049, "decode_str": "\ufffd"} -{"id": 120, "token": "\u00ba", "merges": "NULL", "raw_count": 186284617, "count": 21454382171, "decode_str": "\ufffd"} -{"id": 165, "token": "\u00e9", "merges": "NULL", "raw_count": 2141694037, "count": 22063906362, "decode_str": "\ufffd"} -{"id": 118, "token": "\u00b8", "merges": "NULL", "raw_count": 216292851, "count": 23796573743, "decode_str": "\ufffd"} -{"id": 211, "token": "\u0122", "merges": "NULL", "raw_count": 119104707, "count": 27100899398, "decode_str": "\ufffd"} -{"id": 164, "token": "\u00e8", "merges": "NULL", "raw_count": 2384605604, "count": 35376914820, "decode_str": "\ufffd"} -{"id": 163, "token": "\u00e7", "merges": "NULL", "raw_count": 1836974201, "count": 44115394042, "decode_str": "\ufffd"} -{"id": 160, "token": "\u00e4", "merges": "NULL", "raw_count": 38514, "count": 46332413548, "decode_str": "\ufffd"} -{"id": 162, "token": "\u00e6", "merges": "NULL", "raw_count": 1606856607, "count": 58198612869, "decode_str": "\ufffd"} -{"id": 161, "token": "\u00e5", "merges": "NULL", "raw_count": 1371809397, "count": 89854923589, "decode_str": "\ufffd"}