diff --git "a/tokenizer.json" "b/tokenizer.json" new file mode 100644--- /dev/null +++ "b/tokenizer.json" @@ -0,0 +1,512190 @@ +{ + "version": "1.0", + "truncation": null, + "padding": null, + "added_tokens": [ + { + "id": 0, + "content": "[PAD]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 1, + "content": "[CLS]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 2, + "content": "[SEP]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 3, + "content": "[UNK]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": true, + "special": true + }, + { + "id": 128000, + "content": "[MASK]", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 128001, + "content": "<