Update tokenizer_config.json
Browse files- tokenizer_config.json +1 -1
tokenizer_config.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": false, "strip_accents":
|
|
|
1 |
+
{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": false, "strip_accents": true, "clean_text": false, "model_max_length": 512, "do_basic_tokenize": true, "never_split": null, "special_tokens_map_file": "char-bert-base-uncased/special_tokens_map.json", "name_or_path": "char-bert-base-uncased", "tokenizer_class": "BertTokenizer"}
|