owaiskha9654 commited on
Commit
8026337
1 Parent(s): a5ae6e5

add tokenizer

Browse files
Files changed (2) hide show
  1. tokenizer_config.json +1 -1
  2. vocab.txt +0 -0
tokenizer_config.json CHANGED
@@ -1 +1 @@
1
- {"do_lower_case": true, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-uncased", "tokenizer_class": "BertTokenizer"}
 
1
+ {"do_lower_case": true, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "name_or_path": "dmis-lab/biobert-base-cased-v1.2", "tokenizer_class": "BertTokenizer"}
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff