batterydata commited on
Commit
27725da
1 Parent(s): eab08da
Files changed (2) hide show
  1. tokenizer.json +0 -0
  2. tokenizer_config.json +1 -1
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
tokenizer_config.json CHANGED
@@ -1 +1 @@
1
- {"do_lower_case": true, "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": "/projects/SolarWindowsADSP/shu/models/revision/bert/batteryscibert-cased/", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}
1
+ {"do_lower_case": false, "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": "allenai/scibert_scivocab_cased", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}