lisaterumi commited on
Commit
2d34d57
1 Parent(s): db34103

Upload tokenizer_config.json

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +16 -1
tokenizer_config.json CHANGED
@@ -1 +1,16 @@
1
- {"do_lower_case": true, "max_len": 512}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_basic_tokenize": true,
4
+ "do_lower_case": false,
5
+ "mask_token": "[MASK]",
6
+ "max_len": 512,
7
+ "name_or_path": "pucpr/biobertpt-all",
8
+ "never_split": null,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "special_tokens_map_file": "/root/.cache/huggingface/transformers/d06bbe0fda9ebb9f6c4f5d8534f84d0c6b4c14dbbf3db080008e582a7caa9e61.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d",
12
+ "strip_accents": null,
13
+ "tokenize_chinese_chars": true,
14
+ "tokenizer_class": "BertTokenizer",
15
+ "unk_token": "[UNK]"
16
+ }