junnyu commited on
Commit
e4b0463
1 Parent(s): a9bfcd9

Create tokenizer_config.json

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +17 -0
tokenizer_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_lower_case": true,
3
+ "do_basic_tokenize": true,
4
+ "never_split": null,
5
+ "unk_token": "[UNK]",
6
+ "sep_token": "[SEP]",
7
+ "pad_token": "[PAD]",
8
+ "cls_token": "[CLS]",
9
+ "mask_token": "[MASK]",
10
+ "tokenize_chinese_chars": true,
11
+ "strip_accents": null,
12
+ "model_max_length": 1536,
13
+ "special_tokens_map_file": null,
14
+ "tokenizer_file": null,
15
+ "name_or_path": "junnyu/roformer_chinese_base",
16
+ "tokenizer_class": "RoFormerTokenizer"
17
+ }