Thabet commited on
Commit
42529c7
1 Parent(s): ec9beee

Upload tokenizer_config.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +15 -0
tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "<s>",
5
+ "do_lower_case": true,
6
+ "eos_token": "</s>",
7
+ "mask_token": "<mask>",
8
+ "model_max_length": 512,
9
+ "pad_token": "<pad>",
10
+ "sep_token": "</s>",
11
+ "strip_accents": null,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "MPNetTokenizer",
14
+ "unk_token": "[UNK]"
15
+ }