Davlan commited on
Commit
791ec32
1 Parent(s): 2f80fa5

Upload tokenizer_config.json

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +19 -0
tokenizer_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "__type": "AddedToken",
7
+ "content": "<mask>",
8
+ "lstrip": true,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "model_max_length": 512,
14
+ "pad_token": "<pad>",
15
+ "sep_token": "</s>",
16
+ "special_tokens_map_file": null,
17
+ "tokenizer_class": "XLMRobertaTokenizer",
18
+ "unk_token": "<unk>"
19
+ }