svassileva commited on
Commit
037d22d
·
verified ·
1 Parent(s): c150b5a

Upload tokenizer

Browse files
Files changed (3) hide show
  1. .gitattributes +1 -0
  2. tokenizer.json +3 -0
  3. tokenizer_config.json +24 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afa602b67b7d4f3188dbb004e3daf4a5dc676612bfe7ea362a7f46b44e050d87
3
+ size 16781407
tokenizer_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<s>",
5
+ "cls_token": "<s>",
6
+ "eos_token": "</s>",
7
+ "extra_special_tokens": [
8
+ "<s>",
9
+ "</s>"
10
+ ],
11
+ "is_local": true,
12
+ "local_files_only": false,
13
+ "mask_token": "<mask>",
14
+ "max_length": 512,
15
+ "model_max_length": 512,
16
+ "pad_token": "<pad>",
17
+ "sep_token": "</s>",
18
+ "stride": 128,
19
+ "tokenizer_class": "XLMRobertaTokenizer",
20
+ "truncation_side": "right",
21
+ "truncation_strategy": "longest_first",
22
+ "unk_id": 0,
23
+ "unk_token": "<unk>"
24
+ }