ponik7 commited on
Commit
94b55e7
·
verified ·
1 Parent(s): 1145bda

Upload tokenizer

Browse files
Files changed (3) hide show
  1. .gitattributes +1 -0
  2. tokenizer.json +3 -0
  3. tokenizer_config.json +16 -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 sha256:5df1f55d60c9705a501ab9a75550728625740741fe4be308dac4806c16b7d51d
3
+ size 17098085
tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<s>",
5
+ "clean_up_tokenization_spaces": true,
6
+ "cls_token": "<s>",
7
+ "eos_token": "</s>",
8
+ "is_local": true,
9
+ "mask_token": "<mask>",
10
+ "model_max_length": 8192,
11
+ "pad_token": "<pad>",
12
+ "sep_token": "</s>",
13
+ "sp_model_kwargs": {},
14
+ "tokenizer_class": "XLMRobertaTokenizer",
15
+ "unk_token": "<unk>"
16
+ }