diiogofernands commited on
Commit
8a69515
·
verified ·
1 Parent(s): 774cd47

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 sha256:609d8f4c067cd3950f88594c5a802616cea245823836ef5848ee4fc40aab5b6f
3
+ size 34363188
tokenizer_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<bos>",
4
+ "clean_up_tokenization_spaces": false,
5
+ "cls_token": "<bos>",
6
+ "eos_token": "<eos>",
7
+ "extra_special_tokens": [
8
+ "<start_of_turn>",
9
+ "<end_of_turn>"
10
+ ],
11
+ "is_local": true,
12
+ "mask_token": "<mask>",
13
+ "model_input_names": [
14
+ "input_ids",
15
+ "attention_mask"
16
+ ],
17
+ "model_max_length": 2048,
18
+ "pad_token": "<pad>",
19
+ "padding_side": "right",
20
+ "sep_token": "<eos>",
21
+ "spaces_between_special_tokens": false,
22
+ "tokenizer_class": "TokenizersBackend",
23
+ "unk_token": "<unk>"
24
+ }