Xenova HF staff commited on
Commit
abb3db1
1 Parent(s): f87fc79

Update tokenizer

Browse files
special_tokens_map.json CHANGED
@@ -1,7 +1,23 @@
1
  {
2
- "bos_token": "<s>",
3
- "eos_token": "</s>",
4
- "unk_token": "<unk>",
5
- "b_inst": "[INST]",
6
- "e_inst": "[/INST]"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  }
 
1
  {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
3
+ size 587404
tokenizer.model.v3 ADDED
Binary file (587 kB). View file
 
tokenizer_config.json CHANGED
The diff for this file is too large to render. See raw diff