fxmarty commited on
Commit
ba06efd
1 Parent(s): cf073a5

Upload folder using huggingface_hub

Browse files
Files changed (2) hide show
  1. tokenizer.json +0 -0
  2. tokenizer_config.json +23 -33
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,41 +1,31 @@
1
  {
2
- "add_bos_token": true,
3
- "add_eos_token": false,
4
- "add_prefix_space": null,
5
- "added_tokens_decoder": {
6
- "0": {
7
- "content": "<unk>",
8
- "lstrip": false,
9
- "normalized": true,
10
- "rstrip": false,
11
- "single_word": false,
12
- "special": true
13
- },
14
- "1": {
15
- "content": "<s>",
16
- "lstrip": false,
17
- "normalized": true,
18
- "rstrip": false,
19
- "single_word": false,
20
- "special": true
21
- },
22
- "2": {
23
- "content": "</s>",
24
- "lstrip": false,
25
- "normalized": true,
26
- "rstrip": false,
27
- "single_word": false,
28
- "special": true
29
- }
30
  },
31
- "bos_token": "<s>",
32
  "clean_up_tokenization_spaces": false,
33
- "eos_token": "</s>",
34
- "legacy": true,
 
 
 
 
 
 
35
  "model_max_length": 2048,
36
  "pad_token": null,
37
  "sp_model_kwargs": {},
38
  "tokenizer_class": "LlamaTokenizer",
39
- "unk_token": "<unk>",
40
- "use_default_system_prompt": false
 
 
 
 
 
 
41
  }
 
1
  {
2
+ "bos_token": {
3
+ "__type": "AddedToken",
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9
  },
 
10
  "clean_up_tokenization_spaces": false,
11
+ "eos_token": {
12
+ "__type": "AddedToken",
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
  "model_max_length": 2048,
20
  "pad_token": null,
21
  "sp_model_kwargs": {},
22
  "tokenizer_class": "LlamaTokenizer",
23
+ "unk_token": {
24
+ "__type": "AddedToken",
25
+ "content": "<unk>",
26
+ "lstrip": false,
27
+ "normalized": true,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
  }