asaoka commited on
Commit
4615512
1 Parent(s): a1a8f50

Upload tokenizer

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +23 -30
tokenizer_config.json CHANGED
@@ -1,41 +1,34 @@
1
  {
2
  "add_bos_token": true,
3
  "add_eos_token": false,
4
- "added_tokens_decoder": {
5
- "0": {
6
- "content": "<unk>",
7
- "lstrip": false,
8
- "normalized": true,
9
- "rstrip": false,
10
- "single_word": false,
11
- "special": true
12
- },
13
- "1": {
14
- "content": "<s>",
15
- "lstrip": false,
16
- "normalized": true,
17
- "rstrip": false,
18
- "single_word": false,
19
- "special": true
20
- },
21
- "2": {
22
- "content": "</s>",
23
- "lstrip": false,
24
- "normalized": true,
25
- "rstrip": false,
26
- "single_word": false,
27
- "special": true
28
- }
29
  },
30
- "bos_token": "<s>",
31
  "clean_up_tokenization_spaces": false,
32
- "eos_token": "</s>",
 
 
 
 
 
 
 
33
  "legacy": true,
34
  "model_max_length": 1000000000000000019884624838656,
35
  "pad_token": null,
36
  "sp_model_kwargs": {},
37
- "spaces_between_special_tokens": false,
38
  "tokenizer_class": "LlamaTokenizer",
39
- "unk_token": "<unk>",
40
- "use_default_system_prompt": false
 
 
 
 
 
 
41
  }
 
1
  {
2
  "add_bos_token": true,
3
  "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  },
 
12
  "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
  "legacy": true,
22
  "model_max_length": 1000000000000000019884624838656,
23
  "pad_token": null,
24
  "sp_model_kwargs": {},
 
25
  "tokenizer_class": "LlamaTokenizer",
26
+ "unk_token": {
27
+ "__type": "AddedToken",
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
  }