Pedram Rostami commited on
Commit
569a004
1 Parent(s): 6a64379

Update tokenizer_config.json

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +41 -24
tokenizer_config.json CHANGED
@@ -1,33 +1,50 @@
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
  "model_max_length": 1000000000000000019884624838656,
22
- "pad_token": null,
23
  "sp_model_kwargs": {},
 
24
  "tokenizer_class": "LlamaTokenizer",
25
- "unk_token": {
26
- "__type": "AddedToken",
27
- "content": "<unk>",
28
- "lstrip": false,
29
- "normalized": true,
30
- "rstrip": false,
31
- "single_word": false
32
- }
33
  }
 
1
  {
2
  "add_bos_token": true,
3
  "add_eos_token": false,
4
+ "add_prefix_space": true,
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
+ "41509": {
31
+ "content": "[PAD]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ }
38
  },
39
+ "bos_token": "<s>",
40
  "clean_up_tokenization_spaces": false,
41
+ "eos_token": "</s>",
42
+ "legacy": true,
 
 
 
 
 
 
43
  "model_max_length": 1000000000000000019884624838656,
44
+ "pad_token": "[PAD]",
45
  "sp_model_kwargs": {},
46
+ "spaces_between_special_tokens": false,
47
  "tokenizer_class": "LlamaTokenizer",
48
+ "unk_token": "<unk>",
49
+ "use_default_system_prompt": false
 
 
 
 
 
 
50
  }