Elfrino commited on
Commit
1e358e6
1 Parent(s): bd15004

Update tokenizer_config.json

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +30 -47
tokenizer_config.json CHANGED
@@ -1,52 +1,35 @@
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
- "32000": {
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": 2048,
44
- "pad_token": "[PAD]",
45
- "padding_side": "left",
 
 
 
 
 
 
 
46
  "sp_model_kwargs": {},
47
  "spaces_between_special_tokens": false,
48
  "tokenizer_class": "LlamaTokenizer",
49
- "unk_token": "<unk>",
50
- "use_default_system_prompt": false,
51
- "use_fast": true
52
- }
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "__type": "AddedToken",
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
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": false,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "legacy": false,
20
+ "model_max_length": 1000000000000000019884624838656,
21
+ "pad_token": null,
22
+ "padding_side": "right",
23
  "sp_model_kwargs": {},
24
  "spaces_between_special_tokens": false,
25
  "tokenizer_class": "LlamaTokenizer",
26
+ "unk_token": {
27
+ "__type": "AddedToken",
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ },
34
+ "use_default_system_prompt": true
35
+ }