mlabonne commited on
Commit
55a736c
1 Parent(s): 1820413

Upload tokenizer

Browse files
Files changed (2) hide show
  1. tokenizer.json +1 -10
  2. tokenizer_config.json +30 -24
tokenizer.json CHANGED
@@ -9,7 +9,7 @@
9
  "single_word": false,
10
  "lstrip": false,
11
  "rstrip": false,
12
- "normalized": false,
13
  "special": true
14
  },
15
  {
@@ -29,15 +29,6 @@
29
  "rstrip": false,
30
  "normalized": true,
31
  "special": true
32
- },
33
- {
34
- "id": 32000,
35
- "content": "<pad>",
36
- "single_word": false,
37
- "lstrip": false,
38
- "rstrip": false,
39
- "normalized": true,
40
- "special": false
41
  }
42
  ],
43
  "normalizer": {
 
9
  "single_word": false,
10
  "lstrip": false,
11
  "rstrip": false,
12
+ "normalized": true,
13
  "special": true
14
  },
15
  {
 
29
  "rstrip": false,
30
  "normalized": true,
31
  "special": true
 
 
 
 
 
 
 
 
 
32
  }
33
  ],
34
  "normalizer": {
tokenizer_config.json CHANGED
@@ -1,32 +1,38 @@
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
  "legacy": false,
20
  "model_max_length": 1000000000000000019884624838656,
21
- "pad_token": null,
22
  "sp_model_kwargs": {},
23
  "tokenizer_class": "LlamaTokenizer",
24
- "unk_token": {
25
- "__type": "AddedToken",
26
- "content": "<unk>",
27
- "lstrip": false,
28
- "normalized": true,
29
- "rstrip": false,
30
- "single_word": false
31
- }
32
  }
 
1
  {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": true,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
  },
28
+ "bos_token": "<s>",
29
  "clean_up_tokenization_spaces": false,
30
+ "eos_token": "</s>",
 
 
 
 
 
 
 
31
  "legacy": false,
32
  "model_max_length": 1000000000000000019884624838656,
33
+ "pad_token": "</s>",
34
  "sp_model_kwargs": {},
35
  "tokenizer_class": "LlamaTokenizer",
36
+ "unk_token": "<unk>",
37
+ "use_default_system_prompt": false
 
 
 
 
 
 
38
  }