mlabonne commited on
Commit
cc48fe7
1 Parent(s): ca25f7c

Upload tokenizer

Browse files
special_tokens_map.json CHANGED
@@ -1,6 +1,23 @@
1
  {
2
- "bos_token": "<s>",
3
- "eos_token": "</s>",
4
- "pad_token": "[PAD]",
5
- "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6
  }
 
1
  {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
  }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,6 +1,4 @@
1
  {
2
- "add_bos_token": true,
3
- "add_eos_token": false,
4
  "bos_token": {
5
  "__type": "AddedToken",
6
  "content": "<s>",
@@ -22,9 +20,7 @@
22
  "model_max_length": 1000000000000000019884624838656,
23
  "pad_token": null,
24
  "sp_model_kwargs": {},
25
- "spaces_between_special_tokens": false,
26
  "tokenizer_class": "LlamaTokenizer",
27
- "trust_remote_code": false,
28
  "unk_token": {
29
  "__type": "AddedToken",
30
  "content": "<unk>",
@@ -33,6 +29,5 @@
33
  "rstrip": false,
34
  "single_word": false
35
  },
36
- "use_default_system_prompt": true,
37
- "use_fast": true
38
  }
 
1
  {
 
 
2
  "bos_token": {
3
  "__type": "AddedToken",
4
  "content": "<s>",
 
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>",
 
29
  "rstrip": false,
30
  "single_word": false
31
  },
32
+ "use_default_system_prompt": true
 
33
  }