Reizendretail commited on
Commit
8f2521b
1 Parent(s): 3c18151

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +7 -1
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +32 -24
special_tokens_map.json CHANGED
@@ -13,7 +13,13 @@
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
- "pad_token": "<unk>",
 
 
 
 
 
 
17
  "unk_token": {
18
  "content": "<unk>",
19
  "lstrip": false,
 
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
+ "pad_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
  "unk_token": {
24
  "content": "<unk>",
25
  "lstrip": false,
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,35 +1,43 @@
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": false,
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": false,
18
- "rstrip": false,
19
- "single_word": false
20
- },
21
  "legacy": false,
22
  "model_max_length": 4096,
23
- "pad_token": null,
24
  "padding_side": "right",
25
  "sp_model_kwargs": {},
 
26
  "tokenizer_class": "LlamaTokenizer",
27
- "unk_token": {
28
- "__type": "AddedToken",
29
- "content": "<unk>",
30
- "lstrip": false,
31
- "normalized": false,
32
- "rstrip": false,
33
- "single_word": false
34
- }
35
  }
 
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": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
  },
30
+ "bos_token": "<s>",
31
+ "chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{ 'USER: ' + message['content'].strip() + '\n'}}{% elif message['role'] == 'system' %}{{message['content'].strip() + '\n\n' }}{% elif message['role'] == 'assistant' %}{{ 'ASSISTANT: ' + message['content'] + '</s> \n'}}{% endif %}{% endfor %}",
32
  "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
 
 
 
 
 
 
 
34
  "legacy": false,
35
  "model_max_length": 4096,
36
+ "pad_token": "<unk>",
37
  "padding_side": "right",
38
  "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
  "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false
 
 
 
 
 
 
43
  }