jondurbin commited on
Commit
9ef172d
·
verified ·
1 Parent(s): 26be152

Upload tokenizer

Browse files
Files changed (2) hide show
  1. special_tokens_map.json +0 -12
  2. tokenizer_config.json +4 -14
special_tokens_map.json CHANGED
@@ -1,9 +1,4 @@
1
  {
2
- "additional_special_tokens": [
3
- "<unk>",
4
- "<s>",
5
- "</s>"
6
- ],
7
  "bos_token": {
8
  "content": "<s>",
9
  "lstrip": false,
@@ -18,13 +13,6 @@
18
  "rstrip": false,
19
  "single_word": false
20
  },
21
- "pad_token": {
22
- "content": "<unk>",
23
- "lstrip": false,
24
- "normalized": false,
25
- "rstrip": false,
26
- "single_word": false
27
- },
28
  "unk_token": {
29
  "content": "<unk>",
30
  "lstrip": false,
 
1
  {
 
 
 
 
 
2
  "bos_token": {
3
  "content": "<s>",
4
  "lstrip": false,
 
13
  "rstrip": false,
14
  "single_word": false
15
  },
 
 
 
 
 
 
 
16
  "unk_token": {
17
  "content": "<unk>",
18
  "lstrip": false,
tokenizer_config.json CHANGED
@@ -27,27 +27,17 @@
27
  "special": true
28
  }
29
  },
30
- "additional_special_tokens": [
31
- "<unk>",
32
- "<s>",
33
- "</s>"
34
- ],
35
  "bos_token": "<s>",
36
  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token + ' ' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
37
  "clean_up_tokenization_spaces": false,
38
  "eos_token": "</s>",
39
  "legacy": true,
40
- "max_length": 2048,
41
- "model_max_length": 2048,
42
- "pad_token": "<unk>",
43
  "sp_model_kwargs": {},
44
  "spaces_between_special_tokens": false,
45
- "stride": 0,
46
  "tokenizer_class": "LlamaTokenizer",
47
- "truncation_side": "left",
48
- "truncation_strategy": "longest_first",
49
- "trust_remote_code": false,
50
  "unk_token": "<unk>",
51
- "use_default_system_prompt": false,
52
- "use_fast": true
53
  }
 
27
  "special": true
28
  }
29
  },
30
+ "additional_special_tokens": [],
 
 
 
 
31
  "bos_token": "<s>",
32
  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token + ' ' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
33
  "clean_up_tokenization_spaces": false,
34
  "eos_token": "</s>",
35
  "legacy": true,
36
+ "model_max_length": 1000000000000000019884624838656,
37
+ "pad_token": null,
 
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
  }