ken-miller commited on
Commit
4ebebad
·
verified ·
1 Parent(s): 11510a1

Upload tokenizer

Browse files
Files changed (2) hide show
  1. special_tokens_map.json +5 -0
  2. tokenizer_config.json +8 -2
special_tokens_map.json CHANGED
@@ -1,4 +1,9 @@
1
  {
 
 
 
 
 
2
  "bos_token": {
3
  "content": "<s>",
4
  "lstrip": false,
 
1
  {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>"
6
+ ],
7
  "bos_token": {
8
  "content": "<s>",
9
  "lstrip": false,
tokenizer_config.json CHANGED
@@ -27,7 +27,11 @@
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,
@@ -42,6 +46,8 @@
42
  "tokenizer_class": "LlamaTokenizer",
43
  "truncation_side": "right",
44
  "truncation_strategy": "longest_first",
 
45
  "unk_token": "<unk>",
46
- "use_default_system_prompt": false
 
47
  }
 
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,
 
46
  "tokenizer_class": "LlamaTokenizer",
47
  "truncation_side": "right",
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
  }