gianlucar commited on
Commit
d490381
1 Parent(s): c82ac68

Upload tokenizer

Browse files
Files changed (2) hide show
  1. tokenizer.model +2 -2
  2. tokenizer_config.json +5 -28
tokenizer.model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
- size 499723
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json CHANGED
@@ -25,42 +25,19 @@
25
  "rstrip": false,
26
  "single_word": false,
27
  "special": true
28
- },
29
- "32000": {
30
- "content": "[PAD]",
31
- "lstrip": false,
32
- "normalized": false,
33
- "rstrip": false,
34
- "single_word": false,
35
- "special": true
36
- },
37
- "32001": {
38
- "content": "<|im_start|>",
39
- "lstrip": false,
40
- "normalized": true,
41
- "rstrip": false,
42
- "single_word": false,
43
- "special": false
44
- },
45
- "32002": {
46
- "content": "<|im_end|>",
47
- "lstrip": false,
48
- "normalized": true,
49
- "rstrip": false,
50
- "single_word": false,
51
- "special": false
52
  }
53
  },
 
54
  "bos_token": "<s>",
 
55
  "clean_up_tokenization_spaces": false,
56
  "eos_token": "</s>",
57
- "legacy": false,
58
- "model_max_length": 4096,
59
  "pad_token": "</s>",
60
- "padding_side": "right",
61
  "sp_model_kwargs": {},
62
  "spaces_between_special_tokens": false,
63
  "tokenizer_class": "LlamaTokenizer",
64
  "unk_token": "<unk>",
65
- "use_default_system_prompt": true
66
  }
 
25
  "rstrip": false,
26
  "single_word": false,
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": "</s>",
 
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
  }