efederici commited on
Commit
19fdcd0
1 Parent(s): cd046d4

Upload tokenizer

Browse files
Files changed (2) hide show
  1. tokenizer.json +0 -0
  2. tokenizer_config.json +2 -1
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -32,7 +32,7 @@
32
  "normalized": false,
33
  "rstrip": false,
34
  "single_word": false,
35
- "special": false
36
  },
37
  "32001": {
38
  "content": "<|im_start|>",
@@ -45,6 +45,7 @@
45
  },
46
  "additional_special_tokens": [],
47
  "bos_token": "<s>",
 
48
  "clean_up_tokenization_spaces": false,
49
  "eos_token": "<|im_end|>",
50
  "legacy": true,
 
32
  "normalized": false,
33
  "rstrip": false,
34
  "single_word": false,
35
+ "special": true
36
  },
37
  "32001": {
38
  "content": "<|im_start|>",
 
45
  },
46
  "additional_special_tokens": [],
47
  "bos_token": "<s>",
48
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
49
  "clean_up_tokenization_spaces": false,
50
  "eos_token": "<|im_end|>",
51
  "legacy": true,