teowu commited on
Commit
5186e10
1 Parent(s): b867711

Upload tokenizer_config.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +3 -19
tokenizer_config.json CHANGED
@@ -10,28 +10,12 @@
10
  "rstrip": false,
11
  "single_word": false,
12
  "special": true
13
- },
14
- "100352": {
15
- "content": "<s>",
16
- "lstrip": false,
17
- "normalized": false,
18
- "rstrip": false,
19
- "single_word": false,
20
- "special": true
21
- },
22
- "100353": {
23
- "content": "</s>",
24
- "lstrip": false,
25
- "normalized": false,
26
- "rstrip": false,
27
- "single_word": false,
28
- "special": true
29
  }
30
  },
31
- "bos_token": "<s>",
32
- "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 %}",
33
  "clean_up_tokenization_spaces": false,
34
- "eos_token": "</s>",
35
  "legacy": true,
36
  "model_max_length": 1000000000000000019884624838656,
37
  "pad_token": null,
 
10
  "rstrip": false,
11
  "single_word": false,
12
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
13
  }
14
  },
15
+ "bos_token": null,
16
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}{% elif message['content'] is iterable %}{% for item in message['content'] %}{% if item['type'] == 'text' %}{{ item['text'] }}{% elif item['type'] == 'image' %}<fim_prefix><|img|><fim_suffix>{% endif %}{% endfor %}{% endif %}<|im_end|>\n{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
17
  "clean_up_tokenization_spaces": false,
18
+ "eos_token": null,
19
  "legacy": true,
20
  "model_max_length": 1000000000000000019884624838656,
21
  "pad_token": null,