OGrohit commited on
Commit
00553d6
·
verified ·
1 Parent(s): 017d9c5

Upload tokenizer

Browse files
Files changed (3) hide show
  1. chat_template.jinja +6 -0
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +18 -0
chat_template.jinja ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
2
+ You are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>
3
+ ' }}{% endif %}{{'<|im_start|>' + message['role'] + '
4
+ ' + message['content'] + '<|im_end|>' + '
5
+ '}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
6
+ ' }}{% endif %}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|im_start|>",
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|im_end|>",
7
+ "errors": "replace",
8
+ "extra_special_tokens": [
9
+ "<|im_start|>",
10
+ "<|im_end|>"
11
+ ],
12
+ "is_local": true,
13
+ "model_max_length": 8192,
14
+ "pad_token": "<|im_end|>",
15
+ "tokenizer_class": "GPT2Tokenizer",
16
+ "unk_token": "<|endoftext|>",
17
+ "vocab_size": 49152
18
+ }