nhanv commited on
Commit
b59e637
1 Parent(s): 38a0db7

Upload tokenizer_config.json

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +19 -0
tokenizer_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": false,
5
+ "additional_special_tokens": ["<|im_start|>", "<|im_end|>", "<fim_prefix>", "<fim_middle>", "<fim_suffix>", "<fim_pad>"],
6
+ "bos_token": "<|endoftext|>",
7
+ "clean_up_tokenization_spaces": false,
8
+ "eos_token": "<|im_end|>",
9
+ "legacy": false,
10
+ "model_max_length": 1000000000000000019884624838656,
11
+ "pad_token": "<fim_pad>",
12
+ "sp_model_kwargs": {},
13
+ "spaces_between_special_tokens": false,
14
+ "tokenizer_class": "PreTrainedTokenizerFast",
15
+ "unk_token": "<unk>",
16
+ "use_default_system_prompt": false,
17
+ "add_prefix_space": true,
18
+ "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}"
19
+ }