azizbhh commited on
Commit
7937940
1 Parent(s): 31ba54c

Upload tokenizer_config.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +48 -0
tokenizer_config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ }
28
+ },
29
+ "additional_special_tokens": [
30
+ "<|im_start|>",
31
+ "<|im_end|>"
32
+ ],
33
+ "bos_token": "<|im_end|>",
34
+ "chat_template": "\n{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant. Here is an example:\nQuestion: How many chambers does the stomach of a crocodile have?\n\nOptions:\nA. two\nB. six\nC. ten\nD. three\n\nAnswer:ANow, here is your multiple choice question:\n.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}\n",
35
+ "clean_up_tokenization_spaces": false,
36
+ "eos_token": "<|im_end|>",
37
+ "errors": "replace",
38
+ "max_length": 32768,
39
+ "model_max_length": 32768,
40
+ "pad_token": "<|im_end|>",
41
+ "return_tensors": "pt",
42
+ "split_special_tokens": false,
43
+ "stride": 0,
44
+ "tokenizer_class": "Qwen2Tokenizer",
45
+ "truncation_side": "left",
46
+ "truncation_strategy": "longest_first",
47
+ "unk_token": null
48
+ }