ubaitur5 commited on
Commit
40f9351
·
verified ·
1 Parent(s): 1c69031

Upload tokenizer_config.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +56 -0
tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "additional_special_tokens": [
32
+ "<unk>",
33
+ "<s>",
34
+ "</s>"
35
+ ],
36
+ "bos_token": "<s>",
37
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{bos_token + message['role'] + '\n' + message['content'] + eos_token + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ bos_token + 'assistant\n' }}{% endif %}",
38
+ "clean_up_tokenization_spaces": false,
39
+ "eos_token": "</s>",
40
+ "extra_special_tokens": {},
41
+ "legacy": true,
42
+ "max_length": 512,
43
+ "model_max_length": 1000000000000000019884624838656,
44
+ "pad_to_multiple_of": null,
45
+ "pad_token": "</s>",
46
+ "pad_token_type_id": 0,
47
+ "padding_side": "left",
48
+ "sp_model_kwargs": {},
49
+ "spaces_between_special_tokens": false,
50
+ "stride": 0,
51
+ "tokenizer_class": "LlamaTokenizer",
52
+ "truncation_side": "right",
53
+ "truncation_strategy": "longest_first",
54
+ "unk_token": "<unk>",
55
+ "use_default_system_prompt": true
56
+ }