RichardErkhov commited on
Commit
db84b22
1 Parent(s): 8647931

uploaded model

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +50 -0
tokenizer_config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "additional_special_tokens": [],
31
+ "bos_token": "<s>",
32
+ "chat_template": "{{ bos_token }}{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": true,
36
+ "max_length": 2048,
37
+ "model_max_length": 1000000000000000019884624838656,
38
+ "pad_to_multiple_of": null,
39
+ "pad_token": "<s>",
40
+ "pad_token_type_id": 0,
41
+ "padding_side": "right",
42
+ "sp_model_kwargs": {},
43
+ "spaces_between_special_tokens": false,
44
+ "stride": 0,
45
+ "tokenizer_class": "LlamaTokenizer",
46
+ "truncation_side": "right",
47
+ "truncation_strategy": "longest_first",
48
+ "unk_token": "<unk>",
49
+ "use_default_system_prompt": false
50
+ }