Trouter-Library commited on
Commit
0c9c45e
·
verified ·
1 Parent(s): 3bec1ee

Create tokenizer_config.json

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +53 -0
tokenizer_config.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": false,
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
+ "3": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ }
38
+ },
39
+ "bos_token": "<s>",
40
+ "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{ '<|system|>\n' + message['content'] + '<|end|>\n' }}{% elif message['role'] == 'user' %}{{ '<|user|>\n' + message['content'] + '<|end|>\n' }}{% elif message['role'] == 'assistant' %}{{ '<|assistant|>\n' + message['content'] + '<|end|>\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% endif %}",
41
+ "clean_up_tokenization_spaces": false,
42
+ "eos_token": "</s>",
43
+ "legacy": true,
44
+ "model_max_length": 8192,
45
+ "pad_token": null,
46
+ "padding_side": "right",
47
+ "sp_model_kwargs": {},
48
+ "spaces_between_special_tokens": false,
49
+ "tokenizer_class": "PreTrainedTokenizerFast",
50
+ "truncation_side": "right",
51
+ "unk_token": "<unk>",
52
+ "use_default_system_prompt": false
53
+ }