TeeZee commited on
Commit
fcc69d7
1 Parent(s): 5853dbb

Upload tokenizer_config.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +44 -0
tokenizer_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "\n{{ bos_token }}\n{% for message in messages %}\n{% if message['from'] == 'system' %}\n{% if message['value']%}\n{{'### System:\n' + message['value']+'\n\n'}}\n{% endif %}{% elif message['from'] == 'human' %}\n{{'### User:\n' + message['value']+'\n\n'}}\n{% elif message['from'] == 'gpt' %}\n{{'### Assistant:\n' + message['value'] + '</s>' + '\n'}}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '### Assistant:\n' }}\n{% endif %}\n{% endfor %}\n",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": true,
36
+ "model_max_length": 4096,
37
+ "pad_token": "<unk>",
38
+ "padding_side": "left",
39
+ "sp_model_kwargs": {},
40
+ "spaces_between_special_tokens": false,
41
+ "tokenizer_class": "LlamaTokenizer",
42
+ "unk_token": "<unk>",
43
+ "use_default_system_prompt": true
44
+ }