nickmalhotra commited on
Commit
fa42311
1 Parent(s): d49d2de

Upload tokenizer_config.json

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +39 -0
tokenizer_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "bos_token": "<s>",
29
+ "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ bos_token + 'उपयोगकर्ता\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ bos_token + 'सहायक\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ bos_token + 'सहायक' }}\n{% endif %}\n{% endfor %}\n",
30
+ "clean_up_tokenization_spaces": true,
31
+ "eos_token": "</s>",
32
+ "legacy": false,
33
+ "model_max_length": 1024,
34
+ "pad_token": "</s>",
35
+ "sp_model_kwargs": {},
36
+ "tokenizer_class": "PreTrainedTokenizerFast",
37
+ "unk_token": "<unk>",
38
+ "use_default_system_prompt": false
39
+ }