valpy commited on
Commit
3c6e328
1 Parent(s): e918769

Update tokenizer_config.json

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +32 -1
tokenizer_config.json CHANGED
@@ -1 +1,32 @@
1
- {"add_bos_token": true, "add_eos_token": false, "model_max_length": 2048, "pad_token": null, "sp_model_kwargs": {}, "tokenizer_class": "LlamaTokenizer", "clean_up_tokenization_spaces": false, "bos_token": {"__type": "AddedToken", "content": "<s>", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false}, "eos_token": {"__type": "AddedToken", "content": "</s>", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false}, "unk_token": {"__type": "AddedToken", "content": "<unk>", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false}}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "model_max_length": 2048,
5
+ "pad_token": null,
6
+ "sp_model_kwargs": {},
7
+ "tokenizer_class": "LlamaTokenizer",
8
+ "clean_up_tokenization_spaces": false,
9
+ "bos_token": {
10
+ "__type": "AddedToken",
11
+ "content": "<s>",
12
+ "lstrip": false,
13
+ "normalized": true,
14
+ "rstrip": false,
15
+ "single_word": false},
16
+ "eos_token": {
17
+ "__type": "AddedToken",
18
+ "content": "</s>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false},
23
+ "unk_token": {
24
+ "__type": "AddedToken",
25
+ "content": "<unk>",
26
+ "lstrip": false,
27
+ "normalized": true,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ "chat_template": "{% 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 %}"
32
+ }