Pacific-i64 commited on
Commit
395f5f2
·
verified ·
1 Parent(s): 9ca12ea

Upload 3 files

Browse files
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "<pad>",
5
+ "unk_token": "<unk>"
6
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": true,
4
+ "chat_template": "{% if messages[0]['role'] == 'system' %}{{ messages[0]['content'] }}\n\n{% set ns = namespace(messages=messages[1:]) %}{% else %}{% set ns = namespace(messages=messages) %}{% endif %}{% for message in ns.messages %}{% if message['role'] == 'user' %}User: {{ message['content'] }}\n\n{% elif message['role'] == 'assistant' %}Assistant: {{ message['content'] }}{{ eos_token }}\n{% endif %}{% endfor %}{% if add_generation_prompt %}Assistant:{% endif %}",
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "</s>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<pad>",
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": "<unk>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ }
38
+ },
39
+ "bos_token": "<s>",
40
+ "clean_up_tokenization_spaces": false,
41
+ "eos_token": "</s>",
42
+ "extra_special_tokens": {},
43
+ "model_max_length": 2048,
44
+ "pad_token": "<pad>",
45
+ "tokenizer_class": "PreTrainedTokenizerFast",
46
+ "unk_token": "<unk>"
47
+ }