jaigouk commited on
Commit
accf0d7
1 Parent(s): 187d2b7

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +24 -0
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +66 -0
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|pad|>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "32000": {
28
+ "content": "<|user|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "32001": {
36
+ "content": "<|system|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "32002": {
44
+ "content": "<|assistant|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ }
51
+ },
52
+ "additional_special_tokens": [],
53
+ "bos_token": "<s>",
54
+ "chat_template": "{% for message in messages %}{% if message['role'] == 'function_metadata' %}GPT4 Correct User: You have access to the following functions. Use them if required:\n\n{{ message['content'] }}\n\n{% elif message['role'] == 'user' and loop.index0 == 1 %}{{ message['content'] }}{{ eos_token }}GPT4 Correct Assistant:\n\n{% elif message['role'] == 'assistant' %}{{ message['content'] }}{{ eos_token }}GPT4 Correct User: {% elif message['role'] == 'function_call' %}Function call: {{ message['content'] }}{{ eos_token }}GPT4 Correct User: {% elif message['role'] == 'function_response' %}Here is the response to the function call. If helpful, use it to respond to my question/request:\n\n{{ message['content'] }}{{ eos_token }}GPT4 Correct Assistant:\n\n{% elif message['role'] == 'user' and loop.index0 != 1 %}{{ message['content'] }}{{ eos_token }}GPT4 Correct Assistant:\n\n{% endif %}{% endfor %}",
55
+ "clean_up_tokenization_spaces": false,
56
+ "eos_token": "</s>",
57
+ "legacy": true,
58
+ "model_max_length": 2048,
59
+ "pad_token": "<|pad|>",
60
+ "padding_side": "right",
61
+ "sp_model_kwargs": {},
62
+ "spaces_between_special_tokens": false,
63
+ "tokenizer_class": "LlamaTokenizer",
64
+ "unk_token": "<unk>",
65
+ "use_default_system_prompt": true
66
+ }