MaruchanPark commited on
Commit
1e505a6
1 Parent(s): f43ca49

git add model

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +0 -24
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +0 -97
special_tokens_map.json DELETED
@@ -1,24 +0,0 @@
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": {
17
- "content": "</s>",
18
- "lstrip": false,
19
- "normalized": false,
20
- "rstrip": false,
21
- "single_word": false
22
- },
23
- "unk_token": "<unk>"
24
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json DELETED
@@ -1,97 +0,0 @@
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
- "32000": {
30
- "content": "<|tel|>",
31
- "lstrip": false,
32
- "normalized": false,
33
- "rstrip": false,
34
- "single_word": false,
35
- "special": false
36
- },
37
- "32001": {
38
- "content": "<|rnn|>",
39
- "lstrip": false,
40
- "normalized": false,
41
- "rstrip": false,
42
- "single_word": false,
43
- "special": false
44
- },
45
- "32002": {
46
- "content": "<|email|>",
47
- "lstrip": false,
48
- "normalized": false,
49
- "rstrip": false,
50
- "single_word": false,
51
- "special": false
52
- },
53
- "32003": {
54
- "content": "<|crd|>",
55
- "lstrip": false,
56
- "normalized": false,
57
- "rstrip": false,
58
- "single_word": false,
59
- "special": false
60
- },
61
- "32004": {
62
- "content": "<|acc|>",
63
- "lstrip": false,
64
- "normalized": false,
65
- "rstrip": false,
66
- "single_word": false,
67
- "special": false
68
- },
69
- "51510": {
70
- "content": "<|im_start|>",
71
- "lstrip": false,
72
- "normalized": false,
73
- "rstrip": false,
74
- "single_word": false,
75
- "special": false
76
- },
77
- "51511": {
78
- "content": "<|im_end|>",
79
- "lstrip": false,
80
- "normalized": false,
81
- "rstrip": false,
82
- "single_word": false,
83
- "special": false
84
- }
85
- },
86
- "bos_token": "<s>",
87
- "chat_template": "{{('<|im_start|>assistant\n' + messages[0]['content'].strip() + '<|im_end|>' + '\n' if messages[0]['role'] == 'system' else '')}}{% for message in (messages[1:] if messages[0]['role'] == 'system' else messages) %}{% if message['role'] == 'user' %}{{'<|im_start|>user\n' + message['content'] + '<|im_end|>' + '\n' + '<|im_start|>assistant\n'}}{% elif message['role'] == 'assistant' %}{{message['content']}}{% if loop.last %}{% if add_generation_prompt %}{{'<|im_end|>'}}{% endif %}{% else %}{{'<|im_end|>'}}{% endif %}{% endif %}{% endfor %}",
88
- "clean_up_tokenization_spaces": true,
89
- "eos_token": "</s>",
90
- "legacy": true,
91
- "model_max_length": 1000000000000000019884624838656,
92
- "model_name": "kylin-7b",
93
- "pad_token": "</s>",
94
- "tokenizer_class": "LlamaTokenizer",
95
- "unk_token": "<unk>",
96
- "use_default_system_prompt": false
97
- }