JaeGwang commited on
Commit
b5ec592
1 Parent(s): 4133c1e

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +30 -0
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +98 -0
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,98 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
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
+ "63988": {
31
+ "content": "<|im_start|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "63989": {
39
+ "content": "<|im_end|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "63990": {
47
+ "content": "<|sep|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "63991": {
55
+ "content": "<|endoftext|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "63992": {
63
+ "content": "<|acc|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "63993": {
71
+ "content": "<|rrn|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "63994": {
79
+ "content": "<|tel|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": true
85
+ }
86
+ },
87
+ "bos_token": "<s>",
88
+ "chat_template": "{%- for message in messages %}{%- if message['role'] == 'system' %}{{- '<<SYS>>\\n' + \"당신은 충북대학교 연구중심병원에서 만든 AI 의료챗봇입니다. 당신의 이름은 'adiy'으로, 한국어로는 '돕는자'를 뜻합니다. 당신은 환자에게 물음에 공감하며 친절하게 답변하세요.질문이 이상하다면, 어떤 부분이 이상한지 설명합니다. 거짓 정보를 발언하지 않도록 주의합니다.\" + '\\n참고자료:' + message['content'] + '\\n<</SYS>>\\n\\n' }}{%- elif message['role'] == 'user' %}{{- bos_token + '[INST]' +'질문:'+ message['content'] + '[/INST]\n' }}{%- elif message['role'] == 'assistant' %}{{- '\n답변:' + message['content'] + '</s>' }}{%- endif %}{%- endfor %}",
89
+ "clean_up_tokenization_spaces": false,
90
+ "eos_token": "</s>",
91
+ "legacy": true,
92
+ "model_max_length": 1000000000000000019884624838656,
93
+ "pad_token": "<unk>",
94
+ "padding_side": "right",
95
+ "tokenizer_class": "LlamaTokenizer",
96
+ "unk_token": "<unk>",
97
+ "use_default_system_prompt": false
98
+ }