Hugging Face's logo

kimura
/
llm-jp-13b-instruct-openwebinstruct-eval_best

Transformers
Safetensors
Model card Files
xet
Community
kimura commited on
Commit
610a068
·
verified ·
1 Parent(s): 56d5000

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +57 -0
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +129 -0
special_tokens_map.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<Thought>",
4
+ "</Thought>",
5
+ "<Output>",
6
+ "</Output>"
7
+ ],
8
+ "bos_token": {
9
+ "content": "<s>",
10
+ "lstrip": false,
11
+ "normalized": false,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ },
15
+ "cls_token": {
16
+ "content": "<CLS|LLM-jp>",
17
+ "lstrip": false,
18
+ "normalized": false,
19
+ "rstrip": false,
20
+ "single_word": false
21
+ },
22
+ "eos_token": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false
28
+ },
29
+ "mask_token": {
30
+ "content": "<MASK|LLM-jp>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false
35
+ },
36
+ "pad_token": {
37
+ "content": "<PAD|LLM-jp>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false
42
+ },
43
+ "sep_token": {
44
+ "content": "<SEP|LLM-jp>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false
49
+ },
50
+ "unk_token": {
51
+ "content": "<unk>",
52
+ "lstrip": false,
53
+ "normalized": false,
54
+ "rstrip": false,
55
+ "single_word": false
56
+ }
57
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,129 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "3": {
30
+ "content": "<MASK|LLM-jp>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "4": {
38
+ "content": "<PAD|LLM-jp>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "5": {
46
+ "content": "<CLS|LLM-jp>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "6": {
54
+ "content": "<SEP|LLM-jp>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "7": {
62
+ "content": "<EOD|LLM-jp>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "99574": {
70
+ "content": "<Thought>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "99575": {
78
+ "content": "</Thought>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "99576": {
86
+ "content": "<Output>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "99577": {
94
+ "content": "</Output>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ }
101
+ },
102
+ "additional_special_tokens": [
103
+ "<Thought>",
104
+ "</Thought>",
105
+ "<Output>",
106
+ "</Output>"
107
+ ],
108
+ "bos_token": "<s>",
109
+ "chat_template": "{{bos_token}}{% for message in messages %}{% if message['role'] == 'user' %}{{ '\\n\\n### 指示:\\n' + message['content'] }}{% elif message['role'] == 'system' %}{{ '以下は、タスクを説明する指示です。要求を適切に満たす応答を書きなさい。' }}{% elif message['role'] == 'assistant' %}{{ '\\n\\n### 応答:\\n' + message['content'] + eos_token }}{% endif %}{% if loop.last and add_generation_prompt %}{{ '\\n\\n### 応答:\\n' }}{% endif %}{% endfor %}",
110
+ "clean_up_tokenization_spaces": false,
111
+ "cls_token": "<CLS|LLM-jp>",
112
+ "eod_token": "</s>",
113
+ "eos_token": "</s>",
114
+ "extra_ids": 0,
115
+ "mask_token": "<MASK|LLM-jp>",
116
+ "max_length": 2048,
117
+ "model_max_length": 1000000000000000019884624838656,
118
+ "pad_to_multiple_of": null,
119
+ "pad_token": "<PAD|LLM-jp>",
120
+ "pad_token_type_id": 0,
121
+ "padding_side": "right",
122
+ "sep_token": "<SEP|LLM-jp>",
123
+ "sp_model_kwargs": {},
124
+ "stride": 0,
125
+ "tokenizer_class": "PreTrainedTokenizerFast",
126
+ "truncation_side": "right",
127
+ "truncation_strategy": "longest_first",
128
+ "unk_token": "<unk>"
129
+ }