Hugging Face's logo

ryo0634
/
tiny-lm-4bit-lora

Transformers
Safetensors
Model card Files
xet
Community
ryo0634 commited on
Commit
1b79c84
·
verified ·
1 Parent(s): 44cafea

Upload tokenizer

Browse files
Files changed (4) hide show
  1. special_tokens_map.json +54 -0
  2. spiece.model +3 -0
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +81 -0
special_tokens_map.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<pad>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ }
10
+ ],
11
+ "bos_token": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "cls_token": {
19
+ "content": "<cls>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "eos_token": {
26
+ "content": "</s>",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ },
32
+ "mask_token": {
33
+ "content": "<mask>",
34
+ "lstrip": false,
35
+ "normalized": false,
36
+ "rstrip": false,
37
+ "single_word": false
38
+ },
39
+ "pad_token": "<pad>",
40
+ "sep_token": {
41
+ "content": "<sep>",
42
+ "lstrip": false,
43
+ "normalized": false,
44
+ "rstrip": false,
45
+ "single_word": false
46
+ },
47
+ "unk_token": {
48
+ "content": "<unk>",
49
+ "lstrip": false,
50
+ "normalized": false,
51
+ "rstrip": false,
52
+ "single_word": false
53
+ }
54
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:362dfed338d41958f7c4dcefcf997ecf7cb9a6d67b6146347d3cafd59339cc94
3
+ size 1117982
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<unk>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<pad>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<sep>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "5": {
45
+ "content": "<mask>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "6": {
53
+ "content": "<cls>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ }
60
+ },
61
+ "additional_special_tokens": [
62
+ "<pad>"
63
+ ],
64
+ "bos_token": "<s>",
65
+ "chat_template": "{%- for message in messages %}\n{%- if message['role'] == 'user' %}\n{{ 'ユーザ：' + message['content'] + eos_token }}\n{%- elif message['role'] == 'assistant' %}\n{{ 'アシスタント：' + message['content'] + eos_token }}\n{%- endif %}\n{% if loop.last and add_generation_prompt %}\n{{ 'アシスタント：' }}\n{%- endif %}\n{% endfor %}",
66
+ "clean_up_tokenization_spaces": true,
67
+ "cls_token": "<cls>",
68
+ "do_lower_case": false,
69
+ "eos_token": "</s>",
70
+ "extra_ids": 0,
71
+ "keep_accents": true,
72
+ "legacy": true,
73
+ "mask_token": "<mask>",
74
+ "model_max_length": 1000000000000000019884624838656,
75
+ "pad_token": "<pad>",
76
+ "padding_side": "left",
77
+ "sep_token": "<sep>",
78
+ "sp_model_kwargs": {},
79
+ "tokenizer_class": "T5Tokenizer",
80
+ "unk_token": "<unk>"
81
+ }