Hugging Face's logo

sbintuitions
/
modernbert-ja-30m

Fill-Mask
Transformers
Safetensors
Japanese
English
modernbert
Model card Files
xet
Community
hpprc commited on
Commit
56f7427
·
verified ·
1 Parent(s): 300e2a9

Upload tokenizer

Browse files
Files changed (4) hide show
  1. special_tokens_map.json +51 -0
  2. tokenizer.json +0 -0
  3. tokenizer.model +3 -0
  4. tokenizer_config.json +171 -0
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<cls>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "<sep>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:008293028e1a9d9a1038d9b63d989a2319797dfeaa03f171093a57b33a3a8277
3
+ size 1831879
tokenizer_config.json ADDED
@@ -0,0 +1,171 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_dummy_prefix_space": false,
4
+ "add_eos_token": true,
5
+ "add_prefix_space": false,
6
+ "added_tokens_decoder": {
7
+ "0": {
8
+ "content": "<unk>",
9
+ "lstrip": false,
10
+ "normalized": false,
11
+ "rstrip": false,
12
+ "single_word": false,
13
+ "special": true
14
+ },
15
+ "1": {
16
+ "content": "<s>",
17
+ "lstrip": false,
18
+ "normalized": false,
19
+ "rstrip": false,
20
+ "single_word": false,
21
+ "special": true
22
+ },
23
+ "2": {
24
+ "content": "</s>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false,
29
+ "special": true
30
+ },
31
+ "3": {
32
+ "content": "<pad>",
33
+ "lstrip": false,
34
+ "normalized": false,
35
+ "rstrip": false,
36
+ "single_word": false,
37
+ "special": true
38
+ },
39
+ "4": {
40
+ "content": "<sep>",
41
+ "lstrip": false,
42
+ "normalized": false,
43
+ "rstrip": false,
44
+ "single_word": false,
45
+ "special": true
46
+ },
47
+ "5": {
48
+ "content": "<mask>",
49
+ "lstrip": false,
50
+ "normalized": false,
51
+ "rstrip": false,
52
+ "single_word": false,
53
+ "special": true
54
+ },
55
+ "6": {
56
+ "content": "<cls>",
57
+ "lstrip": false,
58
+ "normalized": false,
59
+ "rstrip": false,
60
+ "single_word": false,
61
+ "special": true
62
+ },
63
+ "7": {
64
+ "content": "<|system|>",
65
+ "lstrip": false,
66
+ "normalized": false,
67
+ "rstrip": false,
68
+ "single_word": false,
69
+ "special": false
70
+ },
71
+ "8": {
72
+ "content": "<|assistant|>",
73
+ "lstrip": false,
74
+ "normalized": false,
75
+ "rstrip": false,
76
+ "single_word": false,
77
+ "special": false
78
+ },
79
+ "9": {
80
+ "content": "<|user|>",
81
+ "lstrip": false,
82
+ "normalized": false,
83
+ "rstrip": false,
84
+ "single_word": false,
85
+ "special": false
86
+ },
87
+ "10": {
88
+ "content": "<|available_tools|>",
89
+ "lstrip": false,
90
+ "normalized": false,
91
+ "rstrip": false,
92
+ "single_word": false,
93
+ "special": false
94
+ },
95
+ "11": {
96
+ "content": "<|tool_calls|>",
97
+ "lstrip": false,
98
+ "normalized": false,
99
+ "rstrip": false,
100
+ "single_word": false,
101
+ "special": false
102
+ },
103
+ "12": {
104
+ "content": "<|tool_results|>",
105
+ "lstrip": false,
106
+ "normalized": false,
107
+ "rstrip": false,
108
+ "single_word": false,
109
+ "special": false
110
+ },
111
+ "13": {
112
+ "content": "<|code|>",
113
+ "lstrip": false,
114
+ "normalized": false,
115
+ "rstrip": false,
116
+ "single_word": false,
117
+ "special": false
118
+ },
119
+ "14": {
120
+ "content": "<|file|>",
121
+ "lstrip": false,
122
+ "normalized": false,
123
+ "rstrip": false,
124
+ "single_word": false,
125
+ "special": false
126
+ },
127
+ "102397": {
128
+ "content": "<|prefix|>",
129
+ "lstrip": false,
130
+ "normalized": false,
131
+ "rstrip": false,
132
+ "single_word": false,
133
+ "special": false
134
+ },
135
+ "102398": {
136
+ "content": "<|suffix|>",
137
+ "lstrip": false,
138
+ "normalized": false,
139
+ "rstrip": false,
140
+ "single_word": false,
141
+ "special": false
142
+ },
143
+ "102399": {
144
+ "content": "<|middle|>",
145
+ "lstrip": false,
146
+ "normalized": false,
147
+ "rstrip": false,
148
+ "single_word": false,
149
+ "special": false
150
+ }
151
+ },
152
+ "bos_token": "<s>",
153
+ "clean_up_tokenization_spaces": false,
154
+ "cls_token": "<cls>",
155
+ "do_lower_case": false,
156
+ "eos_token": "</s>",
157
+ "extra_ids": 0,
158
+ "extra_special_tokens": {},
159
+ "keep_accents": true,
160
+ "legacy": false,
161
+ "mask_token": "<mask>",
162
+ "model_max_length": 1000000000000000019884624838656,
163
+ "pad_token": "<pad>",
164
+ "padding_side": "right",
165
+ "sep_token": "<sep>",
166
+ "sp_model_kwargs": {},
167
+ "spaces_between_special_tokens": false,
168
+ "tokenizer_class": "LlamaTokenizer",
169
+ "unk_token": "<unk>",
170
+ "use_default_system_prompt": false
171
+ }