Hugging Face's logo

anonymouse03052002
/
Kanberta

Model card Files Community
anonymouse03052002 commited on
Commit
7c8157d
•
1 Parent(s): bd76b13

Upload tokenizer

Browse files
Files changed (5) hide show
  1. added_tokens.json +17 -0
  2. special_tokens_map.json +31 -0
  3. spiece.model +3 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +195 -0
added_tokens.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s>": 64001,
3
+ "<2as>": 64003,
4
+ "<2bn>": 64004,
5
+ "<2en>": 64005,
6
+ "<2gu>": 64006,
7
+ "<2hi>": 64007,
8
+ "<2kn>": 64008,
9
+ "<2ml>": 64009,
10
+ "<2mr>": 64010,
11
+ "<2or>": 64011,
12
+ "<2pa>": 64012,
13
+ "<2shuf>": 64002,
14
+ "<2ta>": 64013,
15
+ "<2te>": 64014,
16
+ "<s>": 64000
17
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<s>",
4
+ "</s>",
5
+ "<2as>",
6
+ "<2bn>",
7
+ "<2en>",
8
+ "<2gu>",
9
+ "<2hi>",
10
+ "<2kn>",
11
+ "<2ml>",
12
+ "<2mr>",
13
+ "<2or>",
14
+ "<2pa>",
15
+ "<2ta>",
16
+ "<2te>"
17
+ ],
18
+ "bos_token": "[CLS]",
19
+ "cls_token": "[CLS]",
20
+ "eos_token": "[SEP]",
21
+ "mask_token": {
22
+ "content": "[MASK]",
23
+ "lstrip": true,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "pad_token": "<pad>",
29
+ "sep_token": "[SEP]",
30
+ "unk_token": "<unk>"
31
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27d922f1b9444ae05eab57f3f0a9d60d4147e905a160f07c3b08116e7b3b8c6a
3
+ size 1803730
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,195 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<pad>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<unk>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[MASK]",
37
+ "lstrip": true,
38
+ "normalized": true,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "64000": {
44
+ "content": "<s>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "64001": {
52
+ "content": "</s>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "64002": {
60
+ "content": "<2shuf>",
61
+ "lstrip": false,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": false
66
+ },
67
+ "64003": {
68
+ "content": "<2as>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "64004": {
76
+ "content": "<2bn>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "64005": {
84
+ "content": "<2en>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "64006": {
92
+ "content": "<2gu>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "64007": {
100
+ "content": "<2hi>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "64008": {
108
+ "content": "<2kn>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "64009": {
116
+ "content": "<2ml>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "64010": {
124
+ "content": "<2mr>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "64011": {
132
+ "content": "<2or>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "64012": {
140
+ "content": "<2pa>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "64013": {
148
+ "content": "<2ta>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "64014": {
156
+ "content": "<2te>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ }
163
+ },
164
+ "additional_special_tokens": [
165
+ "<s>",
166
+ "</s>",
167
+ "<2as>",
168
+ "<2bn>",
169
+ "<2en>",
170
+ "<2gu>",
171
+ "<2hi>",
172
+ "<2kn>",
173
+ "<2ml>",
174
+ "<2mr>",
175
+ "<2or>",
176
+ "<2pa>",
177
+ "<2ta>",
178
+ "<2te>"
179
+ ],
180
+ "bos_token": "[CLS]",
181
+ "clean_up_tokenization_spaces": true,
182
+ "cls_token": "[CLS]",
183
+ "do_lower_case": false,
184
+ "eos_token": "[SEP]",
185
+ "keep_accents": true,
186
+ "mask_token": "[MASK]",
187
+ "model_max_length": 1000000000000000019884624838656,
188
+ "pad_token": "<pad>",
189
+ "remove_space": true,
190
+ "sep_token": "[SEP]",
191
+ "sp_model_kwargs": {},
192
+ "tokenizer_class": "AlbertTokenizer",
193
+ "unk_token": "<unk>",
194
+ "use_fast": false
195
+ }