Hugging Face's logo

relik-ie
/
relik-reader-deberta-v3-small-re-wikipedia

Feature Extraction
Transformers
Safetensors
English
relik-reader
custom_code
Model card Files Community
relik-ie commited on
Commit
b7e439b
•
1 Parent(s): d844ec0

Upload tokenizer

Browse files
Files changed (5) hide show
  1. added_tokens.json +33 -0
  2. special_tokens_map.json +83 -0
  3. spm.model +3 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +331 -0
added_tokens.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "[MASK]": 128000,
3
+ "[R-0]": 128001,
4
+ "[R-10]": 128011,
5
+ "[R-11]": 128012,
6
+ "[R-12]": 128013,
7
+ "[R-13]": 128014,
8
+ "[R-14]": 128015,
9
+ "[R-15]": 128016,
10
+ "[R-16]": 128017,
11
+ "[R-17]": 128018,
12
+ "[R-18]": 128019,
13
+ "[R-19]": 128020,
14
+ "[R-1]": 128002,
15
+ "[R-20]": 128021,
16
+ "[R-21]": 128022,
17
+ "[R-22]": 128023,
18
+ "[R-23]": 128024,
19
+ "[R-24]": 128025,
20
+ "[R-25]": 128026,
21
+ "[R-26]": 128027,
22
+ "[R-27]": 128028,
23
+ "[R-28]": 128029,
24
+ "[R-29]": 128030,
25
+ "[R-2]": 128003,
26
+ "[R-3]": 128004,
27
+ "[R-4]": 128005,
28
+ "[R-5]": 128006,
29
+ "[R-6]": 128007,
30
+ "[R-7]": 128008,
31
+ "[R-8]": 128009,
32
+ "[R-9]": 128010
33
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "[R-0]",
4
+ "[R-1]",
5
+ "[R-2]",
6
+ "[R-3]",
7
+ "[R-4]",
8
+ "[R-5]",
9
+ "[R-6]",
10
+ "[R-7]",
11
+ "[R-8]",
12
+ "[R-9]",
13
+ "[R-10]",
14
+ "[R-11]",
15
+ "[R-12]",
16
+ "[R-13]",
17
+ "[R-14]",
18
+ "[R-15]",
19
+ "[R-16]",
20
+ "[R-17]",
21
+ "[R-18]",
22
+ "[R-19]",
23
+ "[R-20]",
24
+ "[R-21]",
25
+ "[R-22]",
26
+ "[R-23]",
27
+ "[R-24]",
28
+ "[R-25]",
29
+ "[R-26]",
30
+ "[R-27]",
31
+ "[R-28]",
32
+ "[R-29]"
33
+ ],
34
+ "bos_token": {
35
+ "content": "[CLS]",
36
+ "lstrip": false,
37
+ "normalized": false,
38
+ "rstrip": false,
39
+ "single_word": false
40
+ },
41
+ "cls_token": {
42
+ "content": "[CLS]",
43
+ "lstrip": false,
44
+ "normalized": false,
45
+ "rstrip": false,
46
+ "single_word": false
47
+ },
48
+ "eos_token": {
49
+ "content": "[SEP]",
50
+ "lstrip": false,
51
+ "normalized": false,
52
+ "rstrip": false,
53
+ "single_word": false
54
+ },
55
+ "mask_token": {
56
+ "content": "[MASK]",
57
+ "lstrip": false,
58
+ "normalized": false,
59
+ "rstrip": false,
60
+ "single_word": false
61
+ },
62
+ "pad_token": {
63
+ "content": "[PAD]",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": false
68
+ },
69
+ "sep_token": {
70
+ "content": "[SEP]",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false
75
+ },
76
+ "unk_token": {
77
+ "content": "[UNK]",
78
+ "lstrip": false,
79
+ "normalized": true,
80
+ "rstrip": false,
81
+ "single_word": false
82
+ }
83
+ }
spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,331 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "[PAD]",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "[CLS]",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "[SEP]",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "[UNK]",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "128000": {
37
+ "content": "[MASK]",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "128001": {
45
+ "content": "[R-0]",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "128002": {
53
+ "content": "[R-1]",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "128003": {
61
+ "content": "[R-2]",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "128004": {
69
+ "content": "[R-3]",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "128005": {
77
+ "content": "[R-4]",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "128006": {
85
+ "content": "[R-5]",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "128007": {
93
+ "content": "[R-6]",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "128008": {
101
+ "content": "[R-7]",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "128009": {
109
+ "content": "[R-8]",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "128010": {
117
+ "content": "[R-9]",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "128011": {
125
+ "content": "[R-10]",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "128012": {
133
+ "content": "[R-11]",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "128013": {
141
+ "content": "[R-12]",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "128014": {
149
+ "content": "[R-13]",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "128015": {
157
+ "content": "[R-14]",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "128016": {
165
+ "content": "[R-15]",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "128017": {
173
+ "content": "[R-16]",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "128018": {
181
+ "content": "[R-17]",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "128019": {
189
+ "content": "[R-18]",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "128020": {
197
+ "content": "[R-19]",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "128021": {
205
+ "content": "[R-20]",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "128022": {
213
+ "content": "[R-21]",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "128023": {
221
+ "content": "[R-22]",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "128024": {
229
+ "content": "[R-23]",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "128025": {
237
+ "content": "[R-24]",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "128026": {
245
+ "content": "[R-25]",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "128027": {
253
+ "content": "[R-26]",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "128028": {
261
+ "content": "[R-27]",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "128029": {
269
+ "content": "[R-28]",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "128030": {
277
+ "content": "[R-29]",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ }
284
+ },
285
+ "additional_special_tokens": [
286
+ "[R-0]",
287
+ "[R-1]",
288
+ "[R-2]",
289
+ "[R-3]",
290
+ "[R-4]",
291
+ "[R-5]",
292
+ "[R-6]",
293
+ "[R-7]",
294
+ "[R-8]",
295
+ "[R-9]",
296
+ "[R-10]",
297
+ "[R-11]",
298
+ "[R-12]",
299
+ "[R-13]",
300
+ "[R-14]",
301
+ "[R-15]",
302
+ "[R-16]",
303
+ "[R-17]",
304
+ "[R-18]",
305
+ "[R-19]",
306
+ "[R-20]",
307
+ "[R-21]",
308
+ "[R-22]",
309
+ "[R-23]",
310
+ "[R-24]",
311
+ "[R-25]",
312
+ "[R-26]",
313
+ "[R-27]",
314
+ "[R-28]",
315
+ "[R-29]"
316
+ ],
317
+ "bos_token": "[CLS]",
318
+ "clean_up_tokenization_spaces": true,
319
+ "cls_token": "[CLS]",
320
+ "do_lower_case": false,
321
+ "eos_token": "[SEP]",
322
+ "mask_token": "[MASK]",
323
+ "model_max_length": 1000000000000000019884624838656,
324
+ "pad_token": "[PAD]",
325
+ "sep_token": "[SEP]",
326
+ "sp_model_kwargs": {},
327
+ "split_by_punct": false,
328
+ "tokenizer_class": "DebertaV2Tokenizer",
329
+ "unk_token": "[UNK]",
330
+ "vocab_type": "spm"
331
+ }