Hugging Face's logo

1anonymous1
/
confidence_checker

Text Classification
Transformers
Safetensors
deberta-v2
Model card Files
xet
Community
1anonymous1 commited on
Commit
09f2700
·
verified ·
1 Parent(s): 0e5da60

Upload tokenizer

Browse files
Files changed (5) hide show
  1. added_tokens.json +40 -0
  2. special_tokens_map.json +90 -0
  3. spm.model +3 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +393 -0
added_tokens.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</CoT>": 128036,
3
+ "</N=0_code>": 128013,
4
+ "</N=0_execution_result>": 128015,
5
+ "</N=1_code>": 128017,
6
+ "</N=1_execution_result>": 128019,
7
+ "</N=2_code>": 128021,
8
+ "</N=2_execution_result>": 128023,
9
+ "</N=3_code>": 128025,
10
+ "</N=3_execution_result>": 128027,
11
+ "</PoT>": 128028,
12
+ "</Question>": 128010,
13
+ "</Table>": 128008,
14
+ "</Table_column_size>": 128004,
15
+ "</Table_row_size>": 128002,
16
+ "</Table_size>": 128006,
17
+ "</answer>": 128035,
18
+ "</solution>": 128033,
19
+ "</text2sql>": 128030,
20
+ "<CoT>": 128031,
21
+ "<N=0_code>": 128012,
22
+ "<N=0_execution_result>": 128014,
23
+ "<N=1_code>": 128016,
24
+ "<N=1_execution_result>": 128018,
25
+ "<N=2_code>": 128020,
26
+ "<N=2_execution_result>": 128022,
27
+ "<N=3_code>": 128024,
28
+ "<N=3_execution_result>": 128026,
29
+ "<NOTHING>": 128037,
30
+ "<PoT>": 128011,
31
+ "<Question>": 128009,
32
+ "<Table>": 128007,
33
+ "<Table_column_size>": 128003,
34
+ "<Table_row_size>": 128001,
35
+ "<Table_size>": 128005,
36
+ "<answer>": 128034,
37
+ "<solution>": 128032,
38
+ "<text2sql>": 128029,
39
+ "[MASK]": 128000
40
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<Table_row_size>",
4
+ "</Table_row_size>",
5
+ "<Table_column_size>",
6
+ "</Table_column_size>",
7
+ "<Table_size>",
8
+ "</Table_size>",
9
+ "<Table>",
10
+ "</Table>",
11
+ "<Question>",
12
+ "</Question>",
13
+ "<PoT>",
14
+ "<N=0_code>",
15
+ "</N=0_code>",
16
+ "<N=0_execution_result>",
17
+ "</N=0_execution_result>",
18
+ "<N=1_code>",
19
+ "</N=1_code>",
20
+ "<N=1_execution_result>",
21
+ "</N=1_execution_result>",
22
+ "<N=2_code>",
23
+ "</N=2_code>",
24
+ "<N=2_execution_result>",
25
+ "</N=2_execution_result>",
26
+ "<N=3_code>",
27
+ "</N=3_code>",
28
+ "<N=3_execution_result>",
29
+ "</N=3_execution_result>",
30
+ "</PoT>",
31
+ "<text2sql>",
32
+ "</text2sql>",
33
+ "<CoT>",
34
+ "<solution>",
35
+ "</solution>",
36
+ "<answer>",
37
+ "</answer>",
38
+ "</CoT>",
39
+ "<NOTHING>"
40
+ ],
41
+ "bos_token": {
42
+ "content": "[CLS]",
43
+ "lstrip": false,
44
+ "normalized": false,
45
+ "rstrip": false,
46
+ "single_word": false
47
+ },
48
+ "cls_token": {
49
+ "content": "[CLS]",
50
+ "lstrip": false,
51
+ "normalized": false,
52
+ "rstrip": false,
53
+ "single_word": false
54
+ },
55
+ "eos_token": {
56
+ "content": "[SEP]",
57
+ "lstrip": false,
58
+ "normalized": false,
59
+ "rstrip": false,
60
+ "single_word": false
61
+ },
62
+ "mask_token": {
63
+ "content": "[MASK]",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": false
68
+ },
69
+ "pad_token": {
70
+ "content": "[PAD]",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false
75
+ },
76
+ "sep_token": {
77
+ "content": "[SEP]",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false
82
+ },
83
+ "unk_token": {
84
+ "content": "[UNK]",
85
+ "lstrip": false,
86
+ "normalized": true,
87
+ "rstrip": false,
88
+ "single_word": false
89
+ }
90
+ }
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 +1,393 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "[CLS]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[SEP]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[UNK]",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128000": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128001": {
44
+ "content": "<Table_row_size>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128002": {
52
+ "content": "</Table_row_size>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128003": {
60
+ "content": "<Table_column_size>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128004": {
68
+ "content": "</Table_column_size>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128005": {
76
+ "content": "<Table_size>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128006": {
84
+ "content": "</Table_size>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128007": {
92
+ "content": "<Table>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128008": {
100
+ "content": "</Table>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128009": {
108
+ "content": "<Question>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128010": {
116
+ "content": "</Question>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128011": {
124
+ "content": "<PoT>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128012": {
132
+ "content": "<N=0_code>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128013": {
140
+ "content": "</N=0_code>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128014": {
148
+ "content": "<N=0_execution_result>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128015": {
156
+ "content": "</N=0_execution_result>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128016": {
164
+ "content": "<N=1_code>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128017": {
172
+ "content": "</N=1_code>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128018": {
180
+ "content": "<N=1_execution_result>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128019": {
188
+ "content": "</N=1_execution_result>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128020": {
196
+ "content": "<N=2_code>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128021": {
204
+ "content": "</N=2_code>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128022": {
212
+ "content": "<N=2_execution_result>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128023": {
220
+ "content": "</N=2_execution_result>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128024": {
228
+ "content": "<N=3_code>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128025": {
236
+ "content": "</N=3_code>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128026": {
244
+ "content": "<N=3_execution_result>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128027": {
252
+ "content": "</N=3_execution_result>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128028": {
260
+ "content": "</PoT>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128029": {
268
+ "content": "<text2sql>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128030": {
276
+ "content": "</text2sql>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128031": {
284
+ "content": "<CoT>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128032": {
292
+ "content": "<solution>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128033": {
300
+ "content": "</solution>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128034": {
308
+ "content": "<answer>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128035": {
316
+ "content": "</answer>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128036": {
324
+ "content": "</CoT>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128037": {
332
+ "content": "<NOTHING>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ }
339
+ },
340
+ "additional_special_tokens": [
341
+ "<Table_row_size>",
342
+ "</Table_row_size>",
343
+ "<Table_column_size>",
344
+ "</Table_column_size>",
345
+ "<Table_size>",
346
+ "</Table_size>",
347
+ "<Table>",
348
+ "</Table>",
349
+ "<Question>",
350
+ "</Question>",
351
+ "<PoT>",
352
+ "<N=0_code>",
353
+ "</N=0_code>",
354
+ "<N=0_execution_result>",
355
+ "</N=0_execution_result>",
356
+ "<N=1_code>",
357
+ "</N=1_code>",
358
+ "<N=1_execution_result>",
359
+ "</N=1_execution_result>",
360
+ "<N=2_code>",
361
+ "</N=2_code>",
362
+ "<N=2_execution_result>",
363
+ "</N=2_execution_result>",
364
+ "<N=3_code>",
365
+ "</N=3_code>",
366
+ "<N=3_execution_result>",
367
+ "</N=3_execution_result>",
368
+ "</PoT>",
369
+ "<text2sql>",
370
+ "</text2sql>",
371
+ "<CoT>",
372
+ "<solution>",
373
+ "</solution>",
374
+ "<answer>",
375
+ "</answer>",
376
+ "</CoT>",
377
+ "<NOTHING>"
378
+ ],
379
+ "bos_token": "[CLS]",
380
+ "clean_up_tokenization_spaces": true,
381
+ "cls_token": "[CLS]",
382
+ "do_lower_case": false,
383
+ "eos_token": "[SEP]",
384
+ "mask_token": "[MASK]",
385
+ "model_max_length": 1000000000000000019884624838656,
386
+ "pad_token": "[PAD]",
387
+ "sep_token": "[SEP]",
388
+ "sp_model_kwargs": {},
389
+ "split_by_punct": false,
390
+ "tokenizer_class": "DebertaV2Tokenizer",
391
+ "unk_token": "[UNK]",
392
+ "vocab_type": "spm"
393
+ }