lucapernice commited on
Commit
47ad9c0
·
verified ·
1 Parent(s): f46d0e7

Add tokenizer

Browse files
Files changed (4) hide show
  1. special_tokens_map.json +37 -0
  2. tokenizer.json +425 -0
  3. tokenizer_config.json +66 -0
  4. vocab.txt +261 -0
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
@@ -0,0 +1,425 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 256,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
+ "padding": {
10
+ "strategy": {
11
+ "Fixed": 256
12
+ },
13
+ "direction": "Right",
14
+ "pad_to_multiple_of": null,
15
+ "pad_id": 0,
16
+ "pad_type_id": 0,
17
+ "pad_token": "[PAD]"
18
+ },
19
+ "added_tokens": [
20
+ {
21
+ "id": 0,
22
+ "content": "[PAD]",
23
+ "single_word": false,
24
+ "lstrip": false,
25
+ "rstrip": false,
26
+ "normalized": false,
27
+ "special": true
28
+ },
29
+ {
30
+ "id": 1,
31
+ "content": "[UNK]",
32
+ "single_word": false,
33
+ "lstrip": false,
34
+ "rstrip": false,
35
+ "normalized": false,
36
+ "special": true
37
+ },
38
+ {
39
+ "id": 2,
40
+ "content": "[CLS]",
41
+ "single_word": false,
42
+ "lstrip": false,
43
+ "rstrip": false,
44
+ "normalized": false,
45
+ "special": true
46
+ },
47
+ {
48
+ "id": 3,
49
+ "content": "[SEP]",
50
+ "single_word": false,
51
+ "lstrip": false,
52
+ "rstrip": false,
53
+ "normalized": false,
54
+ "special": true
55
+ },
56
+ {
57
+ "id": 4,
58
+ "content": "[MASK]",
59
+ "single_word": false,
60
+ "lstrip": false,
61
+ "rstrip": false,
62
+ "normalized": false,
63
+ "special": true
64
+ }
65
+ ],
66
+ "normalizer": {
67
+ "type": "BertNormalizer",
68
+ "clean_text": true,
69
+ "handle_chinese_chars": true,
70
+ "strip_accents": null,
71
+ "lowercase": true
72
+ },
73
+ "pre_tokenizer": {
74
+ "type": "BertPreTokenizer"
75
+ },
76
+ "post_processor": {
77
+ "type": "TemplateProcessing",
78
+ "single": [
79
+ {
80
+ "SpecialToken": {
81
+ "id": "[CLS]",
82
+ "type_id": 0
83
+ }
84
+ },
85
+ {
86
+ "Sequence": {
87
+ "id": "A",
88
+ "type_id": 0
89
+ }
90
+ },
91
+ {
92
+ "SpecialToken": {
93
+ "id": "[SEP]",
94
+ "type_id": 0
95
+ }
96
+ }
97
+ ],
98
+ "pair": [
99
+ {
100
+ "SpecialToken": {
101
+ "id": "[CLS]",
102
+ "type_id": 0
103
+ }
104
+ },
105
+ {
106
+ "Sequence": {
107
+ "id": "A",
108
+ "type_id": 0
109
+ }
110
+ },
111
+ {
112
+ "SpecialToken": {
113
+ "id": "[SEP]",
114
+ "type_id": 0
115
+ }
116
+ },
117
+ {
118
+ "Sequence": {
119
+ "id": "B",
120
+ "type_id": 1
121
+ }
122
+ },
123
+ {
124
+ "SpecialToken": {
125
+ "id": "[SEP]",
126
+ "type_id": 1
127
+ }
128
+ }
129
+ ],
130
+ "special_tokens": {
131
+ "[CLS]": {
132
+ "id": "[CLS]",
133
+ "ids": [
134
+ 2
135
+ ],
136
+ "tokens": [
137
+ "[CLS]"
138
+ ]
139
+ },
140
+ "[SEP]": {
141
+ "id": "[SEP]",
142
+ "ids": [
143
+ 3
144
+ ],
145
+ "tokens": [
146
+ "[SEP]"
147
+ ]
148
+ }
149
+ }
150
+ },
151
+ "decoder": {
152
+ "type": "WordPiece",
153
+ "prefix": "##",
154
+ "cleanup": true
155
+ },
156
+ "model": {
157
+ "type": "WordPiece",
158
+ "unk_token": "[UNK]",
159
+ "continuing_subword_prefix": "##",
160
+ "max_input_chars_per_word": 100,
161
+ "vocab": {
162
+ "[PAD]": 0,
163
+ "[UNK]": 1,
164
+ "[CLS]": 2,
165
+ "[SEP]": 3,
166
+ "[MASK]": 4,
167
+ "0": 5,
168
+ "1": 6,
169
+ "2": 7,
170
+ "3": 8,
171
+ "4": 9,
172
+ "5": 10,
173
+ "6": 11,
174
+ "7": 12,
175
+ "8": 13,
176
+ "9": 14,
177
+ "10": 15,
178
+ "11": 16,
179
+ "12": 17,
180
+ "13": 18,
181
+ "14": 19,
182
+ "15": 20,
183
+ "16": 21,
184
+ "17": 22,
185
+ "18": 23,
186
+ "19": 24,
187
+ "20": 25,
188
+ "21": 26,
189
+ "22": 27,
190
+ "23": 28,
191
+ "24": 29,
192
+ "25": 30,
193
+ "26": 31,
194
+ "27": 32,
195
+ "28": 33,
196
+ "29": 34,
197
+ "30": 35,
198
+ "31": 36,
199
+ "32": 37,
200
+ "33": 38,
201
+ "34": 39,
202
+ "35": 40,
203
+ "36": 41,
204
+ "37": 42,
205
+ "38": 43,
206
+ "39": 44,
207
+ "40": 45,
208
+ "41": 46,
209
+ "42": 47,
210
+ "43": 48,
211
+ "44": 49,
212
+ "45": 50,
213
+ "46": 51,
214
+ "47": 52,
215
+ "48": 53,
216
+ "49": 54,
217
+ "50": 55,
218
+ "51": 56,
219
+ "52": 57,
220
+ "53": 58,
221
+ "54": 59,
222
+ "55": 60,
223
+ "56": 61,
224
+ "57": 62,
225
+ "58": 63,
226
+ "59": 64,
227
+ "60": 65,
228
+ "61": 66,
229
+ "62": 67,
230
+ "63": 68,
231
+ "64": 69,
232
+ "65": 70,
233
+ "66": 71,
234
+ "67": 72,
235
+ "68": 73,
236
+ "69": 74,
237
+ "70": 75,
238
+ "71": 76,
239
+ "72": 77,
240
+ "73": 78,
241
+ "74": 79,
242
+ "75": 80,
243
+ "76": 81,
244
+ "77": 82,
245
+ "78": 83,
246
+ "79": 84,
247
+ "80": 85,
248
+ "81": 86,
249
+ "82": 87,
250
+ "83": 88,
251
+ "84": 89,
252
+ "85": 90,
253
+ "86": 91,
254
+ "87": 92,
255
+ "88": 93,
256
+ "89": 94,
257
+ "90": 95,
258
+ "91": 96,
259
+ "92": 97,
260
+ "93": 98,
261
+ "94": 99,
262
+ "95": 100,
263
+ "96": 101,
264
+ "97": 102,
265
+ "98": 103,
266
+ "99": 104,
267
+ "100": 105,
268
+ "101": 106,
269
+ "102": 107,
270
+ "103": 108,
271
+ "104": 109,
272
+ "105": 110,
273
+ "106": 111,
274
+ "107": 112,
275
+ "108": 113,
276
+ "109": 114,
277
+ "110": 115,
278
+ "111": 116,
279
+ "112": 117,
280
+ "113": 118,
281
+ "114": 119,
282
+ "115": 120,
283
+ "116": 121,
284
+ "117": 122,
285
+ "118": 123,
286
+ "119": 124,
287
+ "120": 125,
288
+ "121": 126,
289
+ "122": 127,
290
+ "123": 128,
291
+ "124": 129,
292
+ "125": 130,
293
+ "126": 131,
294
+ "127": 132,
295
+ "128": 133,
296
+ "129": 134,
297
+ "130": 135,
298
+ "131": 136,
299
+ "132": 137,
300
+ "133": 138,
301
+ "134": 139,
302
+ "135": 140,
303
+ "136": 141,
304
+ "137": 142,
305
+ "138": 143,
306
+ "139": 144,
307
+ "140": 145,
308
+ "141": 146,
309
+ "142": 147,
310
+ "143": 148,
311
+ "144": 149,
312
+ "145": 150,
313
+ "146": 151,
314
+ "147": 152,
315
+ "148": 153,
316
+ "149": 154,
317
+ "150": 155,
318
+ "151": 156,
319
+ "152": 157,
320
+ "153": 158,
321
+ "154": 159,
322
+ "155": 160,
323
+ "156": 161,
324
+ "157": 162,
325
+ "158": 163,
326
+ "159": 164,
327
+ "160": 165,
328
+ "161": 166,
329
+ "162": 167,
330
+ "163": 168,
331
+ "164": 169,
332
+ "165": 170,
333
+ "166": 171,
334
+ "167": 172,
335
+ "168": 173,
336
+ "169": 174,
337
+ "170": 175,
338
+ "171": 176,
339
+ "172": 177,
340
+ "173": 178,
341
+ "174": 179,
342
+ "175": 180,
343
+ "176": 181,
344
+ "177": 182,
345
+ "178": 183,
346
+ "179": 184,
347
+ "180": 185,
348
+ "181": 186,
349
+ "182": 187,
350
+ "183": 188,
351
+ "184": 189,
352
+ "185": 190,
353
+ "186": 191,
354
+ "187": 192,
355
+ "188": 193,
356
+ "189": 194,
357
+ "190": 195,
358
+ "191": 196,
359
+ "192": 197,
360
+ "193": 198,
361
+ "194": 199,
362
+ "195": 200,
363
+ "196": 201,
364
+ "197": 202,
365
+ "198": 203,
366
+ "199": 204,
367
+ "200": 205,
368
+ "201": 206,
369
+ "202": 207,
370
+ "203": 208,
371
+ "204": 209,
372
+ "205": 210,
373
+ "206": 211,
374
+ "207": 212,
375
+ "208": 213,
376
+ "209": 214,
377
+ "210": 215,
378
+ "211": 216,
379
+ "212": 217,
380
+ "213": 218,
381
+ "214": 219,
382
+ "215": 220,
383
+ "216": 221,
384
+ "217": 222,
385
+ "218": 223,
386
+ "219": 224,
387
+ "220": 225,
388
+ "221": 226,
389
+ "222": 227,
390
+ "223": 228,
391
+ "224": 229,
392
+ "225": 230,
393
+ "226": 231,
394
+ "227": 232,
395
+ "228": 233,
396
+ "229": 234,
397
+ "230": 235,
398
+ "231": 236,
399
+ "232": 237,
400
+ "233": 238,
401
+ "234": 239,
402
+ "235": 240,
403
+ "236": 241,
404
+ "237": 242,
405
+ "238": 243,
406
+ "239": 244,
407
+ "240": 245,
408
+ "241": 246,
409
+ "242": 247,
410
+ "243": 248,
411
+ "244": 249,
412
+ "245": 250,
413
+ "246": 251,
414
+ "247": 252,
415
+ "248": 253,
416
+ "249": 254,
417
+ "250": 255,
418
+ "251": 256,
419
+ "252": 257,
420
+ "253": 258,
421
+ "254": 259,
422
+ "255": 260
423
+ }
424
+ }
425
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "max_len": 256,
51
+ "max_length": 256,
52
+ "model_max_length": 256,
53
+ "never_split": null,
54
+ "pad_to_multiple_of": null,
55
+ "pad_token": "[PAD]",
56
+ "pad_token_type_id": 0,
57
+ "padding_side": "right",
58
+ "sep_token": "[SEP]",
59
+ "stride": 0,
60
+ "strip_accents": null,
61
+ "tokenize_chinese_chars": true,
62
+ "tokenizer_class": "BertTokenizer",
63
+ "truncation_side": "right",
64
+ "truncation_strategy": "longest_first",
65
+ "unk_token": "[UNK]"
66
+ }
vocab.txt ADDED
@@ -0,0 +1,261 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [PAD]
2
+ [UNK]
3
+ [CLS]
4
+ [SEP]
5
+ [MASK]
6
+ 0
7
+ 1
8
+ 2
9
+ 3
10
+ 4
11
+ 5
12
+ 6
13
+ 7
14
+ 8
15
+ 9
16
+ 10
17
+ 11
18
+ 12
19
+ 13
20
+ 14
21
+ 15
22
+ 16
23
+ 17
24
+ 18
25
+ 19
26
+ 20
27
+ 21
28
+ 22
29
+ 23
30
+ 24
31
+ 25
32
+ 26
33
+ 27
34
+ 28
35
+ 29
36
+ 30
37
+ 31
38
+ 32
39
+ 33
40
+ 34
41
+ 35
42
+ 36
43
+ 37
44
+ 38
45
+ 39
46
+ 40
47
+ 41
48
+ 42
49
+ 43
50
+ 44
51
+ 45
52
+ 46
53
+ 47
54
+ 48
55
+ 49
56
+ 50
57
+ 51
58
+ 52
59
+ 53
60
+ 54
61
+ 55
62
+ 56
63
+ 57
64
+ 58
65
+ 59
66
+ 60
67
+ 61
68
+ 62
69
+ 63
70
+ 64
71
+ 65
72
+ 66
73
+ 67
74
+ 68
75
+ 69
76
+ 70
77
+ 71
78
+ 72
79
+ 73
80
+ 74
81
+ 75
82
+ 76
83
+ 77
84
+ 78
85
+ 79
86
+ 80
87
+ 81
88
+ 82
89
+ 83
90
+ 84
91
+ 85
92
+ 86
93
+ 87
94
+ 88
95
+ 89
96
+ 90
97
+ 91
98
+ 92
99
+ 93
100
+ 94
101
+ 95
102
+ 96
103
+ 97
104
+ 98
105
+ 99
106
+ 100
107
+ 101
108
+ 102
109
+ 103
110
+ 104
111
+ 105
112
+ 106
113
+ 107
114
+ 108
115
+ 109
116
+ 110
117
+ 111
118
+ 112
119
+ 113
120
+ 114
121
+ 115
122
+ 116
123
+ 117
124
+ 118
125
+ 119
126
+ 120
127
+ 121
128
+ 122
129
+ 123
130
+ 124
131
+ 125
132
+ 126
133
+ 127
134
+ 128
135
+ 129
136
+ 130
137
+ 131
138
+ 132
139
+ 133
140
+ 134
141
+ 135
142
+ 136
143
+ 137
144
+ 138
145
+ 139
146
+ 140
147
+ 141
148
+ 142
149
+ 143
150
+ 144
151
+ 145
152
+ 146
153
+ 147
154
+ 148
155
+ 149
156
+ 150
157
+ 151
158
+ 152
159
+ 153
160
+ 154
161
+ 155
162
+ 156
163
+ 157
164
+ 158
165
+ 159
166
+ 160
167
+ 161
168
+ 162
169
+ 163
170
+ 164
171
+ 165
172
+ 166
173
+ 167
174
+ 168
175
+ 169
176
+ 170
177
+ 171
178
+ 172
179
+ 173
180
+ 174
181
+ 175
182
+ 176
183
+ 177
184
+ 178
185
+ 179
186
+ 180
187
+ 181
188
+ 182
189
+ 183
190
+ 184
191
+ 185
192
+ 186
193
+ 187
194
+ 188
195
+ 189
196
+ 190
197
+ 191
198
+ 192
199
+ 193
200
+ 194
201
+ 195
202
+ 196
203
+ 197
204
+ 198
205
+ 199
206
+ 200
207
+ 201
208
+ 202
209
+ 203
210
+ 204
211
+ 205
212
+ 206
213
+ 207
214
+ 208
215
+ 209
216
+ 210
217
+ 211
218
+ 212
219
+ 213
220
+ 214
221
+ 215
222
+ 216
223
+ 217
224
+ 218
225
+ 219
226
+ 220
227
+ 221
228
+ 222
229
+ 223
230
+ 224
231
+ 225
232
+ 226
233
+ 227
234
+ 228
235
+ 229
236
+ 230
237
+ 231
238
+ 232
239
+ 233
240
+ 234
241
+ 235
242
+ 236
243
+ 237
244
+ 238
245
+ 239
246
+ 240
247
+ 241
248
+ 242
249
+ 243
250
+ 244
251
+ 245
252
+ 246
253
+ 247
254
+ 248
255
+ 249
256
+ 250
257
+ 251
258
+ 252
259
+ 253
260
+ 254
261
+ 255