bullmount commited on
Commit
2dfbbba
1 Parent(s): 806f381

Upload tokenizer.json

Browse files
Files changed (1) hide show
  1. tokenizer.json +1 -513
tokenizer.json CHANGED
@@ -53,519 +53,7 @@
53
  "rstrip": false,
54
  "normalized": false
55
  },
56
- {
57
- "id": 31102,
58
- "special": false,
59
- "content": "disciplinato",
60
- "single_word": false,
61
- "lstrip": false,
62
- "rstrip": false,
63
- "normalized": true
64
- },
65
- {
66
- "id": 31103,
67
- "special": false,
68
- "content": "punito",
69
- "single_word": false,
70
- "lstrip": false,
71
- "rstrip": false,
72
- "normalized": true
73
- },
74
- {
75
- "id": 31104,
76
- "special": false,
77
- "content": "accertamento",
78
- "single_word": false,
79
- "lstrip": false,
80
- "rstrip": false,
81
- "normalized": true
82
- },
83
- {
84
- "id": 31105,
85
- "special": false,
86
- "content": "predetto",
87
- "single_word": false,
88
- "lstrip": false,
89
- "rstrip": false,
90
- "normalized": true
91
- },
92
- {
93
- "id": 31106,
94
- "special": false,
95
- "content": "idrografico",
96
- "single_word": false,
97
- "lstrip": false,
98
- "rstrip": false,
99
- "normalized": true
100
- },
101
- {
102
- "id": 31107,
103
- "special": false,
104
- "content": "adempimento",
105
- "single_word": false,
106
- "lstrip": false,
107
- "rstrip": false,
108
- "normalized": true
109
- },
110
- {
111
- "id": 31108,
112
- "special": false,
113
- "content": "bonifica",
114
- "single_word": false,
115
- "lstrip": false,
116
- "rstrip": false,
117
- "normalized": true
118
- },
119
- {
120
- "id": 31109,
121
- "special": false,
122
- "content": "sanzione",
123
- "single_word": false,
124
- "lstrip": false,
125
- "rstrip": false,
126
- "normalized": true
127
- },
128
- {
129
- "id": 31110,
130
- "special": false,
131
- "content": "modificazione",
132
- "single_word": false,
133
- "lstrip": false,
134
- "rstrip": false,
135
- "normalized": true
136
- },
137
- {
138
- "id": 31111,
139
- "special": false,
140
- "content": "proponente",
141
- "single_word": false,
142
- "lstrip": false,
143
- "rstrip": false,
144
- "normalized": true
145
- },
146
- {
147
- "id": 31112,
148
- "special": false,
149
- "content": "reflua",
150
- "single_word": false,
151
- "lstrip": false,
152
- "rstrip": false,
153
- "normalized": true
154
- },
155
- {
156
- "id": 31113,
157
- "special": false,
158
- "content": "ammenda",
159
- "single_word": false,
160
- "lstrip": false,
161
- "rstrip": false,
162
- "normalized": true
163
- },
164
- {
165
- "id": 31114,
166
- "special": false,
167
- "content": "riutilizzo",
168
- "single_word": false,
169
- "lstrip": false,
170
- "rstrip": false,
171
- "normalized": true
172
- },
173
- {
174
- "id": 31115,
175
- "special": false,
176
- "content": "incenerimento",
177
- "single_word": false,
178
- "lstrip": false,
179
- "rstrip": false,
180
- "normalized": true
181
- },
182
- {
183
- "id": 31116,
184
- "special": false,
185
- "content": "coincenerimento",
186
- "single_word": false,
187
- "lstrip": false,
188
- "rstrip": false,
189
- "normalized": true
190
- },
191
- {
192
- "id": 31117,
193
- "special": false,
194
- "content": "individuazione",
195
- "single_word": false,
196
- "lstrip": false,
197
- "rstrip": false,
198
- "normalized": true
199
- },
200
- {
201
- "id": 31118,
202
- "special": false,
203
- "content": "pecuniaria",
204
- "single_word": false,
205
- "lstrip": false,
206
- "rstrip": false,
207
- "normalized": true
208
- },
209
- {
210
- "id": 31119,
211
- "special": false,
212
- "content": "quater",
213
- "single_word": false,
214
- "lstrip": false,
215
- "rstrip": false,
216
- "normalized": true
217
- },
218
- {
219
- "id": 31120,
220
- "special": false,
221
- "content": "amianto",
222
- "single_word": false,
223
- "lstrip": false,
224
- "rstrip": false,
225
- "normalized": true
226
- },
227
- {
228
- "id": 31121,
229
- "special": false,
230
- "content": "ISPRA",
231
- "single_word": false,
232
- "lstrip": false,
233
- "rstrip": false,
234
- "normalized": true
235
- },
236
- {
237
- "id": 31122,
238
- "special": false,
239
- "content": "territorialmente",
240
- "single_word": false,
241
- "lstrip": false,
242
- "rstrip": false,
243
- "normalized": true
244
- },
245
- {
246
- "id": 31123,
247
- "special": false,
248
- "content": "istruttoria",
249
- "single_word": false,
250
- "lstrip": false,
251
- "rstrip": false,
252
- "normalized": true
253
- },
254
- {
255
- "id": 31124,
256
- "special": false,
257
- "content": "depurazione",
258
- "single_word": false,
259
- "lstrip": false,
260
- "rstrip": false,
261
- "normalized": true
262
- },
263
- {
264
- "id": 31125,
265
- "special": false,
266
- "content": "assoggettabilità",
267
- "single_word": false,
268
- "lstrip": false,
269
- "rstrip": false,
270
- "normalized": true
271
- },
272
- {
273
- "id": 31126,
274
- "special": false,
275
- "content": "quinquies",
276
- "single_word": false,
277
- "lstrip": false,
278
- "rstrip": false,
279
- "normalized": true
280
- },
281
- {
282
- "id": 31127,
283
- "special": false,
284
- "content": "differenziato",
285
- "single_word": false,
286
- "lstrip": false,
287
- "rstrip": false,
288
- "normalized": true
289
- },
290
- {
291
- "id": 31128,
292
- "special": false,
293
- "content": "sexies",
294
- "single_word": false,
295
- "lstrip": false,
296
- "rstrip": false,
297
- "normalized": true
298
- },
299
- {
300
- "id": 31129,
301
- "special": false,
302
- "content": "emanazione",
303
- "single_word": false,
304
- "lstrip": false,
305
- "rstrip": false,
306
- "normalized": true
307
- },
308
- {
309
- "id": 31130,
310
- "special": false,
311
- "content": "albo",
312
- "single_word": false,
313
- "lstrip": false,
314
- "rstrip": false,
315
- "normalized": true
316
- },
317
- {
318
- "id": 31131,
319
- "special": false,
320
- "content": "riciclato",
321
- "single_word": false,
322
- "lstrip": false,
323
- "rstrip": false,
324
- "normalized": true
325
- },
326
- {
327
- "id": 31132,
328
- "special": false,
329
- "content": "ISPESL",
330
- "single_word": false,
331
- "lstrip": false,
332
- "rstrip": false,
333
- "normalized": true
334
- },
335
- {
336
- "id": 31133,
337
- "special": false,
338
- "content": "committente",
339
- "single_word": false,
340
- "lstrip": false,
341
- "rstrip": false,
342
- "normalized": true
343
- },
344
- {
345
- "id": 31134,
346
- "special": false,
347
- "content": "INAIL",
348
- "single_word": false,
349
- "lstrip": false,
350
- "rstrip": false,
351
- "normalized": true
352
- },
353
- {
354
- "id": 31135,
355
- "special": false,
356
- "content": "diffida",
357
- "single_word": false,
358
- "lstrip": false,
359
- "rstrip": false,
360
- "normalized": true
361
- },
362
- {
363
- "id": 31136,
364
- "special": false,
365
- "content": "VLE",
366
- "single_word": false,
367
- "lstrip": false,
368
- "rstrip": false,
369
- "normalized": true
370
- },
371
- {
372
- "id": 31137,
373
- "special": false,
374
- "content": "VAS",
375
- "single_word": false,
376
- "lstrip": false,
377
- "rstrip": false,
378
- "normalized": true
379
- },
380
- {
381
- "id": 31138,
382
- "special": false,
383
- "content": "idoneità",
384
- "single_word": false,
385
- "lstrip": false,
386
- "rstrip": false,
387
- "normalized": true
388
- },
389
- {
390
- "id": 31139,
391
- "special": false,
392
- "content": "semplificato",
393
- "single_word": false,
394
- "lstrip": false,
395
- "rstrip": false,
396
- "normalized": true
397
- },
398
- {
399
- "id": 31140,
400
- "special": false,
401
- "content": "DPI",
402
- "single_word": false,
403
- "lstrip": false,
404
- "rstrip": false,
405
- "normalized": true
406
- },
407
- {
408
- "id": 31141,
409
- "special": false,
410
- "content": "applicarsi",
411
- "single_word": false,
412
- "lstrip": false,
413
- "rstrip": false,
414
- "normalized": true
415
- },
416
- {
417
- "id": 31142,
418
- "special": false,
419
- "content": "octies",
420
- "single_word": false,
421
- "lstrip": false,
422
- "rstrip": false,
423
- "normalized": true
424
- },
425
- {
426
- "id": 31143,
427
- "special": false,
428
- "content": "MW",
429
- "single_word": false,
430
- "lstrip": false,
431
- "rstrip": false,
432
- "normalized": true
433
- },
434
- {
435
- "id": 31144,
436
- "special": false,
437
- "content": "riciclo",
438
- "single_word": false,
439
- "lstrip": false,
440
- "rstrip": false,
441
- "normalized": true
442
- },
443
- {
444
- "id": 31145,
445
- "special": false,
446
- "content": "BAT",
447
- "single_word": false,
448
- "lstrip": false,
449
- "rstrip": false,
450
- "normalized": true
451
- },
452
- {
453
- "id": 31146,
454
- "special": false,
455
- "content": "tracciabilità",
456
- "single_word": false,
457
- "lstrip": false,
458
- "rstrip": false,
459
- "normalized": true
460
- },
461
- {
462
- "id": 31147,
463
- "special": false,
464
- "content": "rappresentativo",
465
- "single_word": false,
466
- "lstrip": false,
467
- "rstrip": false,
468
- "normalized": true
469
- },
470
- {
471
- "id": 31148,
472
- "special": false,
473
- "content": "espletamento",
474
- "single_word": false,
475
- "lstrip": false,
476
- "rstrip": false,
477
- "normalized": true
478
- },
479
- {
480
- "id": 31149,
481
- "special": false,
482
- "content": "effettuazione",
483
- "single_word": false,
484
- "lstrip": false,
485
- "rstrip": false,
486
- "normalized": true
487
- },
488
- {
489
- "id": 31150,
490
- "special": false,
491
- "content": "tempestivamente",
492
- "single_word": false,
493
- "lstrip": false,
494
- "rstrip": false,
495
- "normalized": true
496
- },
497
- {
498
- "id": 31151,
499
- "special": false,
500
- "content": "limitatamente",
501
- "single_word": false,
502
- "lstrip": false,
503
- "rstrip": false,
504
- "normalized": true
505
- },
506
- {
507
- "id": 31152,
508
- "special": false,
509
- "content": "economicità",
510
- "single_word": false,
511
- "lstrip": false,
512
- "rstrip": false,
513
- "normalized": true
514
- },
515
- {
516
- "id": 31153,
517
- "special": false,
518
- "content": "osservanza",
519
- "single_word": false,
520
- "lstrip": false,
521
- "rstrip": false,
522
- "normalized": true
523
- },
524
- {
525
- "id": 31154,
526
- "special": false,
527
- "content": "cancerogeno",
528
- "single_word": false,
529
- "lstrip": false,
530
- "rstrip": false,
531
- "normalized": true
532
- },
533
- {
534
- "id": 31155,
535
- "special": false,
536
- "content": "gassoso",
537
- "single_word": false,
538
- "lstrip": false,
539
- "rstrip": false,
540
- "normalized": true
541
- },
542
- {
543
- "id": 31156,
544
- "special": false,
545
- "content": "caratterizzazione",
546
- "single_word": false,
547
- "lstrip": false,
548
- "rstrip": false,
549
- "normalized": true
550
- },
551
- {
552
- "id": 31157,
553
- "special": false,
554
- "content": "sottosuolo",
555
- "single_word": false,
556
- "lstrip": false,
557
- "rstrip": false,
558
- "normalized": true
559
- },
560
- {
561
- "id": 31158,
562
- "special": false,
563
- "content": "osservatorio",
564
- "single_word": false,
565
- "lstrip": false,
566
- "rstrip": false,
567
- "normalized": true
568
- }
569
  ],
570
  "normalizer": {
571
  "type": "BertNormalizer",
 
53
  "rstrip": false,
54
  "normalized": false
55
  },
56
+
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
57
  ],
58
  "normalizer": {
59
  "type": "BertNormalizer",