hellosindh commited on
Commit
106df91
·
verified ·
1 Parent(s): 5687bb1

Upload 4 files

Browse files
data/indus_tokenizer/indus_id_map.json ADDED
@@ -0,0 +1,643 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "T99": 99,
3
+ "T100": 100,
4
+ "T101": 101,
5
+ "T102": 102,
6
+ "T103": 103,
7
+ "T104": 104,
8
+ "T105": 105,
9
+ "T106": 106,
10
+ "T107": 107,
11
+ "T108": 108,
12
+ "T109": 109,
13
+ "T110": 110,
14
+ "T111": 111,
15
+ "T112": 112,
16
+ "T113": 113,
17
+ "T114": 114,
18
+ "T116": 116,
19
+ "T117": 117,
20
+ "T118": 118,
21
+ "T119": 119,
22
+ "T120": 120,
23
+ "T121": 121,
24
+ "T122": 122,
25
+ "T123": 123,
26
+ "T124": 124,
27
+ "T125": 125,
28
+ "T126": 126,
29
+ "T129": 129,
30
+ "T130": 130,
31
+ "T133": 133,
32
+ "T134": 134,
33
+ "T136": 136,
34
+ "T137": 137,
35
+ "T138": 138,
36
+ "T139": 139,
37
+ "T140": 140,
38
+ "T141": 141,
39
+ "T142": 142,
40
+ "T143": 143,
41
+ "T144": 144,
42
+ "T145": 145,
43
+ "T146": 146,
44
+ "T147": 147,
45
+ "T148": 148,
46
+ "T149": 149,
47
+ "T150": 150,
48
+ "T151": 151,
49
+ "T152": 152,
50
+ "T154": 154,
51
+ "T155": 155,
52
+ "T156": 156,
53
+ "T157": 157,
54
+ "T158": 158,
55
+ "T159": 159,
56
+ "T162": 162,
57
+ "T163": 163,
58
+ "T164": 164,
59
+ "T165": 165,
60
+ "T167": 167,
61
+ "T168": 168,
62
+ "T169": 169,
63
+ "T170": 170,
64
+ "T171": 171,
65
+ "T172": 172,
66
+ "T173": 173,
67
+ "T174": 174,
68
+ "T175": 175,
69
+ "T176": 176,
70
+ "T177": 177,
71
+ "T178": 178,
72
+ "T179": 179,
73
+ "T180": 180,
74
+ "T181": 181,
75
+ "T182": 182,
76
+ "T183": 183,
77
+ "T184": 184,
78
+ "T186": 186,
79
+ "T187": 187,
80
+ "T190": 190,
81
+ "T191": 191,
82
+ "T192": 192,
83
+ "T193": 193,
84
+ "T194": 194,
85
+ "T195": 195,
86
+ "T196": 196,
87
+ "T197": 197,
88
+ "T198": 198,
89
+ "T199": 199,
90
+ "T200": 200,
91
+ "T201": 201,
92
+ "T202": 202,
93
+ "T203": 203,
94
+ "T204": 204,
95
+ "T205": 205,
96
+ "T206": 206,
97
+ "T208": 208,
98
+ "T209": 209,
99
+ "T210": 210,
100
+ "T211": 211,
101
+ "T212": 212,
102
+ "T213": 213,
103
+ "T214": 214,
104
+ "T215": 215,
105
+ "T216": 216,
106
+ "T217": 217,
107
+ "T218": 218,
108
+ "T221": 221,
109
+ "T222": 222,
110
+ "T223": 223,
111
+ "T224": 224,
112
+ "T225": 225,
113
+ "T226": 226,
114
+ "T227": 227,
115
+ "T228": 228,
116
+ "T229": 229,
117
+ "T230": 230,
118
+ "T231": 231,
119
+ "T232": 232,
120
+ "T233": 233,
121
+ "T234": 234,
122
+ "T235": 235,
123
+ "T236": 236,
124
+ "T238": 238,
125
+ "T239": 239,
126
+ "T240": 240,
127
+ "T241": 241,
128
+ "T242": 242,
129
+ "T243": 243,
130
+ "T244": 244,
131
+ "T245": 245,
132
+ "T246": 246,
133
+ "T247": 247,
134
+ "T248": 248,
135
+ "T249": 249,
136
+ "T250": 250,
137
+ "T251": 251,
138
+ "T252": 252,
139
+ "T253": 253,
140
+ "T254": 254,
141
+ "T255": 255,
142
+ "T256": 256,
143
+ "T257": 257,
144
+ "T258": 258,
145
+ "T259": 259,
146
+ "T261": 261,
147
+ "T262": 262,
148
+ "T263": 263,
149
+ "T264": 264,
150
+ "T265": 265,
151
+ "T267": 267,
152
+ "T268": 268,
153
+ "T269": 269,
154
+ "T270": 270,
155
+ "T271": 271,
156
+ "T272": 272,
157
+ "T273": 273,
158
+ "T274": 274,
159
+ "T276": 276,
160
+ "T277": 277,
161
+ "T278": 278,
162
+ "T279": 279,
163
+ "T280": 280,
164
+ "T281": 281,
165
+ "T282": 282,
166
+ "T283": 283,
167
+ "T284": 284,
168
+ "T286": 286,
169
+ "T287": 287,
170
+ "T288": 288,
171
+ "T289": 289,
172
+ "T290": 290,
173
+ "T291": 291,
174
+ "T292": 292,
175
+ "T293": 293,
176
+ "T294": 294,
177
+ "T295": 295,
178
+ "T296": 296,
179
+ "T297": 297,
180
+ "T298": 298,
181
+ "T299": 299,
182
+ "T300": 300,
183
+ "T301": 301,
184
+ "T302": 302,
185
+ "T304": 304,
186
+ "T305": 305,
187
+ "T306": 306,
188
+ "T307": 307,
189
+ "T308": 308,
190
+ "T310": 310,
191
+ "T312": 312,
192
+ "T313": 313,
193
+ "T314": 314,
194
+ "T315": 315,
195
+ "T316": 316,
196
+ "T317": 317,
197
+ "T318": 318,
198
+ "T319": 319,
199
+ "T320": 320,
200
+ "T321": 321,
201
+ "T322": 322,
202
+ "T323": 323,
203
+ "T324": 324,
204
+ "T325": 325,
205
+ "T326": 326,
206
+ "T327": 327,
207
+ "T328": 328,
208
+ "T329": 329,
209
+ "T330": 330,
210
+ "T331": 331,
211
+ "T332": 332,
212
+ "T333": 333,
213
+ "T335": 335,
214
+ "T336": 336,
215
+ "T337": 337,
216
+ "T338": 338,
217
+ "T339": 339,
218
+ "T340": 340,
219
+ "T341": 341,
220
+ "T342": 342,
221
+ "T343": 343,
222
+ "T344": 344,
223
+ "T345": 345,
224
+ "T346": 346,
225
+ "T347": 347,
226
+ "T348": 348,
227
+ "T349": 349,
228
+ "T350": 350,
229
+ "T351": 351,
230
+ "T352": 352,
231
+ "T353": 353,
232
+ "T354": 354,
233
+ "T355": 355,
234
+ "T356": 356,
235
+ "T357": 357,
236
+ "T358": 358,
237
+ "T359": 359,
238
+ "T360": 360,
239
+ "T361": 361,
240
+ "T362": 362,
241
+ "T363": 363,
242
+ "T365": 365,
243
+ "T366": 366,
244
+ "T367": 367,
245
+ "T368": 368,
246
+ "T369": 369,
247
+ "T370": 370,
248
+ "T372": 372,
249
+ "T373": 373,
250
+ "T374": 374,
251
+ "T375": 375,
252
+ "T376": 376,
253
+ "T377": 377,
254
+ "T378": 378,
255
+ "T379": 379,
256
+ "T380": 380,
257
+ "T381": 381,
258
+ "T382": 382,
259
+ "T383": 383,
260
+ "T384": 384,
261
+ "T385": 385,
262
+ "T386": 386,
263
+ "T387": 387,
264
+ "T388": 388,
265
+ "T389": 389,
266
+ "T390": 390,
267
+ "T391": 391,
268
+ "T392": 392,
269
+ "T393": 393,
270
+ "T394": 394,
271
+ "T395": 395,
272
+ "T396": 396,
273
+ "T397": 397,
274
+ "T399": 399,
275
+ "T400": 400,
276
+ "T401": 401,
277
+ "T402": 402,
278
+ "T403": 403,
279
+ "T404": 404,
280
+ "T405": 405,
281
+ "T406": 406,
282
+ "T407": 407,
283
+ "T408": 408,
284
+ "T409": 409,
285
+ "T411": 411,
286
+ "T412": 412,
287
+ "T413": 413,
288
+ "T414": 414,
289
+ "T415": 415,
290
+ "T416": 416,
291
+ "T417": 417,
292
+ "T418": 418,
293
+ "T419": 419,
294
+ "T420": 420,
295
+ "T421": 421,
296
+ "T422": 422,
297
+ "T424": 424,
298
+ "T425": 425,
299
+ "T426": 426,
300
+ "T427": 427,
301
+ "T428": 428,
302
+ "T430": 430,
303
+ "T431": 431,
304
+ "T432": 432,
305
+ "T433": 433,
306
+ "T434": 434,
307
+ "T435": 435,
308
+ "T436": 436,
309
+ "T437": 437,
310
+ "T438": 438,
311
+ "T439": 439,
312
+ "T440": 440,
313
+ "T441": 441,
314
+ "T442": 442,
315
+ "T443": 443,
316
+ "T444": 444,
317
+ "T445": 445,
318
+ "T446": 446,
319
+ "T448": 448,
320
+ "T449": 449,
321
+ "T450": 450,
322
+ "T451": 451,
323
+ "T452": 452,
324
+ "T453": 453,
325
+ "T455": 455,
326
+ "T456": 456,
327
+ "T457": 457,
328
+ "T458": 458,
329
+ "T459": 459,
330
+ "T460": 460,
331
+ "T461": 461,
332
+ "T462": 462,
333
+ "T463": 463,
334
+ "T464": 464,
335
+ "T465": 465,
336
+ "T466": 466,
337
+ "T467": 467,
338
+ "T468": 468,
339
+ "T469": 469,
340
+ "T470": 470,
341
+ "T471": 471,
342
+ "T472": 472,
343
+ "T473": 473,
344
+ "T474": 474,
345
+ "T475": 475,
346
+ "T476": 476,
347
+ "T477": 477,
348
+ "T478": 478,
349
+ "T479": 479,
350
+ "T480": 480,
351
+ "T481": 481,
352
+ "T482": 482,
353
+ "T483": 483,
354
+ "T484": 484,
355
+ "T485": 485,
356
+ "T486": 486,
357
+ "T487": 487,
358
+ "T489": 489,
359
+ "T490": 490,
360
+ "T491": 491,
361
+ "T492": 492,
362
+ "T494": 494,
363
+ "T495": 495,
364
+ "T496": 496,
365
+ "T497": 497,
366
+ "T498": 498,
367
+ "T499": 499,
368
+ "T500": 500,
369
+ "T501": 501,
370
+ "T502": 502,
371
+ "T503": 503,
372
+ "T505": 505,
373
+ "T506": 506,
374
+ "T507": 507,
375
+ "T508": 508,
376
+ "T509": 509,
377
+ "T510": 510,
378
+ "T511": 511,
379
+ "T512": 512,
380
+ "T513": 513,
381
+ "T514": 514,
382
+ "T515": 515,
383
+ "T516": 516,
384
+ "T517": 517,
385
+ "T518": 518,
386
+ "T519": 519,
387
+ "T520": 520,
388
+ "T521": 521,
389
+ "T522": 522,
390
+ "T523": 523,
391
+ "T525": 525,
392
+ "T526": 526,
393
+ "T527": 527,
394
+ "T528": 528,
395
+ "T529": 529,
396
+ "T530": 530,
397
+ "T531": 531,
398
+ "T532": 532,
399
+ "T533": 533,
400
+ "T534": 534,
401
+ "T535": 535,
402
+ "T536": 536,
403
+ "T537": 537,
404
+ "T538": 538,
405
+ "T539": 539,
406
+ "T541": 541,
407
+ "T543": 543,
408
+ "T544": 544,
409
+ "T545": 545,
410
+ "T546": 546,
411
+ "T547": 547,
412
+ "T548": 548,
413
+ "T550": 550,
414
+ "T551": 551,
415
+ "T552": 552,
416
+ "T553": 553,
417
+ "T554": 554,
418
+ "T555": 555,
419
+ "T556": 556,
420
+ "T558": 558,
421
+ "T559": 559,
422
+ "T560": 560,
423
+ "T561": 561,
424
+ "T563": 563,
425
+ "T564": 564,
426
+ "T565": 565,
427
+ "T566": 566,
428
+ "T567": 567,
429
+ "T568": 568,
430
+ "T569": 569,
431
+ "T570": 570,
432
+ "T571": 571,
433
+ "T572": 572,
434
+ "T573": 573,
435
+ "T574": 574,
436
+ "T575": 575,
437
+ "T577": 577,
438
+ "T578": 578,
439
+ "T579": 579,
440
+ "T580": 580,
441
+ "T581": 581,
442
+ "T582": 582,
443
+ "T583": 583,
444
+ "T584": 584,
445
+ "T585": 585,
446
+ "T586": 586,
447
+ "T587": 587,
448
+ "T588": 588,
449
+ "T589": 589,
450
+ "T590": 590,
451
+ "T591": 591,
452
+ "T592": 592,
453
+ "T593": 593,
454
+ "T594": 594,
455
+ "T595": 595,
456
+ "T596": 596,
457
+ "T597": 597,
458
+ "T598": 598,
459
+ "T599": 599,
460
+ "T600": 600,
461
+ "T601": 601,
462
+ "T602": 602,
463
+ "T604": 604,
464
+ "T606": 606,
465
+ "T607": 607,
466
+ "T608": 608,
467
+ "T609": 609,
468
+ "T610": 610,
469
+ "T611": 611,
470
+ "T614": 614,
471
+ "T615": 615,
472
+ "T616": 616,
473
+ "T617": 617,
474
+ "T618": 618,
475
+ "T620": 620,
476
+ "T621": 621,
477
+ "T622": 622,
478
+ "T624": 624,
479
+ "T625": 625,
480
+ "T626": 626,
481
+ "T627": 627,
482
+ "T629": 629,
483
+ "T630": 630,
484
+ "T631": 631,
485
+ "T632": 632,
486
+ "T633": 633,
487
+ "T635": 635,
488
+ "T637": 637,
489
+ "T638": 638,
490
+ "T639": 639,
491
+ "T640": 640,
492
+ "T641": 641,
493
+ "T642": 642,
494
+ "T643": 643,
495
+ "T644": 644,
496
+ "T645": 645,
497
+ "T646": 646,
498
+ "T647": 647,
499
+ "T648": 648,
500
+ "T649": 649,
501
+ "T650": 650,
502
+ "T652": 652,
503
+ "T653": 653,
504
+ "T654": 654,
505
+ "T655": 655,
506
+ "T657": 657,
507
+ "T658": 658,
508
+ "T660": 660,
509
+ "T661": 661,
510
+ "T662": 662,
511
+ "T663": 663,
512
+ "T664": 664,
513
+ "T665": 665,
514
+ "T666": 666,
515
+ "T667": 667,
516
+ "T668": 668,
517
+ "T672": 672,
518
+ "T674": 674,
519
+ "T675": 675,
520
+ "T676": 676,
521
+ "T677": 677,
522
+ "T678": 678,
523
+ "T679": 679,
524
+ "T680": 680,
525
+ "T681": 681,
526
+ "T682": 682,
527
+ "T683": 683,
528
+ "T684": 684,
529
+ "T685": 685,
530
+ "T687": 687,
531
+ "T688": 688,
532
+ "T689": 689,
533
+ "T690": 690,
534
+ "T691": 691,
535
+ "T692": 692,
536
+ "T693": 693,
537
+ "T694": 694,
538
+ "T695": 695,
539
+ "T696": 696,
540
+ "T697": 697,
541
+ "T698": 698,
542
+ "T699": 699,
543
+ "T701": 701,
544
+ "T702": 702,
545
+ "T703": 703,
546
+ "T704": 704,
547
+ "T705": 705,
548
+ "T707": 707,
549
+ "T708": 708,
550
+ "T709": 709,
551
+ "T710": 710,
552
+ "T711": 711,
553
+ "T712": 712,
554
+ "T713": 713,
555
+ "T714": 714,
556
+ "T715": 715,
557
+ "T716": 716,
558
+ "T717": 717,
559
+ "T719": 719,
560
+ "T721": 721,
561
+ "T723": 723,
562
+ "T725": 725,
563
+ "T726": 726,
564
+ "T727": 727,
565
+ "T728": 728,
566
+ "T729": 729,
567
+ "T730": 730,
568
+ "T731": 731,
569
+ "T732": 732,
570
+ "T733": 733,
571
+ "T734": 734,
572
+ "T735": 735,
573
+ "T736": 736,
574
+ "T737": 737,
575
+ "T738": 738,
576
+ "T739": 739,
577
+ "T741": 741,
578
+ "T742": 742,
579
+ "T743": 743,
580
+ "T744": 744,
581
+ "T745": 745,
582
+ "T746": 746,
583
+ "T747": 747,
584
+ "T748": 748,
585
+ "T749": 749,
586
+ "T750": 750,
587
+ "T751": 751,
588
+ "T752": 752,
589
+ "T753": 753,
590
+ "T754": 754,
591
+ "T755": 755,
592
+ "T756": 756,
593
+ "T757": 757,
594
+ "T758": 758,
595
+ "T759": 759,
596
+ "T760": 760,
597
+ "T761": 761,
598
+ "T762": 762,
599
+ "T763": 763,
600
+ "T764": 764,
601
+ "T765": 765,
602
+ "T766": 766,
603
+ "T767": 767,
604
+ "T768": 768,
605
+ "T769": 769,
606
+ "T770": 770,
607
+ "T771": 771,
608
+ "T772": 772,
609
+ "T773": 773,
610
+ "T774": 774,
611
+ "T775": 775,
612
+ "T776": 776,
613
+ "T777": 777,
614
+ "T778": 778,
615
+ "T779": 779,
616
+ "T780": 780,
617
+ "T781": 781,
618
+ "T782": 782,
619
+ "T783": 783,
620
+ "T784": 784,
621
+ "T785": 785,
622
+ "T786": 786,
623
+ "T787": 787,
624
+ "T788": 788,
625
+ "T789": 789,
626
+ "T790": 790,
627
+ "T792": 792,
628
+ "T793": 793,
629
+ "T794": 794,
630
+ "T795": 795,
631
+ "T797": 797,
632
+ "T798": 798,
633
+ "T799": 799,
634
+ "T801": 801,
635
+ "T803": 803,
636
+ "T806": 806,
637
+ "T807": 807,
638
+ "T808": 808,
639
+ "T809": 809,
640
+ "T810": 810,
641
+ "T811": 811,
642
+ "T813": 813
643
+ }
data/indus_tokenizer/tokenizer.json ADDED
@@ -0,0 +1,766 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "[PAD]",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "[UNK]",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 2,
26
+ "content": "[CLS]",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 3,
35
+ "content": "[SEP]",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ },
42
+ {
43
+ "id": 4,
44
+ "content": "[MASK]",
45
+ "single_word": false,
46
+ "lstrip": false,
47
+ "rstrip": false,
48
+ "normalized": false,
49
+ "special": true
50
+ }
51
+ ],
52
+ "normalizer": null,
53
+ "pre_tokenizer": {
54
+ "type": "WhitespaceSplit"
55
+ },
56
+ "post_processor": {
57
+ "type": "TemplateProcessing",
58
+ "single": [
59
+ {
60
+ "SpecialToken": {
61
+ "id": "[CLS]",
62
+ "type_id": 0
63
+ }
64
+ },
65
+ {
66
+ "Sequence": {
67
+ "id": "A",
68
+ "type_id": 0
69
+ }
70
+ },
71
+ {
72
+ "SpecialToken": {
73
+ "id": "[SEP]",
74
+ "type_id": 0
75
+ }
76
+ }
77
+ ],
78
+ "pair": [
79
+ {
80
+ "Sequence": {
81
+ "id": "A",
82
+ "type_id": 0
83
+ }
84
+ },
85
+ {
86
+ "Sequence": {
87
+ "id": "B",
88
+ "type_id": 1
89
+ }
90
+ }
91
+ ],
92
+ "special_tokens": {
93
+ "[CLS]": {
94
+ "id": "[CLS]",
95
+ "ids": [
96
+ 2
97
+ ],
98
+ "tokens": [
99
+ "[CLS]"
100
+ ]
101
+ },
102
+ "[SEP]": {
103
+ "id": "[SEP]",
104
+ "ids": [
105
+ 3
106
+ ],
107
+ "tokens": [
108
+ "[SEP]"
109
+ ]
110
+ }
111
+ }
112
+ },
113
+ "decoder": null,
114
+ "model": {
115
+ "type": "WordLevel",
116
+ "vocab": {
117
+ "[PAD]": 0,
118
+ "[UNK]": 1,
119
+ "[CLS]": 2,
120
+ "[SEP]": 3,
121
+ "[MASK]": 4,
122
+ "T99": 5,
123
+ "T100": 6,
124
+ "T101": 7,
125
+ "T102": 8,
126
+ "T103": 9,
127
+ "T104": 10,
128
+ "T105": 11,
129
+ "T106": 12,
130
+ "T107": 13,
131
+ "T108": 14,
132
+ "T109": 15,
133
+ "T110": 16,
134
+ "T111": 17,
135
+ "T112": 18,
136
+ "T113": 19,
137
+ "T114": 20,
138
+ "T116": 21,
139
+ "T117": 22,
140
+ "T118": 23,
141
+ "T119": 24,
142
+ "T120": 25,
143
+ "T121": 26,
144
+ "T122": 27,
145
+ "T123": 28,
146
+ "T124": 29,
147
+ "T125": 30,
148
+ "T126": 31,
149
+ "T129": 32,
150
+ "T130": 33,
151
+ "T133": 34,
152
+ "T134": 35,
153
+ "T136": 36,
154
+ "T137": 37,
155
+ "T138": 38,
156
+ "T139": 39,
157
+ "T140": 40,
158
+ "T141": 41,
159
+ "T142": 42,
160
+ "T143": 43,
161
+ "T144": 44,
162
+ "T145": 45,
163
+ "T146": 46,
164
+ "T147": 47,
165
+ "T148": 48,
166
+ "T149": 49,
167
+ "T150": 50,
168
+ "T151": 51,
169
+ "T152": 52,
170
+ "T154": 53,
171
+ "T155": 54,
172
+ "T156": 55,
173
+ "T157": 56,
174
+ "T158": 57,
175
+ "T159": 58,
176
+ "T162": 59,
177
+ "T163": 60,
178
+ "T164": 61,
179
+ "T165": 62,
180
+ "T167": 63,
181
+ "T168": 64,
182
+ "T169": 65,
183
+ "T170": 66,
184
+ "T171": 67,
185
+ "T172": 68,
186
+ "T173": 69,
187
+ "T174": 70,
188
+ "T175": 71,
189
+ "T176": 72,
190
+ "T177": 73,
191
+ "T178": 74,
192
+ "T179": 75,
193
+ "T180": 76,
194
+ "T181": 77,
195
+ "T182": 78,
196
+ "T183": 79,
197
+ "T184": 80,
198
+ "T186": 81,
199
+ "T187": 82,
200
+ "T190": 83,
201
+ "T191": 84,
202
+ "T192": 85,
203
+ "T193": 86,
204
+ "T194": 87,
205
+ "T195": 88,
206
+ "T196": 89,
207
+ "T197": 90,
208
+ "T198": 91,
209
+ "T199": 92,
210
+ "T200": 93,
211
+ "T201": 94,
212
+ "T202": 95,
213
+ "T203": 96,
214
+ "T204": 97,
215
+ "T205": 98,
216
+ "T206": 99,
217
+ "T208": 100,
218
+ "T209": 101,
219
+ "T210": 102,
220
+ "T211": 103,
221
+ "T212": 104,
222
+ "T213": 105,
223
+ "T214": 106,
224
+ "T215": 107,
225
+ "T216": 108,
226
+ "T217": 109,
227
+ "T218": 110,
228
+ "T221": 111,
229
+ "T222": 112,
230
+ "T223": 113,
231
+ "T224": 114,
232
+ "T225": 115,
233
+ "T226": 116,
234
+ "T227": 117,
235
+ "T228": 118,
236
+ "T229": 119,
237
+ "T230": 120,
238
+ "T231": 121,
239
+ "T232": 122,
240
+ "T233": 123,
241
+ "T234": 124,
242
+ "T235": 125,
243
+ "T236": 126,
244
+ "T238": 127,
245
+ "T239": 128,
246
+ "T240": 129,
247
+ "T241": 130,
248
+ "T242": 131,
249
+ "T243": 132,
250
+ "T244": 133,
251
+ "T245": 134,
252
+ "T246": 135,
253
+ "T247": 136,
254
+ "T248": 137,
255
+ "T249": 138,
256
+ "T250": 139,
257
+ "T251": 140,
258
+ "T252": 141,
259
+ "T253": 142,
260
+ "T254": 143,
261
+ "T255": 144,
262
+ "T256": 145,
263
+ "T257": 146,
264
+ "T258": 147,
265
+ "T259": 148,
266
+ "T261": 149,
267
+ "T262": 150,
268
+ "T263": 151,
269
+ "T264": 152,
270
+ "T265": 153,
271
+ "T267": 154,
272
+ "T268": 155,
273
+ "T269": 156,
274
+ "T270": 157,
275
+ "T271": 158,
276
+ "T272": 159,
277
+ "T273": 160,
278
+ "T274": 161,
279
+ "T276": 162,
280
+ "T277": 163,
281
+ "T278": 164,
282
+ "T279": 165,
283
+ "T280": 166,
284
+ "T281": 167,
285
+ "T282": 168,
286
+ "T283": 169,
287
+ "T284": 170,
288
+ "T286": 171,
289
+ "T287": 172,
290
+ "T288": 173,
291
+ "T289": 174,
292
+ "T290": 175,
293
+ "T291": 176,
294
+ "T292": 177,
295
+ "T293": 178,
296
+ "T294": 179,
297
+ "T295": 180,
298
+ "T296": 181,
299
+ "T297": 182,
300
+ "T298": 183,
301
+ "T299": 184,
302
+ "T300": 185,
303
+ "T301": 186,
304
+ "T302": 187,
305
+ "T304": 188,
306
+ "T305": 189,
307
+ "T306": 190,
308
+ "T307": 191,
309
+ "T308": 192,
310
+ "T310": 193,
311
+ "T312": 194,
312
+ "T313": 195,
313
+ "T314": 196,
314
+ "T315": 197,
315
+ "T316": 198,
316
+ "T317": 199,
317
+ "T318": 200,
318
+ "T319": 201,
319
+ "T320": 202,
320
+ "T321": 203,
321
+ "T322": 204,
322
+ "T323": 205,
323
+ "T324": 206,
324
+ "T325": 207,
325
+ "T326": 208,
326
+ "T327": 209,
327
+ "T328": 210,
328
+ "T329": 211,
329
+ "T330": 212,
330
+ "T331": 213,
331
+ "T332": 214,
332
+ "T333": 215,
333
+ "T335": 216,
334
+ "T336": 217,
335
+ "T337": 218,
336
+ "T338": 219,
337
+ "T339": 220,
338
+ "T340": 221,
339
+ "T341": 222,
340
+ "T342": 223,
341
+ "T343": 224,
342
+ "T344": 225,
343
+ "T345": 226,
344
+ "T346": 227,
345
+ "T347": 228,
346
+ "T348": 229,
347
+ "T349": 230,
348
+ "T350": 231,
349
+ "T351": 232,
350
+ "T352": 233,
351
+ "T353": 234,
352
+ "T354": 235,
353
+ "T355": 236,
354
+ "T356": 237,
355
+ "T357": 238,
356
+ "T358": 239,
357
+ "T359": 240,
358
+ "T360": 241,
359
+ "T361": 242,
360
+ "T362": 243,
361
+ "T363": 244,
362
+ "T365": 245,
363
+ "T366": 246,
364
+ "T367": 247,
365
+ "T368": 248,
366
+ "T369": 249,
367
+ "T370": 250,
368
+ "T372": 251,
369
+ "T373": 252,
370
+ "T374": 253,
371
+ "T375": 254,
372
+ "T376": 255,
373
+ "T377": 256,
374
+ "T378": 257,
375
+ "T379": 258,
376
+ "T380": 259,
377
+ "T381": 260,
378
+ "T382": 261,
379
+ "T383": 262,
380
+ "T384": 263,
381
+ "T385": 264,
382
+ "T386": 265,
383
+ "T387": 266,
384
+ "T388": 267,
385
+ "T389": 268,
386
+ "T390": 269,
387
+ "T391": 270,
388
+ "T392": 271,
389
+ "T393": 272,
390
+ "T394": 273,
391
+ "T395": 274,
392
+ "T396": 275,
393
+ "T397": 276,
394
+ "T399": 277,
395
+ "T400": 278,
396
+ "T401": 279,
397
+ "T402": 280,
398
+ "T403": 281,
399
+ "T404": 282,
400
+ "T405": 283,
401
+ "T406": 284,
402
+ "T407": 285,
403
+ "T408": 286,
404
+ "T409": 287,
405
+ "T411": 288,
406
+ "T412": 289,
407
+ "T413": 290,
408
+ "T414": 291,
409
+ "T415": 292,
410
+ "T416": 293,
411
+ "T417": 294,
412
+ "T418": 295,
413
+ "T419": 296,
414
+ "T420": 297,
415
+ "T421": 298,
416
+ "T422": 299,
417
+ "T424": 300,
418
+ "T425": 301,
419
+ "T426": 302,
420
+ "T427": 303,
421
+ "T428": 304,
422
+ "T430": 305,
423
+ "T431": 306,
424
+ "T432": 307,
425
+ "T433": 308,
426
+ "T434": 309,
427
+ "T435": 310,
428
+ "T436": 311,
429
+ "T437": 312,
430
+ "T438": 313,
431
+ "T439": 314,
432
+ "T440": 315,
433
+ "T441": 316,
434
+ "T442": 317,
435
+ "T443": 318,
436
+ "T444": 319,
437
+ "T445": 320,
438
+ "T446": 321,
439
+ "T448": 322,
440
+ "T449": 323,
441
+ "T450": 324,
442
+ "T451": 325,
443
+ "T452": 326,
444
+ "T453": 327,
445
+ "T455": 328,
446
+ "T456": 329,
447
+ "T457": 330,
448
+ "T458": 331,
449
+ "T459": 332,
450
+ "T460": 333,
451
+ "T461": 334,
452
+ "T462": 335,
453
+ "T463": 336,
454
+ "T464": 337,
455
+ "T465": 338,
456
+ "T466": 339,
457
+ "T467": 340,
458
+ "T468": 341,
459
+ "T469": 342,
460
+ "T470": 343,
461
+ "T471": 344,
462
+ "T472": 345,
463
+ "T473": 346,
464
+ "T474": 347,
465
+ "T475": 348,
466
+ "T476": 349,
467
+ "T477": 350,
468
+ "T478": 351,
469
+ "T479": 352,
470
+ "T480": 353,
471
+ "T481": 354,
472
+ "T482": 355,
473
+ "T483": 356,
474
+ "T484": 357,
475
+ "T485": 358,
476
+ "T486": 359,
477
+ "T487": 360,
478
+ "T489": 361,
479
+ "T490": 362,
480
+ "T491": 363,
481
+ "T492": 364,
482
+ "T494": 365,
483
+ "T495": 366,
484
+ "T496": 367,
485
+ "T497": 368,
486
+ "T498": 369,
487
+ "T499": 370,
488
+ "T500": 371,
489
+ "T501": 372,
490
+ "T502": 373,
491
+ "T503": 374,
492
+ "T505": 375,
493
+ "T506": 376,
494
+ "T507": 377,
495
+ "T508": 378,
496
+ "T509": 379,
497
+ "T510": 380,
498
+ "T511": 381,
499
+ "T512": 382,
500
+ "T513": 383,
501
+ "T514": 384,
502
+ "T515": 385,
503
+ "T516": 386,
504
+ "T517": 387,
505
+ "T518": 388,
506
+ "T519": 389,
507
+ "T520": 390,
508
+ "T521": 391,
509
+ "T522": 392,
510
+ "T523": 393,
511
+ "T525": 394,
512
+ "T526": 395,
513
+ "T527": 396,
514
+ "T528": 397,
515
+ "T529": 398,
516
+ "T530": 399,
517
+ "T531": 400,
518
+ "T532": 401,
519
+ "T533": 402,
520
+ "T534": 403,
521
+ "T535": 404,
522
+ "T536": 405,
523
+ "T537": 406,
524
+ "T538": 407,
525
+ "T539": 408,
526
+ "T541": 409,
527
+ "T543": 410,
528
+ "T544": 411,
529
+ "T545": 412,
530
+ "T546": 413,
531
+ "T547": 414,
532
+ "T548": 415,
533
+ "T550": 416,
534
+ "T551": 417,
535
+ "T552": 418,
536
+ "T553": 419,
537
+ "T554": 420,
538
+ "T555": 421,
539
+ "T556": 422,
540
+ "T558": 423,
541
+ "T559": 424,
542
+ "T560": 425,
543
+ "T561": 426,
544
+ "T563": 427,
545
+ "T564": 428,
546
+ "T565": 429,
547
+ "T566": 430,
548
+ "T567": 431,
549
+ "T568": 432,
550
+ "T569": 433,
551
+ "T570": 434,
552
+ "T571": 435,
553
+ "T572": 436,
554
+ "T573": 437,
555
+ "T574": 438,
556
+ "T575": 439,
557
+ "T577": 440,
558
+ "T578": 441,
559
+ "T579": 442,
560
+ "T580": 443,
561
+ "T581": 444,
562
+ "T582": 445,
563
+ "T583": 446,
564
+ "T584": 447,
565
+ "T585": 448,
566
+ "T586": 449,
567
+ "T587": 450,
568
+ "T588": 451,
569
+ "T589": 452,
570
+ "T590": 453,
571
+ "T591": 454,
572
+ "T592": 455,
573
+ "T593": 456,
574
+ "T594": 457,
575
+ "T595": 458,
576
+ "T596": 459,
577
+ "T597": 460,
578
+ "T598": 461,
579
+ "T599": 462,
580
+ "T600": 463,
581
+ "T601": 464,
582
+ "T602": 465,
583
+ "T604": 466,
584
+ "T606": 467,
585
+ "T607": 468,
586
+ "T608": 469,
587
+ "T609": 470,
588
+ "T610": 471,
589
+ "T611": 472,
590
+ "T614": 473,
591
+ "T615": 474,
592
+ "T616": 475,
593
+ "T617": 476,
594
+ "T618": 477,
595
+ "T620": 478,
596
+ "T621": 479,
597
+ "T622": 480,
598
+ "T624": 481,
599
+ "T625": 482,
600
+ "T626": 483,
601
+ "T627": 484,
602
+ "T629": 485,
603
+ "T630": 486,
604
+ "T631": 487,
605
+ "T632": 488,
606
+ "T633": 489,
607
+ "T635": 490,
608
+ "T637": 491,
609
+ "T638": 492,
610
+ "T639": 493,
611
+ "T640": 494,
612
+ "T641": 495,
613
+ "T642": 496,
614
+ "T643": 497,
615
+ "T644": 498,
616
+ "T645": 499,
617
+ "T646": 500,
618
+ "T647": 501,
619
+ "T648": 502,
620
+ "T649": 503,
621
+ "T650": 504,
622
+ "T652": 505,
623
+ "T653": 506,
624
+ "T654": 507,
625
+ "T655": 508,
626
+ "T657": 509,
627
+ "T658": 510,
628
+ "T660": 511,
629
+ "T661": 512,
630
+ "T662": 513,
631
+ "T663": 514,
632
+ "T664": 515,
633
+ "T665": 516,
634
+ "T666": 517,
635
+ "T667": 518,
636
+ "T668": 519,
637
+ "T672": 520,
638
+ "T674": 521,
639
+ "T675": 522,
640
+ "T676": 523,
641
+ "T677": 524,
642
+ "T678": 525,
643
+ "T679": 526,
644
+ "T680": 527,
645
+ "T681": 528,
646
+ "T682": 529,
647
+ "T683": 530,
648
+ "T684": 531,
649
+ "T685": 532,
650
+ "T687": 533,
651
+ "T688": 534,
652
+ "T689": 535,
653
+ "T690": 536,
654
+ "T691": 537,
655
+ "T692": 538,
656
+ "T693": 539,
657
+ "T694": 540,
658
+ "T695": 541,
659
+ "T696": 542,
660
+ "T697": 543,
661
+ "T698": 544,
662
+ "T699": 545,
663
+ "T701": 546,
664
+ "T702": 547,
665
+ "T703": 548,
666
+ "T704": 549,
667
+ "T705": 550,
668
+ "T707": 551,
669
+ "T708": 552,
670
+ "T709": 553,
671
+ "T710": 554,
672
+ "T711": 555,
673
+ "T712": 556,
674
+ "T713": 557,
675
+ "T714": 558,
676
+ "T715": 559,
677
+ "T716": 560,
678
+ "T717": 561,
679
+ "T719": 562,
680
+ "T721": 563,
681
+ "T723": 564,
682
+ "T725": 565,
683
+ "T726": 566,
684
+ "T727": 567,
685
+ "T728": 568,
686
+ "T729": 569,
687
+ "T730": 570,
688
+ "T731": 571,
689
+ "T732": 572,
690
+ "T733": 573,
691
+ "T734": 574,
692
+ "T735": 575,
693
+ "T736": 576,
694
+ "T737": 577,
695
+ "T738": 578,
696
+ "T739": 579,
697
+ "T741": 580,
698
+ "T742": 581,
699
+ "T743": 582,
700
+ "T744": 583,
701
+ "T745": 584,
702
+ "T746": 585,
703
+ "T747": 586,
704
+ "T748": 587,
705
+ "T749": 588,
706
+ "T750": 589,
707
+ "T751": 590,
708
+ "T752": 591,
709
+ "T753": 592,
710
+ "T754": 593,
711
+ "T755": 594,
712
+ "T756": 595,
713
+ "T757": 596,
714
+ "T758": 597,
715
+ "T759": 598,
716
+ "T760": 599,
717
+ "T761": 600,
718
+ "T762": 601,
719
+ "T763": 602,
720
+ "T764": 603,
721
+ "T765": 604,
722
+ "T766": 605,
723
+ "T767": 606,
724
+ "T768": 607,
725
+ "T769": 608,
726
+ "T770": 609,
727
+ "T771": 610,
728
+ "T772": 611,
729
+ "T773": 612,
730
+ "T774": 613,
731
+ "T775": 614,
732
+ "T776": 615,
733
+ "T777": 616,
734
+ "T778": 617,
735
+ "T779": 618,
736
+ "T780": 619,
737
+ "T781": 620,
738
+ "T782": 621,
739
+ "T783": 622,
740
+ "T784": 623,
741
+ "T785": 624,
742
+ "T786": 625,
743
+ "T787": 626,
744
+ "T788": 627,
745
+ "T789": 628,
746
+ "T790": 629,
747
+ "T792": 630,
748
+ "T793": 631,
749
+ "T794": 632,
750
+ "T795": 633,
751
+ "T797": 634,
752
+ "T798": 635,
753
+ "T799": 636,
754
+ "T801": 637,
755
+ "T803": 638,
756
+ "T806": 639,
757
+ "T807": 640,
758
+ "T808": 641,
759
+ "T809": 642,
760
+ "T810": 643,
761
+ "T811": 644,
762
+ "T813": 645
763
+ },
764
+ "unk_token": "[UNK]"
765
+ }
766
+ }
data/indus_tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "cls_token": "[CLS]",
4
+ "mask_token": "[MASK]",
5
+ "model_max_length": 1000000000000000019884624838656,
6
+ "pad_token": "[PAD]",
7
+ "sep_token": "[SEP]",
8
+ "tokenizer_class": "TokenizersBackend",
9
+ "unk_token": "[UNK]"
10
+ }
data/indus_tokenizer/tokenizer_info.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "vocab_size": 646,
3
+ "indus_token_count": 641,
4
+ "pad_token_id": 0,
5
+ "cls_token_id": 2,
6
+ "sep_token_id": 3,
7
+ "mask_token_id": 4,
8
+ "unk_token_id": 1
9
+ }