codebyzeb commited on
Commit
e649e4e
·
verified ·
1 Parent(s): 7b7b585

Upload folder using huggingface_hub

Browse files
fw57M_Entropy_thresholdB_16000/tokenizer.json CHANGED
@@ -318,262 +318,262 @@
318
  "Ł": 255,
319
  "ł": 256,
320
  "Ń": 257,
321
- "##=": 258,
322
- "##©": 259,
323
- "##w": 260,
324
- "##Ė": 261,
325
- "###": 262,
326
- "##Ë": 263,
327
- "##_": 264,
328
- "##Å": 265,
329
- "##½": 266,
330
- "##Ì": 267,
331
- "##9": 268,
332
- "##{": 269,
333
- "##W": 270,
334
- "##m": 271,
335
- "##y": 272,
336
- "##Ê": 273,
337
- "##Â": 274,
338
- "##4": 275,
339
- "##7": 276,
340
- "##Ó": 277,
341
- "##ë": 278,
342
- "##i": 279,
343
- "##Ð": 280,
344
- "##Đ": 281,
345
- "##ļ": 282,
346
- "##$": 283,
347
- "##g": 284,
348
- "##ĺ": 285,
349
- "##´": 286,
350
- "##r": 287,
351
- "##Ď": 288,
352
- "##ö": 289,
353
- "##ð": 290,
354
- "##¿": 291,
355
- "##E": 292,
356
- "##u": 293,
357
- "##:": 294,
358
- "##ĉ": 295,
359
- "##Ù": 296,
360
- "##ĭ": 297,
361
- "##/": 298,
362
- "##ç": 299,
363
- "##ĥ": 300,
364
- "##²": 301,
365
- "##Ç": 302,
366
- "##^": 303,
367
- "##ć": 304,
368
- "##j": 305,
369
- "##v": 306,
370
- "##~": 307,
371
- "##N": 308,
372
- "##Ń": 309,
373
- "##q": 310,
374
- "##ġ": 311,
375
- "##È": 312,
376
- "##ğ": 313,
377
- "##ĝ": 314,
378
- "##ø": 315,
379
- "##æ": 316,
380
- "##D": 317,
381
- "##)": 318,
382
- "##ģ": 319,
383
- "##Ý": 320,
384
- "##5": 321,
385
- "##ij": 322,
386
- "##3": 323,
387
- "##ė": 324,
388
- "##ķ": 325,
389
- "##ò": 326,
390
- "##®": 327,
391
- "##x": 328,
392
- "##t": 329,
393
- "##;": 330,
394
- "##¹": 331,
395
- "##×": 332,
396
- "##Û": 333,
397
- "##k": 334,
398
- "##ã": 335,
399
- "##ċ": 336,
400
- "##¤": 337,
401
- "##&": 338,
402
- "##Ä": 339,
403
- "##b": 340,
404
- "##Ñ": 341,
405
- "##Ã": 342,
406
- "##ú": 343,
407
- "##F": 344,
408
- "##¦": 345,
409
- "##p": 346,
410
- "##¼": 347,
411
- "##ä": 348,
412
- "##ï": 349,
413
- "##¢": 350,
414
- "##Ġ": 351,
415
- "##î": 352,
416
- "##Ĩ": 353,
417
- "##Ü": 354,
418
- "##·": 355,
419
- "##¡": 356,
420
- "##°": 357,
421
- "##§": 358,
422
- "##â": 359,
423
- "##[": 360,
424
- "##ď": 361,
425
- "##ā": 362,
426
- "##Þ": 363,
427
- "##Ă": 364,
428
- "##à": 365,
429
- "##Ĥ": 366,
430
- "##c": 367,
431
- "##á": 368,
432
- "##ê": 369,
433
- "##ħ": 370,
434
- "##ĕ": 371,
435
- "##ñ": 372,
436
- "##¯": 373,
437
- "##Ĺ": 374,
438
- "##Ö": 375,
439
- "##Ć": 376,
440
- "##T": 377,
441
- "##Ĵ": 378,
442
- "##>": 379,
443
- "##+": 380,
444
- "##ē": 381,
445
- "##n": 382,
446
- "##¥": 383,
447
- "##Æ": 384,
448
- "##X": 385,
449
- "##³": 386,
450
- "##'": 387,
451
- "##P": 388,
452
- "##Ě": 389,
453
- "##ą": 390,
454
- "##č": 391,
455
- "##µ": 392,
456
- "##R": 393,
457
- "##Ï": 394,
458
- "##ĵ": 395,
459
- "##¸": 396,
460
- "##Ľ": 397,
461
- "##Ĝ": 398,
462
- "##Õ": 399,
463
- "##Ļ": 400,
464
- "##J": 401,
465
- "##»": 402,
466
- "##ª": 403,
467
- "##é": 404,
468
- "##Ę": 405,
469
- "##«": 406,
470
- "##Ī": 407,
471
- "##Ģ": 408,
472
- "##?": 409,
473
- "##Ķ": 410,
474
- "##ł": 411,
475
- "##ě": 412,
476
- "##@": 413,
477
- "##Ĕ": 414,
478
- "##ī": 415,
479
- "##Ĭ": 416,
480
- "##`": 417,
481
- "##Z": 418,
482
- "##ý": 419,
483
- "##]": 420,
484
- "##(": 421,
485
- "##Ē": 422,
486
- "##}": 423,
487
- "##<": 424,
488
- "##K": 425,
489
- "##e": 426,
490
- "##É": 427,
491
- "##.": 428,
492
- "##å": 429,
493
- "##A": 430,
494
- "##f": 431,
495
- "##M": 432,
496
- "##1": 433,
497
- "##G": 434,
498
- "##Î": 435,
499
- "##8": 436,
500
- "##ù": 437,
501
- "##d": 438,
502
- "##z": 439,
503
- "##£": 440,
504
- "##Ā": 441,
505
- "##ę": 442,
506
- "##į": 443,
507
- "##İ": 444,
508
- "##ı": 445,
509
- "##C": 446,
510
- "##÷": 447,
511
- "##ľ": 448,
512
- "##ÿ": 449,
513
- "##!": 450,
514
- "##l": 451,
515
- "##¶": 452,
516
- "##Ą": 453,
517
- "##Ċ": 454,
518
- "##ó": 455,
519
- "##ă": 456,
520
- "##Í": 457,
521
- "##0": 458,
522
- "##À": 459,
523
- "##2": 460,
524
- "##¾": 461,
525
- "##I": 462,
526
- "##Ł": 463,
527
- "##þ": 464,
528
- "##O": 465,
529
- "##Ò": 466,
530
- "##B": 467,
531
- "##\\": 468,
532
- "##Ħ": 469,
533
- "##H": 470,
534
- "##õ": 471,
535
- "##s": 472,
536
- "##Ø": 473,
537
- "##Ú": 474,
538
- "##Á": 475,
539
- "##Ô": 476,
540
- "##í": 477,
541
- "##L": 478,
542
  "##V": 479,
543
- "##\"": 480,
544
- "##û": 481,
545
- "##ü": 482,
546
- "##o": 483,
547
- "##ĩ": 484,
548
- "##a": 485,
549
- "##ì": 486,
550
- "##¬": 487,
551
- "##S": 488,
552
- "##Y": 489,
553
- "##*": 490,
554
- "##º": 491,
555
- "##Ŀ": 492,
556
- "##ĸ": 493,
557
- "##h": 494,
558
- "##¨": 495,
559
- "##Į": 496,
560
- "##-": 497,
561
- "##±": 498,
562
- "##6": 499,
563
- "##%": 500,
564
- "##|": 501,
565
- "##Č": 502,
566
- "##è": 503,
567
- "##Ĉ": 504,
568
- "##ô": 505,
569
  "##IJ": 506,
570
- "##ŀ": 507,
571
- "##đ": 508,
572
- "##ß": 509,
573
- "##U": 510,
574
- "##,": 511,
575
- "##Q": 512,
576
- "##Ğ": 513,
577
  "<|unk|>": 514,
578
  "##in": 515,
579
  "##�": 516,
 
318
  "Ł": 255,
319
  "ł": 256,
320
  "Ń": 257,
321
+ "##S": 258,
322
+ "##E": 259,
323
+ "##_": 260,
324
+ "##Ğ": 261,
325
+ "##Ç": 262,
326
+ "##3": 263,
327
+ "##©": 264,
328
+ "##å": 265,
329
+ "##ê": 266,
330
+ "##Ć": 267,
331
+ "##{": 268,
332
+ "##!": 269,
333
+ "##ï": 270,
334
+ "##/": 271,
335
+ "##ĭ": 272,
336
+ "##ù": 273,
337
+ "##à": 274,
338
+ "##Ĉ": 275,
339
+ "##¤": 276,
340
+ "##*": 277,
341
+ "##ĩ": 278,
342
+ "##o": 279,
343
+ "##\\": 280,
344
+ "##č": 281,
345
+ "##6": 282,
346
+ "##¢": 283,
347
+ "##;": 284,
348
+ "##¶": 285,
349
+ "##B": 286,
350
+ "##û": 287,
351
+ "##@": 288,
352
+ "##z": 289,
353
+ "##ó": 290,
354
+ "##Ĵ": 291,
355
+ "##Ă": 292,
356
+ "##v": 293,
357
+ "##³": 294,
358
+ "##Ë": 295,
359
+ "##ę": 296,
360
+ "##÷": 297,
361
+ "##Č": 298,
362
+ "##L": 299,
363
+ "##½": 300,
364
+ "##Í": 301,
365
+ "##Ĩ": 302,
366
+ "##,": 303,
367
+ "##P": 304,
368
+ "##|": 305,
369
+ "##Ċ": 306,
370
+ "##k": 307,
371
+ "##'": 308,
372
+ "##ċ": 309,
373
+ "##į": 310,
374
+ "##>": 311,
375
+ "##I": 312,
376
+ "##2": 313,
377
+ "##9": 314,
378
+ "##K": 315,
379
+ "##Ô": 316,
380
+ "##ô": 317,
381
+ "##Ě": 318,
382
+ "##ğ": 319,
383
+ "##]": 320,
384
+ "##ø": 321,
385
+ "##C": 322,
386
+ "##A": 323,
387
+ "##a": 324,
388
+ "##H": 325,
389
+ "##«": 326,
390
+ "##×": 327,
391
+ "##ı": 328,
392
+ "##e": 329,
393
+ "##j": 330,
394
+ "##Á": 331,
395
+ "##i": 332,
396
+ "##p": 333,
397
+ "##Z": 334,
398
+ "##§": 335,
399
+ "##¯": 336,
400
+ "##~": 337,
401
+ "##ġ": 338,
402
+ "##À": 339,
403
+ "##ë": 340,
404
+ "##Î": 341,
405
+ "##þ": 342,
406
+ "##ď": 343,
407
+ "##ÿ": 344,
408
+ "##t": 345,
409
+ "##î": 346,
410
+ "##Ø": 347,
411
+ "##Â": 348,
412
+ "##ė": 349,
413
+ "##ò": 350,
414
+ "##ú": 351,
415
+ "##¡": 352,
416
+ "##µ": 353,
417
+ "##(": 354,
418
+ "##â": 355,
419
+ "##F": 356,
420
+ "##ĸ": 357,
421
+ "##ģ": 358,
422
+ "##ß": 359,
423
+ "##%": 360,
424
+ "##ī": 361,
425
+ "##É": 362,
426
+ "##đ": 363,
427
+ "##¥": 364,
428
+ "##O": 365,
429
+ "##ª": 366,
430
+ "##ā": 367,
431
+ "##Æ": 368,
432
+ "##^": 369,
433
+ "##£": 370,
434
+ "##ă": 371,
435
+ "##¬": 372,
436
+ "##q": 373,
437
+ "##-": 374,
438
+ "##Ė": 375,
439
+ "##ij": 376,
440
+ "##R": 377,
441
+ "##¼": 378,
442
+ "##Ĭ": 379,
443
+ "##ö": 380,
444
+ "##d": 381,
445
+ "##Ħ": 382,
446
+ "##c": 383,
447
+ "##+": 384,
448
+ "##Ö": 385,
449
+ "##ł": 386,
450
+ "##ŀ": 387,
451
+ "##Ñ": 388,
452
+ "##ē": 389,
453
+ "##È": 390,
454
+ "##¾": 391,
455
+ "##Ù": 392,
456
+ "##ĕ": 393,
457
+ "##ç": 394,
458
+ "##Ü": 395,
459
+ "##\"": 396,
460
+ "##f": 397,
461
+ "##º": 398,
462
+ "##ě": 399,
463
+ "##n": 400,
464
+ "##¨": 401,
465
+ "##Ã": 402,
466
+ "##Û": 403,
467
+ "##D": 404,
468
+ "##ĥ": 405,
469
+ "##1": 406,
470
+ "##ã": 407,
471
+ "##&": 408,
472
+ "##0": 409,
473
+ "##7": 410,
474
+ "##u": 411,
475
+ "##y": 412,
476
+ "##°": 413,
477
+ "##»": 414,
478
+ "##Ā": 415,
479
+ "##Ķ": 416,
480
+ "##Q": 417,
481
+ "##Ń": 418,
482
+ "##Ē": 419,
483
+ "##<": 420,
484
+ "##´": 421,
485
+ "##b": 422,
486
+ "##ĉ": 423,
487
+ "##¸": 424,
488
+ "##m": 425,
489
+ "##l": 426,
490
+ "##r": 427,
491
+ "##w": 428,
492
+ "##Ä": 429,
493
+ "##x": 430,
494
+ "##Ì": 431,
495
+ "##Ŀ": 432,
496
+ "##`": 433,
497
+ "##á": 434,
498
+ "##ą": 435,
499
+ "##Ę": 436,
500
+ "##Ð": 437,
501
+ "##Ĥ": 438,
502
+ "##)": 439,
503
+ "##²": 440,
504
+ "##¹": 441,
505
+ "##G": 442,
506
+ "##ħ": 443,
507
+ "##ĝ": 444,
508
+ "##õ": 445,
509
+ "##X": 446,
510
+ "##ć": 447,
511
+ "##Ď": 448,
512
+ "##·": 449,
513
+ "##İ": 450,
514
+ "##Þ": 451,
515
+ "##ķ": 452,
516
+ "##Į": 453,
517
+ "##W": 454,
518
+ "##Y": 455,
519
+ "##Ï": 456,
520
+ "##?": 457,
521
+ "##é": 458,
522
+ "##Ľ": 459,
523
+ "##Ó": 460,
524
+ "##[": 461,
525
+ "##Ą": 462,
526
+ "##ĺ": 463,
527
+ "##Ĕ": 464,
528
+ "##8": 465,
529
+ "##¦": 466,
530
+ "##Ú": 467,
531
+ "##h": 468,
532
+ "##U": 469,
533
+ "##ð": 470,
534
+ "##ñ": 471,
535
+ "##g": 472,
536
+ "##Ê": 473,
537
+ "##Ļ": 474,
538
+ "##è": 475,
539
+ "##5": 476,
540
+ "##:": 477,
541
+ "##=": 478,
542
  "##V": 479,
543
+ "##}": 480,
544
+ "##Å": 481,
545
+ "##Đ": 482,
546
+ "##Ī": 483,
547
+ "##$": 484,
548
+ "##ļ": 485,
549
+ "##Ġ": 486,
550
+ "##Ĺ": 487,
551
+ "##ý": 488,
552
+ "##4": 489,
553
+ "##Ģ": 490,
554
+ "##J": 491,
555
+ "##Ł": 492,
556
+ "##¿": 493,
557
+ "##M": 494,
558
+ "##s": 495,
559
+ "##Ý": 496,
560
+ "##®": 497,
561
+ "##ì": 498,
562
+ "##T": 499,
563
+ "##ü": 500,
564
+ "##Õ": 501,
565
+ "###": 502,
566
+ "##.": 503,
567
+ "##ä": 504,
568
+ "##Ĝ": 505,
569
  "##IJ": 506,
570
+ "##Ò": 507,
571
+ "##ĵ": 508,
572
+ "##ľ": 509,
573
+ "##±": 510,
574
+ "##N": 511,
575
+ "##í": 512,
576
+ "##æ": 513,
577
  "<|unk|>": 514,
578
  "##in": 515,
579
  "##�": 516,
fw57M_Entropy_thresholdB_16000/vocab.json CHANGED
The diff for this file is too large to render. See raw diff