codebyzeb commited on
Commit
d000429
·
verified ·
1 Parent(s): 0322999

Upload folder using huggingface_hub

Browse files
fw57M_Entropy_thresholdBX_600/tokenizer.json CHANGED
@@ -36,13 +36,6 @@
36
  "normalizers": [
37
  {
38
  "type": "NFD"
39
- },
40
- {
41
- "type": "Replace",
42
- "pattern": {
43
- "Regex": " +"
44
- },
45
- "content": "Ġ"
46
  }
47
  ]
48
  },
@@ -328,262 +321,262 @@
328
  "Ł": 255,
329
  "ł": 256,
330
  "Ń": 257,
331
- "##:": 258,
332
- "##ª": 259,
333
- "##Ù": 260,
334
- "##á": 261,
335
- "##F": 262,
336
- "##*": 263,
337
- "##8": 264,
338
- "##t": 265,
339
- "##À": 266,
340
- "##Û": 267,
341
- "##Ó": 268,
342
- "##č": 269,
343
- "##Đ": 270,
344
- "##Ē": 271,
345
- "##ñ": 272,
346
- "##K": 273,
347
- "##Ú": 274,
348
- "##3": 275,
349
- "##g": 276,
350
- "##Æ": 277,
351
- "##º": 278,
352
- "##ß": 279,
353
- "##Ä": 280,
354
- "##6": 281,
355
- "##×": 282,
356
- "##ĝ": 283,
357
  "##¡": 284,
358
- "##Ô": 285,
359
- "##ó": 286,
360
- "##D": 287,
361
- "##R": 288,
362
- "##]": 289,
363
- "##ã": 290,
364
- "##H": 291,
365
- "##ď": 292,
366
- "##Ĝ": 293,
367
- "##ì": 294,
368
- "##Ë": 295,
369
- "##V": 296,
370
- "##d": 297,
371
- "##¿": 298,
372
- "##¯": 299,
373
- "##ð": 300,
374
- "##&": 301,
375
- "##õ": 302,
376
- "##!": 303,
377
- "##ä": 304,
378
- "##¾": 305,
379
- "##Ă": 306,
380
- "##=": 307,
381
- "##Ŀ": 308,
382
- "##ć": 309,
383
- "##@": 310,
384
- "##0": 311,
385
- "##1": 312,
386
- "##·": 313,
387
- "##ļ": 314,
388
- "##m": 315,
389
- "##Ċ": 316,
390
- "##Þ": 317,
391
- "##U": 318,
392
- "##.": 319,
393
- "##Ď": 320,
394
- "##%": 321,
395
- "##ċ": 322,
396
- "##_": 323,
397
- "##ľ": 324,
398
- "##Ç": 325,
399
- "##ġ": 326,
400
- "##J": 327,
401
- "##2": 328,
402
- "##`": 329,
403
- "##ĩ": 330,
404
- "##å": 331,
405
- "##ě": 332,
406
- "##½": 333,
407
- "##E": 334,
408
- "##[": 335,
409
- "##s": 336,
410
- "##|": 337,
411
- "##§": 338,
412
- "##ÿ": 339,
413
- "##i": 340,
414
- "##I": 341,
415
- "##Ê": 342,
416
- "##/": 343,
417
- "##Õ": 344,
418
- "##Ą": 345,
419
- "##Ñ": 346,
420
- "##µ": 347,
421
- "##v": 348,
422
- "##Ĥ": 349,
423
- "##ý": 350,
424
- "##Å": 351,
425
- "##ā": 352,
426
- "##}": 353,
427
- "##Ò": 354,
428
- "##9": 355,
429
- "##IJ": 356,
430
- "##Ń": 357,
431
- "##f": 358,
432
- "##Ĉ": 359,
433
- "##û": 360,
434
- "##÷": 361,
435
- "##ø": 362,
436
- "##ĕ": 363,
437
- "##Ķ": 364,
438
- "##e": 365,
439
- "##È": 366,
440
- "##B": 367,
441
- "##>": 368,
442
- "##đ": 369,
443
- "##ë": 370,
444
- "##P": 371,
445
- "##©": 372,
446
- "##ă": 373,
447
- "##¹": 374,
448
- "##Ć": 375,
449
- "##Ī": 376,
450
- "##į": 377,
451
- "##Á": 378,
452
- "##³": 379,
453
- "##Ĺ": 380,
454
- "##Ĕ": 381,
455
- "##N": 382,
456
- "##j": 383,
457
- "##~": 384,
458
- "##¤": 385,
459
- "##b": 386,
460
- "##Ě": 387,
461
- "##ğ": 388,
462
- "##ĸ": 389,
463
- "##{": 390,
464
- "##Ì": 391,
465
- "##²": 392,
466
- "##G": 393,
467
- "##a": 394,
468
- "##u": 395,
469
- "##É": 396,
470
- "##Ï": 397,
471
- "##4": 398,
472
- "##Ü": 399,
473
- "##ĉ": 400,
474
- "##ī": 401,
475
- "##Â": 402,
476
- "##à": 403,
477
- "##ô": 404,
478
- "##í": 405,
479
- "##Ę": 406,
480
- "##Ł": 407,
481
- "##î": 408,
482
- "##ŀ": 409,
483
- "##ı": 410,
484
- "##Ã": 411,
485
- "##Į": 412,
486
- "##æ": 413,
487
- "##o": 414,
488
- "##,": 415,
489
- "##¢": 416,
490
- "##7": 417,
491
- "##<": 418,
492
- "##\"": 419,
493
- "##Q": 420,
494
- "##´": 421,
495
- "##ù": 422,
496
- "##y": 423,
497
- "##q": 424,
498
- "##x": 425,
499
- "##h": 426,
500
- "##ę": 427,
501
- "##Ħ": 428,
502
- "##C": 429,
503
- "##c": 430,
504
- "##ü": 431,
505
- "##L": 432,
506
- "##X": 433,
507
- "##Ľ": 434,
508
- "##Ĵ": 435,
509
- "##Z": 436,
510
- "##â": 437,
511
- "##$": 438,
512
- "##k": 439,
513
- "##°": 440,
514
- "##+": 441,
515
- "##ò": 442,
516
- "##'": 443,
517
- "##W": 444,
518
- "##O": 445,
519
- "##¥": 446,
520
- "##ē": 447,
521
- "##ê": 448,
522
- "##5": 449,
523
- "##ħ": 450,
524
- "##ij": 451,
525
- "##-": 452,
526
- "##þ": 453,
527
- "##n": 454,
528
- "##Ý": 455,
529
- "##^": 456,
530
- "##ĺ": 457,
531
- "##ł": 458,
532
- "##¬": 459,
533
- "##®": 460,
534
- "##Ė": 461,
535
- "##Ļ": 462,
536
- "##ģ": 463,
537
- "##ė": 464,
538
- "##w": 465,
539
- "##é": 466,
540
- "##ą": 467,
541
- "##(": 468,
542
- "##l": 469,
543
- "##»": 470,
544
- "##Ø": 471,
545
- "##ĵ": 472,
546
- "##«": 473,
547
- "##ö": 474,
548
- "##Ā": 475,
549
- "##¦": 476,
550
- "##)": 477,
551
- "###": 478,
552
- "##¶": 479,
553
- "##¸": 480,
554
- "##\\": 481,
555
- "##ç": 482,
556
- "##ú": 483,
557
- "##Ĩ": 484,
558
- "##;": 485,
559
- "##T": 486,
560
- "##A": 487,
561
- "##z": 488,
562
- "##İ": 489,
563
- "##è": 490,
564
- "##¼": 491,
565
- "##£": 492,
566
- "##S": 493,
567
- "##?": 494,
568
- "##r": 495,
569
- "##Î": 496,
570
- "##ï": 497,
571
- "##¨": 498,
572
- "##ķ": 499,
573
- "##Ð": 500,
574
- "##Ģ": 501,
575
- "##ĥ": 502,
576
- "##M": 503,
577
- "##Y": 504,
578
- "##Í": 505,
579
- "##ĭ": 506,
580
- "##Č": 507,
581
- "##Ö": 508,
582
- "##Ğ": 509,
583
- "##p": 510,
584
- "##Ġ": 511,
585
- "##Ĭ": 512,
586
- "##±": 513,
587
  "<|unk|>": 514,
588
  "##ng": 515,
589
  "##�": 516,
 
36
  "normalizers": [
37
  {
38
  "type": "NFD"
 
 
 
 
 
 
 
39
  }
40
  ]
41
  },
 
321
  "Ł": 255,
322
  "ł": 256,
323
  "Ń": 257,
324
+ "##Ċ": 258,
325
+ "##m": 259,
326
+ "##¤": 260,
327
+ "##Ă": 261,
328
+ "##!": 262,
329
+ "###": 263,
330
+ "##.": 264,
331
+ "##8": 265,
332
+ "##E": 266,
333
+ "##×": 267,
334
+ "##ì": 268,
335
+ "##7": 269,
336
+ "##I": 270,
337
+ "##Ë": 271,
338
+ "##L": 272,
339
+ "##{": 273,
340
+ "##+": 274,
341
+ "##Ú": 275,
342
+ "##ë": 276,
343
+ "##Å": 277,
344
+ "##Ç": 278,
345
+ "##q": 279,
346
+ "##î": 280,
347
+ "##IJ": 281,
348
+ "##²": 282,
349
+ "##Ĺ": 283,
350
  "##¡": 284,
351
+ "##Ĩ": 285,
352
+ "##W": 286,
353
+ "##Ï": 287,
354
+ "##Ö": 288,
355
+ "##Õ": 289,
356
+ "##â": 290,
357
+ "##ù": 291,
358
+ "##U": 292,
359
+ "##ď": 293,
360
+ "##c": 294,
361
+ "##ú": 295,
362
+ "##¥": 296,
363
+ "##2": 297,
364
+ "##X": 298,
365
+ "##Ù": 299,
366
+ "##p": 300,
367
+ "##0": 301,
368
+ "##Ć": 302,
369
+ "##y": 303,
370
+ "##ð": 304,
371
+ "##Ĵ": 305,
372
+ "##ł": 306,
373
+ "##]": 307,
374
+ "##_": 308,
375
+ "##h": 309,
376
+ "##b": 310,
377
+ "##B": 311,
378
+ "##Û": 312,
379
+ "##ó": 313,
380
+ "##ô": 314,
381
+ "##Ħ": 315,
382
+ "##ļ": 316,
383
+ "##$": 317,
384
+ "##5": 318,
385
+ "##M": 319,
386
+ "##À": 320,
387
+ "##G": 321,
388
+ "##Ě": 322,
389
+ "##÷": 323,
390
+ "##Đ": 324,
391
+ "##C": 325,
392
+ "##ç": 326,
393
+ "##º": 327,
394
+ "##ħ": 328,
395
+ "##Ļ": 329,
396
+ "##e": 330,
397
+ "##[": 331,
398
+ "##Ā": 332,
399
+ "##@": 333,
400
+ "##v": 334,
401
+ "##a": 335,
402
+ "##ĥ": 336,
403
+ "##V": 337,
404
+ "##d": 338,
405
+ "##j": 339,
406
+ "##İ": 340,
407
+ "##Ł": 341,
408
+ "##~": 342,
409
+ "##ě": 343,
410
+ "##^": 344,
411
+ "##©": 345,
412
+ "##6": 346,
413
+ "##ą": 347,
414
+ "##±": 348,
415
+ "##Ī": 349,
416
+ "##o": 350,
417
+ "##Y": 351,
418
+ "##Z": 352,
419
+ "##ŀ": 353,
420
+ "##į": 354,
421
+ "##ñ": 355,
422
+ "##ö": 356,
423
+ "##Ó": 357,
424
+ "##ø": 358,
425
+ "##Ô": 359,
426
+ "##ß": 360,
427
+ "##ģ": 361,
428
+ "##Ä": 362,
429
+ "##Ý": 363,
430
+ "##u": 364,
431
+ "##Ê": 365,
432
+ "##Ñ": 366,
433
+ "##Ò": 367,
434
+ "##T": 368,
435
+ "##¸": 369,
436
+ "##Ü": 370,
437
+ "##»": 371,
438
+ "##Ē": 372,
439
+ "##*": 373,
440
+ "##¬": 374,
441
+ "##Ď": 375,
442
+ "##ē": 376,
443
+ "##ī": 377,
444
+ "##&": 378,
445
+ "##å": 379,
446
+ "##ċ": 380,
447
+ "##r": 381,
448
+ "##Ĝ": 382,
449
+ "##«": 383,
450
+ "##i": 384,
451
+ "##Ĭ": 385,
452
+ "##\"": 386,
453
+ "##t": 387,
454
+ "##ò": 388,
455
+ "##?": 389,
456
+ "##Ð": 390,
457
+ "##ĵ": 391,
458
+ "##Ń": 392,
459
+ "##°": 393,
460
+ "##ĺ": 394,
461
+ "##w": 395,
462
+ "##ă": 396,
463
+ "##È": 397,
464
+ "##é": 398,
465
+ "##ij": 399,
466
+ "##¯": 400,
467
+ "##K": 401,
468
+ "##Ã": 402,
469
+ "##Č": 403,
470
+ "##Ġ": 404,
471
+ "##,": 405,
472
+ "##ı": 406,
473
+ "##4": 407,
474
+ "##k": 408,
475
+ "##µ": 409,
476
+ "##%": 410,
477
+ "##:": 411,
478
+ "##í": 412,
479
+ "##N": 413,
480
+ "##ĭ": 414,
481
+ "##¨": 415,
482
+ "##Ľ": 416,
483
+ "##x": 417,
484
+ "##Ø": 418,
485
+ "##É": 419,
486
+ "##z": 420,
487
+ "##ÿ": 421,
488
+ "##Ķ": 422,
489
+ "##/": 423,
490
+ "##à": 424,
491
+ "##3": 425,
492
+ "##¦": 426,
493
+ "##æ": 427,
494
+ "##Î": 428,
495
+ "##è": 429,
496
+ "##·": 430,
497
+ "##S": 431,
498
+ "##ľ": 432,
499
+ "##Þ": 433,
500
+ "##ć": 434,
501
+ "##ĉ": 435,
502
+ "##f": 436,
503
+ "##O": 437,
504
+ "##Á": 438,
505
+ "##9": 439,
506
+ "##Ę": 440,
507
+ "##s": 441,
508
+ "##ã": 442,
509
+ "##>": 443,
510
+ "##Q": 444,
511
+ "##<": 445,
512
+ "##R": 446,
513
+ "##®": 447,
514
+ "##ė": 448,
515
+ "##ĝ": 449,
516
+ "##}": 450,
517
+ "##Ė": 451,
518
+ "##Ĉ": 452,
519
+ "##|": 453,
520
+ "##ý": 454,
521
+ "##l": 455,
522
+ "##(": 456,
523
+ "##ĕ": 457,
524
+ "##¢": 458,
525
+ "##=": 459,
526
+ "##ĸ": 460,
527
+ "##'": 461,
528
+ "##ę": 462,
529
+ "##¿": 463,
530
+ "##H": 464,
531
+ "##ġ": 465,
532
+ "##Æ": 466,
533
+ "##Ą": 467,
534
+ "##ü": 468,
535
+ "##¹": 469,
536
+ "##Ģ": 470,
537
+ "##þ": 471,
538
+ "##£": 472,
539
+ "##á": 473,
540
+ "##J": 474,
541
+ "##§": 475,
542
+ "##ğ": 476,
543
+ "##Ğ": 477,
544
+ "##õ": 478,
545
+ "##ª": 479,
546
+ "##½": 480,
547
+ "##Ì": 481,
548
+ "##Í": 482,
549
+ "##ä": 483,
550
+ "##ĩ": 484,
551
+ "##-": 485,
552
+ "##;": 486,
553
+ "##û": 487,
554
+ "##´": 488,
555
+ "##¶": 489,
556
+ "##č": 490,
557
+ "##1": 491,
558
+ "##A": 492,
559
+ "##P": 493,
560
+ "##\\": 494,
561
+ "##`": 495,
562
+ "##n": 496,
563
+ "##Ĕ": 497,
564
+ "##Į": 498,
565
+ "##)": 499,
566
+ "##Ŀ": 500,
567
+ "##đ": 501,
568
+ "##¼": 502,
569
+ "##g": 503,
570
+ "##Â": 504,
571
+ "##ķ": 505,
572
+ "##³": 506,
573
+ "##ê": 507,
574
+ "##Ĥ": 508,
575
+ "##ï": 509,
576
+ "##D": 510,
577
+ "##¾": 511,
578
+ "##ā": 512,
579
+ "##F": 513,
580
  "<|unk|>": 514,
581
  "##ng": 515,
582
  "##�": 516,
fw57M_Entropy_thresholdBX_600/vocab.json CHANGED
@@ -1 +1 @@
1
- {":": 27, "\u00aa": 105, "\u00d9": 151, "\u00e1": 159, "F": 39, "*": 11, "8": 25, "t": 85, "\u00c0": 126, "\u00db": 153, "\u00d3": 145, "\u010d": 203, "\u0110": 206, "\u0112": 208, "\u00f1": 175, "K": 44, "\u00da": 152, "3": 20, "g": 72, "\u00c6": 132, "\u00ba": 120, "\u00df": 157, "\u00c4": 130, "6": 23, "\u00d7": 149, "\u011d": 219, "\u00a1": 96, "\u00d4": 146, "\u00f3": 177, "D": 37, "R": 51, "]": 62, "\u00e3": 161, "H": 41, "\u010f": 205, "\u011c": 218, "\u00ec": 170, "\u00cb": 137, "V": 55, "d": 69, "\u00bf": 125, "\u00af": 109, "\u00f0": 174, "&": 7, "\u00f5": 179, "!": 2, "\u00e4": 162, "\u00be": 124, "\u0102": 192, "=": 30, "\u013f": 253, "\u0107": 197, "@": 33, "0": 17, "1": 18, "\u00b7": 117, "\u013c": 250, "m": 78, "\u010a": 200, "\u00de": 156, "U": 54, ".": 15, "\u010e": 204, "%": 6, "\u010b": 201, "_": 64, "\u013e": 252, "\u00c7": 133, "\u0121": 223, "J": 43, "2": 19, "`": 65, "\u0129": 231, "\u00e5": 163, "\u011b": 217, "\u00bd": 123, "E": 38, "[": 60, "s": 84, "|": 93, "\u00a7": 102, "\u00ff": 189, "i": 74, "I": 42, "\u00ca": 136, "/": 16, "\u00d5": 147, "\u0104": 194, "\u00d1": 143, "\u00b5": 115, "v": 87, "\u0124": 226, "\u00fd": 187, "\u00c5": 131, "\u0101": 191, "}": 94, "\u00d2": 144, "9": 26, "\u0132": 240, "\u0143": 257, "f": 71, "\u0108": 198, "\u00fb": 185, "\u00f7": 181, "\u00f8": 182, "\u0115": 211, "\u0136": 244, "e": 70, "\u00c8": 134, "B": 35, ">": 31, "\u0111": 207, "\u00eb": 169, "P": 49, "\u00a9": 104, "\u0103": 193, "\u00b9": 119, "\u0106": 196, "\u012a": 232, "\u012f": 237, "\u00c1": 127, "\u00b3": 113, "\u0139": 247, "\u0114": 210, "N": 47, "j": 75, "~": 95, "\u00a4": 99, "b": 67, "\u011a": 216, "\u011f": 221, "\u0138": 246, "{": 92, "\u00cc": 138, "\u00b2": 112, "G": 40, "a": 66, "u": 86, "\u00c9": 135, "\u00cf": 141, "4": 21, "\u00dc": 154, "\u0109": 199, "\u012b": 233, "\u00c2": 128, "\u00e0": 158, "\u00f4": 178, "\u00ed": 171, "\u0118": 214, "\u0141": 255, "\u00ee": 172, "\u0140": 254, "\u0131": 239, "\u00c3": 129, "\u012e": 236, "\u00e6": 164, "o": 80, ",": 13, "\u00a2": 97, "7": 24, "<": 29, "\"": 3, "Q": 50, "\u00b4": 114, "\u00f9": 183, "y": 90, "q": 82, "x": 89, "h": 73, "\u0119": 215, "\u0126": 228, "C": 36, "c": 68, "\u00fc": 186, "L": 45, "X": 57, "\u013d": 251, "\u0134": 242, "Z": 59, "\u00e2": 160, "$": 5, "k": 76, "\u00b0": 110, "+": 12, "\u00f2": 176, "'": 8, "W": 56, "O": 48, "\u00a5": 100, "\u0113": 209, "\u00ea": 168, "5": 22, "\u0127": 229, "\u0133": 241, "-": 14, "\u00fe": 188, "n": 79, "\u00dd": 155, "^": 63, "\u013a": 248, "\u0142": 256, "\u00ac": 107, "\u00ae": 108, "\u0116": 212, "\u013b": 249, "\u0123": 225, "\u0117": 213, "w": 88, "\u00e9": 167, "\u0105": 195, "(": 9, "l": 77, "\u00bb": 121, "\u00d8": 150, "\u0135": 243, "\u00ab": 106, "\u00f6": 180, "\u0100": 190, "\u00a6": 101, ")": 10, "#": 4, "\u00b6": 116, "\u00b8": 118, "\\": 61, "\u00e7": 165, "\u00fa": 184, "\u0128": 230, "<|padding|>": 0, ";": 28, "T": 53, "A": 34, "z": 91, "\u0130": 238, "\u00e8": 166, "\u00bc": 122, "\u00a3": 98, "<|endoftext|>": 1, "S": 52, "?": 32, "r": 83, "\u00ce": 140, "\u00ef": 173, "\u00a8": 103, "\u0137": 245, "\u00d0": 142, "\u0122": 224, "\u0125": 227, "M": 46, "Y": 58, "\u00cd": 139, "\u012d": 235, "\u010c": 202, "\u00d6": 148, "\u011e": 220, "p": 81, "\u0120": 222, "\u012c": 234, "\u00b1": 111, "##:": 258, "##\u00aa": 259, "##\u00d9": 260, "##\u00e1": 261, "##F": 262, "##*": 263, "##8": 264, "##t": 265, "##\u00c0": 266, "##\u00db": 267, "##\u00d3": 268, "##\u010d": 269, "##\u0110": 270, "##\u0112": 271, "##\u00f1": 272, "##K": 273, "##\u00da": 274, "##3": 275, "##g": 276, "##\u00c6": 277, "##\u00ba": 278, "##\u00df": 279, "##\u00c4": 280, "##6": 281, "##\u00d7": 282, "##\u011d": 283, "##\u00a1": 284, "##\u00d4": 285, "##\u00f3": 286, "##D": 287, "##R": 288, "##]": 289, "##\u00e3": 290, "##H": 291, "##\u010f": 292, "##\u011c": 293, "##\u00ec": 294, "##\u00cb": 295, "##V": 296, "##d": 297, "##\u00bf": 298, "##\u00af": 299, "##\u00f0": 300, "##&": 301, "##\u00f5": 302, "##!": 303, "##\u00e4": 304, "##\u00be": 305, "##\u0102": 306, "##=": 307, "##\u013f": 308, "##\u0107": 309, "##@": 310, "##0": 311, "##1": 312, "##\u00b7": 313, "##\u013c": 314, "##m": 315, "##\u010a": 316, "##\u00de": 317, "##U": 318, "##.": 319, "##\u010e": 320, "##%": 321, "##\u010b": 322, "##_": 323, "##\u013e": 324, "##\u00c7": 325, "##\u0121": 326, "##J": 327, "##2": 328, "##`": 329, "##\u0129": 330, "##\u00e5": 331, "##\u011b": 332, "##\u00bd": 333, "##E": 334, "##[": 335, "##s": 336, "##|": 337, "##\u00a7": 338, "##\u00ff": 339, "##i": 340, "##I": 341, "##\u00ca": 342, "##/": 343, "##\u00d5": 344, "##\u0104": 345, "##\u00d1": 346, "##\u00b5": 347, "##v": 348, "##\u0124": 349, "##\u00fd": 350, "##\u00c5": 351, "##\u0101": 352, "##}": 353, "##\u00d2": 354, "##9": 355, "##\u0132": 356, "##\u0143": 357, "##f": 358, "##\u0108": 359, "##\u00fb": 360, "##\u00f7": 361, "##\u00f8": 362, "##\u0115": 363, "##\u0136": 364, "##e": 365, "##\u00c8": 366, "##B": 367, "##>": 368, "##\u0111": 369, "##\u00eb": 370, "##P": 371, "##\u00a9": 372, "##\u0103": 373, "##\u00b9": 374, "##\u0106": 375, "##\u012a": 376, "##\u012f": 377, "##\u00c1": 378, "##\u00b3": 379, "##\u0139": 380, "##\u0114": 381, "##N": 382, "##j": 383, "##~": 384, "##\u00a4": 385, "##b": 386, "##\u011a": 387, "##\u011f": 388, "##\u0138": 389, "##{": 390, "##\u00cc": 391, "##\u00b2": 392, "##G": 393, "##a": 394, "##u": 395, "##\u00c9": 396, "##\u00cf": 397, "##4": 398, "##\u00dc": 399, "##\u0109": 400, "##\u012b": 401, "##\u00c2": 402, "##\u00e0": 403, "##\u00f4": 404, "##\u00ed": 405, "##\u0118": 406, "##\u0141": 407, "##\u00ee": 408, "##\u0140": 409, "##\u0131": 410, "##\u00c3": 411, "##\u012e": 412, "##\u00e6": 413, "##o": 414, "##,": 415, "##\u00a2": 416, "##7": 417, "##<": 418, "##\"": 419, "##Q": 420, "##\u00b4": 421, "##\u00f9": 422, "##y": 423, "##q": 424, "##x": 425, "##h": 426, "##\u0119": 427, "##\u0126": 428, "##C": 429, "##c": 430, "##\u00fc": 431, "##L": 432, "##X": 433, "##\u013d": 434, "##\u0134": 435, "##Z": 436, "##\u00e2": 437, "##$": 438, "##k": 439, "##\u00b0": 440, "##+": 441, "##\u00f2": 442, "##'": 443, "##W": 444, "##O": 445, "##\u00a5": 446, "##\u0113": 447, "##\u00ea": 448, "##5": 449, "##\u0127": 450, "##\u0133": 451, "##-": 452, "##\u00fe": 453, "##n": 454, "##\u00dd": 455, "##^": 456, "##\u013a": 457, "##\u0142": 458, "##\u00ac": 459, "##\u00ae": 460, "##\u0116": 461, "##\u013b": 462, "##\u0123": 463, "##\u0117": 464, "##w": 465, "##\u00e9": 466, "##\u0105": 467, "##(": 468, "##l": 469, "##\u00bb": 470, "##\u00d8": 471, "##\u0135": 472, "##\u00ab": 473, "##\u00f6": 474, "##\u0100": 475, "##\u00a6": 476, "##)": 477, "###": 478, "##\u00b6": 479, "##\u00b8": 480, "##\\": 481, "##\u00e7": 482, "##\u00fa": 483, "##\u0128": 484, "##;": 485, "##T": 486, "##A": 487, "##z": 488, "##\u0130": 489, "##\u00e8": 490, "##\u00bc": 491, "##\u00a3": 492, "##S": 493, "##?": 494, "##r": 495, "##\u00ce": 496, "##\u00ef": 497, "##\u00a8": 498, "##\u0137": 499, "##\u00d0": 500, "##\u0122": 501, "##\u0125": 502, "##M": 503, "##Y": 504, "##\u00cd": 505, "##\u012d": 506, "##\u010c": 507, "##\u00d6": 508, "##\u011e": 509, "##p": 510, "##\u0120": 511, "##\u012c": 512, "##\u00b1": 513, "<|unk|>": 514, "##ng": 515, "##\ufffd": 516, "##er": 517, "##nt": 518, "##en": 519, "##on": 520, "##le": 521, "##nd": 522, "##her": 523, "##ent": 524, "##ss": 525, "##gh": 526, "##se": 527, "##em": 528, "##ur": 529, "##he": 530, "##in": 531, "##es": 532, "##th": 533, "##ct": 534, "##al": 535, "##us": 536, "##ar": 537, "##ge": 538, "##at": 539, "##io": 540, "##ve": 541, "##ld": 542, "##ce": 543, "##ion": 544, "##or": 545, "##ple": 546, "##ch": 547, "##te": 548, "##ll": 549, "##me": 550, "##ul": 551, "##re": 552, "##og": 553, "##ti": 554, "##an": 555, "##ra": 556, "##lt": 557, "##rd": 558, "##el": 559, "##ht": 560, "##st": 561, "##ag": 562, "##ut": 563, "##pl": 564, "##ue": 565, "##ing": 566, "##de": 567, "##ow": 568, "##rg": 569, "##ect": 570, "##is": 571, "##et": 572, "##tr": 573, "##ay": 574, "##ma": 575, "##it": 576, "##il": 577, "##ri": 578, "##dy": 579, "##use": 580, "##bl": 581, "##ly": 582, "##and": 583, "##li": 584, "##ne": 585, "##ic": 586, "##tem": 587, "##ed": 588, "##ess": 589, "##as": 590, "##ou": 591, "##ec": 592, "##om": 593, "##uc": 594, "##ke": 595, "##ia": 596, "##ud": 597, "##sh": 598, "##na": 599}
 
1
+ {"\u010a": 200, "m": 78, "\u00a4": 99, "\u0102": 192, "!": 2, "#": 4, ".": 15, "8": 25, "E": 38, "\u00d7": 149, "\u00ec": 170, "7": 24, "I": 42, "\u00cb": 137, "L": 45, "{": 92, "+": 12, "\u00da": 152, "<|endoftext|>": 1, "\u00eb": 169, "\u00c5": 131, "\u00c7": 133, "q": 82, "\u00ee": 172, "\u0132": 240, "\u00b2": 112, "\u0139": 247, "\u00a1": 96, "\u0128": 230, "W": 56, "\u00cf": 141, "\u00d6": 148, "\u00d5": 147, "\u00e2": 160, "\u00f9": 183, "U": 54, "\u010f": 205, "c": 68, "\u00fa": 184, "\u00a5": 100, "2": 19, "X": 57, "\u00d9": 151, "p": 81, "0": 17, "\u0106": 196, "y": 90, "\u00f0": 174, "\u0134": 242, "\u0142": 256, "]": 62, "_": 64, "h": 73, "b": 67, "B": 35, "\u00db": 153, "\u00f3": 177, "\u00f4": 178, "\u0126": 228, "\u013c": 250, "$": 5, "5": 22, "M": 46, "\u00c0": 126, "<|padding|>": 0, "G": 40, "\u011a": 216, "\u00f7": 181, "\u0110": 206, "C": 36, "\u00e7": 165, "\u00ba": 120, "\u0127": 229, "\u013b": 249, "e": 70, "[": 60, "\u0100": 190, "@": 33, "v": 87, "a": 66, "\u0125": 227, "V": 55, "d": 69, "j": 75, "\u0130": 238, "\u0141": 255, "~": 95, "\u011b": 217, "^": 63, "\u00a9": 104, "6": 23, "\u0105": 195, "\u00b1": 111, "\u012a": 232, "o": 80, "Y": 58, "Z": 59, "\u0140": 254, "\u012f": 237, "\u00f1": 175, "\u00f6": 180, "\u00d3": 145, "\u00f8": 182, "\u00d4": 146, "\u00df": 157, "\u0123": 225, "\u00c4": 130, "\u00dd": 155, "u": 86, "\u00ca": 136, "\u00d1": 143, "\u00d2": 144, "T": 53, "\u00b8": 118, "\u00dc": 154, "\u00bb": 121, "\u0112": 208, "*": 11, "\u00ac": 107, "\u010e": 204, "\u0113": 209, "\u012b": 233, "&": 7, "\u00e5": 163, "\u010b": 201, "r": 83, "\u011c": 218, "\u00ab": 106, "i": 74, "\u012c": 234, "\"": 3, "t": 85, "\u00f2": 176, "?": 32, "\u00d0": 142, "\u0135": 243, "\u0143": 257, "\u00b0": 110, "\u013a": 248, "w": 88, "\u0103": 193, "\u00c8": 134, "\u00e9": 167, "\u0133": 241, "\u00af": 109, "K": 44, "\u00c3": 129, "\u010c": 202, "\u0120": 222, ",": 13, "\u0131": 239, "4": 21, "k": 76, "\u00b5": 115, "%": 6, ":": 27, "\u00ed": 171, "N": 47, "\u012d": 235, "\u00a8": 103, "\u013d": 251, "x": 89, "\u00d8": 150, "\u00c9": 135, "z": 91, "\u00ff": 189, "\u0136": 244, "/": 16, "\u00e0": 158, "3": 20, "\u00a6": 101, "\u00e6": 164, "\u00ce": 140, "\u00e8": 166, "\u00b7": 117, "S": 52, "\u013e": 252, "\u00de": 156, "\u0107": 197, "\u0109": 199, "f": 71, "O": 48, "\u00c1": 127, "9": 26, "\u0118": 214, "s": 84, "\u00e3": 161, ">": 31, "Q": 50, "<": 29, "R": 51, "\u00ae": 108, "\u0117": 213, "\u011d": 219, "}": 94, "\u0116": 212, "\u0108": 198, "|": 93, "\u00fd": 187, "l": 77, "(": 9, "\u0115": 211, "\u00a2": 97, "=": 30, "\u0138": 246, "'": 8, "\u0119": 215, "\u00bf": 125, "H": 41, "\u0121": 223, "\u00c6": 132, "\u0104": 194, "\u00fc": 186, "\u00b9": 119, "\u0122": 224, "\u00fe": 188, "\u00a3": 98, "\u00e1": 159, "J": 43, "\u00a7": 102, "\u011f": 221, "\u011e": 220, "\u00f5": 179, "\u00aa": 105, "\u00bd": 123, "\u00cc": 138, "\u00cd": 139, "\u00e4": 162, "\u0129": 231, "-": 14, ";": 28, "\u00fb": 185, "\u00b4": 114, "\u00b6": 116, "\u010d": 203, "1": 18, "A": 34, "P": 49, "\\": 61, "`": 65, "n": 79, "\u0114": 210, "\u012e": 236, ")": 10, "\u013f": 253, "\u0111": 207, "\u00bc": 122, "g": 72, "\u00c2": 128, "\u0137": 245, "\u00b3": 113, "\u00ea": 168, "\u0124": 226, "\u00ef": 173, "D": 37, "\u00be": 124, "\u0101": 191, "F": 39, "##\u010a": 258, "##m": 259, "##\u00a4": 260, "##\u0102": 261, "##!": 262, "###": 263, "##.": 264, "##8": 265, "##E": 266, "##\u00d7": 267, "##\u00ec": 268, "##7": 269, "##I": 270, "##\u00cb": 271, "##L": 272, "##{": 273, "##+": 274, "##\u00da": 275, "##\u00eb": 276, "##\u00c5": 277, "##\u00c7": 278, "##q": 279, "##\u00ee": 280, "##\u0132": 281, "##\u00b2": 282, "##\u0139": 283, "##\u00a1": 284, "##\u0128": 285, "##W": 286, "##\u00cf": 287, "##\u00d6": 288, "##\u00d5": 289, "##\u00e2": 290, "##\u00f9": 291, "##U": 292, "##\u010f": 293, "##c": 294, "##\u00fa": 295, "##\u00a5": 296, "##2": 297, "##X": 298, "##\u00d9": 299, "##p": 300, "##0": 301, "##\u0106": 302, "##y": 303, "##\u00f0": 304, "##\u0134": 305, "##\u0142": 306, "##]": 307, "##_": 308, "##h": 309, "##b": 310, "##B": 311, "##\u00db": 312, "##\u00f3": 313, "##\u00f4": 314, "##\u0126": 315, "##\u013c": 316, "##$": 317, "##5": 318, "##M": 319, "##\u00c0": 320, "##G": 321, "##\u011a": 322, "##\u00f7": 323, "##\u0110": 324, "##C": 325, "##\u00e7": 326, "##\u00ba": 327, "##\u0127": 328, "##\u013b": 329, "##e": 330, "##[": 331, "##\u0100": 332, "##@": 333, "##v": 334, "##a": 335, "##\u0125": 336, "##V": 337, "##d": 338, "##j": 339, "##\u0130": 340, "##\u0141": 341, "##~": 342, "##\u011b": 343, "##^": 344, "##\u00a9": 345, "##6": 346, "##\u0105": 347, "##\u00b1": 348, "##\u012a": 349, "##o": 350, "##Y": 351, "##Z": 352, "##\u0140": 353, "##\u012f": 354, "##\u00f1": 355, "##\u00f6": 356, "##\u00d3": 357, "##\u00f8": 358, "##\u00d4": 359, "##\u00df": 360, "##\u0123": 361, "##\u00c4": 362, "##\u00dd": 363, "##u": 364, "##\u00ca": 365, "##\u00d1": 366, "##\u00d2": 367, "##T": 368, "##\u00b8": 369, "##\u00dc": 370, "##\u00bb": 371, "##\u0112": 372, "##*": 373, "##\u00ac": 374, "##\u010e": 375, "##\u0113": 376, "##\u012b": 377, "##&": 378, "##\u00e5": 379, "##\u010b": 380, "##r": 381, "##\u011c": 382, "##\u00ab": 383, "##i": 384, "##\u012c": 385, "##\"": 386, "##t": 387, "##\u00f2": 388, "##?": 389, "##\u00d0": 390, "##\u0135": 391, "##\u0143": 392, "##\u00b0": 393, "##\u013a": 394, "##w": 395, "##\u0103": 396, "##\u00c8": 397, "##\u00e9": 398, "##\u0133": 399, "##\u00af": 400, "##K": 401, "##\u00c3": 402, "##\u010c": 403, "##\u0120": 404, "##,": 405, "##\u0131": 406, "##4": 407, "##k": 408, "##\u00b5": 409, "##%": 410, "##:": 411, "##\u00ed": 412, "##N": 413, "##\u012d": 414, "##\u00a8": 415, "##\u013d": 416, "##x": 417, "##\u00d8": 418, "##\u00c9": 419, "##z": 420, "##\u00ff": 421, "##\u0136": 422, "##/": 423, "##\u00e0": 424, "##3": 425, "##\u00a6": 426, "##\u00e6": 427, "##\u00ce": 428, "##\u00e8": 429, "##\u00b7": 430, "##S": 431, "##\u013e": 432, "##\u00de": 433, "##\u0107": 434, "##\u0109": 435, "##f": 436, "##O": 437, "##\u00c1": 438, "##9": 439, "##\u0118": 440, "##s": 441, "##\u00e3": 442, "##>": 443, "##Q": 444, "##<": 445, "##R": 446, "##\u00ae": 447, "##\u0117": 448, "##\u011d": 449, "##}": 450, "##\u0116": 451, "##\u0108": 452, "##|": 453, "##\u00fd": 454, "##l": 455, "##(": 456, "##\u0115": 457, "##\u00a2": 458, "##=": 459, "##\u0138": 460, "##'": 461, "##\u0119": 462, "##\u00bf": 463, "##H": 464, "##\u0121": 465, "##\u00c6": 466, "##\u0104": 467, "##\u00fc": 468, "##\u00b9": 469, "##\u0122": 470, "##\u00fe": 471, "##\u00a3": 472, "##\u00e1": 473, "##J": 474, "##\u00a7": 475, "##\u011f": 476, "##\u011e": 477, "##\u00f5": 478, "##\u00aa": 479, "##\u00bd": 480, "##\u00cc": 481, "##\u00cd": 482, "##\u00e4": 483, "##\u0129": 484, "##-": 485, "##;": 486, "##\u00fb": 487, "##\u00b4": 488, "##\u00b6": 489, "##\u010d": 490, "##1": 491, "##A": 492, "##P": 493, "##\\": 494, "##`": 495, "##n": 496, "##\u0114": 497, "##\u012e": 498, "##)": 499, "##\u013f": 500, "##\u0111": 501, "##\u00bc": 502, "##g": 503, "##\u00c2": 504, "##\u0137": 505, "##\u00b3": 506, "##\u00ea": 507, "##\u0124": 508, "##\u00ef": 509, "##D": 510, "##\u00be": 511, "##\u0101": 512, "##F": 513, "<|unk|>": 514, "##ng": 515, "##\ufffd": 516, "##er": 517, "##nt": 518, "##en": 519, "##on": 520, "##le": 521, "##nd": 522, "##her": 523, "##ent": 524, "##ss": 525, "##gh": 526, "##se": 527, "##em": 528, "##ur": 529, "##he": 530, "##in": 531, "##es": 532, "##th": 533, "##ct": 534, "##al": 535, "##us": 536, "##ar": 537, "##ge": 538, "##at": 539, "##io": 540, "##ve": 541, "##ld": 542, "##ce": 543, "##ion": 544, "##or": 545, "##ple": 546, "##ch": 547, "##te": 548, "##ll": 549, "##me": 550, "##ul": 551, "##re": 552, "##og": 553, "##ti": 554, "##an": 555, "##ra": 556, "##lt": 557, "##rd": 558, "##el": 559, "##ht": 560, "##st": 561, "##ag": 562, "##ut": 563, "##pl": 564, "##ue": 565, "##ing": 566, "##de": 567, "##ow": 568, "##rg": 569, "##ect": 570, "##is": 571, "##et": 572, "##tr": 573, "##ay": 574, "##ma": 575, "##it": 576, "##il": 577, "##ri": 578, "##dy": 579, "##use": 580, "##bl": 581, "##ly": 582, "##and": 583, "##li": 584, "##ne": 585, "##ic": 586, "##tem": 587, "##ed": 588, "##ess": 589, "##as": 590, "##ou": 591, "##ec": 592, "##om": 593, "##uc": 594, "##ke": 595, "##ia": 596, "##ud": 597, "##sh": 598, "##na": 599}