codebyzeb commited on
Commit
58beac7
·
verified ·
1 Parent(s): 57b71d2

Upload folder using huggingface_hub

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