codebyzeb commited on
Commit
0322999
·
verified ·
1 Parent(s): c404f26

Upload folder using huggingface_hub

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