codebyzeb commited on
Commit
c404f26
·
verified ·
1 Parent(s): 58beac7

Upload folder using huggingface_hub

Browse files
fw57M_Entropy_thresholdBX_600/tokenizer.json CHANGED
@@ -42,7 +42,7 @@
42
  "pattern": {
43
  "Regex": " +"
44
  },
45
- "content": " "
46
  }
47
  ]
48
  },
@@ -330,262 +330,262 @@
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,
 
42
  "pattern": {
43
  "Regex": " +"
44
  },
45
+ "content": "Ġ"
46
  }
47
  ]
48
  },
 
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,
fw57M_Entropy_thresholdBX_600/vocab.json CHANGED
@@ -1 +1 @@
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}
 
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}