codebyzeb commited on
Commit
39e93f3
·
verified ·
1 Parent(s): 36cd135

Upload folder using huggingface_hub

Browse files
fw57M_Entropy_thresholdB_8064/tokenizer.json CHANGED
@@ -65,703 +65,703 @@
65
  "vocab": {
66
  "<|padding|>": 0,
67
  "<|endoftext|>": 1,
68
- "ĠX": 2,
69
- "X": 3,
70
- "##X": 4,
71
- "7": 5,
72
- "##7": 6,
73
- "ĠÔ": 7,
74
- "Ô": 8,
75
- "##Ô": 9,
76
- "9": 10,
77
- "##9": 11,
78
- "ĠIJ": 12,
79
- "IJ": 13,
80
- "##IJ": 14,
81
- "Ġġ": 15,
82
- "ġ": 16,
83
- "##ġ": 17,
84
- "Ġĥ": 18,
85
- "ĥ": 19,
86
- "##ĥ": 20,
87
- "#": 21,
88
- "###": 22,
89
- "Ġİ": 23,
90
- "İ": 24,
91
- "##İ": 25,
92
- "ĠÇ": 26,
93
- "Ç": 27,
94
- "##Ç": 28,
95
- "ĠZ": 29,
96
- "Z": 30,
97
- "##Z": 31,
98
- "Ġµ": 32,
99
- "µ": 33,
100
- "##µ": 34,
101
- "ĠĽ": 35,
102
- "Ľ": 36,
103
- "##Ľ": 37,
104
- ">": 38,
105
- "##>": 39,
106
- "Ġõ": 40,
107
- "õ": 41,
108
- "##õ": 42,
109
- "ĠG": 43,
110
- "G": 44,
111
- "##G": 45,
112
- "ĠT": 46,
113
- "T": 47,
114
- "##T": 48,
115
- "ĠØ": 49,
116
- "Ø": 50,
117
- "##Ø": 51,
118
- "Ġc": 52,
119
- "c": 53,
120
- "##c": 54,
121
- "ĠL": 55,
122
- "L": 56,
123
- "##L": 57,
124
- "ĠË": 58,
125
- "Ë": 59,
126
- "##Ë": 60,
127
- "Ġé": 61,
128
- "é": 62,
129
- "##é": 63,
130
- "¨": 64,
131
- "##¨": 65,
132
- "Ġþ": 66,
133
- "þ": 67,
134
- "##þ": 68,
135
- "ĠÈ": 69,
136
- "È": 70,
137
- "##È": 71,
138
- "Ġċ": 72,
139
- "ċ": 73,
140
- "##ċ": 74,
141
- "Ġē": 75,
142
- "ē": 76,
143
- "##ē": 77,
144
- "¿": 78,
145
- "##¿": 79,
146
- "ĠÑ": 80,
147
- "Ñ": 81,
148
- "##Ñ": 82,
149
- "«": 83,
150
- "##«": 84,
151
- "Ġø": 85,
152
- "ø": 86,
153
- "##ø": 87,
154
- "ĠĢ": 88,
155
- "Ģ": 89,
156
- "##Ģ": 90,
157
- "¡": 91,
158
- "##¡": 92,
159
- "ĠE": 93,
160
- "E": 94,
161
- "##E": 95,
162
- "ĠĤ": 96,
163
- "Ĥ": 97,
164
- "##Ĥ": 98,
165
- "ĠK": 99,
166
- "K": 100,
167
- "##K": 101,
168
- "ĠĂ": 102,
169
- "Ă": 103,
170
- "##Ă": 104,
171
- "$": 105,
172
- "##$": 106,
173
- "Ġn": 107,
174
- "n": 108,
175
- "##n": 109,
176
- "°": 110,
177
- "##°": 111,
178
- "Ġá": 112,
179
- "á": 113,
180
- "##á": 114,
181
- "Ġć": 115,
182
- "ć": 116,
183
- "##ć": 117,
184
- "ĠĬ": 118,
185
- "Ĭ": 119,
186
- "##Ĭ": 120,
187
- "ĠS": 121,
188
- "S": 122,
189
- "##S": 123,
190
- "Ġđ": 124,
191
- "đ": 125,
192
- "##đ": 126,
193
- "Ġı": 127,
194
- "ı": 128,
195
- "##ı": 129,
196
- "Ġè": 130,
197
- "è": 131,
198
- "##è": 132,
199
- "ĠÆ": 133,
200
- "Æ": 134,
201
- "##Æ": 135,
202
- "Ġë": 136,
203
- "ë": 137,
204
- "##ë": 138,
205
- "'": 139,
206
- "##'": 140,
207
- "Ġú": 141,
208
- "ú": 142,
209
- "##ú": 143,
210
- "¼": 144,
211
- "##¼": 145,
212
- "ĠĚ": 146,
213
- "Ě": 147,
214
- "##Ě": 148,
215
- "Ġl": 149,
216
- "l": 150,
217
- "##l": 151,
218
- "¸": 152,
219
- "##¸": 153,
220
- "©": 154,
221
- "##©": 155,
222
- "Ġç": 156,
223
- "ç": 157,
224
- "##ç": 158,
225
- "Ġâ": 159,
226
- "â": 160,
227
- "##â": 161,
228
- "¾": 162,
229
- "##¾": 163,
230
- "Ġĭ": 164,
231
- "ĭ": 165,
232
- "##ĭ": 166,
233
- "Ġĵ": 167,
234
- "ĵ": 168,
235
- "##ĵ": 169,
236
- "ĠÓ": 170,
237
- "Ó": 171,
238
- "##Ó": 172,
239
- "Ġď": 173,
240
- "ď": 174,
241
- "##ď": 175,
242
- "ĠŃ": 176,
243
- "Ń": 177,
244
- "##Ń": 178,
245
- "ĠÀ": 179,
246
- "À": 180,
247
- "##À": 181,
248
- "Ġî": 182,
249
- "î": 183,
250
- "##î": 184,
251
- "|": 185,
252
- "##|": 186,
253
- "Ġķ": 187,
254
- "ķ": 188,
255
- "##ķ": 189,
256
- "Ġù": 190,
257
- "ù": 191,
258
- "##ù": 192,
259
- "Ġô": 193,
260
- "ô": 194,
261
- "##ô": 195,
262
- "ĠÚ": 196,
263
- "Ú": 197,
264
- "##Ú": 198,
265
- "ĠU": 199,
266
- "U": 200,
267
- "##U": 201,
268
- "ĠĪ": 202,
269
- "Ī": 203,
270
- "##Ī": 204,
271
- "Ġê": 205,
272
- "ê": 206,
273
- "##ê": 207,
274
- "½": 208,
275
- "##½": 209,
276
- "<": 210,
277
- "##<": 211,
278
- "_": 212,
279
- "##_": 213,
280
- "Ġm": 214,
281
- "m": 215,
282
- "##m": 216,
283
- "Ġà": 217,
284
- "à": 218,
285
- "##à": 219,
286
- "ĠO": 220,
287
- "O": 221,
288
- "##O": 222,
289
- "Ġė": 223,
290
- "ė": 224,
291
- "##ė": 225,
292
- "ĠY": 226,
293
- "Y": 227,
294
- "##Y": 228,
295
- "8": 229,
296
- "##8": 230,
297
- "Ġñ": 231,
298
- "ñ": 232,
299
- "##ñ": 233,
300
- "×": 234,
301
- "##×": 235,
302
- "ĠÝ": 236,
303
- "Ý": 237,
304
- "##Ý": 238,
305
- "Ġĺ": 239,
306
- "ĺ": 240,
307
- "##ĺ": 241,
308
- "¤": 242,
309
- "##¤": 243,
310
- "ĠÞ": 244,
311
- "Þ": 245,
312
- "##Þ": 246,
313
- "ĠĦ": 247,
314
- "Ħ": 248,
315
- "##Ħ": 249,
316
- "Ġr": 250,
317
- "r": 251,
318
- "##r": 252,
319
- "2": 253,
320
- "##2": 254,
321
- "ĠV": 255,
322
- "V": 256,
323
- "##V": 257,
324
- "ĠĜ": 258,
325
- "Ĝ": 259,
326
- "##Ĝ": 260,
327
- "ĠÖ": 261,
328
- "Ö": 262,
329
- "##Ö": 263,
330
- "+": 264,
331
- "##+": 265,
332
- ":": 266,
333
- "##:": 267,
334
- "Ġò": 268,
335
- "ò": 269,
336
- "##ò": 270,
337
- "5": 271,
338
- "##5": 272,
339
- "ĠP": 273,
340
- "P": 274,
341
- "##P": 275,
342
- "ĠĴ": 276,
343
- "Ĵ": 277,
344
- "##Ĵ": 278,
345
- "Ġg": 279,
346
- "g": 280,
347
- "##g": 281,
348
- "\\": 282,
349
- "##\\": 283,
350
- "ĠĔ": 284,
351
- "Ĕ": 285,
352
- "##Ĕ": 286,
353
- "Ġļ": 287,
354
- "ļ": 288,
355
- "##ļ": 289,
356
- "¦": 290,
357
- "##¦": 291,
358
- "Ġü": 292,
359
- "ü": 293,
360
- "##ü": 294,
361
- "ĠÅ": 295,
362
- "Å": 296,
363
- "##Å": 297,
364
- "ĠÊ": 298,
365
- "Ê": 299,
366
- "##Ê": 300,
367
- "²": 301,
368
- "##²": 302,
369
- "§": 303,
370
- "##§": 304,
371
- "Ġp": 305,
372
- "p": 306,
373
- "##p": 307,
374
- "Ġħ": 308,
375
- "ħ": 309,
376
- "##ħ": 310,
377
- "¹": 311,
378
- "##¹": 312,
379
- ";": 313,
380
- "##;": 314,
381
- "Ġf": 315,
382
- "f": 316,
383
- "##f": 317,
384
- "Ġó": 318,
385
- "ó": 319,
386
- "##ó": 320,
387
- "Ġß": 321,
388
- "ß": 322,
389
- "##ß": 323,
390
- "-": 324,
391
- "##-": 325,
392
- "ĠĈ": 326,
393
- "Ĉ": 327,
394
- "##Ĉ": 328,
395
- "ĠH": 329,
396
- "H": 330,
397
- "##H": 331,
398
- "\"": 332,
399
- "##\"": 333,
400
- "Ġï": 334,
401
- "ï": 335,
402
- "##ï": 336,
403
- "Ġě": 337,
404
- "ě": 338,
405
- "##ě": 339,
406
- "&": 340,
407
- "##&": 341,
408
- "Ġŀ": 342,
409
- "ŀ": 343,
410
- "##ŀ": 344,
411
- "Ġº": 345,
412
- "º": 346,
413
- "##º": 347,
414
- "1": 348,
415
- "##1": 349,
416
- "Ġx": 350,
417
- "x": 351,
418
- "##x": 352,
419
- "ĠÕ": 353,
420
- "Õ": 354,
421
- "##Õ": 355,
422
- "ĠF": 356,
423
- "F": 357,
424
- "##F": 358,
425
- "ĠÂ": 359,
426
- "Â": 360,
427
- "##Â": 361,
428
- "¬": 362,
429
- "##¬": 363,
430
- "ĠĘ": 364,
431
- "Ę": 365,
432
- "##Ę": 366,
433
- "6": 367,
434
- "##6": 368,
435
- "·": 369,
436
- "##·": 370,
437
- "Ġd": 371,
438
- "d": 372,
439
- "##d": 373,
440
- "ĠW": 374,
441
- "W": 375,
442
- "##W": 376,
443
- "@": 377,
444
- "##@": 378,
445
- "Ġģ": 379,
446
- "ģ": 380,
447
- "##ģ": 381,
448
- "?": 382,
449
- "##?": 383,
450
- "[": 384,
451
- "##[": 385,
452
- "ĠQ": 386,
453
- "Q": 387,
454
- "##Q": 388,
455
- "ĠM": 389,
456
- "M": 390,
457
- "##M": 391,
458
- "ĠÃ": 392,
459
- "Ã": 393,
460
- "##Ã": 394,
461
- "Ġÿ": 395,
462
- "ÿ": 396,
463
- "##ÿ": 397,
464
- "¢": 398,
465
- "##¢": 399,
466
- "÷": 400,
467
- "##÷": 401,
468
- "Ġij": 402,
469
- "ij": 403,
470
- "##ij": 404,
471
- "ĠĶ": 405,
472
- "Ķ": 406,
473
- "##Ķ": 407,
474
- "ĠB": 408,
475
- "B": 409,
476
- "##B": 410,
477
- "Ġì": 411,
478
- "ì": 412,
479
- "##ì": 413,
480
- "ĠN": 414,
481
- "N": 415,
482
- "##N": 416,
483
- "Ġð": 417,
484
- "ð": 418,
485
- "##ð": 419,
486
- "Ġĉ": 420,
487
- "ĉ": 421,
488
- "##ĉ": 422,
489
- "{": 423,
490
- "##{": 424,
491
- "£": 425,
492
- "##£": 426,
493
- "Ġª": 427,
494
- "ª": 428,
495
- "##ª": 429,
496
- "Ġí": 430,
497
- "í": 431,
498
- "##í": 432,
499
- ".": 433,
500
- "##.": 434,
501
- "ĠI": 435,
502
- "I": 436,
503
- "##I": 437,
504
- "´": 438,
505
- "##´": 439,
506
- "Ġû": 440,
507
- "û": 441,
508
- "##û": 442,
509
- "Ġč": 443,
510
- "č": 444,
511
- "##č": 445,
512
- "Ġĩ": 446,
513
- "ĩ": 447,
514
- "##ĩ": 448,
515
- "Ġĸ": 449,
516
- "ĸ": 450,
517
- "##ĸ": 451,
518
- "~": 452,
519
- "##~": 453,
520
- "Ġą": 454,
521
- "ą": 455,
522
- "##ą": 456,
523
- "ĠĮ": 457,
524
- "Į": 458,
525
- "##Į": 459,
526
- "ĠĀ": 460,
527
- "Ā": 461,
528
- "##Ā": 462,
529
- "]": 463,
530
- "##]": 464,
531
- "Ġo": 465,
532
- "o": 466,
533
- "##o": 467,
534
- "ĠÁ": 468,
535
- "Á": 469,
536
- "##Á": 470,
537
- "Ġľ": 471,
538
- "ľ": 472,
539
- "##ľ": 473,
540
- "(": 474,
541
- "##(": 475,
542
- "0": 476,
543
- "##0": 477,
544
- "ĠĠ": 478,
545
- "Ġ": 479,
546
- "##Ġ": 480,
547
- "ĠÉ": 481,
548
- "É": 482,
549
- "##É": 483,
550
- "Ġį": 484,
551
- "į": 485,
552
- "##į": 486,
553
- "±": 487,
554
- "##±": 488,
555
- "ĠC": 489,
556
- "C": 490,
557
- "##C": 491,
558
- "Ġă": 492,
559
- "ă": 493,
560
- "##ă": 494,
561
- "¯": 495,
562
- "##¯": 496,
563
- "ĠŁ": 497,
564
- "Ł": 498,
565
- "##Ł": 499,
566
- "ĠĒ": 500,
567
- "Ē": 501,
568
- "##Ē": 502,
569
- "*": 503,
570
- "##*": 504,
571
- "Ġā": 505,
572
- "ā": 506,
573
- "##ā": 507,
574
- "Ġy": 508,
575
- "y": 509,
576
- "##y": 510,
577
- "ĠR": 511,
578
- "R": 512,
579
- "##R": 513,
580
- "ĠĻ": 514,
581
- "Ļ": 515,
582
- "##Ļ": 516,
583
- "^": 517,
584
- "##^": 518,
585
- "ĠÎ": 519,
586
- "Î": 520,
587
- "##Î": 521,
588
- "ĠÏ": 522,
589
- "Ï": 523,
590
- "##Ï": 524,
591
- "Ġæ": 525,
592
- "æ": 526,
593
- "##æ": 527,
594
- "ĠÄ": 528,
595
- "Ä": 529,
596
- "##Ä": 530,
597
- "%": 531,
598
- "##%": 532,
599
- "ĠĎ": 533,
600
- "Ď": 534,
601
- "##Ď": 535,
602
- "ĠÙ": 536,
603
- "Ù": 537,
604
- "##Ù": 538,
605
- "ĠÐ": 539,
606
- "Ð": 540,
607
- "##Ð": 541,
608
- "ĠÛ": 542,
609
- "Û": 543,
610
- "##Û": 544,
611
- "ĠÜ": 545,
612
- "Ü": 546,
613
- "##Ü": 547,
614
- "Ġĝ": 548,
615
- "ĝ": 549,
616
- "##ĝ": 550,
617
- "ĠĞ": 551,
618
- "Ğ": 552,
619
- "##Ğ": 553,
620
- "Ġk": 554,
621
- "k": 555,
622
- "##k": 556,
623
- "Ġī": 557,
624
- "ī": 558,
625
- "##ī": 559,
626
- "=": 560,
627
- "##=": 561,
628
- "ĠĹ": 562,
629
- "Ĺ": 563,
630
- "##Ĺ": 564,
631
- "ĠĄ": 565,
632
- "Ą": 566,
633
- "##Ą": 567,
634
- "Ġa": 568,
635
- "a": 569,
636
- "##a": 570,
637
- "Ġq": 571,
638
- "q": 572,
639
- "##q": 573,
640
- "Ġt": 574,
641
- "t": 575,
642
- "##t": 576,
643
  "Ġe": 577,
644
  "e": 578,
645
  "##e": 579,
646
- "¥": 580,
647
- "##¥": 581,
648
- "Ġł": 582,
649
- "ł": 583,
650
- "##ł": 584,
651
- ",": 585,
652
- "##,": 586,
653
- "ĠĆ": 587,
654
- "Ć": 588,
655
- "##Ć": 589,
656
- "Ġä": 590,
657
- "ä": 591,
658
- "##ä": 592,
659
- "ĠĨ": 593,
660
- "Ĩ": 594,
661
- "##Ĩ": 595,
662
- "Ġö": 596,
663
- "ö": 597,
664
- "##ö": 598,
665
- "ĠĿ": 599,
666
- "Ŀ": 600,
667
- "##Ŀ": 601,
668
- "Ġh": 602,
669
- "h": 603,
670
- "##h": 604,
671
- "ĠA": 605,
672
- "A": 606,
673
- "##A": 607,
674
- "Ġb": 608,
675
- "b": 609,
676
- "##b": 610,
677
- "Ġw": 611,
678
- "w": 612,
679
- "##w": 613,
680
- "}": 614,
681
- "##}": 615,
682
- "ĠÒ": 616,
683
- "Ò": 617,
684
- "##Ò": 618,
685
- "Ġj": 619,
686
- "j": 620,
687
- "##j": 621,
688
- "/": 622,
689
- "##/": 623,
690
- "`": 624,
691
- "##`": 625,
692
- "ĠĖ": 626,
693
- "Ė": 627,
694
- "##Ė": 628,
695
- "Ġå": 629,
696
- "å": 630,
697
- "##å": 631,
698
- "ĠD": 632,
699
- "D": 633,
700
- "##D": 634,
701
- "Ġý": 635,
702
- "ý": 636,
703
- "##ý": 637,
704
- "Ġę": 638,
705
- "ę": 639,
706
- "##ę": 640,
707
- "4": 641,
708
- "##4": 642,
709
- "Ġs": 643,
710
- "s": 644,
711
- "##s": 645,
712
- "3": 646,
713
- "##3": 647,
714
- "Ġv": 648,
715
- "v": 649,
716
- "##v": 650,
717
- "": 651,
718
- "##¶": 652,
719
- "Ġã": 653,
720
- "ã": 654,
721
- "##ã": 655,
722
- "Ġi": 656,
723
- "i": 657,
724
- "##i": 658,
725
- "Ġz": 659,
726
- "z": 660,
727
- "##z": 661,
728
- "!": 662,
729
- "##!": 663,
730
- "ĠJ": 664,
731
- "J": 665,
732
- "##J": 666,
733
- "®": 667,
734
- "##®": 668,
735
- "Ġĕ": 669,
736
- "ĕ": 670,
737
- "##ĕ": 671,
738
- "ĠČ": 672,
739
- "Č": 673,
740
- "##Č": 674,
741
- "Ġğ": 675,
742
- "ğ": 676,
743
- "##ğ": 677,
744
- ")": 678,
745
- "##)": 679,
746
- "ĠÌ": 680,
747
- "Ì": 681,
748
- "##Ì": 682,
749
- "»": 683,
750
- "##»": 684,
751
- "ĠÍ": 685,
752
- "Í": 686,
753
- "##Í": 687,
754
- "ĠĊ": 688,
755
- "Ċ": 689,
756
- "##Ċ": 690,
757
- "Ġu": 691,
758
- "u": 692,
759
- "##u": 693,
760
- "³": 694,
761
- "##³": 695,
762
- "ĠĐ": 696,
763
- "Đ": 697,
764
- "##Đ": 698,
765
  "<|unk|>": 699,
766
  "##ng": 700,
767
  "##�": 701,
 
65
  "vocab": {
66
  "<|padding|>": 0,
67
  "<|endoftext|>": 1,
68
+ "Ġý": 2,
69
+ "ý": 3,
70
+ "##ý": 4,
71
+ "Ġp": 5,
72
+ "p": 6,
73
+ "##p": 7,
74
+ "Ġi": 8,
75
+ "i": 9,
76
+ "##i": 10,
77
+ "ĠZ": 11,
78
+ "Z": 12,
79
+ "##Z": 13,
80
+ "×": 14,
81
+ "##×": 15,
82
+ "Ġé": 16,
83
+ "é": 17,
84
+ "##é": 18,
85
+ "Ġh": 19,
86
+ "h": 20,
87
+ "##h": 21,
88
+ "Ġª": 22,
89
+ "ª": 23,
90
+ "##ª": 24,
91
+ "Ġz": 25,
92
+ "z": 26,
93
+ "##z": 27,
94
+ "ĠË": 28,
95
+ "Ë": 29,
96
+ "##Ë": 30,
97
+ "Ġb": 31,
98
+ "b": 32,
99
+ "##b": 33,
100
+ "Ġò": 34,
101
+ "ò": 35,
102
+ "##ò": 36,
103
+ "ĠĞ": 37,
104
+ "Ğ": 38,
105
+ "##Ğ": 39,
106
+ "ĠĹ": 40,
107
+ "Ĺ": 41,
108
+ "##Ĺ": 42,
109
+ "!": 43,
110
+ "##!": 44,
111
+ "Ġł": 45,
112
+ "ł": 46,
113
+ "##ł": 47,
114
+ "Ġg": 48,
115
+ "g": 49,
116
+ "##g": 50,
117
+ "ĠÐ": 51,
118
+ "Ð": 52,
119
+ "##Ð": 53,
120
+ "Ġþ": 54,
121
+ "þ": 55,
122
+ "##þ": 56,
123
+ "Ġģ": 57,
124
+ "ģ": 58,
125
+ "##ģ": 59,
126
+ "Ġħ": 60,
127
+ "ħ": 61,
128
+ "##ħ": 62,
129
+ "Ġį": 63,
130
+ "į": 64,
131
+ "##į": 65,
132
+ "ĠĊ": 66,
133
+ "Ċ": 67,
134
+ "##Ċ": 68,
135
+ "Ġĝ": 69,
136
+ "ĝ": 70,
137
+ "##ĝ": 71,
138
+ "ĠÛ": 72,
139
+ "Û": 73,
140
+ "##Û": 74,
141
+ "Ġq": 75,
142
+ "q": 76,
143
+ "##q": 77,
144
+ "ĠÍ": 78,
145
+ "Í": 79,
146
+ "##Í": 80,
147
+ "Ġø": 81,
148
+ "ø": 82,
149
+ "##ø": 83,
150
+ "ĠB": 84,
151
+ "B": 85,
152
+ "##B": 86,
153
+ "Ġĕ": 87,
154
+ "ĕ": 88,
155
+ "##ĕ": 89,
156
+ "ĠÞ": 90,
157
+ "Þ": 91,
158
+ "##Þ": 92,
159
+ "\"": 93,
160
+ "##\"": 94,
161
+ "ĠĢ": 95,
162
+ "Ģ": 96,
163
+ "##Ģ": 97,
164
+ "÷": 98,
165
+ "##÷": 99,
166
+ "Ġē": 100,
167
+ "ē": 101,
168
+ "##ē": 102,
169
+ "ĠÝ": 103,
170
+ "Ý": 104,
171
+ "##Ý": 105,
172
+ "Ġk": 106,
173
+ "k": 107,
174
+ "##k": 108,
175
+ "Ġó": 109,
176
+ "ó": 110,
177
+ "##ó": 111,
178
+ "Ġë": 112,
179
+ "ë": 113,
180
+ "##ë": 114,
181
+ "ĠĨ": 115,
182
+ "Ĩ": 116,
183
+ "##Ĩ": 117,
184
+ "Ġć": 118,
185
+ "ć": 119,
186
+ "##ć": 120,
187
+ "0": 121,
188
+ "##0": 122,
189
+ "=": 123,
190
+ "##=": 124,
191
+ "+": 125,
192
+ "##+": 126,
193
+ ")": 127,
194
+ "##)": 128,
195
+ "Ġà": 129,
196
+ "à": 130,
197
+ "##à": 131,
198
+ "{": 132,
199
+ "##{": 133,
200
+ "^": 134,
201
+ "##^": 135,
202
+ "ĠÑ": 136,
203
+ "Ñ": 137,
204
+ "##Ñ": 138,
205
+ "4": 139,
206
+ "##4": 140,
207
+ ",": 141,
208
+ "##,": 142,
209
+ "Ġĭ": 143,
210
+ "ĭ": 144,
211
+ "##ĭ": 145,
212
+ "Ġù": 146,
213
+ "ù": 147,
214
+ "##ù": 148,
215
+ "Ġî": 149,
216
+ "î": 150,
217
+ "##î": 151,
218
+ "8": 152,
219
+ "##8": 153,
220
+ "ĠÅ": 154,
221
+ "Å": 155,
222
+ "##Å": 156,
223
+ "ĠK": 157,
224
+ "K": 158,
225
+ "##K": 159,
226
+ "?": 160,
227
+ "##?": 161,
228
+ "Ġl": 162,
229
+ "l": 163,
230
+ "##l": 164,
231
+ "ĠÀ": 165,
232
+ "À": 166,
233
+ "##À": 167,
234
+ "ĠÔ": 168,
235
+ "Ô": 169,
236
+ "##Ô": 170,
237
+ "Ġð": 171,
238
+ "ð": 172,
239
+ "##ð": 173,
240
+ "¬": 174,
241
+ "##¬": 175,
242
+ "°": 176,
243
+ "##°": 177,
244
+ "Ġė": 178,
245
+ "ė": 179,
246
+ "##ė": 180,
247
+ "ĠX": 181,
248
+ "X": 182,
249
+ "##X": 183,
250
+ "ĠŃ": 184,
251
+ "Ń": 185,
252
+ "##Ń": 186,
253
+ "ĠĀ": 187,
254
+ "Ā": 188,
255
+ "##Ā": 189,
256
+ "ĠĻ": 190,
257
+ "Ļ": 191,
258
+ "##Ļ": 192,
259
+ "Ġĵ": 193,
260
+ "ĵ": 194,
261
+ "##ĵ": 195,
262
+ "ĠÙ": 196,
263
+ "Ù": 197,
264
+ "##Ù": 198,
265
+ "#": 199,
266
+ "###": 200,
267
+ "Ġæ": 201,
268
+ "æ": 202,
269
+ "##æ": 203,
270
+ "ĠJ": 204,
271
+ "J": 205,
272
+ "##J": 206,
273
+ "Ġġ": 207,
274
+ "ġ": 208,
275
+ "##ġ": 209,
276
+ "¸": 210,
277
+ "##¸": 211,
278
+ "ĠÁ": 212,
279
+ "Á": 213,
280
+ "##Á": 214,
281
+ "§": 215,
282
+ "##§": 216,
283
+ "Ġă": 217,
284
+ "ă": 218,
285
+ "##ă": 219,
286
+ "ĠĮ": 220,
287
+ "Į": 221,
288
+ "##Į": 222,
289
+ "ĠT": 223,
290
+ "T": 224,
291
+ "##T": 225,
292
+ "Ġv": 226,
293
+ "v": 227,
294
+ "##v": 228,
295
+ "$": 229,
296
+ "##$": 230,
297
+ "5": 231,
298
+ "##5": 232,
299
+ "Ġt": 233,
300
+ "t": 234,
301
+ "##t": 235,
302
+ "": 236,
303
+ "##¶": 237,
304
+ "ĠÏ": 238,
305
+ "Ï": 239,
306
+ "##Ï": 240,
307
+ "Ġı": 241,
308
+ "ı": 242,
309
+ "##ı": 243,
310
+ "Ġĺ": 244,
311
+ "ĺ": 245,
312
+ "##ĺ": 246,
313
+ "Ġx": 247,
314
+ "x": 248,
315
+ "##x": 249,
316
+ "<": 250,
317
+ "##<": 251,
318
+ "ĠM": 252,
319
+ "M": 253,
320
+ "##M": 254,
321
+ "ĠÓ": 255,
322
+ "Ó": 256,
323
+ "##Ó": 257,
324
+ "Ġğ": 258,
325
+ "ğ": 259,
326
+ "##ğ": 260,
327
+ "Ġĥ": 261,
328
+ "ĥ": 262,
329
+ "##ĥ": 263,
330
+ ":": 264,
331
+ "##:": 265,
332
+ "£": 266,
333
+ "##£": 267,
334
+ "ĠÚ": 268,
335
+ "Ú": 269,
336
+ "##Ú": 270,
337
+ "Ġī": 271,
338
+ "ī": 272,
339
+ "##ī": 273,
340
+ "(": 274,
341
+ "##(": 275,
342
+ "½": 276,
343
+ "##½": 277,
344
+ "ĠIJ": 278,
345
+ "IJ": 279,
346
+ "##IJ": 280,
347
+ "ĠĠ": 281,
348
+ "Ġ": 282,
349
+ "##Ġ": 283,
350
+ "ĠÃ": 284,
351
+ "Ã": 285,
352
+ "##Ã": 286,
353
+ "ĠÇ": 287,
354
+ "Ç": 288,
355
+ "##Ç": 289,
356
+ "Ġä": 290,
357
+ "ä": 291,
358
+ "##ä": 292,
359
+ "ĠĖ": 293,
360
+ "Ė": 294,
361
+ "##Ė": 295,
362
+ "9": 296,
363
+ "##9": 297,
364
+ "ĠČ": 298,
365
+ "Č": 299,
366
+ "##Č": 300,
367
+ "Ġč": 301,
368
+ "č": 302,
369
+ "##č": 303,
370
+ "Ġđ": 304,
371
+ "đ": 305,
372
+ "##đ": 306,
373
+ "Ġï": 307,
374
+ "ï": 308,
375
+ "##ï": 309,
376
+ "ĠÖ": 310,
377
+ "Ö": 311,
378
+ "##Ö": 312,
379
+ "ĠĘ": 313,
380
+ "Ę": 314,
381
+ "##Ę": 315,
382
+ "ĠF": 316,
383
+ "F": 317,
384
+ "##F": 318,
385
+ "¹": 319,
386
+ "##¹": 320,
387
+ "Ġå": 321,
388
+ "å": 322,
389
+ "##å": 323,
390
+ "ĠĜ": 324,
391
+ "Ĝ": 325,
392
+ "##Ĝ": 326,
393
+ "Ġļ": 327,
394
+ "ļ": 328,
395
+ "##ļ": 329,
396
+ "Ġç": 330,
397
+ "ç": 331,
398
+ "##ç": 332,
399
+ "Ġn": 333,
400
+ "n": 334,
401
+ "##n": 335,
402
+ "]": 336,
403
+ "##]": 337,
404
+ "6": 338,
405
+ "##6": 339,
406
+ "¤": 340,
407
+ "##¤": 341,
408
+ "Ġõ": 342,
409
+ "õ": 343,
410
+ "##õ": 344,
411
+ "ĠĔ": 345,
412
+ "Ĕ": 346,
413
+ "##Ĕ": 347,
414
+ "7": 348,
415
+ "##7": 349,
416
+ "`": 350,
417
+ "##`": 351,
418
+ "ĠĈ": 352,
419
+ "Ĉ": 353,
420
+ "##Ĉ": 354,
421
+ "Ġí": 355,
422
+ "í": 356,
423
+ "##í": 357,
424
+ "Ġě": 358,
425
+ "ě": 359,
426
+ "##ě": 360,
427
+ "Ġİ": 361,
428
+ "İ": 362,
429
+ "##İ": 363,
430
+ "ĠĽ": 364,
431
+ "Ľ": 365,
432
+ "##Ľ": 366,
433
+ "Ġj": 367,
434
+ "j": 368,
435
+ "##j": 369,
436
+ "1": 370,
437
+ "##1": 371,
438
+ ">": 372,
439
+ "##>": 373,
440
+ "-": 374,
441
+ "##-": 375,
442
+ "ĠÒ": 376,
443
+ "Ò": 377,
444
+ "##Ò": 378,
445
+ "Ġŀ": 379,
446
+ "ŀ": 380,
447
+ "##ŀ": 381,
448
+ "\\": 382,
449
+ "##\\": 383,
450
+ "ĠC": 384,
451
+ "C": 385,
452
+ "##C": 386,
453
+ ";": 387,
454
+ "##;": 388,
455
+ "Ġá": 389,
456
+ "á": 390,
457
+ "##á": 391,
458
+ "Ġy": 392,
459
+ "y": 393,
460
+ "##y": 394,
461
+ "ĠG": 395,
462
+ "G": 396,
463
+ "##G": 397,
464
+ "Ġċ": 398,
465
+ "ċ": 399,
466
+ "##ċ": 400,
467
+ "±": 401,
468
+ "##±": 402,
469
+ "³": 403,
470
+ "##³": 404,
471
+ "ĠS": 405,
472
+ "S": 406,
473
+ "##S": 407,
474
+ "Ġķ": 408,
475
+ "ķ": 409,
476
+ "##ķ": 410,
477
+ "@": 411,
478
+ "##@": 412,
479
+ "~": 413,
480
+ "##~": 414,
481
+ "¾": 415,
482
+ "##¾": 416,
483
+ "¦": 417,
484
+ "##¦": 418,
485
+ "Ġã": 419,
486
+ "ã": 420,
487
+ "##ã": 421,
488
+ "Ġú": 422,
489
+ "ú": 423,
490
+ "##ú": 424,
491
+ "Ġÿ": 425,
492
+ "ÿ": 426,
493
+ "##ÿ": 427,
494
+ "ĠĎ": 428,
495
+ "Ď": 429,
496
+ "##Ď": 430,
497
+ "_": 431,
498
+ "##_": 432,
499
+ "ĠĴ": 433,
500
+ "Ĵ": 434,
501
+ "##Ĵ": 435,
502
+ "|": 436,
503
+ "##|": 437,
504
+ "Ġľ": 438,
505
+ "ľ": 439,
506
+ "##ľ": 440,
507
+ "¯": 441,
508
+ "##¯": 442,
509
+ "Ġº": 443,
510
+ "º": 444,
511
+ "##º": 445,
512
+ "Ġâ": 446,
513
+ "â": 447,
514
+ "##â": 448,
515
+ "/": 449,
516
+ "##/": 450,
517
+ "Ġā": 451,
518
+ "ā": 452,
519
+ "##ā": 453,
520
+ "¨": 454,
521
+ "##¨": 455,
522
+ "ĠĒ": 456,
523
+ "Ē": 457,
524
+ "##Ē": 458,
525
+ "ĠU": 459,
526
+ "U": 460,
527
+ "##U": 461,
528
+ "ĠŁ": 462,
529
+ "Ł": 463,
530
+ "##Ł": 464,
531
+ "ĠI": 465,
532
+ "I": 466,
533
+ "##I": 467,
534
+ "¼": 468,
535
+ "##¼": 469,
536
+ "Ġô": 470,
537
+ "ô": 471,
538
+ "##ô": 472,
539
+ "3": 473,
540
+ "##3": 474,
541
+ "ĠÊ": 475,
542
+ "Ê": 476,
543
+ "##Ê": 477,
544
+ "ĠĪ": 478,
545
+ "Ī": 479,
546
+ "##Ī": 480,
547
+ "Ġf": 481,
548
+ "f": 482,
549
+ "##f": 483,
550
+ "ĠĬ": 484,
551
+ "Ĭ": 485,
552
+ "##Ĭ": 486,
553
+ "ĠL": 487,
554
+ "L": 488,
555
+ "##L": 489,
556
+ "Ġµ": 490,
557
+ "µ": 491,
558
+ "##µ": 492,
559
+ "ĠØ": 493,
560
+ "Ø": 494,
561
+ "##Ø": 495,
562
+ "Ġa": 496,
563
+ "a": 497,
564
+ "##a": 498,
565
+ "ĠV": 499,
566
+ "V": 500,
567
+ "##V": 501,
568
+ "ĠĿ": 502,
569
+ "Ŀ": 503,
570
+ "##Ŀ": 504,
571
+ "}": 505,
572
+ "##}": 506,
573
+ "©": 507,
574
+ "##©": 508,
575
+ "Ġü": 509,
576
+ "ü": 510,
577
+ "##ü": 511,
578
+ "¥": 512,
579
+ "##¥": 513,
580
+ "*": 514,
581
+ "##*": 515,
582
+ "ĠN": 516,
583
+ "N": 517,
584
+ "##N": 518,
585
+ "ĠD": 519,
586
+ "D": 520,
587
+ "##D": 521,
588
+ "ĠR": 522,
589
+ "R": 523,
590
+ "##R": 524,
591
+ "Ġê": 525,
592
+ "ê": 526,
593
+ "##ê": 527,
594
+ "Ġö": 528,
595
+ "ö": 529,
596
+ "##ö": 530,
597
+ "ĠĤ": 531,
598
+ "Ĥ": 532,
599
+ "##Ĥ": 533,
600
+ "Ġu": 534,
601
+ "u": 535,
602
+ "##u": 536,
603
+ "ĠW": 537,
604
+ "W": 538,
605
+ "##W": 539,
606
+ "ĠA": 540,
607
+ "A": 541,
608
+ "##A": 542,
609
+ "Ġs": 543,
610
+ "s": 544,
611
+ "##s": 545,
612
+ "·": 546,
613
+ "##·": 547,
614
+ "ĠÆ": 548,
615
+ "Æ": 549,
616
+ "##Æ": 550,
617
+ "Ġm": 551,
618
+ "m": 552,
619
+ "##m": 553,
620
+ "Ġd": 554,
621
+ "d": 555,
622
+ "##d": 556,
623
+ "ĠH": 557,
624
+ "H": 558,
625
+ "##H": 559,
626
+ "ĠÄ": 560,
627
+ "Ä": 561,
628
+ "##Ä": 562,
629
+ "«": 563,
630
+ "##«": 564,
631
+ "¢": 565,
632
+ "##¢": 566,
633
+ "ĠÌ": 567,
634
+ "Ì": 568,
635
+ "##Ì": 569,
636
+ "Ġij": 570,
637
+ "ij": 571,
638
+ "##ij": 572,
639
+ "²": 573,
640
+ "##²": 574,
641
+ "'": 575,
642
+ "##'": 576,
643
  "Ġe": 577,
644
  "e": 578,
645
  "##e": 579,
646
+ "Ġo": 580,
647
+ "o": 581,
648
+ "##o": 582,
649
+ "ĠĐ": 583,
650
+ "Đ": 584,
651
+ "##Đ": 585,
652
+ "ĠP": 586,
653
+ "P": 587,
654
+ "##P": 588,
655
+ "Ġĉ": 589,
656
+ "ĉ": 590,
657
+ "##ĉ": 591,
658
+ "ĠĆ": 592,
659
+ "Ć": 593,
660
+ "##Ć": 594,
661
+ "ĠÉ": 595,
662
+ "É": 596,
663
+ "##É": 597,
664
+ "Ġď": 598,
665
+ "ď": 599,
666
+ "##ď": 600,
667
+ "Ġĸ": 601,
668
+ "ĸ": 602,
669
+ "##ĸ": 603,
670
+ "ĠY": 604,
671
+ "Y": 605,
672
+ "##Y": 606,
673
+ "Ġè": 607,
674
+ "è": 608,
675
+ "##è": 609,
676
+ "¿": 610,
677
+ "##¿": 611,
678
+ "ĠÎ": 612,
679
+ "Î": 613,
680
+ "##Î": 614,
681
+ "Ġą": 615,
682
+ "ą": 616,
683
+ "##ą": 617,
684
+ "[": 618,
685
+ "##[": 619,
686
+ "®": 620,
687
+ "##®": 621,
688
+ "%": 622,
689
+ "##%": 623,
690
+ "ĠĶ": 624,
691
+ "Ķ": 625,
692
+ "##Ķ": 626,
693
+ "Ġc": 627,
694
+ "c": 628,
695
+ "##c": 629,
696
+ "Ġß": 630,
697
+ "ß": 631,
698
+ "##ß": 632,
699
+ "ĠĂ": 633,
700
+ "Ă": 634,
701
+ "##Ă": 635,
702
+ "ĠĄ": 636,
703
+ "Ą": 637,
704
+ "##Ą": 638,
705
+ "Ġę": 639,
706
+ "ę": 640,
707
+ "##ę": 641,
708
+ "ĠĚ": 642,
709
+ "Ě": 643,
710
+ "##Ě": 644,
711
+ "ĠÈ": 645,
712
+ "È": 646,
713
+ "##È": 647,
714
+ "ĠO": 648,
715
+ "O": 649,
716
+ "##O": 650,
717
+ "¡": 651,
718
+ "##¡": 652,
719
+ "ĠÕ": 653,
720
+ "Õ": 654,
721
+ "##Õ": 655,
722
+ "Ġñ": 656,
723
+ "ñ": 657,
724
+ "##ñ": 658,
725
+ "&": 659,
726
+ "##&": 660,
727
+ "2": 661,
728
+ "##2": 662,
729
+ "Ġì": 663,
730
+ "ì": 664,
731
+ "##ì": 665,
732
+ "ĠÂ": 666,
733
+ "Â": 667,
734
+ "##Â": 668,
735
+ ".": 669,
736
+ "##.": 670,
737
+ "Ġw": 671,
738
+ "w": 672,
739
+ "##w": 673,
740
+ "»": 674,
741
+ "##»": 675,
742
+ "´": 676,
743
+ "##´": 677,
744
+ "ĠE": 678,
745
+ "E": 679,
746
+ "##E": 680,
747
+ "Ġû": 681,
748
+ "û": 682,
749
+ "##û": 683,
750
+ "Ġr": 684,
751
+ "r": 685,
752
+ "##r": 686,
753
+ "ĠÜ": 687,
754
+ "Ü": 688,
755
+ "##Ü": 689,
756
+ "ĠĦ": 690,
757
+ "Ħ": 691,
758
+ "##Ħ": 692,
759
+ "Ġĩ": 693,
760
+ "ĩ": 694,
761
+ "##ĩ": 695,
762
+ "ĠQ": 696,
763
+ "Q": 697,
764
+ "##Q": 698,
765
  "<|unk|>": 699,
766
  "##ng": 700,
767
  "##�": 701,
fw57M_Entropy_thresholdB_8064/vocab.json CHANGED
The diff for this file is too large to render. See raw diff