codebyzeb commited on
Commit
cdd9e7b
·
verified ·
1 Parent(s): 0290e96

Upload folder using huggingface_hub

Browse files
fw57Mmulti_Entropy_thresholdB_32000/tokenizer.json CHANGED
@@ -58,518 +58,518 @@
58
  "vocab": {
59
  "<|padding|>": 0,
60
  "<|endoftext|>": 1,
61
- "ĠL": 2,
62
- "##L": 3,
63
- "Ġz": 4,
64
- "##z": 5,
65
- "ĠS": 6,
66
- "##S": 7,
67
- "Ġù": 8,
68
- "##ù": 9,
69
- "Ġğ": 10,
70
- "##ğ": 11,
71
- "Ġg": 12,
72
- "##g": 13,
73
- "Ġ`": 14,
74
- "##`": 15,
75
- "Ġď": 16,
76
- "##ď": 17,
77
- "Ġĥ": 18,
78
- "##ĥ": 19,
79
- "Ġ=": 20,
80
- "##=": 21,
81
- "Ġ-": 22,
82
- "##-": 23,
83
- "ĠÐ": 24,
84
- "##Ð": 25,
85
- "ĠZ": 26,
86
- "##Z": 27,
87
- "Ġ\"": 28,
88
- "##\"": 29,
89
- "Ġ§": 30,
90
- "##§": 31,
91
- "Ġa": 32,
92
- "##a": 33,
93
- "Ġl": 34,
94
- "##l": 35,
95
- {": 36,
96
- "##{": 37,
97
- "ĠÅ": 38,
98
- "##Å": 39,
99
- "ĠĀ": 40,
100
- "##Ā": 41,
101
- "Ġ#": 42,
102
- "###": 43,
103
- "ĠĖ": 44,
104
- "##Ė": 45,
105
- "Ġá": 46,
106
- "##á": 47,
107
- "Ġè": 48,
108
- "##è": 49,
109
- "Ġã": 50,
110
- "##ã": 51,
111
- "Ġĵ": 52,
112
- "##ĵ": 53,
113
- "ĠÄ": 54,
114
- "##Ä": 55,
115
- "Ġø": 56,
116
- "##ø": 57,
117
- "ĠM": 58,
118
- "##M": 59,
119
- "Ġć": 60,
120
- "##ć": 61,
121
- "Ġm": 62,
122
- "##m": 63,
123
- "Ġô": 64,
124
- "##ô": 65,
125
- "Ġ¿": 66,
126
- "##¿": 67,
127
- "Ġd": 68,
128
- "##d": 69,
129
- "Ġ«": 70,
130
- "##«": 71,
131
- "Ġì": 72,
132
- "##ì": 73,
133
- "ĠĹ": 74,
134
- "##Ĺ": 75,
135
- "Ġ£": 76,
136
- "##£": 77,
137
- "Ġò": 78,
138
- "##ò": 79,
139
- "Ġó": 80,
140
- "##ó": 81,
141
- "ĠĮ": 82,
142
- "##Į": 83,
143
- "ĠĚ": 84,
144
- "##Ě": 85,
145
- "Ġ¶": 86,
146
- "##¶": 87,
147
- "Ġæ": 88,
148
- "##æ": 89,
149
- "ĠĜ": 90,
150
- "##Ĝ": 91,
151
- "Ġ8": 92,
152
- "##8": 93,
153
- "ĠŁ": 94,
154
- "##Ł": 95,
155
- "Ġµ": 96,
156
- "##µ": 97,
157
- "Ġî": 98,
158
- "##î": 99,
159
- "ĠÆ": 100,
160
- "##Æ": 101,
161
- "ĠĎ": 102,
162
- "##Ď": 103,
163
- "Ġě": 104,
164
- "##ě": 105,
165
- "Ġs": 106,
166
- "##s": 107,
167
- "Ġ0": 108,
168
- "##0": 109,
169
- "ĠO": 110,
170
- "##O": 111,
171
- "ĠÕ": 112,
172
- "##Õ": 113,
173
- "Ġċ": 114,
174
- "##ċ": 115,
175
- "Ġ¡": 116,
176
- "##¡": 117,
177
- "Ġe": 118,
178
- "##e": 119,
179
- "ĠØ": 120,
180
- "##Ø": 121,
181
- "Ġę": 122,
182
- "##ę": 123,
183
- "Ġ4": 124,
184
- "##4": 125,
185
- "Ġ}": 126,
186
- "##}": 127,
187
- "Ġç": 128,
188
- "##ç": 129,
189
- "Ġij": 130,
190
- "##ij": 131,
191
- "Ġ¯": 132,
192
- "##¯": 133,
193
- "Ġī": 134,
194
- "##ī": 135,
195
- "Ġy": 136,
196
- "##y": 137,
197
- "ĠT": 138,
198
- "##T": 139,
199
- "Ġ[": 140,
200
- "##[": 141,
201
- "Ġ¼": 142,
202
- "##¼": 143,
203
- "Ġ½": 144,
204
- "##½": 145,
205
- "Ġĕ": 146,
206
- "##ĕ": 147,
207
- "ĠÓ": 148,
208
- "##Ó": 149,
209
- "Ġ¸": 150,
210
- "##¸": 151,
211
- "Ġĸ": 152,
212
- "##ĸ": 153,
213
- "ĠÑ": 154,
214
- "##Ñ": 155,
215
- "Ġ³": 156,
216
- "##³": 157,
217
- "ĠE": 158,
218
- "##E": 159,
219
- "Ġp": 160,
220
- "##p": 161,
221
- "ĠĊ": 162,
222
- "##Ċ": 163,
223
- "ĠĒ": 164,
224
- "##Ē": 165,
225
- "Ġ]": 166,
226
- "##]": 167,
227
- "ĠÌ": 168,
228
- "##Ì": 169,
229
- "Ġ(": 170,
230
- "##(": 171,
231
- "ĠI": 172,
232
- "##I": 173,
233
- "Ġf": 174,
234
- "##f": 175,
235
- "Ġ¾": 176,
236
- "##¾": 177,
237
- "Ġ÷": 178,
238
- "##÷": 179,
239
- "Ġö": 180,
240
- "##ö": 181,
241
- "Ġð": 182,
242
- "##ð": 183,
243
- "Ġé": 184,
244
- "##é": 185,
245
- "ĠIJ": 186,
246
- "##IJ": 187,
247
- "ĠP": 188,
248
- "##P": 189,
249
- "Ġw": 190,
250
- "##w": 191,
251
- "ĠÚ": 192,
252
- "##Ú": 193,
253
- "Ġļ": 194,
254
- "##ļ": 195,
255
- "ĠÎ": 196,
256
- "##Î": 197,
257
- "Ġ/": 198,
258
- "##/": 199,
259
- "Ġb": 200,
260
- "##b": 201,
261
- "Ġĉ": 202,
262
- "##ĉ": 203,
263
- "ĠJ": 204,
264
- "##J": 205,
265
- "ĠW": 206,
266
- "##W": 207,
267
- "Ġ:": 208,
268
- "##:": 209,
269
- "Ġ×": 210,
270
- "##×": 211,
271
- "Ġ>": 212,
272
- "##>": 213,
273
- "Ġí": 214,
274
- "##í": 215,
275
- "Ġ+": 216,
276
- "##+": 217,
277
- "ĠĠ": 218,
278
- "##Ġ": 219,
279
- "Ġ3": 220,
280
- "##3": 221,
281
- "Ġ®": 222,
282
- "##®": 223,
283
- "ĠÞ": 224,
284
- "##Þ": 225,
285
- "Ġû": 226,
286
- "##û": 227,
287
- "Ġħ": 228,
288
- "##ħ": 229,
289
- "Ġ¥": 230,
290
- "##¥": 231,
291
- "Ġk": 232,
292
- "##k": 233,
293
- "Ġï": 234,
294
- "##ï": 235,
295
- "Ġ<": 236,
296
- "##<": 237,
297
- 6": 238,
298
- "##6": 239,
299
- "Ġº": 240,
300
- "##º": 241,
301
- "ĠN": 242,
302
- "##N": 243,
303
- "Ġv": 244,
304
- "##v": 245,
305
- "Ġà": 246,
306
- "##à": 247,
307
- "ĠĬ": 248,
308
- "##Ĭ": 249,
309
- "Ġľ": 250,
310
- "##ľ": 251,
311
- "Ġ¤": 252,
312
- "##¤": 253,
313
- "Ġ|": 254,
314
- "##|": 255,
315
- "ĠU": 256,
316
- "##U": 257,
317
- "Ġþ": 258,
318
- "##þ": 259,
319
- "ĠĪ": 260,
320
- "##Ī": 261,
321
- "Ġą": 262,
322
- "##ą": 263,
323
- "ĠG": 264,
324
- "##G": 265,
325
- "ĠĞ": 266,
326
- "##Ğ": 267,
327
- "ĠX": 268,
328
- "##X": 269,
329
- "Ġ¦": 270,
330
- "##¦": 271,
331
- "ĠA": 272,
332
- "##A": 273,
333
- "Ġė": 274,
334
- "##ė": 275,
335
- "ĠĈ": 276,
336
- "##Ĉ": 277,
337
- "ĠÁ": 278,
338
- "##Á": 279,
339
- "ĠĽ": 280,
340
- "##Ľ": 281,
341
- "Ġč": 282,
342
- "##č": 283,
343
- "ĠĔ": 284,
344
- "##Ĕ": 285,
345
- _": 286,
346
- "##_": 287,
347
- "Ġ;": 288,
348
- "##;": 289,
349
- "Ġ?": 290,
350
- "##?": 291,
351
- "Ġē": 292,
352
- "##ē": 293,
353
- "ĠH": 294,
354
- "##H": 295,
355
- "Ġ5": 296,
356
- "##5": 297,
357
- "Ġx": 298,
358
- "##x": 299,
359
- "Ġ,": 300,
360
- "##,": 301,
361
- "ĠC": 302,
362
- "##C": 303,
363
- "ĠÔ": 304,
364
- "##Ô": 305,
365
- "ĠĶ": 306,
366
- "##Ķ": 307,
367
- "Ġ'": 308,
368
- "##'": 309,
369
- "ĠB": 310,
370
- "##B": 311,
371
- "ĠQ": 312,
372
- "##Q": 313,
373
- "Ġ~": 314,
374
- "##~": 315,
375
- "Ġĭ": 316,
376
- "##ĭ": 317,
377
- "ĠĂ": 318,
378
- "##Ă": 319,
379
- "Ġ9": 320,
380
- "##9": 321,
381
- "Ġj": 322,
382
- "##j": 323,
383
- "ĠÙ": 324,
384
- "##Ù": 325,
385
- "Ġ&": 326,
386
- "##&": 327,
387
- "Ġå": 328,
388
- "##å": 329,
389
- "Ġă": 330,
390
- "##ă": 331,
391
- "Ġ1": 332,
392
- "##1": 333,
393
- "ĠÜ": 334,
394
- "##Ü": 335,
395
- "Ġ\\": 336,
396
- "##\\": 337,
397
- "Ġ²": 338,
398
- "##²": 339,
399
- "Ġķ": 340,
400
- "##ķ": 341,
401
- "ĠF": 342,
402
- "##F": 343,
403
- "Ġ@": 344,
404
- "##@": 345,
405
- "ĠÉ": 346,
406
- "##É": 347,
407
- "Ġģ": 348,
408
- "##ģ": 349,
409
- "Ġġ": 350,
410
- "##ġ": 351,
411
- "Ġr": 352,
412
- "##r": 353,
413
- "Ġ©": 354,
414
- "##©": 355,
415
- "Ġõ": 356,
416
- "##õ": 357,
417
- "Ġß": 358,
418
- "##ß": 359,
419
- "Ġ¬": 360,
420
- "##¬": 361,
421
- "ĠĄ": 362,
422
- "##Ą": 363,
423
- "ĠÍ": 364,
424
- "##Í": 365,
425
- "Ġq": 366,
426
- "##q": 367,
427
- "Ġt": 368,
428
- "##t": 369,
429
- "Ġ^": 370,
430
- "##^": 371,
431
- "Ġĩ": 372,
432
- "##ĩ": 373,
433
- "Ġ%": 374,
434
- "##%": 375,
435
- "ĠĤ": 376,
436
- "##Ĥ": 377,
437
- "ĠĿ": 378,
438
- "##Ŀ": 379,
439
- "ĠÏ": 380,
440
- "##Ï": 381,
441
- "ĠÒ": 382,
442
- "##Ò": 383,
443
- "Ġü": 384,
444
- "##ü": 385,
445
- "Ġý": 386,
446
- "##ý": 387,
447
- "ĠĢ": 388,
448
- "##Ģ": 389,
449
- "ĠÖ": 390,
450
- "##Ö": 391,
451
- "Ġo": 392,
452
- "##o": 393,
453
- "ĠÊ": 394,
454
- "##Ê": 395,
455
- "ĠÛ": 396,
456
- "##Û": 397,
457
- "Ġÿ": 398,
458
- "##ÿ": 399,
459
- "Ġ!": 400,
460
- "##!": 401,
461
- "ĠÝ": 402,
462
- "##Ý": 403,
463
- "Ġñ": 404,
464
- "##ñ": 405,
465
- "ĠY": 406,
466
- "##Y": 407,
467
- "Ġİ": 408,
468
- "##İ": 409,
469
- "ĠR": 410,
470
- "##R": 411,
471
- "Ġ±": 412,
472
- "##±": 413,
473
- "ĠÂ": 414,
474
- "##Â": 415,
475
- "Ġį": 416,
476
- "##į": 417,
477
- "Ġ¢": 418,
478
- "##¢": 419,
479
- "Ġi": 420,
480
- "##i": 421,
481
- "Ġ´": 422,
482
- "##´": 423,
483
- "Ġä": 424,
484
- "##ä": 425,
485
- "Ġđ": 426,
486
- "##đ": 427,
487
- "ĠČ": 428,
488
- "##Č": 429,
489
- "Ġĺ": 430,
490
- "##ĺ": 431,
491
- "Ġı": 432,
492
- "##ı": 433,
493
- "ĠD": 434,
494
- "##D": 435,
495
- "Ġê": 436,
496
- "##ê": 437,
497
- "Ġâ": 438,
498
- "##â": 439,
499
- "ĠĦ": 440,
500
- "##Ħ": 441,
501
- "Ġ»": 442,
502
- "##»": 443,
503
- "Ġŀ": 444,
504
- "##ŀ": 445,
505
- "ĠK": 446,
506
- "##K": 447,
507
- "Ġ)": 448,
508
- "##)": 449,
509
- "ĠĻ": 450,
510
- "##Ļ": 451,
511
- "ĠÃ": 452,
512
- "##Ã": 453,
513
- "Ġú": 454,
514
- "##ú": 455,
515
- "ĠĐ": 456,
516
- "##Đ": 457,
517
- "Ġ*": 458,
518
- "##*": 459,
519
- "Ġ¨": 460,
520
- "##¨": 461,
521
- "ĠÀ": 462,
522
- "##À": 463,
523
- "Ġª": 464,
524
- "##ª": 465,
525
- "ĠĴ": 466,
526
- "##Ĵ": 467,
527
- "Ġā": 468,
528
- "##ā": 469,
529
- "Ġ.": 470,
530
- "##.": 471,
531
- "ĠĆ": 472,
532
- "##Ć": 473,
533
- "Ġł": 474,
534
- "##ł": 475,
535
- "ĠÈ": 476,
536
- "##È": 477,
537
- "ĠĘ": 478,
538
- "##Ę": 479,
539
- "Ġh": 480,
540
- "##h": 481,
541
- "ĠÇ": 482,
542
- "##Ç": 483,
543
- "ĠV": 484,
544
- "##V": 485,
545
- "ĠĨ": 486,
546
- "##Ĩ": 487,
547
- "ĠŃ": 488,
548
- "##Ń": 489,
549
- "Ġ·": 490,
550
- "##·": 491,
551
- "Ġn": 492,
552
- "##n": 493,
553
- "Ġ2": 494,
554
- "##2": 495,
555
- "Ġ$": 496,
556
- "##$": 497,
557
- "Ġ¹": 498,
558
- "##¹": 499,
559
- "Ġu": 500,
560
- "##u": 501,
561
- "Ġë": 502,
562
- "##ë": 503,
563
- "Ġĝ": 504,
564
- "##ĝ": 505,
565
- "Ġc": 506,
566
- "##c": 507,
567
- "ĠË": 508,
568
- "##Ë": 509,
569
- "Ġ°": 510,
570
- "##°": 511,
571
- "Ġ7": 512,
572
- "##7": 513,
573
  "<|unk|>": 514,
574
  "##�": 515,
575
  "Ġsa": 516,
 
58
  "vocab": {
59
  "<|padding|>": 0,
60
  "<|endoftext|>": 1,
61
+ "Ġp": 2,
62
+ "##p": 3,
63
+ "Ġ!": 4,
64
+ "##!": 5,
65
+ "ĠJ": 6,
66
+ "##J": 7,
67
+ "Ġï": 8,
68
+ "##ï": 9,
69
+ "ĠÕ": 10,
70
+ "##Õ": 11,
71
+ "Ġº": 12,
72
+ "##º": 13,
73
+ "Ġr": 14,
74
+ "##r": 15,
75
+ "Ġ7": 16,
76
+ "##7": 17,
77
+ "Ġò": 18,
78
+ "##ò": 19,
79
+ "ĠÒ": 20,
80
+ "##Ò": 21,
81
+ "ĠÂ": 22,
82
+ "##Â": 23,
83
+ "ĠĈ": 24,
84
+ "##Ĉ": 25,
85
+ "Ġ´": 26,
86
+ "##´": 27,
87
+ "Ġù": 28,
88
+ "##ù": 29,
89
+ "ĠÏ": 30,
90
+ "##Ï": 31,
91
+ "Ġ\"": 32,
92
+ "##\"": 33,
93
+ "ĠT": 34,
94
+ "##T": 35,
95
+ 9": 36,
96
+ "##9": 37,
97
+ "Ġ3": 38,
98
+ "##3": 39,
99
+ "Ġç": 40,
100
+ "##ç": 41,
101
+ "Ġ¿": 42,
102
+ "##¿": 43,
103
+ "Ġ(": 44,
104
+ "##(": 45,
105
+ "ĠĒ": 46,
106
+ "##Ē": 47,
107
+ "ĠÅ": 48,
108
+ "##Å": 49,
109
+ "ĠÊ": 50,
110
+ "##Ê": 51,
111
+ "Ġ²": 52,
112
+ "##²": 53,
113
+ "Ġ¦": 54,
114
+ "##¦": 55,
115
+ "ĠX": 56,
116
+ "##X": 57,
117
+ "Ġ£": 58,
118
+ "##£": 59,
119
+ "Ġ·": 60,
120
+ "##·": 61,
121
+ "ĠĹ": 62,
122
+ "##Ĺ": 63,
123
+ "Ġ³": 64,
124
+ "##³": 65,
125
+ "Ġ{": 66,
126
+ "##{": 67,
127
+ "Ġĕ": 68,
128
+ "##ĕ": 69,
129
+ "Ġµ": 70,
130
+ "##µ": 71,
131
+ "Ġ}": 72,
132
+ "##}": 73,
133
+ "Ġł": 74,
134
+ "##ł": 75,
135
+ "Ġċ": 76,
136
+ "##ċ": 77,
137
+ "Ġ¥": 78,
138
+ "##¥": 79,
139
+ "ĠĮ": 80,
140
+ "##Į": 81,
141
+ "Ġğ": 82,
142
+ "##ğ": 83,
143
+ "Ġ|": 84,
144
+ "##|": 85,
145
+ "Ġê": 86,
146
+ "##ê": 87,
147
+ "Ġý": 88,
148
+ "##ý": 89,
149
+ "Ġį": 90,
150
+ "##į": 91,
151
+ "Ġñ": 92,
152
+ "##ñ": 93,
153
+ "ĠS": 94,
154
+ "##S": 95,
155
+ "Ġå": 96,
156
+ "##å": 97,
157
+ "Ġû": 98,
158
+ "##û": 99,
159
+ "Ġa": 100,
160
+ "##a": 101,
161
+ "ĠÃ": 102,
162
+ "##Ã": 103,
163
+ "ĠÖ": 104,
164
+ "##Ö": 105,
165
+ "ĠÓ": 106,
166
+ "##Ó": 107,
167
+ "Ġ<": 108,
168
+ "##<": 109,
169
+ "ĠÑ": 110,
170
+ "##Ñ": 111,
171
+ "ĠA": 112,
172
+ "##A": 113,
173
+ "Ġk": 114,
174
+ "##k": 115,
175
+ "Ġà": 116,
176
+ "##à": 117,
177
+ "ĠO": 118,
178
+ "##O": 119,
179
+ "Ġ®": 120,
180
+ "##®": 121,
181
+ "Ġ-": 122,
182
+ "##-": 123,
183
+ "Ġļ": 124,
184
+ "##ļ": 125,
185
+ "Ġÿ": 126,
186
+ "##ÿ": 127,
187
+ "ĠŃ": 128,
188
+ "##Ń": 129,
189
+ "Ġe": 130,
190
+ "##e": 131,
191
+ "Ġ)": 132,
192
+ "##)": 133,
193
+ "ĠF": 134,
194
+ "##F": 135,
195
+ "Ġä": 136,
196
+ "##ä": 137,
197
+ "Ġĸ": 138,
198
+ "##ĸ": 139,
199
+ "Ġď": 140,
200
+ "##ď": 141,
201
+ "ĠĦ": 142,
202
+ "##Ħ": 143,
203
+ "Ġħ": 144,
204
+ "##ħ": 145,
205
+ "ĠČ": 146,
206
+ "##Č": 147,
207
+ "ĠE": 148,
208
+ "##E": 149,
209
+ "Ġĉ": 150,
210
+ "##ĉ": 151,
211
+ "ĠU": 152,
212
+ "##U": 153,
213
+ "Ġ¨": 154,
214
+ "##¨": 155,
215
+ "Ġĥ": 156,
216
+ "##ĥ": 157,
217
+ "Ġ0": 158,
218
+ "##0": 159,
219
+ "Ġİ": 160,
220
+ "##İ": 161,
221
+ "Ġz": 162,
222
+ "##z": 163,
223
+ "Ġë": 164,
224
+ "##ë": 165,
225
+ "ĠĴ": 166,
226
+ "##Ĵ": 167,
227
+ "Ġ×": 168,
228
+ "##×": 169,
229
+ "ĠĤ": 170,
230
+ "##Ĥ": 171,
231
+ "Ġq": 172,
232
+ "##q": 173,
233
+ "Ġė": 174,
234
+ "##ė": 175,
235
+ "Ġġ": 176,
236
+ "##ġ": 177,
237
+ "Ġķ": 178,
238
+ "##ķ": 179,
239
+ "ĠÔ": 180,
240
+ "##Ô": 181,
241
+ "Ġd": 182,
242
+ "##d": 183,
243
+ "ĠQ": 184,
244
+ "##Q": 185,
245
+ "Ġy": 186,
246
+ "##y": 187,
247
+ "Ġę": 188,
248
+ "##ę": 189,
249
+ "Ġî": 190,
250
+ "##î": 191,
251
+ "Ġá": 192,
252
+ "##á": 193,
253
+ "Ġn": 194,
254
+ "##n": 195,
255
+ "Ġþ": 196,
256
+ "##þ": 197,
257
+ "Ġv": 198,
258
+ "##v": 199,
259
+ "ĠÄ": 200,
260
+ "##Ä": 201,
261
+ "Ġ~": 202,
262
+ "##~": 203,
263
+ "ĠĜ": 204,
264
+ "##Ĝ": 205,
265
+ "ĠÆ": 206,
266
+ "##Æ": 207,
267
+ "ĠĊ": 208,
268
+ "##Ċ": 209,
269
+ "Ġđ": 210,
270
+ "##đ": 211,
271
+ "ĠĔ": 212,
272
+ "##Ĕ": 213,
273
+ "Ġ¶": 214,
274
+ "##¶": 215,
275
+ "Ġ[": 216,
276
+ "##[": 217,
277
+ "ĠN": 218,
278
+ "##N": 219,
279
+ "ĠØ": 220,
280
+ "##Ø": 221,
281
+ "ĠR": 222,
282
+ "##R": 223,
283
+ "Ġ©": 224,
284
+ "##©": 225,
285
+ "ĠÐ": 226,
286
+ "##Ð": 227,
287
+ "Ġs": 228,
288
+ "##s": 229,
289
+ "Ġī": 230,
290
+ "##ī": 231,
291
+ "Ġw": 232,
292
+ "##w": 233,
293
+ "ĠĎ": 234,
294
+ "##Ď": 235,
295
+ "Ġh": 236,
296
+ "##h": 237,
297
+ ]": 238,
298
+ "##]": 239,
299
+ "Ġé": 240,
300
+ "##é": 241,
301
+ "ĠW": 242,
302
+ "##W": 243,
303
+ "ĠÞ": 244,
304
+ "##Þ": 245,
305
+ "ĠĶ": 246,
306
+ "##Ķ": 247,
307
+ "Ġľ": 248,
308
+ "##ľ": 249,
309
+ "ĠË": 250,
310
+ "##Ë": 251,
311
+ "ĠÁ": 252,
312
+ "##Á": 253,
313
+ "Ġč": 254,
314
+ "##č": 255,
315
+ "ĠÈ": 256,
316
+ "##È": 257,
317
+ "Ġf": 258,
318
+ "##f": 259,
319
+ "Ġ8": 260,
320
+ "##8": 261,
321
+ "ĠĆ": 262,
322
+ "##Ć": 263,
323
+ "Ġ5": 264,
324
+ "##5": 265,
325
+ "Ġ_": 266,
326
+ "##_": 267,
327
+ "Ġô": 268,
328
+ "##ô": 269,
329
+ "Ġ\\": 270,
330
+ "##\\": 271,
331
+ "Ġć": 272,
332
+ "##ć": 273,
333
+ "ĠŁ": 274,
334
+ "##Ł": 275,
335
+ "Ġõ": 276,
336
+ "##õ": 277,
337
+ "ĠÎ": 278,
338
+ "##Î": 279,
339
+ "ĠÛ": 280,
340
+ "##Û": 281,
341
+ "Ġ?": 282,
342
+ "##?": 283,
343
+ "Ġ=": 284,
344
+ "##=": 285,
345
+ 4": 286,
346
+ "##4": 287,
347
+ "Ġc": 288,
348
+ "##c": 289,
349
+ "Ġ¢": 290,
350
+ "##¢": 291,
351
+ "Ġĝ": 292,
352
+ "##ĝ": 293,
353
+ "ĠĀ": 294,
354
+ "##Ā": 295,
355
+ "Ġ*": 296,
356
+ "##*": 297,
357
+ "ĠÚ": 298,
358
+ "##Ú": 299,
359
+ "Ġĭ": 300,
360
+ "##ĭ": 301,
361
+ "ĠÝ": 302,
362
+ "##Ý": 303,
363
+ "ĠB": 304,
364
+ "##B": 305,
365
+ "Ġü": 306,
366
+ "##ü": 307,
367
+ "ĠL": 308,
368
+ "##L": 309,
369
+ "Ġl": 310,
370
+ "##l": 311,
371
+ "Ġu": 312,
372
+ "##u": 313,
373
+ "Ġm": 314,
374
+ "##m": 315,
375
+ "ĠĪ": 316,
376
+ "##Ī": 317,
377
+ "ĠĠ": 318,
378
+ "##Ġ": 319,
379
+ "ĠK": 320,
380
+ "##K": 321,
381
+ "Ġŀ": 322,
382
+ "##ŀ": 323,
383
+ "Ġ¼": 324,
384
+ "##¼": 325,
385
+ "Ġj": 326,
386
+ "##j": 327,
387
+ "ĠIJ": 328,
388
+ "##IJ": 329,
389
+ "Ġĺ": 330,
390
+ "##ĺ": 331,
391
+ "Ġ±": 332,
392
+ "##±": 333,
393
+ "Ġ»": 334,
394
+ "##»": 335,
395
+ "ĠG": 336,
396
+ "##G": 337,
397
+ "Ġ,": 338,
398
+ "##,": 339,
399
+ "Ġ¡": 340,
400
+ "##¡": 341,
401
+ "ĠĨ": 342,
402
+ "##Ĩ": 343,
403
+ "Ġĵ": 344,
404
+ "##ĵ": 345,
405
+ "Ġ¹": 346,
406
+ "##¹": 347,
407
+ "ĠĄ": 348,
408
+ "##Ą": 349,
409
+ "ĠÜ": 350,
410
+ "##Ü": 351,
411
+ "Ġı": 352,
412
+ "##ı": 353,
413
+ "Ġö": 354,
414
+ "##ö": 355,
415
+ "Ġè": 356,
416
+ "##è": 357,
417
+ "Ġ^": 358,
418
+ "##^": 359,
419
+ "Ġ1": 360,
420
+ "##1": 361,
421
+ "Ġ#": 362,
422
+ "###": 363,
423
+ "Ġ>": 364,
424
+ "##>": 365,
425
+ "Ġą": 366,
426
+ "##ą": 367,
427
+ "ĠĂ": 368,
428
+ "##Ă": 369,
429
+ "ĠĢ": 370,
430
+ "##Ģ": 371,
431
+ "ĠĚ": 372,
432
+ "##Ě": 373,
433
+ "ĠĞ": 374,
434
+ "##Ğ": 375,
435
+ "ĠY": 376,
436
+ "##Y": 377,
437
+ "Ġ+": 378,
438
+ "##+": 379,
439
+ "ĠĬ": 380,
440
+ "##Ĭ": 381,
441
+ "Ġã": 382,
442
+ "##ã": 383,
443
+ "ĠI": 384,
444
+ "##I": 385,
445
+ "ĠĿ": 386,
446
+ "##Ŀ": 387,
447
+ "Ġâ": 388,
448
+ "##â": 389,
449
+ "Ġ;": 390,
450
+ "##;": 391,
451
+ "Ġ:": 392,
452
+ "##:": 393,
453
+ "Ġ«": 394,
454
+ "##«": 395,
455
+ "Ġú": 396,
456
+ "##ú": 397,
457
+ "ĠH": 398,
458
+ "##H": 399,
459
+ "Ġ@": 400,
460
+ "##@": 401,
461
+ "ĠP": 402,
462
+ "##P": 403,
463
+ "Ġ½": 404,
464
+ "##½": 405,
465
+ "ĠC": 406,
466
+ "##C": 407,
467
+ "Ġā": 408,
468
+ "##ā": 409,
469
+ "ĠZ": 410,
470
+ "##Z": 411,
471
+ "Ġ¾": 412,
472
+ "##¾": 413,
473
+ "ĠĽ": 414,
474
+ "##Ľ": 415,
475
+ "Ġó": 416,
476
+ "##ó": 417,
477
+ "Ġ`": 418,
478
+ "##`": 419,
479
+ "Ġ¯": 420,
480
+ "##¯": 421,
481
+ "Ġø": 422,
482
+ "##ø": 423,
483
+ "ĠÀ": 424,
484
+ "##À": 425,
485
+ "Ġ%": 426,
486
+ "##%": 427,
487
+ "ĠÉ": 428,
488
+ "##É": 429,
489
+ "Ġ2": 430,
490
+ "##2": 431,
491
+ "ĠM": 432,
492
+ "##M": 433,
493
+ "Ġæ": 434,
494
+ "##æ": 435,
495
+ "Ġě": 436,
496
+ "##ě": 437,
497
+ "Ġ¬": 438,
498
+ "##¬": 439,
499
+ "Ġ¸": 440,
500
+ "##¸": 441,
501
+ "ĠÙ": 442,
502
+ "##Ù": 443,
503
+ "Ġì": 444,
504
+ "##ì": 445,
505
+ "ĠĘ": 446,
506
+ "##Ę": 447,
507
+ "Ġ§": 448,
508
+ "##§": 449,
509
+ "Ġt": 450,
510
+ "##t": 451,
511
+ "Ġē": 452,
512
+ "##ē": 453,
513
+ "ĠV": 454,
514
+ "##V": 455,
515
+ "Ġ.": 456,
516
+ "##.": 457,
517
+ "Ġx": 458,
518
+ "##x": 459,
519
+ "Ġ&": 460,
520
+ "##&": 461,
521
+ "Ġĩ": 462,
522
+ "##ĩ": 463,
523
+ "Ġb": 464,
524
+ "##b": 465,
525
+ "Ġi": 466,
526
+ "##i": 467,
527
+ "Ġí": 468,
528
+ "##í": 469,
529
+ "ĠÍ": 470,
530
+ "##Í": 471,
531
+ "Ġģ": 472,
532
+ "##ģ": 473,
533
+ "Ġ¤": 474,
534
+ "##¤": 475,
535
+ "Ġij": 476,
536
+ "##ij": 477,
537
+ "ĠĐ": 478,
538
+ "##Đ": 479,
539
+ "Ġß": 480,
540
+ "##ß": 481,
541
+ "Ġg": 482,
542
+ "##g": 483,
543
+ "Ġ÷": 484,
544
+ "##÷": 485,
545
+ "Ġ6": 486,
546
+ "##6": 487,
547
+ "Ġo": 488,
548
+ "##o": 489,
549
+ "ĠĖ": 490,
550
+ "##Ė": 491,
551
+ "ĠÇ": 492,
552
+ "##Ç": 493,
553
+ "ĠD": 494,
554
+ "##D": 495,
555
+ "ĠĻ": 496,
556
+ "##Ļ": 497,
557
+ "Ġ$": 498,
558
+ "##$": 499,
559
+ "Ġª": 500,
560
+ "##ª": 501,
561
+ "Ġă": 502,
562
+ "##ă": 503,
563
+ "Ġ'": 504,
564
+ "##'": 505,
565
+ "Ġ/": 506,
566
+ "##/": 507,
567
+ "Ġð": 508,
568
+ "##ð": 509,
569
+ "ĠÌ": 510,
570
+ "##Ì": 511,
571
+ "Ġ°": 512,
572
+ "##°": 513,
573
  "<|unk|>": 514,
574
  "##�": 515,
575
  "Ġsa": 516,
fw57Mmulti_Entropy_thresholdB_32000/vocab.json CHANGED
The diff for this file is too large to render. See raw diff