codebyzeb commited on
Commit
4637696
·
verified ·
1 Parent(s): aa577b2

Upload folder using huggingface_hub

Browse files
fw57Mmulti_Entropy_thresholdB_64000/tokenizer.json CHANGED
@@ -65,518 +65,518 @@
65
  "vocab": {
66
  "<|padding|>": 0,
67
  "<|endoftext|>": 1,
68
- "Ġ2": 2,
69
- "##2": 3,
70
- "Ġb": 4,
71
- "##b": 5,
72
- "Ġ:": 6,
73
- "##:": 7,
74
- "ĠĻ": 8,
75
- "##Ļ": 9,
76
- "ĠÎ": 10,
77
- "##Î": 11,
78
- "ĠĘ": 12,
79
- "##Ę": 13,
80
- "Ġµ": 14,
81
- "##µ": 15,
82
- "ĠĢ": 16,
83
- "##Ģ": 17,
84
- "Ġæ": 18,
85
- "##æ": 19,
86
- "ĠË": 20,
87
- "##Ë": 21,
88
- "Ġ0": 22,
89
- "##0": 23,
90
- "Ġo": 24,
91
- "##o": 25,
92
- "ĠÚ": 26,
93
- "##Ú": 27,
94
- "ĠT": 28,
95
- "##T": 29,
96
- "Ġ&": 30,
97
- "##&": 31,
98
- "Ġ½": 32,
99
- "##½": 33,
100
- "Ġą": 34,
101
- "##ą": 35,
102
- "Ġ®": 36,
103
- "##®": 37,
104
- "Ġĉ": 38,
105
- "##ĉ": 39,
106
- "ĠY": 40,
107
- "##Y": 41,
108
- "Ġs": 42,
109
- "##s": 43,
110
- "ĠIJ": 44,
111
- "##IJ": 45,
112
- "Ġl": 46,
113
- "##l": 47,
114
- "ĠÈ": 48,
115
- "##È": 49,
116
- "Ġn": 50,
117
- "##n": 51,
118
- "Ġy": 52,
119
- "##y": 53,
120
- "Ġò": 54,
121
- "##ò": 55,
122
- "Ġå": 56,
123
- "##å": 57,
124
- "ĠĄ": 58,
125
- "##Ą": 59,
126
- "Ġđ": 60,
127
- "##đ": 61,
128
- "Ġă": 62,
129
- "##ă": 63,
130
- "Ġý": 64,
131
- "##ý": 65,
132
- "Ġ\"": 66,
133
- "##\"": 67,
134
- "Ġî": 68,
135
- "##î": 69,
136
- "ĠĞ": 70,
137
- "##Ğ": 71,
138
- "Ġ!": 72,
139
- "##!": 73,
140
- "ĠĎ": 74,
141
- "##Ď": 75,
142
- "Ġà": 76,
143
- "##à": 77,
144
- "Ġá": 78,
145
- "##á": 79,
146
- "ĠÜ": 80,
147
- "##Ü": 81,
148
- "Ġ<": 82,
149
- "##<": 83,
150
- "ĠĴ": 84,
151
- "##Ĵ": 85,
152
- "ĠZ": 86,
153
- "##Z": 87,
154
- "Ġį": 88,
155
- "##į": 89,
156
- "Ġć": 90,
157
- "##ć": 91,
158
- "Ġº": 92,
159
- "##º": 93,
160
- "Ġ\\": 94,
161
- "##\\": 95,
162
- "Ġ¦": 96,
163
- "##¦": 97,
164
- "ĠJ": 98,
165
- "##J": 99,
166
- "Ġc": 100,
167
- "##c": 101,
168
- "ĠÛ": 102,
169
- "##Û": 103,
170
- "Ġģ": 104,
171
- "##ģ": 105,
172
- "Ġk": 106,
173
- "##k": 107,
174
- "Ġŀ": 108,
175
- "##ŀ": 109,
176
- "ĠĚ": 110,
177
- "##Ě": 111,
178
- "Ġé": 112,
179
- "##é": 113,
180
- "Ġ¹": 114,
181
- "##¹": 115,
182
- "Ġġ": 116,
183
- "##ġ": 117,
184
- "ĠĠ": 118,
185
- "##Ġ": 119,
186
- "Ġ~": 120,
187
- "##~": 121,
188
- "Ġã": 122,
189
- "##ã": 123,
190
- "Ġô": 124,
191
- "##ô": 125,
192
- "Ġĩ": 126,
193
- "##ĩ": 127,
194
- "Ġļ": 128,
195
- "##ļ": 129,
196
- "Ġ^": 130,
197
- "##^": 131,
198
- "Ġ±": 132,
199
- "##±": 133,
200
- "ĠÇ": 134,
201
- "##Ç": 135,
202
- "Ġ©": 136,
203
- "##©": 137,
204
- "Ġċ": 138,
205
- "##ċ": 139,
206
- "Ġĵ": 140,
207
- "##ĵ": 141,
208
- "Ġg": 142,
209
- "##g": 143,
210
- "Ġ|": 144,
211
- "##|": 145,
212
- "ĠÕ": 146,
213
- "##Õ": 147,
214
- "Ġö": 148,
215
- "##ö": 149,
216
- "Ġī": 150,
217
- "##ī": 151,
218
- "ĠĶ": 152,
219
- "##Ķ": 153,
220
- "Ġr": 154,
221
- "##r": 155,
222
- "ĠĪ": 156,
223
- "##Ī": 157,
224
- "Ġ.": 158,
225
- "##.": 159,
226
- "ĠĆ": 160,
227
- "##Ć": 161,
228
- "ĠĖ": 162,
229
- "##Ė": 163,
230
- "Ġĝ": 164,
231
- "##ĝ": 165,
232
- "ĠÌ": 166,
233
- "##Ì": 167,
234
- "ĠÞ": 168,
235
- "##Þ": 169,
236
- "Ġ÷": 170,
237
- "##÷": 171,
238
- "Ġ£": 172,
239
- "##£": 173,
240
- "ĠE": 174,
241
- "##E": 175,
242
- "ĠĈ": 176,
243
- "##Ĉ": 177,
244
- "Ġ¶": 178,
245
- "##¶": 179,
246
- "ĠO": 180,
247
- "##O": 181,
248
- "ĠĹ": 182,
249
- "##Ĺ": 183,
250
- "Ġë": 184,
251
- "##ë": 185,
252
- "Ġ'": 186,
253
- "##'": 187,
254
- "Ġõ": 188,
255
- "##õ": 189,
256
- "ĠW": 190,
257
- "##W": 191,
258
- "Ġħ": 192,
259
- "##ħ": 193,
260
- "Ġó": 194,
261
- "##ó": 195,
262
- "Ġø": 196,
263
- "##ø": 197,
264
- "Ġ´": 198,
265
- "##´": 199,
266
- "Ġė": 200,
267
- "##ė": 201,
268
- "Ġ»": 202,
269
- "##»": 203,
270
- "Ġv": 204,
271
- "##v": 205,
272
- "Ġ9": 206,
273
- "##9": 207,
274
- "Ġ¼": 208,
275
- "##¼": 209,
276
- "Ġè": 210,
277
- "##è": 211,
278
- "ĠĬ": 212,
279
- "##Ĭ": 213,
280
- "Ġ4": 214,
281
- "##4": 215,
282
- "ĠĜ": 216,
283
- "##Ĝ": 217,
284
- "Ġz": 218,
285
- "##z": 219,
286
- "Ġf": 220,
287
- "##f": 221,
288
- "ĠÓ": 222,
289
- "##Ó": 223,
290
- "Ġ1": 224,
291
- "##1": 225,
292
- "ĠĔ": 226,
293
- "##Ĕ": 227,
294
- "ĠG": 228,
295
- "##G": 229,
296
- "ĠH": 230,
297
- "##H": 231,
298
- "Ġ²": 232,
299
- "##²": 233,
300
- "ĠÍ": 234,
301
- "##Í": 235,
302
- "ĠÑ": 236,
303
- "##Ñ": 237,
304
- "ĠÙ": 238,
305
- "##Ù": 239,
306
- "Ġe": 240,
307
- "##e": 241,
308
- "Ġ$": 242,
309
- "##$": 243,
310
- "ĠC": 244,
311
- "##C": 245,
312
- "Ġm": 246,
313
- "##m": 247,
314
- "Ġ¯": 248,
315
- "##¯": 249,
316
- "Ġě": 250,
317
- "##ě": 251,
318
- "ĠÏ": 252,
319
- "##Ï": 253,
320
- "ĠÐ": 254,
321
- "##Ð": 255,
322
- "ĠÆ": 256,
323
- "##Æ": 257,
324
- "ĠČ": 258,
325
- "##Č": 259,
326
- "ĠÁ": 260,
327
- "##Á": 261,
328
- "ĠN": 262,
329
- "##N": 263,
330
- "Ġñ": 264,
331
- "##ñ": 265,
332
- "ĠĨ": 266,
333
- "##Ĩ": 267,
334
- "Ġû": 268,
335
- "##û": 269,
336
- "Ġē": 270,
337
- "##ē": 271,
338
- "Ġx": 272,
339
- "##x": 273,
340
- "Ġ#": 274,
341
- "###": 275,
342
- "Ġ·": 276,
343
- "##·": 277,
344
- "ĠÄ": 278,
345
- "##Ä": 279,
346
- "ĠÊ": 280,
347
- "##Ê": 281,
348
- "Ġ«": 282,
349
- "##«": 283,
350
- "ĠĽ": 284,
351
- "##Ľ": 285,
352
- "Ġ¥": 286,
353
- "##¥": 287,
354
- "Ġ¤": 288,
355
- "##¤": 289,
356
- "Ġ*": 290,
357
- "##*": 291,
358
- "Ġh": 292,
359
- "##h": 293,
360
- "ĠD": 294,
361
- "##D": 295,
362
- "ĠB": 296,
363
- "##B": 297,
364
- "Ġí": 298,
365
- "##í": 299,
366
- "Ġď": 300,
367
- "##ď": 301,
368
- "ĠÔ": 302,
369
- "##Ô": 303,
370
- "Ġğ": 304,
371
- "##ğ": 305,
372
- "ĠĒ": 306,
373
- "##Ē": 307,
374
- "Ġï": 308,
375
- "##ï": 309,
376
- "Ġ¿": 310,
377
- "##¿": 311,
378
- "Ġù": 312,
379
- "##ù": 313,
380
- "Ġ×": 314,
381
- "##×": 315,
382
- "Ġ¨": 316,
383
- "##¨": 317,
384
- "Ġ(": 318,
385
- "##(": 319,
386
- "Ġu": 320,
387
- "##u": 321,
388
- "ĠS": 322,
389
- "##S": 323,
390
- "Ġ¬": 324,
391
- "##¬": 325,
392
- "Ġß": 326,
393
- "##ß": 327,
394
- "ĠQ": 328,
395
- "##Q": 329,
396
- "ĠĀ": 330,
397
- "##Ā": 331,
398
- "Ġ,": 332,
399
- "##,": 333,
400
- "Ġij": 334,
401
- "##ij": 335,
402
- "Ġľ": 336,
403
- "##ľ": 337,
404
- "ĠĿ": 338,
405
- "##Ŀ": 339,
406
- "Ġj": 340,
407
- "##j": 341,
408
- "ĠĮ": 342,
409
- "##Į": 343,
410
- "Ġ°": 344,
411
- "##°": 345,
412
- "ĠØ": 346,
413
- "##Ø": 347,
414
- "Ġ³": 348,
415
- "##³": 349,
416
- "ĠĐ": 350,
417
- "##Đ": 351,
418
- "Ġę": 352,
419
- "##ę": 353,
420
- "Ġ;": 354,
421
- "##;": 355,
422
- "ĠI": 356,
423
- "##I": 357,
424
- "ĠÂ": 358,
425
- "##Â": 359,
426
- "Ġú": 360,
427
- "##ú": 361,
428
- "Ġ@": 362,
429
- "##@": 363,
430
- "Ġü": 364,
431
- "##ü": 365,
432
- "Ġķ": 366,
433
- "##ķ": 367,
434
- "Ġ]": 368,
435
- "##]": 369,
436
- "ĠÃ": 370,
437
- "##Ã": 371,
438
- "ĠL": 372,
439
- "##L": 373,
440
- "Ġä": 374,
441
- "##ä": 375,
442
- "ĠÒ": 376,
443
- "##Ò": 377,
444
- "Ġĸ": 378,
445
- "##ĸ": 379,
446
- "Ġi": 380,
447
- "##i": 381,
448
- "Ġp": 382,
449
- "##p": 383,
450
- "Ġ¾": 384,
451
- "##¾": 385,
452
- "Ġā": 386,
453
- "##ā": 387,
454
- "ĠÝ": 388,
455
- "##Ý": 389,
456
- "ĠĊ": 390,
457
- "##Ċ": 391,
458
- "Ġ5": 392,
459
- "##5": 393,
460
- "Ġ7": 394,
461
- "##7": 395,
462
- "Ġ¡": 396,
463
- "##¡": 397,
464
- "Ġı": 398,
465
- "##ı": 399,
466
- "Ġ=": 400,
467
- "##=": 401,
468
- "Ġ`": 402,
469
- "##`": 403,
470
- "Ġw": 404,
471
- "##w": 405,
472
- "ĠÀ": 406,
473
- "##À": 407,
474
- "Ġĭ": 408,
475
- "##ĭ": 409,
476
- "Ġİ": 410,
477
- "##İ": 411,
478
- "Ġ_": 412,
479
- "##_": 413,
480
- "Ġ+": 414,
481
- "##+": 415,
482
- "Ġ/": 416,
483
- "##/": 417,
484
- "ĠÅ": 418,
485
- "##Å": 419,
486
- "ĠX": 420,
487
- "##X": 421,
488
- "Ġê": 422,
489
- "##ê": 423,
490
- "ĠĤ": 424,
491
- "##Ĥ": 425,
492
- "Ġa": 426,
493
- "##a": 427,
494
- "Ġð": 428,
495
- "##ð": 429,
496
- "ĠF": 430,
497
- "##F": 431,
498
- "Ġ8": 432,
499
- "##8": 433,
500
- "Ġ-": 434,
501
- "##-": 435,
502
- "Ġ¢": 436,
503
- "##¢": 437,
504
  "Ġâ": 438,
505
  "##â": 439,
506
- "Ġĥ": 440,
507
- "##ĥ": 441,
508
- "ĠŃ": 442,
509
- "##Ń": 443,
510
- "Ġª": 444,
511
- "##ª": 445,
512
- "ĠA": 446,
513
- "##A": 447,
514
- "Ġ%": 448,
515
- "##%": 449,
516
- "ĠK": 450,
517
- "##K": 451,
518
- "Ġÿ": 452,
519
- "##ÿ": 453,
520
- "Ġč": 454,
521
- "##č": 455,
522
- "Ġ6": 456,
523
- "##6": 457,
524
- "ĠĂ": 458,
525
- "##Ă": 459,
526
- "Ġ>": 460,
527
- "##>": 461,
528
- "Ġĕ": 462,
529
- "##ĕ": 463,
530
- "Ġ3": 464,
531
- "##3": 465,
532
- "Ġq": 466,
533
- "##q": 467,
534
- "Ġ§": 468,
535
- "##§": 469,
536
- "Ġ?": 470,
537
- "##?": 471,
538
- "Ġ)": 472,
539
- "##)": 473,
540
- "ĠR": 474,
541
- "##R": 475,
542
- "ĠV": 476,
543
- "##V": 477,
544
- "Ġ[": 478,
545
- "##[": 479,
546
- "ĠU": 480,
547
- "##U": 481,
548
- "Ġç": 482,
549
- "##ç": 483,
550
- "ĠM": 484,
551
- "##M": 485,
552
- "ĠŁ": 486,
553
- "##Ł": 487,
554
- "ĠP": 488,
555
- "##P": 489,
556
- "Ġ{": 490,
557
- "##{": 491,
558
- "Ġì": 492,
559
- "##ì": 493,
560
- "Ġt": 494,
561
- "##t": 495,
562
- "Ġ¸": 496,
563
- "##¸": 497,
564
- "Ġþ": 498,
565
- "##þ": 499,
566
- "ĠĦ": 500,
567
- "##Ħ": 501,
568
- "Ġł": 502,
569
- "##ł": 503,
570
- "Ġ}": 504,
571
- "##}": 505,
572
- "Ġd": 506,
573
- "##d": 507,
574
- "Ġĺ": 508,
575
- "##ĺ": 509,
576
- "ĠÖ": 510,
577
- "##Ö": 511,
578
- "ĠÉ": 512,
579
- "##É": 513,
580
  "<|unk|>": 514,
581
  "##�": 515,
582
  "Ġ�": 516,
 
65
  "vocab": {
66
  "<|padding|>": 0,
67
  "<|endoftext|>": 1,
68
+ "ĠL": 2,
69
+ "##L": 3,
70
+ "Ġz": 4,
71
+ "##z": 5,
72
+ "ĠS": 6,
73
+ "##S": 7,
74
+ "Ġù": 8,
75
+ "##ù": 9,
76
+ "Ġğ": 10,
77
+ "##ğ": 11,
78
+ "Ġg": 12,
79
+ "##g": 13,
80
+ "Ġ`": 14,
81
+ "##`": 15,
82
+ "Ġď": 16,
83
+ "##ď": 17,
84
+ "Ġĥ": 18,
85
+ "##ĥ": 19,
86
+ "Ġ=": 20,
87
+ "##=": 21,
88
+ "Ġ-": 22,
89
+ "##-": 23,
90
+ "ĠÐ": 24,
91
+ "##Ð": 25,
92
+ "ĠZ": 26,
93
+ "##Z": 27,
94
+ "Ġ\"": 28,
95
+ "##\"": 29,
96
+ "Ġ§": 30,
97
+ "##§": 31,
98
+ "Ġa": 32,
99
+ "##a": 33,
100
+ "Ġl": 34,
101
+ "##l": 35,
102
+ "Ġ{": 36,
103
+ "##{": 37,
104
+ "ĠÅ": 38,
105
+ "##Å": 39,
106
+ "ĠĀ": 40,
107
+ "##Ā": 41,
108
+ "Ġ#": 42,
109
+ "###": 43,
110
+ "ĠĖ": 44,
111
+ "##Ė": 45,
112
+ "Ġá": 46,
113
+ "##á": 47,
114
+ "Ġè": 48,
115
+ "##è": 49,
116
+ "Ġã": 50,
117
+ "##ã": 51,
118
+ "Ġĵ": 52,
119
+ "##ĵ": 53,
120
+ "ĠÄ": 54,
121
+ "##Ä": 55,
122
+ "Ġø": 56,
123
+ "##ø": 57,
124
+ "ĠM": 58,
125
+ "##M": 59,
126
+ "Ġć": 60,
127
+ "##ć": 61,
128
+ "Ġm": 62,
129
+ "##m": 63,
130
+ "Ġô": 64,
131
+ "##ô": 65,
132
+ "Ġ¿": 66,
133
+ "##¿": 67,
134
+ "Ġd": 68,
135
+ "##d": 69,
136
+ "Ġ«": 70,
137
+ "##«": 71,
138
+ "Ġì": 72,
139
+ "##ì": 73,
140
+ "ĠĹ": 74,
141
+ "##Ĺ": 75,
142
+ "Ġ£": 76,
143
+ "##£": 77,
144
+ "Ġò": 78,
145
+ "##ò": 79,
146
+ "Ġó": 80,
147
+ "##ó": 81,
148
+ "ĠĮ": 82,
149
+ "##Į": 83,
150
+ "ĠĚ": 84,
151
+ "##Ě": 85,
152
+ "Ġ¶": 86,
153
+ "##¶": 87,
154
+ "Ġæ": 88,
155
+ "##æ": 89,
156
+ "ĠĜ": 90,
157
+ "##Ĝ": 91,
158
+ "Ġ8": 92,
159
+ "##8": 93,
160
+ "ĠŁ": 94,
161
+ "##Ł": 95,
162
+ "Ġµ": 96,
163
+ "##µ": 97,
164
+ "Ġî": 98,
165
+ "##î": 99,
166
+ "ĠÆ": 100,
167
+ "##Æ": 101,
168
+ "ĠĎ": 102,
169
+ "##Ď": 103,
170
+ "Ġě": 104,
171
+ "##ě": 105,
172
+ "Ġs": 106,
173
+ "##s": 107,
174
+ "Ġ0": 108,
175
+ "##0": 109,
176
+ "ĠO": 110,
177
+ "##O": 111,
178
+ "ĠÕ": 112,
179
+ "##Õ": 113,
180
+ "Ġċ": 114,
181
+ "##ċ": 115,
182
+ "Ġ¡": 116,
183
+ "##¡": 117,
184
+ "Ġe": 118,
185
+ "##e": 119,
186
+ "ĠØ": 120,
187
+ "##Ø": 121,
188
+ "Ġę": 122,
189
+ "##ę": 123,
190
+ "Ġ4": 124,
191
+ "##4": 125,
192
+ "Ġ}": 126,
193
+ "##}": 127,
194
+ "Ġç": 128,
195
+ "##ç": 129,
196
+ "Ġij": 130,
197
+ "##ij": 131,
198
+ "Ġ¯": 132,
199
+ "##¯": 133,
200
+ "Ġī": 134,
201
+ "##ī": 135,
202
+ "Ġy": 136,
203
+ "##y": 137,
204
+ "ĠT": 138,
205
+ "##T": 139,
206
+ "Ġ[": 140,
207
+ "##[": 141,
208
+ "Ġ¼": 142,
209
+ "##¼": 143,
210
+ "Ġ½": 144,
211
+ "##½": 145,
212
+ "Ġĕ": 146,
213
+ "##ĕ": 147,
214
+ "ĠÓ": 148,
215
+ "##Ó": 149,
216
+ "Ġ¸": 150,
217
+ "##¸": 151,
218
+ "Ġĸ": 152,
219
+ "##ĸ": 153,
220
+ "ĠÑ": 154,
221
+ "##Ñ": 155,
222
+ "Ġ³": 156,
223
+ "##³": 157,
224
+ "ĠE": 158,
225
+ "##E": 159,
226
+ "Ġp": 160,
227
+ "##p": 161,
228
+ "ĠĊ": 162,
229
+ "##Ċ": 163,
230
+ "ĠĒ": 164,
231
+ "##Ē": 165,
232
+ "Ġ]": 166,
233
+ "##]": 167,
234
+ "ĠÌ": 168,
235
+ "##Ì": 169,
236
+ "Ġ(": 170,
237
+ "##(": 171,
238
+ "ĠI": 172,
239
+ "##I": 173,
240
+ "Ġf": 174,
241
+ "##f": 175,
242
+ "Ġ¾": 176,
243
+ "##¾": 177,
244
+ "Ġ÷": 178,
245
+ "##÷": 179,
246
+ "Ġö": 180,
247
+ "##ö": 181,
248
+ "Ġð": 182,
249
+ "##ð": 183,
250
+ "Ġé": 184,
251
+ "##é": 185,
252
+ "ĠIJ": 186,
253
+ "##IJ": 187,
254
+ "ĠP": 188,
255
+ "##P": 189,
256
+ "Ġw": 190,
257
+ "##w": 191,
258
+ "ĠÚ": 192,
259
+ "##Ú": 193,
260
+ "Ġļ": 194,
261
+ "##ļ": 195,
262
+ "ĠÎ": 196,
263
+ "##Î": 197,
264
+ "Ġ/": 198,
265
+ "##/": 199,
266
+ "Ġb": 200,
267
+ "##b": 201,
268
+ "Ġĉ": 202,
269
+ "##ĉ": 203,
270
+ "ĠJ": 204,
271
+ "##J": 205,
272
+ "ĠW": 206,
273
+ "##W": 207,
274
+ "Ġ:": 208,
275
+ "##:": 209,
276
+ "Ġ×": 210,
277
+ "##×": 211,
278
+ "Ġ>": 212,
279
+ "##>": 213,
280
+ "Ġí": 214,
281
+ "##í": 215,
282
+ "Ġ+": 216,
283
+ "##+": 217,
284
+ "ĠĠ": 218,
285
+ "##Ġ": 219,
286
+ "Ġ3": 220,
287
+ "##3": 221,
288
+ "Ġ®": 222,
289
+ "##®": 223,
290
+ "ĠÞ": 224,
291
+ "##Þ": 225,
292
+ "Ġû": 226,
293
+ "##û": 227,
294
+ "Ġħ": 228,
295
+ "##ħ": 229,
296
+ "Ġ¥": 230,
297
+ "##¥": 231,
298
+ "Ġk": 232,
299
+ "##k": 233,
300
+ "Ġï": 234,
301
+ "##ï": 235,
302
+ "Ġ<": 236,
303
+ "##<": 237,
304
+ "Ġ6": 238,
305
+ "##6": 239,
306
+ "Ġº": 240,
307
+ "##º": 241,
308
+ "ĠN": 242,
309
+ "##N": 243,
310
+ "Ġv": 244,
311
+ "##v": 245,
312
+ "Ġà": 246,
313
+ "##à": 247,
314
+ "ĠĬ": 248,
315
+ "##Ĭ": 249,
316
+ "Ġľ": 250,
317
+ "##ľ": 251,
318
+ "Ġ¤": 252,
319
+ "##¤": 253,
320
+ "Ġ|": 254,
321
+ "##|": 255,
322
+ "ĠU": 256,
323
+ "##U": 257,
324
+ "Ġþ": 258,
325
+ "##þ": 259,
326
+ "ĠĪ": 260,
327
+ "##Ī": 261,
328
+ "Ġą": 262,
329
+ "##ą": 263,
330
+ "ĠG": 264,
331
+ "##G": 265,
332
+ "ĠĞ": 266,
333
+ "##Ğ": 267,
334
+ "ĠX": 268,
335
+ "##X": 269,
336
+ "Ġ¦": 270,
337
+ "##¦": 271,
338
+ "ĠA": 272,
339
+ "##A": 273,
340
+ "Ġė": 274,
341
+ "##ė": 275,
342
+ "ĠĈ": 276,
343
+ "##Ĉ": 277,
344
+ "ĠÁ": 278,
345
+ "##Á": 279,
346
+ "ĠĽ": 280,
347
+ "##Ľ": 281,
348
+ "Ġč": 282,
349
+ "##č": 283,
350
+ "ĠĔ": 284,
351
+ "##Ĕ": 285,
352
+ "Ġ_": 286,
353
+ "##_": 287,
354
+ "Ġ;": 288,
355
+ "##;": 289,
356
+ "Ġ?": 290,
357
+ "##?": 291,
358
+ "Ġē": 292,
359
+ "##ē": 293,
360
+ "ĠH": 294,
361
+ "##H": 295,
362
+ "Ġ5": 296,
363
+ "##5": 297,
364
+ "Ġx": 298,
365
+ "##x": 299,
366
+ "Ġ,": 300,
367
+ "##,": 301,
368
+ "ĠC": 302,
369
+ "##C": 303,
370
+ "ĠÔ": 304,
371
+ "##Ô": 305,
372
+ "ĠĶ": 306,
373
+ "##Ķ": 307,
374
+ "Ġ'": 308,
375
+ "##'": 309,
376
+ "ĠB": 310,
377
+ "##B": 311,
378
+ "ĠQ": 312,
379
+ "##Q": 313,
380
+ "Ġ~": 314,
381
+ "##~": 315,
382
+ "Ġĭ": 316,
383
+ "##ĭ": 317,
384
+ "ĠĂ": 318,
385
+ "##Ă": 319,
386
+ "Ġ9": 320,
387
+ "##9": 321,
388
+ "Ġj": 322,
389
+ "##j": 323,
390
+ "ĠÙ": 324,
391
+ "##Ù": 325,
392
+ "Ġ&": 326,
393
+ "##&": 327,
394
+ "Ġå": 328,
395
+ "##å": 329,
396
+ "Ġă": 330,
397
+ "##ă": 331,
398
+ "Ġ1": 332,
399
+ "##1": 333,
400
+ "ĠÜ": 334,
401
+ "##Ü": 335,
402
+ "Ġ\\": 336,
403
+ "##\\": 337,
404
+ "Ġ²": 338,
405
+ "##²": 339,
406
+ "Ġķ": 340,
407
+ "##ķ": 341,
408
+ "ĠF": 342,
409
+ "##F": 343,
410
+ "Ġ@": 344,
411
+ "##@": 345,
412
+ "ĠÉ": 346,
413
+ "##É": 347,
414
+ "Ġģ": 348,
415
+ "##ģ": 349,
416
+ "Ġġ": 350,
417
+ "##ġ": 351,
418
+ "Ġr": 352,
419
+ "##r": 353,
420
+ "Ġ©": 354,
421
+ "##©": 355,
422
+ "Ġõ": 356,
423
+ "##õ": 357,
424
+ "Ġß": 358,
425
+ "##ß": 359,
426
+ "Ġ¬": 360,
427
+ "##¬": 361,
428
+ "ĠĄ": 362,
429
+ "##Ą": 363,
430
+ "ĠÍ": 364,
431
+ "##Í": 365,
432
+ "Ġq": 366,
433
+ "##q": 367,
434
+ "Ġt": 368,
435
+ "##t": 369,
436
+ "Ġ^": 370,
437
+ "##^": 371,
438
+ "Ġĩ": 372,
439
+ "##ĩ": 373,
440
+ "Ġ%": 374,
441
+ "##%": 375,
442
+ "ĠĤ": 376,
443
+ "##Ĥ": 377,
444
+ "ĠĿ": 378,
445
+ "##Ŀ": 379,
446
+ "ĠÏ": 380,
447
+ "##Ï": 381,
448
+ "ĠÒ": 382,
449
+ "##Ò": 383,
450
+ "Ġü": 384,
451
+ "##ü": 385,
452
+ "Ġý": 386,
453
+ "##ý": 387,
454
+ "ĠĢ": 388,
455
+ "##Ģ": 389,
456
+ "ĠÖ": 390,
457
+ "##Ö": 391,
458
+ "Ġo": 392,
459
+ "##o": 393,
460
+ "ĠÊ": 394,
461
+ "##Ê": 395,
462
+ "ĠÛ": 396,
463
+ "##Û": 397,
464
+ "Ġÿ": 398,
465
+ "##ÿ": 399,
466
+ "Ġ!": 400,
467
+ "##!": 401,
468
+ "ĠÝ": 402,
469
+ "##Ý": 403,
470
+ "Ġñ": 404,
471
+ "##ñ": 405,
472
+ "ĠY": 406,
473
+ "##Y": 407,
474
+ "Ġİ": 408,
475
+ "##İ": 409,
476
+ "ĠR": 410,
477
+ "##R": 411,
478
+ "Ġ±": 412,
479
+ "##±": 413,
480
+ "ĠÂ": 414,
481
+ "##Â": 415,
482
+ "Ġį": 416,
483
+ "##į": 417,
484
+ "Ġ¢": 418,
485
+ "##¢": 419,
486
+ "Ġi": 420,
487
+ "##i": 421,
488
+ "Ġ´": 422,
489
+ "##´": 423,
490
+ "Ġä": 424,
491
+ "##ä": 425,
492
+ "Ġđ": 426,
493
+ "##đ": 427,
494
+ "ĠČ": 428,
495
+ "##Č": 429,
496
+ "Ġĺ": 430,
497
+ "##ĺ": 431,
498
+ "Ġı": 432,
499
+ "##ı": 433,
500
+ "ĠD": 434,
501
+ "##D": 435,
502
+ "Ġê": 436,
503
+ "##ê": 437,
504
  "Ġâ": 438,
505
  "##â": 439,
506
+ "ĠĦ": 440,
507
+ "##Ħ": 441,
508
+ "Ġ»": 442,
509
+ "##»": 443,
510
+ "Ġŀ": 444,
511
+ "##ŀ": 445,
512
+ "ĠK": 446,
513
+ "##K": 447,
514
+ "Ġ)": 448,
515
+ "##)": 449,
516
+ "ĠĻ": 450,
517
+ "##Ļ": 451,
518
+ "ĠÃ": 452,
519
+ "##Ã": 453,
520
+ "Ġú": 454,
521
+ "##ú": 455,
522
+ "ĠĐ": 456,
523
+ "##Đ": 457,
524
+ "Ġ*": 458,
525
+ "##*": 459,
526
+ "Ġ¨": 460,
527
+ "##¨": 461,
528
+ "ĠÀ": 462,
529
+ "##À": 463,
530
+ "Ġª": 464,
531
+ "##ª": 465,
532
+ "ĠĴ": 466,
533
+ "##Ĵ": 467,
534
+ "Ġā": 468,
535
+ "##ā": 469,
536
+ "Ġ.": 470,
537
+ "##.": 471,
538
+ "ĠĆ": 472,
539
+ "##Ć": 473,
540
+ "Ġł": 474,
541
+ "##ł": 475,
542
+ "ĠÈ": 476,
543
+ "##È": 477,
544
+ "ĠĘ": 478,
545
+ "##Ę": 479,
546
+ "Ġh": 480,
547
+ "##h": 481,
548
+ "ĠÇ": 482,
549
+ "##Ç": 483,
550
+ "ĠV": 484,
551
+ "##V": 485,
552
+ "ĠĨ": 486,
553
+ "##Ĩ": 487,
554
+ "ĠŃ": 488,
555
+ "##Ń": 489,
556
+ "Ġ·": 490,
557
+ "##·": 491,
558
+ "Ġn": 492,
559
+ "##n": 493,
560
+ "Ġ2": 494,
561
+ "##2": 495,
562
+ "Ġ$": 496,
563
+ "##$": 497,
564
+ "Ġ¹": 498,
565
+ "##¹": 499,
566
+ "Ġu": 500,
567
+ "##u": 501,
568
+ "Ġë": 502,
569
+ "##ë": 503,
570
+ "Ġĝ": 504,
571
+ "##ĝ": 505,
572
+ "Ġc": 506,
573
+ "##c": 507,
574
+ "ĠË": 508,
575
+ "##Ë": 509,
576
+ "Ġ°": 510,
577
+ "##°": 511,
578
+ "Ġ7": 512,
579
+ "##7": 513,
580
  "<|unk|>": 514,
581
  "##�": 515,
582
  "Ġ�": 516,
fw57Mmulti_Entropy_thresholdB_64000/vocab.json CHANGED
The diff for this file is too large to render. See raw diff