codebyzeb commited on
Commit
30b14ac
·
verified ·
1 Parent(s): f1c1fba

Upload folder using huggingface_hub

Browse files
fw57Mmulti_Surprisal_thresholdB_16000/tokenizer.json CHANGED
@@ -58,518 +58,518 @@
58
  "vocab": {
59
  "<|padding|>": 0,
60
  "<|endoftext|>": 1,
61
- "Ġb": 2,
62
- "##b": 3,
63
- "Ġ®": 4,
64
- "##®": 5,
65
- "ĠE": 6,
66
- "##E": 7,
67
- "ĠW": 8,
68
- "##W": 9,
69
- "Ġĥ": 10,
70
- "##ĥ": 11,
71
- "Ġ~": 12,
72
- "##~": 13,
73
- "Ġd": 14,
74
- "##d": 15,
75
- "Ġę": 16,
76
- "##ę": 17,
77
- "ĠÝ": 18,
78
- "##Ý": 19,
79
- "Ġ£": 20,
80
- "##£": 21,
81
- "Ġz": 22,
82
- "##z": 23,
83
- "ĠĈ": 24,
84
- "##Ĉ": 25,
85
- "ĠV": 26,
86
- "##V": 27,
87
- "ĠG": 28,
88
- "##G": 29,
89
- "Ġg": 30,
90
- "##g": 31,
91
- "Ġt": 32,
92
- "##t": 33,
93
- "Ġ¹": 34,
94
- "##¹": 35,
95
- "ĠĔ": 36,
96
- "##Ĕ": 37,
97
- "Ġw": 38,
98
- "##w": 39,
99
- "Ġĩ": 40,
100
- "##ĩ": 41,
101
- "Ġi": 42,
102
- "##i": 43,
103
- "Ġij": 44,
104
- "##ij": 45,
105
- "Ġü": 46,
106
- "##ü": 47,
107
- "Ġ÷": 48,
108
- "##÷": 49,
109
- "Ġp": 50,
110
- "##p": 51,
111
- "Ġį": 52,
112
- "##į": 53,
113
- "ĠÑ": 54,
114
- "##Ñ": 55,
115
- "ĠU": 56,
116
- "##U": 57,
117
- "ĠĻ": 58,
118
- "##Ļ": 59,
119
- "ĠÔ": 60,
120
- "##Ô": 61,
121
- "Ġ9": 62,
122
- "##9": 63,
123
- "Ġû": 64,
124
- "##û": 65,
125
- "Ġ_": 66,
126
- "##_": 67,
127
- "Ġ0": 68,
128
- "##0": 69,
129
- "Ġà": 70,
130
- "##à": 71,
131
- "Ġč": 72,
132
- "##č": 73,
133
- (": 74,
134
- "##(": 75,
135
- "ĠŃ": 76,
136
- "##Ń": 77,
137
- "Ġ¡": 78,
138
- "##¡": 79,
139
- "Ġ.": 80,
140
- "##.": 81,
141
- "Ġ`": 82,
142
- "##`": 83,
143
- "Ġ%": 84,
144
- "##%": 85,
145
- "ĠP": 86,
146
- "##P": 87,
147
- "Ġî": 88,
148
- "##î": 89,
149
- "ĠĎ": 90,
150
- "##Ď": 91,
151
- "Ġ4": 92,
152
- "##4": 93,
153
- "ĠĶ": 94,
154
- "##Ķ": 95,
155
- "Ġr": 96,
156
- "##r": 97,
157
- "ĠĄ": 98,
158
- "##Ą": 99,
159
- "Ġ!": 100,
160
- "##!": 101,
161
- "Ġ¦": 102,
162
- "##¦": 103,
163
- "Ġĕ": 104,
164
- "##ĕ": 105,
165
- "Ġc": 106,
166
- "##c": 107,
167
- "ĠÀ": 108,
168
- "##À": 109,
169
- "Ġķ": 110,
170
- "##ķ": 111,
171
- "Ġľ": 112,
172
- "##ľ": 113,
173
- "ĠÇ": 114,
174
- "##Ç": 115,
175
- "ĠÍ": 116,
176
- "##Í": 117,
177
- "Ġu": 118,
178
- "##u": 119,
179
- "Ġď": 120,
180
- "##ď": 121,
181
- "ĠĊ": 122,
182
- "##Ċ": 123,
183
- "Ġì": 124,
184
- "##ì": 125,
185
- "Ġí": 126,
186
- "##í": 127,
187
- "Ġy": 128,
188
- "##y": 129,
189
- "Ġð": 130,
190
- "##ð": 131,
191
- "ĠĘ": 132,
192
- "##Ę": 133,
193
- "Ġâ": 134,
194
- "##â": 135,
195
- "Ġý": 136,
196
- "##ý": 137,
197
- "ĠT": 138,
198
- "##T": 139,
199
- "ĠĞ": 140,
200
- "##Ğ": 141,
201
- "Ġm": 142,
202
- "##m": 143,
203
- "Ġ2": 144,
204
- "##2": 145,
205
- "ĠĆ": 146,
206
- "##Ć": 147,
207
- "Ġ§": 148,
208
- "##§": 149,
209
- "ĠÞ": 150,
210
- "##Þ": 151,
211
- "Ġ¶": 152,
212
- "##¶": 153,
213
- "Ġ@": 154,
214
- "##@": 155,
215
- "Ġñ": 156,
216
- "##ñ": 157,
217
- "Ġă": 158,
218
- "##ă": 159,
219
- "ĠĦ": 160,
220
- "##Ħ": 161,
221
- "Ġ5": 162,
222
- "##5": 163,
223
- "Ġ8": 164,
224
- "##8": 165,
225
- "Ġã": 166,
226
- "##ã": 167,
227
- "ĠD": 168,
228
- "##D": 169,
229
- "Ġè": 170,
230
- "##è": 171,
231
- "Ġø": 172,
232
- "##ø": 173,
233
- "ĠĂ": 174,
234
- "##Ă": 175,
235
- "Ġê": 176,
236
- "##ê": 177,
237
- "Ġ¢": 178,
238
- "##¢": 179,
239
- "ĠĖ": 180,
240
- "##Ė": 181,
241
- "Ġ³": 182,
242
- "##³": 183,
243
- "Ġ,": 184,
244
- "##,": 185,
245
- "Ġİ": 186,
246
- "##İ": 187,
247
- "ĠÎ": 188,
248
- "##Î": 189,
249
- "Ġ)": 190,
250
- "##)": 191,
251
- "Ġú": 192,
252
- "##ú": 193,
253
- "ĠC": 194,
254
- "##C": 195,
255
- "ĠĒ": 196,
256
- "##Ē": 197,
257
- "Ġ'": 198,
258
- "##'": 199,
259
- "Ġ<": 200,
260
- "##<": 201,
261
- "ĠM": 202,
262
- "##M": 203,
263
- "Ġa": 204,
264
- "##a": 205,
265
- "Ġ{": 206,
266
- "##{": 207,
267
- "Ġĺ": 208,
268
- "##ĺ": 209,
269
- "Ġ¥": 210,
270
- "##¥": 211,
271
- "ĠÌ": 212,
272
- "##Ì": 213,
273
- "Ġs": 214,
274
- "##s": 215,
275
- "Ġö": 216,
276
- "##ö": 217,
277
- "Ġ¼": 218,
278
- "##¼": 219,
279
- "Ġħ": 220,
280
- "##ħ": 221,
281
- "Ġ·": 222,
282
- "##·": 223,
283
- "ĠIJ": 224,
284
- "##IJ": 225,
285
- "ĠÏ": 226,
286
- "##Ï": 227,
287
- "ĠÚ": 228,
288
- "##Ú": 229,
289
- "ĠĐ": 230,
290
- "##Đ": 231,
291
- "Ġµ": 232,
292
- "##µ": 233,
293
- "Ġï": 234,
294
- "##ï": 235,
295
- "Ġ×": 236,
296
- "##×": 237,
297
- "ĠĚ": 238,
298
- "##Ě": 239,
299
- "Ġ1": 240,
300
- "##1": 241,
301
- "Ġ»": 242,
302
- "##»": 243,
303
- "Ġþ": 244,
304
- "##þ": 245,
305
- "Ġĉ": 246,
306
- "##ĉ": 247,
307
- "ĠÖ": 248,
308
- "##Ö": 249,
309
- "ĠÉ": 250,
310
- "##É": 251,
311
- "ĠØ": 252,
312
- "##Ø": 253,
313
- "ĠH": 254,
314
- "##H": 255,
315
- "Ġ¯": 256,
316
- "##¯": 257,
317
- "ĠJ": 258,
318
- "##J": 259,
319
- "Ġ©": 260,
320
- "##©": 261,
321
- "Ġ;": 262,
322
- "##;": 263,
323
- "Ġf": 264,
324
- "##f": 265,
325
- "Ġx": 266,
326
- "##x": 267,
327
- "ĠQ": 268,
328
- "##Q": 269,
329
- "Ġä": 270,
330
- "##ä": 271,
331
- "Ġī": 272,
332
- "##ī": 273,
333
- "Ġ3": 274,
334
- "##3": 275,
335
- "Ġ¨": 276,
336
- "##¨": 277,
337
- "Ġé": 278,
338
- "##é": 279,
339
- "ĠĤ": 280,
340
- "##Ĥ": 281,
341
- "Ġ}": 282,
342
- "##}": 283,
343
- "Ġ¾": 284,
344
- "##¾": 285,
345
- "Ġô": 286,
346
- "##ô": 287,
347
- "Ġą": 288,
348
- "##ą": 289,
349
- "Ġ[": 290,
350
- "##[": 291,
351
- "Ġģ": 292,
352
- "##ģ": 293,
353
- "ĠĨ": 294,
354
- "##Ĩ": 295,
355
- "ĠÆ": 296,
356
- "##Æ": 297,
357
- "ĠĪ": 298,
358
- "##Ī": 299,
359
- "Ġı": 300,
360
- "##ı": 301,
361
- "ĠX": 302,
362
- "##X": 303,
363
- "ĠA": 304,
364
- "##A": 305,
365
- "Ġ°": 306,
366
- "##°": 307,
367
- "Ġ-": 308,
368
- "##-": 309,
369
- "Ġ7": 310,
370
- "##7": 311,
371
- "Ġq": 312,
372
- "##q": 313,
373
- "Ġç": 314,
374
- "##ç": 315,
375
- "ĠO": 316,
376
- "##O": 317,
377
- "Ġ?": 318,
378
- "##?": 319,
379
- "Ġŀ": 320,
380
- "##ŀ": 321,
381
- "Ġł": 322,
382
- "##ł": 323,
383
- "Ġĸ": 324,
384
- "##ĸ": 325,
385
- "Ġe": 326,
386
- "##e": 327,
387
- "ĠĬ": 328,
388
- "##Ĭ": 329,
389
- "Ġå": 330,
390
- "##å": 331,
391
- "ĠÙ": 332,
392
- "##Ù": 333,
393
- "ĠK": 334,
394
- "##K": 335,
395
- "Ġl": 336,
396
- "##l": 337,
397
- "Ġ6": 338,
398
- "##6": 339,
399
- "ĠÅ": 340,
400
- "##Å": 341,
401
- "Ġė": 342,
402
- "##ė": 343,
403
- "Ġá": 344,
404
- "##á": 345,
405
- "ĠB": 346,
406
- "##B": 347,
407
- "ĠÈ": 348,
408
- "##È": 349,
409
- "Ġ¬": 350,
410
- "##¬": 351,
411
- "ĠĮ": 352,
412
- "##Į": 353,
413
- "Ġ/": 354,
414
- "##/": 355,
415
- "Ġk": 356,
416
- "##k": 357,
417
- "ĠĴ": 358,
418
- "##Ĵ": 359,
419
- "Ġh": 360,
420
- "##h": 361,
421
- "Ġā": 362,
422
- "##ā": 363,
423
- "Ġċ": 364,
424
- "##ċ": 365,
425
- "Ġ*": 366,
426
- "##*": 367,
427
- "ĠÃ": 368,
428
- "##Ã": 369,
429
- "ĠĀ": 370,
430
- "##Ā": 371,
431
- "Ġù": 372,
432
- "##ù": 373,
433
- "Ġæ": 374,
434
- "##æ": 375,
435
- "Ġē": 376,
436
- "##ē": 377,
437
- "ĠF": 378,
438
- "##F": 379,
439
- "Ġ²": 380,
440
- "##²": 381,
441
- "ĠÊ": 382,
442
- "##Ê": 383,
443
- "Ġ\"": 384,
444
- "##\"": 385,
445
- "Ġ+": 386,
446
- "##+": 387,
447
- "ĠÐ": 388,
448
- "##Ð": 389,
449
- "Ġ´": 390,
450
- "##´": 391,
451
- "ĠY": 392,
452
- "##Y": 393,
453
- "Ġÿ": 394,
454
- "##ÿ": 395,
455
- "ĠÁ": 396,
456
- "##Á": 397,
457
- "ĠÓ": 398,
458
- "##Ó": 399,
459
- "Ġò": 400,
460
- "##ò": 401,
461
- "Ġ|": 402,
462
- "##|": 403,
463
- "Ġ±": 404,
464
- "##±": 405,
465
- "Ġ$": 406,
466
- "##$": 407,
467
- "Ġ:": 408,
468
- "##:": 409,
469
- "Ġ\\": 410,
470
- "##\\": 411,
471
- "Ġđ": 412,
472
- "##đ": 413,
473
- "Ġĵ": 414,
474
- "##ĵ": 415,
475
- "Ġğ": 416,
476
- "##ğ": 417,
477
- "ĠÒ": 418,
478
- "##Ò": 419,
479
- "ĠZ": 420,
480
- "##Z": 421,
481
- "ĠÛ": 422,
482
- "##Û": 423,
483
- "Ġ¿": 424,
484
- "##¿": 425,
485
- "ĠŁ": 426,
486
- "##Ł": 427,
487
- "Ġj": 428,
488
- "##j": 429,
489
- "ĠČ": 430,
490
- "##Č": 431,
491
- "ĠN": 432,
492
- "##N": 433,
493
- "Ġ>": 434,
494
- "##>": 435,
495
- "ĠÄ": 436,
496
- "##Ä": 437,
497
- "Ġ]": 438,
498
- "##]": 439,
499
- "ĠĹ": 440,
500
- "##Ĺ": 441,
501
- "Ġ=": 442,
502
- "##=": 443,
503
- "ĠË": 444,
504
- "##Ë": 445,
505
- "Ġº": 446,
506
- "##º": 447,
507
- "ĠÜ": 448,
508
- "##Ü": 449,
509
- "Ġĝ": 450,
510
- "##ĝ": 451,
511
- "Ġo": 452,
512
- "##o": 453,
513
- "Ġë": 454,
514
- "##ë": 455,
515
- "Ġ&": 456,
516
- "##&": 457,
517
- "ĠĿ": 458,
518
- "##Ŀ": 459,
519
- "ĠL": 460,
520
- "##L": 461,
521
- "Ġª": 462,
522
- "##ª": 463,
523
- "ĠÕ": 464,
524
- "##Õ": 465,
525
- "Ġļ": 466,
526
- "##ļ": 467,
527
- "ĠI": 468,
528
- "##I": 469,
529
- "Ġõ": 470,
530
- "##õ": 471,
531
- "Ġó": 472,
532
- "##ó": 473,
533
- "Ġn": 474,
534
- "##n": 475,
535
- "Ġ¤": 476,
536
- "##¤": 477,
537
- "Ġß": 478,
538
- "##ß": 479,
539
- "Ġ¸": 480,
540
- "##¸": 481,
541
- "Ġě": 482,
542
- "##ě": 483,
543
- "ĠĢ": 484,
544
- "##Ģ": 485,
545
- "ĠĽ": 486,
546
- "##Ľ": 487,
547
- "Ġġ": 488,
548
- "##ġ": 489,
549
- "Ġĭ": 490,
550
- "##ĭ": 491,
551
- "Ġ½": 492,
552
- "##½": 493,
553
- "Ġ#": 494,
554
- "###": 495,
555
- "Ġ«": 496,
556
- "##«": 497,
557
- "ĠĜ": 498,
558
- "##Ĝ": 499,
559
- "ĠĠ": 500,
560
- "##Ġ": 501,
561
- "Ġv": 502,
562
- "##v": 503,
563
- "Ġć": 504,
564
- "##ć": 505,
565
- "ĠR": 506,
566
- "##R": 507,
567
- "Ġ^": 508,
568
- "##^": 509,
569
- "ĠS": 510,
570
- "##S": 511,
571
- "ĠÂ": 512,
572
- "##Â": 513,
573
  "<|unk|>": 514,
574
  "##�": 515,
575
  "Ġsa": 516,
 
58
  "vocab": {
59
  "<|padding|>": 0,
60
  "<|endoftext|>": 1,
61
+ "ĠŁ": 2,
62
+ "##Ł": 3,
63
+ "Ġč": 4,
64
+ "##č": 5,
65
+ "Ġ^": 6,
66
+ "##^": 7,
67
+ "Ġ<": 8,
68
+ "##<": 9,
69
+ "Ġr": 10,
70
+ "##r": 11,
71
+ "Ġĺ": 12,
72
+ "##ĺ": 13,
73
+ "ĠĄ": 14,
74
+ "##Ą": 15,
75
+ "Ġ'": 16,
76
+ "##'": 17,
77
+ "Ġij": 18,
78
+ "##ij": 19,
79
+ "Ġ,": 20,
80
+ "##,": 21,
81
+ "ĠĬ": 22,
82
+ "##Ĭ": 23,
83
+ "Ġ4": 24,
84
+ "##4": 25,
85
+ "Ġª": 26,
86
+ "##ª": 27,
87
+ "Ġĕ": 28,
88
+ "##ĕ": 29,
89
+ "Ġį": 30,
90
+ "##į": 31,
91
+ "Ġº": 32,
92
+ "##º": 33,
93
+ "Ġã": 34,
94
+ "##ã": 35,
95
+ "Ġý": 36,
96
+ "##ý": 37,
97
+ "Ġ_": 38,
98
+ "##_": 39,
99
+ "Ġä": 40,
100
+ "##ä": 41,
101
+ "Ġ`": 42,
102
+ "##`": 43,
103
+ "Ġþ": 44,
104
+ "##þ": 45,
105
+ "Ġđ": 46,
106
+ "##đ": 47,
107
+ "Ġò": 48,
108
+ "##ò": 49,
109
+ "Ġ9": 50,
110
+ "##9": 51,
111
+ "Ġú": 52,
112
+ "##ú": 53,
113
+ "Ġķ": 54,
114
+ "##ķ": 55,
115
+ "Ġĵ": 56,
116
+ "##ĵ": 57,
117
+ "ĠĘ": 58,
118
+ "##Ę": 59,
119
+ "Ġġ": 60,
120
+ "##ġ": 61,
121
+ "Ġ¤": 62,
122
+ "##¤": 63,
123
+ "ĠÐ": 64,
124
+ "##Ð": 65,
125
+ "Ġâ": 66,
126
+ "##â": 67,
127
+ "ĠĿ": 68,
128
+ "##Ŀ": 69,
129
+ "Ġß": 70,
130
+ "##ß": 71,
131
+ "ĠÀ": 72,
132
+ "##À": 73,
133
+ [": 74,
134
+ "##[": 75,
135
+ "Ġw": 76,
136
+ "##w": 77,
137
+ "Ġ|": 78,
138
+ "##|": 79,
139
+ "Ġī": 80,
140
+ "##ī": 81,
141
+ "Ġ$": 82,
142
+ "##$": 83,
143
+ "Ġì": 84,
144
+ "##ì": 85,
145
+ "Ġ£": 86,
146
+ "##£": 87,
147
+ "Ġ2": 88,
148
+ "##2": 89,
149
+ "ĠÏ": 90,
150
+ "##Ï": 91,
151
+ "Ġ«": 92,
152
+ "##«": 93,
153
+ "ĠN": 94,
154
+ "##N": 95,
155
+ "ĠF": 96,
156
+ "##F": 97,
157
+ "Ġ¼": 98,
158
+ "##¼": 99,
159
+ "Ġ-": 100,
160
+ "##-": 101,
161
+ "ĠĽ": 102,
162
+ "##Ľ": 103,
163
+ "Ġ½": 104,
164
+ "##½": 105,
165
+ "Ġð": 106,
166
+ "##ð": 107,
167
+ "Ġ©": 108,
168
+ "##©": 109,
169
+ "ĠÂ": 110,
170
+ "##Â": 111,
171
+ "Ġę": 112,
172
+ "##ę": 113,
173
+ "Ġc": 114,
174
+ "##c": 115,
175
+ "ĠA": 116,
176
+ "##A": 117,
177
+ "Ġo": 118,
178
+ "##o": 119,
179
+ "ĠÄ": 120,
180
+ "##Ä": 121,
181
+ "Ġ¸": 122,
182
+ "##¸": 123,
183
+ "ĠĪ": 124,
184
+ "##Ī": 125,
185
+ "Ġě": 126,
186
+ "##ě": 127,
187
+ "Ġñ": 128,
188
+ "##ñ": 129,
189
+ "Ġă": 130,
190
+ "##ă": 131,
191
+ "Ġn": 132,
192
+ "##n": 133,
193
+ "Ġæ": 134,
194
+ "##æ": 135,
195
+ "Ġ¨": 136,
196
+ "##¨": 137,
197
+ "ĠÚ": 138,
198
+ "##Ú": 139,
199
+ "Ġ1": 140,
200
+ "##1": 141,
201
+ "Ġç": 142,
202
+ "##ç": 143,
203
+ "Ġą": 144,
204
+ "##ą": 145,
205
+ "Ġb": 146,
206
+ "##b": 147,
207
+ "ĠM": 148,
208
+ "##M": 149,
209
+ "ĠÛ": 150,
210
+ "##Û": 151,
211
+ "Ġğ": 152,
212
+ "##ğ": 153,
213
+ "ĠĢ": 154,
214
+ "##Ģ": 155,
215
+ "Ġ#": 156,
216
+ "###": 157,
217
+ "Ġ\"": 158,
218
+ "##\"": 159,
219
+ "Ġi": 160,
220
+ "##i": 161,
221
+ "Ġı": 162,
222
+ "##ı": 163,
223
+ "ĠH": 164,
224
+ "##H": 165,
225
+ "ĠË": 166,
226
+ "##Ë": 167,
227
+ "Ġj": 168,
228
+ "##j": 169,
229
+ "ĠÌ": 170,
230
+ "##Ì": 171,
231
+ "ĠĎ": 172,
232
+ "##Ď": 173,
233
+ "ĠĐ": 174,
234
+ "##Đ": 175,
235
+ "ĠQ": 176,
236
+ "##Q": 177,
237
+ "ĠĆ": 178,
238
+ "##Ć": 179,
239
+ "ĠĶ": 180,
240
+ "##Ķ": 181,
241
+ "Ġ6": 182,
242
+ "##6": 183,
243
+ "ĠČ": 184,
244
+ "##Č": 185,
245
+ "Ġ7": 186,
246
+ "##7": 187,
247
+ "Ġć": 188,
248
+ "##ć": 189,
249
+ "Ġ=": 190,
250
+ "##=": 191,
251
+ "Ġĭ": 192,
252
+ "##ĭ": 193,
253
+ "Ġ´": 194,
254
+ "##´": 195,
255
+ "ĠJ": 196,
256
+ "##J": 197,
257
+ "ĠW": 198,
258
+ "##W": 199,
259
+ "ĠĴ": 200,
260
+ "##Ĵ": 201,
261
+ "Ġ+": 202,
262
+ "##+": 203,
263
+ "Ġ§": 204,
264
+ "##§": 205,
265
+ "Ġĩ": 206,
266
+ "##ĩ": 207,
267
+ "Ġk": 208,
268
+ "##k": 209,
269
+ "Ġ¢": 210,
270
+ "##¢": 211,
271
+ "Ġx": 212,
272
+ "##x": 213,
273
+ "ĠI": 214,
274
+ "##I": 215,
275
+ "Ġ³": 216,
276
+ "##³": 217,
277
+ "Ġ5": 218,
278
+ "##5": 219,
279
+ "Ġ¿": 220,
280
+ "##¿": 221,
281
+ "Ġï": 222,
282
+ "##ï": 223,
283
+ "ĠÁ": 224,
284
+ "##Á": 225,
285
+ "ĠĦ": 226,
286
+ "##Ħ": 227,
287
+ "ĠĔ": 228,
288
+ "##Ĕ": 229,
289
+ "ĠĒ": 230,
290
+ "##Ē": 231,
291
+ "ĠÔ": 232,
292
+ "##Ô": 233,
293
+ "Ġ°": 234,
294
+ "##°": 235,
295
+ "ĠĜ": 236,
296
+ "##Ĝ": 237,
297
+ "Ġ:": 238,
298
+ "##:": 239,
299
+ "ĠR": 240,
300
+ "##R": 241,
301
+ "Ġ0": 242,
302
+ "##0": 243,
303
+ "Ġz": 244,
304
+ "##z": 245,
305
+ "ĠĮ": 246,
306
+ "##Į": 247,
307
+ "Ġľ": 248,
308
+ "##ľ": 249,
309
+ "ĠT": 250,
310
+ "##T": 251,
311
+ "Ġh": 252,
312
+ "##h": 253,
313
+ "Ġf": 254,
314
+ "##f": 255,
315
+ "ĠG": 256,
316
+ "##G": 257,
317
+ "ĠÎ": 258,
318
+ "##Î": 259,
319
+ "Ġ¬": 260,
320
+ "##¬": 261,
321
+ "ĠØ": 262,
322
+ "##Ø": 263,
323
+ "ĠL": 264,
324
+ "##L": 265,
325
+ "Ġ¦": 266,
326
+ "##¦": 267,
327
+ "Ġ>": 268,
328
+ "##>": 269,
329
+ "ĠÞ": 270,
330
+ "##Þ": 271,
331
+ "Ġy": 272,
332
+ "##y": 273,
333
+ "ĠÊ": 274,
334
+ "##Ê": 275,
335
+ "Ġg": 276,
336
+ "##g": 277,
337
+ "Ġö": 278,
338
+ "##ö": 279,
339
+ "Ġł": 280,
340
+ "##ł": 281,
341
+ "Ġ.": 282,
342
+ "##.": 283,
343
+ "Ġď": 284,
344
+ "##ď": 285,
345
+ "ĠÜ": 286,
346
+ "##Ü": 287,
347
+ "ĠU": 288,
348
+ "##U": 289,
349
+ "Ġv": 290,
350
+ "##v": 291,
351
+ "Ġî": 292,
352
+ "##î": 293,
353
+ "Ġ/": 294,
354
+ "##/": 295,
355
+ "ĠĀ": 296,
356
+ "##Ā": 297,
357
+ "Ġm": 298,
358
+ "##m": 299,
359
+ "Ġu": 300,
360
+ "##u": 301,
361
+ "Ġ)": 302,
362
+ "##)": 303,
363
+ "Ġ¯": 304,
364
+ "##¯": 305,
365
+ "Ġê": 306,
366
+ "##ê": 307,
367
+ "Ġÿ": 308,
368
+ "##ÿ": 309,
369
+ "ĠĖ": 310,
370
+ "##Ė": 311,
371
+ "Ġİ": 312,
372
+ "##İ": 313,
373
+ "ĠC": 314,
374
+ "##C": 315,
375
+ "Ġù": 316,
376
+ "##ù": 317,
377
+ "Ġā": 318,
378
+ "##ā": 319,
379
+ "ĠD": 320,
380
+ "##D": 321,
381
+ "Ġ?": 322,
382
+ "##?": 323,
383
+ "ĠY": 324,
384
+ "##Y": 325,
385
+ "Ġė": 326,
386
+ "##ė": 327,
387
+ "ĠS": 328,
388
+ "##S": 329,
389
+ "Ġ(": 330,
390
+ "##(": 331,
391
+ "Ġ}": 332,
392
+ "##}": 333,
393
+ "Ġ¹": 334,
394
+ "##¹": 335,
395
+ "ĠÝ": 336,
396
+ "##Ý": 337,
397
+ "Ġp": 338,
398
+ "##p": 339,
399
+ "Ġü": 340,
400
+ "##ü": 341,
401
+ "ĠÇ": 342,
402
+ "##Ç": 343,
403
+ "Ġt": 344,
404
+ "##t": 345,
405
+ "ĠÅ": 346,
406
+ "##Å": 347,
407
+ "Ġċ": 348,
408
+ "##ċ": 349,
409
+ "Ġ;": 350,
410
+ "##;": 351,
411
+ "ĠÒ": 352,
412
+ "##Ò": 353,
413
+ "Ġû": 354,
414
+ "##û": 355,
415
+ "Ġl": 356,
416
+ "##l": 357,
417
+ "ĠE": 358,
418
+ "##E": 359,
419
+ "Ġí": 360,
420
+ "##í": 361,
421
+ "ĠĂ": 362,
422
+ "##Ă": 363,
423
+ "ĠĈ": 364,
424
+ "##Ĉ": 365,
425
+ "Ġŀ": 366,
426
+ "##ŀ": 367,
427
+ "Ġá": 368,
428
+ "##á": 369,
429
+ "ĠŃ": 370,
430
+ "##Ń": 371,
431
+ "Ġ®": 372,
432
+ "##®": 373,
433
+ "Ġ±": 374,
434
+ "##±": 375,
435
+ "Ġ¥": 376,
436
+ "##¥": 377,
437
+ "Ġd": 378,
438
+ "##d": 379,
439
+ "ĠÙ": 380,
440
+ "##Ù": 381,
441
+ "Ġ¡": 382,
442
+ "##¡": 383,
443
+ "ĠÈ": 384,
444
+ "##È": 385,
445
+ "Ġ!": 386,
446
+ "##!": 387,
447
+ "Ġ~": 388,
448
+ "##~": 389,
449
+ "Ġ3": 390,
450
+ "##3": 391,
451
+ "Ġ×": 392,
452
+ "##×": 393,
453
+ "Ġ÷": 394,
454
+ "##÷": 395,
455
+ "Ġe": 396,
456
+ "##e": 397,
457
+ "Ġ]": 398,
458
+ "##]": 399,
459
+ "Ġå": 400,
460
+ "##å": 401,
461
+ "ĠĊ": 402,
462
+ "##Ċ": 403,
463
+ "Ġô": 404,
464
+ "##ô": 405,
465
+ "ĠĹ": 406,
466
+ "##Ĺ": 407,
467
+ "ĠĞ": 408,
468
+ "##Ğ": 409,
469
+ "Ġĥ": 410,
470
+ "##ĥ": 411,
471
+ "ĠĚ": 412,
472
+ "##Ě": 413,
473
+ "Ġë": 414,
474
+ "##ë": 415,
475
+ "Ġ²": 416,
476
+ "##²": 417,
477
+ "Ġà": 418,
478
+ "##à": 419,
479
+ "ĠĨ": 420,
480
+ "##Ĩ": 421,
481
+ "ĠÑ": 422,
482
+ "##Ñ": 423,
483
+ "ĠV": 424,
484
+ "##V": 425,
485
+ "Ġµ": 426,
486
+ "##µ": 427,
487
+ "Ġĸ": 428,
488
+ "##ĸ": 429,
489
+ "Ġ»": 430,
490
+ "##»": 431,
491
+ "Ġõ": 432,
492
+ "##õ": 433,
493
+ "ĠĻ": 434,
494
+ "##Ļ": 435,
495
+ "Ġè": 436,
496
+ "##è": 437,
497
+ "ĠO": 438,
498
+ "##O": 439,
499
+ "Ġĉ": 440,
500
+ "##ĉ": 441,
501
+ "ĠÓ": 442,
502
+ "##Ó": 443,
503
+ "Ġø": 444,
504
+ "##ø": 445,
505
+ "Ġ·": 446,
506
+ "##·": 447,
507
+ "ĠK": 448,
508
+ "##K": 449,
509
+ "ĠÍ": 450,
510
+ "##Í": 451,
511
+ "Ġa": 452,
512
+ "##a": 453,
513
+ "ĠZ": 454,
514
+ "##Z": 455,
515
+ "ĠX": 456,
516
+ "##X": 457,
517
+ "ĠÕ": 458,
518
+ "##Õ": 459,
519
+ "Ġ@": 460,
520
+ "##@": 461,
521
+ "Ġ%": 462,
522
+ "##%": 463,
523
+ "Ġ*": 464,
524
+ "##*": 465,
525
+ "Ġs": 466,
526
+ "##s": 467,
527
+ "ĠP": 468,
528
+ "##P": 469,
529
+ "Ġħ": 470,
530
+ "##ħ": 471,
531
+ "Ġļ": 472,
532
+ "##ļ": 473,
533
+ "Ġé": 474,
534
+ "##é": 475,
535
+ "Ġē": 476,
536
+ "##ē": 477,
537
+ "ĠB": 478,
538
+ "##B": 479,
539
+ "Ġ{": 480,
540
+ "##{": 481,
541
+ "Ġ&": 482,
542
+ "##&": 483,
543
+ "ĠÉ": 484,
544
+ "##É": 485,
545
+ "Ġģ": 486,
546
+ "##ģ": 487,
547
+ "ĠIJ": 488,
548
+ "##IJ": 489,
549
+ "Ġ¾": 490,
550
+ "##¾": 491,
551
+ "ĠÖ": 492,
552
+ "##Ö": 493,
553
+ "Ġ¶": 494,
554
+ "##¶": 495,
555
+ "Ġó": 496,
556
+ "##ó": 497,
557
+ "Ġ\\": 498,
558
+ "##\\": 499,
559
+ "Ġĝ": 500,
560
+ "##ĝ": 501,
561
+ "ĠĤ": 502,
562
+ "##Ĥ": 503,
563
+ "Ġ8": 504,
564
+ "##8": 505,
565
+ "Ġq": 506,
566
+ "##q": 507,
567
+ "ĠÃ": 508,
568
+ "##Ã": 509,
569
+ "ĠÆ": 510,
570
+ "##Æ": 511,
571
+ "ĠĠ": 512,
572
+ "##Ġ": 513,
573
  "<|unk|>": 514,
574
  "##�": 515,
575
  "Ġsa": 516,
fw57Mmulti_Surprisal_thresholdB_16000/vocab.json CHANGED
The diff for this file is too large to render. See raw diff