codebyzeb commited on
Commit
208cdf5
·
verified ·
1 Parent(s): 04e3b97

Upload folder using huggingface_hub

Browse files
fw57Mmulti_Entropy_threshold_16000/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|padding|>",
5
+ "unk_token": "<|unk|>"
6
+ }
fw57Mmulti_Entropy_threshold_16000/stats.csv ADDED
The diff for this file is too large to render. See raw diff
 
fw57Mmulti_Entropy_threshold_16000/tokenizer.json ADDED
@@ -0,0 +1,1046 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "<|padding|>",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "<|endoftext|>",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 698,
26
+ "content": "<|unk|>",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ }
33
+ ],
34
+ "normalizer": null,
35
+ "pre_tokenizer": {
36
+ "type": "ByteLevel",
37
+ "add_prefix_space": true,
38
+ "trim_offsets": true,
39
+ "use_regex": true
40
+ },
41
+ "post_processor": {
42
+ "type": "ByteLevel",
43
+ "add_prefix_space": true,
44
+ "trim_offsets": true,
45
+ "use_regex": true
46
+ },
47
+ "decoder": {
48
+ "type": "ByteLevel",
49
+ "add_prefix_space": true,
50
+ "trim_offsets": true,
51
+ "use_regex": true
52
+ },
53
+ "model": {
54
+ "type": "WordPiece",
55
+ "unk_token": "<|unk|>",
56
+ "continuing_subword_prefix": "##",
57
+ "max_input_chars_per_word": 100,
58
+ "vocab": {
59
+ "<|padding|>": 0,
60
+ "<|endoftext|>": 1,
61
+ "Ġd": 2,
62
+ "d": 3,
63
+ "##d": 4,
64
+ "Ġĩ": 5,
65
+ "ĩ": 6,
66
+ "##ĩ": 7,
67
+ "Ġº": 8,
68
+ "º": 9,
69
+ "##º": 10,
70
+ "5": 11,
71
+ "##5": 12,
72
+ "Ġć": 13,
73
+ "ć": 14,
74
+ "##ć": 15,
75
+ "?": 16,
76
+ "##?": 17,
77
+ "ĠĮ": 18,
78
+ "Į": 19,
79
+ "##Į": 20,
80
+ "ĠV": 21,
81
+ "V": 22,
82
+ "##V": 23,
83
+ ",": 24,
84
+ "##,": 25,
85
+ "ĠĐ": 26,
86
+ "Đ": 27,
87
+ "##Đ": 28,
88
+ "ĠU": 29,
89
+ "U": 30,
90
+ "##U": 31,
91
+ "Ġä": 32,
92
+ "ä": 33,
93
+ "##ä": 34,
94
+ "`": 35,
95
+ "##`": 36,
96
+ "ĠÜ": 37,
97
+ "Ü": 38,
98
+ "##Ü": 39,
99
+ "Ġk": 40,
100
+ "k": 41,
101
+ "##k": 42,
102
+ "Ġâ": 43,
103
+ "â": 44,
104
+ "##â": 45,
105
+ "Ġb": 46,
106
+ "b": 47,
107
+ "##b": 48,
108
+ "@": 49,
109
+ "##@": 50,
110
+ "Ġæ": 51,
111
+ "æ": 52,
112
+ "##æ": 53,
113
+ "¾": 54,
114
+ "##¾": 55,
115
+ "Ġþ": 56,
116
+ "þ": 57,
117
+ "##þ": 58,
118
+ "Ġj": 59,
119
+ "j": 60,
120
+ "##j": 61,
121
+ "Ġf": 62,
122
+ "f": 63,
123
+ "##f": 64,
124
+ "Ġú": 65,
125
+ "ú": 66,
126
+ "##ú": 67,
127
+ "1": 68,
128
+ "##1": 69,
129
+ "Ġª": 70,
130
+ "ª": 71,
131
+ "##ª": 72,
132
+ "Ġm": 73,
133
+ "m": 74,
134
+ "##m": 75,
135
+ "$": 76,
136
+ "##$": 77,
137
+ "¦": 78,
138
+ "##¦": 79,
139
+ "2": 80,
140
+ "##2": 81,
141
+ "ĠIJ": 82,
142
+ "IJ": 83,
143
+ "##IJ": 84,
144
+ "¯": 85,
145
+ "##¯": 86,
146
+ "ĠD": 87,
147
+ "D": 88,
148
+ "##D": 89,
149
+ "Ġÿ": 90,
150
+ "ÿ": 91,
151
+ "##ÿ": 92,
152
+ "ĠĄ": 93,
153
+ "Ą": 94,
154
+ "##Ą": 95,
155
+ "}": 96,
156
+ "##}": 97,
157
+ "ĠĻ": 98,
158
+ "Ļ": 99,
159
+ "##Ļ": 100,
160
+ ".": 101,
161
+ "##.": 102,
162
+ "©": 103,
163
+ "##©": 104,
164
+ "ĠY": 105,
165
+ "Y": 106,
166
+ "##Y": 107,
167
+ "ĠĖ": 108,
168
+ "Ė": 109,
169
+ "##Ė": 110,
170
+ "Ġŀ": 111,
171
+ "ŀ": 112,
172
+ "##ŀ": 113,
173
+ "Ġę": 114,
174
+ "ę": 115,
175
+ "##ę": 116,
176
+ "0": 117,
177
+ "##0": 118,
178
+ "Ġò": 119,
179
+ "ò": 120,
180
+ "##ò": 121,
181
+ "Ġđ": 122,
182
+ "đ": 123,
183
+ "##đ": 124,
184
+ "ĠÐ": 125,
185
+ "Ð": 126,
186
+ "##Ð": 127,
187
+ "ĠØ": 128,
188
+ "Ø": 129,
189
+ "##Ø": 130,
190
+ "~": 131,
191
+ "##~": 132,
192
+ "Ġó": 133,
193
+ "ó": 134,
194
+ "##ó": 135,
195
+ "Ġē": 136,
196
+ "ē": 137,
197
+ "##ē": 138,
198
+ "ĠĹ": 139,
199
+ "Ĺ": 140,
200
+ "##Ĺ": 141,
201
+ "®": 142,
202
+ "##®": 143,
203
+ "ĠÛ": 144,
204
+ "Û": 145,
205
+ "##Û": 146,
206
+ "Ġċ": 147,
207
+ "ċ": 148,
208
+ "##ċ": 149,
209
+ "Ġð": 150,
210
+ "ð": 151,
211
+ "##ð": 152,
212
+ "Ġij": 153,
213
+ "ij": 154,
214
+ "##ij": 155,
215
+ "Ġs": 156,
216
+ "s": 157,
217
+ "##s": 158,
218
+ "Ġq": 159,
219
+ "q": 160,
220
+ "##q": 161,
221
+ "«": 162,
222
+ "##«": 163,
223
+ "ĠR": 164,
224
+ "R": 165,
225
+ "##R": 166,
226
+ "ĠM": 167,
227
+ "M": 168,
228
+ "##M": 169,
229
+ "²": 170,
230
+ "##²": 171,
231
+ "°": 172,
232
+ "##°": 173,
233
+ "Ġc": 174,
234
+ "c": 175,
235
+ "##c": 176,
236
+ "£": 177,
237
+ "##£": 178,
238
+ "¥": 179,
239
+ "##¥": 180,
240
+ "ĠC": 181,
241
+ "C": 182,
242
+ "##C": 183,
243
+ "ĠT": 184,
244
+ "T": 185,
245
+ "##T": 186,
246
+ "ĠÞ": 187,
247
+ "Þ": 188,
248
+ "##Þ": 189,
249
+ "Ġn": 190,
250
+ "n": 191,
251
+ "##n": 192,
252
+ "ĠĂ": 193,
253
+ "Ă": 194,
254
+ "##Ă": 195,
255
+ "Ġķ": 196,
256
+ "ķ": 197,
257
+ "##ķ": 198,
258
+ "¿": 199,
259
+ "##¿": 200,
260
+ "|": 201,
261
+ "##|": 202,
262
+ "ĠZ": 203,
263
+ "Z": 204,
264
+ "##Z": 205,
265
+ "Ġü": 206,
266
+ "ü": 207,
267
+ "##ü": 208,
268
+ "ĠĨ": 209,
269
+ "Ĩ": 210,
270
+ "##Ĩ": 211,
271
+ "Ġģ": 212,
272
+ "ģ": 213,
273
+ "##ģ": 214,
274
+ "ĠÌ": 215,
275
+ "Ì": 216,
276
+ "##Ì": 217,
277
+ "½": 218,
278
+ "##½": 219,
279
+ "»": 220,
280
+ "##»": 221,
281
+ "¸": 222,
282
+ "##¸": 223,
283
+ "ĠG": 224,
284
+ "G": 225,
285
+ "##G": 226,
286
+ "ĠÒ": 227,
287
+ "Ò": 228,
288
+ "##Ò": 229,
289
+ "×": 230,
290
+ "##×": 231,
291
+ "Ġă": 232,
292
+ "ă": 233,
293
+ "##ă": 234,
294
+ "ĠĪ": 235,
295
+ "Ī": 236,
296
+ "##Ī": 237,
297
+ "Ġî": 238,
298
+ "î": 239,
299
+ "##î": 240,
300
+ "Ġg": 241,
301
+ "g": 242,
302
+ "##g": 243,
303
+ "¤": 244,
304
+ "##¤": 245,
305
+ "ĠÇ": 246,
306
+ "Ç": 247,
307
+ "##Ç": 248,
308
+ "4": 249,
309
+ "##4": 250,
310
+ "´": 251,
311
+ "##´": 252,
312
+ "§": 253,
313
+ "##§": 254,
314
+ "ĠÈ": 255,
315
+ "È": 256,
316
+ "##È": 257,
317
+ "Ġè": 258,
318
+ "è": 259,
319
+ "##è": 260,
320
+ "Ġt": 261,
321
+ "t": 262,
322
+ "##t": 263,
323
+ "Ġā": 264,
324
+ "ā": 265,
325
+ "##ā": 266,
326
+ "{": 267,
327
+ "##{": 268,
328
+ "ĠA": 269,
329
+ "A": 270,
330
+ "##A": 271,
331
+ "ĠĢ": 272,
332
+ "Ģ": 273,
333
+ "##Ģ": 274,
334
+ "Ġļ": 275,
335
+ "ļ": 276,
336
+ "##ļ": 277,
337
+ "#": 278,
338
+ "###": 279,
339
+ "ĠI": 280,
340
+ "I": 281,
341
+ "##I": 282,
342
+ "ĠÕ": 283,
343
+ "Õ": 284,
344
+ "##Õ": 285,
345
+ "Ġá": 286,
346
+ "á": 287,
347
+ "##á": 288,
348
+ "±": 289,
349
+ "##±": 290,
350
+ "Ġğ": 291,
351
+ "ğ": 292,
352
+ "##ğ": 293,
353
+ "ĠÉ": 294,
354
+ "É": 295,
355
+ "##É": 296,
356
+ "ĠĆ": 297,
357
+ "Ć": 298,
358
+ "##Ć": 299,
359
+ "ĠĴ": 300,
360
+ "Ĵ": 301,
361
+ "##Ĵ": 302,
362
+ "Ġù": 303,
363
+ "ù": 304,
364
+ "##ù": 305,
365
+ "]": 306,
366
+ "##]": 307,
367
+ "Ġû": 308,
368
+ "û": 309,
369
+ "##û": 310,
370
+ "ĠÓ": 311,
371
+ "Ó": 312,
372
+ "##Ó": 313,
373
+ "ĠĜ": 314,
374
+ "Ĝ": 315,
375
+ "##Ĝ": 316,
376
+ "Ġy": 317,
377
+ "y": 318,
378
+ "##y": 319,
379
+ "³": 320,
380
+ "##³": 321,
381
+ "[": 322,
382
+ "##[": 323,
383
+ "Ġħ": 324,
384
+ "ħ": 325,
385
+ "##ħ": 326,
386
+ "Ġĸ": 327,
387
+ "ĸ": 328,
388
+ "##ĸ": 329,
389
+ "ĠŁ": 330,
390
+ "Ł": 331,
391
+ "##Ł": 332,
392
+ "Ġį": 333,
393
+ "į": 334,
394
+ "##į": 335,
395
+ "_": 336,
396
+ "##_": 337,
397
+ ":": 338,
398
+ "##:": 339,
399
+ "-": 340,
400
+ "##-": 341,
401
+ "ĠW": 342,
402
+ "W": 343,
403
+ "##W": 344,
404
+ "ĠÁ": 345,
405
+ "Á": 346,
406
+ "##Á": 347,
407
+ "Ġã": 348,
408
+ "ã": 349,
409
+ "##ã": 350,
410
+ "ĠÆ": 351,
411
+ "Æ": 352,
412
+ "##Æ": 353,
413
+ "ĠĚ": 354,
414
+ "Ě": 355,
415
+ "##Ě": 356,
416
+ "Ġĥ": 357,
417
+ "ĥ": 358,
418
+ "##ĥ": 359,
419
+ "¨": 360,
420
+ "##¨": 361,
421
+ "ĠL": 362,
422
+ "L": 363,
423
+ "##L": 364,
424
+ "Ġô": 365,
425
+ "ô": 366,
426
+ "##ô": 367,
427
+ "Ġĵ": 368,
428
+ "ĵ": 369,
429
+ "##ĵ": 370,
430
+ "ĠĦ": 371,
431
+ "Ħ": 372,
432
+ "##Ħ": 373,
433
+ "ĠÀ": 374,
434
+ "À": 375,
435
+ "##À": 376,
436
+ "ĠÎ": 377,
437
+ "Î": 378,
438
+ "##Î": 379,
439
+ "ĠĀ": 380,
440
+ "Ā": 381,
441
+ "##Ā": 382,
442
+ "ĠĘ": 383,
443
+ "Ę": 384,
444
+ "##Ę": 385,
445
+ "9": 386,
446
+ "##9": 387,
447
+ "ĠF": 388,
448
+ "F": 389,
449
+ "##F": 390,
450
+ "ĠĊ": 391,
451
+ "Ċ": 392,
452
+ "##Ċ": 393,
453
+ "ĠÄ": 394,
454
+ "Ä": 395,
455
+ "##Ä": 396,
456
+ "ĠE": 397,
457
+ "E": 398,
458
+ "##E": 399,
459
+ "¬": 400,
460
+ "##¬": 401,
461
+ "'": 402,
462
+ "##'": 403,
463
+ ">": 404,
464
+ "##>": 405,
465
+ "ĠX": 406,
466
+ "X": 407,
467
+ "##X": 408,
468
+ "Ġı": 409,
469
+ "ı": 410,
470
+ "##ı": 411,
471
+ "Ġď": 412,
472
+ "ď": 413,
473
+ "##ď": 414,
474
+ "ĠB": 415,
475
+ "B": 416,
476
+ "##B": 417,
477
+ "Ġą": 418,
478
+ "ą": 419,
479
+ "##ą": 420,
480
+ "ĠÃ": 421,
481
+ "Ã": 422,
482
+ "##Ã": 423,
483
+ "Ġo": 424,
484
+ "o": 425,
485
+ "##o": 426,
486
+ "¹": 427,
487
+ "##¹": 428,
488
+ "Ġa": 429,
489
+ "a": 430,
490
+ "##a": 431,
491
+ "Ġr": 432,
492
+ "r": 433,
493
+ "##r": 434,
494
+ "8": 435,
495
+ "##8": 436,
496
+ ")": 437,
497
+ "##)": 438,
498
+ ";": 439,
499
+ "##;": 440,
500
+ "ĠQ": 441,
501
+ "Q": 442,
502
+ "##Q": 443,
503
+ "Ġx": 444,
504
+ "x": 445,
505
+ "##x": 446,
506
+ "·": 447,
507
+ "##·": 448,
508
+ "ĠÏ": 449,
509
+ "Ï": 450,
510
+ "##Ï": 451,
511
+ "Ġë": 452,
512
+ "ë": 453,
513
+ "##ë": 454,
514
+ "ĠĿ": 455,
515
+ "Ŀ": 456,
516
+ "##Ŀ": 457,
517
+ "Ġö": 458,
518
+ "ö": 459,
519
+ "##ö": 460,
520
+ "ĠĔ": 461,
521
+ "Ĕ": 462,
522
+ "##Ĕ": 463,
523
+ "Ġç": 464,
524
+ "ç": 465,
525
+ "##ç": 466,
526
+ "Ġu": 467,
527
+ "u": 468,
528
+ "##u": 469,
529
+ "Ġľ": 470,
530
+ "ľ": 471,
531
+ "##ľ": 472,
532
+ "Ġé": 473,
533
+ "é": 474,
534
+ "##é": 475,
535
+ "Ġà": 476,
536
+ "à": 477,
537
+ "##à": 478,
538
+ "Ġñ": 479,
539
+ "ñ": 480,
540
+ "##ñ": 481,
541
+ "3": 482,
542
+ "##3": 483,
543
+ "Ġĉ": 484,
544
+ "ĉ": 485,
545
+ "##ĉ": 486,
546
+ "Ġł": 487,
547
+ "ł": 488,
548
+ "##ł": 489,
549
+ "Ġz": 490,
550
+ "z": 491,
551
+ "##z": 492,
552
+ "Ġí": 493,
553
+ "í": 494,
554
+ "##í": 495,
555
+ "Ġw": 496,
556
+ "w": 497,
557
+ "##w": 498,
558
+ "ĠĶ": 499,
559
+ "Ķ": 500,
560
+ "##Ķ": 501,
561
+ "ĠŃ": 502,
562
+ "Ń": 503,
563
+ "##Ń": 504,
564
+ "ĠÚ": 505,
565
+ "Ú": 506,
566
+ "##Ú": 507,
567
+ "+": 508,
568
+ "##+": 509,
569
+ "ĠÊ": 510,
570
+ "Ê": 511,
571
+ "##Ê": 512,
572
+ "Ġĕ": 513,
573
+ "ĕ": 514,
574
+ "##ĕ": 515,
575
+ "¼": 516,
576
+ "##¼": 517,
577
+ "ĠĎ": 518,
578
+ "Ď": 519,
579
+ "##Ď": 520,
580
+ "Ġė": 521,
581
+ "ė": 522,
582
+ "##ė": 523,
583
+ "ĠÅ": 524,
584
+ "Å": 525,
585
+ "##Å": 526,
586
+ "Ġß": 527,
587
+ "ß": 528,
588
+ "##ß": 529,
589
+ "ĠJ": 530,
590
+ "J": 531,
591
+ "##J": 532,
592
+ "Ġµ": 533,
593
+ "µ": 534,
594
+ "##µ": 535,
595
+ "ĠĬ": 536,
596
+ "Ĭ": 537,
597
+ "##Ĭ": 538,
598
+ "Ġý": 539,
599
+ "ý": 540,
600
+ "##ý": 541,
601
+ "=": 542,
602
+ "##=": 543,
603
+ "ĠÝ": 544,
604
+ "Ý": 545,
605
+ "##Ý": 546,
606
+ "Ġě": 547,
607
+ "ě": 548,
608
+ "##ě": 549,
609
+ "Ġč": 550,
610
+ "č": 551,
611
+ "##č": 552,
612
+ "ĠK": 553,
613
+ "K": 554,
614
+ "##K": 555,
615
+ "ĠO": 556,
616
+ "O": 557,
617
+ "##O": 558,
618
+ "ĠÑ": 559,
619
+ "Ñ": 560,
620
+ "##Ñ": 561,
621
+ "^": 562,
622
+ "##^": 563,
623
+ "*": 564,
624
+ "##*": 565,
625
+ "ĠĒ": 566,
626
+ "Ē": 567,
627
+ "##Ē": 568,
628
+ "!": 569,
629
+ "##!": 570,
630
+ "Ġĭ": 571,
631
+ "ĭ": 572,
632
+ "##ĭ": 573,
633
+ "ĠS": 574,
634
+ "S": 575,
635
+ "##S": 576,
636
+ "Ġİ": 577,
637
+ "İ": 578,
638
+ "##İ": 579,
639
+ "Ġø": 580,
640
+ "ø": 581,
641
+ "##ø": 582,
642
+ "ĠÍ": 583,
643
+ "Í": 584,
644
+ "##Í": 585,
645
+ "ĠH": 586,
646
+ "H": 587,
647
+ "##H": 588,
648
+ "Ġì": 589,
649
+ "ì": 590,
650
+ "##ì": 591,
651
+ "Ġe": 592,
652
+ "e": 593,
653
+ "##e": 594,
654
+ "¶": 595,
655
+ "##¶": 596,
656
+ "(": 597,
657
+ "##(": 598,
658
+ "Ġõ": 599,
659
+ "õ": 600,
660
+ "##õ": 601,
661
+ "ĠĈ": 602,
662
+ "Ĉ": 603,
663
+ "##Ĉ": 604,
664
+ "Ġī": 605,
665
+ "ī": 606,
666
+ "##ī": 607,
667
+ "Ġġ": 608,
668
+ "ġ": 609,
669
+ "##ġ": 610,
670
+ "/": 611,
671
+ "##/": 612,
672
+ "ĠÂ": 613,
673
+ "Â": 614,
674
+ "##Â": 615,
675
+ "Ġv": 616,
676
+ "v": 617,
677
+ "##v": 618,
678
+ "%": 619,
679
+ "##%": 620,
680
+ "ĠÙ": 621,
681
+ "Ù": 622,
682
+ "##Ù": 623,
683
+ "&": 624,
684
+ "##&": 625,
685
+ "ĠË": 626,
686
+ "Ë": 627,
687
+ "##Ë": 628,
688
+ "Ġh": 629,
689
+ "h": 630,
690
+ "##h": 631,
691
+ "Ġĝ": 632,
692
+ "ĝ": 633,
693
+ "##ĝ": 634,
694
+ "ĠÔ": 635,
695
+ "Ô": 636,
696
+ "##Ô": 637,
697
+ "Ġï": 638,
698
+ "ï": 639,
699
+ "##ï": 640,
700
+ "ĠP": 641,
701
+ "P": 642,
702
+ "##P": 643,
703
+ "ĠĤ": 644,
704
+ "Ĥ": 645,
705
+ "##Ĥ": 646,
706
+ "Ġp": 647,
707
+ "p": 648,
708
+ "##p": 649,
709
+ "Ġ": 650,
710
+ "##Ġ": 651,
711
+ "\\": 652,
712
+ "##\\": 653,
713
+ "ĠÖ": 654,
714
+ "Ö": 655,
715
+ "##Ö": 656,
716
+ "<": 657,
717
+ "##<": 658,
718
+ "¢": 659,
719
+ "##¢": 660,
720
+ "Ġå": 661,
721
+ "å": 662,
722
+ "##å": 663,
723
+ "ĠČ": 664,
724
+ "Č": 665,
725
+ "##Č": 666,
726
+ "Ġê": 667,
727
+ "ê": 668,
728
+ "##ê": 669,
729
+ "ĠN": 670,
730
+ "N": 671,
731
+ "##N": 672,
732
+ "7": 673,
733
+ "##7": 674,
734
+ "ĠĞ": 675,
735
+ "Ğ": 676,
736
+ "##Ğ": 677,
737
+ "Ġĺ": 678,
738
+ "ĺ": 679,
739
+ "##ĺ": 680,
740
+ "\"": 681,
741
+ "##\"": 682,
742
+ "¡": 683,
743
+ "##¡": 684,
744
+ "Ġl": 685,
745
+ "l": 686,
746
+ "##l": 687,
747
+ "ĠĽ": 688,
748
+ "Ľ": 689,
749
+ "##Ľ": 690,
750
+ "Ġi": 691,
751
+ "i": 692,
752
+ "##i": 693,
753
+ "6": 694,
754
+ "##6": 695,
755
+ "÷": 696,
756
+ "##÷": 697,
757
+ "<|unk|>": 698,
758
+ "##ng": 699,
759
+ "##pi": 700,
760
+ "##ó": 701,
761
+ "##ħ": 702,
762
+ "##in": 703,
763
+ "##é": 704,
764
+ "##ga": 705,
765
+ "##ÃŃ": 706,
766
+ "##ku": 707,
767
+ "##an": 708,
768
+ "##ah": 709,
769
+ "##as": 710,
770
+ "##ºŃ": 711,
771
+ "##bo": 712,
772
+ "##ka": 713,
773
+ "##iÃ": 714,
774
+ "##og": 715,
775
+ "##ag": 716,
776
+ "##sa": 717,
777
+ "##ik": 718,
778
+ "##de": 719,
779
+ "##ad": 720,
780
+ "##asa": 721,
781
+ "##mi": 722,
782
+ "##al": 723,
783
+ "##³w": 724,
784
+ "##nt": 725,
785
+ "##ÙĦ": 726,
786
+ "##ibo": 727,
787
+ "##ro": 728,
788
+ "##ak": 729,
789
+ "##os": 730,
790
+ "##id": 731,
791
+ "##ĢĻ": 732,
792
+ "##§h": 733,
793
+ "##ĊĊ": 734,
794
+ "##ig": 735,
795
+ "##00": 736,
796
+ ":/": 737,
797
+ "##ir": 738,
798
+ "##ib": 739,
799
+ "##op": 740,
800
+ "##§Ã": 741,
801
+ "##ab": 742,
802
+ "##la": 743,
803
+ "##ul": 744,
804
+ "##ż": 745,
805
+ "##es": 746,
806
+ "##lag": 747,
807
+ "##na": 748,
808
+ "##da": 749,
809
+ "##ina": 750,
810
+ "##ta": 751,
811
+ "##ac": 752,
812
+ "##ar": 753,
813
+ "##ep": 754,
814
+ "##Ãł": 755,
815
+ "##tro": 756,
816
+ "##en": 757,
817
+ "##tz": 758,
818
+ "##§a": 759,
819
+ "##©s": 760,
820
+ "##á": 761,
821
+ "##pan": 762,
822
+ "##em": 763,
823
+ "##¹´": 764,
824
+ "##it": 765,
825
+ "##ä": 766,
826
+ "##lo": 767,
827
+ "##ala": 768,
828
+ "##ba": 769,
829
+ "##te": 770,
830
+ "##//": 771,
831
+ "##aka": 772,
832
+ "##ri": 773,
833
+ "##hi": 774,
834
+ "##at": 775,
835
+ "##ti": 776,
836
+ "##¼j": 777,
837
+ "##ö": 778,
838
+ "##ra": 779,
839
+ "##ang": 780,
840
+ "##ten": 781,
841
+ "##ahi": 782,
842
+ "##ko": 783,
843
+ "##pa": 784,
844
+ "##oz": 785,
845
+ "##un": 786,
846
+ "##ı": 787,
847
+ "##lu": 788,
848
+ "##sar": 789,
849
+ "##er": 790,
850
+ "##ngan": 791,
851
+ "##zten": 792,
852
+ "##im": 793,
853
+ "##re": 794,
854
+ "##mu": 795,
855
+ "##to": 796,
856
+ "##eh": 797,
857
+ "##tr": 798,
858
+ "##aba": 799,
859
+ "##ĦØ": 800,
860
+ "##zt": 801,
861
+ "##gs": 802,
862
+ "##ts": 803,
863
+ "##gsa": 804,
864
+ "##rr": 805,
865
+ "##him": 806,
866
+ "##den": 807,
867
+ "##ngang": 808,
868
+ "##za": 809,
869
+ "##Ä¡": 810,
870
+ "##ao": 811,
871
+ "##asad": 812,
872
+ "##alag": 813,
873
+ "##rt": 814,
874
+ "##dp": 815,
875
+ "##ire": 816,
876
+ "##ek": 817,
877
+ "##ió": 818,
878
+ "##az": 819,
879
+ "##et": 820,
880
+ "##á»": 821,
881
+ "##np": 822,
882
+ "##err": 823,
883
+ "##ki": 824,
884
+ "##ni": 825,
885
+ "##il": 826,
886
+ "##ho": 827,
887
+ "##sad": 828,
888
+ "##gan": 829,
889
+ "##on": 830,
890
+ "##bi": 831,
891
+ "##kar": 832,
892
+ "##ĪÙ": 833,
893
+ "##nd": 834,
894
+ "##³n": 835,
895
+ "##¶m": 836,
896
+ "##ahin": 837,
897
+ "##aci": 838,
898
+ "##ue": 839,
899
+ "##or": 840,
900
+ "##rri": 841,
901
+ "##ny": 842,
902
+ "##od": 843,
903
+ "##aga": 844,
904
+ "##¶z": 845,
905
+ "##ert": 846,
906
+ "##ou": 847,
907
+ "##is": 848,
908
+ "##dl": 849,
909
+ "an": 850,
910
+ "##bab": 851,
911
+ "##ci": 852,
912
+ "##Ñı": 853,
913
+ "##¡s": 854,
914
+ "##iy": 855,
915
+ "##ren": 856,
916
+ "##±Å": 857,
917
+ "##gw": 858,
918
+ "##jo": 859,
919
+ "##©g": 860,
920
+ "##erri": 861,
921
+ "##sÃ": 862,
922
+ "Ġda": 863,
923
+ "##nai": 864,
924
+ "##oa": 865,
925
+ "##big": 866,
926
+ "##ÙĦØ": 867,
927
+ "##kÃ": 868,
928
+ "##ÅŁ": 869,
929
+ "##ch": 870,
930
+ "##ros": 871,
931
+ "##do": 872,
932
+ "##el": 873,
933
+ "20": 874,
934
+ "##ĊĊĊĊ": 875,
935
+ "##eka": 876,
936
+ "##ĭi": 877,
937
+ "##..": 878,
938
+ "##iren": 879,
939
+ "##tu": 880,
940
+ "##̬": 881,
941
+ "##ags": 882,
942
+ "##dla": 883,
943
+ "##aw": 884,
944
+ "##tod": 885,
945
+ "##iz": 886,
946
+ "##uk": 887,
947
+ "##¡r": 888,
948
+ "##li": 889,
949
+ "##kk": 890,
950
+ "##ijĺ": 891,
951
+ "Ġsa": 892,
952
+ "##¤n": 893,
953
+ "##agat": 894,
954
+ "##hin": 895,
955
+ "##br": 896,
956
+ "##ila": 897,
957
+ "##rts": 898,
958
+ "##ako": 899,
959
+ "##ur": 900,
960
+ "##le": 901,
961
+ "##ai": 902,
962
+ "##ªu": 903,
963
+ "##Ã¥": 904,
964
+ "##¡g": 905,
965
+ "##ay": 906,
966
+ "##ke": 907,
967
+ "##adp": 908,
968
+ "##bag": 909,
969
+ "##¼jo": 910,
970
+ "##ia": 911,
971
+ "##ale": 912,
972
+ "##ºŃt": 913,
973
+ "##ha": 914,
974
+ "##me": 915,
975
+ "##alo": 916,
976
+ "##ug": 917,
977
+ "##po": 918,
978
+ "##dto": 919,
979
+ "##au": 920,
980
+ "##wa": 921,
981
+ "##ie": 922,
982
+ "##bot": 923,
983
+ "##ma": 924,
984
+ "##inai": 925,
985
+ "##gang": 926,
986
+ "##º©": 927,
987
+ "##gi": 928,
988
+ "ĊĊ": 929,
989
+ "##epa": 930,
990
+ "##gat": 931,
991
+ "##ong": 932,
992
+ "##tso": 933,
993
+ "##erts": 934,
994
+ "##rÃ": 935,
995
+ "##ez": 936,
996
+ "##êu": 937,
997
+ "##yo": 938,
998
+ "##»į": 939,
999
+ "##um": 940,
1000
+ "##ss": 941,
1001
+ "##Ńpo": 942,
1002
+ "##am": 943,
1003
+ "##ŁÄ": 944,
1004
+ "##ae": 945,
1005
+ "##oga": 946,
1006
+ "##kö": 947,
1007
+ "##mm": 948,
1008
+ "##ero": 949,
1009
+ "##ll": 950,
1010
+ "##mb": 951,
1011
+ "##us": 952,
1012
+ "##tt": 953,
1013
+ "##ب": 954,
1014
+ "##tÃ": 955,
1015
+ "ha": 956,
1016
+ "##ua": 957,
1017
+ "##xx": 958,
1018
+ "Ġkina": 959,
1019
+ "##alags": 960,
1020
+ "##mÃ": 961,
1021
+ "##zj": 962,
1022
+ "##eg": 963,
1023
+ "##si": 964,
1024
+ "##abo": 965,
1025
+ "##ui": 966,
1026
+ "##oÃ": 967,
1027
+ "##ali": 968,
1028
+ "##ate": 969,
1029
+ "##ég": 970,
1030
+ "##eme": 971,
1031
+ "##¿t": 972,
1032
+ "##ihan": 973,
1033
+ "##iha": 974,
1034
+ "##sh": 975,
1035
+ "##nda": 976,
1036
+ "##ing": 977,
1037
+ "##sy": 978,
1038
+ "##±z": 979,
1039
+ "##nh": 980,
1040
+ "##ebi": 981,
1041
+ "##hÃ": 982,
1042
+ "##akar": 983,
1043
+ "##gt": 984
1044
+ }
1045
+ }
1046
+ }
fw57Mmulti_Entropy_threshold_16000/tokenizer_config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<|padding|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<|endoftext|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "698": {
21
+ "content": "<|unk|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ }
28
+ },
29
+ "bos_token": "<|endoftext|>",
30
+ "clean_up_tokenization_spaces": false,
31
+ "eos_token": "<|endoftext|>",
32
+ "extra_special_tokens": {},
33
+ "model_max_length": 1000000000000000019884624838656,
34
+ "pad_token": "<|padding|>",
35
+ "tokenizer_class": "PreTrainedTokenizer",
36
+ "unk_token": "<|unk|>"
37
+ }
fw57Mmulti_Entropy_threshold_16000/vocab.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<|padding|>": 0, "<|endoftext|>": 1, "\u0120d": 2, "d": 3, "##d": 4, "\u0120\u0129": 5, "\u0129": 6, "##\u0129": 7, "\u0120\u00ba": 8, "\u00ba": 9, "##\u00ba": 10, "5": 11, "##5": 12, "\u0120\u0107": 13, "\u0107": 14, "##\u0107": 15, "?": 16, "##?": 17, "\u0120\u012e": 18, "\u012e": 19, "##\u012e": 20, "\u0120V": 21, "V": 22, "##V": 23, ",": 24, "##,": 25, "\u0120\u0110": 26, "\u0110": 27, "##\u0110": 28, "\u0120U": 29, "U": 30, "##U": 31, "\u0120\u00e4": 32, "\u00e4": 33, "##\u00e4": 34, "`": 35, "##`": 36, "\u0120\u00dc": 37, "\u00dc": 38, "##\u00dc": 39, "\u0120k": 40, "k": 41, "##k": 42, "\u0120\u00e2": 43, "\u00e2": 44, "##\u00e2": 45, "\u0120b": 46, "b": 47, "##b": 48, "@": 49, "##@": 50, "\u0120\u00e6": 51, "\u00e6": 52, "##\u00e6": 53, "\u00be": 54, "##\u00be": 55, "\u0120\u00fe": 56, "\u00fe": 57, "##\u00fe": 58, "\u0120j": 59, "j": 60, "##j": 61, "\u0120f": 62, "f": 63, "##f": 64, "\u0120\u00fa": 65, "\u00fa": 66, "##\u00fa": 67, "1": 68, "##1": 69, "\u0120\u00aa": 70, "\u00aa": 71, "##\u00aa": 72, "\u0120m": 73, "m": 74, "##m": 75, "$": 76, "##$": 77, "\u00a6": 78, "##\u00a6": 79, "2": 80, "##2": 81, "\u0120\u0132": 82, "\u0132": 83, "##\u0132": 84, "\u00af": 85, "##\u00af": 86, "\u0120D": 87, "D": 88, "##D": 89, "\u0120\u00ff": 90, "\u00ff": 91, "##\u00ff": 92, "\u0120\u0104": 93, "\u0104": 94, "##\u0104": 95, "}": 96, "##}": 97, "\u0120\u013b": 98, "\u013b": 99, "##\u013b": 100, ".": 101, "##.": 102, "\u00a9": 103, "##\u00a9": 104, "\u0120Y": 105, "Y": 106, "##Y": 107, "\u0120\u0116": 108, "\u0116": 109, "##\u0116": 110, "\u0120\u0140": 111, "\u0140": 112, "##\u0140": 113, "\u0120\u0119": 114, "\u0119": 115, "##\u0119": 116, "0": 117, "##0": 118, "\u0120\u00f2": 119, "\u00f2": 120, "##\u00f2": 121, "\u0120\u0111": 122, "\u0111": 123, "##\u0111": 124, "\u0120\u00d0": 125, "\u00d0": 126, "##\u00d0": 127, "\u0120\u00d8": 128, "\u00d8": 129, "##\u00d8": 130, "~": 131, "##~": 132, "\u0120\u00f3": 133, "\u00f3": 134, "##\u00f3": 135, "\u0120\u0113": 136, "\u0113": 137, "##\u0113": 138, "\u0120\u0139": 139, "\u0139": 140, "##\u0139": 141, "\u00ae": 142, "##\u00ae": 143, "\u0120\u00db": 144, "\u00db": 145, "##\u00db": 146, "\u0120\u010b": 147, "\u010b": 148, "##\u010b": 149, "\u0120\u00f0": 150, "\u00f0": 151, "##\u00f0": 152, "\u0120\u0133": 153, "\u0133": 154, "##\u0133": 155, "\u0120s": 156, "s": 157, "##s": 158, "\u0120q": 159, "q": 160, "##q": 161, "\u00ab": 162, "##\u00ab": 163, "\u0120R": 164, "R": 165, "##R": 166, "\u0120M": 167, "M": 168, "##M": 169, "\u00b2": 170, "##\u00b2": 171, "\u00b0": 172, "##\u00b0": 173, "\u0120c": 174, "c": 175, "##c": 176, "\u00a3": 177, "##\u00a3": 178, "\u00a5": 179, "##\u00a5": 180, "\u0120C": 181, "C": 182, "##C": 183, "\u0120T": 184, "T": 185, "##T": 186, "\u0120\u00de": 187, "\u00de": 188, "##\u00de": 189, "\u0120n": 190, "n": 191, "##n": 192, "\u0120\u0102": 193, "\u0102": 194, "##\u0102": 195, "\u0120\u0137": 196, "\u0137": 197, "##\u0137": 198, "\u00bf": 199, "##\u00bf": 200, "|": 201, "##|": 202, "\u0120Z": 203, "Z": 204, "##Z": 205, "\u0120\u00fc": 206, "\u00fc": 207, "##\u00fc": 208, "\u0120\u0128": 209, "\u0128": 210, "##\u0128": 211, "\u0120\u0123": 212, "\u0123": 213, "##\u0123": 214, "\u0120\u00cc": 215, "\u00cc": 216, "##\u00cc": 217, "\u00bd": 218, "##\u00bd": 219, "\u00bb": 220, "##\u00bb": 221, "\u00b8": 222, "##\u00b8": 223, "\u0120G": 224, "G": 225, "##G": 226, "\u0120\u00d2": 227, "\u00d2": 228, "##\u00d2": 229, "\u00d7": 230, "##\u00d7": 231, "\u0120\u0103": 232, "\u0103": 233, "##\u0103": 234, "\u0120\u012a": 235, "\u012a": 236, "##\u012a": 237, "\u0120\u00ee": 238, "\u00ee": 239, "##\u00ee": 240, "\u0120g": 241, "g": 242, "##g": 243, "\u00a4": 244, "##\u00a4": 245, "\u0120\u00c7": 246, "\u00c7": 247, "##\u00c7": 248, "4": 249, "##4": 250, "\u00b4": 251, "##\u00b4": 252, "\u00a7": 253, "##\u00a7": 254, "\u0120\u00c8": 255, "\u00c8": 256, "##\u00c8": 257, "\u0120\u00e8": 258, "\u00e8": 259, "##\u00e8": 260, "\u0120t": 261, "t": 262, "##t": 263, "\u0120\u0101": 264, "\u0101": 265, "##\u0101": 266, "{": 267, "##{": 268, "\u0120A": 269, "A": 270, "##A": 271, "\u0120\u0122": 272, "\u0122": 273, "##\u0122": 274, "\u0120\u013c": 275, "\u013c": 276, "##\u013c": 277, "#": 278, "###": 279, "\u0120I": 280, "I": 281, "##I": 282, "\u0120\u00d5": 283, "\u00d5": 284, "##\u00d5": 285, "\u0120\u00e1": 286, "\u00e1": 287, "##\u00e1": 288, "\u00b1": 289, "##\u00b1": 290, "\u0120\u011f": 291, "\u011f": 292, "##\u011f": 293, "\u0120\u00c9": 294, "\u00c9": 295, "##\u00c9": 296, "\u0120\u0106": 297, "\u0106": 298, "##\u0106": 299, "\u0120\u0134": 300, "\u0134": 301, "##\u0134": 302, "\u0120\u00f9": 303, "\u00f9": 304, "##\u00f9": 305, "]": 306, "##]": 307, "\u0120\u00fb": 308, "\u00fb": 309, "##\u00fb": 310, "\u0120\u00d3": 311, "\u00d3": 312, "##\u00d3": 313, "\u0120\u011c": 314, "\u011c": 315, "##\u011c": 316, "\u0120y": 317, "y": 318, "##y": 319, "\u00b3": 320, "##\u00b3": 321, "[": 322, "##[": 323, "\u0120\u0127": 324, "\u0127": 325, "##\u0127": 326, "\u0120\u0138": 327, "\u0138": 328, "##\u0138": 329, "\u0120\u0141": 330, "\u0141": 331, "##\u0141": 332, "\u0120\u012f": 333, "\u012f": 334, "##\u012f": 335, "_": 336, "##_": 337, ":": 338, "##:": 339, "-": 340, "##-": 341, "\u0120W": 342, "W": 343, "##W": 344, "\u0120\u00c1": 345, "\u00c1": 346, "##\u00c1": 347, "\u0120\u00e3": 348, "\u00e3": 349, "##\u00e3": 350, "\u0120\u00c6": 351, "\u00c6": 352, "##\u00c6": 353, "\u0120\u011a": 354, "\u011a": 355, "##\u011a": 356, "\u0120\u0125": 357, "\u0125": 358, "##\u0125": 359, "\u00a8": 360, "##\u00a8": 361, "\u0120L": 362, "L": 363, "##L": 364, "\u0120\u00f4": 365, "\u00f4": 366, "##\u00f4": 367, "\u0120\u0135": 368, "\u0135": 369, "##\u0135": 370, "\u0120\u0126": 371, "\u0126": 372, "##\u0126": 373, "\u0120\u00c0": 374, "\u00c0": 375, "##\u00c0": 376, "\u0120\u00ce": 377, "\u00ce": 378, "##\u00ce": 379, "\u0120\u0100": 380, "\u0100": 381, "##\u0100": 382, "\u0120\u0118": 383, "\u0118": 384, "##\u0118": 385, "9": 386, "##9": 387, "\u0120F": 388, "F": 389, "##F": 390, "\u0120\u010a": 391, "\u010a": 392, "##\u010a": 393, "\u0120\u00c4": 394, "\u00c4": 395, "##\u00c4": 396, "\u0120E": 397, "E": 398, "##E": 399, "\u00ac": 400, "##\u00ac": 401, "'": 402, "##'": 403, ">": 404, "##>": 405, "\u0120X": 406, "X": 407, "##X": 408, "\u0120\u0131": 409, "\u0131": 410, "##\u0131": 411, "\u0120\u010f": 412, "\u010f": 413, "##\u010f": 414, "\u0120B": 415, "B": 416, "##B": 417, "\u0120\u0105": 418, "\u0105": 419, "##\u0105": 420, "\u0120\u00c3": 421, "\u00c3": 422, "##\u00c3": 423, "\u0120o": 424, "o": 425, "##o": 426, "\u00b9": 427, "##\u00b9": 428, "\u0120a": 429, "a": 430, "##a": 431, "\u0120r": 432, "r": 433, "##r": 434, "8": 435, "##8": 436, ")": 437, "##)": 438, ";": 439, "##;": 440, "\u0120Q": 441, "Q": 442, "##Q": 443, "\u0120x": 444, "x": 445, "##x": 446, "\u00b7": 447, "##\u00b7": 448, "\u0120\u00cf": 449, "\u00cf": 450, "##\u00cf": 451, "\u0120\u00eb": 452, "\u00eb": 453, "##\u00eb": 454, "\u0120\u013f": 455, "\u013f": 456, "##\u013f": 457, "\u0120\u00f6": 458, "\u00f6": 459, "##\u00f6": 460, "\u0120\u0114": 461, "\u0114": 462, "##\u0114": 463, "\u0120\u00e7": 464, "\u00e7": 465, "##\u00e7": 466, "\u0120u": 467, "u": 468, "##u": 469, "\u0120\u013e": 470, "\u013e": 471, "##\u013e": 472, "\u0120\u00e9": 473, "\u00e9": 474, "##\u00e9": 475, "\u0120\u00e0": 476, "\u00e0": 477, "##\u00e0": 478, "\u0120\u00f1": 479, "\u00f1": 480, "##\u00f1": 481, "3": 482, "##3": 483, "\u0120\u0109": 484, "\u0109": 485, "##\u0109": 486, "\u0120\u0142": 487, "\u0142": 488, "##\u0142": 489, "\u0120z": 490, "z": 491, "##z": 492, "\u0120\u00ed": 493, "\u00ed": 494, "##\u00ed": 495, "\u0120w": 496, "w": 497, "##w": 498, "\u0120\u0136": 499, "\u0136": 500, "##\u0136": 501, "\u0120\u0143": 502, "\u0143": 503, "##\u0143": 504, "\u0120\u00da": 505, "\u00da": 506, "##\u00da": 507, "+": 508, "##+": 509, "\u0120\u00ca": 510, "\u00ca": 511, "##\u00ca": 512, "\u0120\u0115": 513, "\u0115": 514, "##\u0115": 515, "\u00bc": 516, "##\u00bc": 517, "\u0120\u010e": 518, "\u010e": 519, "##\u010e": 520, "\u0120\u0117": 521, "\u0117": 522, "##\u0117": 523, "\u0120\u00c5": 524, "\u00c5": 525, "##\u00c5": 526, "\u0120\u00df": 527, "\u00df": 528, "##\u00df": 529, "\u0120J": 530, "J": 531, "##J": 532, "\u0120\u00b5": 533, "\u00b5": 534, "##\u00b5": 535, "\u0120\u012c": 536, "\u012c": 537, "##\u012c": 538, "\u0120\u00fd": 539, "\u00fd": 540, "##\u00fd": 541, "=": 542, "##=": 543, "\u0120\u00dd": 544, "\u00dd": 545, "##\u00dd": 546, "\u0120\u011b": 547, "\u011b": 548, "##\u011b": 549, "\u0120\u010d": 550, "\u010d": 551, "##\u010d": 552, "\u0120K": 553, "K": 554, "##K": 555, "\u0120O": 556, "O": 557, "##O": 558, "\u0120\u00d1": 559, "\u00d1": 560, "##\u00d1": 561, "^": 562, "##^": 563, "*": 564, "##*": 565, "\u0120\u0112": 566, "\u0112": 567, "##\u0112": 568, "!": 569, "##!": 570, "\u0120\u012d": 571, "\u012d": 572, "##\u012d": 573, "\u0120S": 574, "S": 575, "##S": 576, "\u0120\u0130": 577, "\u0130": 578, "##\u0130": 579, "\u0120\u00f8": 580, "\u00f8": 581, "##\u00f8": 582, "\u0120\u00cd": 583, "\u00cd": 584, "##\u00cd": 585, "\u0120H": 586, "H": 587, "##H": 588, "\u0120\u00ec": 589, "\u00ec": 590, "##\u00ec": 591, "\u0120e": 592, "e": 593, "##e": 594, "\u00b6": 595, "##\u00b6": 596, "(": 597, "##(": 598, "\u0120\u00f5": 599, "\u00f5": 600, "##\u00f5": 601, "\u0120\u0108": 602, "\u0108": 603, "##\u0108": 604, "\u0120\u012b": 605, "\u012b": 606, "##\u012b": 607, "\u0120\u0121": 608, "\u0121": 609, "##\u0121": 610, "/": 611, "##/": 612, "\u0120\u00c2": 613, "\u00c2": 614, "##\u00c2": 615, "\u0120v": 616, "v": 617, "##v": 618, "%": 619, "##%": 620, "\u0120\u00d9": 621, "\u00d9": 622, "##\u00d9": 623, "&": 624, "##&": 625, "\u0120\u00cb": 626, "\u00cb": 627, "##\u00cb": 628, "\u0120h": 629, "h": 630, "##h": 631, "\u0120\u011d": 632, "\u011d": 633, "##\u011d": 634, "\u0120\u00d4": 635, "\u00d4": 636, "##\u00d4": 637, "\u0120\u00ef": 638, "\u00ef": 639, "##\u00ef": 640, "\u0120P": 641, "P": 642, "##P": 643, "\u0120\u0124": 644, "\u0124": 645, "##\u0124": 646, "\u0120p": 647, "p": 648, "##p": 649, "\u0120": 650, "##\u0120": 651, "\\": 652, "##\\": 653, "\u0120\u00d6": 654, "\u00d6": 655, "##\u00d6": 656, "<": 657, "##<": 658, "\u00a2": 659, "##\u00a2": 660, "\u0120\u00e5": 661, "\u00e5": 662, "##\u00e5": 663, "\u0120\u010c": 664, "\u010c": 665, "##\u010c": 666, "\u0120\u00ea": 667, "\u00ea": 668, "##\u00ea": 669, "\u0120N": 670, "N": 671, "##N": 672, "7": 673, "##7": 674, "\u0120\u011e": 675, "\u011e": 676, "##\u011e": 677, "\u0120\u013a": 678, "\u013a": 679, "##\u013a": 680, "\"": 681, "##\"": 682, "\u00a1": 683, "##\u00a1": 684, "\u0120l": 685, "l": 686, "##l": 687, "\u0120\u013d": 688, "\u013d": 689, "##\u013d": 690, "\u0120i": 691, "i": 692, "##i": 693, "6": 694, "##6": 695, "\u00f7": 696, "##\u00f7": 697, "<|unk|>": 698, "##ng": 699, "##pi": 700, "##\u00c3\u00b3": 701, "##\u00c4\u00a7": 702, "##in": 703, "##\u00c3\u00a9": 704, "##ga": 705, "##\u00c3\u0143": 706, "##ku": 707, "##an": 708, "##ah": 709, "##as": 710, "##\u00ba\u0143": 711, "##bo": 712, "##ka": 713, "##i\u00c3": 714, "##og": 715, "##ag": 716, "##sa": 717, "##ik": 718, "##de": 719, "##ad": 720, "##asa": 721, "##mi": 722, "##al": 723, "##\u00b3w": 724, "##nt": 725, "##\u00d9\u0126": 726, "##ibo": 727, "##ro": 728, "##ak": 729, "##os": 730, "##id": 731, "##\u0122\u013b": 732, "##\u00a7h": 733, "##\u010a\u010a": 734, "##ig": 735, "##00": 736, ":/": 737, "##ir": 738, "##ib": 739, "##op": 740, "##\u00a7\u00c3": 741, "##ab": 742, "##la": 743, "##ul": 744, "##\u00c5\u00bc": 745, "##es": 746, "##lag": 747, "##na": 748, "##da": 749, "##ina": 750, "##ta": 751, "##ac": 752, "##ar": 753, "##ep": 754, "##\u00c3\u0142": 755, "##tro": 756, "##en": 757, "##tz": 758, "##\u00a7a": 759, "##\u00a9s": 760, "##\u00c3\u00a1": 761, "##pan": 762, "##em": 763, "##\u00b9\u00b4": 764, "##it": 765, "##\u00c3\u00a4": 766, "##lo": 767, "##ala": 768, "##ba": 769, "##te": 770, "##//": 771, "##aka": 772, "##ri": 773, "##hi": 774, "##at": 775, "##ti": 776, "##\u00bcj": 777, "##\u00c3\u00b6": 778, "##ra": 779, "##ang": 780, "##ten": 781, "##ahi": 782, "##ko": 783, "##pa": 784, "##oz": 785, "##un": 786, "##\u00c4\u00b1": 787, "##lu": 788, "##sar": 789, "##er": 790, "##ngan": 791, "##zten": 792, "##im": 793, "##re": 794, "##mu": 795, "##to": 796, "##eh": 797, "##tr": 798, "##aba": 799, "##\u0126\u00d8": 800, "##zt": 801, "##gs": 802, "##ts": 803, "##gsa": 804, "##rr": 805, "##him": 806, "##den": 807, "##ngang": 808, "##za": 809, "##\u00c4\u00a1": 810, "##ao": 811, "##asad": 812, "##alag": 813, "##rt": 814, "##dp": 815, "##ire": 816, "##ek": 817, "##i\u00c3\u00b3": 818, "##az": 819, "##et": 820, "##\u00e1\u00bb": 821, "##np": 822, "##err": 823, "##ki": 824, "##ni": 825, "##il": 826, "##ho": 827, "##sad": 828, "##gan": 829, "##on": 830, "##bi": 831, "##kar": 832, "##\u012a\u00d9": 833, "##nd": 834, "##\u00b3n": 835, "##\u00b6m": 836, "##ahin": 837, "##aci": 838, "##ue": 839, "##or": 840, "##rri": 841, "##ny": 842, "##od": 843, "##aga": 844, "##\u00b6z": 845, "##ert": 846, "##ou": 847, "##is": 848, "##dl": 849, "an": 850, "##bab": 851, "##ci": 852, "##\u00d1\u0131": 853, "##\u00a1s": 854, "##iy": 855, "##ren": 856, "##\u00b1\u00c5": 857, "##gw": 858, "##jo": 859, "##\u00a9g": 860, "##erri": 861, "##s\u00c3": 862, "\u0120da": 863, "##nai": 864, "##oa": 865, "##big": 866, "##\u00d9\u0126\u00d8": 867, "##k\u00c3": 868, "##\u00c5\u0141": 869, "##ch": 870, "##ros": 871, "##do": 872, "##el": 873, "20": 874, "##\u010a\u010a\u010a\u010a": 875, "##eka": 876, "##\u012di": 877, "##..": 878, "##iren": 879, "##tu": 880, "##\u0122\u00ac": 881, "##ags": 882, "##dla": 883, "##aw": 884, "##tod": 885, "##iz": 886, "##uk": 887, "##\u00a1r": 888, "##li": 889, "##kk": 890, "##\u0133\u013a": 891, "\u0120sa": 892, "##\u00a4n": 893, "##agat": 894, "##hin": 895, "##br": 896, "##ila": 897, "##rts": 898, "##ako": 899, "##ur": 900, "##le": 901, "##ai": 902, "##\u00aau": 903, "##\u00c3\u00a5": 904, "##\u00a1g": 905, "##ay": 906, "##ke": 907, "##adp": 908, "##bag": 909, "##\u00bcjo": 910, "##ia": 911, "##ale": 912, "##\u00ba\u0143t": 913, "##ha": 914, "##me": 915, "##alo": 916, "##ug": 917, "##po": 918, "##dto": 919, "##au": 920, "##wa": 921, "##ie": 922, "##bot": 923, "##ma": 924, "##inai": 925, "##gang": 926, "##\u00ba\u00a9": 927, "##gi": 928, "\u010a\u010a": 929, "##epa": 930, "##gat": 931, "##ong": 932, "##tso": 933, "##erts": 934, "##r\u00c3": 935, "##ez": 936, "##\u00c3\u00aau": 937, "##yo": 938, "##\u00bb\u012f": 939, "##um": 940, "##ss": 941, "##\u0143po": 942, "##am": 943, "##\u0141\u00c4": 944, "##ae": 945, "##oga": 946, "##k\u00c3\u00b6": 947, "##mm": 948, "##ero": 949, "##ll": 950, "##mb": 951, "##us": 952, "##tt": 953, "##\u00d8\u00a8": 954, "##t\u00c3": 955, "ha": 956, "##ua": 957, "##xx": 958, "\u0120kina": 959, "##alags": 960, "##m\u00c3": 961, "##zj": 962, "##eg": 963, "##si": 964, "##abo": 965, "##ui": 966, "##o\u00c3": 967, "##ali": 968, "##ate": 969, "##\u00c3\u00a9g": 970, "##eme": 971, "##\u00bft": 972, "##ihan": 973, "##iha": 974, "##sh": 975, "##nda": 976, "##ing": 977, "##sy": 978, "##\u00b1z": 979, "##nh": 980, "##ebi": 981, "##h\u00c3": 982, "##akar": 983, "##gt": 984}