codebyzeb commited on
Commit
a134d5c
·
verified ·
1 Parent(s): 294b287

Upload folder using huggingface_hub

Browse files
fw57Mmulti_Surprisal_threshold_256000/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_Surprisal_threshold_256000/stats.csv ADDED
The diff for this file is too large to render. See raw diff
 
fw57Mmulti_Surprisal_threshold_256000/tokenizer.json ADDED
@@ -0,0 +1,1390 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "Ġõ": 2,
62
+ "õ": 3,
63
+ "##õ": 4,
64
+ "Ġö": 5,
65
+ "ö": 6,
66
+ "##ö": 7,
67
+ "Ġª": 8,
68
+ "ª": 9,
69
+ "##ª": 10,
70
+ "ĠĽ": 11,
71
+ "Ľ": 12,
72
+ "##Ľ": 13,
73
+ "ĠĐ": 14,
74
+ "Đ": 15,
75
+ "##Đ": 16,
76
+ "`": 17,
77
+ "##`": 18,
78
+ ".": 19,
79
+ "##.": 20,
80
+ "ĠO": 21,
81
+ "O": 22,
82
+ "##O": 23,
83
+ "®": 24,
84
+ "##®": 25,
85
+ "½": 26,
86
+ "##½": 27,
87
+ "ĠF": 28,
88
+ "F": 29,
89
+ "##F": 30,
90
+ "Ġá": 31,
91
+ "á": 32,
92
+ "##á": 33,
93
+ "Ġø": 34,
94
+ "ø": 35,
95
+ "##ø": 36,
96
+ "ĠT": 37,
97
+ "T": 38,
98
+ "##T": 39,
99
+ "\"": 40,
100
+ "##\"": 41,
101
+ "9": 42,
102
+ "##9": 43,
103
+ "¥": 44,
104
+ "##¥": 45,
105
+ "¸": 46,
106
+ "##¸": 47,
107
+ "_": 48,
108
+ "##_": 49,
109
+ "ĠB": 50,
110
+ "B": 51,
111
+ "##B": 52,
112
+ "Ġĺ": 53,
113
+ "ĺ": 54,
114
+ "##ĺ": 55,
115
+ "ĠÈ": 56,
116
+ "È": 57,
117
+ "##È": 58,
118
+ "ĠÄ": 59,
119
+ "Ä": 60,
120
+ "##Ä": 61,
121
+ "Ġķ": 62,
122
+ "ķ": 63,
123
+ "##ķ": 64,
124
+ "¤": 65,
125
+ "##¤": 66,
126
+ "Ġo": 67,
127
+ "o": 68,
128
+ "##o": 69,
129
+ "ĠĮ": 70,
130
+ "Į": 71,
131
+ "##Į": 72,
132
+ "Ġð": 73,
133
+ "ð": 74,
134
+ "##ð": 75,
135
+ "\\": 76,
136
+ "##\\": 77,
137
+ "ĠĿ": 78,
138
+ "Ŀ": 79,
139
+ "##Ŀ": 80,
140
+ "^": 81,
141
+ "##^": 82,
142
+ "ĠĊ": 83,
143
+ "Ċ": 84,
144
+ "##Ċ": 85,
145
+ "Ġj": 86,
146
+ "j": 87,
147
+ "##j": 88,
148
+ "Ġn": 89,
149
+ "n": 90,
150
+ "##n": 91,
151
+ "Ġ": 92,
152
+ "##Ġ": 93,
153
+ "Ġþ": 94,
154
+ "þ": 95,
155
+ "##þ": 96,
156
+ "ĠD": 97,
157
+ "D": 98,
158
+ "##D": 99,
159
+ "ĠĔ": 100,
160
+ "Ĕ": 101,
161
+ "##Ĕ": 102,
162
+ "ĠL": 103,
163
+ "L": 104,
164
+ "##L": 105,
165
+ "Ġå": 106,
166
+ "å": 107,
167
+ "##å": 108,
168
+ "ĠJ": 109,
169
+ "J": 110,
170
+ "##J": 111,
171
+ "Ġe": 112,
172
+ "e": 113,
173
+ "##e": 114,
174
+ "Ġu": 115,
175
+ "u": 116,
176
+ "##u": 117,
177
+ "ĠĄ": 118,
178
+ "Ą": 119,
179
+ "##Ą": 120,
180
+ "Ġı": 121,
181
+ "ı": 122,
182
+ "##ı": 123,
183
+ "ĠĴ": 124,
184
+ "Ĵ": 125,
185
+ "##Ĵ": 126,
186
+ "*": 127,
187
+ "##*": 128,
188
+ "5": 129,
189
+ "##5": 130,
190
+ "ĠĖ": 131,
191
+ "Ė": 132,
192
+ "##Ė": 133,
193
+ "ĠĎ": 134,
194
+ "Ď": 135,
195
+ "##Ď": 136,
196
+ "ĠĢ": 137,
197
+ "Ģ": 138,
198
+ "##Ģ": 139,
199
+ "ĠY": 140,
200
+ "Y": 141,
201
+ "##Y": 142,
202
+ "ĠÜ": 143,
203
+ "Ü": 144,
204
+ "##Ü": 145,
205
+ ";": 146,
206
+ "##;": 147,
207
+ "¿": 148,
208
+ "##¿": 149,
209
+ "~": 150,
210
+ "##~": 151,
211
+ "2": 152,
212
+ "##2": 153,
213
+ "´": 154,
214
+ "##´": 155,
215
+ "¦": 156,
216
+ "##¦": 157,
217
+ "ĠÀ": 158,
218
+ "À": 159,
219
+ "##À": 160,
220
+ "Ġé": 161,
221
+ "é": 162,
222
+ "##é": 163,
223
+ "Ġħ": 164,
224
+ "ħ": 165,
225
+ "##ħ": 166,
226
+ "¢": 167,
227
+ "##¢": 168,
228
+ "ĠĚ": 169,
229
+ "Ě": 170,
230
+ "##Ě": 171,
231
+ "Ġã": 172,
232
+ "ã": 173,
233
+ "##ã": 174,
234
+ "Ġę": 175,
235
+ "ę": 176,
236
+ "##ę": 177,
237
+ "(": 178,
238
+ "##(": 179,
239
+ "¬": 180,
240
+ "##¬": 181,
241
+ "«": 182,
242
+ "##«": 183,
243
+ "6": 184,
244
+ "##6": 185,
245
+ "ĠE": 186,
246
+ "E": 187,
247
+ "##E": 188,
248
+ "£": 189,
249
+ "##£": 190,
250
+ "Ġg": 191,
251
+ "g": 192,
252
+ "##g": 193,
253
+ "¹": 194,
254
+ "##¹": 195,
255
+ "Ġą": 196,
256
+ "ą": 197,
257
+ "##ą": 198,
258
+ "8": 199,
259
+ "##8": 200,
260
+ "-": 201,
261
+ "##-": 202,
262
+ "¨": 203,
263
+ "##¨": 204,
264
+ "&": 205,
265
+ "##&": 206,
266
+ "Ġī": 207,
267
+ "ī": 208,
268
+ "##ī": 209,
269
+ "Ġă": 210,
270
+ "ă": 211,
271
+ "##ă": 212,
272
+ "ĠÊ": 213,
273
+ "Ê": 214,
274
+ "##Ê": 215,
275
+ "ĠQ": 216,
276
+ "Q": 217,
277
+ "##Q": 218,
278
+ "ĠĀ": 219,
279
+ "Ā": 220,
280
+ "##Ā": 221,
281
+ "ĠIJ": 222,
282
+ "IJ": 223,
283
+ "##IJ": 224,
284
+ "ĠÆ": 225,
285
+ "Æ": 226,
286
+ "##Æ": 227,
287
+ "ĠV": 228,
288
+ "V": 229,
289
+ "##V": 230,
290
+ "ĠÉ": 231,
291
+ "É": 232,
292
+ "##É": 233,
293
+ "§": 234,
294
+ "##§": 235,
295
+ "Ġĝ": 236,
296
+ "ĝ": 237,
297
+ "##ĝ": 238,
298
+ "ĠŃ": 239,
299
+ "Ń": 240,
300
+ "##Ń": 241,
301
+ "ĠÚ": 242,
302
+ "Ú": 243,
303
+ "##Ú": 244,
304
+ "Ġĵ": 245,
305
+ "ĵ": 246,
306
+ "##ĵ": 247,
307
+ "Ġµ": 248,
308
+ "µ": 249,
309
+ "##µ": 250,
310
+ "¶": 251,
311
+ "##¶": 252,
312
+ "ĠP": 253,
313
+ "P": 254,
314
+ "##P": 255,
315
+ "Ġij": 256,
316
+ "ij": 257,
317
+ "##ij": 258,
318
+ "²": 259,
319
+ "##²": 260,
320
+ "ĠÎ": 261,
321
+ "Î": 262,
322
+ "##Î": 263,
323
+ "Ġâ": 264,
324
+ "â": 265,
325
+ "##â": 266,
326
+ "ĠS": 267,
327
+ "S": 268,
328
+ "##S": 269,
329
+ "ĠÇ": 270,
330
+ "Ç": 271,
331
+ "##Ç": 272,
332
+ "ĠČ": 273,
333
+ "Č": 274,
334
+ "##Č": 275,
335
+ "ĠI": 276,
336
+ "I": 277,
337
+ "##I": 278,
338
+ "ĠH": 279,
339
+ "H": 280,
340
+ "##H": 281,
341
+ "|": 282,
342
+ "##|": 283,
343
+ "ĠÝ": 284,
344
+ "Ý": 285,
345
+ "##Ý": 286,
346
+ "Ġė": 287,
347
+ "ė": 288,
348
+ "##ė": 289,
349
+ "×": 290,
350
+ "##×": 291,
351
+ "Ġx": 292,
352
+ "x": 293,
353
+ "##x": 294,
354
+ "Ġā": 295,
355
+ "ā": 296,
356
+ "##ā": 297,
357
+ "ĠĶ": 298,
358
+ "Ķ": 299,
359
+ "##Ķ": 300,
360
+ "ĠĞ": 301,
361
+ "Ğ": 302,
362
+ "##Ğ": 303,
363
+ "'": 304,
364
+ "##'": 305,
365
+ "Ġĩ": 306,
366
+ "ĩ": 307,
367
+ "##ĩ": 308,
368
+ "Ġĥ": 309,
369
+ "ĥ": 310,
370
+ "##ĥ": 311,
371
+ "Ġq": 312,
372
+ "q": 313,
373
+ "##q": 314,
374
+ "@": 315,
375
+ "##@": 316,
376
+ "Ġp": 317,
377
+ "p": 318,
378
+ "##p": 319,
379
+ "Ġw": 320,
380
+ "w": 321,
381
+ "##w": 322,
382
+ "!": 323,
383
+ "##!": 324,
384
+ "#": 325,
385
+ "###": 326,
386
+ "Ġf": 327,
387
+ "f": 328,
388
+ "##f": 329,
389
+ "¾": 330,
390
+ "##¾": 331,
391
+ "ĠÒ": 332,
392
+ "Ò": 333,
393
+ "##Ò": 334,
394
+ "ĠÙ": 335,
395
+ "Ù": 336,
396
+ "##Ù": 337,
397
+ "Ġç": 338,
398
+ "ç": 339,
399
+ "##ç": 340,
400
+ ">": 341,
401
+ "##>": 342,
402
+ "ĠÁ": 343,
403
+ "Á": 344,
404
+ "##Á": 345,
405
+ "Ġí": 346,
406
+ "í": 347,
407
+ "##í": 348,
408
+ "0": 349,
409
+ "##0": 350,
410
+ ")": 351,
411
+ "##)": 352,
412
+ "Ġú": 353,
413
+ "ú": 354,
414
+ "##ú": 355,
415
+ "]": 356,
416
+ "##]": 357,
417
+ "Ġñ": 358,
418
+ "ñ": 359,
419
+ "##ñ": 360,
420
+ "Ġĭ": 361,
421
+ "ĭ": 362,
422
+ "##ĭ": 363,
423
+ "ĠĹ": 364,
424
+ "Ĺ": 365,
425
+ "##Ĺ": 366,
426
+ "ĠĈ": 367,
427
+ "Ĉ": 368,
428
+ "##Ĉ": 369,
429
+ "ĠÖ": 370,
430
+ "Ö": 371,
431
+ "##Ö": 372,
432
+ "Ġô": 373,
433
+ "ô": 374,
434
+ "##ô": 375,
435
+ "ĠĘ": 376,
436
+ "Ę": 377,
437
+ "##Ę": 378,
438
+ "ĠĨ": 379,
439
+ "Ĩ": 380,
440
+ "##Ĩ": 381,
441
+ "ĠK": 382,
442
+ "K": 383,
443
+ "##K": 384,
444
+ "Ġh": 385,
445
+ "h": 386,
446
+ "##h": 387,
447
+ "Ġi": 388,
448
+ "i": 389,
449
+ "##i": 390,
450
+ "Ġº": 391,
451
+ "º": 392,
452
+ "##º": 393,
453
+ "Ġē": 394,
454
+ "ē": 395,
455
+ "##ē": 396,
456
+ "Ġæ": 397,
457
+ "æ": 398,
458
+ "##æ": 399,
459
+ "Ġt": 400,
460
+ "t": 401,
461
+ "##t": 402,
462
+ "Ġî": 403,
463
+ "î": 404,
464
+ "##î": 405,
465
+ "1": 406,
466
+ "##1": 407,
467
+ "Ġy": 408,
468
+ "y": 409,
469
+ "##y": 410,
470
+ "ĠÍ": 411,
471
+ "Í": 412,
472
+ "##Í": 413,
473
+ "ĠÂ": 414,
474
+ "Â": 415,
475
+ "##Â": 416,
476
+ "Ġċ": 417,
477
+ "ċ": 418,
478
+ "##ċ": 419,
479
+ "ĠØ": 420,
480
+ "Ø": 421,
481
+ "##Ø": 422,
482
+ "ĠÌ": 423,
483
+ "Ì": 424,
484
+ "##Ì": 425,
485
+ "ĠĻ": 426,
486
+ "Ļ": 427,
487
+ "##Ļ": 428,
488
+ ":": 429,
489
+ "##:": 430,
490
+ "ĠM": 431,
491
+ "M": 432,
492
+ "##M": 433,
493
+ "Ġa": 434,
494
+ "a": 435,
495
+ "##a": 436,
496
+ "ĠG": 437,
497
+ "G": 438,
498
+ "##G": 439,
499
+ "÷": 440,
500
+ "##÷": 441,
501
+ "Ġľ": 442,
502
+ "ľ": 443,
503
+ "##ľ": 444,
504
+ "Ġk": 445,
505
+ "k": 446,
506
+ "##k": 447,
507
+ "ĠW": 448,
508
+ "W": 449,
509
+ "##W": 450,
510
+ "ĠÛ": 451,
511
+ "Û": 452,
512
+ "##Û": 453,
513
+ "ĠA": 454,
514
+ "A": 455,
515
+ "##A": 456,
516
+ "Ġİ": 457,
517
+ "İ": 458,
518
+ "##İ": 459,
519
+ "ĠÞ": 460,
520
+ "Þ": 461,
521
+ "##Þ": 462,
522
+ "Ġà": 463,
523
+ "à": 464,
524
+ "##à": 465,
525
+ "·": 466,
526
+ "##·": 467,
527
+ "Ġÿ": 468,
528
+ "ÿ": 469,
529
+ "##ÿ": 470,
530
+ "[": 471,
531
+ "##[": 472,
532
+ "=": 473,
533
+ "##=": 474,
534
+ "ĠÑ": 475,
535
+ "Ñ": 476,
536
+ "##Ñ": 477,
537
+ "Ġč": 478,
538
+ "č": 479,
539
+ "##č": 480,
540
+ "ĠX": 481,
541
+ "X": 482,
542
+ "##X": 483,
543
+ "ĠË": 484,
544
+ "Ë": 485,
545
+ "##Ë": 486,
546
+ "ĠZ": 487,
547
+ "Z": 488,
548
+ "##Z": 489,
549
+ "ĠĂ": 490,
550
+ "Ă": 491,
551
+ "##Ă": 492,
552
+ "ĠĬ": 493,
553
+ "Ĭ": 494,
554
+ "##Ĭ": 495,
555
+ "Ġď": 496,
556
+ "ď": 497,
557
+ "##ď": 498,
558
+ "Ġý": 499,
559
+ "ý": 500,
560
+ "##ý": 501,
561
+ "+": 502,
562
+ "##+": 503,
563
+ "ĠU": 504,
564
+ "U": 505,
565
+ "##U": 506,
566
+ "Ġz": 507,
567
+ "z": 508,
568
+ "##z": 509,
569
+ "Ġü": 510,
570
+ "ü": 511,
571
+ "##ü": 512,
572
+ "Ġģ": 513,
573
+ "ģ": 514,
574
+ "##ģ": 515,
575
+ "»": 516,
576
+ "##»": 517,
577
+ "ĠÐ": 518,
578
+ "Ð": 519,
579
+ "##Ð": 520,
580
+ "Ġġ": 521,
581
+ "ġ": 522,
582
+ "##ġ": 523,
583
+ "Ġë": 524,
584
+ "ë": 525,
585
+ "##ë": 526,
586
+ "ĠN": 527,
587
+ "N": 528,
588
+ "##N": 529,
589
+ "ĠR": 530,
590
+ "R": 531,
591
+ "##R": 532,
592
+ "Ġđ": 533,
593
+ "đ": 534,
594
+ "##đ": 535,
595
+ "Ġê": 536,
596
+ "ê": 537,
597
+ "##ê": 538,
598
+ "Ġò": 539,
599
+ "ò": 540,
600
+ "##ò": 541,
601
+ "Ġû": 542,
602
+ "û": 543,
603
+ "##û": 544,
604
+ "{": 545,
605
+ "##{": 546,
606
+ "Ġm": 547,
607
+ "m": 548,
608
+ "##m": 549,
609
+ "©": 550,
610
+ "##©": 551,
611
+ "Ġĸ": 552,
612
+ "ĸ": 553,
613
+ "##ĸ": 554,
614
+ "ĠĤ": 555,
615
+ "Ĥ": 556,
616
+ "##Ĥ": 557,
617
+ "Ġä": 558,
618
+ "ä": 559,
619
+ "##ä": 560,
620
+ "ĠÓ": 561,
621
+ "Ó": 562,
622
+ "##Ó": 563,
623
+ "Ġù": 564,
624
+ "ù": 565,
625
+ "##ù": 566,
626
+ "$": 567,
627
+ "##$": 568,
628
+ "Ġě": 569,
629
+ "ě": 570,
630
+ "##ě": 571,
631
+ "¯": 572,
632
+ "##¯": 573,
633
+ "Ġs": 574,
634
+ "s": 575,
635
+ "##s": 576,
636
+ "ĠÅ": 577,
637
+ "Å": 578,
638
+ "##Å": 579,
639
+ "Ġv": 580,
640
+ "v": 581,
641
+ "##v": 582,
642
+ "°": 583,
643
+ "##°": 584,
644
+ ",": 585,
645
+ "##,": 586,
646
+ "Ġó": 587,
647
+ "ó": 588,
648
+ "##ó": 589,
649
+ "Ġŀ": 590,
650
+ "ŀ": 591,
651
+ "##ŀ": 592,
652
+ "Ġć": 593,
653
+ "ć": 594,
654
+ "##ć": 595,
655
+ "Ġł": 596,
656
+ "ł": 597,
657
+ "##ł": 598,
658
+ "Ġß": 599,
659
+ "ß": 600,
660
+ "##ß": 601,
661
+ "4": 602,
662
+ "##4": 603,
663
+ "ĠÔ": 604,
664
+ "Ô": 605,
665
+ "##Ô": 606,
666
+ "Ġį": 607,
667
+ "į": 608,
668
+ "##į": 609,
669
+ "ĠĜ": 610,
670
+ "Ĝ": 611,
671
+ "##Ĝ": 612,
672
+ "%": 613,
673
+ "##%": 614,
674
+ "ĠÏ": 615,
675
+ "Ï": 616,
676
+ "##Ï": 617,
677
+ "}": 618,
678
+ "##}": 619,
679
+ "Ġì": 620,
680
+ "ì": 621,
681
+ "##ì": 622,
682
+ "Ġļ": 623,
683
+ "ļ": 624,
684
+ "##ļ": 625,
685
+ "ĠĒ": 626,
686
+ "Ē": 627,
687
+ "##Ē": 628,
688
+ "¡": 629,
689
+ "##¡": 630,
690
+ "ĠÃ": 631,
691
+ "Ã": 632,
692
+ "##Ã": 633,
693
+ "ĠÕ": 634,
694
+ "Õ": 635,
695
+ "##Õ": 636,
696
+ "Ġĕ": 637,
697
+ "ĕ": 638,
698
+ "##ĕ": 639,
699
+ "ĠĦ": 640,
700
+ "Ħ": 641,
701
+ "##Ħ": 642,
702
+ "ĠĪ": 643,
703
+ "Ī": 644,
704
+ "##Ī": 645,
705
+ "Ġr": 646,
706
+ "r": 647,
707
+ "##r": 648,
708
+ "ĠĆ": 649,
709
+ "Ć": 650,
710
+ "##Ć": 651,
711
+ "Ġğ": 652,
712
+ "ğ": 653,
713
+ "##ğ": 654,
714
+ "Ġc": 655,
715
+ "c": 656,
716
+ "##c": 657,
717
+ "ĠC": 658,
718
+ "C": 659,
719
+ "##C": 660,
720
+ "<": 661,
721
+ "##<": 662,
722
+ "¼": 663,
723
+ "##¼": 664,
724
+ "Ġĉ": 665,
725
+ "ĉ": 666,
726
+ "##ĉ": 667,
727
+ "Ġl": 668,
728
+ "l": 669,
729
+ "##l": 670,
730
+ "3": 671,
731
+ "##3": 672,
732
+ "?": 673,
733
+ "##?": 674,
734
+ "±": 675,
735
+ "##±": 676,
736
+ "Ġï": 677,
737
+ "ï": 678,
738
+ "##ï": 679,
739
+ "³": 680,
740
+ "##³": 681,
741
+ "Ġb": 682,
742
+ "b": 683,
743
+ "##b": 684,
744
+ "Ġd": 685,
745
+ "d": 686,
746
+ "##d": 687,
747
+ "Ġè": 688,
748
+ "è": 689,
749
+ "##è": 690,
750
+ "ĠŁ": 691,
751
+ "Ł": 692,
752
+ "##Ł": 693,
753
+ "7": 694,
754
+ "##7": 695,
755
+ "/": 696,
756
+ "##/": 697,
757
+ "<|unk|>": 698,
758
+ "##ä": 699,
759
+ "##äÃ": 700,
760
+ "##it": 701,
761
+ "##an": 702,
762
+ "##as": 703,
763
+ "##asa": 704,
764
+ "##ge": 705,
765
+ "##de": 706,
766
+ "##bi": 707,
767
+ "##ga": 708,
768
+ "##ta": 709,
769
+ "##ang": 710,
770
+ "##pa": 711,
771
+ "##le": 712,
772
+ "##ng": 713,
773
+ "##na": 714,
774
+ "##ina": 715,
775
+ ":/": 716,
776
+ "##en": 717,
777
+ "##ra": 718,
778
+ "##den": 719,
779
+ "##ro": 720,
780
+ "##on": 721,
781
+ "##bo": 722,
782
+ "##ibo": 723,
783
+ "##ci": 724,
784
+ "##ul": 725,
785
+ "##ºŃ": 726,
786
+ "##mu": 727,
787
+ "##in": 728,
788
+ "##ma": 729,
789
+ "##ah": 730,
790
+ "##ar": 731,
791
+ "##ai": 732,
792
+ "##nai": 733,
793
+ "##aci": 734,
794
+ "##sa": 735,
795
+ "##inai": 736,
796
+ "##ba": 737,
797
+ "##uo": 738,
798
+ "##bab": 739,
799
+ "##ir": 740,
800
+ "##ire": 741,
801
+ "##baba": 742,
802
+ "##¶Ã": 743,
803
+ "##iz": 744,
804
+ "##ni": 745,
805
+ "##ri": 746,
806
+ "##rri": 747,
807
+ "##erri": 748,
808
+ "##gan": 749,
809
+ "##nt": 750,
810
+ "##te": 751,
811
+ "##ab": 752,
812
+ "##gs": 753,
813
+ "##ags": 754,
814
+ "##zt": 755,
815
+ "##zte": 756,
816
+ "##zten": 757,
817
+ "##la": 758,
818
+ "##aba": 759,
819
+ "##tr": 760,
820
+ "##tro": 761,
821
+ "##eh": 762,
822
+ "##ahi": 763,
823
+ "##ahin": 764,
824
+ "##ep": 765,
825
+ "##ion": 766,
826
+ "##00": 767,
827
+ "##pi": 768,
828
+ "##re": 769,
829
+ "##ö": 770,
830
+ "##ue": 771,
831
+ "##ak": 772,
832
+ "##..": 773,
833
+ "##ia": 774,
834
+ "##ssa": 775,
835
+ "##at": 776,
836
+ "##ob": 777,
837
+ "##ag": 778,
838
+ "##aga": 779,
839
+ "##so": 780,
840
+ "##dl": 781,
841
+ "##rt": 782,
842
+ "##tt": 783,
843
+ "##¼l": 784,
844
+ "##Ńt": 785,
845
+ "##ºŃt": 786,
846
+ "##od": 787,
847
+ "##um": 788,
848
+ "##gang": 789,
849
+ "##ngang": 790,
850
+ "##lo": 791,
851
+ "##bre": 792,
852
+ "##tj": 793,
853
+ "##abi": 794,
854
+ "##ik": 795,
855
+ "##ros": 796,
856
+ "##bit": 797,
857
+ "##ie": 798,
858
+ "##ien": 799,
859
+ "##ap": 800,
860
+ "##og": 801,
861
+ "##¡l": 802,
862
+ "##ek": 803,
863
+ "##eka": 804,
864
+ "##etro": 805,
865
+ "##ay": 806,
866
+ "##baga": 807,
867
+ "##abaga": 808,
868
+ "##au": 809,
869
+ "##hi": 810,
870
+ "##him": 811,
871
+ "##hin": 812,
872
+ "##zi": 813,
873
+ "##ÃŃ": 814,
874
+ "##to": 815,
875
+ "##ekak": 816,
876
+ "##ot": 817,
877
+ "##bot": 818,
878
+ "##ibot": 819,
879
+ "##abo": 820,
880
+ "##¤l": 821,
881
+ "##et": 822,
882
+ "##ad": 823,
883
+ "##er": 824,
884
+ "##ti": 825,
885
+ "##ao": 826,
886
+ "##op": 827,
887
+ "##om": 828,
888
+ "##ha": 829,
889
+ "##aha": 830,
890
+ "##err": 831,
891
+ "##ran": 832,
892
+ "##sod": 833,
893
+ "##ae": 834,
894
+ "##sar": 835,
895
+ "##im": 836,
896
+ "##ahim": 837,
897
+ "##ig": 838,
898
+ "##ib": 839,
899
+ "##da": 840,
900
+ "##áº": 841,
901
+ "##si": 842,
902
+ "##asi": 843,
903
+ "##ya": 844,
904
+ "##al": 845,
905
+ "##mi": 846,
906
+ "##ala": 847,
907
+ "##ur": 848,
908
+ "##iy": 849,
909
+ "##os": 850,
910
+ "##fi": 851,
911
+ "##abag": 852,
912
+ "##ch": 853,
913
+ "##Ãł": 854,
914
+ "##ko": 855,
915
+ "##Ãłi": 856,
916
+ "##ali": 857,
917
+ "##alib": 858,
918
+ "##alibo": 859,
919
+ "##tan": 860,
920
+ "##li": 861,
921
+ "##wa": 862,
922
+ "##mb": 863,
923
+ "##gh": 864,
924
+ "##pt": 865,
925
+ "##pti": 866,
926
+ "Ġna": 867,
927
+ "##libo": 868,
928
+ "##nay": 869,
929
+ "##asod": 870,
930
+ "##ero": 871,
931
+ "An": 872,
932
+ "Ang": 873,
933
+ "##pu": 874,
934
+ "##himu": 875,
935
+ "##dt": 876,
936
+ "##dto": 877,
937
+ "##oh": 878,
938
+ "##¤t": 879,
939
+ "##etr": 880,
940
+ "##ı": 881,
941
+ "##ata": 882,
942
+ "##io": 883,
943
+ "##»į": 884,
944
+ "##es": 885,
945
+ "##ila": 886,
946
+ "##oga": 887,
947
+ "Ġki": 888,
948
+ "Ġkin": 889,
949
+ "Ġkina": 890,
950
+ "##¤Ã": 891,
951
+ "##uj": 892,
952
+ "##is": 893,
953
+ "à¤": 894,
954
+ "##nga": 895,
955
+ "##ngan": 896,
956
+ "##imu": 897,
957
+ "##uk": 898,
958
+ "##uki": 899,
959
+ "##ukir": 900,
960
+ "##ukira": 901,
961
+ "##ukiran": 902,
962
+ "##inab": 903,
963
+ "##rr": 904,
964
+ "Ġla": 905,
965
+ "Ġlal": 906,
966
+ "##wig": 907,
967
+ "##ehi": 908,
968
+ "##tz": 909,
969
+ "##han": 910,
970
+ "##ren": 911,
971
+ "##iren": 912,
972
+ "##res": 913,
973
+ "##ntz": 914,
974
+ "Ġlala": 915,
975
+ "##»Ľ": 916,
976
+ "##no": 917,
977
+ "##©s": 918,
978
+ "##mo": 919,
979
+ "##omo": 920,
980
+ "##lags": 921,
981
+ "##kti": 922,
982
+ "##akti": 923,
983
+ "##libot": 924,
984
+ "##alibot": 925,
985
+ "##ÙĬ": 926,
986
+ "##ts": 927,
987
+ "##rts": 928,
988
+ "##erts": 929,
989
+ "Ġda": 930,
990
+ "an": 931,
991
+ "##ong": 932,
992
+ "##asar": 933,
993
+ "##pan": 934,
994
+ "##ten": 935,
995
+ "##yo": 936,
996
+ "##oa": 937,
997
+ "##tod": 938,
998
+ "##itz": 939,
999
+ "##il": 940,
1000
+ "##uden": 941,
1001
+ "##ebi": 942,
1002
+ "##ahimu": 943,
1003
+ "##izi": 944,
1004
+ "##bizi": 945,
1005
+ "##or": 946,
1006
+ "Ġsa": 947,
1007
+ "##ana": 948,
1008
+ "##em": 949,
1009
+ "##me": 950,
1010
+ "##ka": 951,
1011
+ "##aka": 952,
1012
+ "##id": 953,
1013
+ "##idl": 954,
1014
+ "##idla": 955,
1015
+ "##lag": 956,
1016
+ "Ġka": 957,
1017
+ "Ġkas": 958,
1018
+ "Ġkasa": 959,
1019
+ "Ġkasar": 960,
1020
+ "##gw": 961,
1021
+ "##do": 962,
1022
+ "##ing": 963,
1023
+ "##ua": 964,
1024
+ "##ŁÄ": 965,
1025
+ "##oÃł": 966,
1026
+ "##akar": 967,
1027
+ "##ume": 968,
1028
+ "##hong": 969,
1029
+ "##lu": 970,
1030
+ "##alu": 971,
1031
+ "Ġan": 972,
1032
+ "Ġang": 973,
1033
+ "##eme": 974,
1034
+ "##ug": 975,
1035
+ "##uz": 976,
1036
+ "##am": 977,
1037
+ "##kop": 978,
1038
+ "##wi": 979,
1039
+ "##än": 980,
1040
+ "##arr": 981,
1041
+ "##ÄĽ": 982,
1042
+ "##gat": 983,
1043
+ "##met": 984,
1044
+ "##lib": 985,
1045
+ "##tu": 986,
1046
+ "##gt": 987,
1047
+ "##gto": 988,
1048
+ "##gtod": 989,
1049
+ "##§Ã": 990,
1050
+ "##//": 991,
1051
+ "##kan": 992,
1052
+ "##nd": 993,
1053
+ "##and": 994,
1054
+ "##dad": 995,
1055
+ "##ou": 996,
1056
+ "##oun": 997,
1057
+ "##Łu": 998,
1058
+ "##oÃ": 999,
1059
+ "##ghi": 1000,
1060
+ "##eek": 1001,
1061
+ "°": 1002,
1062
+ "##ud": 1003,
1063
+ "##ude": 1004,
1064
+ "##aa": 1005,
1065
+ "##aan": 1006,
1066
+ "##tang": 1007,
1067
+ "##un": 1008,
1068
+ "##nit": 1009,
1069
+ "##st": 1010,
1070
+ "##sta": 1011,
1071
+ "##ol": 1012,
1072
+ "##ez": 1013,
1073
+ "Ġes": 1014,
1074
+ "Ġest": 1015,
1075
+ "##ø": 1016,
1076
+ "##ku": 1017,
1077
+ "##nda": 1018,
1078
+ "##za": 1019,
1079
+ "##zar": 1020,
1080
+ "##np": 1021,
1081
+ "##ilo": 1022,
1082
+ "##dla": 1023,
1083
+ "Ġzi": 1024,
1084
+ "Ġzir": 1025,
1085
+ "Ġzire": 1026,
1086
+ "Ġziren": 1027,
1087
+ "##pr": 1028,
1088
+ "##npr": 1029,
1089
+ "##ac": 1030,
1090
+ "##ns": 1031,
1091
+ "##dpa": 1032,
1092
+ "##adpa": 1033,
1093
+ "##sadpa": 1034,
1094
+ "##asadpa": 1035,
1095
+ "##eta": 1036,
1096
+ "##eg": 1037,
1097
+ "##ita": 1038,
1098
+ "##nita": 1039,
1099
+ "##ung": 1040,
1100
+ "##¡n": 1041,
1101
+ "##¸j": 1042,
1102
+ "##ntro": 1043,
1103
+ "##son": 1044,
1104
+ "##¡nÃ": 1045,
1105
+ "##¡nÃŃ": 1046,
1106
+ "##Ľn": 1047,
1107
+ "##po": 1048,
1108
+ "##pon": 1049,
1109
+ "##pong": 1050,
1110
+ "##bag": 1051,
1111
+ "##ho": 1052,
1112
+ "##hon": 1053,
1113
+ "##uzte": 1054,
1114
+ "##alags": 1055,
1115
+ "##³w": 1056,
1116
+ "##aw": 1057,
1117
+ "##mÃ": 1058,
1118
+ "##mó": 1059,
1119
+ "##ub": 1060,
1120
+ "##euden": 1061,
1121
+ "##ado": 1062,
1122
+ "##iÄ": 1063,
1123
+ "##ne": 1064,
1124
+ "##nes": 1065,
1125
+ "##ora": 1066,
1126
+ "##ini": 1067,
1127
+ "Ġng": 1068,
1128
+ "Ġnga": 1069,
1129
+ "##tzi": 1070,
1130
+ "##ó": 1071,
1131
+ "##kar": 1072,
1132
+ "##akan": 1073,
1133
+ "##lakan": 1074,
1134
+ "##áºŃ": 1075,
1135
+ "##sy": 1076,
1136
+ "##se": 1077,
1137
+ "##eae": 1078,
1138
+ "##ceae": 1079,
1139
+ "##¡d": 1080,
1140
+ "##agat": 1081,
1141
+ "Ġdag": 1082,
1142
+ "##ea": 1083,
1143
+ "##tros": 1084,
1144
+ "##adp": 1085,
1145
+ "://": 1086,
1146
+ "##ÅĻ": 1087,
1147
+ "##ve": 1088,
1148
+ "##ver": 1089,
1149
+ "##nito": 1090,
1150
+ "##lak": 1091,
1151
+ "##alag": 1092,
1152
+ "##alagsa": 1093,
1153
+ "##baw": 1094,
1154
+ "##ow": 1095,
1155
+ "##uzten": 1096,
1156
+ "##oka": 1097,
1157
+ "##lus": 1098,
1158
+ "##ĢĻ": 1099,
1159
+ "##abit": 1100,
1160
+ "##metr": 1101,
1161
+ "##metro": 1102,
1162
+ "##ona": 1103,
1163
+ "##uba": 1104,
1164
+ "##¿t": 1105,
1165
+ "Ġgi": 1106,
1166
+ "##ki": 1107,
1167
+ "Ġta": 1108,
1168
+ "##br": 1109,
1169
+ "##awi": 1110,
1170
+ "##eb": 1111,
1171
+ "##ih": 1112,
1172
+ "##biy": 1113,
1173
+ "##¹´": 1114,
1174
+ "##agw": 1115,
1175
+ "##bita": 1116,
1176
+ "##abita": 1117,
1177
+ "habita": 1118,
1178
+ "##ert": 1119,
1179
+ "##sad": 1120,
1180
+ "##asad": 1121,
1181
+ "##nÃ": 1122,
1182
+ "##ito": 1123,
1183
+ "##ss": 1124,
1184
+ "##ÅŁ": 1125,
1185
+ "##áºŃt": 1126,
1186
+ "Ġnah": 1127,
1187
+ "Ġnahi": 1128,
1188
+ "Ġnahim": 1129,
1189
+ "##±ÅŁ": 1130,
1190
+ "##ura": 1131,
1191
+ "##uran": 1132,
1192
+ "##kt": 1133,
1193
+ "##tza": 1134,
1194
+ "##ld": 1135,
1195
+ "Ġkm": 1136,
1196
+ "##itu": 1137,
1197
+ "##asadp": 1138,
1198
+ "##ê": 1139,
1199
+ "##ú": 1140,
1200
+ "##kir": 1141,
1201
+ "ĠAn": 1142,
1202
+ "ĠAng": 1143,
1203
+ "##mak": 1144,
1204
+ "##á": 1145,
1205
+ "##ág": 1146,
1206
+ "##sadp": 1147,
1207
+ "##sadpan": 1148,
1208
+ "##enda": 1149,
1209
+ "##gi": 1150,
1210
+ "##Äĭ": 1151,
1211
+ "##co": 1152,
1212
+ "Ġph": 1153,
1213
+ "##rg": 1154,
1214
+ "##kira": 1155,
1215
+ "##kiran": 1156,
1216
+ "##kang": 1157,
1217
+ "##akang": 1158,
1218
+ "##lakang": 1159,
1219
+ "##dlakang": 1160,
1220
+ "##idlakang": 1161,
1221
+ "##iÃ": 1162,
1222
+ "##ió": 1163,
1223
+ "##ako": 1164,
1224
+ "##we": 1165,
1225
+ "##ysa": 1166,
1226
+ "##rop": 1167,
1227
+ "##ika": 1168,
1228
+ "##az": 1169,
1229
+ "##jo": 1170,
1230
+ "##zz": 1171,
1231
+ "##ula": 1172,
1232
+ "##¥d": 1173,
1233
+ "##¼u": 1174,
1234
+ "##be": 1175,
1235
+ "##ħ": 1176,
1236
+ "##tso": 1177,
1237
+ "##tson": 1178,
1238
+ "##iet": 1179,
1239
+ "##§h": 1180,
1240
+ "##ami": 1181,
1241
+ "##§a": 1182,
1242
+ "##ee": 1183,
1243
+ "##Ã¥d": 1184,
1244
+ "##ijl": 1185,
1245
+ "##§o": 1186,
1246
+ "##nah": 1187,
1247
+ "##±m": 1188,
1248
+ "##ħa": 1189,
1249
+ "##abaw": 1190,
1250
+ "##ihan": 1191,
1251
+ "##utang": 1192,
1252
+ "##mutang": 1193,
1253
+ "##AT": 1194,
1254
+ "Ġpu": 1195,
1255
+ "Ġze": 1196,
1256
+ "##us": 1197,
1257
+ "Ġni": 1198,
1258
+ "##¼i": 1199,
1259
+ "##bl": 1200,
1260
+ "##bli": 1201,
1261
+ "##ikaz": 1202,
1262
+ "##ut": 1203,
1263
+ "##uen": 1204,
1264
+ "##ate": 1205,
1265
+ "##¡g": 1206,
1266
+ "##rÄ": 1207,
1267
+ "##ent": 1208,
1268
+ "##©g": 1209,
1269
+ "##zj": 1210,
1270
+ "##Ńm": 1211,
1271
+ "##cia": 1212,
1272
+ "##oz": 1213,
1273
+ "##à¤": 1214,
1274
+ "##rÃ": 1215,
1275
+ "##Äĭe": 1216,
1276
+ "##¤Ĥ": 1217,
1277
+ "##el": 1218,
1278
+ "##ĭi": 1219,
1279
+ "##ru": 1220,
1280
+ "##las": 1221,
1281
+ "##ulas": 1222,
1282
+ "##iran": 1223,
1283
+ "##idlak": 1224,
1284
+ "##bagat": 1225,
1285
+ "##abagat": 1226,
1286
+ "##iyo": 1227,
1287
+ "##ye": 1228,
1288
+ "##pres": 1229,
1289
+ "##npres": 1230,
1290
+ "##DE": 1231,
1291
+ "##tuzte": 1232,
1292
+ "##kai": 1233,
1293
+ "##ubi": 1234,
1294
+ "##ubig": 1235,
1295
+ "##§r": 1236,
1296
+ "##akt": 1237,
1297
+ "##dlak": 1238,
1298
+ "##gk": 1239,
1299
+ "##ll": 1240,
1300
+ "##ż": 1241,
1301
+ "##ħh": 1242,
1302
+ "##akop": 1243,
1303
+ "##big": 1244,
1304
+ "##iez": 1245,
1305
+ "##³l": 1246,
1306
+ "##ahab": 1247,
1307
+ "##ahabo": 1248,
1308
+ "##ahabog": 1249,
1309
+ "##naha": 1250,
1310
+ "Ġkw": 1251,
1311
+ "Ġkwa": 1252,
1312
+ "##Å«": 1253,
1313
+ "##é": 1254,
1314
+ "##¡rÃ": 1255,
1315
+ "##árÃ": 1256,
1316
+ "##idlaka": 1257,
1317
+ "##idlakan": 1258,
1318
+ "Ġpa": 1259,
1319
+ "##habo": 1260,
1320
+ "##yon": 1261,
1321
+ "##go": 1262,
1322
+ "##ngo": 1263,
1323
+ "##ghim": 1264,
1324
+ "##aghim": 1265,
1325
+ "##Äģ": 1266,
1326
+ "##biz": 1267,
1327
+ "##ira": 1268,
1328
+ "##oÄ": 1269,
1329
+ "##º¿t": 1270,
1330
+ "Ġkinai": 1271,
1331
+ "##inabu": 1272,
1332
+ "##nty": 1273,
1333
+ "##pre": 1274,
1334
+ "##¡r": 1275,
1335
+ "##ár": 1276,
1336
+ "##¤k": 1277,
1337
+ "##äk": 1278,
1338
+ "##laka": 1279,
1339
+ "##ler": 1280,
1340
+ "##lerr": 1281,
1341
+ "##lerri": 1282,
1342
+ "##·¯": 1283,
1343
+ "##bog": 1284,
1344
+ "##inau": 1285,
1345
+ "##»ĵ": 1286,
1346
+ "##hp": 1287,
1347
+ "##hÃ": 1288,
1348
+ "Ġre": 1289,
1349
+ "##igan": 1290,
1350
+ "##kaz": 1291,
1351
+ "##gsa": 1292,
1352
+ "##zon": 1293,
1353
+ "##aso": 1294,
1354
+ "##gwa": 1295,
1355
+ "##Ńj": 1296,
1356
+ "Ġul": 1297,
1357
+ "##syo": 1298,
1358
+ "##agsa": 1299,
1359
+ "##tor": 1300,
1360
+ "##gtor": 1301,
1361
+ "##ĦØ": 1302,
1362
+ "##ÙĦØ": 1303,
1363
+ "Âł": 1304,
1364
+ "##hiy": 1305,
1365
+ "##ima": 1306,
1366
+ "##³n": 1307,
1367
+ "##dp": 1308,
1368
+ "##Łi": 1309,
1369
+ "##RE": 1310,
1370
+ "##rang": 1311,
1371
+ "##á»": 1312,
1372
+ "##eu": 1313,
1373
+ "##eud": 1314,
1374
+ "##eude": 1315,
1375
+ "##lagsa": 1316,
1376
+ "##tuz": 1317,
1377
+ "##tuzt": 1318,
1378
+ "##tuzten": 1319,
1379
+ "##¼j": 1320,
1380
+ "##¼jo": 1321,
1381
+ "##zo": 1322,
1382
+ "##jon": 1323,
1383
+ "##lig": 1324,
1384
+ "##azz": 1325,
1385
+ "##bu": 1326,
1386
+ "##abu": 1327,
1387
+ "##nÄ": 1328
1388
+ }
1389
+ }
1390
+ }
fw57Mmulti_Surprisal_threshold_256000/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_Surprisal_threshold_256000/vocab.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<|padding|>": 0, "<|endoftext|>": 1, "\u0120\u00f5": 2, "\u00f5": 3, "##\u00f5": 4, "\u0120\u00f6": 5, "\u00f6": 6, "##\u00f6": 7, "\u0120\u00aa": 8, "\u00aa": 9, "##\u00aa": 10, "\u0120\u013d": 11, "\u013d": 12, "##\u013d": 13, "\u0120\u0110": 14, "\u0110": 15, "##\u0110": 16, "`": 17, "##`": 18, ".": 19, "##.": 20, "\u0120O": 21, "O": 22, "##O": 23, "\u00ae": 24, "##\u00ae": 25, "\u00bd": 26, "##\u00bd": 27, "\u0120F": 28, "F": 29, "##F": 30, "\u0120\u00e1": 31, "\u00e1": 32, "##\u00e1": 33, "\u0120\u00f8": 34, "\u00f8": 35, "##\u00f8": 36, "\u0120T": 37, "T": 38, "##T": 39, "\"": 40, "##\"": 41, "9": 42, "##9": 43, "\u00a5": 44, "##\u00a5": 45, "\u00b8": 46, "##\u00b8": 47, "_": 48, "##_": 49, "\u0120B": 50, "B": 51, "##B": 52, "\u0120\u013a": 53, "\u013a": 54, "##\u013a": 55, "\u0120\u00c8": 56, "\u00c8": 57, "##\u00c8": 58, "\u0120\u00c4": 59, "\u00c4": 60, "##\u00c4": 61, "\u0120\u0137": 62, "\u0137": 63, "##\u0137": 64, "\u00a4": 65, "##\u00a4": 66, "\u0120o": 67, "o": 68, "##o": 69, "\u0120\u012e": 70, "\u012e": 71, "##\u012e": 72, "\u0120\u00f0": 73, "\u00f0": 74, "##\u00f0": 75, "\\": 76, "##\\": 77, "\u0120\u013f": 78, "\u013f": 79, "##\u013f": 80, "^": 81, "##^": 82, "\u0120\u010a": 83, "\u010a": 84, "##\u010a": 85, "\u0120j": 86, "j": 87, "##j": 88, "\u0120n": 89, "n": 90, "##n": 91, "\u0120": 92, "##\u0120": 93, "\u0120\u00fe": 94, "\u00fe": 95, "##\u00fe": 96, "\u0120D": 97, "D": 98, "##D": 99, "\u0120\u0114": 100, "\u0114": 101, "##\u0114": 102, "\u0120L": 103, "L": 104, "##L": 105, "\u0120\u00e5": 106, "\u00e5": 107, "##\u00e5": 108, "\u0120J": 109, "J": 110, "##J": 111, "\u0120e": 112, "e": 113, "##e": 114, "\u0120u": 115, "u": 116, "##u": 117, "\u0120\u0104": 118, "\u0104": 119, "##\u0104": 120, "\u0120\u0131": 121, "\u0131": 122, "##\u0131": 123, "\u0120\u0134": 124, "\u0134": 125, "##\u0134": 126, "*": 127, "##*": 128, "5": 129, "##5": 130, "\u0120\u0116": 131, "\u0116": 132, "##\u0116": 133, "\u0120\u010e": 134, "\u010e": 135, "##\u010e": 136, "\u0120\u0122": 137, "\u0122": 138, "##\u0122": 139, "\u0120Y": 140, "Y": 141, "##Y": 142, "\u0120\u00dc": 143, "\u00dc": 144, "##\u00dc": 145, ";": 146, "##;": 147, "\u00bf": 148, "##\u00bf": 149, "~": 150, "##~": 151, "2": 152, "##2": 153, "\u00b4": 154, "##\u00b4": 155, "\u00a6": 156, "##\u00a6": 157, "\u0120\u00c0": 158, "\u00c0": 159, "##\u00c0": 160, "\u0120\u00e9": 161, "\u00e9": 162, "##\u00e9": 163, "\u0120\u0127": 164, "\u0127": 165, "##\u0127": 166, "\u00a2": 167, "##\u00a2": 168, "\u0120\u011a": 169, "\u011a": 170, "##\u011a": 171, "\u0120\u00e3": 172, "\u00e3": 173, "##\u00e3": 174, "\u0120\u0119": 175, "\u0119": 176, "##\u0119": 177, "(": 178, "##(": 179, "\u00ac": 180, "##\u00ac": 181, "\u00ab": 182, "##\u00ab": 183, "6": 184, "##6": 185, "\u0120E": 186, "E": 187, "##E": 188, "\u00a3": 189, "##\u00a3": 190, "\u0120g": 191, "g": 192, "##g": 193, "\u00b9": 194, "##\u00b9": 195, "\u0120\u0105": 196, "\u0105": 197, "##\u0105": 198, "8": 199, "##8": 200, "-": 201, "##-": 202, "\u00a8": 203, "##\u00a8": 204, "&": 205, "##&": 206, "\u0120\u012b": 207, "\u012b": 208, "##\u012b": 209, "\u0120\u0103": 210, "\u0103": 211, "##\u0103": 212, "\u0120\u00ca": 213, "\u00ca": 214, "##\u00ca": 215, "\u0120Q": 216, "Q": 217, "##Q": 218, "\u0120\u0100": 219, "\u0100": 220, "##\u0100": 221, "\u0120\u0132": 222, "\u0132": 223, "##\u0132": 224, "\u0120\u00c6": 225, "\u00c6": 226, "##\u00c6": 227, "\u0120V": 228, "V": 229, "##V": 230, "\u0120\u00c9": 231, "\u00c9": 232, "##\u00c9": 233, "\u00a7": 234, "##\u00a7": 235, "\u0120\u011d": 236, "\u011d": 237, "##\u011d": 238, "\u0120\u0143": 239, "\u0143": 240, "##\u0143": 241, "\u0120\u00da": 242, "\u00da": 243, "##\u00da": 244, "\u0120\u0135": 245, "\u0135": 246, "##\u0135": 247, "\u0120\u00b5": 248, "\u00b5": 249, "##\u00b5": 250, "\u00b6": 251, "##\u00b6": 252, "\u0120P": 253, "P": 254, "##P": 255, "\u0120\u0133": 256, "\u0133": 257, "##\u0133": 258, "\u00b2": 259, "##\u00b2": 260, "\u0120\u00ce": 261, "\u00ce": 262, "##\u00ce": 263, "\u0120\u00e2": 264, "\u00e2": 265, "##\u00e2": 266, "\u0120S": 267, "S": 268, "##S": 269, "\u0120\u00c7": 270, "\u00c7": 271, "##\u00c7": 272, "\u0120\u010c": 273, "\u010c": 274, "##\u010c": 275, "\u0120I": 276, "I": 277, "##I": 278, "\u0120H": 279, "H": 280, "##H": 281, "|": 282, "##|": 283, "\u0120\u00dd": 284, "\u00dd": 285, "##\u00dd": 286, "\u0120\u0117": 287, "\u0117": 288, "##\u0117": 289, "\u00d7": 290, "##\u00d7": 291, "\u0120x": 292, "x": 293, "##x": 294, "\u0120\u0101": 295, "\u0101": 296, "##\u0101": 297, "\u0120\u0136": 298, "\u0136": 299, "##\u0136": 300, "\u0120\u011e": 301, "\u011e": 302, "##\u011e": 303, "'": 304, "##'": 305, "\u0120\u0129": 306, "\u0129": 307, "##\u0129": 308, "\u0120\u0125": 309, "\u0125": 310, "##\u0125": 311, "\u0120q": 312, "q": 313, "##q": 314, "@": 315, "##@": 316, "\u0120p": 317, "p": 318, "##p": 319, "\u0120w": 320, "w": 321, "##w": 322, "!": 323, "##!": 324, "#": 325, "###": 326, "\u0120f": 327, "f": 328, "##f": 329, "\u00be": 330, "##\u00be": 331, "\u0120\u00d2": 332, "\u00d2": 333, "##\u00d2": 334, "\u0120\u00d9": 335, "\u00d9": 336, "##\u00d9": 337, "\u0120\u00e7": 338, "\u00e7": 339, "##\u00e7": 340, ">": 341, "##>": 342, "\u0120\u00c1": 343, "\u00c1": 344, "##\u00c1": 345, "\u0120\u00ed": 346, "\u00ed": 347, "##\u00ed": 348, "0": 349, "##0": 350, ")": 351, "##)": 352, "\u0120\u00fa": 353, "\u00fa": 354, "##\u00fa": 355, "]": 356, "##]": 357, "\u0120\u00f1": 358, "\u00f1": 359, "##\u00f1": 360, "\u0120\u012d": 361, "\u012d": 362, "##\u012d": 363, "\u0120\u0139": 364, "\u0139": 365, "##\u0139": 366, "\u0120\u0108": 367, "\u0108": 368, "##\u0108": 369, "\u0120\u00d6": 370, "\u00d6": 371, "##\u00d6": 372, "\u0120\u00f4": 373, "\u00f4": 374, "##\u00f4": 375, "\u0120\u0118": 376, "\u0118": 377, "##\u0118": 378, "\u0120\u0128": 379, "\u0128": 380, "##\u0128": 381, "\u0120K": 382, "K": 383, "##K": 384, "\u0120h": 385, "h": 386, "##h": 387, "\u0120i": 388, "i": 389, "##i": 390, "\u0120\u00ba": 391, "\u00ba": 392, "##\u00ba": 393, "\u0120\u0113": 394, "\u0113": 395, "##\u0113": 396, "\u0120\u00e6": 397, "\u00e6": 398, "##\u00e6": 399, "\u0120t": 400, "t": 401, "##t": 402, "\u0120\u00ee": 403, "\u00ee": 404, "##\u00ee": 405, "1": 406, "##1": 407, "\u0120y": 408, "y": 409, "##y": 410, "\u0120\u00cd": 411, "\u00cd": 412, "##\u00cd": 413, "\u0120\u00c2": 414, "\u00c2": 415, "##\u00c2": 416, "\u0120\u010b": 417, "\u010b": 418, "##\u010b": 419, "\u0120\u00d8": 420, "\u00d8": 421, "##\u00d8": 422, "\u0120\u00cc": 423, "\u00cc": 424, "##\u00cc": 425, "\u0120\u013b": 426, "\u013b": 427, "##\u013b": 428, ":": 429, "##:": 430, "\u0120M": 431, "M": 432, "##M": 433, "\u0120a": 434, "a": 435, "##a": 436, "\u0120G": 437, "G": 438, "##G": 439, "\u00f7": 440, "##\u00f7": 441, "\u0120\u013e": 442, "\u013e": 443, "##\u013e": 444, "\u0120k": 445, "k": 446, "##k": 447, "\u0120W": 448, "W": 449, "##W": 450, "\u0120\u00db": 451, "\u00db": 452, "##\u00db": 453, "\u0120A": 454, "A": 455, "##A": 456, "\u0120\u0130": 457, "\u0130": 458, "##\u0130": 459, "\u0120\u00de": 460, "\u00de": 461, "##\u00de": 462, "\u0120\u00e0": 463, "\u00e0": 464, "##\u00e0": 465, "\u00b7": 466, "##\u00b7": 467, "\u0120\u00ff": 468, "\u00ff": 469, "##\u00ff": 470, "[": 471, "##[": 472, "=": 473, "##=": 474, "\u0120\u00d1": 475, "\u00d1": 476, "##\u00d1": 477, "\u0120\u010d": 478, "\u010d": 479, "##\u010d": 480, "\u0120X": 481, "X": 482, "##X": 483, "\u0120\u00cb": 484, "\u00cb": 485, "##\u00cb": 486, "\u0120Z": 487, "Z": 488, "##Z": 489, "\u0120\u0102": 490, "\u0102": 491, "##\u0102": 492, "\u0120\u012c": 493, "\u012c": 494, "##\u012c": 495, "\u0120\u010f": 496, "\u010f": 497, "##\u010f": 498, "\u0120\u00fd": 499, "\u00fd": 500, "##\u00fd": 501, "+": 502, "##+": 503, "\u0120U": 504, "U": 505, "##U": 506, "\u0120z": 507, "z": 508, "##z": 509, "\u0120\u00fc": 510, "\u00fc": 511, "##\u00fc": 512, "\u0120\u0123": 513, "\u0123": 514, "##\u0123": 515, "\u00bb": 516, "##\u00bb": 517, "\u0120\u00d0": 518, "\u00d0": 519, "##\u00d0": 520, "\u0120\u0121": 521, "\u0121": 522, "##\u0121": 523, "\u0120\u00eb": 524, "\u00eb": 525, "##\u00eb": 526, "\u0120N": 527, "N": 528, "##N": 529, "\u0120R": 530, "R": 531, "##R": 532, "\u0120\u0111": 533, "\u0111": 534, "##\u0111": 535, "\u0120\u00ea": 536, "\u00ea": 537, "##\u00ea": 538, "\u0120\u00f2": 539, "\u00f2": 540, "##\u00f2": 541, "\u0120\u00fb": 542, "\u00fb": 543, "##\u00fb": 544, "{": 545, "##{": 546, "\u0120m": 547, "m": 548, "##m": 549, "\u00a9": 550, "##\u00a9": 551, "\u0120\u0138": 552, "\u0138": 553, "##\u0138": 554, "\u0120\u0124": 555, "\u0124": 556, "##\u0124": 557, "\u0120\u00e4": 558, "\u00e4": 559, "##\u00e4": 560, "\u0120\u00d3": 561, "\u00d3": 562, "##\u00d3": 563, "\u0120\u00f9": 564, "\u00f9": 565, "##\u00f9": 566, "$": 567, "##$": 568, "\u0120\u011b": 569, "\u011b": 570, "##\u011b": 571, "\u00af": 572, "##\u00af": 573, "\u0120s": 574, "s": 575, "##s": 576, "\u0120\u00c5": 577, "\u00c5": 578, "##\u00c5": 579, "\u0120v": 580, "v": 581, "##v": 582, "\u00b0": 583, "##\u00b0": 584, ",": 585, "##,": 586, "\u0120\u00f3": 587, "\u00f3": 588, "##\u00f3": 589, "\u0120\u0140": 590, "\u0140": 591, "##\u0140": 592, "\u0120\u0107": 593, "\u0107": 594, "##\u0107": 595, "\u0120\u0142": 596, "\u0142": 597, "##\u0142": 598, "\u0120\u00df": 599, "\u00df": 600, "##\u00df": 601, "4": 602, "##4": 603, "\u0120\u00d4": 604, "\u00d4": 605, "##\u00d4": 606, "\u0120\u012f": 607, "\u012f": 608, "##\u012f": 609, "\u0120\u011c": 610, "\u011c": 611, "##\u011c": 612, "%": 613, "##%": 614, "\u0120\u00cf": 615, "\u00cf": 616, "##\u00cf": 617, "}": 618, "##}": 619, "\u0120\u00ec": 620, "\u00ec": 621, "##\u00ec": 622, "\u0120\u013c": 623, "\u013c": 624, "##\u013c": 625, "\u0120\u0112": 626, "\u0112": 627, "##\u0112": 628, "\u00a1": 629, "##\u00a1": 630, "\u0120\u00c3": 631, "\u00c3": 632, "##\u00c3": 633, "\u0120\u00d5": 634, "\u00d5": 635, "##\u00d5": 636, "\u0120\u0115": 637, "\u0115": 638, "##\u0115": 639, "\u0120\u0126": 640, "\u0126": 641, "##\u0126": 642, "\u0120\u012a": 643, "\u012a": 644, "##\u012a": 645, "\u0120r": 646, "r": 647, "##r": 648, "\u0120\u0106": 649, "\u0106": 650, "##\u0106": 651, "\u0120\u011f": 652, "\u011f": 653, "##\u011f": 654, "\u0120c": 655, "c": 656, "##c": 657, "\u0120C": 658, "C": 659, "##C": 660, "<": 661, "##<": 662, "\u00bc": 663, "##\u00bc": 664, "\u0120\u0109": 665, "\u0109": 666, "##\u0109": 667, "\u0120l": 668, "l": 669, "##l": 670, "3": 671, "##3": 672, "?": 673, "##?": 674, "\u00b1": 675, "##\u00b1": 676, "\u0120\u00ef": 677, "\u00ef": 678, "##\u00ef": 679, "\u00b3": 680, "##\u00b3": 681, "\u0120b": 682, "b": 683, "##b": 684, "\u0120d": 685, "d": 686, "##d": 687, "\u0120\u00e8": 688, "\u00e8": 689, "##\u00e8": 690, "\u0120\u0141": 691, "\u0141": 692, "##\u0141": 693, "7": 694, "##7": 695, "/": 696, "##/": 697, "<|unk|>": 698, "##\u00c3\u00a4": 699, "##\u00c3\u00a4\u00c3": 700, "##it": 701, "##an": 702, "##as": 703, "##asa": 704, "##ge": 705, "##de": 706, "##bi": 707, "##ga": 708, "##ta": 709, "##ang": 710, "##pa": 711, "##le": 712, "##ng": 713, "##na": 714, "##ina": 715, ":/": 716, "##en": 717, "##ra": 718, "##den": 719, "##ro": 720, "##on": 721, "##bo": 722, "##ibo": 723, "##ci": 724, "##ul": 725, "##\u00ba\u0143": 726, "##mu": 727, "##in": 728, "##ma": 729, "##ah": 730, "##ar": 731, "##ai": 732, "##nai": 733, "##aci": 734, "##sa": 735, "##inai": 736, "##ba": 737, "##uo": 738, "##bab": 739, "##ir": 740, "##ire": 741, "##baba": 742, "##\u00b6\u00c3": 743, "##iz": 744, "##ni": 745, "##ri": 746, "##rri": 747, "##erri": 748, "##gan": 749, "##nt": 750, "##te": 751, "##ab": 752, "##gs": 753, "##ags": 754, "##zt": 755, "##zte": 756, "##zten": 757, "##la": 758, "##aba": 759, "##tr": 760, "##tro": 761, "##eh": 762, "##ahi": 763, "##ahin": 764, "##ep": 765, "##ion": 766, "##00": 767, "##pi": 768, "##re": 769, "##\u00c3\u00b6": 770, "##ue": 771, "##ak": 772, "##..": 773, "##ia": 774, "##ssa": 775, "##at": 776, "##ob": 777, "##ag": 778, "##aga": 779, "##so": 780, "##dl": 781, "##rt": 782, "##tt": 783, "##\u00bcl": 784, "##\u0143t": 785, "##\u00ba\u0143t": 786, "##od": 787, "##um": 788, "##gang": 789, "##ngang": 790, "##lo": 791, "##bre": 792, "##tj": 793, "##abi": 794, "##ik": 795, "##ros": 796, "##bit": 797, "##ie": 798, "##ien": 799, "##ap": 800, "##og": 801, "##\u00a1l": 802, "##ek": 803, "##eka": 804, "##etro": 805, "##ay": 806, "##baga": 807, "##abaga": 808, "##au": 809, "##hi": 810, "##him": 811, "##hin": 812, "##zi": 813, "##\u00c3\u0143": 814, "##to": 815, "##ekak": 816, "##ot": 817, "##bot": 818, "##ibot": 819, "##abo": 820, "##\u00a4l": 821, "##et": 822, "##ad": 823, "##er": 824, "##ti": 825, "##ao": 826, "##op": 827, "##om": 828, "##ha": 829, "##aha": 830, "##err": 831, "##ran": 832, "##sod": 833, "##ae": 834, "##sar": 835, "##im": 836, "##ahim": 837, "##ig": 838, "##ib": 839, "##da": 840, "##\u00e1\u00ba": 841, "##si": 842, "##asi": 843, "##ya": 844, "##al": 845, "##mi": 846, "##ala": 847, "##ur": 848, "##iy": 849, "##os": 850, "##fi": 851, "##abag": 852, "##ch": 853, "##\u00c3\u0142": 854, "##ko": 855, "##\u00c3\u0142i": 856, "##ali": 857, "##alib": 858, "##alibo": 859, "##tan": 860, "##li": 861, "##wa": 862, "##mb": 863, "##gh": 864, "##pt": 865, "##pti": 866, "\u0120na": 867, "##libo": 868, "##nay": 869, "##asod": 870, "##ero": 871, "An": 872, "Ang": 873, "##pu": 874, "##himu": 875, "##dt": 876, "##dto": 877, "##oh": 878, "##\u00a4t": 879, "##etr": 880, "##\u00c4\u00b1": 881, "##ata": 882, "##io": 883, "##\u00bb\u012f": 884, "##es": 885, "##ila": 886, "##oga": 887, "\u0120ki": 888, "\u0120kin": 889, "\u0120kina": 890, "##\u00a4\u00c3": 891, "##uj": 892, "##is": 893, "\u00e0\u00a4": 894, "##nga": 895, "##ngan": 896, "##imu": 897, "##uk": 898, "##uki": 899, "##ukir": 900, "##ukira": 901, "##ukiran": 902, "##inab": 903, "##rr": 904, "\u0120la": 905, "\u0120lal": 906, "##wig": 907, "##ehi": 908, "##tz": 909, "##han": 910, "##ren": 911, "##iren": 912, "##res": 913, "##ntz": 914, "\u0120lala": 915, "##\u00bb\u013d": 916, "##no": 917, "##\u00a9s": 918, "##mo": 919, "##omo": 920, "##lags": 921, "##kti": 922, "##akti": 923, "##libot": 924, "##alibot": 925, "##\u00d9\u012c": 926, "##ts": 927, "##rts": 928, "##erts": 929, "\u0120da": 930, "an": 931, "##ong": 932, "##asar": 933, "##pan": 934, "##ten": 935, "##yo": 936, "##oa": 937, "##tod": 938, "##itz": 939, "##il": 940, "##uden": 941, "##ebi": 942, "##ahimu": 943, "##izi": 944, "##bizi": 945, "##or": 946, "\u0120sa": 947, "##ana": 948, "##em": 949, "##me": 950, "##ka": 951, "##aka": 952, "##id": 953, "##idl": 954, "##idla": 955, "##lag": 956, "\u0120ka": 957, "\u0120kas": 958, "\u0120kasa": 959, "\u0120kasar": 960, "##gw": 961, "##do": 962, "##ing": 963, "##ua": 964, "##\u0141\u00c4": 965, "##o\u00c3\u0142": 966, "##akar": 967, "##ume": 968, "##hong": 969, "##lu": 970, "##alu": 971, "\u0120an": 972, "\u0120ang": 973, "##eme": 974, "##ug": 975, "##uz": 976, "##am": 977, "##kop": 978, "##wi": 979, "##\u00c3\u00a4n": 980, "##arr": 981, "##\u00c4\u013d": 982, "##gat": 983, "##met": 984, "##lib": 985, "##tu": 986, "##gt": 987, "##gto": 988, "##gtod": 989, "##\u00a7\u00c3": 990, "##//": 991, "##kan": 992, "##nd": 993, "##and": 994, "##dad": 995, "##ou": 996, "##oun": 997, "##\u0141u": 998, "##o\u00c3": 999, "##ghi": 1000, "##eek": 1001, "\u00c2\u00b0": 1002, "##ud": 1003, "##ude": 1004, "##aa": 1005, "##aan": 1006, "##tang": 1007, "##un": 1008, "##nit": 1009, "##st": 1010, "##sta": 1011, "##ol": 1012, "##ez": 1013, "\u0120es": 1014, "\u0120est": 1015, "##\u00c3\u00b8": 1016, "##ku": 1017, "##nda": 1018, "##za": 1019, "##zar": 1020, "##np": 1021, "##ilo": 1022, "##dla": 1023, "\u0120zi": 1024, "\u0120zir": 1025, "\u0120zire": 1026, "\u0120ziren": 1027, "##pr": 1028, "##npr": 1029, "##ac": 1030, "##ns": 1031, "##dpa": 1032, "##adpa": 1033, "##sadpa": 1034, "##asadpa": 1035, "##eta": 1036, "##eg": 1037, "##ita": 1038, "##nita": 1039, "##ung": 1040, "##\u00a1n": 1041, "##\u00b8j": 1042, "##ntro": 1043, "##son": 1044, "##\u00a1n\u00c3": 1045, "##\u00a1n\u00c3\u0143": 1046, "##\u013dn": 1047, "##po": 1048, "##pon": 1049, "##pong": 1050, "##bag": 1051, "##ho": 1052, "##hon": 1053, "##uzte": 1054, "##alags": 1055, "##\u00b3w": 1056, "##aw": 1057, "##m\u00c3": 1058, "##m\u00c3\u00b3": 1059, "##ub": 1060, "##euden": 1061, "##ado": 1062, "##i\u00c4": 1063, "##ne": 1064, "##nes": 1065, "##ora": 1066, "##ini": 1067, "\u0120ng": 1068, "\u0120nga": 1069, "##tzi": 1070, "##\u00c3\u00b3": 1071, "##kar": 1072, "##akan": 1073, "##lakan": 1074, "##\u00e1\u00ba\u0143": 1075, "##sy": 1076, "##se": 1077, "##eae": 1078, "##ceae": 1079, "##\u00a1d": 1080, "##agat": 1081, "\u0120dag": 1082, "##ea": 1083, "##tros": 1084, "##adp": 1085, "://": 1086, "##\u00c5\u013b": 1087, "##ve": 1088, "##ver": 1089, "##nito": 1090, "##lak": 1091, "##alag": 1092, "##alagsa": 1093, "##baw": 1094, "##ow": 1095, "##uzten": 1096, "##oka": 1097, "##lus": 1098, "##\u0122\u013b": 1099, "##abit": 1100, "##metr": 1101, "##metro": 1102, "##ona": 1103, "##uba": 1104, "##\u00bft": 1105, "\u0120gi": 1106, "##ki": 1107, "\u0120ta": 1108, "##br": 1109, "##awi": 1110, "##eb": 1111, "##ih": 1112, "##biy": 1113, "##\u00b9\u00b4": 1114, "##agw": 1115, "##bita": 1116, "##abita": 1117, "habita": 1118, "##ert": 1119, "##sad": 1120, "##asad": 1121, "##n\u00c3": 1122, "##ito": 1123, "##ss": 1124, "##\u00c5\u0141": 1125, "##\u00e1\u00ba\u0143t": 1126, "\u0120nah": 1127, "\u0120nahi": 1128, "\u0120nahim": 1129, "##\u00b1\u00c5\u0141": 1130, "##ura": 1131, "##uran": 1132, "##kt": 1133, "##tza": 1134, "##ld": 1135, "\u0120km": 1136, "##itu": 1137, "##asadp": 1138, "##\u00c3\u00aa": 1139, "##\u00c3\u00ba": 1140, "##kir": 1141, "\u0120An": 1142, "\u0120Ang": 1143, "##mak": 1144, "##\u00c3\u00a1": 1145, "##\u00c3\u00a1g": 1146, "##sadp": 1147, "##sadpan": 1148, "##enda": 1149, "##gi": 1150, "##\u00c4\u012d": 1151, "##co": 1152, "\u0120ph": 1153, "##rg": 1154, "##kira": 1155, "##kiran": 1156, "##kang": 1157, "##akang": 1158, "##lakang": 1159, "##dlakang": 1160, "##idlakang": 1161, "##i\u00c3": 1162, "##i\u00c3\u00b3": 1163, "##ako": 1164, "##we": 1165, "##ysa": 1166, "##rop": 1167, "##ika": 1168, "##az": 1169, "##jo": 1170, "##zz": 1171, "##ula": 1172, "##\u00a5d": 1173, "##\u00bcu": 1174, "##be": 1175, "##\u00c4\u00a7": 1176, "##tso": 1177, "##tson": 1178, "##iet": 1179, "##\u00a7h": 1180, "##ami": 1181, "##\u00a7a": 1182, "##ee": 1183, "##\u00c3\u00a5d": 1184, "##\u0133l": 1185, "##\u00a7o": 1186, "##nah": 1187, "##\u00b1m": 1188, "##\u00c4\u00a7a": 1189, "##abaw": 1190, "##ihan": 1191, "##utang": 1192, "##mutang": 1193, "##AT": 1194, "\u0120pu": 1195, "\u0120ze": 1196, "##us": 1197, "\u0120ni": 1198, "##\u00bci": 1199, "##bl": 1200, "##bli": 1201, "##ikaz": 1202, "##ut": 1203, "##uen": 1204, "##ate": 1205, "##\u00a1g": 1206, "##r\u00c4": 1207, "##ent": 1208, "##\u00a9g": 1209, "##zj": 1210, "##\u0143m": 1211, "##cia": 1212, "##oz": 1213, "##\u00e0\u00a4": 1214, "##r\u00c3": 1215, "##\u00c4\u012de": 1216, "##\u00a4\u0124": 1217, "##el": 1218, "##\u012di": 1219, "##ru": 1220, "##las": 1221, "##ulas": 1222, "##iran": 1223, "##idlak": 1224, "##bagat": 1225, "##abagat": 1226, "##iyo": 1227, "##ye": 1228, "##pres": 1229, "##npres": 1230, "##DE": 1231, "##tuzte": 1232, "##kai": 1233, "##ubi": 1234, "##ubig": 1235, "##\u00a7r": 1236, "##akt": 1237, "##dlak": 1238, "##gk": 1239, "##ll": 1240, "##\u00c5\u00bc": 1241, "##\u00c4\u00a7h": 1242, "##akop": 1243, "##big": 1244, "##iez": 1245, "##\u00b3l": 1246, "##ahab": 1247, "##ahabo": 1248, "##ahabog": 1249, "##naha": 1250, "\u0120kw": 1251, "\u0120kwa": 1252, "##\u00c5\u00ab": 1253, "##\u00c3\u00a9": 1254, "##\u00a1r\u00c3": 1255, "##\u00c3\u00a1r\u00c3": 1256, "##idlaka": 1257, "##idlakan": 1258, "\u0120pa": 1259, "##habo": 1260, "##yon": 1261, "##go": 1262, "##ngo": 1263, "##ghim": 1264, "##aghim": 1265, "##\u00c4\u0123": 1266, "##biz": 1267, "##ira": 1268, "##o\u00c4": 1269, "##\u00ba\u00bft": 1270, "\u0120kinai": 1271, "##inabu": 1272, "##nty": 1273, "##pre": 1274, "##\u00a1r": 1275, "##\u00c3\u00a1r": 1276, "##\u00a4k": 1277, "##\u00c3\u00a4k": 1278, "##laka": 1279, "##ler": 1280, "##lerr": 1281, "##lerri": 1282, "##\u00b7\u00af": 1283, "##bog": 1284, "##inau": 1285, "##\u00bb\u0135": 1286, "##hp": 1287, "##h\u00c3": 1288, "\u0120re": 1289, "##igan": 1290, "##kaz": 1291, "##gsa": 1292, "##zon": 1293, "##aso": 1294, "##gwa": 1295, "##\u0143j": 1296, "\u0120ul": 1297, "##syo": 1298, "##agsa": 1299, "##tor": 1300, "##gtor": 1301, "##\u0126\u00d8": 1302, "##\u00d9\u0126\u00d8": 1303, "\u00c2\u0142": 1304, "##hiy": 1305, "##ima": 1306, "##\u00b3n": 1307, "##dp": 1308, "##\u0141i": 1309, "##RE": 1310, "##rang": 1311, "##\u00e1\u00bb": 1312, "##eu": 1313, "##eud": 1314, "##eude": 1315, "##lagsa": 1316, "##tuz": 1317, "##tuzt": 1318, "##tuzten": 1319, "##\u00bcj": 1320, "##\u00bcjo": 1321, "##zo": 1322, "##jon": 1323, "##lig": 1324, "##azz": 1325, "##bu": 1326, "##abu": 1327, "##n\u00c4": 1328}