michelleyunun commited on
Commit
1b81239
·
1 Parent(s): 7df621a

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +2 -1
  2. tokenizer.json +1911 -1901
  3. tokenizer_config.json +1 -0
special_tokens_map.json CHANGED
@@ -1,3 +1,4 @@
1
  {
2
- "eos_token": "<end>"
 
3
  }
 
1
  {
2
+ "eos_token": "<end>",
3
+ "pad_token": "<pad>"
4
  }
tokenizer.json CHANGED
@@ -11,6 +11,15 @@
11
  "rstrip": false,
12
  "normalized": false,
13
  "special": true
 
 
 
 
 
 
 
 
 
14
  }
15
  ],
16
  "normalizer": null,
@@ -39,1907 +48,1908 @@
39
  "byte_fallback": false,
40
  "vocab": {
41
  "<end>": 0,
42
- "!": 1,
43
- "\"": 2,
44
- "'": 3,
45
- "(": 4,
46
- ")": 5,
47
- ",": 6,
48
- "-": 7,
49
- ".": 8,
50
- "0": 9,
51
- "1": 10,
52
- "2": 11,
53
- "3": 12,
54
- "4": 13,
55
- "5": 14,
56
- "6": 15,
57
- "7": 16,
58
- "8": 17,
59
- "9": 18,
60
- ":": 19,
61
- "?": 20,
62
- "A": 21,
63
- "B": 22,
64
- "C": 23,
65
- "D": 24,
66
- "E": 25,
67
- "F": 26,
68
- "G": 27,
69
- "H": 28,
70
- "I": 29,
71
- "J": 30,
72
- "K": 31,
73
- "L": 32,
74
- "M": 33,
75
- "N": 34,
76
- "O": 35,
77
- "P": 36,
78
- "Q": 37,
79
- "R": 38,
80
- "S": 39,
81
- "T": 40,
82
- "U": 41,
83
- "V": 42,
84
- "W": 43,
85
- "Y": 44,
86
- "Z": 45,
87
- "a": 46,
88
- "b": 47,
89
- "c": 48,
90
- "d": 49,
91
- "e": 50,
92
- "f": 51,
93
- "g": 52,
94
- "h": 53,
95
- "i": 54,
96
- "j": 55,
97
- "k": 56,
98
- "l": 57,
99
- "m": 58,
100
- "n": 59,
101
- "o": 60,
102
- "p": 61,
103
- "q": 62,
104
- "r": 63,
105
- "s": 64,
106
- "t": 65,
107
- "u": 66,
108
- "v": 67,
109
- "w": 68,
110
- "x": 69,
111
- "y": 70,
112
- "z": 71,
113
- "«": 72,
114
- "»": 73,
115
- "": 74,
116
- "": 75,
117
- "": 76,
118
- "AO": 77,
119
- "th": 78,
120
- "ER": 79,
121
- "er": 80,
122
- "AOR": 81,
123
- "ERG": 82,
124
- "EN": 83,
125
- "ay": 84,
126
- "AT": 85,
127
- "in": 86,
128
- "DAT": 87,
129
- "SS": 88,
130
- "say": 89,
131
- "sg": 90,
132
- "en": 91,
133
- "on": 92,
134
- "NE": 93,
135
- "is": 94,
136
- "at": 95,
137
- "ENT": 96,
138
- "1sg": 97,
139
- "re": 98,
140
- "MP": 99,
141
- "an": 100,
142
- "INE": 101,
143
- "ing": 102,
144
- "se": 103,
145
- "be": 104,
146
- "IMP": 105,
147
- "ou": 106,
148
- "INESS": 107,
149
- "ab": 108,
150
- "one": 109,
151
- "AOC": 110,
152
- "FO": 111,
153
- "FOC": 112,
154
- "GEN": 113,
155
- "abs": 114,
156
- "pl": 115,
157
- "this": 116,
158
- "PL": 117,
159
- "that": 118,
160
- "ed": 119,
161
- "ar": 120,
162
- "BL": 121,
163
- "OBL": 122,
164
- "ST": 123,
165
- "he": 124,
166
- "ap": 125,
167
- "ther": 126,
168
- "gi": 127,
169
- "DI": 128,
170
- "or": 129,
171
- "DIR": 130,
172
- "go": 131,
173
- "ke": 132,
174
- "ow": 133,
175
- "1pl": 134,
176
- "ll": 135,
177
- "IMPF": 136,
178
- "the": 137,
179
- "as": 138,
180
- "»,": 139,
181
- "me": 140,
182
- "to": 141,
183
- "co": 142,
184
- "PST": 143,
185
- "ve": 144,
186
- "app": 145,
187
- "AOP": 146,
188
- "ter": 147,
189
- "st": 148,
190
- "PSS": 149,
191
- "SPSS": 150,
192
- "ut": 151,
193
- "2sg": 152,
194
- "ake": 153,
195
- "her": 154,
196
- "PER": 155,
197
- "it": 156,
198
- "gen": 157,
199
- "happ": 158,
200
- "ro": 159,
201
- "PERF": 160,
202
- "ce": 161,
203
- "bo": 162,
204
- "now": 163,
205
- "mo": 164,
206
- "al": 165,
207
- "de": 166,
208
- "rl": 167,
209
- "ch": 168,
210
- "ur": 169,
211
- "NEG": 170,
212
- "happen": 171,
213
- "..": 172,
214
- "ND": 173,
215
- "wi": 174,
216
- "was": 175,
217
- "happened": 176,
218
- "FU": 177,
219
- "FUT": 178,
220
- "ad": 179,
221
- "so": 180,
222
- "boy": 181,
223
- "ag": 182,
224
- "do": 183,
225
- "hi": 184,
226
- "IMPV": 185,
227
- "give": 186,
228
- "girl": 187,
229
- "you": 188,
230
- "urn": 189,
231
- "CO": 190,
232
- "PT": 191,
233
- "turn": 192,
234
- "fter": 193,
235
- "here": 194,
236
- "ti": 195,
237
- "and": 196,
238
- "EMP": 197,
239
- "TEMP": 198,
240
- "li": 199,
241
- "lo": 200,
242
- ",.": 201,
243
- "after": 202,
244
- "take": 203,
245
- "PTP": 204,
246
- "SB": 205,
247
- "EL": 206,
248
- "ant": 207,
249
- "COND": 208,
250
- "ev": 209,
251
- "cop": 210,
252
- "all": 211,
253
- "know": 212,
254
- "return": 213,
255
- "sel": 214,
256
- "there": 215,
257
- "king": 216,
258
- "ESS": 217,
259
- "br": 218,
260
- "gh": 219,
261
- "want": 220,
262
- "le": 221,
263
- "msel": 222,
264
- "ent": 223,
265
- "these": 224,
266
- "AD": 225,
267
- "make": 226,
268
- "un": 227,
269
- "oun": 228,
270
- "ord": 229,
271
- "OESS": 230,
272
- "POESS": 231,
273
- "wh": 232,
274
- "himsel": 233,
275
- "himself": 234,
276
- "ame": 235,
277
- "man": 236,
278
- "come": 237,
279
- "LAT": 238,
280
- "ac": 239,
281
- "if": 240,
282
- "we": 241,
283
- "».": 242,
284
- "INELAT": 243,
285
- "with": 244,
286
- "age": 245,
287
- "what": 246,
288
- "am": 247,
289
- "fro": 248,
290
- "il": 249,
291
- "od": 250,
292
- "ok": 251,
293
- "si": 252,
294
- "vi": 253,
295
- "wo": 254,
296
- "more": 255,
297
- "ery": 256,
298
- "time": 257,
299
- "from": 258,
300
- "IN": 259,
301
- "ain": 260,
302
- "put": 261,
303
- "then": 262,
304
- "end": 263,
305
- "mother": 264,
306
- "bring": 265,
307
- "ght": 266,
308
- "day": 267,
309
- "hor": 268,
310
- "ri": 269,
311
- "us": 270,
312
- "...": 271,
313
- "horse": 272,
314
- "but": 273,
315
- "erg": 274,
316
- "art": 275,
317
- "SBST": 276,
318
- "INF": 277,
319
- "es": 278,
320
- "dog": 279,
321
- "no": 280,
322
- "ul": 281,
323
- "ount": 282,
324
- "HO": 283,
325
- "RT": 284,
326
- "fe": 285,
327
- "HORT": 286,
328
- "IM": 287,
329
- "di": 288,
330
- "te": 289,
331
- "own": 290,
332
- "also": 291,
333
- "pe": 292,
334
- "sea": 293,
335
- "they": 294,
336
- "side": 295,
337
- "fa": 296,
338
- "gr": 297,
339
- "hou": 298,
340
- "other": 299,
341
- "same": 300,
342
- "way": 301,
343
- "com": 302,
344
- "fi": 303,
345
- "fo": 304,
346
- "hu": 305,
347
- "ne": 306,
348
- "she": 307,
349
- "um": 308,
350
- "ish": 309,
351
- "ple": 310,
352
- "house": 311,
353
- "aut": 312,
354
- "for": 313,
355
- "ion": 314,
356
- "very": 315,
357
- "word": 316,
358
- "beaut": 317,
359
- "our": 318,
360
- "like": 319,
361
- "SBSS": 320,
362
- "AB": 321,
363
- "two": 322,
364
- "uch": 323,
365
- "out": 324,
366
- "order": 325,
367
- "iful": 326,
368
- "beautiful": 327,
369
- "ABS": 328,
370
- "wat": 329,
371
- "enter": 330,
372
- "ree": 331,
373
- "ance": 332,
374
- "good": 333,
375
- "llage": 334,
376
- "dear": 335,
377
- "will": 336,
378
- "village": 337,
379
- "coming": 338,
380
- "water": 339,
381
- "ak": 340,
382
- "down": 341,
383
- "how": 342,
384
- "ol": 343,
385
- "thing": 344,
386
- "ate": 345,
387
- "look": 346,
388
- "father": 347,
389
- "SU": 348,
390
- "bre": 349,
391
- "bro": 350,
392
- "call": 351,
393
- "ha": 352,
394
- "ir": 353,
395
- "ly": 354,
396
- "my": 355,
397
- "ment": 356,
398
- "sp": 357,
399
- "apter": 358,
400
- "today": 359,
401
- "chapter": 360,
402
- "wee": 361,
403
- "fore": 362,
404
- "new": 363,
405
- "brother": 364,
406
- "MS": 365,
407
- "PR": 366,
408
- "ace": 367,
409
- "ey": 368,
410
- "han": 369,
411
- "ight": 370,
412
- "mount": 371,
413
- "much": 372,
414
- "place": 373,
415
- "ashu": 374,
416
- "acher": 375,
417
- "teacher": 376,
418
- "fire": 377,
419
- "ashuq": 378,
420
- "": 379,
421
- "Be": 380,
422
- "NT": 381,
423
- "fri": 382,
424
- "ill": 383,
425
- "ps": 384,
426
- "pas": 385,
427
- "ry": 386,
428
- "son": 387,
429
- "up": 388,
430
- "res": 389,
431
- "see": 390,
432
- "MSD": 391,
433
- "friend": 392,
434
- "AND": 393,
435
- "TH": 394,
436
- "ding": 395,
437
- "et": 396,
438
- "ex": 397,
439
- "night": 398,
440
- "of": 399,
441
- "wed": 400,
442
- "where": 401,
443
- "ind": 402,
444
- "reat": 403,
445
- "being": 404,
446
- "apper": 405,
447
- "soil": 406,
448
- "love": 407,
449
- "ound": 408,
450
- "ack": 409,
451
- "IMC": 410,
452
- "": 411,
453
- "OH": 412,
454
- "cap": 413,
455
- "count": 414,
456
- "ep": 415,
457
- "four": 416,
458
- "ls": 417,
459
- "pi": 418,
460
- "ty": 419,
461
- "ten": 420,
462
- "tal": 421,
463
- "ving": 422,
464
- "wound": 423,
465
- "rem": 424,
466
- "before": 425,
467
- "arm": 426,
468
- "arls": 427,
469
- "hey": 428,
470
- "top": 429,
471
- "took": 430,
472
- "road": 431,
473
- "every": 432,
474
- "pearls": 433,
475
- "fort": 434,
476
- "PROH": 435,
477
- "pass": 436,
478
- "apperance": 437,
479
- "ci": 438,
480
- "clo": 439,
481
- "hit": 440,
482
- "ice": 441,
483
- "name": 442,
484
- "rin": 443,
485
- "ser": 444,
486
- "swee": 445,
487
- "whi": 446,
488
- "three": 447,
489
- "ine": 448,
490
- "ought": 449,
491
- "ary": 450,
492
- "head": 451,
493
- "wife": 452,
494
- "tion": 453,
495
- "even": 454,
496
- "lea": 455,
497
- "not": 456,
498
- "bread": 457,
499
- "ress": 458,
500
- "wedding": 459,
501
- "remain": 460,
502
- "fortress": 461,
503
- "They": 462,
504
- "ai": 463,
505
- "az": 464,
506
- "ct": 465,
507
- "der": 466,
508
- "great": 467,
509
- "irl": 468,
510
- "khan": 469,
511
- "oh": 470,
512
- "zkhan": 471,
513
- "ong": 472,
514
- "red": 473,
515
- "ani": 474,
516
- "ans": 475,
517
- "heart": 476,
518
- "theart": 477,
519
- "ste": 478,
520
- "still": 479,
521
- "happy": 480,
522
- "chil": 481,
523
- "again": 482,
524
- "die": 483,
525
- "grand": 484,
526
- "Bezkhan": 485,
527
- "fourty": 486,
528
- "sweetheart": 487,
529
- "child": 488,
530
- "Bezkhanum": 489,
531
- "An": 490,
532
- "UR": 491,
533
- "back": 492,
534
- "ear": 493,
535
- "ho": 494,
536
- "hand": 495,
537
- "ith": 496,
538
- "mil": 497,
539
- "ople": 498,
540
- "po": 499,
541
- "py": 500,
542
- "pro": 501,
543
- "ring": 502,
544
- "rit": 503,
545
- "send": 504,
546
- "vin": 505,
547
- "writ": 506,
548
- "yes": 507,
549
- "ers": 508,
550
- "erman": 509,
551
- "ation": 510,
552
- "ream": 511,
553
- "hel": 512,
554
- "them": 513,
555
- "stay": 514,
556
- "wood": 515,
557
- "escap": 516,
558
- "fell": 517,
559
- "people": 518,
560
- "eye": 519,
561
- "country": 520,
562
- "tention": 521,
563
- "provin": 522,
564
- "province": 523,
565
- "ANT": 524,
566
- "MANT": 525,
567
- "PUR": 526,
568
- "ath": 527,
569
- "ase": 528,
570
- "bl": 529,
571
- "border": 530,
572
- "din": 531,
573
- "dag": 532,
574
- "ful": 533,
575
- "ge": 534,
576
- "had": 535,
577
- "pt": 536,
578
- "par": 537,
579
- "pun": 538,
580
- "pup": 539,
581
- "ust": 540,
582
- "war": 541,
583
- "erb": 542,
584
- "only": 543,
585
- "ist": 544,
586
- "attention": 545,
587
- "rest": 546,
588
- "seen": 547,
589
- "aper": 548,
590
- "ory": 549,
591
- "story": 550,
592
- "itary": 551,
593
- "turns": 552,
594
- "well": 553,
595
- "vice": 554,
596
- "IMMANT": 555,
597
- "ishment": 556,
598
- "SUB": 557,
599
- "leave": 558,
600
- "steed": 559,
601
- "military": 560,
602
- "write": 561,
603
- "PURP": 562,
604
- "punishment": 563,
605
- "puppy": 564,
606
- "": 565,
607
- "2pl": 566,
608
- "?-": 567,
609
- "Bak": 568,
610
- "DO": 569,
611
- "ED": 570,
612
- "Lith": 571,
613
- "Ma": 572,
614
- "Sed": 573,
615
- "Sev": 574,
616
- "Sha": 575,
617
- "bu": 576,
618
- "bor": 577,
619
- "ck": 578,
620
- "car": 579,
621
- "cle": 580,
622
- "don": 581,
623
- "dat": 582,
624
- "drin": 583,
625
- "dream": 584,
626
- "em": 585,
627
- "fin": 586,
628
- "hdag": 587,
629
- "jum": 588,
630
- "just": 589,
631
- "ning": 590,
632
- "nine": 591,
633
- "oo": 592,
634
- "op": 593,
635
- "ov": 594,
636
- "oice": 595,
637
- "por": 596,
638
- "ure": 597,
639
- "uani": 598,
640
- "voice": 599,
641
- "went": 600,
642
- "thre": 601,
643
- "ati": 602,
644
- "ank": 603,
645
- "another": 604,
646
- "oul": 605,
647
- "ough": 606,
648
- "kept": 607,
649
- "ity": 608,
650
- "agree": 609,
651
- "CONT": 610,
652
- "ever": 611,
653
- "brought": 612,
654
- "let": 613,
655
- "aget": 614,
656
- "bringing": 615,
657
- "old": 616,
658
- "SUPER": 617,
659
- "spaper": 618,
660
- "newspaper": 619,
661
- "service": 620,
662
- "while": 621,
663
- "grandfather": 622,
664
- "help": 623,
665
- "escape": 624,
666
- "Baku": 625,
667
- "Lithuani": 626,
668
- "Sedaget": 627,
669
- "Shahdag": 628,
670
- "drink": 629,
671
- "finish": 630,
672
- "open": 631,
673
- "threw": 632,
674
- "Lithuania": 633,
675
- "German": 634,
676
- "Ja": 635,
677
- "Let": 636,
678
- "OPT": 637,
679
- "Sam": 638,
680
- "ach": 639,
681
- "bir": 640,
682
- "bank": 641,
683
- "con": 642,
684
- "cis": 643,
685
- "can": 644,
686
- "cut": 645,
687
- "far": 646,
688
- "gn": 647,
689
- "gu": 648,
690
- "ian": 649,
691
- "jan": 650,
692
- "lan": 651,
693
- "led": 652,
694
- "mis": 653,
695
- "ot": 654,
696
- "obl": 655,
697
- "sent": 656,
698
- "stop": 657,
699
- "sho": 658,
700
- "tr": 659,
701
- "ting": 660,
702
- "wish": 661,
703
- "year": 662,
704
- "enian": 663,
705
- "atch": 664,
706
- "bet": 665,
707
- "plough": 666,
708
- "giving": 667,
709
- "keep": 668,
710
- "thes": 669,
711
- "ves": 670,
712
- "appro": 671,
713
- "stm": 672,
714
- "stone": 673,
715
- "start": 674,
716
- "boat": 675,
717
- "deci": 676,
718
- "decis": 677,
719
- "sol": 678,
720
- "your": 679,
721
- "lie": 680,
722
- "lot": 681,
723
- "knowled": 682,
724
- "ADESS": 683,
725
- "under": 684,
726
- "teen": 685,
727
- "please": 686,
728
- "have": 687,
729
- "spring": 688,
730
- "week": 689,
731
- "pict": 690,
732
- "talking": 691,
733
- "armenian": 692,
734
- "clothes": 693,
735
- "evening": 694,
736
- "aijan": 695,
737
- "answ": 696,
738
- "And": 697,
739
- "jumps": 698,
740
- "port": 699,
741
- "Samur": 700,
742
- "started": 701,
743
- "decision": 702,
744
- "knowledge": 703,
745
- "picture": 704,
746
- "Az": 705,
747
- "After": 706,
748
- "IV": 707,
749
- "ME": 708,
750
- "NK": 709,
751
- "OU": 710,
752
- "RE": 711,
753
- "TIM": 712,
754
- "WN": 713,
755
- "Zey": 714,
756
- "ah": 715,
757
- "are": 716,
758
- "dy": 717,
759
- "dut": 718,
760
- "fall": 719,
761
- "get": 720,
762
- "his": 721,
763
- "hun": 722,
764
- "hind": 723,
765
- "jar": 724,
766
- "long": 725,
767
- "may": 726,
768
- "never": 727,
769
- "ph": 728,
770
- "per": 729,
771
- "pher": 730,
772
- "qu": 731,
773
- "ra": 732,
774
- "ran": 733,
775
- "run": 734,
776
- "rus": 735,
777
- "sis": 736,
778
- "such": 737,
779
- "show": 738,
780
- "sai": 739,
781
- "wal": 740,
782
- "yr": 741,
783
- "inside": 742,
784
- "once": 743,
785
- "separ": 744,
786
- "bec": 745,
787
- "behind": 746,
788
- "oup": 747,
789
- "ous": 748,
790
- "ard": 749,
791
- "going": 750,
792
- "themsel": 751,
793
- "their": 752,
794
- "means": 753,
795
- "tom": 754,
796
- "ition": 755,
797
- "body": 756,
798
- "choo": 757,
799
- "tire": 758,
800
- "life": 759,
801
- "eved": 760,
802
- "leg": 761,
803
- "uncle": 762,
804
- "wear": 763,
805
- "did": 764,
806
- "died": 765,
807
- "tea": 766,
808
- "group": 767,
809
- "shepher": 768,
810
- "outpo": 769,
811
- "breath": 770,
812
- "forest": 771,
813
- "mountain": 772,
814
- "fireplace": 773,
815
- "THAT": 774,
816
- "pig": 775,
817
- "talk": 776,
818
- "everybody": 777,
819
- "stayed": 778,
820
- "hadful": 779,
821
- "erbaijan": 780,
822
- "DOWN": 781,
823
- "Germans": 782,
824
- "Jahan": 783,
825
- "guage": 784,
826
- "language": 785,
827
- "decieved": 786,
828
- "answer": 787,
829
- "Azerbaijan": 788,
830
- "TIME": 789,
831
- "Zeyn": 790,
832
- "duty": 791,
833
- "longed": 792,
834
- "maybe": 793,
835
- "person": 794,
836
- "sister": 795,
837
- "said": 796,
838
- "walk": 797,
839
- "themselves": 798,
840
- "choose": 799,
841
- "shepherd": 800,
842
- "outpost": 801,
843
- ".(": 802,
844
- "00": 803,
845
- "04": 804,
846
- "BE": 805,
847
- "Bat": 806,
848
- "Derb": 807,
849
- "Every": 808,
850
- "Fr": 809,
851
- "Had": 810,
852
- "IS": 811,
853
- "IT": 812,
854
- "Im": 813,
855
- "Is": 814,
856
- "Isi": 815,
857
- "Len": 816,
858
- "MO": 817,
859
- "Mi": 818,
860
- "MENT": 819,
861
- "Nus": 820,
862
- "Pol": 821,
863
- "Ta": 822,
864
- "UND": 823,
865
- "Ve": 824,
866
- "aun": 825,
867
- "blo": 826,
868
- "bought": 827,
869
- "cu": 828,
870
- "cre": 829,
871
- "coul": 830,
872
- "catch": 831,
873
- "da": 832,
874
- "dd": 833,
875
- "das": 834,
876
- "find": 835,
877
- "german": 836,
878
- "igh": 837,
879
- "ign": 838,
880
- "ji": 839,
881
- "ka": 840,
882
- "lk": 841,
883
- "lin": 842,
884
- "low": 843,
885
- "mal": 844,
886
- "om": 845,
887
- "prin": 846,
888
- "pati": 847,
889
- "pra": 848,
890
- "rad": 849,
891
- "sc": 850,
892
- "su": 851,
893
- "soul": 852,
894
- "tan": 853,
895
- "wind": 854,
896
- "ya": 855,
897
- "yev": 856,
898
- "yard": 857,
899
- "ERST": 858,
900
- "enc": 859,
901
- "ence": 860,
902
- "isn": 861,
903
- "rec": 862,
904
- "ret": 863,
905
- "read": 864,
906
- "reign": 865,
907
- "ingrad": 866,
908
- "beg": 867,
909
- "abal": 868,
910
- "abdin": 869,
911
- "edj": 870,
912
- "heal": 871,
913
- "giyev": 872,
914
- "llah": 873,
915
- "asant": 874,
916
- "astop": 875,
917
- "appear": 876,
918
- "stri": 877,
919
- "state": 878,
920
- "station": 879,
921
- "alabdin": 880,
922
- "adyr": 881,
923
- "hidd": 882,
924
- "COME": 883,
925
- "live": 884,
926
- "lips": 885,
927
- "libeg": 886,
928
- "returned": 887,
929
- "self": 888,
930
- "woman": 889,
931
- "dier": 890,
932
- "face": 891,
933
- "others": 892,
934
- "comm": 893,
935
- "neigh": 894,
936
- "pleasant": 895,
937
- "akh": 896,
938
- "things": 897,
939
- "spit": 898,
940
- "PRF": 899,
941
- "song": 900,
942
- "THIS": 901,
943
- "exist": 902,
944
- "export": 903,
945
- "which": 904,
946
- "azakh": 905,
947
- "animal": 906,
948
- "Anadyr": 907,
949
- "poem": 908,
950
- "Sevda": 909,
951
- "Sevastop": 910,
952
- "born": 911,
953
- "nineteen": 912,
954
- "over": 913,
955
- "bird": 914,
956
- "mistake": 915,
957
- "shops": 916,
958
- "boatman": 917,
959
- "soldier": 918,
960
- "running": 919,
961
- "Zeynalabdin": 920,
962
- "Bats": 921,
963
- "Derbent": 922,
964
- "Everything": 923,
965
- "France": 924,
966
- "Hadji": 925,
967
- "Imran": 926,
968
- "Isabal": 927,
969
- "Leningrad": 928,
970
- "MOMENT": 929,
971
- "Migr": 930,
972
- "Nusret": 931,
973
- "Poland": 932,
974
- "Tagiyev": 933,
975
- "UNDERST": 934,
976
- "Velibeg": 935,
977
- "aunt": 936,
978
- "blood": 937,
979
- "create": 938,
980
- "could": 939,
981
- "dastan": 940,
982
- "patience": 941,
983
- "prais": 942,
984
- "strike": 943,
985
- "statement": 944,
986
- "hidden": 945,
987
- "neighbor": 946,
988
- "Sevastopol": 947,
989
- "Isabala": 948,
990
- "UNDERSTAND": 949,
991
- "-.": 950,
992
- ".\"": 951,
993
- "01": 952,
994
- "03": 953,
995
- "05": 954,
996
- "34": 955,
997
- "59": 956,
998
- "AC": 957,
999
- "AR": 958,
1000
- "AY": 959,
1001
- "ANK": 960,
1002
- "Allah": 961,
1003
- "Ber": 962,
1004
- "BEL": 963,
1005
- "Chu": 964,
1006
- "DD": 965,
1007
- "Ge": 966,
1008
- "Ho": 967,
1009
- "HED": 968,
1010
- "IL": 969,
1011
- "Khu": 970,
1012
- "Kazakh": 971,
1013
- "LE": 972,
1014
- "LY": 973,
1015
- "Le": 974,
1016
- "Ledj": 975,
1017
- "Naz": 976,
1018
- "Nov": 977,
1019
- "Ol": 978,
1020
- "Rus": 979,
1021
- "Se": 980,
1022
- "TO": 981,
1023
- "Too": 982,
1024
- "US": 983,
1025
- "UNK": 984,
1026
- "WIL": 985,
1027
- "Yal": 986,
1028
- "YOU": 987,
1029
- "au": 988,
1030
- "aw": 989,
1031
- "ather": 990,
1032
- "aking": 991,
1033
- "away": 992,
1034
- "air": 993,
1035
- "bb": 994,
1036
- "by": 995,
1037
- "bing": 996,
1038
- "bab": 997,
1039
- "bar": 998,
1040
- "bal": 999,
1041
- "burn": 1000,
1042
- "bli": 1001,
1043
- "bath": 1002,
1044
- "cer": 1003,
1045
- "cal": 1004,
1046
- "cur": 1005,
1047
- "cli": 1006,
1048
- "cour": 1007,
1049
- "cout": 1008,
1050
- "creat": 1009,
1051
- "case": 1010,
1052
- "city": 1011,
1053
- "ds": 1012,
1054
- "dent": 1013,
1055
- "dred": 1014,
1056
- "ef": 1015,
1057
- "ff": 1016,
1058
- "fr": 1017,
1059
- "fif": 1018,
1060
- "fend": 1019,
1061
- "gar": 1020,
1062
- "gor": 1021,
1063
- "gun": 1022,
1064
- "gri": 1023,
1065
- "hay": 1024,
1066
- "ide": 1025,
1067
- "iers": 1026,
1068
- "ick": 1027,
1069
- "ious": 1028,
1070
- "kind": 1029,
1071
- "kot": 1030,
1072
- "ld": 1031,
1073
- "lgi": 1032,
1074
- "lit": 1033,
1075
- "lder": 1034,
1076
- "lati": 1035,
1077
- "mer": 1036,
1078
- "mar": 1037,
1079
- "mall": 1038,
1080
- "mun": 1039,
1081
- "mak": 1040,
1082
- "mine": 1041,
1083
- "match": 1042,
1084
- "mbing": 1043,
1085
- "ng": 1044,
1086
- "nes": 1045,
1087
- "nice": 1046,
1088
- "ose": 1047,
1089
- "pu": 1048,
1090
- "ping": 1049,
1091
- "ped": 1050,
1092
- "pend": 1051,
1093
- "pres": 1052,
1094
- "row": 1053,
1095
- "rack": 1054,
1096
- "rong": 1055,
1097
- "ration": 1056,
1098
- "sing": 1057,
1099
- "sit": 1058,
1100
- "snow": 1059,
1101
- "smo": 1060,
1102
- "sur": 1061,
1103
- "sle": 1062,
1104
- "spe": 1063,
1105
- "squ": 1064,
1106
- "slow": 1065,
1107
- "saw": 1066,
1108
- "small": 1067,
1109
- "tle": 1068,
1110
- "town": 1069,
1111
- "taking": 1070,
1112
- "ue": 1071,
1113
- "ver": 1072,
1114
- "vain": 1073,
1115
- "vity": 1074,
1116
- "wa": 1075,
1117
- "wor": 1076,
1118
- "zgi": 1077,
1119
- "ziers": 1078,
1120
- "thous": 1079,
1121
- "those": 1080,
1122
- "ERFO": 1081,
1123
- "ENLY": 1082,
1124
- "inde": 1083,
1125
- "ont": 1084,
1126
- "onder": 1085,
1127
- "NESS": 1086,
1128
- "att": 1087,
1129
- "remo": 1088,
1130
- "relea": 1089,
1131
- "reach": 1090,
1132
- "relati": 1091,
1133
- "aning": 1092,
1134
- "sed": 1093,
1135
- "seing": 1094,
1136
- "been": 1095,
1137
- "beat": 1096,
1138
- "bear": 1097,
1139
- "plary": 1098,
1140
- "height": 1099,
1141
- "gia": 1100,
1142
- "orious": 1101,
1143
- "orgia": 1102,
1144
- "gold": 1103,
1145
- "key": 1104,
1146
- "lland": 1105,
1147
- "asph": 1106,
1148
- "toge": 1107,
1149
- "cook": 1108,
1150
- "stan": 1109,
1151
- "stage": 1110,
1152
- "step": 1111,
1153
- "strong": 1112,
1154
- "ution": 1113,
1155
- "room": 1114,
1156
- "robb": 1115,
1157
- "cei": 1116,
1158
- "book": 1117,
1159
- "moaning": 1118,
1160
- "alt": 1119,
1161
- "deed": 1120,
1162
- "dest": 1121,
1163
- "defend": 1122,
1164
- "decei": 1123,
1165
- "happening": 1124,
1166
- "wasn": 1125,
1167
- "addin": 1126,
1168
- "boys": 1127,
1169
- "agh": 1128,
1170
- "door": 1129,
1171
- "does": 1130,
1172
- "him": 1131,
1173
- "high": 1132,
1174
- "young": 1133,
1175
- "turned": 1134,
1176
- "till": 1135,
1177
- "tivity": 1136,
1178
- "liking": 1137,
1179
- "event": 1138,
1180
- "ally": 1139,
1181
- "brill": 1140,
1182
- "bride": 1141,
1183
- "unit": 1142,
1184
- "acci": 1143,
1185
- "ween": 1144,
1186
- "weak": 1145,
1187
- "ama": 1146,
1188
- "ample": 1147,
1189
- "amaz": 1148,
1190
- "among": 1149,
1191
- "ammun": 1150,
1192
- "six": 1151,
1193
- "sign": 1152,
1194
- "vict": 1153,
1195
- "viziers": 1154,
1196
- "putting": 1155,
1197
- "ried": 1156,
1198
- "right": 1157,
1199
- "usar": 1158,
1200
- "artist": 1159,
1201
- "fear": 1160,
1202
- "direc": 1161,
1203
- "owner": 1162,
1204
- "faith": 1163,
1205
- "gry": 1164,
1206
- "five": 1165,
1207
- "fight": 1166,
1208
- "foot": 1167,
1209
- "folk": 1168,
1210
- "sheep": 1169,
1211
- "SUDD": 1170,
1212
- "ircle": 1171,
1213
- "news": 1172,
1214
- "Bebir": 1173,
1215
- "Belgi": 1174,
1216
- "pasport": 1175,
1217
- "ryside": 1176,
1218
- "THANK": 1177,
1219
- "THERFO": 1178,
1220
- "exem": 1179,
1221
- "example": 1180,
1222
- "off": 1181,
1223
- "captivity": 1182,
1224
- "tale": 1183,
1225
- "passing": 1184,
1226
- "ciple": 1185,
1227
- "cloth": 1186,
1228
- "serving": 1187,
1229
- "steal": 1188,
1230
- "grandmother": 1189,
1231
- "backwar": 1190,
1232
- "hospit": 1191,
1233
- "reaming": 1192,
1234
- "helps": 1193,
1235
- "escaped": 1194,
1236
- "fellow": 1195,
1237
- "countryman": 1196,
1238
- "park": 1197,
1239
- "DONE": 1198,
1240
- "bug": 1199,
1241
- "buy": 1200,
1242
- "donkey": 1201,
1243
- "justice": 1202,
1244
- "agreement": 1203,
1245
- "finished": 1204,
1246
- "concer": 1205,
1247
- "missur": 1206,
1248
- "better": 1207,
1249
- "between": 1208,
1250
- "approch": 1209,
1251
- "approach": 1210,
1252
- "solution": 1211,
1253
- "yourself": 1212,
1254
- "IVE": 1213,
1255
- "IVED": 1214,
1256
- "REAC": 1215,
1257
- "hundred": 1216,
1258
- "hungry": 1217,
1259
- "phone": 1218,
1260
- "separate": 1219,
1261
- "became": 1220,
1262
- "becau": 1221,
1263
- "cube": 1222,
1264
- "principle": 1223,
1265
- "screaming": 1224,
1266
- "sugar": 1225,
1267
- "encircle": 1226,
1268
- "appearing": 1227,
1269
- "commmissur": 1228,
1270
- "Migragh": 1229,
1271
- "praise": 1230,
1272
- "Berlin": 1231,
1273
- "BELIVED": 1232,
1274
- "Chukot": 1233,
1275
- "Georgia": 1234,
1276
- "Holland": 1235,
1277
- "Khudat": 1236,
1278
- "Kazakhstan": 1237,
1279
- "Lezgi": 1238,
1280
- "Ledjet": 1239,
1281
- "Nazir": 1240,
1282
- "Novgor": 1241,
1283
- "Oldest": 1242,
1284
- "Sebrill": 1243,
1285
- "WILL": 1244,
1286
- "Yalama": 1245,
1287
- "baby": 1246,
1288
- "barrack": 1247,
1289
- "bald": 1248,
1290
- "blic": 1249,
1291
- "bathhouse": 1250,
1292
- "calm": 1251,
1293
- "climbing": 1252,
1294
- "coutryside": 1253,
1295
- "ffer": 1254,
1296
- "front": 1255,
1297
- "guns": 1256,
1298
- "grief": 1257,
1299
- "little": 1258,
1300
- "married": 1259,
1301
- "makers": 1260,
1302
- "matchmakers": 1261,
1303
- "ness": 1262,
1304
- "public": 1263,
1305
- "pendent": 1264,
1306
- "present": 1265,
1307
- "smoke": 1266,
1308
- "sleep": 1267,
1309
- "speak": 1268,
1310
- "square": 1269,
1311
- "slowly": 1270,
1312
- "thousand": 1271,
1313
- "independent": 1272,
1314
- "removing": 1273,
1315
- "reached": 1274,
1316
- "relative": 1275,
1317
- "asphalt": 1276,
1318
- "together": 1277,
1319
- "robbers": 1278,
1320
- "doesn": 1279,
1321
- "accident": 1280,
1322
- "amazing": 1281,
1323
- "ammunition": 1282,
1324
- "victorious": 1283,
1325
- "direction": 1284,
1326
- "faithful": 1285,
1327
- "SUDDENLY": 1286,
1328
- "Belgium": 1287,
1329
- "THERFORE": 1288,
1330
- "exemplary": 1289,
1331
- "backwards": 1290,
1332
- "hospital": 1291,
1333
- "concert": 1292,
1334
- "REACHED": 1293,
1335
- "because": 1294,
1336
- "sugarcube": 1295,
1337
- "encirclement": 1296,
1338
- "commmissurate": 1297,
1339
- "Chukotka": 1298,
1340
- "Novgorod": 1299,
1341
- "Sebrilla": 1300,
1342
- "!\"": 1301,
1343
- "02": 1302,
1344
- "06": 1303,
1345
- "07": 1304,
1346
- "18": 1305,
1347
- "100": 1306,
1348
- "20": 1307,
1349
- "28": 1308,
1350
- "30": 1309,
1351
- "32": 1310,
1352
- "39": 1311,
1353
- "41": 1312,
1354
- "47": 1313,
1355
- ":\"": 1314,
1356
- "?\"": 1315,
1357
- "?)": 1316,
1358
- "AL": 1317,
1359
- "AN": 1318,
1360
- "AP": 1319,
1361
- "Ab": 1320,
1362
- "Ak": 1321,
1363
- "ASS": 1322,
1364
- "Ase": 1323,
1365
- "Afi": 1324,
1366
- "Aly": 1325,
1367
- "AME": 1326,
1368
- "Amer": 1327,
1369
- "BR": 1328,
1370
- "Bi": 1329,
1371
- "But": 1330,
1372
- "Bes": 1331,
1373
- "CI": 1332,
1374
- "CAME": 1333,
1375
- "ES": 1334,
1376
- "ECOND": 1335,
1377
- "EMS": 1336,
1378
- "EAR": 1337,
1379
- "Fer": 1338,
1380
- "FLE": 1339,
1381
- "FIVE": 1340,
1382
- "GH": 1341,
1383
- "GO": 1342,
1384
- "Gusar": 1343,
1385
- "GIVE": 1344,
1386
- "HI": 1345,
1387
- "HEAR": 1346,
1388
- "IB": 1347,
1389
- "Id": 1348,
1390
- "IST": 1349,
1391
- "KO": 1350,
1392
- "Kh": 1351,
1393
- "KIN": 1352,
1394
- "Ley": 1353,
1395
- "LIT": 1354,
1396
- "LIST": 1355,
1397
- "Me": 1356,
1398
- "Medj": 1357,
1399
- "Nas": 1358,
1400
- "Of": 1359,
1401
- "OCI": 1360,
1402
- "OGO": 1361,
1403
- "PY": 1362,
1404
- "Ra": 1363,
1405
- "So": 1364,
1406
- "Sab": 1365,
1407
- "She": 1366,
1408
- "Shi": 1367,
1409
- "Shu": 1368,
1410
- "Sho": 1369,
1411
- "SECOND": 1370,
1412
- "TW": 1371,
1413
- "TUR": 1372,
1414
- "TLE": 1373,
1415
- "TAL": 1374,
1416
- "UP": 1375,
1417
- "Uh": 1376,
1418
- "USS": 1377,
1419
- "VES": 1378,
1420
- "WAY": 1379,
1421
- "Yus": 1380,
1422
- "Yes": 1381,
1423
- "YWAY": 1382,
1424
- "av": 1383,
1425
- "ade": 1384,
1426
- "aur": 1385,
1427
- "athing": 1386,
1428
- "bone": 1387,
1429
- "bas": 1388,
1430
- "bur": 1389,
1431
- "ble": 1390,
1432
- "bill": 1391,
1433
- "baijan": 1392,
1434
- "bathing": 1393,
1435
- "ca": 1394,
1436
- "cl": 1395,
1437
- "che": 1396,
1438
- "cas": 1397,
1439
- "cking": 1398,
1440
- "cun": 1399,
1441
- "cam": 1400,
1442
- "cus": 1401,
1443
- "cart": 1402,
1444
- "cum": 1403,
1445
- "cry": 1404,
1446
- "dis": 1405,
1447
- "ded": 1406,
1448
- "dit": 1407,
1449
- "dal": 1408,
1450
- "dri": 1409,
1451
- "dance": 1410,
1452
- "dry": 1411,
1453
- "dist": 1412,
1454
- "dra": 1413,
1455
- "dition": 1414,
1456
- "eas": 1415,
1457
- "est": 1416,
1458
- "ece": 1417,
1459
- "eance": 1418,
1460
- "ely": 1419,
1461
- "ewish": 1420,
1462
- "elder": 1421,
1463
- "ebaijan": 1422,
1464
- "flo": 1423,
1465
- "fate": 1424,
1466
- "flin": 1425,
1467
- "flow": 1426,
1468
- "gy": 1427,
1469
- "ger": 1428,
1470
- "gree": 1429,
1471
- "gather": 1430,
1472
- "gusar": 1431,
1473
- "ht": 1432,
1474
- "hame": 1433,
1475
- "hman": 1434,
1476
- "im": 1435,
1477
- "ies": 1436,
1478
- "icall": 1437,
1479
- "ica": 1438,
1480
- "jewish": 1439,
1481
- "ky": 1440,
1482
- "kno": 1441,
1483
- "kazakh": 1442,
1484
- "kick": 1443,
1485
- "lve": 1444,
1486
- "line": 1445,
1487
- "ms": 1446,
1488
- "mu": 1447,
1489
- "men": 1448,
1490
- "mon": 1449,
1491
- "mou": 1450,
1492
- "mone": 1451,
1493
- "mor": 1452,
1494
- "mas": 1453,
1495
- "mad": 1454,
1496
- "mand": 1455,
1497
- "mill": 1456,
1498
- "msed": 1457,
1499
- "made": 1458,
1500
- "ns": 1459,
1501
- "ner": 1460,
1502
- "nun": 1461,
1503
- "nation": 1462,
1504
- "ored": 1463,
1505
- "oever": 1464,
1506
- "phi": 1465,
1507
- "pri": 1466,
1508
- "part": 1467,
1509
- "pour": 1468,
1510
- "pate": 1469,
1511
- "pha": 1470,
1512
- "pty": 1471,
1513
- "pine": 1472,
1514
- "path": 1473,
1515
- "paper": 1474,
1516
- "pity": 1475,
1517
- "pair": 1476,
1518
- "ru": 1477,
1519
- "ris": 1478,
1520
- "rone": 1479,
1521
- "rand": 1480,
1522
- "rain": 1481,
1523
- "sto": 1482,
1524
- "sal": 1483,
1525
- "sad": 1484,
1526
- "shi": 1485,
1527
- "sage": 1486,
1528
- "shou": 1487,
1529
- "sum": 1488,
1530
- "sly": 1489,
1531
- "sup": 1490,
1532
- "shame": 1491,
1533
- "sky": 1492,
1534
- "ton": 1493,
1535
- "tou": 1494,
1536
- "ted": 1495,
1537
- "twe": 1496,
1538
- "tage": 1497,
1539
- "tain": 1498,
1540
- "tes": 1499,
1541
- "trem": 1500,
1542
- "tong": 1501,
1543
- "twent": 1502,
1544
- "ttom": 1503,
1545
- "tition": 1504,
1546
- "uh": 1505,
1547
- "uy": 1506,
1548
- "uish": 1507,
1549
- "ven": 1508,
1550
- "ved": 1509,
1551
- "vall": 1510,
1552
- "vac": 1511,
1553
- "vol": 1512,
1554
- "wing": 1513,
1555
- "wake": 1514,
1556
- "wonder": 1515,
1557
- "xim": 1516,
1558
- "yway": 1517,
1559
- "yclo": 1518,
1560
- "yonder": 1519,
1561
- "thy": 1520,
1562
- "thin": 1521,
1563
- "thor": 1522,
1564
- "thro": 1523,
1565
- "thought": 1524,
1566
- "thank": 1525,
1567
- "throw": 1526,
1568
- "throne": 1527,
1569
- "ATED": 1528,
1570
- "into": 1529,
1571
- "inter": 1530,
1572
- "intention": 1531,
1573
- "insky": 1532,
1574
- "enough": 1533,
1575
- "onies": 1534,
1576
- "NED": 1535,
1577
- "ated": 1536,
1578
- "attr": 1537,
1579
- "ENTY": 1538,
1580
- "really": 1539,
1581
- "anish": 1540,
1582
- "anger": 1541,
1583
- "anyway": 1542,
1584
- "set": 1543,
1585
- "seat": 1544,
1586
- "sell": 1545,
1587
- "secu": 1546,
1588
- "secur": 1547,
1589
- "seven": 1548,
1590
- "beli": 1549,
1591
- "belie": 1550,
1592
- "FOCUS": 1551,
1593
- "absol": 1552,
1594
- "play": 1553,
1595
- "plov": 1554,
1596
- "arab": 1555,
1597
- "arac": 1556,
1598
- "arding": 1557,
1599
- "STAY": 1558,
1600
- "heav": 1559,
1601
- "orrow": 1560,
1602
- "lla": 1561,
1603
- "lls": 1562,
1604
- "llar": 1563,
1605
- "ask": 1564,
1606
- "aster": 1565,
1607
- "asking": 1566,
1608
- "aska": 1567,
1609
- "toom": 1568,
1610
- "cool": 1569,
1611
- "cover": 1570,
1612
- "stati": 1571,
1613
- "utely": 1572,
1614
- "itself": 1573,
1615
- "happing": 1574,
1616
- "ceed": 1575,
1617
- "cele": 1576,
1618
- "board": 1577,
1619
- "bottom": 1578,
1620
- "boarding": 1579,
1621
- "botoom": 1580,
1622
- "moon": 1581,
1623
- "move": 1582,
1624
- "mood": 1583,
1625
- "moment": 1584,
1626
- "alread": 1585,
1627
- "alpha": 1586,
1628
- "dead": 1587,
1629
- "degree": 1588,
1630
- "demand": 1589,
1631
- "rlpo": 1590,
1632
- "chance": 1591,
1633
- "charac": 1592,
1634
- "advice": 1593,
1635
- "adtition": 1594,
1636
- "soon": 1595,
1637
- "some": 1596,
1638
- "sopy": 1597,
1639
- "docum": 1598,
1640
- "hir": 1599,
1641
- "tici": 1600,
1642
- "tired": 1601,
1643
- "lied": 1602,
1644
- "light": 1603,
1645
- "living": 1604,
1646
- "losopy": 1605,
1647
- "ELVES": 1606,
1648
- "evil": 1607,
1649
- "returnes": 1608,
1650
- "brate": 1609,
1651
- "ently": 1610,
1652
- "untr": 1611,
1653
- "unfaithful": 1612,
1654
- "why": 1613,
1655
- "when": 1614,
1656
- "whoever": 1615,
1657
- "manat": 1616,
1658
- "act": 1617,
1659
- "acqu": 1618,
1660
- "weather": 1619,
1661
- "frost": 1620,
1662
- "ilding": 1621,
1663
- "sia": 1622,
1664
- "sick": 1623,
1665
- "vie": 1624,
1666
- "vide": 1625,
1667
- "viet": 1626,
1668
- "wolk": 1627,
1669
- "women": 1628,
1670
- "aining": 1629,
1671
- "ainted": 1630,
1672
- "puting": 1631,
1673
- "endure": 1632,
1674
- "days": 1633,
1675
- "ries": 1634,
1676
- "rict": 1635,
1677
- "ript": 1636,
1678
- "button": 1637,
1679
- "divide": 1638,
1680
- "pect": 1639,
1681
- "grum": 1640,
1682
- "grate": 1641,
1683
- "ground": 1642,
1684
- "comfort": 1643,
1685
- "fice": 1644,
1686
- "foam": 1645,
1687
- "hulla": 1646,
1688
- "near": 1647,
1689
- "neck": 1648,
1690
- "words": 1649,
1691
- "beauty": 1650,
1692
- "outdoor": 1651,
1693
- "waters": 1652,
1694
- "ately": 1653,
1695
- "looked": 1654,
1696
- "break": 1655,
1697
- "spread": 1656,
1698
- "hang": 1657,
1699
- "respect": 1658,
1700
- "seems": 1659,
1701
- "friendshi": 1660,
1702
- "THEMS": 1661,
1703
- "exting": 1662,
1704
- "exceed": 1663,
1705
- "office": 1664,
1706
- "appereance": 1665,
1707
- "lovesick": 1666,
1708
- "captain": 1667,
1709
- "countries": 1668,
1710
- "fourteen": 1669,
1711
- "pile": 1670,
1712
- "piece": 1671,
1713
- "arms": 1672,
1714
- "PROHIB": 1673,
1715
- "closer": 1674,
1716
- "clock": 1675,
1717
- "served": 1676,
1718
- "sweet": 1677,
1719
- "whirlpo": 1678,
1720
- "leather": 1679,
1721
- "azer": 1680,
1722
- "azebaijan": 1681,
1723
- "grandchild": 1682,
1724
- "milk": 1683,
1725
- "writing": 1684,
1726
- "black": 1685,
1727
- "blue": 1686,
1728
- "dinner": 1687,
1729
- "dagist": 1688,
1730
- "partici": 1689,
1731
- "usted": 1690,
1732
- "restaur": 1691,
1733
- "bulls": 1692,
1734
- "building": 1693,
1735
- "carry": 1694,
1736
- "empty": 1695,
1737
- "jumping": 1696,
1738
- "porter": 1697,
1739
- "Jaffer": 1698,
1740
- "aching": 1699,
1741
- "contr": 1700,
1742
- "consc": 1701,
1743
- "condition": 1702,
1744
- "cutting": 1703,
1745
- "guy": 1704,
1746
- "stopping": 1705,
1747
- "stopped": 1706,
1748
- "shop": 1707,
1749
- "shoot": 1708,
1750
- "tradtition": 1709,
1751
- "training": 1710,
1752
- "bets": 1711,
1753
- "approxim": 1712,
1754
- "decided": 1713,
1755
- "springboard": 1714,
1756
- "answers": 1715,
1757
- "OUND": 1716,
1758
- "OUGH": 1717,
1759
- "area": 1718,
1760
- "quick": 1719,
1761
- "yrdal": 1720,
1762
- "separation": 1721,
1763
- "separated": 1722,
1764
- "tomonies": 1723,
1765
- "tomorrow": 1724,
1766
- "talked": 1725,
1767
- "Zeynaddin": 1726,
1768
- "walked": 1727,
1769
- "print": 1728,
1770
- "suffer": 1729,
1771
- "window": 1730,
1772
- "encyclo": 1731,
1773
- "recently": 1732,
1774
- "reigned": 1733,
1775
- "commonly": 1734,
1776
- "existed": 1735,
1777
- "mistakes": 1736,
1778
- "Migrah": 1737,
1779
- "praised": 1738,
1780
- "AROUND": 1739,
1781
- "Ruslan": 1740,
1782
- "Russia": 1741,
1783
- "byaddin": 1742,
1784
- "curse": 1743,
1785
- "course": 1744,
1786
- "courage": 1745,
1787
- "creating": 1746,
1788
- "created": 1747,
1789
- "fifty": 1748,
1790
- "fifteen": 1749,
1791
- "pedis": 1750,
1792
- "sings": 1751,
1793
- "singers": 1752,
1794
- "sitting": 1753,
1795
- "wait": 1754,
1796
- "waves": 1755,
1797
- "working": 1756,
1798
- "worthy": 1757,
1799
- "attack": 1758,
1800
- "attaching": 1759,
1801
- "release": 1760,
1802
- "released": 1761,
1803
- "deceive": 1762,
1804
- "deceiving": 1763,
1805
- "footprint": 1764,
1806
- "accidentally": 1765,
1807
- "ANYWAY": 1766,
1808
- "APC": 1767,
1809
- "About": 1768,
1810
- "Akht": 1769,
1811
- "ASSOCI": 1770,
1812
- "Asef": 1771,
1813
- "Afiya": 1772,
1814
- "Alyaska": 1773,
1815
- "America": 1774,
1816
- "BROUGH": 1775,
1817
- "Big": 1776,
1818
- "Beshir": 1777,
1819
- "Ferhad": 1778,
1820
- "FLEW": 1779,
1821
- "HID": 1780,
1822
- "HEARD": 1781,
1823
- "Idris": 1782,
1824
- "KOPY": 1783,
1825
- "Khyrdal": 1784,
1826
- "KING": 1785,
1827
- "Leyli": 1786,
1828
- "LITTLE": 1787,
1829
- "LISTEN": 1788,
1830
- "Mehman": 1789,
1831
- "Medjnun": 1790,
1832
- "Nasru": 1791,
1833
- "OGON": 1792,
1834
- "Rahulla": 1793,
1835
- "Soviet": 1794,
1836
- "Sabri": 1795,
1837
- "Shemsed": 1796,
1838
- "Shirin": 1797,
1839
- "Shubyaddin": 1798,
1840
- "Shollar": 1799,
1841
- "TWENTY": 1800,
1842
- "TURNED": 1801,
1843
- "TALKING": 1802,
1844
- "Uhm": 1803,
1845
- "USSR": 1804,
1846
- "Yusif": 1805,
1847
- "basicall": 1806,
1848
- "bury": 1807,
1849
- "bles": 1808,
1850
- "clever": 1809,
1851
- "checking": 1810,
1852
- "casset": 1811,
1853
- "cunning": 1812,
1854
- "camp": 1813,
1855
- "custom": 1814,
1856
- "disaster": 1815,
1857
- "ditch": 1816,
1858
- "driver": 1817,
1859
- "district": 1818,
1860
- "draw": 1819,
1861
- "easy": 1820,
1862
- "esting": 1821,
1863
- "floored": 1822,
1864
- "flint": 1823,
1865
- "flower": 1824,
1866
- "gym": 1825,
1867
- "gusaris": 1826,
1868
- "knock": 1827,
1869
- "mug": 1828,
1870
- "month": 1829,
1871
- "mouth": 1830,
1872
- "money": 1831,
1873
- "morning": 1832,
1874
- "massage": 1833,
1875
- "mills": 1834,
1876
- "philosopy": 1835,
1877
- "price": 1836,
1878
- "party": 1837,
1879
- "pouring": 1838,
1880
- "paths": 1839,
1881
- "randchild": 1840,
1882
- "stove": 1841,
1883
- "sale": 1842,
1884
- "sadness": 1843,
1885
- "shoulder": 1844,
1886
- "summer": 1845,
1887
- "slyness": 1846,
1888
- "supporter": 1847,
1889
- "touch": 1848,
1890
- "twelve": 1849,
1891
- "testomonies": 1850,
1892
- "tremor": 1851,
1893
- "tongue": 1852,
1894
- "twenty": 1853,
1895
- "valley": 1854,
1896
- "vacation": 1855,
1897
- "voltage": 1856,
1898
- "thinking": 1857,
1899
- "thorns": 1858,
1900
- "throat": 1859,
1901
- "thanks": 1860,
1902
- "throwing": 1861,
1903
- "interesting": 1862,
1904
- "attract": 1863,
1905
- "secured": 1864,
1906
- "security": 1865,
1907
- "belivie": 1866,
1908
- "believe": 1867,
1909
- "absolutely": 1868,
1910
- "STAYED": 1869,
1911
- "heavy": 1870,
1912
- "celebrate": 1871,
1913
- "already": 1872,
1914
- "alphabets": 1873,
1915
- "character": 1874,
1916
- "document": 1875,
1917
- "lightning": 1876,
1918
- "untrusted": 1877,
1919
- "acquainted": 1878,
1920
- "grumbles": 1879,
1921
- "grateful": 1880,
1922
- "outdoors": 1881,
1923
- "friendship": 1882,
1924
- "THEMSELVES": 1883,
1925
- "extinguish": 1884,
1926
- "whirlpool": 1885,
1927
- "azebaijanis": 1886,
1928
- "dagistanish": 1887,
1929
- "participate": 1888,
1930
- "restaurant": 1889,
1931
- "contrary": 1890,
1932
- "conscript": 1891,
1933
- "approximately": 1892,
1934
- "quickly": 1893,
1935
- "encyclopedis": 1894,
1936
- "Akhtinsky": 1895,
1937
- "ASSOCIATED": 1896,
1938
- "BROUGHT": 1897,
1939
- "Khyrdalan": 1898,
1940
- "Nasrullah": 1899,
1941
- "Shemseddin": 1900,
1942
- "basically": 1901
 
1943
  },
1944
  "merges": [
1945
  "A O",
 
11
  "rstrip": false,
12
  "normalized": false,
13
  "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "<pad>",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
  }
24
  ],
25
  "normalizer": null,
 
48
  "byte_fallback": false,
49
  "vocab": {
50
  "<end>": 0,
51
+ "<pad>": 1,
52
+ "!": 2,
53
+ "\"": 3,
54
+ "'": 4,
55
+ "(": 5,
56
+ ")": 6,
57
+ ",": 7,
58
+ "-": 8,
59
+ ".": 9,
60
+ "0": 10,
61
+ "1": 11,
62
+ "2": 12,
63
+ "3": 13,
64
+ "4": 14,
65
+ "5": 15,
66
+ "6": 16,
67
+ "7": 17,
68
+ "8": 18,
69
+ "9": 19,
70
+ ":": 20,
71
+ "?": 21,
72
+ "A": 22,
73
+ "B": 23,
74
+ "C": 24,
75
+ "D": 25,
76
+ "E": 26,
77
+ "F": 27,
78
+ "G": 28,
79
+ "H": 29,
80
+ "I": 30,
81
+ "J": 31,
82
+ "K": 32,
83
+ "L": 33,
84
+ "M": 34,
85
+ "N": 35,
86
+ "O": 36,
87
+ "P": 37,
88
+ "Q": 38,
89
+ "R": 39,
90
+ "S": 40,
91
+ "T": 41,
92
+ "U": 42,
93
+ "V": 43,
94
+ "W": 44,
95
+ "Y": 45,
96
+ "Z": 46,
97
+ "a": 47,
98
+ "b": 48,
99
+ "c": 49,
100
+ "d": 50,
101
+ "e": 51,
102
+ "f": 52,
103
+ "g": 53,
104
+ "h": 54,
105
+ "i": 55,
106
+ "j": 56,
107
+ "k": 57,
108
+ "l": 58,
109
+ "m": 59,
110
+ "n": 60,
111
+ "o": 61,
112
+ "p": 62,
113
+ "q": 63,
114
+ "r": 64,
115
+ "s": 65,
116
+ "t": 66,
117
+ "u": 67,
118
+ "v": 68,
119
+ "w": 69,
120
+ "x": 70,
121
+ "y": 71,
122
+ "z": 72,
123
+ "«": 73,
124
+ "»": 74,
125
+ "": 75,
126
+ "": 76,
127
+ "": 77,
128
+ "AO": 78,
129
+ "th": 79,
130
+ "ER": 80,
131
+ "er": 81,
132
+ "AOR": 82,
133
+ "ERG": 83,
134
+ "EN": 84,
135
+ "ay": 85,
136
+ "AT": 86,
137
+ "in": 87,
138
+ "DAT": 88,
139
+ "SS": 89,
140
+ "say": 90,
141
+ "sg": 91,
142
+ "en": 92,
143
+ "on": 93,
144
+ "NE": 94,
145
+ "is": 95,
146
+ "at": 96,
147
+ "ENT": 97,
148
+ "1sg": 98,
149
+ "re": 99,
150
+ "MP": 100,
151
+ "an": 101,
152
+ "INE": 102,
153
+ "ing": 103,
154
+ "se": 104,
155
+ "be": 105,
156
+ "IMP": 106,
157
+ "ou": 107,
158
+ "INESS": 108,
159
+ "ab": 109,
160
+ "one": 110,
161
+ "AOC": 111,
162
+ "FO": 112,
163
+ "FOC": 113,
164
+ "GEN": 114,
165
+ "abs": 115,
166
+ "pl": 116,
167
+ "this": 117,
168
+ "PL": 118,
169
+ "that": 119,
170
+ "ed": 120,
171
+ "ar": 121,
172
+ "BL": 122,
173
+ "OBL": 123,
174
+ "ST": 124,
175
+ "he": 125,
176
+ "ap": 126,
177
+ "ther": 127,
178
+ "gi": 128,
179
+ "DI": 129,
180
+ "or": 130,
181
+ "DIR": 131,
182
+ "go": 132,
183
+ "ke": 133,
184
+ "ow": 134,
185
+ "1pl": 135,
186
+ "ll": 136,
187
+ "IMPF": 137,
188
+ "the": 138,
189
+ "as": 139,
190
+ "»,": 140,
191
+ "me": 141,
192
+ "to": 142,
193
+ "co": 143,
194
+ "PST": 144,
195
+ "ve": 145,
196
+ "app": 146,
197
+ "AOP": 147,
198
+ "ter": 148,
199
+ "st": 149,
200
+ "PSS": 150,
201
+ "SPSS": 151,
202
+ "ut": 152,
203
+ "2sg": 153,
204
+ "ake": 154,
205
+ "her": 155,
206
+ "PER": 156,
207
+ "it": 157,
208
+ "gen": 158,
209
+ "happ": 159,
210
+ "ro": 160,
211
+ "PERF": 161,
212
+ "ce": 162,
213
+ "bo": 163,
214
+ "now": 164,
215
+ "mo": 165,
216
+ "al": 166,
217
+ "de": 167,
218
+ "rl": 168,
219
+ "ch": 169,
220
+ "ur": 170,
221
+ "NEG": 171,
222
+ "happen": 172,
223
+ "..": 173,
224
+ "ND": 174,
225
+ "wi": 175,
226
+ "was": 176,
227
+ "happened": 177,
228
+ "FU": 178,
229
+ "FUT": 179,
230
+ "ad": 180,
231
+ "so": 181,
232
+ "boy": 182,
233
+ "ag": 183,
234
+ "do": 184,
235
+ "hi": 185,
236
+ "IMPV": 186,
237
+ "give": 187,
238
+ "girl": 188,
239
+ "you": 189,
240
+ "urn": 190,
241
+ "CO": 191,
242
+ "PT": 192,
243
+ "turn": 193,
244
+ "fter": 194,
245
+ "here": 195,
246
+ "ti": 196,
247
+ "and": 197,
248
+ "EMP": 198,
249
+ "TEMP": 199,
250
+ "li": 200,
251
+ "lo": 201,
252
+ ",.": 202,
253
+ "after": 203,
254
+ "take": 204,
255
+ "PTP": 205,
256
+ "SB": 206,
257
+ "EL": 207,
258
+ "ant": 208,
259
+ "COND": 209,
260
+ "ev": 210,
261
+ "cop": 211,
262
+ "all": 212,
263
+ "know": 213,
264
+ "return": 214,
265
+ "sel": 215,
266
+ "there": 216,
267
+ "king": 217,
268
+ "ESS": 218,
269
+ "br": 219,
270
+ "gh": 220,
271
+ "want": 221,
272
+ "le": 222,
273
+ "msel": 223,
274
+ "ent": 224,
275
+ "these": 225,
276
+ "AD": 226,
277
+ "make": 227,
278
+ "un": 228,
279
+ "oun": 229,
280
+ "ord": 230,
281
+ "OESS": 231,
282
+ "POESS": 232,
283
+ "wh": 233,
284
+ "himsel": 234,
285
+ "himself": 235,
286
+ "ame": 236,
287
+ "man": 237,
288
+ "come": 238,
289
+ "LAT": 239,
290
+ "ac": 240,
291
+ "if": 241,
292
+ "we": 242,
293
+ "».": 243,
294
+ "INELAT": 244,
295
+ "with": 245,
296
+ "age": 246,
297
+ "what": 247,
298
+ "am": 248,
299
+ "fro": 249,
300
+ "il": 250,
301
+ "od": 251,
302
+ "ok": 252,
303
+ "si": 253,
304
+ "vi": 254,
305
+ "wo": 255,
306
+ "more": 256,
307
+ "ery": 257,
308
+ "time": 258,
309
+ "from": 259,
310
+ "IN": 260,
311
+ "ain": 261,
312
+ "put": 262,
313
+ "then": 263,
314
+ "end": 264,
315
+ "mother": 265,
316
+ "bring": 266,
317
+ "ght": 267,
318
+ "day": 268,
319
+ "hor": 269,
320
+ "ri": 270,
321
+ "us": 271,
322
+ "...": 272,
323
+ "horse": 273,
324
+ "but": 274,
325
+ "erg": 275,
326
+ "art": 276,
327
+ "SBST": 277,
328
+ "INF": 278,
329
+ "es": 279,
330
+ "dog": 280,
331
+ "no": 281,
332
+ "ul": 282,
333
+ "ount": 283,
334
+ "HO": 284,
335
+ "RT": 285,
336
+ "fe": 286,
337
+ "HORT": 287,
338
+ "IM": 288,
339
+ "di": 289,
340
+ "te": 290,
341
+ "own": 291,
342
+ "also": 292,
343
+ "pe": 293,
344
+ "sea": 294,
345
+ "they": 295,
346
+ "side": 296,
347
+ "fa": 297,
348
+ "gr": 298,
349
+ "hou": 299,
350
+ "other": 300,
351
+ "same": 301,
352
+ "way": 302,
353
+ "com": 303,
354
+ "fi": 304,
355
+ "fo": 305,
356
+ "hu": 306,
357
+ "ne": 307,
358
+ "she": 308,
359
+ "um": 309,
360
+ "ish": 310,
361
+ "ple": 311,
362
+ "house": 312,
363
+ "aut": 313,
364
+ "for": 314,
365
+ "ion": 315,
366
+ "very": 316,
367
+ "word": 317,
368
+ "beaut": 318,
369
+ "our": 319,
370
+ "like": 320,
371
+ "SBSS": 321,
372
+ "AB": 322,
373
+ "two": 323,
374
+ "uch": 324,
375
+ "out": 325,
376
+ "order": 326,
377
+ "iful": 327,
378
+ "beautiful": 328,
379
+ "ABS": 329,
380
+ "wat": 330,
381
+ "enter": 331,
382
+ "ree": 332,
383
+ "ance": 333,
384
+ "good": 334,
385
+ "llage": 335,
386
+ "dear": 336,
387
+ "will": 337,
388
+ "village": 338,
389
+ "coming": 339,
390
+ "water": 340,
391
+ "ak": 341,
392
+ "down": 342,
393
+ "how": 343,
394
+ "ol": 344,
395
+ "thing": 345,
396
+ "ate": 346,
397
+ "look": 347,
398
+ "father": 348,
399
+ "SU": 349,
400
+ "bre": 350,
401
+ "bro": 351,
402
+ "call": 352,
403
+ "ha": 353,
404
+ "ir": 354,
405
+ "ly": 355,
406
+ "my": 356,
407
+ "ment": 357,
408
+ "sp": 358,
409
+ "apter": 359,
410
+ "today": 360,
411
+ "chapter": 361,
412
+ "wee": 362,
413
+ "fore": 363,
414
+ "new": 364,
415
+ "brother": 365,
416
+ "MS": 366,
417
+ "PR": 367,
418
+ "ace": 368,
419
+ "ey": 369,
420
+ "han": 370,
421
+ "ight": 371,
422
+ "mount": 372,
423
+ "much": 373,
424
+ "place": 374,
425
+ "ashu": 375,
426
+ "acher": 376,
427
+ "teacher": 377,
428
+ "fire": 378,
429
+ "ashuq": 379,
430
+ "": 380,
431
+ "Be": 381,
432
+ "NT": 382,
433
+ "fri": 383,
434
+ "ill": 384,
435
+ "ps": 385,
436
+ "pas": 386,
437
+ "ry": 387,
438
+ "son": 388,
439
+ "up": 389,
440
+ "res": 390,
441
+ "see": 391,
442
+ "MSD": 392,
443
+ "friend": 393,
444
+ "AND": 394,
445
+ "TH": 395,
446
+ "ding": 396,
447
+ "et": 397,
448
+ "ex": 398,
449
+ "night": 399,
450
+ "of": 400,
451
+ "wed": 401,
452
+ "where": 402,
453
+ "ind": 403,
454
+ "reat": 404,
455
+ "being": 405,
456
+ "apper": 406,
457
+ "soil": 407,
458
+ "love": 408,
459
+ "ound": 409,
460
+ "ack": 410,
461
+ "IMC": 411,
462
+ "": 412,
463
+ "OH": 413,
464
+ "cap": 414,
465
+ "count": 415,
466
+ "ep": 416,
467
+ "four": 417,
468
+ "ls": 418,
469
+ "pi": 419,
470
+ "ty": 420,
471
+ "ten": 421,
472
+ "tal": 422,
473
+ "ving": 423,
474
+ "wound": 424,
475
+ "rem": 425,
476
+ "before": 426,
477
+ "arm": 427,
478
+ "arls": 428,
479
+ "hey": 429,
480
+ "top": 430,
481
+ "took": 431,
482
+ "road": 432,
483
+ "every": 433,
484
+ "pearls": 434,
485
+ "fort": 435,
486
+ "PROH": 436,
487
+ "pass": 437,
488
+ "apperance": 438,
489
+ "ci": 439,
490
+ "clo": 440,
491
+ "hit": 441,
492
+ "ice": 442,
493
+ "name": 443,
494
+ "rin": 444,
495
+ "ser": 445,
496
+ "swee": 446,
497
+ "whi": 447,
498
+ "three": 448,
499
+ "ine": 449,
500
+ "ought": 450,
501
+ "ary": 451,
502
+ "head": 452,
503
+ "wife": 453,
504
+ "tion": 454,
505
+ "even": 455,
506
+ "lea": 456,
507
+ "not": 457,
508
+ "bread": 458,
509
+ "ress": 459,
510
+ "wedding": 460,
511
+ "remain": 461,
512
+ "fortress": 462,
513
+ "They": 463,
514
+ "ai": 464,
515
+ "az": 465,
516
+ "ct": 466,
517
+ "der": 467,
518
+ "great": 468,
519
+ "irl": 469,
520
+ "khan": 470,
521
+ "oh": 471,
522
+ "zkhan": 472,
523
+ "ong": 473,
524
+ "red": 474,
525
+ "ani": 475,
526
+ "ans": 476,
527
+ "heart": 477,
528
+ "theart": 478,
529
+ "ste": 479,
530
+ "still": 480,
531
+ "happy": 481,
532
+ "chil": 482,
533
+ "again": 483,
534
+ "die": 484,
535
+ "grand": 485,
536
+ "Bezkhan": 486,
537
+ "fourty": 487,
538
+ "sweetheart": 488,
539
+ "child": 489,
540
+ "Bezkhanum": 490,
541
+ "An": 491,
542
+ "UR": 492,
543
+ "back": 493,
544
+ "ear": 494,
545
+ "ho": 495,
546
+ "hand": 496,
547
+ "ith": 497,
548
+ "mil": 498,
549
+ "ople": 499,
550
+ "po": 500,
551
+ "py": 501,
552
+ "pro": 502,
553
+ "ring": 503,
554
+ "rit": 504,
555
+ "send": 505,
556
+ "vin": 506,
557
+ "writ": 507,
558
+ "yes": 508,
559
+ "ers": 509,
560
+ "erman": 510,
561
+ "ation": 511,
562
+ "ream": 512,
563
+ "hel": 513,
564
+ "them": 514,
565
+ "stay": 515,
566
+ "wood": 516,
567
+ "escap": 517,
568
+ "fell": 518,
569
+ "people": 519,
570
+ "eye": 520,
571
+ "country": 521,
572
+ "tention": 522,
573
+ "provin": 523,
574
+ "province": 524,
575
+ "ANT": 525,
576
+ "MANT": 526,
577
+ "PUR": 527,
578
+ "ath": 528,
579
+ "ase": 529,
580
+ "bl": 530,
581
+ "border": 531,
582
+ "din": 532,
583
+ "dag": 533,
584
+ "ful": 534,
585
+ "ge": 535,
586
+ "had": 536,
587
+ "pt": 537,
588
+ "par": 538,
589
+ "pun": 539,
590
+ "pup": 540,
591
+ "ust": 541,
592
+ "war": 542,
593
+ "erb": 543,
594
+ "only": 544,
595
+ "ist": 545,
596
+ "attention": 546,
597
+ "rest": 547,
598
+ "seen": 548,
599
+ "aper": 549,
600
+ "ory": 550,
601
+ "story": 551,
602
+ "itary": 552,
603
+ "turns": 553,
604
+ "well": 554,
605
+ "vice": 555,
606
+ "IMMANT": 556,
607
+ "ishment": 557,
608
+ "SUB": 558,
609
+ "leave": 559,
610
+ "steed": 560,
611
+ "military": 561,
612
+ "write": 562,
613
+ "PURP": 563,
614
+ "punishment": 564,
615
+ "puppy": 565,
616
+ "": 566,
617
+ "2pl": 567,
618
+ "?-": 568,
619
+ "Bak": 569,
620
+ "DO": 570,
621
+ "ED": 571,
622
+ "Lith": 572,
623
+ "Ma": 573,
624
+ "Sed": 574,
625
+ "Sev": 575,
626
+ "Sha": 576,
627
+ "bu": 577,
628
+ "bor": 578,
629
+ "ck": 579,
630
+ "car": 580,
631
+ "cle": 581,
632
+ "don": 582,
633
+ "dat": 583,
634
+ "drin": 584,
635
+ "dream": 585,
636
+ "em": 586,
637
+ "fin": 587,
638
+ "hdag": 588,
639
+ "jum": 589,
640
+ "just": 590,
641
+ "ning": 591,
642
+ "nine": 592,
643
+ "oo": 593,
644
+ "op": 594,
645
+ "ov": 595,
646
+ "oice": 596,
647
+ "por": 597,
648
+ "ure": 598,
649
+ "uani": 599,
650
+ "voice": 600,
651
+ "went": 601,
652
+ "thre": 602,
653
+ "ati": 603,
654
+ "ank": 604,
655
+ "another": 605,
656
+ "oul": 606,
657
+ "ough": 607,
658
+ "kept": 608,
659
+ "ity": 609,
660
+ "agree": 610,
661
+ "CONT": 611,
662
+ "ever": 612,
663
+ "brought": 613,
664
+ "let": 614,
665
+ "aget": 615,
666
+ "bringing": 616,
667
+ "old": 617,
668
+ "SUPER": 618,
669
+ "spaper": 619,
670
+ "newspaper": 620,
671
+ "service": 621,
672
+ "while": 622,
673
+ "grandfather": 623,
674
+ "help": 624,
675
+ "escape": 625,
676
+ "Baku": 626,
677
+ "Lithuani": 627,
678
+ "Sedaget": 628,
679
+ "Shahdag": 629,
680
+ "drink": 630,
681
+ "finish": 631,
682
+ "open": 632,
683
+ "threw": 633,
684
+ "Lithuania": 634,
685
+ "German": 635,
686
+ "Ja": 636,
687
+ "Let": 637,
688
+ "OPT": 638,
689
+ "Sam": 639,
690
+ "ach": 640,
691
+ "bir": 641,
692
+ "bank": 642,
693
+ "con": 643,
694
+ "cis": 644,
695
+ "can": 645,
696
+ "cut": 646,
697
+ "far": 647,
698
+ "gn": 648,
699
+ "gu": 649,
700
+ "ian": 650,
701
+ "jan": 651,
702
+ "lan": 652,
703
+ "led": 653,
704
+ "mis": 654,
705
+ "ot": 655,
706
+ "obl": 656,
707
+ "sent": 657,
708
+ "stop": 658,
709
+ "sho": 659,
710
+ "tr": 660,
711
+ "ting": 661,
712
+ "wish": 662,
713
+ "year": 663,
714
+ "enian": 664,
715
+ "atch": 665,
716
+ "bet": 666,
717
+ "plough": 667,
718
+ "giving": 668,
719
+ "keep": 669,
720
+ "thes": 670,
721
+ "ves": 671,
722
+ "appro": 672,
723
+ "stm": 673,
724
+ "stone": 674,
725
+ "start": 675,
726
+ "boat": 676,
727
+ "deci": 677,
728
+ "decis": 678,
729
+ "sol": 679,
730
+ "your": 680,
731
+ "lie": 681,
732
+ "lot": 682,
733
+ "knowled": 683,
734
+ "ADESS": 684,
735
+ "under": 685,
736
+ "teen": 686,
737
+ "please": 687,
738
+ "have": 688,
739
+ "spring": 689,
740
+ "week": 690,
741
+ "pict": 691,
742
+ "talking": 692,
743
+ "armenian": 693,
744
+ "clothes": 694,
745
+ "evening": 695,
746
+ "aijan": 696,
747
+ "answ": 697,
748
+ "And": 698,
749
+ "jumps": 699,
750
+ "port": 700,
751
+ "Samur": 701,
752
+ "started": 702,
753
+ "decision": 703,
754
+ "knowledge": 704,
755
+ "picture": 705,
756
+ "Az": 706,
757
+ "After": 707,
758
+ "IV": 708,
759
+ "ME": 709,
760
+ "NK": 710,
761
+ "OU": 711,
762
+ "RE": 712,
763
+ "TIM": 713,
764
+ "WN": 714,
765
+ "Zey": 715,
766
+ "ah": 716,
767
+ "are": 717,
768
+ "dy": 718,
769
+ "dut": 719,
770
+ "fall": 720,
771
+ "get": 721,
772
+ "his": 722,
773
+ "hun": 723,
774
+ "hind": 724,
775
+ "jar": 725,
776
+ "long": 726,
777
+ "may": 727,
778
+ "never": 728,
779
+ "ph": 729,
780
+ "per": 730,
781
+ "pher": 731,
782
+ "qu": 732,
783
+ "ra": 733,
784
+ "ran": 734,
785
+ "run": 735,
786
+ "rus": 736,
787
+ "sis": 737,
788
+ "such": 738,
789
+ "show": 739,
790
+ "sai": 740,
791
+ "wal": 741,
792
+ "yr": 742,
793
+ "inside": 743,
794
+ "once": 744,
795
+ "separ": 745,
796
+ "bec": 746,
797
+ "behind": 747,
798
+ "oup": 748,
799
+ "ous": 749,
800
+ "ard": 750,
801
+ "going": 751,
802
+ "themsel": 752,
803
+ "their": 753,
804
+ "means": 754,
805
+ "tom": 755,
806
+ "ition": 756,
807
+ "body": 757,
808
+ "choo": 758,
809
+ "tire": 759,
810
+ "life": 760,
811
+ "eved": 761,
812
+ "leg": 762,
813
+ "uncle": 763,
814
+ "wear": 764,
815
+ "did": 765,
816
+ "died": 766,
817
+ "tea": 767,
818
+ "group": 768,
819
+ "shepher": 769,
820
+ "outpo": 770,
821
+ "breath": 771,
822
+ "forest": 772,
823
+ "mountain": 773,
824
+ "fireplace": 774,
825
+ "THAT": 775,
826
+ "pig": 776,
827
+ "talk": 777,
828
+ "everybody": 778,
829
+ "stayed": 779,
830
+ "hadful": 780,
831
+ "erbaijan": 781,
832
+ "DOWN": 782,
833
+ "Germans": 783,
834
+ "Jahan": 784,
835
+ "guage": 785,
836
+ "language": 786,
837
+ "decieved": 787,
838
+ "answer": 788,
839
+ "Azerbaijan": 789,
840
+ "TIME": 790,
841
+ "Zeyn": 791,
842
+ "duty": 792,
843
+ "longed": 793,
844
+ "maybe": 794,
845
+ "person": 795,
846
+ "sister": 796,
847
+ "said": 797,
848
+ "walk": 798,
849
+ "themselves": 799,
850
+ "choose": 800,
851
+ "shepherd": 801,
852
+ "outpost": 802,
853
+ ".(": 803,
854
+ "00": 804,
855
+ "04": 805,
856
+ "BE": 806,
857
+ "Bat": 807,
858
+ "Derb": 808,
859
+ "Every": 809,
860
+ "Fr": 810,
861
+ "Had": 811,
862
+ "IS": 812,
863
+ "IT": 813,
864
+ "Im": 814,
865
+ "Is": 815,
866
+ "Isi": 816,
867
+ "Len": 817,
868
+ "MO": 818,
869
+ "Mi": 819,
870
+ "MENT": 820,
871
+ "Nus": 821,
872
+ "Pol": 822,
873
+ "Ta": 823,
874
+ "UND": 824,
875
+ "Ve": 825,
876
+ "aun": 826,
877
+ "blo": 827,
878
+ "bought": 828,
879
+ "cu": 829,
880
+ "cre": 830,
881
+ "coul": 831,
882
+ "catch": 832,
883
+ "da": 833,
884
+ "dd": 834,
885
+ "das": 835,
886
+ "find": 836,
887
+ "german": 837,
888
+ "igh": 838,
889
+ "ign": 839,
890
+ "ji": 840,
891
+ "ka": 841,
892
+ "lk": 842,
893
+ "lin": 843,
894
+ "low": 844,
895
+ "mal": 845,
896
+ "om": 846,
897
+ "prin": 847,
898
+ "pati": 848,
899
+ "pra": 849,
900
+ "rad": 850,
901
+ "sc": 851,
902
+ "su": 852,
903
+ "soul": 853,
904
+ "tan": 854,
905
+ "wind": 855,
906
+ "ya": 856,
907
+ "yev": 857,
908
+ "yard": 858,
909
+ "ERST": 859,
910
+ "enc": 860,
911
+ "ence": 861,
912
+ "isn": 862,
913
+ "rec": 863,
914
+ "ret": 864,
915
+ "read": 865,
916
+ "reign": 866,
917
+ "ingrad": 867,
918
+ "beg": 868,
919
+ "abal": 869,
920
+ "abdin": 870,
921
+ "edj": 871,
922
+ "heal": 872,
923
+ "giyev": 873,
924
+ "llah": 874,
925
+ "asant": 875,
926
+ "astop": 876,
927
+ "appear": 877,
928
+ "stri": 878,
929
+ "state": 879,
930
+ "station": 880,
931
+ "alabdin": 881,
932
+ "adyr": 882,
933
+ "hidd": 883,
934
+ "COME": 884,
935
+ "live": 885,
936
+ "lips": 886,
937
+ "libeg": 887,
938
+ "returned": 888,
939
+ "self": 889,
940
+ "woman": 890,
941
+ "dier": 891,
942
+ "face": 892,
943
+ "others": 893,
944
+ "comm": 894,
945
+ "neigh": 895,
946
+ "pleasant": 896,
947
+ "akh": 897,
948
+ "things": 898,
949
+ "spit": 899,
950
+ "PRF": 900,
951
+ "song": 901,
952
+ "THIS": 902,
953
+ "exist": 903,
954
+ "export": 904,
955
+ "which": 905,
956
+ "azakh": 906,
957
+ "animal": 907,
958
+ "Anadyr": 908,
959
+ "poem": 909,
960
+ "Sevda": 910,
961
+ "Sevastop": 911,
962
+ "born": 912,
963
+ "nineteen": 913,
964
+ "over": 914,
965
+ "bird": 915,
966
+ "mistake": 916,
967
+ "shops": 917,
968
+ "boatman": 918,
969
+ "soldier": 919,
970
+ "running": 920,
971
+ "Zeynalabdin": 921,
972
+ "Bats": 922,
973
+ "Derbent": 923,
974
+ "Everything": 924,
975
+ "France": 925,
976
+ "Hadji": 926,
977
+ "Imran": 927,
978
+ "Isabal": 928,
979
+ "Leningrad": 929,
980
+ "MOMENT": 930,
981
+ "Migr": 931,
982
+ "Nusret": 932,
983
+ "Poland": 933,
984
+ "Tagiyev": 934,
985
+ "UNDERST": 935,
986
+ "Velibeg": 936,
987
+ "aunt": 937,
988
+ "blood": 938,
989
+ "create": 939,
990
+ "could": 940,
991
+ "dastan": 941,
992
+ "patience": 942,
993
+ "prais": 943,
994
+ "strike": 944,
995
+ "statement": 945,
996
+ "hidden": 946,
997
+ "neighbor": 947,
998
+ "Sevastopol": 948,
999
+ "Isabala": 949,
1000
+ "UNDERSTAND": 950,
1001
+ "-.": 951,
1002
+ ".\"": 952,
1003
+ "01": 953,
1004
+ "03": 954,
1005
+ "05": 955,
1006
+ "34": 956,
1007
+ "59": 957,
1008
+ "AC": 958,
1009
+ "AR": 959,
1010
+ "AY": 960,
1011
+ "ANK": 961,
1012
+ "Allah": 962,
1013
+ "Ber": 963,
1014
+ "BEL": 964,
1015
+ "Chu": 965,
1016
+ "DD": 966,
1017
+ "Ge": 967,
1018
+ "Ho": 968,
1019
+ "HED": 969,
1020
+ "IL": 970,
1021
+ "Khu": 971,
1022
+ "Kazakh": 972,
1023
+ "LE": 973,
1024
+ "LY": 974,
1025
+ "Le": 975,
1026
+ "Ledj": 976,
1027
+ "Naz": 977,
1028
+ "Nov": 978,
1029
+ "Ol": 979,
1030
+ "Rus": 980,
1031
+ "Se": 981,
1032
+ "TO": 982,
1033
+ "Too": 983,
1034
+ "US": 984,
1035
+ "UNK": 985,
1036
+ "WIL": 986,
1037
+ "Yal": 987,
1038
+ "YOU": 988,
1039
+ "au": 989,
1040
+ "aw": 990,
1041
+ "ather": 991,
1042
+ "aking": 992,
1043
+ "away": 993,
1044
+ "air": 994,
1045
+ "bb": 995,
1046
+ "by": 996,
1047
+ "bing": 997,
1048
+ "bab": 998,
1049
+ "bar": 999,
1050
+ "bal": 1000,
1051
+ "burn": 1001,
1052
+ "bli": 1002,
1053
+ "bath": 1003,
1054
+ "cer": 1004,
1055
+ "cal": 1005,
1056
+ "cur": 1006,
1057
+ "cli": 1007,
1058
+ "cour": 1008,
1059
+ "cout": 1009,
1060
+ "creat": 1010,
1061
+ "case": 1011,
1062
+ "city": 1012,
1063
+ "ds": 1013,
1064
+ "dent": 1014,
1065
+ "dred": 1015,
1066
+ "ef": 1016,
1067
+ "ff": 1017,
1068
+ "fr": 1018,
1069
+ "fif": 1019,
1070
+ "fend": 1020,
1071
+ "gar": 1021,
1072
+ "gor": 1022,
1073
+ "gun": 1023,
1074
+ "gri": 1024,
1075
+ "hay": 1025,
1076
+ "ide": 1026,
1077
+ "iers": 1027,
1078
+ "ick": 1028,
1079
+ "ious": 1029,
1080
+ "kind": 1030,
1081
+ "kot": 1031,
1082
+ "ld": 1032,
1083
+ "lgi": 1033,
1084
+ "lit": 1034,
1085
+ "lder": 1035,
1086
+ "lati": 1036,
1087
+ "mer": 1037,
1088
+ "mar": 1038,
1089
+ "mall": 1039,
1090
+ "mun": 1040,
1091
+ "mak": 1041,
1092
+ "mine": 1042,
1093
+ "match": 1043,
1094
+ "mbing": 1044,
1095
+ "ng": 1045,
1096
+ "nes": 1046,
1097
+ "nice": 1047,
1098
+ "ose": 1048,
1099
+ "pu": 1049,
1100
+ "ping": 1050,
1101
+ "ped": 1051,
1102
+ "pend": 1052,
1103
+ "pres": 1053,
1104
+ "row": 1054,
1105
+ "rack": 1055,
1106
+ "rong": 1056,
1107
+ "ration": 1057,
1108
+ "sing": 1058,
1109
+ "sit": 1059,
1110
+ "snow": 1060,
1111
+ "smo": 1061,
1112
+ "sur": 1062,
1113
+ "sle": 1063,
1114
+ "spe": 1064,
1115
+ "squ": 1065,
1116
+ "slow": 1066,
1117
+ "saw": 1067,
1118
+ "small": 1068,
1119
+ "tle": 1069,
1120
+ "town": 1070,
1121
+ "taking": 1071,
1122
+ "ue": 1072,
1123
+ "ver": 1073,
1124
+ "vain": 1074,
1125
+ "vity": 1075,
1126
+ "wa": 1076,
1127
+ "wor": 1077,
1128
+ "zgi": 1078,
1129
+ "ziers": 1079,
1130
+ "thous": 1080,
1131
+ "those": 1081,
1132
+ "ERFO": 1082,
1133
+ "ENLY": 1083,
1134
+ "inde": 1084,
1135
+ "ont": 1085,
1136
+ "onder": 1086,
1137
+ "NESS": 1087,
1138
+ "att": 1088,
1139
+ "remo": 1089,
1140
+ "relea": 1090,
1141
+ "reach": 1091,
1142
+ "relati": 1092,
1143
+ "aning": 1093,
1144
+ "sed": 1094,
1145
+ "seing": 1095,
1146
+ "been": 1096,
1147
+ "beat": 1097,
1148
+ "bear": 1098,
1149
+ "plary": 1099,
1150
+ "height": 1100,
1151
+ "gia": 1101,
1152
+ "orious": 1102,
1153
+ "orgia": 1103,
1154
+ "gold": 1104,
1155
+ "key": 1105,
1156
+ "lland": 1106,
1157
+ "asph": 1107,
1158
+ "toge": 1108,
1159
+ "cook": 1109,
1160
+ "stan": 1110,
1161
+ "stage": 1111,
1162
+ "step": 1112,
1163
+ "strong": 1113,
1164
+ "ution": 1114,
1165
+ "room": 1115,
1166
+ "robb": 1116,
1167
+ "cei": 1117,
1168
+ "book": 1118,
1169
+ "moaning": 1119,
1170
+ "alt": 1120,
1171
+ "deed": 1121,
1172
+ "dest": 1122,
1173
+ "defend": 1123,
1174
+ "decei": 1124,
1175
+ "happening": 1125,
1176
+ "wasn": 1126,
1177
+ "addin": 1127,
1178
+ "boys": 1128,
1179
+ "agh": 1129,
1180
+ "door": 1130,
1181
+ "does": 1131,
1182
+ "him": 1132,
1183
+ "high": 1133,
1184
+ "young": 1134,
1185
+ "turned": 1135,
1186
+ "till": 1136,
1187
+ "tivity": 1137,
1188
+ "liking": 1138,
1189
+ "event": 1139,
1190
+ "ally": 1140,
1191
+ "brill": 1141,
1192
+ "bride": 1142,
1193
+ "unit": 1143,
1194
+ "acci": 1144,
1195
+ "ween": 1145,
1196
+ "weak": 1146,
1197
+ "ama": 1147,
1198
+ "ample": 1148,
1199
+ "amaz": 1149,
1200
+ "among": 1150,
1201
+ "ammun": 1151,
1202
+ "six": 1152,
1203
+ "sign": 1153,
1204
+ "vict": 1154,
1205
+ "viziers": 1155,
1206
+ "putting": 1156,
1207
+ "ried": 1157,
1208
+ "right": 1158,
1209
+ "usar": 1159,
1210
+ "artist": 1160,
1211
+ "fear": 1161,
1212
+ "direc": 1162,
1213
+ "owner": 1163,
1214
+ "faith": 1164,
1215
+ "gry": 1165,
1216
+ "five": 1166,
1217
+ "fight": 1167,
1218
+ "foot": 1168,
1219
+ "folk": 1169,
1220
+ "sheep": 1170,
1221
+ "SUDD": 1171,
1222
+ "ircle": 1172,
1223
+ "news": 1173,
1224
+ "Bebir": 1174,
1225
+ "Belgi": 1175,
1226
+ "pasport": 1176,
1227
+ "ryside": 1177,
1228
+ "THANK": 1178,
1229
+ "THERFO": 1179,
1230
+ "exem": 1180,
1231
+ "example": 1181,
1232
+ "off": 1182,
1233
+ "captivity": 1183,
1234
+ "tale": 1184,
1235
+ "passing": 1185,
1236
+ "ciple": 1186,
1237
+ "cloth": 1187,
1238
+ "serving": 1188,
1239
+ "steal": 1189,
1240
+ "grandmother": 1190,
1241
+ "backwar": 1191,
1242
+ "hospit": 1192,
1243
+ "reaming": 1193,
1244
+ "helps": 1194,
1245
+ "escaped": 1195,
1246
+ "fellow": 1196,
1247
+ "countryman": 1197,
1248
+ "park": 1198,
1249
+ "DONE": 1199,
1250
+ "bug": 1200,
1251
+ "buy": 1201,
1252
+ "donkey": 1202,
1253
+ "justice": 1203,
1254
+ "agreement": 1204,
1255
+ "finished": 1205,
1256
+ "concer": 1206,
1257
+ "missur": 1207,
1258
+ "better": 1208,
1259
+ "between": 1209,
1260
+ "approch": 1210,
1261
+ "approach": 1211,
1262
+ "solution": 1212,
1263
+ "yourself": 1213,
1264
+ "IVE": 1214,
1265
+ "IVED": 1215,
1266
+ "REAC": 1216,
1267
+ "hundred": 1217,
1268
+ "hungry": 1218,
1269
+ "phone": 1219,
1270
+ "separate": 1220,
1271
+ "became": 1221,
1272
+ "becau": 1222,
1273
+ "cube": 1223,
1274
+ "principle": 1224,
1275
+ "screaming": 1225,
1276
+ "sugar": 1226,
1277
+ "encircle": 1227,
1278
+ "appearing": 1228,
1279
+ "commmissur": 1229,
1280
+ "Migragh": 1230,
1281
+ "praise": 1231,
1282
+ "Berlin": 1232,
1283
+ "BELIVED": 1233,
1284
+ "Chukot": 1234,
1285
+ "Georgia": 1235,
1286
+ "Holland": 1236,
1287
+ "Khudat": 1237,
1288
+ "Kazakhstan": 1238,
1289
+ "Lezgi": 1239,
1290
+ "Ledjet": 1240,
1291
+ "Nazir": 1241,
1292
+ "Novgor": 1242,
1293
+ "Oldest": 1243,
1294
+ "Sebrill": 1244,
1295
+ "WILL": 1245,
1296
+ "Yalama": 1246,
1297
+ "baby": 1247,
1298
+ "barrack": 1248,
1299
+ "bald": 1249,
1300
+ "blic": 1250,
1301
+ "bathhouse": 1251,
1302
+ "calm": 1252,
1303
+ "climbing": 1253,
1304
+ "coutryside": 1254,
1305
+ "ffer": 1255,
1306
+ "front": 1256,
1307
+ "guns": 1257,
1308
+ "grief": 1258,
1309
+ "little": 1259,
1310
+ "married": 1260,
1311
+ "makers": 1261,
1312
+ "matchmakers": 1262,
1313
+ "ness": 1263,
1314
+ "public": 1264,
1315
+ "pendent": 1265,
1316
+ "present": 1266,
1317
+ "smoke": 1267,
1318
+ "sleep": 1268,
1319
+ "speak": 1269,
1320
+ "square": 1270,
1321
+ "slowly": 1271,
1322
+ "thousand": 1272,
1323
+ "independent": 1273,
1324
+ "removing": 1274,
1325
+ "reached": 1275,
1326
+ "relative": 1276,
1327
+ "asphalt": 1277,
1328
+ "together": 1278,
1329
+ "robbers": 1279,
1330
+ "doesn": 1280,
1331
+ "accident": 1281,
1332
+ "amazing": 1282,
1333
+ "ammunition": 1283,
1334
+ "victorious": 1284,
1335
+ "direction": 1285,
1336
+ "faithful": 1286,
1337
+ "SUDDENLY": 1287,
1338
+ "Belgium": 1288,
1339
+ "THERFORE": 1289,
1340
+ "exemplary": 1290,
1341
+ "backwards": 1291,
1342
+ "hospital": 1292,
1343
+ "concert": 1293,
1344
+ "REACHED": 1294,
1345
+ "because": 1295,
1346
+ "sugarcube": 1296,
1347
+ "encirclement": 1297,
1348
+ "commmissurate": 1298,
1349
+ "Chukotka": 1299,
1350
+ "Novgorod": 1300,
1351
+ "Sebrilla": 1301,
1352
+ "!\"": 1302,
1353
+ "02": 1303,
1354
+ "06": 1304,
1355
+ "07": 1305,
1356
+ "18": 1306,
1357
+ "100": 1307,
1358
+ "20": 1308,
1359
+ "28": 1309,
1360
+ "30": 1310,
1361
+ "32": 1311,
1362
+ "39": 1312,
1363
+ "41": 1313,
1364
+ "47": 1314,
1365
+ ":\"": 1315,
1366
+ "?\"": 1316,
1367
+ "?)": 1317,
1368
+ "AL": 1318,
1369
+ "AN": 1319,
1370
+ "AP": 1320,
1371
+ "Ab": 1321,
1372
+ "Ak": 1322,
1373
+ "ASS": 1323,
1374
+ "Ase": 1324,
1375
+ "Afi": 1325,
1376
+ "Aly": 1326,
1377
+ "AME": 1327,
1378
+ "Amer": 1328,
1379
+ "BR": 1329,
1380
+ "Bi": 1330,
1381
+ "But": 1331,
1382
+ "Bes": 1332,
1383
+ "CI": 1333,
1384
+ "CAME": 1334,
1385
+ "ES": 1335,
1386
+ "ECOND": 1336,
1387
+ "EMS": 1337,
1388
+ "EAR": 1338,
1389
+ "Fer": 1339,
1390
+ "FLE": 1340,
1391
+ "FIVE": 1341,
1392
+ "GH": 1342,
1393
+ "GO": 1343,
1394
+ "Gusar": 1344,
1395
+ "GIVE": 1345,
1396
+ "HI": 1346,
1397
+ "HEAR": 1347,
1398
+ "IB": 1348,
1399
+ "Id": 1349,
1400
+ "IST": 1350,
1401
+ "KO": 1351,
1402
+ "Kh": 1352,
1403
+ "KIN": 1353,
1404
+ "Ley": 1354,
1405
+ "LIT": 1355,
1406
+ "LIST": 1356,
1407
+ "Me": 1357,
1408
+ "Medj": 1358,
1409
+ "Nas": 1359,
1410
+ "Of": 1360,
1411
+ "OCI": 1361,
1412
+ "OGO": 1362,
1413
+ "PY": 1363,
1414
+ "Ra": 1364,
1415
+ "So": 1365,
1416
+ "Sab": 1366,
1417
+ "She": 1367,
1418
+ "Shi": 1368,
1419
+ "Shu": 1369,
1420
+ "Sho": 1370,
1421
+ "SECOND": 1371,
1422
+ "TW": 1372,
1423
+ "TUR": 1373,
1424
+ "TLE": 1374,
1425
+ "TAL": 1375,
1426
+ "UP": 1376,
1427
+ "Uh": 1377,
1428
+ "USS": 1378,
1429
+ "VES": 1379,
1430
+ "WAY": 1380,
1431
+ "Yus": 1381,
1432
+ "Yes": 1382,
1433
+ "YWAY": 1383,
1434
+ "av": 1384,
1435
+ "ade": 1385,
1436
+ "aur": 1386,
1437
+ "athing": 1387,
1438
+ "bone": 1388,
1439
+ "bas": 1389,
1440
+ "bur": 1390,
1441
+ "ble": 1391,
1442
+ "bill": 1392,
1443
+ "baijan": 1393,
1444
+ "bathing": 1394,
1445
+ "ca": 1395,
1446
+ "cl": 1396,
1447
+ "che": 1397,
1448
+ "cas": 1398,
1449
+ "cking": 1399,
1450
+ "cun": 1400,
1451
+ "cam": 1401,
1452
+ "cus": 1402,
1453
+ "cart": 1403,
1454
+ "cum": 1404,
1455
+ "cry": 1405,
1456
+ "dis": 1406,
1457
+ "ded": 1407,
1458
+ "dit": 1408,
1459
+ "dal": 1409,
1460
+ "dri": 1410,
1461
+ "dance": 1411,
1462
+ "dry": 1412,
1463
+ "dist": 1413,
1464
+ "dra": 1414,
1465
+ "dition": 1415,
1466
+ "eas": 1416,
1467
+ "est": 1417,
1468
+ "ece": 1418,
1469
+ "eance": 1419,
1470
+ "ely": 1420,
1471
+ "ewish": 1421,
1472
+ "elder": 1422,
1473
+ "ebaijan": 1423,
1474
+ "flo": 1424,
1475
+ "fate": 1425,
1476
+ "flin": 1426,
1477
+ "flow": 1427,
1478
+ "gy": 1428,
1479
+ "ger": 1429,
1480
+ "gree": 1430,
1481
+ "gather": 1431,
1482
+ "gusar": 1432,
1483
+ "ht": 1433,
1484
+ "hame": 1434,
1485
+ "hman": 1435,
1486
+ "im": 1436,
1487
+ "ies": 1437,
1488
+ "icall": 1438,
1489
+ "ica": 1439,
1490
+ "jewish": 1440,
1491
+ "ky": 1441,
1492
+ "kno": 1442,
1493
+ "kazakh": 1443,
1494
+ "kick": 1444,
1495
+ "lve": 1445,
1496
+ "line": 1446,
1497
+ "ms": 1447,
1498
+ "mu": 1448,
1499
+ "men": 1449,
1500
+ "mon": 1450,
1501
+ "mou": 1451,
1502
+ "mone": 1452,
1503
+ "mor": 1453,
1504
+ "mas": 1454,
1505
+ "mad": 1455,
1506
+ "mand": 1456,
1507
+ "mill": 1457,
1508
+ "msed": 1458,
1509
+ "made": 1459,
1510
+ "ns": 1460,
1511
+ "ner": 1461,
1512
+ "nun": 1462,
1513
+ "nation": 1463,
1514
+ "ored": 1464,
1515
+ "oever": 1465,
1516
+ "phi": 1466,
1517
+ "pri": 1467,
1518
+ "part": 1468,
1519
+ "pour": 1469,
1520
+ "pate": 1470,
1521
+ "pha": 1471,
1522
+ "pty": 1472,
1523
+ "pine": 1473,
1524
+ "path": 1474,
1525
+ "paper": 1475,
1526
+ "pity": 1476,
1527
+ "pair": 1477,
1528
+ "ru": 1478,
1529
+ "ris": 1479,
1530
+ "rone": 1480,
1531
+ "rand": 1481,
1532
+ "rain": 1482,
1533
+ "sto": 1483,
1534
+ "sal": 1484,
1535
+ "sad": 1485,
1536
+ "shi": 1486,
1537
+ "sage": 1487,
1538
+ "shou": 1488,
1539
+ "sum": 1489,
1540
+ "sly": 1490,
1541
+ "sup": 1491,
1542
+ "shame": 1492,
1543
+ "sky": 1493,
1544
+ "ton": 1494,
1545
+ "tou": 1495,
1546
+ "ted": 1496,
1547
+ "twe": 1497,
1548
+ "tage": 1498,
1549
+ "tain": 1499,
1550
+ "tes": 1500,
1551
+ "trem": 1501,
1552
+ "tong": 1502,
1553
+ "twent": 1503,
1554
+ "ttom": 1504,
1555
+ "tition": 1505,
1556
+ "uh": 1506,
1557
+ "uy": 1507,
1558
+ "uish": 1508,
1559
+ "ven": 1509,
1560
+ "ved": 1510,
1561
+ "vall": 1511,
1562
+ "vac": 1512,
1563
+ "vol": 1513,
1564
+ "wing": 1514,
1565
+ "wake": 1515,
1566
+ "wonder": 1516,
1567
+ "xim": 1517,
1568
+ "yway": 1518,
1569
+ "yclo": 1519,
1570
+ "yonder": 1520,
1571
+ "thy": 1521,
1572
+ "thin": 1522,
1573
+ "thor": 1523,
1574
+ "thro": 1524,
1575
+ "thought": 1525,
1576
+ "thank": 1526,
1577
+ "throw": 1527,
1578
+ "throne": 1528,
1579
+ "ATED": 1529,
1580
+ "into": 1530,
1581
+ "inter": 1531,
1582
+ "intention": 1532,
1583
+ "insky": 1533,
1584
+ "enough": 1534,
1585
+ "onies": 1535,
1586
+ "NED": 1536,
1587
+ "ated": 1537,
1588
+ "attr": 1538,
1589
+ "ENTY": 1539,
1590
+ "really": 1540,
1591
+ "anish": 1541,
1592
+ "anger": 1542,
1593
+ "anyway": 1543,
1594
+ "set": 1544,
1595
+ "seat": 1545,
1596
+ "sell": 1546,
1597
+ "secu": 1547,
1598
+ "secur": 1548,
1599
+ "seven": 1549,
1600
+ "beli": 1550,
1601
+ "belie": 1551,
1602
+ "FOCUS": 1552,
1603
+ "absol": 1553,
1604
+ "play": 1554,
1605
+ "plov": 1555,
1606
+ "arab": 1556,
1607
+ "arac": 1557,
1608
+ "arding": 1558,
1609
+ "STAY": 1559,
1610
+ "heav": 1560,
1611
+ "orrow": 1561,
1612
+ "lla": 1562,
1613
+ "lls": 1563,
1614
+ "llar": 1564,
1615
+ "ask": 1565,
1616
+ "aster": 1566,
1617
+ "asking": 1567,
1618
+ "aska": 1568,
1619
+ "toom": 1569,
1620
+ "cool": 1570,
1621
+ "cover": 1571,
1622
+ "stati": 1572,
1623
+ "utely": 1573,
1624
+ "itself": 1574,
1625
+ "happing": 1575,
1626
+ "ceed": 1576,
1627
+ "cele": 1577,
1628
+ "board": 1578,
1629
+ "bottom": 1579,
1630
+ "boarding": 1580,
1631
+ "botoom": 1581,
1632
+ "moon": 1582,
1633
+ "move": 1583,
1634
+ "mood": 1584,
1635
+ "moment": 1585,
1636
+ "alread": 1586,
1637
+ "alpha": 1587,
1638
+ "dead": 1588,
1639
+ "degree": 1589,
1640
+ "demand": 1590,
1641
+ "rlpo": 1591,
1642
+ "chance": 1592,
1643
+ "charac": 1593,
1644
+ "advice": 1594,
1645
+ "adtition": 1595,
1646
+ "soon": 1596,
1647
+ "some": 1597,
1648
+ "sopy": 1598,
1649
+ "docum": 1599,
1650
+ "hir": 1600,
1651
+ "tici": 1601,
1652
+ "tired": 1602,
1653
+ "lied": 1603,
1654
+ "light": 1604,
1655
+ "living": 1605,
1656
+ "losopy": 1606,
1657
+ "ELVES": 1607,
1658
+ "evil": 1608,
1659
+ "returnes": 1609,
1660
+ "brate": 1610,
1661
+ "ently": 1611,
1662
+ "untr": 1612,
1663
+ "unfaithful": 1613,
1664
+ "why": 1614,
1665
+ "when": 1615,
1666
+ "whoever": 1616,
1667
+ "manat": 1617,
1668
+ "act": 1618,
1669
+ "acqu": 1619,
1670
+ "weather": 1620,
1671
+ "frost": 1621,
1672
+ "ilding": 1622,
1673
+ "sia": 1623,
1674
+ "sick": 1624,
1675
+ "vie": 1625,
1676
+ "vide": 1626,
1677
+ "viet": 1627,
1678
+ "wolk": 1628,
1679
+ "women": 1629,
1680
+ "aining": 1630,
1681
+ "ainted": 1631,
1682
+ "puting": 1632,
1683
+ "endure": 1633,
1684
+ "days": 1634,
1685
+ "ries": 1635,
1686
+ "rict": 1636,
1687
+ "ript": 1637,
1688
+ "button": 1638,
1689
+ "divide": 1639,
1690
+ "pect": 1640,
1691
+ "grum": 1641,
1692
+ "grate": 1642,
1693
+ "ground": 1643,
1694
+ "comfort": 1644,
1695
+ "fice": 1645,
1696
+ "foam": 1646,
1697
+ "hulla": 1647,
1698
+ "near": 1648,
1699
+ "neck": 1649,
1700
+ "words": 1650,
1701
+ "beauty": 1651,
1702
+ "outdoor": 1652,
1703
+ "waters": 1653,
1704
+ "ately": 1654,
1705
+ "looked": 1655,
1706
+ "break": 1656,
1707
+ "spread": 1657,
1708
+ "hang": 1658,
1709
+ "respect": 1659,
1710
+ "seems": 1660,
1711
+ "friendshi": 1661,
1712
+ "THEMS": 1662,
1713
+ "exting": 1663,
1714
+ "exceed": 1664,
1715
+ "office": 1665,
1716
+ "appereance": 1666,
1717
+ "lovesick": 1667,
1718
+ "captain": 1668,
1719
+ "countries": 1669,
1720
+ "fourteen": 1670,
1721
+ "pile": 1671,
1722
+ "piece": 1672,
1723
+ "arms": 1673,
1724
+ "PROHIB": 1674,
1725
+ "closer": 1675,
1726
+ "clock": 1676,
1727
+ "served": 1677,
1728
+ "sweet": 1678,
1729
+ "whirlpo": 1679,
1730
+ "leather": 1680,
1731
+ "azer": 1681,
1732
+ "azebaijan": 1682,
1733
+ "grandchild": 1683,
1734
+ "milk": 1684,
1735
+ "writing": 1685,
1736
+ "black": 1686,
1737
+ "blue": 1687,
1738
+ "dinner": 1688,
1739
+ "dagist": 1689,
1740
+ "partici": 1690,
1741
+ "usted": 1691,
1742
+ "restaur": 1692,
1743
+ "bulls": 1693,
1744
+ "building": 1694,
1745
+ "carry": 1695,
1746
+ "empty": 1696,
1747
+ "jumping": 1697,
1748
+ "porter": 1698,
1749
+ "Jaffer": 1699,
1750
+ "aching": 1700,
1751
+ "contr": 1701,
1752
+ "consc": 1702,
1753
+ "condition": 1703,
1754
+ "cutting": 1704,
1755
+ "guy": 1705,
1756
+ "stopping": 1706,
1757
+ "stopped": 1707,
1758
+ "shop": 1708,
1759
+ "shoot": 1709,
1760
+ "tradtition": 1710,
1761
+ "training": 1711,
1762
+ "bets": 1712,
1763
+ "approxim": 1713,
1764
+ "decided": 1714,
1765
+ "springboard": 1715,
1766
+ "answers": 1716,
1767
+ "OUND": 1717,
1768
+ "OUGH": 1718,
1769
+ "area": 1719,
1770
+ "quick": 1720,
1771
+ "yrdal": 1721,
1772
+ "separation": 1722,
1773
+ "separated": 1723,
1774
+ "tomonies": 1724,
1775
+ "tomorrow": 1725,
1776
+ "talked": 1726,
1777
+ "Zeynaddin": 1727,
1778
+ "walked": 1728,
1779
+ "print": 1729,
1780
+ "suffer": 1730,
1781
+ "window": 1731,
1782
+ "encyclo": 1732,
1783
+ "recently": 1733,
1784
+ "reigned": 1734,
1785
+ "commonly": 1735,
1786
+ "existed": 1736,
1787
+ "mistakes": 1737,
1788
+ "Migrah": 1738,
1789
+ "praised": 1739,
1790
+ "AROUND": 1740,
1791
+ "Ruslan": 1741,
1792
+ "Russia": 1742,
1793
+ "byaddin": 1743,
1794
+ "curse": 1744,
1795
+ "course": 1745,
1796
+ "courage": 1746,
1797
+ "creating": 1747,
1798
+ "created": 1748,
1799
+ "fifty": 1749,
1800
+ "fifteen": 1750,
1801
+ "pedis": 1751,
1802
+ "sings": 1752,
1803
+ "singers": 1753,
1804
+ "sitting": 1754,
1805
+ "wait": 1755,
1806
+ "waves": 1756,
1807
+ "working": 1757,
1808
+ "worthy": 1758,
1809
+ "attack": 1759,
1810
+ "attaching": 1760,
1811
+ "release": 1761,
1812
+ "released": 1762,
1813
+ "deceive": 1763,
1814
+ "deceiving": 1764,
1815
+ "footprint": 1765,
1816
+ "accidentally": 1766,
1817
+ "ANYWAY": 1767,
1818
+ "APC": 1768,
1819
+ "About": 1769,
1820
+ "Akht": 1770,
1821
+ "ASSOCI": 1771,
1822
+ "Asef": 1772,
1823
+ "Afiya": 1773,
1824
+ "Alyaska": 1774,
1825
+ "America": 1775,
1826
+ "BROUGH": 1776,
1827
+ "Big": 1777,
1828
+ "Beshir": 1778,
1829
+ "Ferhad": 1779,
1830
+ "FLEW": 1780,
1831
+ "HID": 1781,
1832
+ "HEARD": 1782,
1833
+ "Idris": 1783,
1834
+ "KOPY": 1784,
1835
+ "Khyrdal": 1785,
1836
+ "KING": 1786,
1837
+ "Leyli": 1787,
1838
+ "LITTLE": 1788,
1839
+ "LISTEN": 1789,
1840
+ "Mehman": 1790,
1841
+ "Medjnun": 1791,
1842
+ "Nasru": 1792,
1843
+ "OGON": 1793,
1844
+ "Rahulla": 1794,
1845
+ "Soviet": 1795,
1846
+ "Sabri": 1796,
1847
+ "Shemsed": 1797,
1848
+ "Shirin": 1798,
1849
+ "Shubyaddin": 1799,
1850
+ "Shollar": 1800,
1851
+ "TWENTY": 1801,
1852
+ "TURNED": 1802,
1853
+ "TALKING": 1803,
1854
+ "Uhm": 1804,
1855
+ "USSR": 1805,
1856
+ "Yusif": 1806,
1857
+ "basicall": 1807,
1858
+ "bury": 1808,
1859
+ "bles": 1809,
1860
+ "clever": 1810,
1861
+ "checking": 1811,
1862
+ "casset": 1812,
1863
+ "cunning": 1813,
1864
+ "camp": 1814,
1865
+ "custom": 1815,
1866
+ "disaster": 1816,
1867
+ "ditch": 1817,
1868
+ "driver": 1818,
1869
+ "district": 1819,
1870
+ "draw": 1820,
1871
+ "easy": 1821,
1872
+ "esting": 1822,
1873
+ "floored": 1823,
1874
+ "flint": 1824,
1875
+ "flower": 1825,
1876
+ "gym": 1826,
1877
+ "gusaris": 1827,
1878
+ "knock": 1828,
1879
+ "mug": 1829,
1880
+ "month": 1830,
1881
+ "mouth": 1831,
1882
+ "money": 1832,
1883
+ "morning": 1833,
1884
+ "massage": 1834,
1885
+ "mills": 1835,
1886
+ "philosopy": 1836,
1887
+ "price": 1837,
1888
+ "party": 1838,
1889
+ "pouring": 1839,
1890
+ "paths": 1840,
1891
+ "randchild": 1841,
1892
+ "stove": 1842,
1893
+ "sale": 1843,
1894
+ "sadness": 1844,
1895
+ "shoulder": 1845,
1896
+ "summer": 1846,
1897
+ "slyness": 1847,
1898
+ "supporter": 1848,
1899
+ "touch": 1849,
1900
+ "twelve": 1850,
1901
+ "testomonies": 1851,
1902
+ "tremor": 1852,
1903
+ "tongue": 1853,
1904
+ "twenty": 1854,
1905
+ "valley": 1855,
1906
+ "vacation": 1856,
1907
+ "voltage": 1857,
1908
+ "thinking": 1858,
1909
+ "thorns": 1859,
1910
+ "throat": 1860,
1911
+ "thanks": 1861,
1912
+ "throwing": 1862,
1913
+ "interesting": 1863,
1914
+ "attract": 1864,
1915
+ "secured": 1865,
1916
+ "security": 1866,
1917
+ "belivie": 1867,
1918
+ "believe": 1868,
1919
+ "absolutely": 1869,
1920
+ "STAYED": 1870,
1921
+ "heavy": 1871,
1922
+ "celebrate": 1872,
1923
+ "already": 1873,
1924
+ "alphabets": 1874,
1925
+ "character": 1875,
1926
+ "document": 1876,
1927
+ "lightning": 1877,
1928
+ "untrusted": 1878,
1929
+ "acquainted": 1879,
1930
+ "grumbles": 1880,
1931
+ "grateful": 1881,
1932
+ "outdoors": 1882,
1933
+ "friendship": 1883,
1934
+ "THEMSELVES": 1884,
1935
+ "extinguish": 1885,
1936
+ "whirlpool": 1886,
1937
+ "azebaijanis": 1887,
1938
+ "dagistanish": 1888,
1939
+ "participate": 1889,
1940
+ "restaurant": 1890,
1941
+ "contrary": 1891,
1942
+ "conscript": 1892,
1943
+ "approximately": 1893,
1944
+ "quickly": 1894,
1945
+ "encyclopedis": 1895,
1946
+ "Akhtinsky": 1896,
1947
+ "ASSOCIATED": 1897,
1948
+ "BROUGHT": 1898,
1949
+ "Khyrdalan": 1899,
1950
+ "Nasrullah": 1900,
1951
+ "Shemseddin": 1901,
1952
+ "basically": 1902
1953
  },
1954
  "merges": [
1955
  "A O",
tokenizer_config.json CHANGED
@@ -2,5 +2,6 @@
2
  "clean_up_tokenization_spaces": true,
3
  "eos_token": "<end>",
4
  "model_max_length": 1000000000000000019884624838656,
 
5
  "tokenizer_class": "PreTrainedTokenizerFast"
6
  }
 
2
  "clean_up_tokenization_spaces": true,
3
  "eos_token": "<end>",
4
  "model_max_length": 1000000000000000019884624838656,
5
+ "pad_token": "<pad>",
6
  "tokenizer_class": "PreTrainedTokenizerFast"
7
  }