Vectorrent commited on
Commit
cd789a1
·
verified ·
1 Parent(s): 7b0d7a6

Upload 3 files

Browse files
Files changed (1) hide show
  1. tokenizer.json +1423 -1423
tokenizer.json CHANGED
@@ -46,12 +46,6 @@
46
  "pre_tokenizer": {
47
  "type": "Sequence",
48
  "pretokenizers": [
49
- {
50
- "type": "ByteLevel",
51
- "add_prefix_space": false,
52
- "trim_offsets": true,
53
- "use_regex": true
54
- },
55
  {
56
  "type": "Punctuation",
57
  "behavior": "Isolated"
@@ -59,6 +53,12 @@
59
  {
60
  "type": "Digits",
61
  "individual_digits": true
 
 
 
 
 
 
62
  }
63
  ]
64
  },
@@ -349,765 +349,765 @@
349
  "he": 262,
350
  "in": 263,
351
  "re": 264,
352
- "on": 265,
353
- "er": 266,
354
- "Ġo": 267,
355
- "at": 268,
356
- "Ġs": 269,
357
- "en": 270,
358
- "Ġc": 271,
359
- "Ġw": 272,
360
  "es": 273,
361
- "is": 274,
362
- "nd": 275,
363
- "it": 276,
364
- "or": 277,
365
- "Ġp": 278,
366
- "al": 279,
367
- "Ġb": 280,
368
- "ed": 281,
369
- "an": 282,
370
- "Ġf": 283,
371
- "ou": 284,
372
- "ar": 285,
373
- "Ġm": 286,
374
- "ic": 287,
375
- "Ġd": 288,
376
- "le": 289,
377
- "ro": 290,
378
- "as": 291,
379
- "Ġh": 292,
380
- "ct": 293,
381
- "Ġe": 294,
382
- "il": 295,
383
- "om": 296,
384
- "ve": 297,
385
- "Ġl": 298,
386
- "st": 299,
387
- "Ġn": 300,
388
- "ly": 301,
389
- "âĢ": 302,
390
- "et": 303,
391
- "ĠT": 304,
392
- "ol": 305,
393
- "se": 306,
394
- "Ġg": 307,
395
- "im": 308,
396
- "id": 309,
397
- "ot": 310,
398
- "ut": 311,
399
- "ow": 312,
400
- "ce": 313,
401
- "ur": 314,
402
- "ra": 315,
403
- "ch": 316,
404
- "ĠA": 317,
405
- "ig": 318,
406
- "ĠS": 319,
407
- "Ġu": 320,
408
- "ĠC": 321,
409
- "ir": 322,
410
- "ĠI": 323,
411
- "Ġy": 324,
412
- "ts": 325,
413
- "el": 326,
414
- "ul": 327,
415
- "ay": 328,
416
- "am": 329,
417
- "ad": 330,
418
- "if": 331,
419
- "od": 332,
420
- "ĠM": 333,
421
- "op": 334,
422
- "iv": 335,
423
- "ge": 336,
424
- "th": 337,
425
- "ec": 338,
426
- "ĠP": 339,
427
- "Ġv": 340,
428
- "um": 341,
429
- "ab": 342,
430
- "ĠB": 343,
431
- "em": 344,
432
- "us": 345,
433
- "ti": 346,
434
- "ac": 347,
435
- "ĠH": 348,
436
- "os": 349,
437
- "ld": 350,
438
- "ke": 351,
439
- "nt": 352,
440
- "qu": 353,
441
- "ĠW": 354,
442
- "ri": 355,
443
- "pp": 356,
444
- "ĠD": 357,
445
- "ud": 358,
446
- "ĠE": 359,
447
- "oc": 360,
448
- "ĠR": 361,
449
- "Ġr": 362,
450
- "ĠF": 363,
451
- "si": 364,
452
- "un": 365,
453
- "ff": 366,
454
- "ll": 367,
455
- "og": 368,
456
- "ĠG": 369,
457
- "ĠN": 370,
458
- "ls": 371,
459
- "ew": 372,
460
- "ht": 373,
461
- "ho": 374,
462
- "ĠL": 375,
463
- "te": 376,
464
- "ta": 377,
465
- "ss": 378,
466
- "la": 379,
467
- "du": 380,
468
- "ap": 381,
469
- "ev": 382,
470
- "ep": 383,
471
- "ĠO": 384,
472
- "ĠJ": 385,
473
- "tr": 386,
474
- "ub": 387,
475
- "Ġk": 388,
476
- "xp": 389,
477
- "ag": 390,
478
- "ak": 391,
479
- "ĠU": 392,
480
- "iz": 393,
481
- "gh": 394,
482
- "ft": 395,
483
- "hi": 396,
484
- "cc": 397,
485
- "ov": 398,
486
- "ef": 399,
487
- "ci": 400,
488
- "oo": 401,
489
- "ds": 402,
490
- "li": 403,
491
- "pe": 404,
492
- "to": 405,
493
- "ks": 406,
494
- "fe": 407,
495
- "lo": 408,
496
- "av": 409,
497
- "ia": 410,
498
- "cl": 411,
499
- "eg": 412,
500
- "au": 413,
501
- "gs": 414,
502
- "ry": 415,
503
- "ru": 416,
504
- "Ġj": 417,
505
- "hr": 418,
506
- "ue": 419,
507
- "ĠK": 420,
508
- "pt": 421,
509
- "hy": 422,
510
- "xt": 423,
511
- "ee": 424,
512
- "pl": 425,
513
- "tt": 426,
514
- "pa": 427,
515
- "rs": 428,
516
- "ms": 429,
517
- "ne": 430,
518
- "ps": 431,
519
- "ĠV": 432,
520
- "ny": 433,
521
- "ea": 434,
522
- "we": 435,
523
- "sp": 436,
524
- "je": 437,
525
- "ng": 438,
526
- "ĠY": 439,
527
- "ib": 440,
528
- "wo": 441,
529
- "ty": 442,
530
- "ns": 443,
531
- "tu": 444,
532
- "dd": 445,
533
- "ph": 446,
534
- "ma": 447,
535
- "su": 448,
536
- "uc": 449,
537
- "rt": 450,
538
- "ob": 451,
539
- "wn": 452,
540
- "lp": 453,
541
- "ug": 454,
542
- "eb": 455,
543
- "cy": 456,
544
- "ip": 457,
545
- "ha": 458,
546
- "rg": 459,
547
- "In": 460,
548
- "ie": 461,
549
- "aw": 462,
550
- "ga": 463,
551
- "yp": 464,
552
- "ym": 465,
553
- "nc": 466,
554
- "up": 467,
555
- "lu": 468,
556
- "vi": 469,
557
- "bs": 470,
558
- "de": 471,
559
- "ys": 472,
560
- "ck": 473,
561
- "Th": 474,
562
- "mo": 475,
563
- "mb": 476,
564
- "dv": 477,
565
- "gu": 478,
566
- "mp": 479,
567
- "di": 480,
568
- "pr": 481,
569
- "ni": 482,
570
- "gy": 483,
571
- "nm": 484,
572
- "co": 485,
573
- "fa": 486,
574
- "ex": 487,
575
- "sc": 488,
576
- "eh": 489,
577
- "me": 490,
578
- "rd": 491,
579
- "rn": 492,
580
- "gr": 493,
581
- "ey": 494,
582
- "gi": 495,
583
- "sa": 496,
584
- "tm": 497,
585
- "lf": 498,
586
- "ox": 499,
587
- "rc": 500,
588
- "ix": 501,
589
- "po": 502,
590
- "aj": 503,
591
- "va": 504,
592
- "be": 505,
593
- "bo": 506,
594
- "wa": 507,
595
- "lt": 508,
596
- "oy": 509,
597
- "ax": 510,
598
- "io": 511,
599
- "fr": 512,
600
- "sh": 513,
601
- "sk": 514,
602
- "sf": 515,
603
- "rm": 516,
604
- "It": 517,
605
- "Wh": 518,
606
- "oh": 519,
607
- "fl": 520,
608
- "nn": 521,
609
- "ah": 522,
610
- "ye": 523,
611
- "fo": 524,
612
- "sy": 525,
613
- "br": 526,
614
- "dm": 527,
615
- "sm": 528,
616
- "go": 529,
617
- "ĠZ": 530,
618
- "af": 531,
619
- "ik": 532,
620
- "ĠQ": 533,
621
- "ww": 534,
622
- "vo": 535,
623
- "lv": 536,
624
- "az": 537,
625
- "tl": 538,
626
- "lw": 539,
627
- "na": 540,
628
- "We": 541,
629
- "of": 542,
630
- "If": 543,
631
- "bi": 544,
632
- "mm": 545,
633
- "yn": 546,
634
- "yd": 547,
635
- "bl": 548,
636
- "bu": 549,
637
- "As": 550,
638
- "by": 551,
639
- "sl": 552,
640
- "xc": 553,
641
- "ca": 554,
642
- "SA": 555,
643
- "NA": 556,
644
- "nf": 557,
645
- "Ġz": 558,
646
- "py": 559,
647
- "eo": 560,
648
- "ba": 561,
649
- "hm": 562,
650
- "no": 563,
651
- "tc": 564,
652
- "ky": 565,
653
- "dl": 566,
654
- "ER": 567,
655
- "do": 568,
656
- "gl": 569,
657
- "ai": 570,
658
- "He": 571,
659
- "An": 572,
660
- "ze": 573,
661
- "rr": 574,
662
- "kn": 575,
663
- "fi": 576,
664
- "Ġi": 577,
665
- "ws": 578,
666
- "hs": 579,
667
- "To": 580,
668
- "St": 581,
669
- "ĠX": 582,
670
- "ek": 583,
671
- "tn": 584,
672
- "eu": 585,
673
- "gt": 586,
674
- "ju": 587,
675
- "gg": 588,
676
- "rb": 589,
677
- "On": 590,
678
- "xa": 591,
679
- "pi": 592,
680
- "é": 593,
681
- "ID": 594,
682
- "ka": 595,
683
- "nv": 596,
684
- "cu": 597,
685
- "ES": 598,
686
- "gn": 599,
687
- "cr": 600,
688
- "AT": 601,
689
- "ae": 602,
690
- "ĠÂ": 603,
691
- "AR": 604,
692
- "so": 605,
693
- "yc": 606,
694
- "hl": 607,
695
- "dr": 608,
696
- "xi": 609,
697
- "uy": 610,
698
- "IN": 611,
699
- "yl": 612,
700
- "ON": 613,
701
- "Ch": 614,
702
- "IS": 615,
703
- "yr": 616,
704
- "Mo": 617,
705
- "OR": 618,
706
- "nl": 619,
707
- "Al": 620,
708
- "II": 621,
709
- "ok": 622,
710
- "AN": 623,
711
- "So": 624,
712
- "yt": 625,
713
- "pd": 626,
714
- "fu": 627,
715
- "IC": 628,
716
- "lm": 629,
717
- "ln": 630,
718
- "wh": 631,
719
- "hb": 632,
720
- "AS": 633,
721
- "uk": 634,
722
- "EN": 635,
723
- "IV": 636,
724
- "gm": 637,
725
- "da": 638,
726
- "AC": 639,
727
- "Ġx": 640,
728
- "ED": 641,
729
- "yg": 642,
730
- "IT": 643,
731
- "At": 644,
732
- "mi": 645,
733
- "By": 646,
734
- "hu": 647,
735
- "sn": 648,
736
- "PA": 649,
737
- "Ev": 650,
738
- "lb": 651,
739
- "bb": 652,
740
- "kl": 653,
741
- "Am": 654,
742
- "oz": 655,
743
- "ki": 656,
744
- "AL": 657,
745
- "oa": 658,
746
- "oi": 659,
747
- "ez": 660,
748
- "hw": 661,
749
- "Re": 662,
750
- "HE": 663,
751
- "RE": 664,
752
- "ST": 665,
753
- "gd": 666,
754
- "oe": 667,
755
- "DA": 668,
756
- "Ġâ": 669,
757
- "rw": 670,
758
- "Cl": 671,
759
- "Le": 672,
760
- "ya": 673,
761
- "EC": 674,
762
- "sw": 675,
763
- "SS": 676,
764
- "AM": 677,
765
- "°": 678,
766
- "uz": 679,
767
- "à¤": 680,
768
- "yz": 681,
769
- "yb": 682,
770
- "ET": 683,
771
- "np": 684,
772
- "dw": 685,
773
- "EM": 686,
774
- "dy": 687,
775
- "my": 688,
776
- "SB": 689,
777
- "za": 690,
778
- "PS": 691,
779
- "lg": 692,
780
- "No": 693,
781
- "Do": 694,
782
- "CO": 695,
783
- "Is": 696,
784
- "dn": 697,
785
- "bn": 698,
786
- "RO": 699,
787
- "ux": 700,
788
- "Äģ": 701,
789
- "bt": 702,
790
- "AD": 703,
791
- "ĠÃ": 704,
792
- "CC": 705,
793
- "nw": 706,
794
- "Go": 707,
795
- "AP": 708,
796
- "EL": 709,
797
- "OT": 710,
798
- "dh": 711,
799
- "ml": 712,
800
- "Ph": 713,
801
- "ND": 714,
802
- "OS": 715,
803
- "SD": 716,
804
- "Sh": 717,
805
- "RI": 718,
806
- "BC": 719,
807
- "Sp": 720,
808
- "Un": 721,
809
- "sb": 722,
810
- "ÃŃ": 723,
811
- "ii": 724,
812
- "kw": 725,
813
- "De": 726,
814
- "DF": 727,
815
- "OV": 728,
816
- "ei": 729,
817
- "US": 730,
818
- "Dr": 731,
819
- "MS": 732,
820
- "Ot": 733,
821
- "Ab": 734,
822
- "DC": 735,
823
- "ĠÎ": 736,
824
- "HO": 737,
825
- "Po": 738,
826
- "mf": 739,
827
- "Ex": 740,
828
- "CT": 741,
829
- "wr": 742,
830
- "Pl": 743,
831
- "Te": 744,
832
- "CE": 745,
833
- "IL": 746,
834
- "Ne": 747,
835
- "bd": 748,
836
- "hd": 749,
837
- "My": 750,
838
- "hn": 751,
839
- "Se": 752,
840
- "Su": 753,
841
- "UR": 754,
842
- "Ma": 755,
843
- "jo": 756,
844
- "LE": 757,
845
- "df": 758,
846
- "yw": 759,
847
- "xf": 760,
848
- "Us": 761,
849
- "CS": 762,
850
- "Qu": 763,
851
- "CR": 764,
852
- "tz": 765,
853
- "Pe": 766,
854
- "Co": 767,
855
- "kp": 768,
856
- "xh": 769,
857
- "IP": 770,
858
- "OM": 771,
859
- "EP": 772,
860
- "LA": 773,
861
- "tw": 774,
862
- "Ju": 775,
863
- "km": 776,
864
- "Pr": 777,
865
- "Ov": 778,
866
- "Be": 779,
867
- "Pa": 780,
868
- "OL": 781,
869
- "TI": 782,
870
- "Di": 783,
871
- "DP": 784,
872
- "ao": 785,
873
- "Ar": 786,
874
- "ML": 787,
875
- "TS": 788,
876
- "IA": 789,
877
- "BS": 790,
878
- "CA": 791,
879
- "IR": 792,
880
- "IG": 793,
881
- "Sc": 794,
882
- "Bl": 795,
883
- "pm": 796,
884
- "wd": 797,
885
- "Ha": 798,
886
- "SP": 799,
887
- "mn": 800,
888
- "ij": 801,
889
- "IM": 802,
890
- "ua": 803,
891
- "kt": 804,
892
- "OP": 805,
893
- "Li": 806,
894
- "lc": 807,
895
- "tp": 808,
896
- "Me": 809,
897
- "gf": 810,
898
- "Or": 811,
899
- "ĠÐ": 812,
900
- "CH": 813,
901
- "dj": 814,
902
- "kf": 815,
903
- "kh": 816,
904
- "UN": 817,
905
- "RA": 818,
906
- "sd": 819,
907
- "OC": 820,
908
- "tf": 821,
909
- "Br": 822,
910
- "Tr": 823,
911
- "NS": 824,
912
- "AA": 825,
913
- "â": 826,
914
- "kb": 827,
915
- "wl": 828,
916
- "Of": 829,
917
- "Fi": 830,
918
- "lz": 831,
919
- "nb": 832,
920
- "HD": 833,
921
- "UT": 834,
922
- "PR": 835,
923
- "CD": 836,
924
- "mu": 837,
925
- "EE": 838,
926
- "uh": 839,
927
- "lk": 840,
928
- "CP": 841,
929
- "Vi": 842,
930
- "fs": 843,
931
- "MA": 844,
932
- "cC": 845,
933
- "HA": 846,
934
- "TP": 847,
935
- "ä": 848,
936
- "ko": 849,
937
- "Fo": 850,
938
- "Ed": 851,
939
- "OD": 852,
940
- "ji": 853,
941
- "SC": 854,
942
- "zy": 855,
943
- "pw": 856,
944
- "AB": 857,
945
- "EF": 858,
946
- "OW": 859,
947
- "HS": 860,
948
- "pb": 861,
949
- "La": 862,
950
- "zi": 863,
951
- "zo": 864,
952
- "MP": 865,
953
- "nh": 866,
954
- "RC": 867,
955
- "hf": 868,
956
- "DS": 869,
957
- "Ea": 870,
958
- "Fr": 871,
959
- "CL": 872,
960
- "BT": 873,
961
- "Ad": 874,
962
- "uv": 875,
963
- "SO": 876,
964
- "IF": 877,
965
- "EG": 878,
966
- "а": 879,
967
- "Ùİ": 880,
968
- "®": 881,
969
- "rk": 882,
970
- "TH": 883,
971
- "MC": 884,
972
- "Fa": 885,
973
- "Sa": 886,
974
- "pg": 887,
975
- "ñ": 888,
976
- "UL": 889,
977
- "MD": 890,
978
- "ja": 891,
979
- "fn": 892,
980
- "EA": 893,
981
- "е": 894,
982
- "Ca": 895,
983
- "SL": 896,
984
- "GE": 897,
985
- "MI": 898,
986
- "PL": 899,
987
- "TA": 900,
988
- "Wr": 901,
989
- "Sm": 902,
990
- "Op": 903,
991
- "Ġ×": 904,
992
- "SE": 905,
993
- "à¥": 906,
994
- "sg": 907,
995
- "PI": 908,
996
- "xu": 909,
997
- "Ta": 910,
998
- "Gr": 911,
999
- "zl": 912,
1000
- "fy": 913,
1001
- "ĪĴ": 914,
1002
- "EO": 915,
1003
- "AF": 916,
1004
- "DL": 917,
1005
- "ĠØ": 918,
1006
- "Ge": 919,
1007
- "Ac": 920,
1008
- "hD": 921,
1009
- "Ke": 922,
1010
- "è": 923,
1011
- "NC": 924,
1012
- "Ĥ¬": 925,
1013
- "nu": 926,
1014
- "DR": 927,
1015
- "PP": 928,
1016
- "db": 929,
1017
- "LS": 930,
1018
- "CB": 931,
1019
- "и": 932,
1020
- "TR": 933,
1021
- "td": 934,
1022
- "ãģ": 935,
1023
- "QL": 936,
1024
- "Ĩij": 937,
1025
- "ih": 938,
1026
- "wb": 939,
1027
- "Ps": 940,
1028
- "GS": 941,
1029
- "nk": 942,
1030
- "PV": 943,
1031
- "ui": 944,
1032
- "NT": 945,
1033
- "RS": 946,
1034
- "CI": 947,
1035
- "En": 948,
1036
- "Fe": 949,
1037
- "Os": 950,
1038
- "BI": 951,
1039
- "Im": 952,
1040
- "gb": 953,
1041
- "α": 954,
1042
- "BA": 955,
1043
- "SI": 956,
1044
- "Gu": 957,
1045
- "UC": 958,
1046
- "Hz": 959,
1047
- "iy": 960,
1048
- "SM": 961,
1049
- "Bu": 962,
1050
- "HT": 963,
1051
- "Jo": 964,
1052
- "Fl": 965,
1053
- "LL": 966,
1054
- "BM": 967,
1055
- "Kn": 968,
1056
- "Eu": 969,
1057
- "TE": 970,
1058
- "iu": 971,
1059
- "Lo": 972,
1060
- "PU": 973,
1061
- "NE": 974,
1062
- "TC": 975,
1063
- "uf": 976,
1064
- "wi": 977,
1065
- "SF": 978,
1066
- "tg": 979,
1067
- "©": 980,
1068
- "ÙĦ": 981,
1069
- "Bi": 982,
1070
- "UM": 983,
1071
- "Ob": 984,
1072
- "AV": 985,
1073
- "Ra": 986,
1074
- "CM": 987,
1075
- "vy": 988,
1076
- "RL": 989,
1077
- "BD": 990,
1078
- "ÑĤ": 991,
1079
- "RT": 992,
1080
- "Cr": 993,
1081
- "PD": 994,
1082
- "EV": 995,
1083
- "cm": 996,
1084
- "xy": 997,
1085
- "dg": 998,
1086
- "âĦ": 999,
1087
- "rh": 1000,
1088
- "PT": 1001,
1089
- "ÑĢ": 1002,
1090
- "PC": 1003,
1091
- "LC": 1004,
1092
- "OU": 1005,
1093
- "pc": 1006,
1094
- "nj": 1007,
1095
- "ĠÏ": 1008,
1096
- "wf": 1009,
1097
- "Mu": 1010,
1098
- "FA": 1011,
1099
- "Ñģ": 1012,
1100
- "ME": 1013,
1101
- "rp": 1014,
1102
- "VD": 1015,
1103
- "PM": 1016,
1104
- "FC": 1017,
1105
- "Åį": 1018,
1106
- "tb": 1019,
1107
- "sv": 1020,
1108
- "kg": 1021,
1109
- "WS": 1022,
1110
- "HC": 1023
1111
  },
1112
  "merges": [
1113
  "Ġ t",
@@ -1115,6 +1115,7 @@
1115
  "h e",
1116
  "i n",
1117
  "r e",
 
1118
  "o n",
1119
  "e r",
1120
  "Ġ o",
@@ -1122,8 +1123,8 @@
1122
  "Ġ s",
1123
  "e n",
1124
  "Ġ c",
1125
- "Ġ w",
1126
  "e s",
 
1127
  "i s",
1128
  "n d",
1129
  "i t",
@@ -1132,748 +1133,747 @@
1132
  "a l",
1133
  "Ġ b",
1134
  "e d",
 
1135
  "a n",
1136
  "Ġ f",
 
 
1137
  "o u",
1138
  "a r",
1139
  "Ġ m",
 
 
1140
  "i c",
1141
  "Ġ d",
 
1142
  "l e",
1143
  "r o",
1144
  "a s",
1145
  "Ġ h",
 
 
1146
  "c t",
1147
  "Ġ e",
1148
  "i l",
 
1149
  "o m",
1150
  "v e",
1151
  "Ġ l",
1152
  "s t",
1153
  "Ġ n",
1154
- "l y",
1155
  "â Ģ",
1156
- "e t",
 
 
1157
  "Ġ T",
1158
- "o l",
1159
  "s e",
 
1160
  "Ġ g",
 
1161
  "i m",
1162
  "i d",
1163
- "o t",
1164
  "u t",
1165
- "o w",
1166
  "c e",
 
1167
  "u r",
1168
  "r a",
1169
  "c h",
 
1170
  "Ġ A",
 
1171
  "i g",
1172
- "Ġ S",
1173
  "Ġ u",
1174
- C",
 
 
 
 
 
1175
  "i r",
 
1176
  "Ġ I",
1177
- "Ġ y",
1178
- "t s",
1179
- "e l",
1180
  "u l",
1181
  "a y",
1182
  "a m",
 
 
 
1183
  "a d",
 
 
 
 
 
 
1184
  "i f",
 
 
 
 
 
1185
  "o d",
 
1186
  "Ġ M",
1187
- "o p",
1188
- "i v",
1189
  "g e",
1190
- "t h",
1191
- "e c",
1192
  "Ġ P",
1193
- "Ġ v",
1194
- "u m",
 
 
 
 
 
 
 
1195
  "a b",
 
 
1196
  "Ġ B",
1197
- "e m",
1198
  "u s",
1199
- "t i",
 
 
 
 
 
 
 
 
1200
  "a c",
 
 
 
 
1201
  "Ġ H",
1202
- "o s",
1203
  "l d",
 
 
1204
  "k e",
1205
- "n t",
 
 
1206
  "q u",
 
 
1207
  "Ġ W",
1208
- "r i",
 
1209
  "p p",
1210
- "Ġ D",
1211
  "u d",
 
 
 
 
1212
  "Ġ E",
 
1213
  "o c",
1214
- "Ġ R",
1215
  "Ġ r",
 
 
 
1216
  "Ġ F",
1217
- "s i",
 
 
1218
  "u n",
1219
- "f f",
1220
- "l l",
1221
- "o g",
 
1222
  "Ġ G",
1223
  "Ġ N",
1224
- "l s",
1225
- "e w",
1226
- "h t",
1227
- "h o",
1228
  "Ġ L",
1229
- "t e",
1230
- "t a",
1231
- "s s",
1232
- "l a",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1233
  "d u",
1234
- "a p",
1235
- "e v",
1236
- "e p",
1237
- "Ġ O",
1238
- "Ġ J",
1239
- "t r",
1240
- "u b",
1241
- "Ġ k",
1242
- "x p",
1243
  "a g",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1244
  "a k",
1245
- "Ġ U",
 
 
 
 
 
 
 
 
1246
  "i z",
1247
- "g h",
1248
- "f t",
1249
- "h i",
 
 
 
 
 
 
 
 
1250
  "c c",
1251
- "o v",
1252
- "e f",
1253
- "c i",
1254
- "o o",
1255
- "d s",
1256
- "l i",
1257
- "p e",
1258
- "t o",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1259
  "k s",
1260
- "f e",
1261
- "l o",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1262
  "a v",
1263
- "i a",
1264
- "c l",
1265
- "e g",
1266
  "a u",
1267
- "g s",
1268
- "r y",
1269
- "r u",
1270
  "Ġ j",
1271
- "h r",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1272
  "u e",
 
 
 
 
 
 
 
 
 
 
 
1273
  "Ġ K",
1274
- "p t",
1275
- "h y",
1276
- "x t",
1277
- "e e",
1278
- "p l",
1279
- "t t",
1280
- "p a",
1281
- "r s",
1282
- "m s",
1283
- "n e",
1284
- "p s",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1285
  "Ġ V",
1286
- "n y",
1287
- "e a",
 
 
 
 
 
 
 
 
 
 
 
1288
  "w e",
1289
- "s p",
1290
- "j e",
1291
- "n g",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1292
  "Ġ Y",
1293
- "i b",
1294
- "w o",
1295
- "t y",
1296
- "n s",
1297
- "t u",
1298
- "d d",
1299
- "p h",
1300
- "m a",
1301
- "s u",
1302
- "u c",
1303
- "r t",
 
 
 
1304
  "o b",
1305
- "w n",
1306
- "l p",
1307
- "u g",
1308
- "e b",
1309
- "c y",
1310
- "i p",
1311
- "h a",
1312
- "r g",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1313
  "I n",
1314
- "i e",
 
 
 
 
 
 
1315
  "a w",
1316
- "g a",
1317
- "y p",
1318
- "y m",
1319
- "n c",
1320
- "u p",
1321
- "l u",
1322
- "v i",
1323
- "b s",
1324
- "d e",
1325
- "y s",
1326
- "c k",
1327
- "T h",
1328
- "m o",
1329
- "m b",
1330
- "d v",
1331
- "g u",
1332
- "m p",
1333
- "d i",
1334
- "p r",
1335
- "n i",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1336
  "g y",
1337
- "n m",
1338
- "c o",
1339
- "f a",
1340
- "e x",
1341
- "s c",
1342
- "e h",
1343
- "m e",
1344
- "r d",
1345
- "r n",
1346
- "g r",
1347
- "e y",
1348
- "g i",
1349
- "s a",
1350
- "t m",
1351
- "l f",
1352
- "o x",
1353
- "r c",
1354
- "i x",
1355
- "p o",
1356
- "a j",
1357
- "v a",
1358
- "b e",
1359
- "b o",
1360
- "w a",
1361
- "l t",
1362
  "o y",
1363
- "a x",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1364
  "i o",
1365
- "f r",
1366
- "s h",
1367
- "s k",
1368
- "s f",
1369
- "r m",
1370
- "I t",
1371
- "W h",
1372
- "o h",
1373
- "f l",
1374
- "n n",
1375
- "a h",
1376
- "y e",
1377
- "f o",
1378
- "s y",
1379
- "b r",
1380
- "d m",
1381
- "s m",
1382
- "g o",
1383
- "Ġ Z",
1384
- "a f",
1385
- "i k",
1386
- "Ġ Q",
1387
- "w w",
1388
- "v o",
1389
- "l v",
1390
- "a z",
1391
- "t l",
1392
- "l w",
1393
- "n a",
1394
- "W e",
1395
- "o f",
1396
- "I f",
1397
- "b i",
1398
- "m m",
1399
- "y n",
1400
- "y d",
1401
- "b l",
1402
- "b u",
1403
- "A s",
1404
- "b y",
1405
- "s l",
1406
- "x c",
1407
- "c a",
1408
- "S A",
1409
- "N A",
1410
- "n f",
1411
- "Ġ z",
1412
- "p y",
1413
- "e o",
1414
- "b a",
1415
- "h m",
1416
- "n o",
1417
- "t c",
1418
- "k y",
1419
- "d l",
1420
- "E R",
1421
- "d o",
1422
- "g l",
1423
- "a i",
1424
- "H e",
1425
- "A n",
1426
- "z e",
1427
- "r r",
1428
- "k n",
1429
- "f i",
1430
- "Ġ i",
1431
- "w s",
1432
- "h s",
1433
- "T o",
1434
- "S t",
1435
- "Ġ X",
1436
- "e k",
1437
- "t n",
1438
- "e u",
1439
- "g t",
1440
- "j u",
1441
  "g g",
1442
- "r b",
1443
- "O n",
1444
- "x a",
1445
- "p i",
1446
- "Ã ©",
1447
- "I D",
1448
- "k a",
1449
- "n v",
1450
- "c u",
1451
- "E S",
1452
- "g n",
1453
- "c r",
1454
- "A T",
1455
- "a e",
1456
- "Ġ Â",
1457
- "A R",
1458
- "s o",
1459
- "y c",
1460
- "h l",
1461
- "d r",
1462
- "x i",
1463
- "u y",
1464
- "I N",
1465
- "y l",
1466
- "O N",
1467
- "C h",
1468
- "I S",
1469
- "y r",
1470
- "M o",
1471
- "O R",
1472
- "n l",
1473
- "A l",
1474
- "I I",
1475
- "o k",
1476
- "A N",
1477
- "S o",
1478
- "y t",
1479
- "p d",
1480
- "f u",
1481
- "I C",
1482
- "l m",
1483
- "l n",
1484
- "w h",
1485
- "h b",
1486
- "A S",
1487
- "u k",
1488
- "E N",
1489
- "I V",
1490
- "g m",
1491
- "d a",
1492
- "A C",
1493
- "Ġ x",
1494
- "E D",
1495
- "y g",
1496
- "I T",
1497
- "A t",
1498
- "m i",
1499
- "B y",
1500
- "h u",
1501
- "s n",
1502
- "P A",
1503
- "E v",
1504
- "l b",
1505
- "b b",
1506
- "k l",
1507
- "A m",
1508
- "o z",
1509
- "k i",
1510
- "A L",
1511
- "o a",
1512
- "o i",
1513
- "e z",
1514
- "h w",
1515
- "R e",
1516
- "H E",
1517
- "R E",
1518
- "S T",
1519
- "g d",
1520
- "o e",
1521
- "D A",
1522
- "Ġ â",
1523
- "r w",
1524
- "C l",
1525
- "L e",
1526
- "y a",
1527
- "E C",
1528
- "s w",
1529
- "S S",
1530
- "A M",
1531
- "Â °",
1532
- "u z",
1533
- "à ¤",
1534
- "y z",
1535
- "y b",
1536
- "E T",
1537
- "n p",
1538
- "d w",
1539
- "E M",
1540
- "d y",
1541
- "m y",
1542
- "S B",
1543
- "z a",
1544
- "P S",
1545
- "l g",
1546
- "N o",
1547
- "D o",
1548
- "C O",
1549
- "I s",
1550
- "d n",
1551
- "b n",
1552
- "R O",
1553
- "u x",
1554
- "Ä ģ",
1555
- "b t",
1556
- "A D",
1557
- "Ġ Ã",
1558
- "C C",
1559
- "n w",
1560
- "G o",
1561
- "A P",
1562
- "E L",
1563
- "O T",
1564
- "d h",
1565
- "m l",
1566
- "P h",
1567
- "N D",
1568
- "O S",
1569
- "S D",
1570
- "S h",
1571
- "R I",
1572
- "B C",
1573
- "S p",
1574
- "U n",
1575
- "s b",
1576
- "Ã Ń",
1577
- "i i",
1578
- "k w",
1579
- "D e",
1580
- "D F",
1581
- "O V",
1582
- "e i",
1583
- "U S",
1584
- "D r",
1585
- "M S",
1586
- "O t",
1587
- "A b",
1588
- "D C",
1589
- "Ġ Î",
1590
- "H O",
1591
- "P o",
1592
- "m f",
1593
- "E x",
1594
- "C T",
1595
- "w r",
1596
- "P l",
1597
- "T e",
1598
- "C E",
1599
- "I L",
1600
- "N e",
1601
- "b d",
1602
- "h d",
1603
- "M y",
1604
- "h n",
1605
- "S e",
1606
- "S u",
1607
- "U R",
1608
- "M a",
1609
- "j o",
1610
- "L E",
1611
- "d f",
1612
- "y w",
1613
- "x f",
1614
- "U s",
1615
- "C S",
1616
- "Q u",
1617
- "C R",
1618
- "t z",
1619
- "P e",
1620
- "C o",
1621
- "k p",
1622
- "x h",
1623
- "I P",
1624
- "O M",
1625
- "E P",
1626
- "L A",
1627
- "t w",
1628
- "J u",
1629
- "k m",
1630
- "P r",
1631
- "O v",
1632
- "B e",
1633
- "P a",
1634
- "O L",
1635
- "T I",
1636
- "D i",
1637
- "D P",
1638
- "a o",
1639
- "A r",
1640
- "M L",
1641
- "T S",
1642
- "I A",
1643
- "B S",
1644
- "C A",
1645
- "I R",
1646
- "I G",
1647
- "S c",
1648
- "B l",
1649
- "p m",
1650
- "w d",
1651
- "H a",
1652
- "S P",
1653
- "m n",
1654
- "i j",
1655
- "I M",
1656
- "u a",
1657
- "k t",
1658
- "O P",
1659
- "L i",
1660
- "l c",
1661
- "t p",
1662
- "M e",
1663
- "g f",
1664
- "O r",
1665
- "Ġ Ð",
1666
- "C H",
1667
- "d j",
1668
- "k f",
1669
- "k h",
1670
- "U N",
1671
- "R A",
1672
- "s d",
1673
- "O C",
1674
- "t f",
1675
- "B r",
1676
- "T r",
1677
- "N S",
1678
- "A A",
1679
- "Ã ¢",
1680
- "k b",
1681
- "w l",
1682
- "O f",
1683
- "F i",
1684
- "l z",
1685
- "n b",
1686
- "H D",
1687
- "U T",
1688
- "P R",
1689
- "C D",
1690
- "m u",
1691
- "E E",
1692
- "u h",
1693
- "l k",
1694
- "C P",
1695
- "V i",
1696
- "f s",
1697
- "M A",
1698
- "c C",
1699
- "H A",
1700
- "T P",
1701
- "Ã ¤",
1702
- "k o",
1703
- "F o",
1704
- "E d",
1705
- "O D",
1706
- "j i",
1707
- "S C",
1708
- "z y",
1709
- "p w",
1710
- "A B",
1711
- "E F",
1712
- "O W",
1713
- "H S",
1714
- "p b",
1715
- "L a",
1716
- "z i",
1717
- "z o",
1718
- "M P",
1719
- "n h",
1720
- "R C",
1721
- "h f",
1722
- "D S",
1723
- "E a",
1724
- "F r",
1725
- "C L",
1726
- "B T",
1727
- "A d",
1728
- "u v",
1729
- "S O",
1730
- "I F",
1731
- "E G",
1732
- "Ð °",
1733
- "Ù İ",
1734
- "Â ®",
1735
- "r k",
1736
- "T H",
1737
- "M C",
1738
- "F a",
1739
- "S a",
1740
- "p g",
1741
- "Ã ±",
1742
- "U L",
1743
- "M D",
1744
- "j a",
1745
- "f n",
1746
- "E A",
1747
- "Ð µ",
1748
- "C a",
1749
- "S L",
1750
- "G E",
1751
- "M I",
1752
- "P L",
1753
- "T A",
1754
- "W r",
1755
- "S m",
1756
- "O p",
1757
- "Ġ ×",
1758
- "S E",
1759
- "à ¥",
1760
- "s g",
1761
- "P I",
1762
- "x u",
1763
- "T a",
1764
- "G r",
1765
- "z l",
1766
- "f y",
1767
- "Ī Ĵ",
1768
- "E O",
1769
- "A F",
1770
- "D L",
1771
- "Ġ Ø",
1772
- "G e",
1773
- "A c",
1774
- "h D",
1775
- "K e",
1776
- "Ã ¨",
1777
- "N C",
1778
- "Ĥ ¬",
1779
- "n u",
1780
- "D R",
1781
- "P P",
1782
- "d b",
1783
- "L S",
1784
- "C B",
1785
- "Ð ¸",
1786
- "T R",
1787
- "t d",
1788
- "ã ģ",
1789
- "Q L",
1790
- "Ĩ ij",
1791
- "i h",
1792
- "w b",
1793
- "P s",
1794
- "G S",
1795
- "n k",
1796
- "P V",
1797
- "u i",
1798
- "N T",
1799
- "R S",
1800
- "C I",
1801
- "E n",
1802
- "F e",
1803
- "O s",
1804
- "B I",
1805
- "I m",
1806
- "g b",
1807
- "Î ±",
1808
- "B A",
1809
- "S I",
1810
- "G u",
1811
- "U C",
1812
- "H z",
1813
- "i y",
1814
- "S M",
1815
- "B u",
1816
- "H T",
1817
- "J o",
1818
- "F l",
1819
- "L L",
1820
- "B M",
1821
- "K n",
1822
- "E u",
1823
- "T E",
1824
- "i u",
1825
- "L o",
1826
- "P U",
1827
- "N E",
1828
- "T C",
1829
- "u f",
1830
- "w i",
1831
- "S F",
1832
- "t g",
1833
- "Â ©",
1834
- "Ù Ħ",
1835
- "B i",
1836
- "U M",
1837
- "O b",
1838
- "A V",
1839
- "R a",
1840
- "C M",
1841
- "v y",
1842
- "R L",
1843
- "B D",
1844
- "Ñ Ĥ",
1845
- "R T",
1846
- "C r",
1847
- "P D",
1848
- "E V",
1849
- "c m",
1850
- "x y",
1851
- "d g",
1852
- "â Ħ",
1853
- "r h",
1854
- "P T",
1855
- "Ñ Ģ",
1856
- "P C",
1857
- "L C",
1858
- "O U",
1859
- "p c",
1860
- "n j",
1861
- "Ġ Ï",
1862
- "w f",
1863
- "M u",
1864
- "F A",
1865
- "Ñ ģ",
1866
- "M E",
1867
- "r p",
1868
- "V D",
1869
- "P M",
1870
- "F C",
1871
- "Å į",
1872
- "t b",
1873
- "s v",
1874
- "k g",
1875
- "W S",
1876
- "H C"
1877
  ]
1878
  }
1879
  }
 
46
  "pre_tokenizer": {
47
  "type": "Sequence",
48
  "pretokenizers": [
 
 
 
 
 
 
49
  {
50
  "type": "Punctuation",
51
  "behavior": "Isolated"
 
53
  {
54
  "type": "Digits",
55
  "individual_digits": true
56
+ },
57
+ {
58
+ "type": "ByteLevel",
59
+ "add_prefix_space": false,
60
+ "trim_offsets": true,
61
+ "use_regex": true
62
  }
63
  ]
64
  },
 
349
  "he": 262,
350
  "in": 263,
351
  "re": 264,
352
+ "Ġthe": 265,
353
+ "on": 266,
354
+ "er": 267,
355
+ "Ġo": 268,
356
+ "at": 269,
357
+ "Ġs": 270,
358
+ "en": 271,
359
+ "Ġc": 272,
360
  "es": 273,
361
+ "Ġw": 274,
362
+ "is": 275,
363
+ "nd": 276,
364
+ "it": 277,
365
+ "or": 278,
366
+ "Ġp": 279,
367
+ "al": 280,
368
+ "Ġb": 281,
369
+ "ed": 282,
370
+ "Ġof": 283,
371
+ "an": 284,
372
+ "Ġf": 285,
373
+ "ing": 286,
374
+ "Ġin": 287,
375
+ "ou": 288,
376
+ "ar": 289,
377
+ "Ġm": 290,
378
+ "Ġand": 291,
379
+ "Ġto": 292,
380
+ "ic": 293,
381
+ "Ġd": 294,
382
+ "ion": 295,
383
+ "le": 296,
384
+ "ro": 297,
385
+ "as": 298,
386
+ "Ġh": 299,
387
+ "ent": 300,
388
+ "Ġth": 301,
389
+ "ct": 302,
390
+ "Ġe": 303,
391
+ "il": 304,
392
+ "Ġre": 305,
393
+ "om": 306,
394
+ "ve": 307,
395
+ "Ġl": 308,
396
+ "st": 309,
397
+ "Ġn": 310,
398
+ "âĢ": 311,
399
+ "ly": 312,
400
+ "Ġbe": 313,
401
+ "Ġis": 314,
402
+ "ĠT": 315,
403
+ "se": 316,
404
+ "ol": 317,
405
+ "Ġg": 318,
406
+ "ation": 319,
407
+ "im": 320,
408
+ "id": 321,
409
+ "et": 322,
410
+ "ut": 323,
411
+ "ce": 324,
412
+ "ot": 325,
413
+ "ur": 326,
414
+ "ra": 327,
415
+ "ch": 328,
416
+ "ow": 329,
417
+ "ĠA": 330,
418
+ "Ġfor": 331,
419
+ "ig": 332,
420
+ "Ġu": 333,
421
+ "ĠS": 334,
422
+ "Ġon": 335,
423
+ "Ġthat": 336,
424
+ "Ġst": 337,
425
+ "ver": 338,
426
+ "Ġy": 339,
427
+ "ir": 340,
428
+ "ĠC": 341,
429
+ "ĠI": 342,
430
+ "ul": 343,
431
+ "ay": 344,
432
+ "am": 345,
433
+ "Ġas": 346,
434
+ "ith": 347,
435
+ "el": 348,
436
+ "ad": 349,
437
+ "Ġpro": 350,
438
+ "her": 351,
439
+ "Ġare": 352,
440
+ "Ġcon": 353,
441
+ "Ġan": 354,
442
+ "Ġwith": 355,
443
+ "if": 356,
444
+ "Ġyou": 357,
445
+ "Ġwh": 358,
446
+ "Ġor": 359,
447
+ "Ġit": 360,
448
+ "Ġal": 361,
449
+ "od": 362,
450
+ "ter": 363,
451
+ "ĠM": 364,
452
+ "ĠThe": 365,
453
+ "ment": 366,
454
+ "ge": 367,
455
+ "ĠP": 368,
456
+ "th": 369,
457
+ "op": 370,
458
+ "ate": 371,
459
+ "ist": 372,
460
+ "ers": 373,
461
+ "Ġde": 374,
462
+ "ess": 375,
463
+ "ill": 376,
464
+ "ies": 377,
465
+ "ab": 378,
466
+ "Ġhe": 379,
467
+ "Ġex": 380,
468
+ "ĠB": 381,
469
+ "us": 382,
470
+ "ect": 383,
471
+ "Ġwe": 384,
472
+ "âĢĻ": 385,
473
+ "ore": 386,
474
+ "Ġcom": 387,
475
+ "Ġsu": 388,
476
+ "ity": 389,
477
+ "est": 390,
478
+ "res": 391,
479
+ "ac": 392,
480
+ "ive": 393,
481
+ "Ġha": 394,
482
+ "um": 395,
483
+ "rom": 396,
484
+ "ĠH": 397,
485
+ "ld": 398,
486
+ "Ġv": 399,
487
+ "os": 400,
488
+ "ke": 401,
489
+ "Ġby": 402,
490
+ "ant": 403,
491
+ "em": 404,
492
+ "qu": 405,
493
+ "iv": 406,
494
+ "ain": 407,
495
+ "ĠW": 408,
496
+ "nt": 409,
497
+ "Ġat": 410,
498
+ "pp": 411,
499
+ "igh": 412,
500
+ "ud": 413,
501
+ "ĠD": 414,
502
+ "Ġwas": 415,
503
+ "Ġcan": 416,
504
+ "Ġfrom": 417,
505
+ "ĠE": 418,
506
+ "Ġch": 419,
507
+ "oc": 420,
508
+ "and": 421,
509
+ "Ġr": 422,
510
+ "ort": 423,
511
+ "ĠR": 424,
512
+ "Ġne": 425,
513
+ "ĠF": 426,
514
+ "ial": 427,
515
+ "Ġse": 428,
516
+ "ure": 429,
517
+ "un": 430,
518
+ "Ġnot": 431,
519
+ "Ġle": 432,
520
+ "ical": 433,
521
+ "art": 434,
522
+ "ĠG": 435,
523
+ "ĠN": 436,
524
+ "Ġhave": 437,
525
+ "ri": 438,
526
+ "og": 439,
527
+ "ĠL": 440,
528
+ "Ġsh": 441,
529
+ "Ġen": 442,
530
+ "Ġsp": 443,
531
+ "Ġthis": 444,
532
+ "pt": 445,
533
+ "Ġwor": 446,
534
+ "ight": 447,
535
+ "Ġab": 448,
536
+ "ich": 449,
537
+ "rou": 450,
538
+ "red": 451,
539
+ "all": 452,
540
+ "ions": 453,
541
+ "ould": 454,
542
+ "ost": 455,
543
+ "ther": 456,
544
+ "our": 457,
545
+ "gh": 458,
546
+ "The": 459,
547
+ "du": 460,
548
+ "ome": 461,
549
+ "Ġim": 462,
550
+ "ated": 463,
551
+ "ine": 464,
552
+ "per": 465,
553
+ "Ġus": 466,
554
+ "Ġpl": 467,
555
+ "ag": 468,
556
+ "out": 469,
557
+ "ard": 470,
558
+ "act": 471,
559
+ "ell": 472,
560
+ "ff": 473,
561
+ "ide": 474,
562
+ "Ġtheir": 475,
563
+ "Ġint": 476,
564
+ "pl": 477,
565
+ "ĠO": 478,
566
+ "ans": 479,
567
+ "ear": 480,
568
+ "ast": 481,
569
+ "age": 482,
570
+ "ak": 483,
571
+ "ust": 484,
572
+ "Ġwhich": 485,
573
+ "Ġk": 486,
574
+ "Ġyour": 487,
575
+ "Ġwhe": 488,
576
+ "ĠJ": 489,
577
+ "ec": 490,
578
+ "ous": 491,
579
+ "Ġthey": 492,
580
+ "iz": 493,
581
+ "ĠU": 494,
582
+ "ood": 495,
583
+ "ult": 496,
584
+ "Ġad": 497,
585
+ "Ġall": 498,
586
+ "Ġwill": 499,
587
+ "Ġcont": 500,
588
+ "ib": 501,
589
+ "Ġinc": 502,
590
+ "ĠIn": 503,
591
+ "end": 504,
592
+ "cc": 505,
593
+ "âĢľ": 506,
594
+ "Ġdis": 507,
595
+ "ru": 508,
596
+ "âĢĿ": 509,
597
+ "Ġcomp": 510,
598
+ "ap": 511,
599
+ "Ġmore": 512,
600
+ "Ġres": 513,
601
+ "ong": 514,
602
+ "ip": 515,
603
+ "vel": 516,
604
+ "ia": 517,
605
+ "ew": 518,
606
+ "ations": 519,
607
+ "Ġhas": 520,
608
+ "ere": 521,
609
+ "Ġdo": 522,
610
+ "orm": 523,
611
+ "ary": 524,
612
+ "so": 525,
613
+ "ater": 526,
614
+ "ence": 527,
615
+ "able": 528,
616
+ "are": 529,
617
+ "ild": 530,
618
+ "ĠTh": 531,
619
+ "Ġman": 532,
620
+ "Ġcl": 533,
621
+ "ual": 534,
622
+ "Ġother": 535,
623
+ "ks": 536,
624
+ "Ġbut": 537,
625
+ "ry": 538,
626
+ "Ġwere": 539,
627
+ "ind": 540,
628
+ "Ġper": 541,
629
+ "ents": 542,
630
+ "Ġte": 543,
631
+ "ep": 544,
632
+ "ach": 545,
633
+ "Ġimp": 546,
634
+ "ance": 547,
635
+ "Ġme": 548,
636
+ "Ġone": 549,
637
+ "Ġalso": 550,
638
+ "ose": 551,
639
+ "ign": 552,
640
+ "reat": 553,
641
+ "ake": 554,
642
+ "ress": 555,
643
+ "ass": 556,
644
+ "ase": 557,
645
+ "av": 558,
646
+ "au": 559,
647
+ "ction": 560,
648
+ "Ġj": 561,
649
+ "Ġso": 562,
650
+ "ition": 563,
651
+ "Ġout": 564,
652
+ "ice": 565,
653
+ "Ġun": 566,
654
+ "ber": 567,
655
+ "one": 568,
656
+ "Ġapp": 569,
657
+ "very": 570,
658
+ "Ġar": 571,
659
+ "ime": 572,
660
+ "Ġstud": 573,
661
+ "Ġpart": 574,
662
+ "ord": 575,
663
+ "Ġabout": 576,
664
+ "ory": 577,
665
+ "ace": 578,
666
+ "Ġev": 579,
667
+ "ens": 580,
668
+ "ount": 581,
669
+ "ish": 582,
670
+ "ok": 583,
671
+ "ack": 584,
672
+ "ire": 585,
673
+ "ĠSt": 586,
674
+ "Ġwho": 587,
675
+ "Ġpe": 588,
676
+ "Ġinf": 589,
677
+ "ame": 590,
678
+ "Ġsy": 591,
679
+ "Ġhis": 592,
680
+ "ue": 593,
681
+ "ub": 594,
682
+ "Ġcomm": 595,
683
+ "Ġsc": 596,
684
+ "ors": 597,
685
+ "ite": 598,
686
+ "ang": 599,
687
+ "Ġthem": 600,
688
+ "ces": 601,
689
+ "ike": 602,
690
+ "ree": 603,
691
+ "ound": 604,
692
+ "ĠK": 605,
693
+ "olog": 606,
694
+ "Ġpre": 607,
695
+ "low": 608,
696
+ "now": 609,
697
+ "Ġbec": 610,
698
+ "Ġup": 611,
699
+ "ric": 612,
700
+ "ĠIt": 613,
701
+ "Ġqu": 614,
702
+ "iff": 615,
703
+ "Ġthan": 616,
704
+ "Ġmay": 617,
705
+ "ie": 618,
706
+ "ile": 619,
707
+ "ays": 620,
708
+ "ople": 621,
709
+ "Ġrec": 622,
710
+ "Ġsome": 623,
711
+ "Ġyear": 624,
712
+ "ates": 625,
713
+ "Ġbeen": 626,
714
+ "ail": 627,
715
+ "ĠCh": 628,
716
+ "Ġwhen": 629,
717
+ "Ġthere": 630,
718
+ "nder": 631,
719
+ "ings": 632,
720
+ "âĢĵ": 633,
721
+ "ian": 634,
722
+ "mer": 635,
723
+ "rit": 636,
724
+ "Ġits": 637,
725
+ "ren": 638,
726
+ "Ġinto": 639,
727
+ "Ġwork": 640,
728
+ "ough": 641,
729
+ "Ġgo": 642,
730
+ "ph": 643,
731
+ "Ġtra": 644,
732
+ "Ġag": 645,
733
+ "Ġtime": 646,
734
+ "vers": 647,
735
+ "Ġdiff": 648,
736
+ "te": 649,
737
+ "ĠThis": 650,
738
+ "Ġover": 651,
739
+ "Ġthese": 652,
740
+ "Ġhow": 653,
741
+ "erv": 654,
742
+ "Ġpeople": 655,
743
+ "Ġro": 656,
744
+ "ons": 657,
745
+ "rough": 658,
746
+ "ĠV": 659,
747
+ "ally": 660,
748
+ "lud": 661,
749
+ "ause": 662,
750
+ "ond": 663,
751
+ "Ġcons": 664,
752
+ "Ġuse": 665,
753
+ "Ġcol": 666,
754
+ "ms": 667,
755
+ "Ġtr": 668,
756
+ "ll": 669,
757
+ "Ġra": 670,
758
+ "ific": 671,
759
+ "tern": 672,
760
+ "we": 673,
761
+ "Ġbet": 674,
762
+ "Ġhad": 675,
763
+ "Ġact": 676,
764
+ "ys": 677,
765
+ "ove": 678,
766
+ "Ġour": 679,
767
+ "int": 680,
768
+ "Ġmost": 681,
769
+ "alth": 682,
770
+ "Ġlike": 683,
771
+ "irst": 684,
772
+ "ities": 685,
773
+ "Ġknow": 686,
774
+ "Ġunder": 687,
775
+ "lic": 688,
776
+ "Ġbl": 689,
777
+ "lect": 690,
778
+ "Ġsa": 691,
779
+ "ments": 692,
780
+ "Ġdes": 693,
781
+ "les": 694,
782
+ "row": 695,
783
+ "ject": 696,
784
+ "Ġacc": 697,
785
+ "ning": 698,
786
+ "ook": 699,
787
+ "ious": 700,
788
+ "ĠY": 701,
789
+ "velop": 702,
790
+ "Ġwould": 703,
791
+ "stem": 704,
792
+ "Ġtw": 705,
793
+ "ffect": 706,
794
+ "Ġnew": 707,
795
+ "Ġrel": 708,
796
+ "Ġneed": 709,
797
+ "Ġsuch": 710,
798
+ "Ġrep": 711,
799
+ "Ġif": 712,
800
+ "Ġgen": 713,
801
+ "Ġchild": 714,
802
+ "ient": 715,
803
+ "ob": 716,
804
+ "Ġinclud": 717,
805
+ "Ġhel": 718,
806
+ "ational": 719,
807
+ "Ġany": 720,
808
+ "cess": 721,
809
+ "ative": 722,
810
+ "ple": 723,
811
+ "hed": 724,
812
+ "Ġpr": 725,
813
+ "ular": 726,
814
+ "Ġph": 727,
815
+ "Ġwhat": 728,
816
+ "ced": 729,
817
+ "Ġused": 730,
818
+ "yp": 731,
819
+ "Ġprodu": 732,
820
+ "Ġhelp": 733,
821
+ "ool": 734,
822
+ "ating": 735,
823
+ "Ġonly": 736,
824
+ "ov": 737,
825
+ "Ġind": 738,
826
+ "Ġno": 739,
827
+ "Ġam": 740,
828
+ "Ġprov": 741,
829
+ "Ġmany": 742,
830
+ "Ġdevelop": 743,
831
+ "Ġfirst": 744,
832
+ "Ġthrough": 745,
833
+ "Ġoff": 746,
834
+ "ĠUn": 747,
835
+ "Ġfe": 748,
836
+ "Ġspec": 749,
837
+ "ath": 750,
838
+ "Ġac": 751,
839
+ "fter": 752,
840
+ "ise": 753,
841
+ "ark": 754,
842
+ "ics": 755,
843
+ "round": 756,
844
+ "oss": 757,
845
+ "uc": 758,
846
+ "iet": 759,
847
+ "Ġpo": 760,
848
+ "Ġreg": 761,
849
+ "Ġexp": 762,
850
+ "Ġem": 763,
851
+ "uring": 764,
852
+ "Ġdiffere": 765,
853
+ "Ġtwo": 766,
854
+ "erm": 767,
855
+ "rib": 768,
856
+ "hen": 769,
857
+ "Ġsystem": 770,
858
+ "ts": 771,
859
+ "ful": 772,
860
+ "eth": 773,
861
+ "oth": 774,
862
+ "iss": 775,
863
+ "ink": 776,
864
+ "ne": 777,
865
+ "ied": 778,
866
+ "Ġob": 779,
867
+ "rop": 780,
868
+ "als": 781,
869
+ "Ġass": 782,
870
+ "old": 783,
871
+ "ility": 784,
872
+ "Ġdec": 785,
873
+ "ased": 786,
874
+ "ible": 787,
875
+ "Ġatt": 788,
876
+ "ange": 789,
877
+ "Ġadd": 790,
878
+ "Ġsur": 791,
879
+ "ten": 792,
880
+ "arch": 793,
881
+ "Ġshould": 794,
882
+ "ower": 795,
883
+ "ures": 796,
884
+ "ife": 797,
885
+ "ween": 798,
886
+ "Ġwell": 799,
887
+ "ĠHe": 800,
888
+ "ble": 801,
889
+ "fore": 802,
890
+ "ert": 803,
891
+ "ng": 804,
892
+ "ract": 805,
893
+ "In": 806,
894
+ "Ġsupp": 807,
895
+ "Ġfl": 808,
896
+ "Ġwater": 809,
897
+ "ram": 810,
898
+ "Ġrem": 811,
899
+ "own": 812,
900
+ "Ġsub": 813,
901
+ "aw": 814,
902
+ "Ġco": 815,
903
+ "Ġinv": 816,
904
+ "Ġyears": 817,
905
+ "gan": 818,
906
+ "Ġbetween": 819,
907
+ "Ġhealth": 820,
908
+ "ution": 821,
909
+ "Ġsm": 822,
910
+ "ade": 823,
911
+ "sel": 824,
912
+ "hes": 825,
913
+ "Ġhigh": 826,
914
+ "Ġpres": 827,
915
+ "Ġcould": 828,
916
+ "cy": 829,
917
+ "its": 830,
918
+ "Ġwhere": 831,
919
+ "ever": 832,
920
+ "ick": 833,
921
+ "Ġtrans": 834,
922
+ "Ġrese": 835,
923
+ "ss": 836,
924
+ "âĢĶ": 837,
925
+ "ily": 838,
926
+ "Ġmake": 839,
927
+ "wn": 840,
928
+ "ants": 841,
929
+ "Ġget": 842,
930
+ "uch": 843,
931
+ "ology": 844,
932
+ "xt": 845,
933
+ "Ġpers": 846,
934
+ "chool": 847,
935
+ "Ġbu": 848,
936
+ "form": 849,
937
+ "Ġimport": 850,
938
+ "chn": 851,
939
+ "ident": 852,
940
+ "Ġher": 853,
941
+ "Ġmod": 854,
942
+ "ural": 855,
943
+ "Ġform": 856,
944
+ "ience": 857,
945
+ "Ġear": 858,
946
+ "Ġinter": 859,
947
+ "ited": 860,
948
+ "Ġpol": 861,
949
+ "ting": 862,
950
+ "meric": 863,
951
+ "Ġnum": 864,
952
+ "ivers": 865,
953
+ "Ġexam": 866,
954
+ "Ġinst": 867,
955
+ "ines": 868,
956
+ "ins": 869,
957
+ "land": 870,
958
+ "Ġdisc": 871,
959
+ "Ġdifferent": 872,
960
+ "hat": 873,
961
+ "ef": 874,
962
+ "Ġeffect": 875,
963
+ "Ġlear": 876,
964
+ "ont": 877,
965
+ "Ġfound": 878,
966
+ "ict": 879,
967
+ "ists": 880,
968
+ "ness": 881,
969
+ "Ġbecause": 882,
970
+ "Ġsim": 883,
971
+ "ata": 884,
972
+ "ually": 885,
973
+ "Ġcar": 886,
974
+ "ism": 887,
975
+ "Ġafter": 888,
976
+ "Ġlong": 889,
977
+ "Ġexper": 890,
978
+ "Ġworld": 891,
979
+ "Ġlar": 892,
980
+ "cept": 893,
981
+ "Ġmed": 894,
982
+ "Ġvery": 895,
983
+ "Ġincre": 896,
984
+ "Ġcent": 897,
985
+ "Ġthen": 898,
986
+ "gy": 899,
987
+ "Ġeven": 900,
988
+ "Ġjust": 901,
989
+ "oy": 902,
990
+ "ft": 903,
991
+ "ature": 904,
992
+ "Ġed": 905,
993
+ "Ġcount": 906,
994
+ "Ġdet": 907,
995
+ "Ġway": 908,
996
+ "Ġresp": 909,
997
+ "Ġtyp": 910,
998
+ "get": 911,
999
+ "urn": 912,
1000
+ "Ġhum": 913,
1001
+ "Ġinform": 914,
1002
+ "aking": 915,
1003
+ "other": 916,
1004
+ "ically": 917,
1005
+ "iew": 918,
1006
+ "Ġsign": 919,
1007
+ "vent": 920,
1008
+ "ĠAmeric": 921,
1009
+ "Ġvar": 922,
1010
+ "Ġgener": 923,
1011
+ "Ġsee": 924,
1012
+ "Ġke": 925,
1013
+ "Ġref": 926,
1014
+ "ives": 927,
1015
+ "ollow": 928,
1016
+ "Ġthose": 929,
1017
+ "Ġpat": 930,
1018
+ "Ġsoc": 931,
1019
+ "Ġext": 932,
1020
+ "Ġresult": 933,
1021
+ "Ġprog": 934,
1022
+ "Ġpub": 935,
1023
+ "Ġevery": 936,
1024
+ "Ġprocess": 937,
1025
+ "Ġsaid": 938,
1026
+ "Ġcall": 939,
1027
+ "cer": 940,
1028
+ "Ġfact": 941,
1029
+ "ases": 942,
1030
+ "Ġchildren": 943,
1031
+ "ck": 944,
1032
+ "arm": 945,
1033
+ "Ġgra": 946,
1034
+ "Ġeach": 947,
1035
+ "omm": 948,
1036
+ "Ġbeing": 949,
1037
+ "ps": 950,
1038
+ "ues": 951,
1039
+ "Ġca": 952,
1040
+ "led": 953,
1041
+ "ds": 954,
1042
+ "Ġsec": 955,
1043
+ "Ġloc": 956,
1044
+ "ruct": 957,
1045
+ "iron": 958,
1046
+ "ody": 959,
1047
+ "ork": 960,
1048
+ "ages": 961,
1049
+ "Ġpartic": 962,
1050
+ "Ġrequ": 963,
1051
+ "Ġimportant": 964,
1052
+ "Ġlife": 965,
1053
+ "Ġtechn": 966,
1054
+ "tle": 967,
1055
+ "ved": 968,
1056
+ "Ġdist": 969,
1057
+ "Ġset": 970,
1058
+ "Th": 971,
1059
+ "io": 972,
1060
+ "Ġcommun": 973,
1061
+ "ĠAl": 974,
1062
+ "Ġmuch": 975,
1063
+ "Ġdef": 976,
1064
+ "Ġmon": 977,
1065
+ "Ġshe": 978,
1066
+ "cent": 979,
1067
+ "Ġduring": 980,
1068
+ "Ġdep": 981,
1069
+ "ĠWe": 982,
1070
+ "Ġstudents": 983,
1071
+ "Ġcre": 984,
1072
+ "ather": 985,
1073
+ "Ġent": 986,
1074
+ "Ġfam": 987,
1075
+ "ized": 988,
1076
+ "vern": 989,
1077
+ "Ġread": 990,
1078
+ "imes": 991,
1079
+ "Ġart": 992,
1080
+ "Ġstudy": 993,
1081
+ "ward": 994,
1082
+ "Ġfollow": 995,
1083
+ "Ġown": 996,
1084
+ "Ġlevel": 997,
1085
+ "Ġfood": 998,
1086
+ "Ġlead": 999,
1087
+ "ĠPro": 1000,
1088
+ "Ġsk": 1001,
1089
+ "ices": 1002,
1090
+ "gg": 1003,
1091
+ "Ġmy": 1004,
1092
+ "Ġinformation": 1005,
1093
+ "Ġright": 1006,
1094
+ "Ġaut": 1007,
1095
+ "Ġdoes": 1008,
1096
+ "Ġsame": 1009,
1097
+ "ĠAs": 1010,
1098
+ "any": 1011,
1099
+ "Ġgrow": 1012,
1100
+ "Ġmade": 1013,
1101
+ "ĠThey": 1014,
1102
+ "ĠRe": 1015,
1103
+ "ize": 1016,
1104
+ "Ġproble": 1017,
1105
+ "Ġperson": 1018,
1106
+ "Ġdata": 1019,
1107
+ "Ġfind": 1020,
1108
+ "ection": 1021,
1109
+ "Ġcur": 1022,
1110
+ "hip": 1023
1111
  },
1112
  "merges": [
1113
  "Ġ t",
 
1115
  "h e",
1116
  "i n",
1117
  "r e",
1118
+ "Ġt he",
1119
  "o n",
1120
  "e r",
1121
  "Ġ o",
 
1123
  "Ġ s",
1124
  "e n",
1125
  "Ġ c",
 
1126
  "e s",
1127
+ "Ġ w",
1128
  "i s",
1129
  "n d",
1130
  "i t",
 
1133
  "a l",
1134
  "Ġ b",
1135
  "e d",
1136
+ "Ġo f",
1137
  "a n",
1138
  "Ġ f",
1139
+ "in g",
1140
+ "Ġ in",
1141
  "o u",
1142
  "a r",
1143
  "Ġ m",
1144
+ "Ġa nd",
1145
+ "Ġt o",
1146
  "i c",
1147
  "Ġ d",
1148
+ "i on",
1149
  "l e",
1150
  "r o",
1151
  "a s",
1152
  "Ġ h",
1153
+ "en t",
1154
+ "Ġt h",
1155
  "c t",
1156
  "Ġ e",
1157
  "i l",
1158
+ "Ġ re",
1159
  "o m",
1160
  "v e",
1161
  "Ġ l",
1162
  "s t",
1163
  "Ġ n",
 
1164
  "â Ģ",
1165
+ "l y",
1166
+ "Ġb e",
1167
+ "Ġ is",
1168
  "Ġ T",
 
1169
  "s e",
1170
+ "o l",
1171
  "Ġ g",
1172
+ "at ion",
1173
  "i m",
1174
  "i d",
1175
+ "e t",
1176
  "u t",
 
1177
  "c e",
1178
+ "o t",
1179
  "u r",
1180
  "r a",
1181
  "c h",
1182
+ "o w",
1183
  "Ġ A",
1184
+ "Ġf or",
1185
  "i g",
 
1186
  "Ġ u",
1187
+ S",
1188
+ "Ġ on",
1189
+ "Ġth at",
1190
+ "Ġs t",
1191
+ "v er",
1192
+ "Ġ y",
1193
  "i r",
1194
+ "Ġ C",
1195
  "Ġ I",
 
 
 
1196
  "u l",
1197
  "a y",
1198
  "a m",
1199
+ "Ġa s",
1200
+ "it h",
1201
+ "e l",
1202
  "a d",
1203
+ "Ġp ro",
1204
+ "he r",
1205
+ "Ġa re",
1206
+ "Ġc on",
1207
+ "Ġa n",
1208
+ "Ġw ith",
1209
  "i f",
1210
+ "Ġy ou",
1211
+ "Ġw h",
1212
+ "Ġo r",
1213
+ "Ġ it",
1214
+ "Ġa l",
1215
  "o d",
1216
+ "t er",
1217
  "Ġ M",
1218
+ "ĠT he",
1219
+ "m ent",
1220
  "g e",
 
 
1221
  "Ġ P",
1222
+ "t h",
1223
+ "o p",
1224
+ "at e",
1225
+ "is t",
1226
+ "er s",
1227
+ "Ġd e",
1228
+ "es s",
1229
+ "il l",
1230
+ "i es",
1231
  "a b",
1232
+ "Ġ he",
1233
+ "Ġe x",
1234
  "Ġ B",
 
1235
  "u s",
1236
+ "e ct",
1237
+ "Ġw e",
1238
+ "âĢ Ļ",
1239
+ "o re",
1240
+ "Ġc om",
1241
+ "Ġs u",
1242
+ "it y",
1243
+ "es t",
1244
+ "re s",
1245
  "a c",
1246
+ "i ve",
1247
+ "Ġh a",
1248
+ "u m",
1249
+ "ro m",
1250
  "Ġ H",
 
1251
  "l d",
1252
+ "Ġ v",
1253
+ "o s",
1254
  "k e",
1255
+ "Ġb y",
1256
+ "an t",
1257
+ "e m",
1258
  "q u",
1259
+ "i v",
1260
+ "a in",
1261
  "Ġ W",
1262
+ "n t",
1263
+ "Ġa t",
1264
  "p p",
1265
+ "ig h",
1266
  "u d",
1267
+ "Ġ D",
1268
+ "Ġw as",
1269
+ "Ġc an",
1270
+ "Ġf rom",
1271
  "Ġ E",
1272
+ "Ġc h",
1273
  "o c",
1274
+ "a nd",
1275
  "Ġ r",
1276
+ "or t",
1277
+ "Ġ R",
1278
+ "Ġn e",
1279
  "Ġ F",
1280
+ "i al",
1281
+ "Ġs e",
1282
+ "u re",
1283
  "u n",
1284
+ "Ġn ot",
1285
+ "Ġ le",
1286
+ "ic al",
1287
+ "ar t",
1288
  "Ġ G",
1289
  "Ġ N",
1290
+ "Ġha ve",
1291
+ "r i",
1292
+ "o g",
 
1293
  "Ġ L",
1294
+ "Ġs h",
1295
+ "Ġ en",
1296
+ "Ġs p",
1297
+ "Ġth is",
1298
+ "p t",
1299
+ "Ġw or",
1300
+ "igh t",
1301
+ "Ġa b",
1302
+ "ic h",
1303
+ "r ou",
1304
+ "re d",
1305
+ "al l",
1306
+ "ion s",
1307
+ "ou ld",
1308
+ "o st",
1309
+ "t her",
1310
+ "ou r",
1311
+ "g h",
1312
+ "T he",
1313
  "d u",
1314
+ "om e",
1315
+ "Ġ im",
1316
+ "at ed",
1317
+ "in e",
1318
+ "p er",
1319
+ "Ġu s",
1320
+ "Ġp l",
 
 
1321
  "a g",
1322
+ "ou t",
1323
+ "ar d",
1324
+ "a ct",
1325
+ "el l",
1326
+ "f f",
1327
+ "id e",
1328
+ "Ġthe ir",
1329
+ "Ġin t",
1330
+ "p l",
1331
+ "Ġ O",
1332
+ "an s",
1333
+ "e ar",
1334
+ "as t",
1335
+ "a ge",
1336
  "a k",
1337
+ "u st",
1338
+ "Ġwh ich",
1339
+ "Ġ k",
1340
+ "Ġyou r",
1341
+ "Ġw he",
1342
+ "Ġ J",
1343
+ "e c",
1344
+ "ou s",
1345
+ "Ġthe y",
1346
  "i z",
1347
+ "Ġ U",
1348
+ "o od",
1349
+ "ul t",
1350
+ "Ġa d",
1351
+ "Ġal l",
1352
+ "Ġw ill",
1353
+ "Ġcon t",
1354
+ "i b",
1355
+ "Ġin c",
1356
+ "ĠI n",
1357
+ "en d",
1358
  "c c",
1359
+ "âĢ ľ",
1360
+ "Ġd is",
1361
+ "r u",
1362
+ "âĢ Ŀ",
1363
+ "Ġcom p",
1364
+ "a p",
1365
+ "Ġm ore",
1366
+ "Ġre s",
1367
+ "on g",
1368
+ "i p",
1369
+ "ve l",
1370
+ "i a",
1371
+ "e w",
1372
+ "ation s",
1373
+ "Ġh as",
1374
+ "e re",
1375
+ "Ġd o",
1376
+ "or m",
1377
+ "ar y",
1378
+ "s o",
1379
+ "at er",
1380
+ "en ce",
1381
+ "ab le",
1382
+ "a re",
1383
+ "il d",
1384
+ "ĠT h",
1385
+ "Ġm an",
1386
+ "Ġc l",
1387
+ "u al",
1388
+ "Ġo ther",
1389
  "k s",
1390
+ "Ġb ut",
1391
+ "r y",
1392
+ "Ġwe re",
1393
+ "in d",
1394
+ "Ġp er",
1395
+ "ent s",
1396
+ "Ġt e",
1397
+ "e p",
1398
+ "a ch",
1399
+ "Ġim p",
1400
+ "an ce",
1401
+ "Ġm e",
1402
+ "Ġon e",
1403
+ "Ġal so",
1404
+ "o se",
1405
+ "ig n",
1406
+ "re at",
1407
+ "a ke",
1408
+ "res s",
1409
+ "as s",
1410
+ "as e",
1411
  "a v",
 
 
 
1412
  "a u",
1413
+ "ct ion",
 
 
1414
  "Ġ j",
1415
+ "Ġs o",
1416
+ "it ion",
1417
+ "Ġo ut",
1418
+ "ic e",
1419
+ "Ġu n",
1420
+ "b er",
1421
+ "on e",
1422
+ "Ġa pp",
1423
+ "ver y",
1424
+ "Ġa r",
1425
+ "im e",
1426
+ "Ġst ud",
1427
+ "Ġp art",
1428
+ "or d",
1429
+ "Ġab out",
1430
+ "or y",
1431
+ "a ce",
1432
+ "Ġe v",
1433
+ "en s",
1434
+ "ou nt",
1435
+ "is h",
1436
+ "o k",
1437
+ "ac k",
1438
+ "i re",
1439
+ "ĠS t",
1440
+ "Ġwh o",
1441
+ "Ġp e",
1442
+ "Ġin f",
1443
+ "am e",
1444
+ "Ġs y",
1445
+ "Ġh is",
1446
  "u e",
1447
+ "u b",
1448
+ "Ġcom m",
1449
+ "Ġs c",
1450
+ "or s",
1451
+ "it e",
1452
+ "an g",
1453
+ "Ġthe m",
1454
+ "c es",
1455
+ "i ke",
1456
+ "re e",
1457
+ "ou nd",
1458
  "Ġ K",
1459
+ "ol og",
1460
+ "Ġp re",
1461
+ "l ow",
1462
+ "n ow",
1463
+ "Ġbe c",
1464
+ "Ġu p",
1465
+ "r ic",
1466
+ "ĠI t",
1467
+ "Ġ qu",
1468
+ "if f",
1469
+ "Ġth an",
1470
+ "Ġm ay",
1471
+ "i e",
1472
+ "i le",
1473
+ "ay s",
1474
+ "op le",
1475
+ "Ġre c",
1476
+ "Ġs ome",
1477
+ "Ġy ear",
1478
+ "at es",
1479
+ "Ġbe en",
1480
+ "a il",
1481
+ "ĠC h",
1482
+ "Ġwhe n",
1483
+ "Ġthe re",
1484
+ "nd er",
1485
+ "ing s",
1486
+ "âĢ ĵ",
1487
+ "i an",
1488
+ "m er",
1489
+ "r it",
1490
+ "Ġit s",
1491
+ "re n",
1492
+ "Ġint o",
1493
+ "Ġwor k",
1494
+ "ou gh",
1495
+ "Ġg o",
1496
+ "p h",
1497
+ "Ġt ra",
1498
+ "Ġa g",
1499
+ "Ġt ime",
1500
+ "ver s",
1501
+ "Ġd iff",
1502
+ "t e",
1503
+ "ĠTh is",
1504
+ "Ġo ver",
1505
+ "Ġthe se",
1506
+ "Ġh ow",
1507
+ "er v",
1508
+ "Ġpe ople",
1509
+ "Ġ ro",
1510
+ "on s",
1511
+ "rou gh",
1512
  "Ġ V",
1513
+ "al ly",
1514
+ "l ud",
1515
+ "au se",
1516
+ "on d",
1517
+ "Ġcon s",
1518
+ "Ġu se",
1519
+ "Ġc ol",
1520
+ "m s",
1521
+ "Ġt r",
1522
+ "l l",
1523
+ "Ġ ra",
1524
+ "if ic",
1525
+ "ter n",
1526
  "w e",
1527
+ "Ġbe t",
1528
+ "Ġh ad",
1529
+ "Ġa ct",
1530
+ "y s",
1531
+ "o ve",
1532
+ "Ġo ur",
1533
+ "in t",
1534
+ "Ġm ost",
1535
+ "al th",
1536
+ "Ġl ike",
1537
+ "ir st",
1538
+ "it ies",
1539
+ "Ġk now",
1540
+ "Ġu nder",
1541
+ "l ic",
1542
+ "Ġb l",
1543
+ "le ct",
1544
+ "Ġs a",
1545
+ "ment s",
1546
+ "Ġd es",
1547
+ "l es",
1548
+ "ro w",
1549
+ "j ect",
1550
+ "Ġa cc",
1551
+ "n ing",
1552
+ "o ok",
1553
+ "i ous",
1554
  "Ġ Y",
1555
+ "vel op",
1556
+ "Ġw ould",
1557
+ "st em",
1558
+ "Ġt w",
1559
+ "ff ect",
1560
+ "Ġne w",
1561
+ "Ġre l",
1562
+ "Ġne ed",
1563
+ "Ġsu ch",
1564
+ "Ġre p",
1565
+ "Ġ if",
1566
+ "Ġg en",
1567
+ "Ġch ild",
1568
+ "i ent",
1569
  "o b",
1570
+ "Ġinc lud",
1571
+ "Ġhe l",
1572
+ "ation al",
1573
+ "Ġan y",
1574
+ "c ess",
1575
+ "at ive",
1576
+ "p le",
1577
+ "he d",
1578
+ "Ġp r",
1579
+ "ul ar",
1580
+ "Ġp h",
1581
+ "Ġwh at",
1582
+ "c ed",
1583
+ "Ġus ed",
1584
+ "y p",
1585
+ "Ġpro du",
1586
+ "Ġhel p",
1587
+ "o ol",
1588
+ "at ing",
1589
+ "Ġon ly",
1590
+ "o v",
1591
+ "Ġin d",
1592
+ "Ġn o",
1593
+ "Ġa m",
1594
+ "Ġpro v",
1595
+ "Ġman y",
1596
+ "Ġde velop",
1597
+ "Ġf irst",
1598
+ "Ġth rough",
1599
+ "Ġof f",
1600
+ "ĠU n",
1601
+ "Ġf e",
1602
+ "Ġsp ec",
1603
+ "at h",
1604
+ "Ġa c",
1605
+ "f ter",
1606
+ "is e",
1607
+ "ar k",
1608
+ "ic s",
1609
+ "rou nd",
1610
+ "os s",
1611
+ "u c",
1612
+ "i et",
1613
+ "Ġp o",
1614
+ "Ġre g",
1615
+ "Ġex p",
1616
+ "Ġe m",
1617
+ "ur ing",
1618
+ "Ġdiff ere",
1619
+ "Ġtw o",
1620
+ "er m",
1621
+ "ri b",
1622
+ "he n",
1623
+ "Ġsy stem",
1624
+ "t s",
1625
+ "f ul",
1626
+ "et h",
1627
+ "ot h",
1628
+ "is s",
1629
+ "in k",
1630
+ "n e",
1631
+ "i ed",
1632
+ "Ġo b",
1633
+ "ro p",
1634
+ "al s",
1635
+ "Ġas s",
1636
+ "ol d",
1637
+ "il ity",
1638
+ "Ġde c",
1639
+ "as ed",
1640
+ "ib le",
1641
+ "Ġat t",
1642
+ "an ge",
1643
+ "Ġad d",
1644
+ "Ġs ur",
1645
+ "t en",
1646
+ "ar ch",
1647
+ "Ġsh ould",
1648
+ "ow er",
1649
+ "u res",
1650
+ "if e",
1651
+ "we en",
1652
+ "Ġw ell",
1653
+ "ĠH e",
1654
+ "b le",
1655
+ "f ore",
1656
+ "er t",
1657
+ "n g",
1658
+ "ra ct",
1659
  "I n",
1660
+ "Ġsu pp",
1661
+ "Ġf l",
1662
+ "Ġw ater",
1663
+ "ra m",
1664
+ "Ġre m",
1665
+ "ow n",
1666
+ "Ġsu b",
1667
  "a w",
1668
+ "Ġc o",
1669
+ "Ġin v",
1670
+ "Ġyear s",
1671
+ "g an",
1672
+ "Ġbet ween",
1673
+ "Ġhe alth",
1674
+ "ut ion",
1675
+ "Ġs m",
1676
+ "ad e",
1677
+ "se l",
1678
+ "he s",
1679
+ "Ġh igh",
1680
+ "Ġp res",
1681
+ "Ġc ould",
1682
+ "c y",
1683
+ "it s",
1684
+ "Ġwhe re",
1685
+ "e ver",
1686
+ "ic k",
1687
+ "Ġtr ans",
1688
+ "Ġre se",
1689
+ "s s",
1690
+ "âĢ Ķ",
1691
+ "il y",
1692
+ "Ġm ake",
1693
+ "w n",
1694
+ "ant s",
1695
+ "Ġg et",
1696
+ "u ch",
1697
+ "olog y",
1698
+ "x t",
1699
+ "Ġp ers",
1700
+ "ch ool",
1701
+ "Ġb u",
1702
+ "f orm",
1703
+ "Ġimp ort",
1704
+ "ch n",
1705
+ "id ent",
1706
+ "Ġ her",
1707
+ "Ġm od",
1708
+ "ur al",
1709
+ "Ġfor m",
1710
+ "i ence",
1711
+ "Ġe ar",
1712
+ "Ġin ter",
1713
+ "it ed",
1714
+ "Ġp ol",
1715
+ "t ing",
1716
+ "mer ic",
1717
+ "Ġn um",
1718
+ "i vers",
1719
+ "Ġex am",
1720
+ "Ġin st",
1721
+ "in es",
1722
+ "in s",
1723
+ "l and",
1724
+ "Ġdis c",
1725
+ "Ġdiffere nt",
1726
+ "h at",
1727
+ "e f",
1728
+ "Ġe ffect",
1729
+ "Ġle ar",
1730
+ "on t",
1731
+ "Ġf ound",
1732
+ "ic t",
1733
+ "ist s",
1734
+ "n ess",
1735
+ "Ġbec ause",
1736
+ "Ġs im",
1737
+ "at a",
1738
+ "ual ly",
1739
+ "Ġc ar",
1740
+ "is m",
1741
+ "Ġa fter",
1742
+ "Ġl ong",
1743
+ "Ġex per",
1744
+ "Ġwor ld",
1745
+ "Ġl ar",
1746
+ "ce pt",
1747
+ "Ġm ed",
1748
+ "Ġ very",
1749
+ "Ġinc re",
1750
+ "Ġc ent",
1751
+ "Ġthe n",
1752
  "g y",
1753
+ "Ġev en",
1754
+ "Ġj ust",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1755
  "o y",
1756
+ "f t",
1757
+ "at ure",
1758
+ "Ġ ed",
1759
+ "Ġc ount",
1760
+ "Ġd et",
1761
+ "Ġw ay",
1762
+ "Ġres p",
1763
+ "Ġt yp",
1764
+ "g et",
1765
+ "ur n",
1766
+ "Ġh um",
1767
+ "Ġinf orm",
1768
+ "ak ing",
1769
+ "ot her",
1770
+ "ical ly",
1771
+ "i ew",
1772
+ "Ġs ign",
1773
+ "v ent",
1774
+ "ĠA meric",
1775
+ "Ġv ar",
1776
+ "Ġgen er",
1777
+ "Ġse e",
1778
+ "Ġ ke",
1779
+ "Ġre f",
1780
+ "iv es",
1781
+ "ol low",
1782
+ "Ġth ose",
1783
+ "Ġp at",
1784
+ "Ġs oc",
1785
+ "Ġex t",
1786
+ "Ġres ult",
1787
+ "Ġpro g",
1788
+ "Ġp ub",
1789
+ "Ġe very",
1790
+ "Ġpro cess",
1791
+ "Ġsa id",
1792
+ "Ġc all",
1793
+ "c er",
1794
+ "Ġf act",
1795
+ "as es",
1796
+ "Ġchild ren",
1797
+ "c k",
1798
+ "ar m",
1799
+ "Ġg ra",
1800
+ "Ġe ach",
1801
+ "om m",
1802
+ "Ġbe ing",
1803
+ "p s",
1804
+ "u es",
1805
+ "Ġc a",
1806
+ "l ed",
1807
+ "d s",
1808
+ "Ġse c",
1809
+ "Ġl oc",
1810
+ "ru ct",
1811
+ "ir on",
1812
+ "od y",
1813
+ "or k",
1814
+ "ag es",
1815
+ "Ġpart ic",
1816
+ "Ġre qu",
1817
+ "Ġimport ant",
1818
+ "Ġl ife",
1819
+ "Ġte chn",
1820
+ "t le",
1821
+ "v ed",
1822
+ "Ġd ist",
1823
+ "Ġs et",
1824
+ "T h",
1825
  "i o",
1826
+ "Ġcomm un",
1827
+ "ĠA l",
1828
+ "Ġm uch",
1829
+ "Ġde f",
1830
+ "Ġm on",
1831
+ "Ġs he",
1832
+ "c ent",
1833
+ "Ġd uring",
1834
+ "Ġde p",
1835
+ "ĠW e",
1836
+ "Ġstud ents",
1837
+ "Ġc re",
1838
+ "at her",
1839
+ "Ġ ent",
1840
+ "Ġf am",
1841
+ "iz ed",
1842
+ "ver n",
1843
+ "Ġre ad",
1844
+ "im es",
1845
+ "Ġar t",
1846
+ "Ġstud y",
1847
+ "w ard",
1848
+ "Ġf ollow",
1849
+ "Ġo wn",
1850
+ "Ġle vel",
1851
+ "Ġf ood",
1852
+ "Ġle ad",
1853
+ "ĠP ro",
1854
+ "Ġs k",
1855
+ "ic es",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1856
  "g g",
1857
+ "Ġm y",
1858
+ "Ġinform ation",
1859
+ "Ġr ight",
1860
+ "Ġa ut",
1861
+ "Ġdo es",
1862
+ "Ġs ame",
1863
+ "ĠA s",
1864
+ "an y",
1865
+ "Ġg row",
1866
+ "Ġm ade",
1867
+ "ĠThe y",
1868
+ "ĠR e",
1869
+ "iz e",
1870
+ "Ġpro ble",
1871
+ "Ġpers on",
1872
+ "Ġd ata",
1873
+ "Ġf ind",
1874
+ "ect ion",
1875
+ "Ġc ur",
1876
+ "h ip"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1877
  ]
1878
  }
1879
  }