tokenizer/vocab.json

{
  "!": 5,
  "\"": 6,
  "#": 7,
  "$": 8,
  "%": 9,
  "&": 10,
  "'": 11,
  "(": 12,
  ")": 13,
  "*": 14,
  "+": 15,
  ",": 16,
  ",@": 565,
  "-": 17,
  "-@": 280,
  ".": 18,
  ".@": 514,
  "/": 19,
  "0": 20,
  "00": 336,
  "1": 21,
  "2": 22,
  "3": 23,
  "4": 24,
  "5": 25,
  "6": 26,
  "7": 27,
  "8": 28,
  "9": 29,
  ":": 30,
  ";": 31,
  "<": 32,
  "</s>": 2,
  "<mask>": 4,
  "<pad>": 1,
  "<s>": 0,
  "<unk>": 3,
  "=": 33,
  ">": 34,
  "?": 35,
  "@": 36,
  "A": 37,
  "B": 38,
  "C": 39,
  "D": 40,
  "E": 41,
  "F": 42,
  "G": 43,
  "H": 44,
  "I": 45,
  "J": 46,
  "K": 47,
  "L": 48,
  "M": 49,
  "N": 50,
  "O": 51,
  "P": 52,
  "Q": 53,
  "R": 54,
  "S": 55,
  "T": 56,
  "U": 57,
  "V": 58,
  "W": 59,
  "X": 60,
  "Y": 61,
  "Z": 62,
  "[": 63,
  "\\": 64,
  "]": 65,
  "^": 66,
  "_": 67,
  "`": 68,
  "a": 69,
  "ab": 376,
  "able": 618,
  "ac": 261,
  "ace": 575,
  "ach": 536,
  "ack": 398,
  "act": 542,
  "ad": 260,
  "ade": 538,
  "ag": 334,
  "age": 495,
  "ah": 956,
  "aid": 814,
  "ail": 655,
  "ain": 338,
  "ained": 894,
  "air": 903,
  "aj": 838,
  "ak": 372,
  "ake": 661,
  "al": 226,
  "ale": 846,
  "all": 370,
  "ally": 421,
  "als": 641,
  "am": 255,
  "ame": 390,
  "ames": 732,
  "amp": 604,
  "an": 224,
  "ance": 571,
  "and": 329,
  "ane": 851,
  "ang": 572,
  "ank": 862,
  "ann": 790,
  "ans": 742,
  "ant": 377,
  "any": 809,
  "ap": 426,
  "apt": 982,
  "ar": 221,
  "ard": 368,
  "are": 535,
  "ared": 948,
  "ark": 576,
  "ars": 823,
  "art": 371,
  "ary": 434,
  "as": 230,
  "ase": 630,
  "ased": 624,
  "ason": 603,
  "ass": 485,
  "ast": 408,
  "at": 212,
  "ate": 369,
  "ated": 384,
  "ater": 479,
  "ates": 635,
  "ath": 637,
  "ather": 905,
  "ating": 765,
  "ation": 295,
  "ational": 702,
  "ations": 528,
  "ative": 945,
  "att": 672,
  "au": 975,
  "aus": 662,
  "ause": 852,
  "av": 340,
  "ave": 433,
  "aw": 659,
  "ay": 292,
  "az": 953,
  "b": 70,
  "ber": 380,
  "bum": 775,
  "c": 71,
  "cc": 442,
  "ce": 302,
  "ced": 589,
  "ces": 617,
  "ch": 313,
  "ct": 325,
  "ction": 561,
  "d": 72,
  "der": 979,
  "du": 505,
  "e": 73,
  "ear": 387,
  "ec": 266,
  "ect": 399,
  "ed": 208,
  "ek": 854,
  "el": 252,
  "elf": 942,
  "ell": 420,
  "els": 983,
  "ely": 543,
  "em": 307,
  "emb": 978,
  "ember": 580,
  "ement": 919,
  "en": 217,
  "ence": 511,
  "end": 487,
  "ener": 761,
  "ens": 583,
  "ent": 246,
  "ents": 622,
  "ep": 653,
  "er": 203,
  "ere": 354,
  "ered": 669,
  "erm": 960,
  "ern": 904,
  "ers": 324,
  "ert": 898,
  "es": 220,
  "ess": 386,
  "est": 332,
  "et": 273,
  "ever": 621,
  "ew": 365,
  "ey": 643,
  "f": 74,
  "fer": 656,
  "ff": 469,
  "fore": 721,
  "form": 654,
  "ft": 682,
  "fter": 455,
  "ful": 906,
  "g": 75,
  "gan": 647,
  "ge": 415,
  "gh": 382,
  "h": 76,
  "he": 199,
  "hed": 462,
  "hen": 791,
  "her": 298,
  "hes": 763,
  "hip": 709,
  "hn": 714,
  "i": 77,
  "ia": 431,
  "ial": 457,
  "iam": 940,
  "ian": 410,
  "ib": 555,
  "ic": 233,
  "ical": 456,
  "ice": 574,
  "ich": 373,
  "ick": 677,
  "ics": 794,
  "ict": 644,
  "id": 275,
  "ide": 450,
  "ident": 896,
  "ie": 482,
  "ied": 610,
  "iel": 797,
  "ield": 892,
  "ier": 857,
  "ies": 350,
  "iet": 868,
  "iew": 719,
  "if": 351,
  "ife": 826,
  "ific": 782,
  "ig": 282,
  "igh": 367,
  "ight": 424,
  "igin": 873,
  "ign": 478,
  "ik": 969,
  "ike": 787,
  "il": 247,
  "ild": 631,
  "ile": 519,
  "ill": 355,
  "ilm": 670,
  "ily": 798,
  "im": 277,
  "ime": 509,
  "in": 201,
  "ince": 860,
  "ind": 696,
  "ine": 419,
  "ined": 925,
  "ines": 832,
  "ing": 227,
  "ings": 615,
  "inn": 913,
  "ins": 780,
  "int": 598,
  "io": 834,
  "ion": 237,
  "ions": 447,
  "ious": 636,
  "ip": 418,
  "ir": 279,
  "ird": 829,
  "ire": 486,
  "irect": 864,
  "ired": 965,
  "irst": 440,
  "is": 219,
  "ise": 858,
  "ised": 842,
  "ish": 428,
  "ished": 740,
  "ision": 723,
  "iss": 642,
  "ist": 337,
  "it": 215,
  "ite": 564,
  "ited": 620,
  "ith": 291,
  "ities": 843,
  "ition": 526,
  "its": 872,
  "ity": 383,
  "iv": 276,
  "ive": 392,
  "ived": 781,
  "iver": 833,
  "ivers": 952,
  "ix": 629,
  "iz": 533,
  "ized": 972,
  "j": 78,
  "ject": 836,
  "k": 79,
  "ke": 563,
  "l": 80,
  "land": 512,
  "ld": 356,
  "le": 238,
  "lect": 795,
  "led": 918,
  "les": 597,
  "ley": 928,
  "ll": 804,
  "low": 502,
  "lud": 537,
  "ly": 268,
  "m": 81,
  "man": 584,
  "ment": 412,
  "ments": 971,
  "mer": 499,
  "meric": 764,
  "n": 82,
  "nd": 211,
  "nder": 587,
  "o": 83,
  "ob": 710,
  "ober": 927,
  "oc": 379,
  "ock": 726,
  "od": 339,
  "ode": 853,
  "og": 436,
  "ok": 474,
  "ol": 274,
  "old": 640,
  "ollow": 689,
  "olog": 731,
  "om": 253,
  "ome": 483,
  "on": 204,
  "ond": 501,
  "one": 592,
  "ong": 366,
  "ons": 679,
  "ood": 627,
  "ook": 684,
  "ool": 916,
  "oot": 962,
  "op": 347,
  "or": 214,
  "ord": 416,
  "ore": 360,
  "ork": 484,
  "orld": 754,
  "orm": 481,
  "orn": 724,
  "ors": 625,
  "ort": 353,
  "orth": 667,
  "ory": 525,
  "os": 320,
  "ose": 611,
  "ost": 423,
  "ot": 283,
  "oth": 683,
  "other": 835,
  "ou": 239,
  "ough": 518,
  "ould": 460,
  "oun": 430,
  "ound": 553,
  "ount": 549,
  "our": 422,
  "ous": 439,
  "out": 466,
  "outh": 690,
  "ov": 406,
  "over": 556,
  "overn": 947,
  "ow": 288,
  "ower": 921,
  "owever": 824,
  "own": 473,
  "oy": 626,
  "p": 84,
  "per": 477,
  "ph": 579,
  "pl": 524,
  "port": 593,
  "pp": 358,
  "pr": 874,
  "pt": 385,
  "q": 85,
  "qu": 391,
  "r": 86,
  "ra": 318,
  "ral": 700,
  "ram": 884,
  "ran": 480,
  "rans": 807,
  "re": 206,
  "reat": 686,
  "red": 405,
  "ree": 517,
  "ren": 596,
  "res": 349,
  "ress": 570,
  "ri": 341,
  "rib": 612,
  "ric": 527,
  "rit": 417,
  "ro": 232,
  "rom": 328,
  "ron": 720,
  "rop": 639,
  "ros": 811,
  "ross": 977,
  "rou": 393,
  "rough": 588,
  "round": 594,
  "row": 863,
  "ru": 446,
  "ry": 492,
  "s": 87,
  "se": 403,
  "so": 452,
  "son": 865,
  "st": 250,
  "t": 88,
  "te": 567,
  "ted": 748,
  "ten": 839,
  "ter": 284,
  "tern": 616,
  "ters": 694,
  "th": 303,
  "ther": 425,
  "though": 914,
  "til": 990,
  "ton": 855,
  "ts": 749,
  "u": 89,
  "ual": 783,
  "ually": 961,
  "ub": 467,
  "ubl": 658,
  "uc": 818,
  "uch": 936,
  "ud": 378,
  "ue": 471,
  "ued": 999,
  "ug": 680,
  "ul": 310,
  "ular": 704,
  "ult": 516,
  "um": 331,
  "un": 306,
  "une": 989,
  "up": 915,
  "ur": 264,
  "urch": 889,
  "ure": 451,
  "ures": 899,
  "uring": 523,
  "urn": 568,
  "ury": 747,
  "us": 287,
  "ust": 435,
  "ut": 290,
  "ute": 937,
  "v": 90,
  "ve": 715,
  "ved": 671,
  "vel": 600,
  "velop": 844,
  "ver": 296,
  "w": 91,
  "ward": 607,
  "way": 687,
  "we": 595,
  "ween": 691,
  "wn": 578,
  "wo": 465,
  "x": 92,
  "y": 93,
  "yl": 934,
  "z": 94,
  "|": 95,
  "}": 96,
  "~": 97,
  "¡": 98,
  "¢": 99,
  "£": 100,
  "¤": 101,
  "¥": 102,
  "¦": 103,
  "§": 104,
  "¨": 105,
  "©": 106,
  "ª": 107,
  "«": 108,
  "¬": 109,
  "®": 110,
  "¯": 111,
  "°": 112,
  "±": 113,
  "²": 114,
  "³": 115,
  "´": 116,
  "µ": 117,
  "¶": 118,
  "·": 119,
  "¸": 120,
  "¹": 121,
  "º": 122,
  "»": 123,
  "¼": 124,
  "½": 125,
  "¾": 126,
  "¿": 127,
  "Â": 128,
  "Ã": 129,
  "Ä": 130,
  "Å": 131,
  "Æ": 132,
  "Ç": 133,
  "È": 134,
  "É": 135,
  "Ê": 136,
  "Ë": 137,
  "Ì": 138,
  "Í": 139,
  "Î": 140,
  "Ï": 141,
  "Ð": 142,
  "Ñ": 143,
  "Ö": 144,
  "×": 145,
  "Ø": 146,
  "Ù": 147,
  "Ü": 148,
  "à": 149,
  "á": 150,
  "â": 151,
  "ã": 152,
  "ä": 153,
  "å": 154,
  "æ": 155,
  "ç": 156,
  "è": 157,
  "é": 158,
  "ë": 159,
  "ì": 160,
  "ï": 161,
  "Ċ": 162,
  "Ġ": 163,
  "Ġ\"": 243,
  "Ġ'": 272,
  "Ġ(": 315,
  "Ġ)": 314,
  "Ġ,": 205,
  "Ġ.": 213,
  "Ġ/": 875,
  "Ġ0": 800,
  "Ġ00": 725,
  "Ġ000": 806,
  "Ġ1": 249,
  "Ġ10": 817,
  "Ġ11": 924,
  "Ġ12": 841,
  "Ġ15": 920,
  "Ġ16": 869,
  "Ġ17": 929,
  "Ġ18": 513,
  "Ġ19": 327,
  "Ġ194": 949,
  "Ġ196": 964,
  "Ġ197": 973,
  "Ġ198": 902,
  "Ġ199": 693,
  "Ġ2": 293,
  "Ġ20": 468,
  "Ġ200": 437,
  "Ġ201": 550,
  "Ġ3": 432,
  "Ġ4": 497,
  "Ġ5": 506,
  "Ġ6": 609,
  "Ġ7": 633,
  "Ġ8": 676,
  "Ġ9": 674,
  "Ġ:": 470,
  "Ġ;": 444,
  "Ġ=": 242,
  "Ġ@": 259,
  "Ġ@,@": 566,
  "Ġ@-@": 281,
  "Ġ@.@": 515,
  "ĠA": 244,
  "ĠAfter": 933,
  "ĠAl": 521,
  "ĠAmeric": 768,
  "ĠAn": 632,
  "ĠAr": 708,
  "ĠAs": 666,
  "ĠAt": 779,
  "ĠB": 269,
  "ĠBr": 987,
  "ĠBrit": 867,
  "ĠC": 251,
  "ĠCh": 429,
  "ĠCom": 707,
  "ĠCon": 995,
  "ĠD": 304,
  "ĠE": 342,
  "ĠEn": 692,
  "ĠEng": 815,
  "ĠF": 308,
  "ĠG": 319,
  "ĠH": 286,
  "ĠHe": 496,
  "ĠI": 270,
  "ĠIn": 361,
  "ĠInd": 970,
  "ĠIs": 988,
  "ĠIt": 534,
  "ĠJ": 333,
  "ĠJo": 803,
  "ĠJohn": 922,
  "ĠK": 388,
  "ĠL": 321,
  "ĠLe": 767,
  "ĠM": 263,
  "ĠMar": 685,
  "ĠN": 322,
  "ĠNew": 756,
  "ĠO": 343,
  "ĠOn": 599,
  "ĠP": 294,
  "ĠR": 301,
  "ĠRe": 793,
  "ĠS": 245,
  "ĠSc": 856,
  "ĠSe": 746,
  "ĠSh": 812,
  "ĠShe": 939,
  "ĠSt": 407,
  "ĠT": 240,
  "ĠTh": 504,
  "ĠThe": 265,
  "ĠThis": 799,
  "ĠU": 401,
  "ĠUn": 613,
  "ĠUnited": 917,
  "ĠV": 441,
  "ĠW": 316,
  "ĠWh": 984,
  "ĠY": 562,
  "ĠZ": 907,
  "Ġa": 200,
  "Ġab": 489,
  "Ġabout": 697,
  "Ġac": 776,
  "Ġacc": 758,
  "Ġact": 737,
  "Ġad": 490,
  "Ġadd": 886,
  "Ġafter": 554,
  "Ġag": 546,
  "Ġagain": 699,
  "Ġagainst": 876,
  "Ġal": 312,
  "Ġalbum": 805,
  "Ġall": 614,
  "Ġalso": 475,
  "Ġam": 784,
  "Ġan": 330,
  "Ġand": 229,
  "Ġapp": 532,
  "Ġar": 458,
  "Ġare": 394,
  "Ġart": 986,
  "Ġas": 285,
  "Ġass": 745,
  "Ġat": 323,
  "Ġatt": 573,
  "Ġb": 223,
  "Ġback": 885,
  "Ġbe": 297,
  "Ġbec": 531,
  "Ġbecame": 878,
  "Ġbeen": 508,
  "Ġbefore": 810,
  "Ġbegan": 963,
  "Ġbeing": 816,
  "Ġbel": 997,
  "Ġbet": 649,
  "Ġbetween": 712,
  "Ġbl": 845,
  "Ġboth": 861,
  "Ġbu": 773,
  "Ġbut": 449,
  "Ġby": 311,
  "Ġc": 216,
  "Ġcall": 802,
  "Ġcalled": 998,
  "Ġcan": 688,
  "Ġcent": 628,
  "Ġcentury": 930,
  "Ġch": 374,
  "Ġchar": 716,
  "Ġcharac": 882,
  "Ġcl": 476,
  "Ġco": 771,
  "Ġcol": 717,
  "Ġcom": 345,
  "Ġcomm": 601,
  "Ġcomp": 445,
  "Ġcomple": 985,
  "Ġcon": 317,
  "Ġconc": 944,
  "Ġcons": 664,
  "Ġcont": 453,
  "Ġcontin": 967,
  "Ġcould": 994,
  "Ġcre": 946,
  "Ġcrit": 991,
  "Ġd": 235,
  "Ġday": 796,
  "Ġde": 357,
  "Ġdec": 675,
  "Ġdef": 774,
  "Ġdep": 901,
  "Ġdes": 545,
  "Ġdesc": 890,
  "Ġdevelop": 938,
  "Ġdid": 996,
  "Ġdif": 966,
  "Ġdirect": 974,
  "Ġdis": 529,
  "Ġdo": 808,
  "Ġduring": 665,
  "Ġe": 257,
  "Ġear": 657,
  "Ġearly": 993,
  "Ġem": 897,
  "Ġen": 558,
  "Ġend": 730,
  "Ġent": 825,
  "Ġep": 819,
  "Ġepis": 870,
  "Ġest": 932,
  "Ġev": 585,
  "Ġex": 381,
  "Ġexp": 879,
  "Ġext": 976,
  "Ġf": 218,
  "Ġfe": 645,
  "Ġfilm": 739,
  "Ġfin": 590,
  "Ġfirst": 459,
  "Ġfl": 713,
  "Ġfollow": 778,
  "Ġfor": 278,
  "Ġform": 744,
  "Ġfound": 828,
  "Ġfour": 788,
  "Ġfrom": 344,
  "Ġg": 271,
  "Ġgame": 678,
  "Ġgo": 888,
  "Ġh": 236,
  "Ġhad": 402,
  "Ġhas": 503,
  "Ġhave": 494,
  "Ġhe": 335,
  "Ġher": 472,
  "Ġhigh": 827,
  "Ġhim": 623,
  "Ġhis": 346,
  "Ġhist": 992,
  "Ġim": 560,
  "Ġin": 225,
  "Ġinc": 443,
  "Ġinclud": 569,
  "Ġincluding": 871,
  "Ġind": 789,
  "Ġint": 454,
  "Ġinter": 766,
  "Ġinto": 591,
  "Ġinv": 900,
  "Ġis": 305,
  "Ġit": 326,
  "Ġits": 461,
  "Ġj": 540,
  "Ġk": 397,
  "Ġkn": 660,
  "Ġknown": 880,
  "Ġl": 254,
  "Ġlar": 772,
  "Ġlater": 728,
  "Ġle": 413,
  "Ġlead": 954,
  "Ġloc": 848,
  "Ġlong": 912,
  "Ġm": 234,
  "Ġmade": 750,
  "Ġmain": 910,
  "Ġman": 541,
  "Ġmany": 909,
  "Ġmay": 981,
  "Ġme": 705,
  "Ġmet": 926,
  "Ġmill": 959,
  "Ġmin": 935,
  "Ġmon": 908,
  "Ġmore": 608,
  "Ġmost": 663,
  "Ġmov": 762,
  "Ġmus": 777,
  "Ġn": 258,
  "Ġne": 711,
  "Ġnew": 668,
  "Ġno": 830,
  "Ġnot": 414,
  "Ġnum": 729,
  "Ġnumber": 849,
  "Ġo": 209,
  "Ġob": 957,
  "Ġof": 222,
  "Ġoff": 559,
  "Ġon": 267,
  "Ġone": 500,
  "Ġonly": 673,
  "Ġop": 923,
  "Ġor": 375,
  "Ġorigin": 950,
  "Ġother": 552,
  "Ġout": 577,
  "Ġover": 551,
  "Ġp": 228,
  "Ġpart": 544,
  "Ġpe": 752,
  "Ġper": 507,
  "Ġperform": 893,
  "Ġpl": 389,
  "Ġplay": 539,
  "Ġpo": 638,
  "Ġpol": 980,
  "Ġpop": 887,
  "Ġpos": 733,
  "Ġpr": 741,
  "Ġpre": 581,
  "Ġpres": 850,
  "Ġpro": 348,
  "Ġprodu": 735,
  "Ġpubl": 801,
  "Ġqu": 759,
  "Ġr": 362,
  "Ġra": 769,
  "Ġre": 241,
  "Ġrec": 493,
  "Ġrece": 895,
  "Ġrecord": 718,
  "Ġreg": 743,
  "Ġrel": 695,
  "Ġrele": 738,
  "Ġrem": 652,
  "Ġrep": 943,
  "Ġres": 488,
  "Ġret": 755,
  "Ġrev": 958,
  "Ġro": 498,
  "Ġs": 207,
  "Ġsc": 522,
  "Ġse": 363,
  "Ġseason": 698,
  "Ġsec": 648,
  "Ġsecond": 786,
  "Ġser": 557,
  "Ġseries": 847,
  "Ġset": 831,
  "Ġsever": 859,
  "Ġseveral": 955,
  "Ġsh": 396,
  "Ġshe": 602,
  "Ġshow": 941,
  "Ġsign": 968,
  "Ġsing": 891,
  "Ġsm": 951,
  "Ġso": 753,
  "Ġsome": 770,
  "Ġsong": 651,
  "Ġsp": 409,
  "Ġspec": 757,
  "Ġst": 289,
  "Ġstud": 911,
  "Ġsu": 359,
  "Ġsub": 751,
  "Ġsuch": 785,
  "Ġsupp": 820,
  "Ġsur": 837,
  "Ġsy": 813,
  "Ġt": 198,
  "Ġte": 605,
  "Ġteam": 931,
  "Ġth": 248,
  "Ġthan": 706,
  "Ġthat": 299,
  "Ġthe": 202,
  "Ġtheir": 448,
  "Ġthem": 646,
  "Ġthen": 866,
  "Ġthere": 821,
  "Ġthey": 547,
  "Ġthis": 530,
  "Ġthree": 701,
  "Ġthrough": 722,
  "Ġtime": 586,
  "Ġto": 231,
  "Ġtr": 681,
  "Ġtra": 840,
  "Ġtrans": 881,
  "Ġtwo": 510,
  "Ġu": 427,
  "Ġun": 438,
  "Ġunder": 703,
  "Ġup": 582,
  "Ġus": 491,
  "Ġused": 792,
  "Ġv": 352,
  "Ġver": 727,
  "Ġw": 210,
  "Ġwas": 262,
  "Ġwe": 619,
  "Ġwell": 877,
  "Ġwere": 364,
  "Ġwh": 309,
  "Ġwhe": 464,
  "Ġwhen": 650,
  "Ġwhere": 760,
  "Ġwhich": 404,
  "Ġwhile": 736,
  "Ġwho": 520,
  "Ġwith": 300,
  "Ġwork": 634,
  "Ġwould": 606,
  "Ġwrit": 734,
  "Ġy": 411,
  "Ġyear": 548,
  "Ġyears": 822,
  "Ġâ": 395,
  "ĠâĢ": 400,
  "ĠâĢĵ": 463,
  "ĠâĢĶ": 883,
  "ĠĊ": 256,
  "Ģ": 164,
  "ģ": 165,
  "Ĥ": 166,
  "ĥ": 167,
  "Ħ": 168,
  "ħ": 169,
  "Ĩ": 170,
  "ĩ": 171,
  "Ī": 172,
  "ī": 173,
  "Ĭ": 174,
  "ĭ": 175,
  "Į": 176,
  "į": 177,
  "İ": 178,
  "ı": 179,
  "IJ": 180,
  "ij": 181,
  "Ĵ": 182,
  "ĵ": 183,
  "Ķ": 184,
  "ķ": 185,
  "ĸ": 186,
  "Ĺ": 187,
  "ĺ": 188,
  "Ļ": 189,
  "ļ": 190,
  "Ľ": 191,
  "ľ": 192,
  "Ŀ": 193,
  "ŀ": 194,
  "Ł": 195,
  "ł": 196,
  "Ń": 197
}