BAAR4-embed-49M / tokenizer.json
aixk's picture
Upload folder using huggingface_hub
0833edb verified
Raw History Blame Contribute Delete
38.7 kB
{
"version": "1.0",
"model": {
"type": "WordLevel",
"vocab": {
"<pad>": 0,
"<unk>": 1,
"<bos>": 2,
"<eos>": 3,
"<0x00>": 4,
"<0x01>": 5,
"<0x02>": 6,
"<0x03>": 7,
"<0x04>": 8,
"<0x05>": 9,
"<0x06>": 10,
"<0x07>": 11,
"<0x08>": 12,
"<0x09>": 13,
"<0x0A>": 14,
"<0x0B>": 15,
"<0x0C>": 16,
"<0x0D>": 17,
"<0x0E>": 18,
"<0x0F>": 19,
"<0x10>": 20,
"<0x11>": 21,
"<0x12>": 22,
"<0x13>": 23,
"<0x14>": 24,
"<0x15>": 25,
"<0x16>": 26,
"<0x17>": 27,
"<0x18>": 28,
"<0x19>": 29,
"<0x1A>": 30,
"<0x1B>": 31,
"<0x1C>": 32,
"<0x1D>": 33,
"<0x1E>": 34,
"<0x1F>": 35,
"<0x20>": 36,
"<0x21>": 37,
"<0x22>": 38,
"<0x23>": 39,
"<0x24>": 40,
"<0x25>": 41,
"<0x26>": 42,
"<0x27>": 43,
"<0x28>": 44,
"<0x29>": 45,
"<0x2A>": 46,
"<0x2B>": 47,
"<0x2C>": 48,
"<0x2D>": 49,
"<0x2E>": 50,
"<0x2F>": 51,
"<0x30>": 52,
"<0x31>": 53,
"<0x32>": 54,
"<0x33>": 55,
"<0x34>": 56,
"<0x35>": 57,
"<0x36>": 58,
"<0x37>": 59,
"<0x38>": 60,
"<0x39>": 61,
"<0x3A>": 62,
"<0x3B>": 63,
"<0x3C>": 64,
"<0x3D>": 65,
"<0x3E>": 66,
"<0x3F>": 67,
"<0x40>": 68,
"<0x41>": 69,
"<0x42>": 70,
"<0x43>": 71,
"<0x44>": 72,
"<0x45>": 73,
"<0x46>": 74,
"<0x47>": 75,
"<0x48>": 76,
"<0x49>": 77,
"<0x4A>": 78,
"<0x4B>": 79,
"<0x4C>": 80,
"<0x4D>": 81,
"<0x4E>": 82,
"<0x4F>": 83,
"<0x50>": 84,
"<0x51>": 85,
"<0x52>": 86,
"<0x53>": 87,
"<0x54>": 88,
"<0x55>": 89,
"<0x56>": 90,
"<0x57>": 91,
"<0x58>": 92,
"<0x59>": 93,
"<0x5A>": 94,
"<0x5B>": 95,
"<0x5C>": 96,
"<0x5D>": 97,
"<0x5E>": 98,
"<0x5F>": 99,
"<0x60>": 100,
"<0x61>": 101,
"<0x62>": 102,
"<0x63>": 103,
"<0x64>": 104,
"<0x65>": 105,
"<0x66>": 106,
"<0x67>": 107,
"<0x68>": 108,
"<0x69>": 109,
"<0x6A>": 110,
"<0x6B>": 111,
"<0x6C>": 112,
"<0x6D>": 113,
"<0x6E>": 114,
"<0x6F>": 115,
"<0x70>": 116,
"<0x71>": 117,
"<0x72>": 118,
"<0x73>": 119,
"<0x74>": 120,
"<0x75>": 121,
"<0x76>": 122,
"<0x77>": 123,
"<0x78>": 124,
"<0x79>": 125,
"<0x7A>": 126,
"<0x7B>": 127,
"<0x7C>": 128,
"<0x7D>": 129,
"<0x7E>": 130,
"<0x7F>": 131,
"<0x80>": 132,
"<0x81>": 133,
"<0x82>": 134,
"<0x83>": 135,
"<0x84>": 136,
"<0x85>": 137,
"<0x86>": 138,
"<0x87>": 139,
"<0x88>": 140,
"<0x89>": 141,
"<0x8A>": 142,
"<0x8B>": 143,
"<0x8C>": 144,
"<0x8D>": 145,
"<0x8E>": 146,
"<0x8F>": 147,
"<0x90>": 148,
"<0x91>": 149,
"<0x92>": 150,
"<0x93>": 151,
"<0x94>": 152,
"<0x95>": 153,
"<0x96>": 154,
"<0x97>": 155,
"<0x98>": 156,
"<0x99>": 157,
"<0x9A>": 158,
"<0x9B>": 159,
"<0x9C>": 160,
"<0x9D>": 161,
"<0x9E>": 162,
"<0x9F>": 163,
"<0xA0>": 164,
"<0xA1>": 165,
"<0xA2>": 166,
"<0xA3>": 167,
"<0xA4>": 168,
"<0xA5>": 169,
"<0xA6>": 170,
"<0xA7>": 171,
"<0xA8>": 172,
"<0xA9>": 173,
"<0xAA>": 174,
"<0xAB>": 175,
"<0xAC>": 176,
"<0xAD>": 177,
"<0xAE>": 178,
"<0xAF>": 179,
"<0xB0>": 180,
"<0xB1>": 181,
"<0xB2>": 182,
"<0xB3>": 183,
"<0xB4>": 184,
"<0xB5>": 185,
"<0xB6>": 186,
"<0xB7>": 187,
"<0xB8>": 188,
"<0xB9>": 189,
"<0xBA>": 190,
"<0xBB>": 191,
"<0xBC>": 192,
"<0xBD>": 193,
"<0xBE>": 194,
"<0xBF>": 195,
"<0xC0>": 196,
"<0xC1>": 197,
"<0xC2>": 198,
"<0xC3>": 199,
"<0xC4>": 200,
"<0xC5>": 201,
"<0xC6>": 202,
"<0xC7>": 203,
"<0xC8>": 204,
"<0xC9>": 205,
"<0xCA>": 206,
"<0xCB>": 207,
"<0xCC>": 208,
"<0xCD>": 209,
"<0xCE>": 210,
"<0xCF>": 211,
"<0xD0>": 212,
"<0xD1>": 213,
"<0xD2>": 214,
"<0xD3>": 215,
"<0xD4>": 216,
"<0xD5>": 217,
"<0xD6>": 218,
"<0xD7>": 219,
"<0xD8>": 220,
"<0xD9>": 221,
"<0xDA>": 222,
"<0xDB>": 223,
"<0xDC>": 224,
"<0xDD>": 225,
"<0xDE>": 226,
"<0xDF>": 227,
"<0xE0>": 228,
"<0xE1>": 229,
"<0xE2>": 230,
"<0xE3>": 231,
"<0xE4>": 232,
"<0xE5>": 233,
"<0xE6>": 234,
"<0xE7>": 235,
"<0xE8>": 236,
"<0xE9>": 237,
"<0xEA>": 238,
"<0xEB>": 239,
"<0xEC>": 240,
"<0xED>": 241,
"<0xEE>": 242,
"<0xEF>": 243,
"<0xF0>": 244,
"<0xF1>": 245,
"<0xF2>": 246,
"<0xF3>": 247,
"<0xF4>": 248,
"<0xF5>": 249,
"[LANG_KO]": 250,
"[LANG_EN]": 251,
"<token_252>": 252,
"<token_253>": 253,
"<token_254>": 254,
"<token_255>": 255,
"<token_256>": 256,
"<token_257>": 257,
"<token_258>": 258,
"<token_259>": 259,
"<token_260>": 260,
"<token_261>": 261,
"<token_262>": 262,
"<token_263>": 263,
"<token_264>": 264,
"<token_265>": 265,
"<token_266>": 266,
"<token_267>": 267,
"<token_268>": 268,
"<token_269>": 269,
"<token_270>": 270,
"<token_271>": 271,
"<token_272>": 272,
"<token_273>": 273,
"<token_274>": 274,
"<token_275>": 275,
"<token_276>": 276,
"<token_277>": 277,
"<token_278>": 278,
"<token_279>": 279,
" ": 1034,
"\n": 1067,
".": 1035,
",": 1036,
"?": 1037,
"!": 1038,
":": 1039,
";": 1040,
"\"": 1041,
"'": 1042,
"(": 1043,
")": 1044,
"[": 1045,
"]": 1046,
"-": 1051,
"/": 1052,
"~": 1055,
"%": 1059,
"@": 1056,
"#": 1057,
"$": 1058,
"&": 1061,
"*": 1062,
"+": 1063,
"=": 1064,
"은": 1908,
"는": 1909,
"이": 1910,
"가": 1911,
"을": 1912,
"를": 1913,
"의": 1915,
"에": 1916,
"에서": 313,
"로": 1918,
"으로": 315,
"에게": 316,
"와": 1922,
"과": 1914,
"도": 1923,
"만": 1924,
"부터": 321,
"까지": 322,
"그리고": 323,
"하지만": 324,
"또는": 325,
"그래서": 326,
"왜냐하면": 327,
"만약": 328,
"나": 329,
"너": 330,
"그": 364,
"그녀": 332,
"우리": 513,
"그들": 402,
"이다": 335,
"있다": 336,
"아니다": 337,
"에 대해": 339,
"에 대한": 340,
"있": 1939,
"외부": 343,
"할 수 있": 821,
"할 수 있어요": 345,
"이것": 346,
"있었다": 519,
"한 개": 350,
"그들의": 351,
"물": 353,
"수": 1942,
"사람": 628,
"사람들": 356,
"더": 357,
"더 많은": 358,
"다음": 522,
"그 다음": 360,
"그의": 363,
"그런 것": 365,
"그런": 366,
"다른 것": 472,
"다른": 470,
"개": 369,
"강아지": 370,
"지나가면서": 371,
"지나가며": 372,
"만들어라": 373,
"만들자": 390,
"들어": 375,
"부여": 377,
"주어졌다": 378,
"시간": 379,
"시간이": 380,
"몇 개": 908,
"사용": 396,
"이용": 383,
"모두": 384,
"모든 것": 385,
"하얀색": 386,
"흰색": 911,
"당신의": 388,
"당신": 389,
"창조": 391,
"검은색": 392,
"검정색": 393,
"많이": 740,
"많은": 395,
"사용된": 397,
"이것들": 398,
"새로운": 400,
"새": 401,
"그놈들": 403,
"도움": 404,
"도와줘": 405,
"셔츠": 407,
"착용": 408,
"입는 것": 409,
"어디": 410,
"어디에": 411,
"생성": 412,
"발생": 413,
"예를 들어": 414,
"예를 들면": 415,
"수영": 416,
"헤엄치기": 417,
"제공": 1015,
"공급": 646,
"사이": 420,
"그 사이에": 421,
"대부분": 422,
"가장": 423,
"하는 것": 426,
"하고 있어요": 427,
"연도": 428,
"여자": 429,
"여성": 430,
"가져와": 431,
"가져가": 432,
"길거리": 433,
"길": 811,
"세계": 435,
"세상": 436,
"걷는 것": 437,
"걷기": 898,
"방법": 595,
"만드는 것": 441,
"만드는": 442,
"어떤 것": 443,
"어떤 것도": 444,
"데이터": 445,
"자료": 446,
"각각": 447,
"각": 684,
"중요함": 449,
"목록": 450,
"리스트": 451,
"아래로": 452,
"아래로 내려": 453,
"일": 1008,
"작업": 703,
"큰": 456,
"크다": 457,
"근거": 458,
"찾아라": 459,
"찾아": 460,
"종류": 905,
"유형": 462,
"빨간색": 463,
"붉은색": 464,
"존재": 465,
"존재함": 466,
"서 있는 것": 467,
"서 있는 상태": 468,
"또 다른": 471,
"젊은": 473,
"어린": 474,
"전체적으로": 475,
"전체": 476,
"알다시피": 477,
"알려진": 478,
"생명": 479,
"생활": 480,
"파란색": 481,
"푸른색": 482,
"몇 가지": 484,
"중": 789,
"이 과정에서": 486,
"둘 다": 487,
"둘다": 488,
"하루": 489,
"예제": 491,
"예": 492,
"확인": 493,
"식별": 494,
"종종": 495,
"그 후": 496,
"그 후에": 497,
"높은": 498,
"높다": 499,
"쓰기": 500,
"써라": 501,
"필요": 655,
"필요성": 654,
"포함": 504,
"포함하다": 505,
"과정": 506,
"처리": 507,
"개선": 508,
"향상": 509,
"숫자": 510,
"번호": 511,
"우리의": 512,
"전에": 514,
"제작된": 515,
"제작": 516,
"길다": 517,
"길게": 518,
"세트": 520,
"집합": 521,
"다음으로": 523,
"한 번": 524,
"한번": 525,
"주변에": 526,
"주변": 527,
"줄여라": 528,
"줄여": 529,
"잠자리": 530,
"잠자고 있다": 531,
"도시": 1011,
"시": 1012,
"특정": 534,
"특이성": 535,
"작은": 536,
"작은 것": 537,
"그룹": 538,
"집단": 539,
"남자": 721,
"사람이": 542,
"경험": 543,
"경험자": 544,
"의미있는": 545,
"의미 있는": 546,
"가지고 있었다": 547,
"가장 좋은": 548,
"최고": 549,
"역할": 550,
"역할을": 551,
"시스템": 552,
"체계": 553,
"해야 하다": 711,
"언어": 555,
"주요": 767,
"주": 557,
"같이": 558,
"함께": 559,
"심지어": 560,
"심지어는": 561,
"몸": 562,
"몸체": 563,
"가능": 564,
"가능한": 565,
"앞면": 840,
"앞": 567,
"변화": 568,
"변경": 569,
"훌륭하다": 570,
"훌륭해요": 571,
"손": 572,
"손자": 573,
"상단": 574,
"멀리서": 575,
"멀리": 576,
"기타": 578,
"꺼내": 579,
"꺼": 580,
"복용": 581,
"복용하는 것": 582,
"앉아 있는 것": 583,
"앉아있는 것": 584,
"잠재력": 585,
"가능성": 586,
"영향력": 587,
"영향": 588,
"텍스트": 589,
"문장": 590,
"디자인": 591,
"설계": 889,
"키": 593,
"열쇠": 594,
"길들": 596,
"좋아": 598,
"학습": 599,
"배움": 600,
"더 좋아": 601,
"더 좋네요": 602,
"따라": 603,
"영업": 604,
"농장": 605,
"보고": 606,
"보고 있다": 607,
"장소": 897,
"위치": 926,
"요약": 611,
"결과": 612,
"결과는": 613,
"입력": 614,
"입": 616,
"건강": 617,
"보건": 618,
"범위": 619,
"범주": 620,
"부지": 621,
"면적": 622,
"가족": 623,
"가정": 624,
"빛": 625,
"가벼운": 626,
"인간": 627,
"에너지": 630,
"일반적으로": 994,
"보통": 993,
"순서": 633,
"명령": 634,
"양식": 635,
"형태": 636,
"흔한": 637,
"일반": 638,
"필수요소": 639,
"필수": 640,
"지원": 641,
"지지": 642,
"시작": 643,
"시작해": 644,
"내부에서": 647,
"내부": 648,
"음식": 649,
"식품": 650,
"스토리": 651,
"부분": 652,
"일부": 653,
"짧은": 656,
"짧다": 657,
"다섯": 658,
"전력": 659,
"힘": 660,
"증가": 871,
"증대": 662,
"접근": 663,
"접근성": 664,
"배워라": 665,
"배우기": 666,
"효과적": 667,
"효과": 668,
"반대": 669,
"반대하고": 670,
"연주": 671,
"놀아": 672,
"이해해": 673,
"이해해요": 674,
"상점": 675,
"매장": 676,
"감소": 677,
"줄이는": 678,
"개발": 834,
"발전": 835,
"말": 681,
"단어": 682,
"모든": 683,
"능력": 685,
"능력을": 686,
"끝": 687,
"종말": 688,
"될 수 있다": 689,
"될 것": 690,
"사용자": 692,
"추가로": 693,
"추가적으로": 694,
"품질": 695,
"질": 696,
"오렌지색": 697,
"오렌지": 698,
"팀": 699,
"팀이": 700,
"늙은": 701,
"늙어": 702,
"일하다": 704,
"더하기": 705,
"옆면": 706,
"측면": 707,
"산책로": 708,
"산책로는": 709,
"고객": 712,
"고객이": 713,
"가까이": 714,
"근방": 715,
"배경": 716,
"배후": 717,
"아버지": 718,
"아빠": 719,
"소년": 720,
"집에": 722,
"집": 723,
"연합": 724,
"통일": 725,
"노란색": 726,
"황색": 727,
"제안하다": 728,
"기간": 729,
"용어": 730,
"태어났다": 731,
"출생": 732,
"사업": 733,
"비즈니스": 734,
"현장": 735,
"가치": 736,
"값": 737,
"발견": 738,
"발견된": 739,
"아주": 975,
"야외에서": 742,
"야외": 743,
"공기": 744,
"도달": 745,
"달성": 884,
"집중": 747,
"집중력": 748,
"미래": 749,
"미래에": 750,
"저 사람": 751,
"그 사람": 752,
"고유한": 753,
"유일하다": 754,
"공": 1952,
"볼": 756,
"내용": 757,
"함수": 777,
"날짜": 760,
"가득": 761,
"완전": 762,
"국가": 890,
"상태": 764,
"뒤에서": 765,
"뒤에": 766,
"주력": 768,
"개별": 769,
"성격": 770,
"성질": 771,
"기다린다": 772,
"기다려야지": 773,
"서비스": 774,
"봉사": 836,
"기능": 776,
"내버려 두자": 778,
"내버려두자": 779,
"제품": 780,
"상품": 781,
"양성": 782,
"긍정적으로": 783,
"기한": 784,
"유료": 785,
"발걸음": 786,
"발자국": 787,
"그 중": 788,
"신체적": 790,
"육체적": 791,
"강한": 792,
"강하다": 793,
"의사소통": 794,
"소통": 795,
"통제": 796,
"제어": 797,
"아들": 798,
"아들아": 799,
"복합적": 800,
"복잡함": 801,
"진짜": 802,
"실제": 803,
"의자": 804,
"좌석": 805,
"활동": 806,
"행동": 948,
"심장": 809,
"도로": 810,
"결정": 966,
"결정하는": 813,
"단순함": 814,
"단순": 815,
"영화": 816,
"필름": 817,
"느끼기": 818,
"느껴라": 819,
"될 수 있": 820,
"사건": 822,
"이벤트": 823,
"금액": 824,
"위험": 826,
"위험성": 827,
"기계": 828,
"기기": 829,
"구조": 830,
"구성": 831,
"컴퓨터": 833,
"봉송": 837,
"계획": 838,
"기획": 839,
"전면": 841,
"복수": 842,
"다중": 843,
"번": 844,
"문제": 845,
"문제점": 846,
"수준": 847,
"레벨": 848,
"스틱": 850,
"자연": 851,
"본성": 852,
"생산량": 853,
"출력": 854,
"이해": 866,
"이해함": 856,
"남아있어요": 857,
"계속 있어": 858,
"직책": 859,
"미국": 860,
"미국인": 861,
"효율적": 862,
"효율성": 863,
"암흑": 864,
"어두운": 865,
"확실": 867,
"마지막으로": 868,
"드디어": 869,
"성장": 870,
"잠들어 있는 상태": 872,
"잠들어 있는 것": 873,
"어려운": 874,
"어려운 것": 875,
"정부": 876,
"정부가": 877,
"아래": 878,
"밑": 879,
"시장": 881,
"햇빛": 882,
"태양": 883,
"성취": 885,
"자유": 886,
"무료": 887,
"설계된": 888,
"나라": 891,
"전류": 892,
"현재": 893,
"원하고": 894,
"원하는": 895,
"걷다": 899,
"달리는 것": 900,
"달리는": 901,
"에 따라": 946,
"에 따라서": 903,
"품종": 904,
"강력하다": 906,
"힘 있는": 907,
"몇 명": 909,
"회색": 910,
"선도적": 912,
"선두": 913,
"열렸어": 914,
"열려있어요": 915,
"넓은": 916,
"넓다": 917,
"원산지": 918,
"그 사람들": 919,
"제안": 920,
"방지": 922,
"예방": 923,
"대중적": 924,
"인기 있는": 925,
"위상": 927,
"시리즈": 928,
"연대": 929,
"비중": 930,
"공유": 931,
"인공": 932,
"사진": 933,
"이미지": 934,
"위": 935,
"나이": 936,
"연령": 937,
"선택": 938,
"선택하라": 939,
"가볍게": 940,
"쉽게": 962,
"비용": 942,
"비용은": 943,
"성능": 944,
"성과": 945,
"따라서": 947,
"행위": 949,
"결론": 951,
"말하는 것": 952,
"말하는것": 953,
"반환": 954,
"돌려": 955,
"색상": 956,
"색": 957,
"트랙": 958,
"경로": 959,
"주제": 961,
"손쉽게": 963,
"생각해 보세요": 965,
"결의": 967,
"나무": 968,
"깨끗": 969,
"깨끗한": 970,
"목적": 971,
"목표": 972,
"안전성": 973,
"보안": 974,
"매우": 976,
"피톤": 977,
"파톤": 978,
"쇼": 979,
"공연": 980,
"효율적으로": 981,
"효과적으로": 982,
"탄소": 983,
"석탄": 984,
"사용 가능": 985,
"사용가능": 986,
"특징": 987,
"특성": 988,
"게임": 989,
"놀이": 990,
"숲": 991,
"산림": 992,
"고려": 995,
"고려한": 996,
"얼굴을": 997,
"다 됐어": 998,
"다 됐어요": 999,
"지역": 1000,
"지방": 1001,
"먹는 것": 1002,
"먹어": 1003,
"통과": 1004,
"합격": 1005,
"땅": 1006,
"지구": 1007,
"기후": 1009,
"기상": 1010,
"바위": 1013,
"암석": 1014,
"제공된": 1016,
"운송": 1017,
"교통": 1018,
"따라와": 1019,
"따라가": 1020,
"살아": 1021,
"살아요": 1022,
"직업": 1023,
"0": 1024,
"1": 1025,
"2": 1026,
"3": 1027,
"4": 1028,
"5": 1029,
"6": 1030,
"7": 1031,
"8": 1032,
"9": 1033,
"{": 1047,
"}": 1048,
"<": 1049,
">": 1050,
"\\": 1053,
"_": 1054,
"^": 1060,
"|": 1065,
"`": 1066,
"\t": 1068,
"a": 1069,
"b": 1070,
"c": 1071,
"d": 1072,
"e": 1073,
"f": 1074,
"g": 1075,
"h": 1076,
"i": 1077,
"j": 1078,
"k": 1079,
"l": 1080,
"m": 1081,
"n": 1082,
"o": 1083,
"p": 1084,
"q": 1085,
"r": 1086,
"s": 1087,
"t": 1088,
"u": 1089,
"v": 1090,
"w": 1091,
"x": 1092,
"y": 1093,
"z": 1094,
"A": 1095,
"B": 1096,
"C": 1097,
"D": 1098,
"E": 1099,
"F": 1100,
"G": 1101,
"H": 1102,
"I": 1103,
"J": 1104,
"K": 1105,
"L": 1106,
"M": 1107,
"N": 1108,
"O": 1109,
"P": 1110,
"Q": 1111,
"R": 1112,
"S": 1113,
"T": 1114,
"U": 1115,
"V": 1116,
"W": 1117,
"X": 1118,
"Y": 1119,
"Z": 1120,
"ä": 1121,
"ö": 1122,
"ü": 1123,
"ß": 1124,
"Ä": 1125,
"Ö": 1126,
"Ü": 1127,
"á": 1128,
"é": 1129,
"í": 1130,
"ó": 1131,
"ú": 1132,
"ñ": 1133,
"Á": 1134,
"É": 1135,
"Í": 1136,
"Ó": 1137,
"Ú": 1138,
"Ñ": 1139,
"ã": 1140,
"õ": 1141,
"ç": 1142,
"Ã": 1143,
"Õ": 1144,
"Ç": 1145,
"à": 1146,
"è": 1147,
"ì": 1148,
"ò": 1149,
"ù": 1150,
"À": 1151,
"È": 1152,
"Ò": 1153,
"Ù": 1154,
"â": 1155,
"ê": 1156,
"î": 1157,
"ô": 1158,
"û": 1159,
"Â": 1160,
"Ê": 1161,
"Î": 1162,
"Ô": 1163,
"Û": 1164,
"ă": 1165,
"đ": 1166,
"ơ": 1167,
"ư": 1168,
"Ă": 1169,
"Đ": 1170,
"Ơ": 1171,
"Ư": 1172,
"ạ": 1173,
"ả": 1174,
"ấ": 1175,
"ầ": 1176,
"ẩ": 1177,
"ẫ": 1178,
"ậ": 1179,
"ắ": 1180,
"ằ": 1181,
"ẳ": 1182,
"ẵ": 1183,
"ặ": 1184,
"ẹ": 1185,
"ẻ": 1186,
"ẽ": 1187,
"ế": 1188,
"ề": 1189,
"ể": 1190,
"ễ": 1191,
"ệ": 1192,
"ỉ": 1193,
"ị": 1194,
"ọ": 1195,
"ỏ": 1196,
"ố": 1197,
"ồ": 1198,
"ổ": 1199,
"ỗ": 1200,
"ộ": 1201,
"ớ": 1202,
"ờ": 1203,
"ở": 1204,
"ỡ": 1205,
"ợ": 1206,
"ụ": 1207,
"ủ": 1208,
"ứ": 1209,
"ừ": 1210,
"ử": 1211,
"ữ": 1212,
"ự": 1213,
"ỳ": 1214,
"ỵ": 1215,
"ỷ": 1216,
"ỹ": 1217,
"ą": 1218,
"ć": 1219,
"ę": 1220,
"ł": 1221,
"ń": 1222,
"ś": 1223,
"ź": 1224,
"ż": 1225,
"Ą": 1226,
"Ć": 1227,
"Ę": 1228,
"Ł": 1229,
"Ń": 1230,
"Ś": 1231,
"Ź": 1232,
"Ż": 1233,
"ğ": 1234,
"ı": 1235,
"ş": 1236,
"Ğ": 1237,
"İ": 1238,
"Ş": 1239,
"а": 1240,
"б": 1241,
"в": 1242,
"г": 1243,
"д": 1244,
"е": 1245,
"ё": 1246,
"ж": 1247,
"з": 1248,
"и": 1249,
"й": 1250,
"к": 1251,
"л": 1252,
"м": 1253,
"н": 1254,
"о": 1255,
"п": 1256,
"р": 1257,
"с": 1258,
"т": 1259,
"у": 1260,
"ф": 1261,
"х": 1262,
"ц": 1263,
"ч": 1264,
"ш": 1265,
"щ": 1266,
"ъ": 1267,
"ы": 1268,
"ь": 1269,
"э": 1270,
"ю": 1271,
"я": 1272,
"А": 1273,
"Б": 1274,
"В": 1275,
"Г": 1276,
"Д": 1277,
"Е": 1278,
"Ё": 1279,
"Ж": 1280,
"З": 1281,
"И": 1282,
"Й": 1283,
"К": 1284,
"Л": 1285,
"М": 1286,
"Н": 1287,
"О": 1288,
"П": 1289,
"Р": 1290,
"С": 1291,
"Т": 1292,
"У": 1293,
"Ф": 1294,
"Х": 1295,
"Ц": 1296,
"Ч": 1297,
"Ш": 1298,
"Щ": 1299,
"Ъ": 1300,
"Ы": 1301,
"Ь": 1302,
"Э": 1303,
"Ю": 1304,
"Я": 1305,
"Ͱ": 1306,
"ͱ": 1307,
"Ͳ": 1308,
"ͳ": 1309,
"ʹ": 1310,
"͵": 1311,
"Ͷ": 1312,
"ͷ": 1313,
"ͺ": 1314,
"ͻ": 1315,
"ͼ": 1316,
"ͽ": 1317,
";": 1318,
"Ϳ": 1319,
"΄": 1320,
"΅": 1321,
"Ά": 1322,
"·": 1323,
"Έ": 1324,
"Ή": 1325,
"Ί": 1326,
"Ό": 1327,
"Ύ": 1328,
"Ώ": 1329,
"ΐ": 1330,
"Α": 1331,
"Β": 1332,
"Γ": 1333,
"Δ": 1334,
"Ε": 1335,
"Ζ": 1336,
"Η": 1337,
"Θ": 1338,
"Ι": 1339,
"Κ": 1340,
"Λ": 1341,
"Μ": 1342,
"Ν": 1343,
"Ξ": 1344,
"Ο": 1345,
"Π": 1346,
"Ρ": 1347,
"Σ": 1348,
"Τ": 1349,
"Υ": 1350,
"Φ": 1351,
"Χ": 1352,
"Ψ": 1353,
"Ω": 1354,
"Ϊ": 1355,
"Ϋ": 1356,
"ά": 1357,
"έ": 1358,
"ή": 1359,
"ί": 1360,
"ΰ": 1361,
"α": 1362,
"β": 1363,
"γ": 1364,
"δ": 1365,
"ε": 1366,
"ζ": 1367,
"η": 1368,
"θ": 1369,
"ι": 1370,
"κ": 1371,
"λ": 1372,
"μ": 1373,
"ν": 1374,
"ξ": 1375,
"ο": 1376,
"π": 1377,
"ρ": 1378,
"ς": 1379,
"σ": 1380,
"τ": 1381,
"υ": 1382,
"φ": 1383,
"χ": 1384,
"ψ": 1385,
"ω": 1386,
"ϊ": 1387,
"ϋ": 1388,
"ό": 1389,
"ύ": 1390,
"ώ": 1391,
"Ϗ": 1392,
"ϐ": 1393,
"ϑ": 1394,
"ϒ": 1395,
"ϓ": 1396,
"ϔ": 1397,
"ϕ": 1398,
"ϖ": 1399,
"ϗ": 1400,
"Ϙ": 1401,
"ϙ": 1402,
"Ϛ": 1403,
"ϛ": 1404,
"Ϝ": 1405,
"ϝ": 1406,
"Ϟ": 1407,
"ϟ": 1408,
"Ϡ": 1409,
"ϡ": 1410,
"Ϣ": 1411,
"ϣ": 1412,
"Ϥ": 1413,
"ϥ": 1414,
"Ϧ": 1415,
"ϧ": 1416,
"Ϩ": 1417,
"ϩ": 1418,
"Ϫ": 1419,
"ϫ": 1420,
"Ϭ": 1421,
"ϭ": 1422,
"Ϯ": 1423,
"ϯ": 1424,
"ϰ": 1425,
"ϱ": 1426,
"ϲ": 1427,
"ϳ": 1428,
"ϴ": 1429,
"ϵ": 1430,
"϶": 1431,
"Ϸ": 1432,
"ϸ": 1433,
"Ϲ": 1434,
"Ϻ": 1435,
"ϻ": 1436,
"ϼ": 1437,
"Ͻ": 1438,
"Ͼ": 1439,
"؀": 1440,
"؁": 1441,
"؂": 1442,
"؃": 1443,
"؄": 1444,
"؅": 1445,
"؆": 1446,
"؇": 1447,
"؈": 1448,
"؉": 1449,
"؊": 1450,
"؋": 1451,
"،": 1452,
"؍": 1453,
"؎": 1454,
"؏": 1455,
"ؐ": 1456,
"ؑ": 1457,
"ؒ": 1458,
"ؓ": 1459,
"ؔ": 1460,
"ؕ": 1461,
"ؖ": 1462,
"ؗ": 1463,
"ؘ": 1464,
"ؙ": 1465,
"ؚ": 1466,
"؛": 1467,
"؜": 1468,
"؝": 1469,
"؞": 1470,
"؟": 1471,
"ؠ": 1472,
"ء": 1473,
"آ": 1474,
"أ": 1475,
"ؤ": 1476,
"إ": 1477,
"ئ": 1478,
"ا": 1479,
"ب": 1480,
"ة": 1481,
"ت": 1482,
"ث": 1483,
"ج": 1484,
"ح": 1485,
"خ": 1486,
"د": 1487,
"ذ": 1488,
"ر": 1489,
"ز": 1490,
"س": 1491,
"ش": 1492,
"ص": 1493,
"ض": 1494,
"ط": 1495,
"ظ": 1496,
"ع": 1497,
"غ": 1498,
"ػ": 1499,
"ؼ": 1500,
"ؽ": 1501,
"ؾ": 1502,
"ؿ": 1503,
"ـ": 1504,
"ف": 1505,
"ق": 1506,
"ك": 1507,
"ل": 1508,
"م": 1509,
"ن": 1510,
"ه": 1511,
"و": 1512,
"ى": 1513,
"ي": 1514,
"ً": 1515,
"ٌ": 1516,
"ٍ": 1517,
"َ": 1518,
"ُ": 1519,
"ِ": 1520,
"ّ": 1521,
"ْ": 1522,
"ٓ": 1523,
"ٔ": 1524,
"ٕ": 1525,
"ٖ": 1526,
"ٗ": 1527,
"٘": 1528,
"ٙ": 1529,
"ٚ": 1530,
"ٛ": 1531,
"ٜ": 1532,
"ٝ": 1533,
"ٞ": 1534,
"ٟ": 1535,
"٠": 1536,
"١": 1537,
"٢": 1538,
"٣": 1539,
"٤": 1540,
"٥": 1541,
"٦": 1542,
"٧": 1543,
"٨": 1544,
"٩": 1545,
"٪": 1546,
"٫": 1547,
"٬": 1548,
"٭": 1549,
"ٮ": 1550,
"ٯ": 1551,
"ٰ": 1552,
"ٱ": 1553,
"ٲ": 1554,
"ٳ": 1555,
"ٴ": 1556,
"ٵ": 1557,
"ٶ": 1558,
"ٷ": 1559,
"ٸ": 1560,
"ٹ": 1561,
"ٺ": 1562,
"ٻ": 1563,
"ټ": 1564,
"ٽ": 1565,
"پ": 1566,
"ٿ": 1567,
"ڀ": 1568,
"ځ": 1569,
"ڂ": 1570,
"ڃ": 1571,
"ڄ": 1572,
"څ": 1573,
"چ": 1574,
"ڇ": 1575,
"ڈ": 1576,
"ډ": 1577,
"ڊ": 1578,
"ڋ": 1579,
"ڌ": 1580,
"ڍ": 1581,
"ڎ": 1582,
"ڏ": 1583,
"ڐ": 1584,
"ڑ": 1585,
"ڒ": 1586,
"ړ": 1587,
"ڔ": 1588,
"ڕ": 1589,
"ږ": 1590,
"ڗ": 1591,
"ژ": 1592,
"ڙ": 1593,
"ښ": 1594,
"ڛ": 1595,
"ڜ": 1596,
"ڝ": 1597,
"ڞ": 1598,
"ڟ": 1599,
"ڠ": 1600,
"ڡ": 1601,
"ڢ": 1602,
"ڣ": 1603,
"ڤ": 1604,
"ڥ": 1605,
"ڦ": 1606,
"ڧ": 1607,
"ڨ": 1608,
"ک": 1609,
"ڪ": 1610,
"ګ": 1611,
"ڬ": 1612,
"ڭ": 1613,
"ڮ": 1614,
"گ": 1615,
"ڰ": 1616,
"ڱ": 1617,
"ڲ": 1618,
"ڳ": 1619,
"ڴ": 1620,
"ڵ": 1621,
"ڶ": 1622,
"ڷ": 1623,
"ڸ": 1624,
"ڹ": 1625,
"ں": 1626,
"ڻ": 1627,
"ڼ": 1628,
"ڽ": 1629,
"ھ": 1630,
"ڿ": 1631,
"ۀ": 1632,
"ہ": 1633,
"ۂ": 1634,
"ۃ": 1635,
"ۄ": 1636,
"ۅ": 1637,
"ۆ": 1638,
"ۇ": 1639,
"ۈ": 1640,
"ۉ": 1641,
"ۊ": 1642,
"ۋ": 1643,
"ی": 1644,
"ۍ": 1645,
"ێ": 1646,
"ۏ": 1647,
"ې": 1648,
"ۑ": 1649,
"ے": 1650,
"ۓ": 1651,
"۔": 1652,
"ە": 1653,
"ۖ": 1654,
"ۗ": 1655,
"ۘ": 1656,
"ۙ": 1657,
"ۚ": 1658,
"ۛ": 1659,
"ۜ": 1660,
"۝": 1661,
"۞": 1662,
"۟": 1663,
"۠": 1664,
"ۡ": 1665,
"ۢ": 1666,
"ۣ": 1667,
"ۤ": 1668,
"ۥ": 1669,
"ۦ": 1670,
"ۧ": 1671,
"ۨ": 1672,
"۩": 1673,
"۪": 1674,
"۫": 1675,
"۬": 1676,
"ۭ": 1677,
"ۮ": 1678,
"ۯ": 1679,
"۰": 1680,
"۱": 1681,
"۲": 1682,
"۳": 1683,
"۴": 1684,
"۵": 1685,
"۶": 1686,
"۷": 1687,
"۸": 1688,
"۹": 1689,
"ۺ": 1690,
"ۻ": 1691,
"ۼ": 1692,
"۽": 1693,
"۾": 1694,
"ऀ": 1695,
"ँ": 1696,
"ं": 1697,
"ः": 1698,
"ऄ": 1699,
"अ": 1700,
"आ": 1701,
"इ": 1702,
"ई": 1703,
"उ": 1704,
"ऊ": 1705,
"ऋ": 1706,
"ऌ": 1707,
"ऍ": 1708,
"ऎ": 1709,
"ए": 1710,
"ऐ": 1711,
"ऑ": 1712,
"ऒ": 1713,
"ओ": 1714,
"औ": 1715,
"क": 1716,
"ख": 1717,
"ग": 1718,
"घ": 1719,
"ङ": 1720,
"च": 1721,
"छ": 1722,
"ज": 1723,
"झ": 1724,
"ञ": 1725,
"ट": 1726,
"ठ": 1727,
"ड": 1728,
"ढ": 1729,
"ण": 1730,
"त": 1731,
"थ": 1732,
"द": 1733,
"ध": 1734,
"न": 1735,
"ऩ": 1736,
"प": 1737,
"फ": 1738,
"ब": 1739,
"भ": 1740,
"म": 1741,
"य": 1742,
"र": 1743,
"ऱ": 1744,
"ल": 1745,
"ळ": 1746,
"ऴ": 1747,
"व": 1748,
"श": 1749,
"ष": 1750,
"स": 1751,
"ह": 1752,
"ऺ": 1753,
"ऻ": 1754,
"़": 1755,
"ऽ": 1756,
"ा": 1757,
"ि": 1758,
"ी": 1759,
"ु": 1760,
"ू": 1761,
"ृ": 1762,
"ॄ": 1763,
"ॅ": 1764,
"ॆ": 1765,
"े": 1766,
"ै": 1767,
"ॉ": 1768,
"ॊ": 1769,
"ो": 1770,
"ौ": 1771,
"्": 1772,
"ॎ": 1773,
"ॏ": 1774,
"ॐ": 1775,
"॑": 1776,
"॒": 1777,
"॓": 1778,
"॔": 1779,
"ॕ": 1780,
"ॖ": 1781,
"ॗ": 1782,
"क़": 1783,
"ख़": 1784,
"ग़": 1785,
"ज़": 1786,
"ड़": 1787,
"ढ़": 1788,
"फ़": 1789,
"य़": 1790,
"ॠ": 1791,
"ॡ": 1792,
"ॢ": 1793,
"ॣ": 1794,
"।": 1795,
"॥": 1796,
"०": 1797,
"१": 1798,
"२": 1799,
"३": 1800,
"४": 1801,
"५": 1802,
"६": 1803,
"७": 1804,
"८": 1805,
"९": 1806,
"॰": 1807,
"ॱ": 1808,
"ॲ": 1809,
"ॳ": 1810,
"ॴ": 1811,
"ॵ": 1812,
"ॶ": 1813,
"ॷ": 1814,
"ॸ": 1815,
"ॹ": 1816,
"ॺ": 1817,
"ॻ": 1818,
"ॼ": 1819,
"ॽ": 1820,
"ॾ": 1821,
"ก": 1822,
"ข": 1823,
"ฃ": 1824,
"ค": 1825,
"ฅ": 1826,
"ฆ": 1827,
"ง": 1828,
"จ": 1829,
"ฉ": 1830,
"ช": 1831,
"ซ": 1832,
"ฌ": 1833,
"ญ": 1834,
"ฎ": 1835,
"ฏ": 1836,
"ฐ": 1837,
"ฑ": 1838,
"ฒ": 1839,
"ณ": 1840,
"ด": 1841,
"ต": 1842,
"ถ": 1843,
"ท": 1844,
"ธ": 1845,
"น": 1846,
"บ": 1847,
"ป": 1848,
"ผ": 1849,
"ฝ": 1850,
"พ": 1851,
"ฟ": 1852,
"ภ": 1853,
"ม": 1854,
"ย": 1855,
"ร": 1856,
"ฤ": 1857,
"ล": 1858,
"ฦ": 1859,
"ว": 1860,
"ศ": 1861,
"ษ": 1862,
"ส": 1863,
"ห": 1864,
"ฬ": 1865,
"อ": 1866,
"ฮ": 1867,
"ฯ": 1868,
"ะ": 1869,
"ั": 1870,
"า": 1871,
"ำ": 1872,
"ิ": 1873,
"ี": 1874,
"ึ": 1875,
"ื": 1876,
"ุ": 1877,
"ู": 1878,
"ฺ": 1879,
"฿": 1880,
"เ": 1881,
"แ": 1882,
"โ": 1883,
"ใ": 1884,
"ไ": 1885,
"ๅ": 1886,
"ๆ": 1887,
"็": 1888,
"่": 1889,
"้": 1890,
"๊": 1891,
"๋": 1892,
"์": 1893,
"ํ": 1894,
"๎": 1895,
"๏": 1896,
"๐": 1897,
"๑": 1898,
"๒": 1899,
"๓": 1900,
"๔": 1901,
"๕": 1902,
"๖": 1903,
"๗": 1904,
"๘": 1905,
"๙": 1906,
"๚": 1907,
"서": 1917,
"으": 1919,
"하": 1920,
"고": 1921,
"까": 1925,
"지": 1926,
"부": 1927,
"터": 1928,
"게": 1929,
"한": 1930,
"테": 1931,
"며": 1932,
"습": 1933,
"니": 1934,
"다": 1935,
"되": 1936,
"했": 1937,
"어": 1938,
"없": 1940,
"것": 1941,
"등": 1943,
"및": 1944,
"대": 1945,
"민": 1946,
"국": 1947,
"울": 1948,
"날": 1949,
"씨": 1950,
"인": 1951,
"능": 1953,
"기": 1954,
"술": 1955,
"ᄀ": 1956,
"ᄁ": 1957,
"ᄂ": 1958,
"ᄃ": 1959,
"ᄄ": 1960,
"ᄅ": 1961,
"ᄆ": 1962,
"ᄇ": 1963,
"ᄈ": 1964,
"ᄉ": 1965,
"ᄊ": 1966,
"ᄋ": 1967,
"ᄌ": 1968,
"ᄍ": 1969,
"ᄎ": 1970,
"ᄏ": 1971,
"ᄐ": 1972,
"ᄑ": 1973,
"ᄒ": 1974,
"ᅡ": 1975,
"ᅢ": 1976,
"ᅣ": 1977,
"ᅤ": 1978,
"ᅥ": 1979,
"ᅦ": 1980,
"ᅧ": 1981,
"ᅨ": 1982,
"ᅩ": 1983,
"ᅪ": 1984,
"ᅫ": 1985,
"ᅬ": 1986,
"ᅭ": 1987,
"ᅮ": 1988,
"ᅯ": 1989,
"ᅰ": 1990,
"ᅱ": 1991,
"ᅲ": 1992,
"ᅳ": 1993,
"ᅴ": 1994,
"ᅵ": 1995,
"ᆨ": 1996,
"ᆩ": 1997,
"ᆪ": 1998,
"ᆫ": 1999,
"ᆬ": 2000,
"ᆭ": 2001,
"ᆮ": 2002,
"ᆯ": 2003,
"ᆰ": 2004,
"ᆱ": 2005,
"ᆲ": 2006,
"ᆳ": 2007,
"ᆴ": 2008,
"ᆵ": 2009,
"ᆶ": 2010,
"ᆷ": 2011,
"ᆸ": 2012,
"ᆹ": 2013,
"ᆺ": 2014,
"ᆻ": 2015,
"ᆼ": 2016,
"ᆽ": 2017,
"ᆾ": 2018,
"ᆿ": 2019,
"ᇀ": 2020,
"ᇁ": 2021,
"ᇂ": 2022,
"あ": 2023,
"い": 2024,
"う": 2025,
"え": 2026,
"お": 2027,
"か": 2028,
"き": 2029,
"く": 2030,
"け": 2031,
"こ": 2032,
"さ": 2033,
"し": 2034,
"す": 2035,
"せ": 2036,
"そ": 2037,
"た": 2038,
"ち": 2039,
"つ": 2040,
"て": 2041,
"と": 2042,
"な": 2043,
"に": 2044,
"ぬ": 2045,
"ね": 2046,
"の": 2047
},
"unk_token": "<unk>"
}
}