kresnik's picture
Upload tokenizer
b141b18
{
"[PAD]": 1081,
"[UNK]": 1080,
"k": 1,
"t": 2,
"|": 0,
"’": 3,
"…": 4,
"ㆍ": 5,
"가": 6,
"각": 7,
"간": 8,
"갈": 9,
"감": 10,
"갑": 11,
"값": 12,
"갓": 13,
"갔": 14,
"강": 15,
"갖": 16,
"같": 17,
"갚": 18,
"갛": 19,
"개": 20,
"객": 21,
"갤": 22,
"갯": 23,
"갸": 24,
"걀": 25,
"걔": 26,
"거": 27,
"걱": 28,
"건": 29,
"걷": 30,
"걸": 31,
"검": 32,
"겁": 33,
"것": 34,
"겅": 35,
"겉": 36,
"게": 37,
"겠": 38,
"겨": 39,
"격": 40,
"견": 41,
"결": 42,
"겸": 43,
"겹": 44,
"겼": 45,
"경": 46,
"곁": 47,
"계": 48,
"고": 49,
"곡": 50,
"곤": 51,
"곧": 52,
"골": 53,
"곰": 54,
"곱": 55,
"곳": 56,
"공": 57,
"과": 58,
"관": 59,
"광": 60,
"괜": 61,
"괴": 62,
"굉": 63,
"교": 64,
"구": 65,
"국": 66,
"군": 67,
"굳": 68,
"굴": 69,
"굵": 70,
"굶": 71,
"굽": 72,
"굿": 73,
"궁": 74,
"궂": 75,
"권": 76,
"궐": 77,
"궤": 78,
"귀": 79,
"귓": 80,
"규": 81,
"그": 82,
"극": 83,
"근": 84,
"글": 85,
"긁": 86,
"금": 87,
"급": 88,
"긋": 89,
"기": 90,
"긱": 91,
"긴": 92,
"긷": 93,
"길": 94,
"김": 95,
"깃": 96,
"깊": 97,
"까": 98,
"깍": 99,
"깎": 100,
"깐": 101,
"깔": 102,
"깜": 103,
"깝": 104,
"깡": 105,
"깨": 106,
"깽": 107,
"꺼": 108,
"꺾": 109,
"껀": 110,
"껄": 111,
"껌": 112,
"껏": 113,
"껐": 114,
"껑": 115,
"께": 116,
"껴": 117,
"꼈": 118,
"꼬": 119,
"꼭": 120,
"꼰": 121,
"꼴": 122,
"꼽": 123,
"꽁": 124,
"꽂": 125,
"꽃": 126,
"꽈": 127,
"꽉": 128,
"꽥": 129,
"꾀": 130,
"꾸": 131,
"꾹": 132,
"꾼": 133,
"꿀": 134,
"꿇": 135,
"꿈": 136,
"꿩": 137,
"꿰": 138,
"뀔": 139,
"끄": 140,
"끈": 141,
"끊": 142,
"끌": 143,
"끓": 144,
"끔": 145,
"끗": 146,
"끝": 147,
"끼": 148,
"끽": 149,
"낀": 150,
"낌": 151,
"낏": 152,
"나": 153,
"낙": 154,
"난": 155,
"날": 156,
"남": 157,
"납": 158,
"낫": 159,
"났": 160,
"낭": 161,
"낮": 162,
"낯": 163,
"낱": 164,
"낳": 165,
"내": 166,
"낸": 167,
"낼": 168,
"냄": 169,
"냅": 170,
"냈": 171,
"냉": 172,
"냐": 173,
"냘": 174,
"냥": 175,
"너": 176,
"넉": 177,
"넌": 178,
"널": 179,
"넓": 180,
"넘": 181,
"넛": 182,
"넣": 183,
"네": 184,
"녀": 185,
"녁": 186,
"년": 187,
"념": 188,
"녕": 189,
"노": 190,
"녹": 191,
"논": 192,
"놀": 193,
"놈": 194,
"놋": 195,
"농": 196,
"높": 197,
"놓": 198,
"놔": 199,
"뇌": 200,
"뇨": 201,
"누": 202,
"눈": 203,
"눌": 204,
"눔": 205,
"눕": 206,
"뉘": 207,
"늉": 208,
"느": 209,
"는": 210,
"늘": 211,
"늙": 212,
"능": 213,
"늦": 214,
"니": 215,
"닉": 216,
"닌": 217,
"닐": 218,
"님": 219,
"닙": 220,
"다": 221,
"닥": 222,
"닦": 223,
"단": 224,
"닫": 225,
"달": 226,
"닭": 227,
"닮": 228,
"닳": 229,
"담": 230,
"답": 231,
"닷": 232,
"당": 233,
"닿": 234,
"대": 235,
"댁": 236,
"댓": 237,
"더": 238,
"덕": 239,
"던": 240,
"덜": 241,
"덤": 242,
"덥": 243,
"덧": 244,
"덩": 245,
"덮": 246,
"데": 247,
"덴": 248,
"도": 249,
"독": 250,
"돈": 251,
"돋": 252,
"돌": 253,
"돕": 254,
"동": 255,
"돼": 256,
"됐": 257,
"되": 258,
"된": 259,
"될": 260,
"됨": 261,
"됩": 262,
"두": 263,
"둑": 264,
"둔": 265,
"둘": 266,
"둠": 267,
"둣": 268,
"둥": 269,
"뒤": 270,
"뒷": 271,
"듀": 272,
"드": 273,
"득": 274,
"든": 275,
"듣": 276,
"들": 277,
"듬": 278,
"듭": 279,
"듯": 280,
"등": 281,
"디": 282,
"딘": 283,
"딜": 284,
"딧": 285,
"딪": 286,
"따": 287,
"딱": 288,
"딴": 289,
"딸": 290,
"땀": 291,
"땅": 292,
"때": 293,
"땡": 294,
"떠": 295,
"떡": 296,
"떤": 297,
"떨": 298,
"떴": 299,
"떻": 300,
"떼": 301,
"또": 302,
"똑": 303,
"똥": 304,
"뚜": 305,
"뚝": 306,
"뚫": 307,
"뚱": 308,
"뛰": 309,
"뛴": 310,
"뜨": 311,
"뜩": 312,
"뜯": 313,
"뜰": 314,
"뜸": 315,
"뜻": 316,
"띄": 317,
"띠": 318,
"띤": 319,
"띵": 320,
"라": 321,
"락": 322,
"란": 323,
"랄": 324,
"람": 325,
"랍": 326,
"랏": 327,
"랐": 328,
"랑": 329,
"랗": 330,
"래": 331,
"램": 332,
"랫": 333,
"랬": 334,
"랴": 335,
"략": 336,
"량": 337,
"러": 338,
"럭": 339,
"런": 340,
"럴": 341,
"럼": 342,
"럽": 343,
"렀": 344,
"렁": 345,
"렇": 346,
"레": 347,
"렌": 348,
"려": 349,
"력": 350,
"련": 351,
"렬": 352,
"렴": 353,
"렵": 354,
"렷": 355,
"렸": 356,
"령": 357,
"례": 358,
"로": 359,
"록": 360,
"론": 361,
"롬": 362,
"롭": 363,
"롯": 364,
"롱": 365,
"뢰": 366,
"료": 367,
"룡": 368,
"루": 369,
"룩": 370,
"룰": 371,
"룹": 372,
"룻": 373,
"룽": 374,
"류": 375,
"륙": 376,
"륜": 377,
"률": 378,
"륭": 379,
"르": 380,
"른": 381,
"를": 382,
"름": 383,
"릅": 384,
"릇": 385,
"릉": 386,
"릎": 387,
"리": 388,
"린": 389,
"릴": 390,
"림": 391,
"립": 392,
"릿": 393,
"마": 394,
"막": 395,
"만": 396,
"많": 397,
"말": 398,
"맘": 399,
"맙": 400,
"맛": 401,
"망": 402,
"맞": 403,
"맡": 404,
"맣": 405,
"매": 406,
"맥": 407,
"맨": 408,
"맹": 409,
"맺": 410,
"머": 411,
"먹": 412,
"먼": 413,
"멀": 414,
"멈": 415,
"멍": 416,
"멓": 417,
"메": 418,
"멕": 419,
"멘": 420,
"며": 421,
"면": 422,
"멸": 423,
"명": 424,
"몇": 425,
"모": 426,
"목": 427,
"몬": 428,
"몰": 429,
"몸": 430,
"몹": 431,
"못": 432,
"몽": 433,
"묘": 434,
"무": 435,
"묵": 436,
"문": 437,
"묻": 438,
"물": 439,
"뭇": 440,
"뭉": 441,
"뭍": 442,
"뭐": 443,
"뭔": 444,
"뭘": 445,
"뮤": 446,
"므": 447,
"미": 448,
"민": 449,
"믿": 450,
"밀": 451,
"밉": 452,
"및": 453,
"밑": 454,
"바": 455,
"박": 456,
"밖": 457,
"반": 458,
"받": 459,
"발": 460,
"밝": 461,
"밤": 462,
"밥": 463,
"밧": 464,
"방": 465,
"밭": 466,
"배": 467,
"백": 468,
"뱀": 469,
"뱁": 470,
"뱃": 471,
"뱄": 472,
"뱅": 473,
"버": 474,
"벅": 475,
"번": 476,
"벌": 477,
"범": 478,
"법": 479,
"벗": 480,
"벙": 481,
"베": 482,
"벤": 483,
"벨": 484,
"벼": 485,
"벽": 486,
"변": 487,
"별": 488,
"볍": 489,
"병": 490,
"볕": 491,
"보": 492,
"복": 493,
"볶": 494,
"본": 495,
"볼": 496,
"봄": 497,
"봅": 498,
"봉": 499,
"봐": 500,
"봤": 501,
"부": 502,
"북": 503,
"분": 504,
"불": 505,
"붉": 506,
"붐": 507,
"붕": 508,
"붙": 509,
"브": 510,
"비": 511,
"빈": 512,
"빌": 513,
"빗": 514,
"빙": 515,
"빚": 516,
"빛": 517,
"빠": 518,
"빡": 519,
"빨": 520,
"빵": 521,
"빼": 522,
"빽": 523,
"뺄": 524,
"뺑": 525,
"뺨": 526,
"뻐": 527,
"뻔": 528,
"뻗": 529,
"뻘": 530,
"뻣": 531,
"뻤": 532,
"뼈": 533,
"뼉": 534,
"뼛": 535,
"뽀": 536,
"뽑": 537,
"뽕": 538,
"뾰": 539,
"뿌": 540,
"뿐": 541,
"뿡": 542,
"쁘": 543,
"쁜": 544,
"쁨": 545,
"삐": 546,
"사": 547,
"삭": 548,
"삯": 549,
"산": 550,
"살": 551,
"삶": 552,
"삼": 553,
"삽": 554,
"삿": 555,
"상": 556,
"새": 557,
"색": 558,
"샘": 559,
"생": 560,
"서": 561,
"석": 562,
"섞": 563,
"선": 564,
"설": 565,
"섬": 566,
"섭": 567,
"섯": 568,
"섰": 569,
"성": 570,
"세": 571,
"센": 572,
"셈": 573,
"셋": 574,
"셔": 575,
"션": 576,
"셨": 577,
"소": 578,
"속": 579,
"손": 580,
"솔": 581,
"솜": 582,
"솟": 583,
"송": 584,
"쇠": 585,
"쇼": 586,
"수": 587,
"숙": 588,
"순": 589,
"술": 590,
"숨": 591,
"숫": 592,
"숭": 593,
"숯": 594,
"쉬": 595,
"쉰": 596,
"쉴": 597,
"쉽": 598,
"스": 599,
"슥": 600,
"슨": 601,
"슬": 602,
"슴": 603,
"습": 604,
"슷": 605,
"승": 606,
"시": 607,
"식": 608,
"신": 609,
"싣": 610,
"실": 611,
"싫": 612,
"심": 613,
"십": 614,
"싯": 615,
"싱": 616,
"싶": 617,
"싸": 618,
"싹": 619,
"쌀": 620,
"쌍": 621,
"쌓": 622,
"써": 623,
"썩": 624,
"썹": 625,
"썼": 626,
"썽": 627,
"쎄": 628,
"쏘": 629,
"쏟": 630,
"쏠": 631,
"쏴": 632,
"쑥": 633,
"쓰": 634,
"쓱": 635,
"쓴": 636,
"쓸": 637,
"씀": 638,
"씌": 639,
"씨": 640,
"씩": 641,
"씬": 642,
"씰": 643,
"씹": 644,
"씻": 645,
"씽": 646,
"아": 647,
"악": 648,
"안": 649,
"앉": 650,
"않": 651,
"알": 652,
"앓": 653,
"암": 654,
"압": 655,
"앗": 656,
"았": 657,
"앙": 658,
"앞": 659,
"애": 660,
"액": 661,
"앤": 662,
"야": 663,
"약": 664,
"얀": 665,
"양": 666,
"얕": 667,
"얗": 668,
"얘": 669,
"어": 670,
"억": 671,
"언": 672,
"얹": 673,
"얻": 674,
"얼": 675,
"얽": 676,
"엄": 677,
"업": 678,
"없": 679,
"엇": 680,
"었": 681,
"엉": 682,
"엌": 683,
"엎": 684,
"에": 685,
"엔": 686,
"엘": 687,
"여": 688,
"역": 689,
"연": 690,
"열": 691,
"엷": 692,
"염": 693,
"였": 694,
"영": 695,
"옆": 696,
"옇": 697,
"예": 698,
"옛": 699,
"오": 700,
"옥": 701,
"온": 702,
"올": 703,
"옮": 704,
"옵": 705,
"옷": 706,
"옹": 707,
"와": 708,
"완": 709,
"왈": 710,
"왔": 711,
"왕": 712,
"왜": 713,
"외": 714,
"요": 715,
"욕": 716,
"용": 717,
"우": 718,
"욱": 719,
"운": 720,
"울": 721,
"움": 722,
"웃": 723,
"웅": 724,
"워": 725,
"원": 726,
"월": 727,
"웠": 728,
"웬": 729,
"위": 730,
"윗": 731,
"유": 732,
"육": 733,
"윤": 734,
"율": 735,
"윷": 736,
"으": 737,
"은": 738,
"을": 739,
"음": 740,
"읍": 741,
"응": 742,
"의": 743,
"이": 744,
"익": 745,
"인": 746,
"일": 747,
"읽": 748,
"잃": 749,
"임": 750,
"입": 751,
"잇": 752,
"있": 753,
"잉": 754,
"잊": 755,
"잎": 756,
"자": 757,
"작": 758,
"잔": 759,
"잖": 760,
"잘": 761,
"잠": 762,
"잡": 763,
"잤": 764,
"장": 765,
"잦": 766,
"재": 767,
"쟁": 768,
"저": 769,
"적": 770,
"전": 771,
"절": 772,
"젊": 773,
"점": 774,
"접": 775,
"젓": 776,
"정": 777,
"젖": 778,
"제": 779,
"젠": 780,
"젯": 781,
"져": 782,
"졌": 783,
"조": 784,
"족": 785,
"존": 786,
"졸": 787,
"좀": 788,
"좁": 789,
"종": 790,
"좋": 791,
"좌": 792,
"죄": 793,
"죠": 794,
"주": 795,
"죽": 796,
"준": 797,
"줄": 798,
"줌": 799,
"줍": 800,
"중": 801,
"줘": 802,
"줬": 803,
"쥐": 804,
"쥔": 805,
"쥠": 806,
"즈": 807,
"즉": 808,
"즐": 809,
"즘": 810,
"증": 811,
"지": 812,
"직": 813,
"진": 814,
"질": 815,
"짐": 816,
"집": 817,
"짓": 818,
"징": 819,
"짖": 820,
"짙": 821,
"짚": 822,
"짜": 823,
"짝": 824,
"짠": 825,
"째": 826,
"쨌": 827,
"쩌": 828,
"쩍": 829,
"쩐": 830,
"쩔": 831,
"쪼": 832,
"쪽": 833,
"쫑": 834,
"쫓": 835,
"쫙": 836,
"쭈": 837,
"쭉": 838,
"쯤": 839,
"찌": 840,
"찍": 841,
"찔": 842,
"찜": 843,
"찡": 844,
"찢": 845,
"찧": 846,
"차": 847,
"착": 848,
"찬": 849,
"찮": 850,
"찰": 851,
"참": 852,
"찻": 853,
"찼": 854,
"창": 855,
"찾": 856,
"채": 857,
"책": 858,
"챘": 859,
"챙": 860,
"처": 861,
"척": 862,
"천": 863,
"철": 864,
"첨": 865,
"첩": 866,
"첫": 867,
"청": 868,
"체": 869,
"쳐": 870,
"쳤": 871,
"초": 872,
"촌": 873,
"총": 874,
"최": 875,
"추": 876,
"축": 877,
"춘": 878,
"출": 879,
"춤": 880,
"충": 881,
"춰": 882,
"취": 883,
"츠": 884,
"측": 885,
"츤": 886,
"츰": 887,
"층": 888,
"치": 889,
"칙": 890,
"친": 891,
"칠": 892,
"침": 893,
"칩": 894,
"칫": 895,
"칭": 896,
"카": 897,
"칵": 898,
"칼": 899,
"캄": 900,
"커": 901,
"컥": 902,
"컨": 903,
"컬": 904,
"컴": 905,
"컷": 906,
"컸": 907,
"케": 908,
"켓": 909,
"켕": 910,
"켜": 911,
"켤": 912,
"켰": 913,
"코": 914,
"콘": 915,
"콧": 916,
"콩": 917,
"쾌": 918,
"쿠": 919,
"쿵": 920,
"쿼": 921,
"퀴": 922,
"크": 923,
"큰": 924,
"클": 925,
"큼": 926,
"키": 927,
"킥": 928,
"킨": 929,
"킬": 930,
"타": 931,
"탁": 932,
"탄": 933,
"탈": 934,
"탐": 935,
"탓": 936,
"탔": 937,
"탕": 938,
"태": 939,
"택": 940,
"탱": 941,
"터": 942,
"턱": 943,
"털": 944,
"텀": 945,
"텅": 946,
"테": 947,
"텐": 948,
"텔": 949,
"템": 950,
"토": 951,
"톨": 952,
"통": 953,
"퇴": 954,
"투": 955,
"툭": 956,
"툼": 957,
"퉁": 958,
"튀": 959,
"트": 960,
"특": 961,
"튼": 962,
"튿": 963,
"틀": 964,
"틈": 965,
"티": 966,
"틴": 967,
"파": 968,
"판": 969,
"팔": 970,
"팠": 971,
"팡": 972,
"팥": 973,
"패": 974,
"팽": 975,
"퍼": 976,
"퍽": 977,
"펄": 978,
"페": 979,
"펴": 980,
"편": 981,
"폈": 982,
"평": 983,
"포": 984,
"폭": 985,
"폰": 986,
"폿": 987,
"표": 988,
"푸": 989,
"푹": 990,
"푼": 991,
"풀": 992,
"품": 993,
"풋": 994,
"풍": 995,
"프": 996,
"픈": 997,
"플": 998,
"픔": 999,
"피": 1000,
"픽": 1001,
"핀": 1002,
"필": 1003,
"핍": 1004,
"핏": 1005,
"핑": 1006,
"하": 1007,
"학": 1008,
"한": 1009,
"할": 1010,
"함": 1011,
"합": 1012,
"항": 1013,
"해": 1014,
"핵": 1015,
"핸": 1016,
"햇": 1017,
"했": 1018,
"행": 1019,
"향": 1020,
"허": 1021,
"헌": 1022,
"헐": 1023,
"험": 1024,
"헛": 1025,
"헤": 1026,
"혀": 1027,
"혁": 1028,
"현": 1029,
"혈": 1030,
"혔": 1031,
"형": 1032,
"혜": 1033,
"호": 1034,
"혹": 1035,
"혼": 1036,
"홀": 1037,
"홋": 1038,
"홍": 1039,
"화": 1040,
"확": 1041,
"환": 1042,
"활": 1043,
"황": 1044,
"홰": 1045,
"홱": 1046,
"횅": 1047,
"회": 1048,
"획": 1049,
"횡": 1050,
"효": 1051,
"후": 1052,
"훈": 1053,
"훌": 1054,
"훑": 1055,
"훔": 1056,
"훤": 1057,
"훨": 1058,
"휘": 1059,
"휙": 1060,
"휩": 1061,
"휴": 1062,
"흉": 1063,
"흐": 1064,
"흑": 1065,
"흔": 1066,
"흗": 1067,
"흘": 1068,
"흙": 1069,
"흠": 1070,
"흡": 1071,
"흥": 1072,
"흩": 1073,
"희": 1074,
"흰": 1075,
"히": 1076,
"힌": 1077,
"힐": 1078,
"힘": 1079
}