haseong8012's picture
Upload tokenizer
37bdfe2
raw
history blame
17 kB
{
"[PAD]": 1204,
"[UNK]": 1203,
"|": 288,
"가": 171,
"각": 562,
"간": 516,
"갈": 314,
"감": 964,
"갑": 1197,
"값": 1028,
"갓": 948,
"갔": 806,
"강": 693,
"갖": 924,
"같": 155,
"갚": 29,
"개": 1085,
"객": 605,
"갠": 390,
"갤": 600,
"갯": 657,
"갱": 753,
"거": 345,
"걱": 347,
"건": 661,
"걷": 533,
"걸": 858,
"검": 707,
"겁": 722,
"것": 295,
"겉": 1044,
"게": 239,
"겐": 625,
"겟": 1088,
"겠": 736,
"겨": 94,
"격": 890,
"겪": 1168,
"견": 302,
"결": 387,
"겸": 54,
"겹": 565,
"겼": 194,
"경": 752,
"곁": 149,
"계": 961,
"고": 700,
"곡": 989,
"곤": 465,
"곧": 52,
"골": 807,
"곰": 776,
"곱": 650,
"곳": 392,
"공": 926,
"곶": 269,
"과": 1170,
"곽": 868,
"관": 911,
"괄": 224,
"괌": 1073,
"광": 406,
"괘": 992,
"괭": 1134,
"괴": 405,
"굉": 826,
"교": 101,
"구": 356,
"국": 580,
"군": 378,
"굳": 184,
"굴": 331,
"굵": 395,
"굶": 123,
"굽": 653,
"굿": 719,
"궁": 205,
"궈": 532,
"권": 1090,
"궐": 800,
"궤": 318,
"귀": 154,
"규": 647,
"균": 837,
"그": 609,
"극": 460,
"근": 68,
"글": 365,
"금": 652,
"급": 593,
"긋": 337,
"긍": 388,
"기": 1151,
"긴": 551,
"길": 100,
"김": 1,
"깁": 666,
"깃": 522,
"깊": 857,
"까": 678,
"깎": 125,
"깔": 997,
"깝": 453,
"깡": 139,
"깥": 853,
"깨": 497,
"깬": 207,
"꺼": 597,
"껍": 8,
"껏": 196,
"껑": 268,
"께": 960,
"껴": 324,
"꼈": 38,
"꼬": 584,
"꼭": 332,
"꼴": 86,
"꼼": 317,
"꼽": 1156,
"꽁": 963,
"꽂": 1027,
"꽃": 783,
"꽝": 319,
"꽥": 376,
"꾸": 1076,
"꾼": 888,
"꿀": 214,
"꿇": 120,
"꿈": 40,
"꿎": 848,
"꿔": 856,
"꿨": 466,
"꿰": 762,
"뀌": 257,
"뀐": 128,
"끄": 1019,
"끅": 651,
"끈": 45,
"끊": 680,
"끌": 832,
"끓": 489,
"끔": 586,
"끗": 1084,
"끝": 546,
"끼": 350,
"끽": 66,
"낀": 13,
"낌": 25,
"나": 923,
"낙": 579,
"난": 403,
"날": 819,
"낡": 1180,
"남": 259,
"납": 204,
"낫": 56,
"났": 64,
"낭": 810,
"낮": 781,
"낯": 1119,
"낳": 325,
"내": 815,
"낸": 704,
"낼": 616,
"냄": 696,
"냅": 965,
"냇": 534,
"냈": 361,
"냉": 341,
"냐": 370,
"냥": 358,
"너": 513,
"넉": 643,
"넌": 53,
"널": 1132,
"넓": 1052,
"넘": 511,
"넛": 1064,
"넣": 78,
"네": 1062,
"넥": 878,
"넨": 741,
"넷": 1079,
"녀": 441,
"녁": 1111,
"년": 613,
"념": 791,
"녔": 745,
"녕": 1175,
"녘": 953,
"노": 1015,
"녹": 36,
"논": 667,
"놀": 602,
"놈": 1086,
"농": 797,
"높": 864,
"놓": 811,
"놨": 217,
"뇌": 1006,
"뇨": 777,
"뇽": 793,
"누": 866,
"눈": 871,
"눌": 991,
"눠": 606,
"뉜": 4,
"뉴": 328,
"늉": 1160,
"느": 929,
"는": 844,
"늘": 756,
"늠": 718,
"능": 744,
"늦": 340,
"늪": 383,
"늬": 248,
"니": 659,
"닉": 274,
"닌": 202,
"닐": 779,
"님": 1061,
"닙": 483,
"닛": 223,
"닝": 1007,
"다": 473,
"닥": 1183,
"닦": 662,
"단": 1072,
"닫": 617,
"달": 1184,
"닭": 1186,
"닮": 687,
"닳": 930,
"담": 710,
"답": 249,
"닷": 780,
"당": 1101,
"닿": 107,
"대": 936,
"댁": 628,
"댐": 366,
"댓": 321,
"더": 594,
"덕": 481,
"던": 1018,
"덜": 772,
"덟": 437,
"덤": 603,
"덧": 1082,
"덩": 684,
"덫": 260,
"덮": 530,
"데": 1164,
"덴": 141,
"델": 1041,
"뎅": 15,
"뎌": 233,
"도": 554,
"독": 825,
"돈": 1067,
"돋": 705,
"돌": 841,
"돔": 1117,
"돕": 1176,
"돗": 739,
"동": 1083,
"돛": 133,
"돼": 514,
"됐": 459,
"되": 75,
"된": 1032,
"될": 105,
"됨": 17,
"됩": 382,
"두": 591,
"둑": 1126,
"둔": 407,
"둘": 698,
"둠": 108,
"둥": 1166,
"둬": 1159,
"뒀": 21,
"뒤": 446,
"뒷": 782,
"듀": 860,
"드": 908,
"득": 6,
"든": 424,
"듣": 482,
"들": 138,
"듬": 244,
"듭": 768,
"듯": 433,
"등": 189,
"디": 940,
"딘": 520,
"딜": 510,
"딥": 766,
"딨": 646,
"딩": 639,
"딪": 172,
"따": 1011,
"딱": 715,
"딴": 746,
"딸": 1133,
"땀": 0,
"땄": 503,
"땅": 686,
"때": 775,
"땐": 14,
"땠": 373,
"땡": 470,
"떠": 35,
"떡": 230,
"떤": 894,
"떨": 225,
"떴": 1094,
"떻": 913,
"떼": 922,
"뗄": 850,
"또": 817,
"똑": 754,
"똥": 502,
"뚜": 1102,
"뚝": 74,
"뚫": 915,
"뛰": 220,
"뛴": 450,
"뜨": 462,
"뜯": 901,
"뜸": 633,
"뜻": 721,
"띄": 16,
"띔": 1010,
"띠": 711,
"띤": 544,
"띨": 1004,
"띵": 942,
"라": 623,
"락": 1029,
"란": 479,
"랄": 944,
"람": 211,
"랍": 1196,
"랐": 251,
"랑": 469,
"래": 1012,
"랙": 824,
"랜": 59,
"램": 1152,
"랫": 834,
"랬": 1060,
"랭": 148,
"랴": 919,
"략": 612,
"량": 604,
"러": 493,
"럭": 676,
"런": 413,
"럴": 449,
"럼": 104,
"럽": 655,
"렀": 442,
"렁": 336,
"렇": 1021,
"레": 18,
"렉": 113,
"렌": 93,
"렘": 638,
"렛": 411,
"려": 620,
"력": 42,
"련": 49,
"렬": 1123,
"렴": 1040,
"렵": 109,
"렷": 970,
"렸": 182,
"령": 967,
"례": 165,
"로": 162,
"록": 43,
"론": 703,
"롤": 769,
"롬": 279,
"롭": 87,
"롯": 494,
"롱": 697,
"뢰": 596,
"료": 303,
"룡": 972,
"루": 812,
"룬": 599,
"룰": 362,
"룸": 1050,
"룹": 891,
"뤄": 749,
"뤘": 1181,
"뤼": 348,
"류": 132,
"륙": 140,
"륜": 312,
"률": 103,
"륭": 836,
"르": 987,
"륵": 1022,
"른": 414,
"를": 1074,
"름": 713,
"릅": 914,
"릇": 95,
"릉": 998,
"릎": 587,
"리": 939,
"릭": 277,
"린": 203,
"릴": 567,
"림": 1163,
"립": 404,
"릿": 410,
"링": 475,
"마": 1025,
"막": 423,
"만": 342,
"많": 1056,
"맏": 461,
"말": 906,
"맑": 186,
"맘": 690,
"맙": 272,
"맛": 294,
"망": 861,
"맞": 527,
"맡": 542,
"매": 788,
"맥": 626,
"맨": 880,
"맹": 925,
"맺": 1033,
"머": 379,
"먹": 833,
"먼": 802,
"멀": 419,
"멈": 283,
"멋": 786,
"멍": 539,
"메": 273,
"멕": 33,
"멘": 975,
"멜": 946,
"멧": 941,
"며": 1145,
"면": 440,
"멸": 255,
"명": 988,
"몇": 877,
"모": 179,
"목": 1039,
"몫": 757,
"몬": 487,
"몰": 76,
"몸": 480,
"못": 240,
"몽": 778,
"묘": 391,
"무": 243,
"묵": 498,
"묶": 556,
"문": 491,
"묻": 435,
"물": 796,
"뭄": 577,
"뭇": 96,
"뭐": 760,
"뭔": 90,
"뭘": 570,
"뮤": 65,
"뮬": 996,
"므": 870,
"믈": 566,
"미": 729,
"믹": 150,
"민": 681,
"믿": 20,
"밀": 367,
"밋": 855,
"밌": 999,
"밍": 886,
"및": 153,
"밑": 927,
"바": 192,
"박": 219,
"밖": 976,
"반": 689,
"받": 867,
"발": 193,
"밝": 60,
"밤": 119,
"밥": 84,
"방": 583,
"밭": 568,
"배": 296,
"백": 1100,
"밴": 1141,
"뱀": 9,
"뱃": 71,
"뱅": 706,
"버": 1112,
"벅": 368,
"번": 1069,
"벌": 804,
"범": 771,
"법": 708,
"벗": 112,
"벚": 280,
"베": 701,
"벤": 199,
"벨": 354,
"벳": 792,
"벼": 232,
"벽": 545,
"변": 447,
"별": 499,
"볍": 909,
"볐": 1146,
"병": 789,
"볕": 82,
"보": 682,
"복": 742,
"볶": 126,
"본": 231,
"볼": 1113,
"봄": 1105,
"봅": 1066,
"봇": 57,
"봉": 917,
"봐": 912,
"봤": 895,
"뵈": 1035,
"뵙": 714,
"부": 1157,
"북": 619,
"분": 770,
"불": 921,
"붉": 195,
"붐": 177,
"붓": 500,
"붕": 830,
"붙": 357,
"뷔": 874,
"뷰": 823,
"브": 31,
"븐": 478,
"블": 488,
"비": 910,
"빅": 1118,
"빈": 829,
"빌": 271,
"빗": 145,
"빙": 1202,
"빚": 798,
"빛": 541,
"빠": 1030,
"빨": 55,
"빵": 380,
"빼": 147,
"뺀": 1114,
"뺌": 1020,
"뺏": 501,
"뺑": 144,
"뻐": 397,
"뻑": 589,
"뻔": 455,
"뻗": 50,
"뻘": 246,
"뼈": 114,
"뽀": 1121,
"뽑": 505,
"뽕": 89,
"뿌": 242,
"뿐": 1031,
"뿜": 608,
"쁘": 977,
"쁜": 206,
"쁩": 22,
"삐": 560,
"사": 124,
"삭": 375,
"산": 644,
"살": 831,
"삶": 1174,
"삼": 905,
"삽": 343,
"삿": 88,
"샀": 1142,
"상": 688,
"새": 306,
"색": 48,
"샌": 637,
"샐": 561,
"샘": 496,
"생": 1195,
"샤": 111,
"샬": 982,
"샵": 569,
"샷": 159,
"서": 420,
"석": 166,
"섞": 372,
"선": 227,
"섣": 795,
"설": 393,
"섬": 1068,
"섭": 787,
"섯": 110,
"섰": 980,
"성": 444,
"세": 725,
"섹": 338,
"센": 34,
"셀": 46,
"셈": 209,
"셉": 298,
"셋": 1189,
"셔": 1120,
"션": 847,
"셜": 161,
"셨": 281,
"셰": 508,
"소": 266,
"속": 1172,
"손": 399,
"솔": 585,
"솜": 1187,
"솟": 377,
"송": 986,
"솥": 631,
"쇄": 876,
"쇠": 163,
"쇤": 349,
"쇼": 1129,
"숍": 740,
"수": 935,
"숙": 307,
"순": 576,
"술": 118,
"숨": 934,
"숭": 122,
"숲": 282,
"쉬": 1099,
"쉰": 39,
"쉼": 98,
"쉽": 355,
"슈": 418,
"슐": 396,
"스": 201,
"슨": 1143,
"슬": 415,
"슴": 758,
"습": 228,
"슷": 320,
"승": 799,
"시": 77,
"식": 969,
"신": 931,
"실": 572,
"싫": 540,
"심": 748,
"십": 933,
"싱": 656,
"싶": 692,
"싸": 813,
"싹": 773,
"싼": 235,
"쌀": 1048,
"쌈": 58,
"쌌": 344,
"쌍": 716,
"쌓": 1095,
"써": 1130,
"썩": 903,
"썰": 767,
"썼": 428,
"쏘": 1096,
"쏜": 669,
"쏟": 1161,
"쏠": 1158,
"쑤": 889,
"쓰": 790,
"쓴": 672,
"쓸": 63,
"씀": 735,
"씁": 615,
"씌": 685,
"씨": 950,
"씩": 892,
"씬": 978,
"씸": 863,
"씻": 1034,
"아": 439,
"악": 1136,
"안": 966,
"앉": 523,
"않": 170,
"알": 835,
"앓": 1024,
"암": 215,
"압": 627,
"앗": 486,
"았": 72,
"앙": 265,
"앞": 875,
"애": 581,
"액": 430,
"앤": 504,
"앨": 928,
"앱": 335,
"앵": 389,
"야": 127,
"약": 181,
"얇": 400,
"양": 1149,
"얗": 492,
"얘": 457,
"어": 73,
"억": 1057,
"언": 174,
"얹": 536,
"얻": 47,
"얼": 290,
"얽": 1037,
"엄": 381,
"업": 208,
"없": 1148,
"엇": 222,
"었": 270,
"엉": 543,
"엎": 555,
"에": 952,
"엑": 634,
"엔": 920,
"엘": 1104,
"엠": 452,
"엡": 663,
"엣": 339,
"여": 229,
"역": 518,
"연": 873,
"열": 724,
"엷": 3,
"염": 524,
"엽": 299,
"엿": 1093,
"였": 164,
"영": 695,
"옆": 19,
"예": 1080,
"옛": 845,
"오": 156,
"옥": 557,
"온": 264,
"올": 237,
"옮": 176,
"옳": 702,
"옴": 1045,
"옵": 1153,
"옷": 10,
"옹": 129,
"와": 468,
"완": 476,
"왈": 1013,
"왔": 1049,
"왕": 221,
"왜": 993,
"외": 649,
"왼": 326,
"요": 70,
"욕": 531,
"용": 23,
"우": 759,
"욱": 409,
"운": 635,
"울": 683,
"움": 1071,
"웁": 327,
"웃": 143,
"웅": 694,
"워": 846,
"원": 1135,
"월": 1191,
"웠": 750,
"웨": 99,
"웬": 958,
"웹": 574,
"위": 1154,
"윈": 1124,
"윌": 794,
"윗": 26,
"윙": 183,
"유": 550,
"육": 51,
"윤": 763,
"율": 28,
"융": 293,
"으": 1188,
"은": 1087,
"을": 438,
"음": 427,
"읍": 1003,
"응": 575,
"의": 262,
"이": 506,
"익": 611,
"인": 614,
"일": 943,
"읽": 169,
"잃": 351,
"임": 1140,
"입": 412,
"잇": 436,
"있": 828,
"잉": 732,
"잊": 374,
"잎": 37,
"자": 216,
"작": 893,
"잔": 102,
"잖": 899,
"잘": 252,
"잠": 276,
"잡": 640,
"잣": 62,
"장": 743,
"잦": 11,
"재": 1106,
"잭": 1150,
"잰": 947,
"잽": 1171,
"쟁": 1042,
"저": 526,
"적": 12,
"전": 429,
"절": 962,
"젊": 236,
"젋": 954,
"점": 32,
"접": 549,
"젓": 571,
"정": 173,
"젖": 726,
"제": 1047,
"젝": 525,
"젠": 85,
"젤": 117,
"져": 1169,
"젼": 27,
"졌": 882,
"조": 610,
"족": 607,
"존": 1078,
"졸": 304,
"좀": 535,
"좁": 932,
"종": 80,
"좋": 918,
"좌": 761,
"죄": 538,
"죠": 590,
"주": 1075,
"죽": 284,
"준": 902,
"줄": 485,
"줍": 1179,
"중": 622,
"줘": 814,
"줬": 712,
"쥐": 731,
"쥔": 313,
"쥘": 582,
"쥬": 904,
"즈": 839,
"즉": 1023,
"즌": 629,
"즐": 121,
"즘": 1109,
"증": 512,
"지": 1017,
"직": 537,
"진": 323,
"질": 136,
"짊": 226,
"짐": 250,
"집": 431,
"짓": 291,
"징": 180,
"짖": 490,
"짙": 371,
"짚": 1054,
"짜": 827,
"짝": 474,
"짧": 61,
"짬": 1097,
"째": 1147,
"쨌": 660,
"쩌": 956,
"쩍": 1005,
"쩔": 197,
"쩜": 1026,
"쪼": 275,
"쪽": 665,
"쫄": 618,
"쫓": 134,
"쭉": 386,
"쯤": 995,
"찌": 212,
"찍": 558,
"찔": 67,
"찢": 1058,
"찧": 675,
"차": 785,
"착": 945,
"찬": 69,
"찮": 422,
"찰": 851,
"참": 588,
"찻": 699,
"창": 1063,
"찾": 315,
"채": 728,
"책": 135,
"챌": 624,
"챔": 30,
"챙": 198,
"챠": 1190,
"처": 1110,
"척": 363,
"천": 645,
"철": 552,
"첨": 654,
"첩": 2,
"첫": 840,
"청": 261,
"체": 152,
"첸": 289,
"첼": 984,
"쳇": 385,
"쳐": 1115,
"쳤": 253,
"초": 865,
"촉": 1103,
"촌": 808,
"촘": 971,
"촛": 547,
"총": 472,
"촨": 334,
"촬": 200,
"최": 872,
"추": 495,
"축": 7,
"춘": 985,
"출": 158,
"춤": 1177,
"충": 885,
"춰": 564,
"취": 456,
"츠": 727,
"측": 41,
"츰": 218,
"층": 747,
"치": 24,
"칙": 241,
"친": 592,
"칠": 720,
"침": 937,
"칩": 190,
"칫": 116,
"칭": 884,
"카": 898,
"칸": 563,
"칼": 879,
"캉": 1046,
"캐": 822,
"캔": 955,
"캘": 426,
"캠": 854,
"커": 1116,
"컥": 1053,
"컨": 115,
"컫": 818,
"컴": 394,
"컵": 1201,
"컷": 310,
"컸": 1182,
"케": 738,
"켈": 188,
"켐": 573,
"켑": 916,
"켓": 1193,
"켜": 507,
"켰": 1065,
"코": 346,
"콘": 254,
"콜": 1199,
"콤": 1165,
"콥": 352,
"콧": 641,
"콩": 1192,
"쾌": 630,
"쿄": 994,
"쿠": 311,
"쿡": 1001,
"쿨": 842,
"쿼": 421,
"퀴": 1131,
"큐": 267,
"크": 881,
"큰": 1173,
"클": 883,
"큼": 959,
"키": 973,
"킥": 160,
"킨": 843,
"킬": 1091,
"킷": 1038,
"킹": 131,
"타": 130,
"탁": 213,
"탄": 1155,
"탈": 679,
"탐": 432,
"탑": 869,
"탓": 1000,
"탕": 548,
"태": 632,
"택": 467,
"탠": 401,
"탬": 463,
"탱": 821,
"터": 859,
"턱": 464,
"턴": 245,
"털": 408,
"텃": 256,
"텅": 178,
"테": 445,
"텍": 167,
"텐": 175,
"텔": 92,
"템": 774,
"텼": 717,
"토": 887,
"톡": 519,
"톤": 360,
"톨": 658,
"톰": 598,
"통": 369,
"퇴": 1167,
"투": 329,
"툴": 5,
"툼": 1092,
"퉁": 238,
"튀": 671,
"튜": 79,
"튬": 809,
"트": 1002,
"특": 509,
"튼": 1137,
"튿": 106,
"틀": 1016,
"틈": 838,
"티": 364,
"틱": 359,
"틴": 1162,
"틸": 471,
"팀": 820,
"팅": 137,
"파": 443,
"팍": 322,
"팎": 1081,
"판": 896,
"팔": 434,
"팜": 957,
"팡": 816,
"패": 1198,
"팩": 168,
"팬": 1051,
"팰": 330,
"팻": 938,
"팽": 416,
"퍼": 333,
"펀": 1089,
"펄": 146,
"펌": 784,
"페": 723,
"펜": 309,
"펠": 521,
"펫": 730,
"펴": 157,
"편": 1059,
"펼": 305,
"폄": 398,
"폈": 1139,
"평": 673,
"폐": 292,
"포": 553,
"폭": 454,
"폰": 301,
"폴": 709,
"폼": 448,
"표": 983,
"푸": 1128,
"푹": 755,
"푼": 1098,
"풀": 1108,
"품": 91,
"풋": 636,
"풍": 951,
"퓨": 1200,
"퓰": 670,
"프": 691,
"픈": 517,
"플": 1070,
"픔": 515,
"피": 674,
"픽": 648,
"핀": 1138,
"필": 765,
"핏": 968,
"핑": 44,
"하": 981,
"학": 979,
"한": 733,
"할": 990,
"함": 803,
"합": 1185,
"핫": 402,
"항": 417,
"해": 805,
"핵": 425,
"핸": 477,
"햇": 451,
"했": 1125,
"행": 234,
"향": 907,
"허": 384,
"헌": 142,
"헐": 1009,
"험": 1014,
"헝": 529,
"헤": 734,
"헨": 801,
"헬": 849,
"헴": 287,
"헷": 528,
"혀": 308,
"혁": 81,
"현": 1036,
"혈": 578,
"혐": 1178,
"협": 297,
"혔": 185,
"형": 263,
"혜": 1127,
"호": 1194,
"혹": 974,
"혼": 621,
"홀": 764,
"홈": 897,
"홉": 83,
"홍": 642,
"화": 278,
"확": 1144,
"환": 900,
"활": 1043,
"황": 664,
"회": 187,
"획": 862,
"횡": 1107,
"효": 668,
"후": 353,
"훈": 1122,
"훌": 151,
"훤": 737,
"훨": 258,
"훼": 97,
"휘": 316,
"휩": 210,
"휴": 852,
"흉": 285,
"흐": 1055,
"흑": 677,
"흔": 484,
"흘": 247,
"흙": 559,
"흠": 458,
"흡": 601,
"흥": 300,
"흩": 286,
"희": 1008,
"흰": 751,
"히": 595,
"힌": 949,
"힐": 1077,
"힘": 191
}