jw4169's picture
Upload tokenizer
72dbf6b
raw
history blame
17 kB
{
"[PAD]": 1204,
"[UNK]": 1203,
"|": 859,
"가": 26,
"각": 433,
"간": 656,
"갈": 488,
"감": 615,
"갑": 750,
"값": 377,
"갓": 799,
"갔": 459,
"강": 478,
"갖": 122,
"같": 1122,
"갚": 255,
"개": 584,
"객": 1054,
"갠": 803,
"갤": 694,
"갯": 1035,
"갱": 114,
"거": 780,
"걱": 330,
"건": 848,
"걷": 602,
"걸": 299,
"검": 654,
"겁": 769,
"것": 104,
"겉": 311,
"게": 980,
"겐": 647,
"겟": 121,
"겠": 594,
"겨": 527,
"격": 422,
"겪": 45,
"견": 1123,
"결": 89,
"겸": 471,
"겹": 354,
"겼": 543,
"경": 158,
"곁": 986,
"계": 1137,
"고": 261,
"곡": 466,
"곤": 172,
"곧": 1134,
"골": 905,
"곰": 1199,
"곱": 508,
"곳": 402,
"공": 1012,
"곶": 293,
"과": 918,
"곽": 903,
"관": 741,
"괄": 699,
"괌": 473,
"광": 47,
"괘": 912,
"괭": 74,
"괴": 1065,
"굉": 52,
"교": 53,
"구": 805,
"국": 167,
"군": 1132,
"굳": 212,
"굴": 1147,
"굵": 1133,
"굶": 332,
"굽": 823,
"굿": 105,
"궁": 19,
"궈": 87,
"권": 920,
"궐": 484,
"궤": 179,
"귀": 153,
"규": 1116,
"균": 1153,
"그": 469,
"극": 914,
"근": 125,
"글": 554,
"금": 707,
"급": 981,
"긋": 778,
"긍": 360,
"기": 35,
"긴": 725,
"길": 995,
"김": 827,
"깁": 400,
"깃": 109,
"깊": 2,
"까": 1094,
"깎": 1026,
"깔": 692,
"깝": 40,
"깡": 636,
"깥": 1163,
"깨": 624,
"깬": 213,
"꺼": 951,
"껍": 324,
"껏": 693,
"껑": 996,
"께": 234,
"껴": 697,
"꼈": 451,
"꼬": 994,
"꼭": 968,
"꼴": 1193,
"꼼": 1007,
"꼽": 432,
"꽁": 399,
"꽂": 305,
"꽃": 599,
"꽝": 825,
"꽥": 894,
"꾸": 960,
"꾼": 1066,
"꿀": 1151,
"꿇": 1159,
"꿈": 628,
"꿎": 195,
"꿔": 301,
"꿨": 141,
"꿰": 916,
"뀌": 772,
"뀐": 455,
"끄": 781,
"끅": 397,
"끈": 955,
"끊": 1042,
"끌": 241,
"끓": 391,
"끔": 506,
"끗": 39,
"끝": 706,
"끼": 588,
"끽": 43,
"낀": 1010,
"낌": 1090,
"나": 552,
"낙": 625,
"난": 56,
"날": 861,
"낡": 698,
"남": 253,
"납": 589,
"낫": 575,
"났": 793,
"낭": 585,
"낮": 684,
"낯": 653,
"낳": 123,
"내": 786,
"낸": 249,
"낼": 100,
"냄": 460,
"냅": 798,
"냇": 1053,
"냈": 956,
"냉": 77,
"냐": 544,
"냥": 950,
"너": 910,
"넉": 1126,
"넌": 21,
"널": 604,
"넓": 1150,
"넘": 1160,
"넛": 1119,
"넣": 119,
"네": 965,
"넥": 66,
"넨": 417,
"넷": 81,
"녀": 418,
"녁": 618,
"년": 670,
"념": 1107,
"녔": 773,
"녕": 458,
"녘": 560,
"노": 637,
"녹": 61,
"논": 244,
"놀": 282,
"놈": 252,
"농": 328,
"높": 1124,
"놓": 809,
"놨": 495,
"뇌": 368,
"뇨": 181,
"뇽": 842,
"누": 438,
"눈": 274,
"눌": 521,
"눠": 881,
"뉜": 146,
"뉴": 947,
"늉": 1128,
"느": 110,
"는": 227,
"늘": 1073,
"늠": 314,
"능": 292,
"늦": 267,
"늪": 1024,
"늬": 214,
"니": 648,
"닉": 925,
"닌": 383,
"닐": 822,
"님": 970,
"닙": 1105,
"닛": 161,
"닝": 240,
"다": 962,
"닥": 265,
"닦": 34,
"단": 1104,
"닫": 902,
"달": 28,
"닭": 474,
"닮": 814,
"닳": 337,
"담": 759,
"답": 103,
"닷": 572,
"당": 1111,
"닿": 592,
"대": 375,
"댁": 207,
"댐": 617,
"댓": 1034,
"더": 1014,
"덕": 79,
"던": 200,
"덜": 306,
"덟": 78,
"덤": 90,
"덧": 1202,
"덩": 662,
"덫": 1146,
"덮": 411,
"데": 171,
"덴": 997,
"델": 51,
"뎅": 882,
"뎌": 811,
"도": 590,
"독": 376,
"돈": 366,
"돋": 767,
"돌": 860,
"돔": 307,
"돕": 908,
"돗": 419,
"동": 457,
"돛": 1171,
"돼": 1084,
"됐": 1129,
"되": 733,
"된": 318,
"될": 1028,
"됨": 1079,
"됩": 631,
"두": 761,
"둑": 574,
"둔": 440,
"둘": 132,
"둠": 450,
"둥": 863,
"둬": 1191,
"뒀": 414,
"뒤": 164,
"뒷": 135,
"듀": 1103,
"드": 755,
"득": 349,
"든": 669,
"듣": 756,
"들": 586,
"듬": 523,
"듭": 942,
"듯": 846,
"등": 329,
"디": 762,
"딘": 1002,
"딜": 984,
"딥": 345,
"딨": 1063,
"딩": 657,
"딪": 80,
"따": 675,
"딱": 634,
"딴": 202,
"딸": 1097,
"땀": 8,
"땄": 685,
"땅": 437,
"때": 465,
"땐": 509,
"땠": 982,
"땡": 868,
"떠": 113,
"떡": 937,
"떤": 412,
"떨": 696,
"떴": 736,
"떻": 1018,
"떼": 751,
"뗄": 1155,
"또": 189,
"똑": 528,
"똥": 228,
"뚜": 390,
"뚝": 973,
"뚫": 893,
"뛰": 783,
"뛴": 219,
"뜨": 967,
"뜯": 888,
"뜸": 20,
"뜻": 285,
"띄": 748,
"띔": 958,
"띠": 1183,
"띤": 272,
"띨": 928,
"띵": 386,
"라": 664,
"락": 25,
"란": 344,
"랄": 396,
"람": 487,
"랍": 55,
"랐": 713,
"랑": 524,
"래": 959,
"랙": 170,
"랜": 1089,
"램": 612,
"랫": 496,
"랬": 835,
"랭": 665,
"랴": 134,
"략": 211,
"량": 398,
"러": 4,
"럭": 876,
"런": 341,
"럴": 1052,
"럼": 319,
"럽": 475,
"렀": 936,
"렁": 251,
"렇": 409,
"레": 1179,
"렉": 150,
"렌": 237,
"렘": 890,
"렛": 988,
"려": 853,
"력": 939,
"련": 1177,
"렬": 556,
"렴": 666,
"렵": 632,
"렷": 1029,
"렸": 1059,
"령": 900,
"례": 1143,
"로": 836,
"록": 1039,
"론": 294,
"롤": 1071,
"롬": 1033,
"롭": 27,
"롯": 642,
"롱": 1194,
"뢰": 682,
"료": 605,
"룡": 340,
"루": 198,
"룬": 946,
"룰": 147,
"룸": 215,
"룹": 370,
"뤄": 378,
"뤘": 623,
"뤼": 257,
"류": 456,
"륙": 193,
"륜": 491,
"률": 845,
"륭": 1036,
"르": 5,
"륵": 705,
"른": 485,
"를": 679,
"름": 480,
"릅": 220,
"릇": 1056,
"릉": 790,
"릎": 539,
"리": 931,
"릭": 1117,
"린": 462,
"릴": 435,
"림": 1045,
"립": 102,
"릿": 210,
"링": 891,
"마": 63,
"막": 858,
"만": 738,
"많": 124,
"맏": 23,
"말": 516,
"맑": 380,
"맘": 1087,
"맙": 536,
"맛": 33,
"망": 727,
"맞": 1048,
"맡": 461,
"매": 502,
"맥": 587,
"맨": 806,
"맹": 57,
"맺": 197,
"머": 867,
"먹": 704,
"먼": 334,
"멀": 722,
"멈": 428,
"멋": 144,
"멍": 764,
"메": 703,
"멕": 73,
"멘": 1020,
"멜": 865,
"멧": 75,
"며": 689,
"면": 522,
"멸": 570,
"명": 415,
"몇": 808,
"모": 84,
"목": 313,
"몫": 486,
"몬": 901,
"몰": 281,
"몸": 405,
"못": 659,
"몽": 676,
"묘": 721,
"무": 765,
"묵": 1022,
"묶": 139,
"문": 714,
"묻": 129,
"물": 232,
"뭄": 1162,
"뭇": 355,
"뭐": 309,
"뭔": 3,
"뭘": 754,
"뮤": 1106,
"뮬": 13,
"므": 930,
"믈": 820,
"미": 1092,
"믹": 926,
"민": 163,
"믿": 1030,
"밀": 178,
"밋": 1152,
"밌": 10,
"밍": 816,
"및": 95,
"밑": 88,
"바": 1011,
"박": 262,
"밖": 490,
"반": 1082,
"받": 1004,
"발": 54,
"밝": 674,
"밤": 182,
"밥": 949,
"방": 420,
"밭": 1069,
"배": 277,
"백": 230,
"밴": 935,
"뱀": 595,
"뱃": 601,
"뱅": 627,
"버": 573,
"벅": 97,
"번": 472,
"벌": 497,
"범": 1156,
"법": 1047,
"벗": 482,
"벚": 24,
"베": 785,
"벤": 287,
"벨": 290,
"벳": 217,
"벼": 792,
"벽": 507,
"변": 533,
"별": 351,
"볍": 0,
"볐": 489,
"병": 260,
"볕": 247,
"보": 583,
"복": 291,
"볶": 933,
"본": 192,
"볼": 964,
"봄": 708,
"봅": 131,
"봇": 18,
"봉": 342,
"봐": 441,
"봤": 208,
"뵈": 531,
"뵙": 371,
"부": 254,
"북": 145,
"분": 174,
"불": 564,
"붉": 283,
"붐": 17,
"붓": 941,
"붕": 1176,
"붙": 673,
"뷔": 990,
"뷰": 1136,
"브": 151,
"븐": 1165,
"블": 568,
"비": 763,
"빅": 250,
"빈": 203,
"빌": 169,
"빗": 515,
"빙": 829,
"빚": 1080,
"빛": 606,
"빠": 452,
"빨": 578,
"빵": 856,
"빼": 288,
"뺀": 513,
"뺌": 1154,
"뺏": 620,
"뺑": 978,
"뻐": 1068,
"뻑": 92,
"뻔": 68,
"뻗": 37,
"뻘": 357,
"뼈": 745,
"뽀": 1043,
"뽑": 1187,
"뽕": 423,
"뿌": 537,
"뿐": 69,
"뿜": 1118,
"쁘": 221,
"쁜": 1125,
"쁩": 779,
"삐": 639,
"사": 467,
"삭": 60,
"산": 923,
"살": 597,
"삶": 446,
"삼": 157,
"삽": 977,
"삿": 320,
"샀": 538,
"상": 347,
"새": 1098,
"색": 32,
"샌": 107,
"샐": 622,
"샘": 907,
"생": 802,
"샤": 416,
"샬": 641,
"샵": 159,
"샷": 945,
"서": 166,
"석": 236,
"섞": 1180,
"선": 887,
"섣": 477,
"설": 581,
"섬": 434,
"섭": 273,
"섯": 1046,
"섰": 940,
"성": 503,
"세": 569,
"섹": 1102,
"센": 525,
"셀": 854,
"셈": 535,
"셉": 1095,
"셋": 1157,
"셔": 794,
"션": 735,
"셜": 143,
"셨": 315,
"셰": 165,
"소": 42,
"속": 385,
"손": 718,
"솔": 974,
"솜": 201,
"솟": 957,
"송": 343,
"솥": 1088,
"쇄": 663,
"쇠": 966,
"쇤": 1169,
"쇼": 1149,
"숍": 1200,
"수": 1140,
"숙": 492,
"순": 837,
"술": 323,
"숨": 885,
"숭": 322,
"숲": 728,
"쉬": 162,
"쉰": 353,
"쉼": 644,
"쉽": 833,
"슈": 1050,
"슐": 29,
"스": 427,
"슨": 874,
"슬": 1145,
"슴": 295,
"습": 596,
"슷": 671,
"승": 1032,
"시": 526,
"식": 963,
"신": 1021,
"실": 553,
"싫": 1076,
"심": 381,
"십": 593,
"싱": 857,
"싶": 661,
"싸": 677,
"싹": 1019,
"싼": 626,
"쌀": 635,
"쌈": 1093,
"쌌": 610,
"쌍": 724,
"쌓": 650,
"써": 879,
"썩": 558,
"썰": 303,
"썼": 796,
"쏘": 932,
"쏜": 691,
"쏟": 638,
"쏠": 327,
"쑤": 256,
"쓰": 896,
"쓴": 128,
"쓸": 757,
"씀": 140,
"씁": 1015,
"씌": 740,
"씨": 430,
"씩": 93,
"씬": 429,
"씸": 889,
"씻": 352,
"아": 886,
"악": 36,
"안": 406,
"앉": 866,
"않": 421,
"알": 771,
"앓": 917,
"암": 766,
"압": 289,
"앗": 616,
"았": 758,
"앙": 363,
"앞": 739,
"애": 1013,
"액": 1017,
"앤": 519,
"앨": 582,
"앱": 196,
"앵": 742,
"야": 775,
"약": 611,
"얇": 871,
"양": 1138,
"얗": 797,
"얘": 680,
"어": 1083,
"억": 1060,
"언": 993,
"얹": 512,
"얻": 1173,
"얼": 1072,
"얽": 326,
"엄": 62,
"업": 1101,
"없": 346,
"엇": 510,
"었": 156,
"엉": 824,
"엎": 603,
"에": 804,
"엑": 826,
"엔": 540,
"엘": 1189,
"엠": 70,
"엡": 1190,
"엣": 551,
"여": 975,
"역": 367,
"연": 15,
"열": 904,
"엷": 744,
"염": 1055,
"엽": 813,
"엿": 321,
"였": 870,
"영": 1061,
"옆": 646,
"예": 224,
"옛": 225,
"오": 839,
"옥": 687,
"온": 784,
"올": 49,
"옮": 185,
"옳": 683,
"옴": 613,
"옵": 59,
"옷": 563,
"옹": 598,
"와": 1174,
"완": 111,
"왈": 338,
"왔": 374,
"왕": 715,
"왜": 83,
"외": 921,
"왼": 448,
"요": 86,
"욕": 660,
"용": 410,
"우": 1074,
"욱": 1166,
"운": 216,
"울": 952,
"움": 788,
"웁": 1182,
"웃": 468,
"웅": 1135,
"워": 118,
"원": 731,
"월": 1112,
"웠": 310,
"웨": 1067,
"웬": 1121,
"웹": 67,
"위": 160,
"윈": 1181,
"윌": 1058,
"윗": 550,
"윙": 1051,
"유": 449,
"육": 737,
"윤": 898,
"율": 481,
"융": 268,
"으": 393,
"은": 880,
"을": 173,
"음": 1031,
"읍": 31,
"응": 108,
"의": 927,
"이": 127,
"익": 184,
"인": 817,
"일": 308,
"읽": 843,
"잃": 1023,
"임": 1130,
"입": 1044,
"잇": 233,
"있": 517,
"잉": 777,
"잊": 1142,
"잎": 999,
"자": 1001,
"작": 194,
"잔": 971,
"잖": 205,
"잘": 655,
"잠": 99,
"잡": 239,
"잣": 567,
"장": 276,
"잦": 312,
"재": 972,
"잭": 1167,
"잰": 864,
"잽": 545,
"쟁": 976,
"저": 542,
"적": 743,
"전": 243,
"절": 1081,
"젊": 913,
"젋": 607,
"점": 493,
"접": 720,
"젓": 924,
"정": 532,
"젖": 22,
"제": 1006,
"젝": 897,
"젠": 862,
"젤": 389,
"져": 547,
"젼": 534,
"졌": 576,
"조": 44,
"족": 709,
"존": 851,
"졸": 565,
"좀": 1192,
"좁": 11,
"종": 608,
"좋": 855,
"좌": 500,
"죄": 919,
"죠": 726,
"주": 922,
"죽": 1197,
"준": 1195,
"줄": 832,
"줍": 187,
"중": 1003,
"줘": 579,
"줬": 426,
"쥐": 359,
"쥔": 116,
"쥘": 1158,
"쥬": 204,
"즈": 364,
"즉": 408,
"즌": 136,
"즐": 286,
"즘": 801,
"증": 562,
"지": 640,
"직": 561,
"진": 702,
"질": 384,
"짊": 280,
"짐": 120,
"집": 336,
"짓": 571,
"징": 953,
"짖": 188,
"짙": 700,
"짚": 1170,
"짜": 875,
"짝": 1077,
"짧": 447,
"짬": 369,
"째": 176,
"쨌": 325,
"쩌": 1100,
"쩍": 1064,
"쩔": 621,
"쩜": 938,
"쪼": 828,
"쪽": 442,
"쫄": 64,
"쫓": 600,
"쭉": 849,
"쯤": 362,
"찌": 1037,
"찍": 464,
"찔": 753,
"찢": 206,
"찧": 12,
"차": 934,
"착": 1057,
"찬": 302,
"찮": 557,
"찰": 1099,
"참": 270,
"찻": 1184,
"창": 395,
"찾": 630,
"채": 245,
"책": 404,
"챌": 1198,
"챔": 413,
"챙": 317,
"챠": 555,
"처": 668,
"척": 701,
"천": 424,
"철": 649,
"첨": 1131,
"첩": 1070,
"첫": 501,
"청": 333,
"체": 499,
"첸": 844,
"첼": 348,
"쳇": 7,
"쳐": 388,
"쳤": 1038,
"초": 695,
"촉": 998,
"촌": 821,
"촘": 297,
"촛": 850,
"총": 1115,
"촨": 929,
"촬": 812,
"최": 511,
"추": 1009,
"축": 944,
"춘": 747,
"출": 186,
"춤": 774,
"충": 238,
"춰": 218,
"취": 1078,
"츠": 443,
"측": 425,
"츰": 810,
"층": 710,
"치": 723,
"칙": 372,
"친": 445,
"칠": 1,
"침": 992,
"칩": 989,
"칫": 235,
"칭": 191,
"카": 878,
"칸": 331,
"칼": 284,
"캉": 463,
"캐": 658,
"캔": 732,
"캘": 304,
"캠": 1091,
"커": 1144,
"컥": 869,
"컨": 48,
"컫": 259,
"컴": 943,
"컵": 183,
"컷": 1148,
"컸": 30,
"케": 98,
"켈": 541,
"켐": 1096,
"켑": 190,
"켓": 847,
"켜": 1120,
"켰": 776,
"코": 46,
"콘": 155,
"콜": 65,
"콤": 264,
"콥": 1113,
"콧": 549,
"콩": 180,
"쾌": 609,
"쿄": 734,
"쿠": 819,
"쿡": 830,
"쿨": 729,
"쿼": 559,
"퀴": 1108,
"큐": 782,
"크": 1201,
"큰": 50,
"클": 373,
"큼": 436,
"키": 841,
"킥": 231,
"킨": 58,
"킬": 884,
"킷": 248,
"킹": 431,
"타": 1040,
"탁": 142,
"탄": 358,
"탈": 229,
"탐": 789,
"탑": 643,
"탓": 470,
"탕": 1175,
"태": 71,
"택": 1172,
"탠": 112,
"탬": 1164,
"탱": 651,
"터": 1141,
"턱": 791,
"턴": 883,
"털": 387,
"텃": 591,
"텅": 504,
"테": 807,
"텍": 948,
"텐": 222,
"텔": 94,
"템": 177,
"텼": 209,
"토": 483,
"톡": 505,
"톤": 895,
"톨": 716,
"톰": 672,
"통": 298,
"퇴": 401,
"투": 479,
"툴": 529,
"툼": 242,
"퉁": 688,
"튀": 6,
"튜": 906,
"튬": 1025,
"트": 246,
"특": 619,
"튼": 152,
"튿": 454,
"틀": 961,
"틈": 271,
"티": 514,
"틱": 269,
"틴": 126,
"틸": 476,
"팀": 379,
"팅": 38,
"파": 719,
"팍": 787,
"팎": 899,
"판": 991,
"팔": 365,
"팜": 1168,
"팡": 101,
"패": 909,
"팩": 91,
"팬": 1161,
"팰": 130,
"팻": 133,
"팽": 652,
"퍼": 987,
"펀": 96,
"펄": 834,
"펌": 746,
"페": 768,
"펜": 518,
"펠": 407,
"펫": 838,
"펴": 760,
"편": 1127,
"펼": 969,
"폄": 175,
"폈": 258,
"평": 361,
"폐": 915,
"포": 530,
"폭": 115,
"폰": 629,
"폴": 1062,
"폼": 548,
"표": 168,
"푸": 1185,
"푹": 1027,
"푼": 633,
"풀": 1114,
"품": 439,
"풋": 1188,
"풍": 690,
"퓨": 985,
"퓰": 296,
"프": 1139,
"픈": 350,
"플": 892,
"픔": 9,
"피": 840,
"픽": 199,
"핀": 76,
"필": 717,
"핏": 566,
"핑": 614,
"하": 1178,
"학": 818,
"한": 752,
"할": 795,
"함": 316,
"합": 494,
"핫": 1109,
"항": 339,
"해": 278,
"핵": 16,
"핸": 730,
"햇": 117,
"했": 14,
"행": 154,
"향": 82,
"허": 106,
"헌": 580,
"헐": 266,
"험": 815,
"헝": 72,
"헤": 226,
"헨": 800,
"헬": 1110,
"헴": 279,
"헷": 1008,
"혀": 1049,
"혁": 911,
"현": 1186,
"혈": 546,
"혐": 1041,
"협": 85,
"혔": 749,
"형": 137,
"혜": 577,
"호": 1085,
"혹": 453,
"혼": 686,
"홀": 1005,
"홈": 1016,
"홉": 392,
"홍": 954,
"화": 382,
"확": 300,
"환": 148,
"활": 877,
"황": 263,
"회": 711,
"획": 1000,
"횡": 873,
"효": 678,
"후": 41,
"훈": 1196,
"훌": 149,
"훤": 520,
"훨": 667,
"훼": 138,
"휘": 770,
"휩": 872,
"휴": 712,
"흉": 394,
"흐": 831,
"흑": 645,
"흔": 681,
"흘": 979,
"흙": 444,
"흠": 1086,
"흡": 403,
"흥": 983,
"흩": 335,
"희": 275,
"흰": 356,
"히": 852,
"힌": 498,
"힐": 1075,
"힘": 223
}