Gummybear05's picture
Upload tokenizer
de59df6 verified
raw
history blame
17 kB
{
"(": 1,
")": 2,
":": 3,
"?": 4,
"N": 5,
"P": 6,
"S": 7,
"[PAD]": 1204,
"[UNK]": 1203,
"|": 0,
"": 8,
"가": 9,
"각": 10,
"간": 11,
"갇": 12,
"갈": 13,
"갉": 14,
"감": 15,
"갑": 16,
"값": 17,
"갓": 18,
"갔": 19,
"강": 20,
"갖": 21,
"같": 22,
"개": 23,
"객": 24,
"갠": 25,
"갱": 26,
"갸": 27,
"걀": 28,
"걔": 29,
"거": 30,
"걱": 31,
"건": 32,
"걷": 33,
"걸": 34,
"검": 35,
"겁": 36,
"것": 37,
"겉": 38,
"겊": 39,
"게": 40,
"겐": 41,
"겟": 42,
"겠": 43,
"겨": 44,
"격": 45,
"겪": 46,
"견": 47,
"결": 48,
"겸": 49,
"겹": 50,
"겼": 51,
"경": 52,
"곁": 53,
"계": 54,
"고": 55,
"곡": 56,
"곤": 57,
"곧": 58,
"골": 59,
"곰": 60,
"곱": 61,
"곳": 62,
"공": 63,
"곶": 64,
"과": 65,
"관": 66,
"광": 67,
"괜": 68,
"괭": 69,
"괴": 70,
"굉": 71,
"교": 72,
"구": 73,
"국": 74,
"군": 75,
"굳": 76,
"굴": 77,
"굵": 78,
"굶": 79,
"굽": 80,
"굿": 81,
"궁": 82,
"궂": 83,
"궈": 84,
"권": 85,
"귀": 86,
"귄": 87,
"규": 88,
"균": 89,
"그": 90,
"극": 91,
"근": 92,
"글": 93,
"긁": 94,
"금": 95,
"급": 96,
"긋": 97,
"긍": 98,
"기": 99,
"긴": 100,
"길": 101,
"김": 102,
"깁": 103,
"깃": 104,
"깄": 105,
"깊": 106,
"까": 107,
"깍": 108,
"깐": 109,
"깔": 110,
"깜": 111,
"깝": 112,
"깥": 113,
"깨": 114,
"깬": 115,
"깼": 116,
"꺼": 117,
"꺽": 118,
"껀": 119,
"껌": 120,
"껍": 121,
"껏": 122,
"껑": 123,
"께": 124,
"껴": 125,
"꼈": 126,
"꼬": 127,
"꼭": 128,
"꼼": 129,
"꼽": 130,
"꽁": 131,
"꽂": 132,
"꽃": 133,
"꽝": 134,
"꽤": 135,
"꾀": 136,
"꾸": 137,
"꾹": 138,
"꾼": 139,
"꿀": 140,
"꿈": 141,
"꿉": 142,
"꿍": 143,
"꿔": 144,
"꿨": 145,
"뀌": 146,
"뀐": 147,
"뀔": 148,
"끄": 149,
"끈": 150,
"끊": 151,
"끌": 152,
"끓": 153,
"끔": 154,
"끗": 155,
"끝": 156,
"끼": 157,
"끽": 158,
"낀": 159,
"낄": 160,
"낌": 161,
"나": 162,
"낙": 163,
"낚": 164,
"난": 165,
"날": 166,
"낡": 167,
"남": 168,
"납": 169,
"낫": 170,
"났": 171,
"낭": 172,
"낮": 173,
"낯": 174,
"낳": 175,
"내": 176,
"낸": 177,
"낼": 178,
"냄": 179,
"냈": 180,
"냉": 181,
"냐": 182,
"냥": 183,
"너": 184,
"넉": 185,
"넌": 186,
"널": 187,
"넓": 188,
"넘": 189,
"넣": 190,
"네": 191,
"넷": 192,
"녀": 193,
"녁": 194,
"년": 195,
"념": 196,
"녔": 197,
"녕": 198,
"노": 199,
"녹": 200,
"논": 201,
"놀": 202,
"놈": 203,
"농": 204,
"높": 205,
"놓": 206,
"놔": 207,
"놨": 208,
"뇌": 209,
"뇨": 210,
"누": 211,
"눅": 212,
"눈": 213,
"눌": 214,
"눗": 215,
"눠": 216,
"눴": 217,
"뉘": 218,
"뉴": 219,
"늄": 220,
"느": 221,
"는": 222,
"늘": 223,
"늙": 224,
"능": 225,
"늦": 226,
"늪": 227,
"늬": 228,
"니": 229,
"닌": 230,
"닐": 231,
"님": 232,
"닙": 233,
"닝": 234,
"다": 235,
"닥": 236,
"닦": 237,
"단": 238,
"닫": 239,
"달": 240,
"닭": 241,
"닮": 242,
"담": 243,
"답": 244,
"닷": 245,
"당": 246,
"닿": 247,
"대": 248,
"댁": 249,
"댄": 250,
"댐": 251,
"댕": 252,
"더": 253,
"덕": 254,
"던": 255,
"덜": 256,
"덟": 257,
"덤": 258,
"덥": 259,
"덧": 260,
"덩": 261,
"덮": 262,
"데": 263,
"덴": 264,
"델": 265,
"도": 266,
"독": 267,
"돈": 268,
"돋": 269,
"돌": 270,
"돕": 271,
"돗": 272,
"동": 273,
"돼": 274,
"됐": 275,
"되": 276,
"된": 277,
"될": 278,
"됨": 279,
"됩": 280,
"두": 281,
"둑": 282,
"둔": 283,
"둘": 284,
"둡": 285,
"둥": 286,
"둬": 287,
"뒀": 288,
"뒤": 289,
"뒷": 290,
"드": 291,
"득": 292,
"든": 293,
"듣": 294,
"들": 295,
"듬": 296,
"듯": 297,
"등": 298,
"디": 299,
"딘": 300,
"딜": 301,
"딤": 302,
"딨": 303,
"딩": 304,
"딪": 305,
"따": 306,
"딱": 307,
"딴": 308,
"딸": 309,
"땀": 310,
"땅": 311,
"때": 312,
"땐": 313,
"땜": 314,
"땠": 315,
"땡": 316,
"떠": 317,
"떡": 318,
"떤": 319,
"떨": 320,
"떴": 321,
"떻": 322,
"떼": 323,
"또": 324,
"똑": 325,
"똘": 326,
"똥": 327,
"뚜": 328,
"뚝": 329,
"뚫": 330,
"뛰": 331,
"뜀": 332,
"뜨": 333,
"뜩": 334,
"뜬": 335,
"뜯": 336,
"뜰": 337,
"뜸": 338,
"뜻": 339,
"띄": 340,
"띕": 341,
"띠": 342,
"띵": 343,
"라": 344,
"락": 345,
"란": 346,
"랄": 347,
"람": 348,
"랍": 349,
"랏": 350,
"랐": 351,
"랑": 352,
"랗": 353,
"래": 354,
"랙": 355,
"랜": 356,
"램": 357,
"랩": 358,
"랫": 359,
"랬": 360,
"랭": 361,
"랴": 362,
"략": 363,
"량": 364,
"러": 365,
"럭": 366,
"런": 367,
"럴": 368,
"럼": 369,
"럽": 370,
"럿": 371,
"렀": 372,
"렁": 373,
"렇": 374,
"레": 375,
"렉": 376,
"렌": 377,
"렘": 378,
"려": 379,
"력": 380,
"련": 381,
"렬": 382,
"렴": 383,
"렵": 384,
"렷": 385,
"렸": 386,
"령": 387,
"례": 388,
"로": 389,
"록": 390,
"론": 391,
"롤": 392,
"롭": 393,
"롯": 394,
"롱": 395,
"뢰": 396,
"료": 397,
"루": 398,
"룩": 399,
"룬": 400,
"룰": 401,
"룸": 402,
"룹": 403,
"뤄": 404,
"류": 405,
"륙": 406,
"륜": 407,
"률": 408,
"륨": 409,
"륭": 410,
"르": 411,
"른": 412,
"를": 413,
"름": 414,
"릅": 415,
"릇": 416,
"릉": 417,
"릎": 418,
"리": 419,
"릭": 420,
"린": 421,
"릴": 422,
"림": 423,
"립": 424,
"릿": 425,
"링": 426,
"마": 427,
"막": 428,
"만": 429,
"많": 430,
"말": 431,
"맑": 432,
"맘": 433,
"맙": 434,
"맛": 435,
"망": 436,
"맞": 437,
"맡": 438,
"매": 439,
"맥": 440,
"맨": 441,
"맵": 442,
"맷": 443,
"맹": 444,
"머": 445,
"먹": 446,
"먼": 447,
"멀": 448,
"멈": 449,
"멋": 450,
"멍": 451,
"메": 452,
"멘": 453,
"멜": 454,
"멤": 455,
"멧": 456,
"멩": 457,
"며": 458,
"면": 459,
"멸": 460,
"명": 461,
"몇": 462,
"모": 463,
"목": 464,
"몬": 465,
"몰": 466,
"몸": 467,
"못": 468,
"몽": 469,
"묘": 470,
"무": 471,
"묵": 472,
"묶": 473,
"문": 474,
"묻": 475,
"물": 476,
"뭉": 477,
"뭐": 478,
"뭔": 479,
"뭘": 480,
"뮤": 481,
"므": 482,
"미": 483,
"믹": 484,
"민": 485,
"믿": 486,
"밀": 487,
"밉": 488,
"밌": 489,
"밍": 490,
"밑": 491,
"바": 492,
"박": 493,
"밖": 494,
"반": 495,
"받": 496,
"발": 497,
"밝": 498,
"밟": 499,
"밤": 500,
"밥": 501,
"방": 502,
"밭": 503,
"배": 504,
"백": 505,
"밴": 506,
"밸": 507,
"뱃": 508,
"버": 509,
"벅": 510,
"번": 511,
"벌": 512,
"범": 513,
"법": 514,
"벗": 515,
"베": 516,
"벤": 517,
"벨": 518,
"벳": 519,
"벼": 520,
"벽": 521,
"변": 522,
"별": 523,
"볍": 524,
"병": 525,
"볕": 526,
"보": 527,
"복": 528,
"볶": 529,
"본": 530,
"볼": 531,
"봄": 532,
"봅": 533,
"봇": 534,
"봉": 535,
"봐": 536,
"봤": 537,
"봬": 538,
"뵈": 539,
"부": 540,
"북": 541,
"분": 542,
"불": 543,
"붉": 544,
"붐": 545,
"붓": 546,
"붕": 547,
"붙": 548,
"뷔": 549,
"뷰": 550,
"브": 551,
"블": 552,
"비": 553,
"빅": 554,
"빈": 555,
"빌": 556,
"빔": 557,
"빕": 558,
"빗": 559,
"빙": 560,
"빛": 561,
"빠": 562,
"빡": 563,
"빨": 564,
"빴": 565,
"빵": 566,
"빼": 567,
"빽": 568,
"뺐": 569,
"뺨": 570,
"뻐": 571,
"뻔": 572,
"뻗": 573,
"뻥": 574,
"뼈": 575,
"뼛": 576,
"뽀": 577,
"뽑": 578,
"뽕": 579,
"뾰": 580,
"뿌": 581,
"뿍": 582,
"뿐": 583,
"뿜": 584,
"쁘": 585,
"쁜": 586,
"쁠": 587,
"삐": 588,
"사": 589,
"삭": 590,
"산": 591,
"살": 592,
"삶": 593,
"삼": 594,
"샀": 595,
"상": 596,
"새": 597,
"색": 598,
"샐": 599,
"샘": 600,
"생": 601,
"샤": 602,
"샴": 603,
"샵": 604,
"샷": 605,
"섀": 606,
"서": 607,
"석": 608,
"섞": 609,
"선": 610,
"설": 611,
"섬": 612,
"섭": 613,
"섯": 614,
"섰": 615,
"성": 616,
"세": 617,
"센": 618,
"셀": 619,
"셈": 620,
"셋": 621,
"셔": 622,
"션": 623,
"셨": 624,
"셰": 625,
"소": 626,
"속": 627,
"손": 628,
"솔": 629,
"솜": 630,
"송": 631,
"쇄": 632,
"쇠": 633,
"쇼": 634,
"숍": 635,
"수": 636,
"숙": 637,
"순": 638,
"숟": 639,
"술": 640,
"숨": 641,
"숫": 642,
"숭": 643,
"숯": 644,
"숱": 645,
"쉐": 646,
"쉬": 647,
"쉴": 648,
"쉽": 649,
"슈": 650,
"슐": 651,
"슘": 652,
"스": 653,
"슥": 654,
"슨": 655,
"슬": 656,
"슴": 657,
"습": 658,
"슷": 659,
"승": 660,
"시": 661,
"식": 662,
"신": 663,
"싣": 664,
"실": 665,
"싫": 666,
"심": 667,
"십": 668,
"싱": 669,
"싶": 670,
"싸": 671,
"싹": 672,
"싼": 673,
"쌀": 674,
"쌈": 675,
"쌌": 676,
"쌓": 677,
"쌤": 678,
"써": 679,
"썩": 680,
"썬": 681,
"썰": 682,
"썼": 683,
"쎄": 684,
"쏘": 685,
"쏙": 686,
"쏟": 687,
"쏠": 688,
"쐬": 689,
"쑤": 690,
"쑥": 691,
"쓰": 692,
"쓴": 693,
"쓸": 694,
"씀": 695,
"씁": 696,
"씨": 697,
"씩": 698,
"씬": 699,
"씹": 700,
"씻": 701,
"아": 702,
"악": 703,
"안": 704,
"앉": 705,
"않": 706,
"알": 707,
"앓": 708,
"암": 709,
"압": 710,
"앗": 711,
"았": 712,
"앙": 713,
"앞": 714,
"애": 715,
"액": 716,
"앤": 717,
"앨": 718,
"앱": 719,
"앵": 720,
"야": 721,
"약": 722,
"얀": 723,
"얄": 724,
"얇": 725,
"얌": 726,
"양": 727,
"얘": 728,
"어": 729,
"억": 730,
"언": 731,
"얹": 732,
"얻": 733,
"얼": 734,
"엄": 735,
"업": 736,
"없": 737,
"엇": 738,
"었": 739,
"엉": 740,
"엊": 741,
"엌": 742,
"엎": 743,
"에": 744,
"엑": 745,
"엔": 746,
"엘": 747,
"엠": 748,
"엣": 749,
"엥": 750,
"여": 751,
"역": 752,
"연": 753,
"열": 754,
"염": 755,
"엽": 756,
"엿": 757,
"였": 758,
"영": 759,
"옆": 760,
"예": 761,
"옛": 762,
"오": 763,
"옥": 764,
"온": 765,
"올": 766,
"옮": 767,
"옵": 768,
"옷": 769,
"옹": 770,
"와": 771,
"왁": 772,
"완": 773,
"왓": 774,
"왔": 775,
"왕": 776,
"왜": 777,
"왠": 778,
"외": 779,
"왼": 780,
"요": 781,
"욕": 782,
"용": 783,
"우": 784,
"욱": 785,
"운": 786,
"울": 787,
"움": 788,
"웃": 789,
"웅": 790,
"워": 791,
"웍": 792,
"원": 793,
"월": 794,
"웠": 795,
"웨": 796,
"웬": 797,
"위": 798,
"유": 799,
"육": 800,
"윤": 801,
"율": 802,
"윳": 803,
"융": 804,
"으": 805,
"은": 806,
"을": 807,
"읊": 808,
"음": 809,
"읍": 810,
"응": 811,
"의": 812,
"이": 813,
"익": 814,
"인": 815,
"일": 816,
"읽": 817,
"잃": 818,
"임": 819,
"입": 820,
"잇": 821,
"있": 822,
"잉": 823,
"잊": 824,
"잌": 825,
"잎": 826,
"자": 827,
"작": 828,
"잔": 829,
"잖": 830,
"잘": 831,
"잠": 832,
"잡": 833,
"잣": 834,
"잤": 835,
"장": 836,
"재": 837,
"쟁": 838,
"저": 839,
"적": 840,
"전": 841,
"절": 842,
"젊": 843,
"점": 844,
"접": 845,
"젓": 846,
"정": 847,
"젖": 848,
"제": 849,
"젝": 850,
"젠": 851,
"져": 852,
"졌": 853,
"조": 854,
"족": 855,
"존": 856,
"졸": 857,
"좀": 858,
"좁": 859,
"종": 860,
"좋": 861,
"좌": 862,
"죄": 863,
"죠": 864,
"주": 865,
"죽": 866,
"준": 867,
"줄": 868,
"줌": 869,
"중": 870,
"줘": 871,
"줬": 872,
"쥐": 873,
"즈": 874,
"즉": 875,
"즌": 876,
"즐": 877,
"즘": 878,
"즙": 879,
"증": 880,
"지": 881,
"직": 882,
"진": 883,
"질": 884,
"짐": 885,
"집": 886,
"짓": 887,
"징": 888,
"짚": 889,
"짜": 890,
"짝": 891,
"짧": 892,
"짬": 893,
"짰": 894,
"짱": 895,
"째": 896,
"쨌": 897,
"쨍": 898,
"쩌": 899,
"쩍": 900,
"쩐": 901,
"쩔": 902,
"쩜": 903,
"쩡": 904,
"쪄": 905,
"쪘": 906,
"쪼": 907,
"쪽": 908,
"쫀": 909,
"쫄": 910,
"쫌": 911,
"쫓": 912,
"쫙": 913,
"쬐": 914,
"쭈": 915,
"쭉": 916,
"쭤": 917,
"쯤": 918,
"찌": 919,
"찍": 920,
"찐": 921,
"찔": 922,
"찜": 923,
"찝": 924,
"찢": 925,
"차": 926,
"착": 927,
"찬": 928,
"찮": 929,
"찰": 930,
"참": 931,
"찹": 932,
"찻": 933,
"창": 934,
"찾": 935,
"채": 936,
"책": 937,
"챙": 938,
"챠": 939,
"처": 940,
"척": 941,
"천": 942,
"철": 943,
"첨": 944,
"첫": 945,
"청": 946,
"체": 947,
"쳇": 948,
"쳐": 949,
"쳤": 950,
"초": 951,
"촉": 952,
"촌": 953,
"총": 954,
"촬": 955,
"최": 956,
"추": 957,
"축": 958,
"춘": 959,
"출": 960,
"춤": 961,
"춥": 962,
"춧": 963,
"충": 964,
"춰": 965,
"췄": 966,
"취": 967,
"츄": 968,
"츠": 969,
"측": 970,
"층": 971,
"치": 972,
"칙": 973,
"친": 974,
"칠": 975,
"칡": 976,
"침": 977,
"칫": 978,
"칭": 979,
"카": 980,
"칵": 981,
"칸": 982,
"칼": 983,
"캉": 984,
"캐": 985,
"캔": 986,
"캠": 987,
"캡": 988,
"캬": 989,
"커": 990,
"컥": 991,
"컨": 992,
"컬": 993,
"컴": 994,
"컵": 995,
"컷": 996,
"컸": 997,
"케": 998,
"켓": 999,
"켜": 1000,
"켰": 1001,
"코": 1002,
"콕": 1003,
"콘": 1004,
"콜": 1005,
"콤": 1006,
"콧": 1007,
"콩": 1008,
"쾌": 1009,
"쿄": 1010,
"쿠": 1011,
"쿨": 1012,
"쿽": 1013,
"퀴": 1014,
"큐": 1015,
"큘": 1016,
"크": 1017,
"큰": 1018,
"클": 1019,
"큼": 1020,
"키": 1021,
"킨": 1022,
"킬": 1023,
"킹": 1024,
"타": 1025,
"탁": 1026,
"탄": 1027,
"탈": 1028,
"탐": 1029,
"탑": 1030,
"탓": 1031,
"탔": 1032,
"탕": 1033,
"태": 1034,
"택": 1035,
"탱": 1036,
"터": 1037,
"턱": 1038,
"턴": 1039,
"털": 1040,
"텀": 1041,
"텁": 1042,
"텃": 1043,
"텅": 1044,
"테": 1045,
"텍": 1046,
"텐": 1047,
"텔": 1048,
"템": 1049,
"텨": 1050,
"토": 1051,
"톡": 1052,
"톤": 1053,
"톨": 1054,
"톱": 1055,
"통": 1056,
"퇴": 1057,
"투": 1058,
"툭": 1059,
"툴": 1060,
"퉁": 1061,
"튀": 1062,
"튈": 1063,
"튜": 1064,
"트": 1065,
"특": 1066,
"튼": 1067,
"틀": 1068,
"틈": 1069,
"티": 1070,
"틱": 1071,
"틴": 1072,
"틸": 1073,
"팀": 1074,
"팁": 1075,
"팅": 1076,
"파": 1077,
"팍": 1078,
"팎": 1079,
"판": 1080,
"팔": 1081,
"팟": 1082,
"팠": 1083,
"팡": 1084,
"패": 1085,
"팩": 1086,
"팬": 1087,
"팰": 1088,
"팽": 1089,
"퍼": 1090,
"펄": 1091,
"펍": 1092,
"페": 1093,
"펙": 1094,
"펜": 1095,
"펭": 1096,
"펴": 1097,
"편": 1098,
"펼": 1099,
"폈": 1100,
"평": 1101,
"폐": 1102,
"포": 1103,
"폭": 1104,
"폰": 1105,
"폴": 1106,
"폼": 1107,
"표": 1108,
"푸": 1109,
"푹": 1110,
"푼": 1111,
"풀": 1112,
"품": 1113,
"풍": 1114,
"퓨": 1115,
"프": 1116,
"픈": 1117,
"플": 1118,
"픔": 1119,
"피": 1120,
"픽": 1121,
"핀": 1122,
"필": 1123,
"핏": 1124,
"핑": 1125,
"하": 1126,
"학": 1127,
"한": 1128,
"할": 1129,
"함": 1130,
"합": 1131,
"핫": 1132,
"항": 1133,
"해": 1134,
"핵": 1135,
"핸": 1136,
"햄": 1137,
"햇": 1138,
"했": 1139,
"행": 1140,
"향": 1141,
"허": 1142,
"헌": 1143,
"헐": 1144,
"험": 1145,
"헛": 1146,
"헝": 1147,
"헤": 1148,
"헬": 1149,
"헹": 1150,
"혀": 1151,
"혁": 1152,
"현": 1153,
"혈": 1154,
"협": 1155,
"혔": 1156,
"형": 1157,
"혜": 1158,
"호": 1159,
"혹": 1160,
"혼": 1161,
"홀": 1162,
"홈": 1163,
"홉": 1164,
"홍": 1165,
"화": 1166,
"확": 1167,
"환": 1168,
"활": 1169,
"황": 1170,
"회": 1171,
"획": 1172,
"횟": 1173,
"횡": 1174,
"효": 1175,
"후": 1176,
"훅": 1177,
"훈": 1178,
"훌": 1179,
"훑": 1180,
"훤": 1181,
"훨": 1182,
"훼": 1183,
"휘": 1184,
"휙": 1185,
"휠": 1186,
"휴": 1187,
"흐": 1188,
"흑": 1189,
"흔": 1190,
"흘": 1191,
"흙": 1192,
"흠": 1193,
"흡": 1194,
"흥": 1195,
"흩": 1196,
"희": 1197,
"흰": 1198,
"히": 1199,
"힌": 1200,
"힐": 1201,
"힘": 1202
}