Gummybear05's picture
Upload tokenizer
6b4ea3f verified
raw
history blame
16.9 kB
{
"(": 1,
")": 2,
":": 3,
"?": 4,
"N": 5,
"O": 6,
"P": 7,
"S": 8,
"[PAD]": 1202,
"[UNK]": 1201,
"|": 0,
"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,
"갛": 23,
"개": 24,
"객": 25,
"갠": 26,
"갱": 27,
"갸": 28,
"걀": 29,
"걔": 30,
"거": 31,
"걱": 32,
"건": 33,
"걷": 34,
"걸": 35,
"검": 36,
"겁": 37,
"것": 38,
"겄": 39,
"겉": 40,
"겊": 41,
"게": 42,
"겐": 43,
"겟": 44,
"겠": 45,
"겨": 46,
"격": 47,
"겪": 48,
"견": 49,
"결": 50,
"겸": 51,
"겹": 52,
"겼": 53,
"경": 54,
"곁": 55,
"계": 56,
"고": 57,
"곡": 58,
"곤": 59,
"곧": 60,
"골": 61,
"곰": 62,
"곱": 63,
"곳": 64,
"공": 65,
"곶": 66,
"과": 67,
"관": 68,
"광": 69,
"괜": 70,
"괴": 71,
"굉": 72,
"교": 73,
"구": 74,
"국": 75,
"군": 76,
"굳": 77,
"굴": 78,
"굵": 79,
"굶": 80,
"굽": 81,
"굿": 82,
"궁": 83,
"궈": 84,
"권": 85,
"궐": 86,
"귀": 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,
"깃": 103,
"깄": 104,
"깊": 105,
"까": 106,
"깍": 107,
"깎": 108,
"깐": 109,
"깔": 110,
"깜": 111,
"깝": 112,
"깥": 113,
"깨": 114,
"깬": 115,
"깻": 116,
"깼": 117,
"꺼": 118,
"꺽": 119,
"꺾": 120,
"껀": 121,
"껌": 122,
"껍": 123,
"껑": 124,
"께": 125,
"껴": 126,
"꼈": 127,
"꼬": 128,
"꼭": 129,
"꼼": 130,
"꼽": 131,
"꽁": 132,
"꽂": 133,
"꽃": 134,
"꽝": 135,
"꽤": 136,
"꾀": 137,
"꾸": 138,
"꾹": 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,
"낳": 174,
"내": 175,
"낸": 176,
"낼": 177,
"냄": 178,
"냅": 179,
"냈": 180,
"냉": 181,
"냐": 182,
"냥": 183,
"너": 184,
"넉": 185,
"넌": 186,
"널": 187,
"넓": 188,
"넘": 189,
"넙": 190,
"넣": 191,
"네": 192,
"넷": 193,
"녀": 194,
"녁": 195,
"년": 196,
"념": 197,
"녔": 198,
"녕": 199,
"노": 200,
"녹": 201,
"논": 202,
"놀": 203,
"놈": 204,
"농": 205,
"높": 206,
"놓": 207,
"놔": 208,
"놨": 209,
"뇌": 210,
"뇨": 211,
"누": 212,
"눅": 213,
"눈": 214,
"눌": 215,
"눠": 216,
"눴": 217,
"뉘": 218,
"뉴": 219,
"늄": 220,
"느": 221,
"는": 222,
"늘": 223,
"늙": 224,
"능": 225,
"늦": 226,
"늬": 227,
"니": 228,
"닌": 229,
"닐": 230,
"님": 231,
"닙": 232,
"닝": 233,
"다": 234,
"닥": 235,
"닦": 236,
"단": 237,
"닫": 238,
"달": 239,
"닭": 240,
"닮": 241,
"담": 242,
"답": 243,
"닷": 244,
"당": 245,
"닿": 246,
"대": 247,
"댁": 248,
"댄": 249,
"댐": 250,
"댑": 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,
"뎌": 266,
"도": 267,
"독": 268,
"돈": 269,
"돋": 270,
"돌": 271,
"돕": 272,
"돗": 273,
"동": 274,
"돼": 275,
"됐": 276,
"되": 277,
"된": 278,
"될": 279,
"됨": 280,
"됩": 281,
"두": 282,
"둑": 283,
"둔": 284,
"둘": 285,
"둡": 286,
"둥": 287,
"둬": 288,
"뒀": 289,
"뒤": 290,
"뒷": 291,
"뒹": 292,
"드": 293,
"득": 294,
"든": 295,
"듣": 296,
"들": 297,
"듬": 298,
"듯": 299,
"등": 300,
"디": 301,
"딘": 302,
"딜": 303,
"딨": 304,
"딩": 305,
"딪": 306,
"따": 307,
"딱": 308,
"딴": 309,
"딸": 310,
"땀": 311,
"땅": 312,
"때": 313,
"땐": 314,
"땜": 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,
"뚱": 330,
"뛰": 331,
"뜨": 332,
"뜩": 333,
"뜬": 334,
"뜯": 335,
"뜰": 336,
"뜸": 337,
"뜹": 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,
"렀": 371,
"렁": 372,
"렇": 373,
"레": 374,
"렉": 375,
"렌": 376,
"려": 377,
"력": 378,
"련": 379,
"렬": 380,
"렴": 381,
"렵": 382,
"렸": 383,
"령": 384,
"례": 385,
"로": 386,
"록": 387,
"론": 388,
"롤": 389,
"롭": 390,
"롯": 391,
"롱": 392,
"뢰": 393,
"료": 394,
"루": 395,
"룩": 396,
"룬": 397,
"룰": 398,
"룸": 399,
"룹": 400,
"룻": 401,
"뤄": 402,
"류": 403,
"륙": 404,
"륜": 405,
"률": 406,
"륨": 407,
"륭": 408,
"르": 409,
"른": 410,
"를": 411,
"름": 412,
"릅": 413,
"릇": 414,
"릉": 415,
"릎": 416,
"리": 417,
"릭": 418,
"린": 419,
"릴": 420,
"림": 421,
"립": 422,
"릿": 423,
"링": 424,
"마": 425,
"막": 426,
"만": 427,
"많": 428,
"말": 429,
"맑": 430,
"맘": 431,
"맙": 432,
"맛": 433,
"망": 434,
"맞": 435,
"맡": 436,
"맣": 437,
"매": 438,
"맥": 439,
"맨": 440,
"맵": 441,
"맹": 442,
"맺": 443,
"머": 444,
"먹": 445,
"먼": 446,
"멀": 447,
"멈": 448,
"멋": 449,
"멍": 450,
"메": 451,
"멘": 452,
"멜": 453,
"멤": 454,
"멧": 455,
"멩": 456,
"며": 457,
"면": 458,
"멸": 459,
"명": 460,
"몇": 461,
"모": 462,
"목": 463,
"몬": 464,
"몰": 465,
"몸": 466,
"못": 467,
"몽": 468,
"묘": 469,
"무": 470,
"묵": 471,
"묶": 472,
"문": 473,
"묻": 474,
"물": 475,
"뭇": 476,
"뭉": 477,
"뭐": 478,
"뭔": 479,
"뭘": 480,
"뭡": 481,
"뮤": 482,
"믄": 483,
"미": 484,
"믹": 485,
"민": 486,
"믿": 487,
"밀": 488,
"밉": 489,
"밌": 490,
"밍": 491,
"밑": 492,
"바": 493,
"박": 494,
"밖": 495,
"반": 496,
"받": 497,
"발": 498,
"밝": 499,
"밟": 500,
"밤": 501,
"밥": 502,
"방": 503,
"밭": 504,
"배": 505,
"백": 506,
"밴": 507,
"뱃": 508,
"버": 509,
"벅": 510,
"번": 511,
"벌": 512,
"범": 513,
"법": 514,
"벗": 515,
"벚": 516,
"베": 517,
"벤": 518,
"벨": 519,
"벼": 520,
"벽": 521,
"변": 522,
"별": 523,
"볍": 524,
"볏": 525,
"병": 526,
"볕": 527,
"보": 528,
"복": 529,
"볶": 530,
"본": 531,
"볼": 532,
"봄": 533,
"봇": 534,
"봉": 535,
"봐": 536,
"봤": 537,
"봬": 538,
"뵈": 539,
"부": 540,
"북": 541,
"분": 542,
"불": 543,
"붉": 544,
"붓": 545,
"붕": 546,
"붙": 547,
"뷔": 548,
"뷰": 549,
"브": 550,
"블": 551,
"비": 552,
"빅": 553,
"빈": 554,
"빌": 555,
"빔": 556,
"빕": 557,
"빗": 558,
"빙": 559,
"빛": 560,
"빠": 561,
"빡": 562,
"빨": 563,
"빴": 564,
"빵": 565,
"빼": 566,
"빽": 567,
"뺀": 568,
"뺄": 569,
"뺐": 570,
"뻐": 571,
"뻔": 572,
"뻗": 573,
"뻣": 574,
"뻤": 575,
"뼈": 576,
"뼛": 577,
"뽀": 578,
"뽈": 579,
"뽑": 580,
"뽕": 581,
"뿌": 582,
"뿍": 583,
"뿐": 584,
"뿜": 585,
"쁘": 586,
"쁜": 587,
"쁠": 588,
"삐": 589,
"사": 590,
"삭": 591,
"산": 592,
"살": 593,
"삶": 594,
"삼": 595,
"샀": 596,
"상": 597,
"새": 598,
"색": 599,
"샐": 600,
"샘": 601,
"생": 602,
"샤": 603,
"샵": 604,
"샷": 605,
"서": 606,
"석": 607,
"섞": 608,
"선": 609,
"설": 610,
"섬": 611,
"섭": 612,
"섯": 613,
"섰": 614,
"성": 615,
"세": 616,
"센": 617,
"셀": 618,
"셈": 619,
"셋": 620,
"셔": 621,
"션": 622,
"셜": 623,
"셨": 624,
"셰": 625,
"소": 626,
"속": 627,
"손": 628,
"솔": 629,
"솜": 630,
"솟": 631,
"송": 632,
"솥": 633,
"쇄": 634,
"쇠": 635,
"쇼": 636,
"숍": 637,
"수": 638,
"숙": 639,
"순": 640,
"숟": 641,
"술": 642,
"숨": 643,
"숫": 644,
"숭": 645,
"숯": 646,
"숲": 647,
"쉐": 648,
"쉬": 649,
"쉴": 650,
"쉽": 651,
"슈": 652,
"슐": 653,
"슘": 654,
"스": 655,
"슥": 656,
"슨": 657,
"슬": 658,
"슭": 659,
"슴": 660,
"습": 661,
"슷": 662,
"승": 663,
"시": 664,
"식": 665,
"신": 666,
"싣": 667,
"실": 668,
"싫": 669,
"심": 670,
"십": 671,
"싱": 672,
"싶": 673,
"싸": 674,
"싹": 675,
"싼": 676,
"쌀": 677,
"쌈": 678,
"쌌": 679,
"쌓": 680,
"쌤": 681,
"써": 682,
"썩": 683,
"썬": 684,
"썰": 685,
"썼": 686,
"쎄": 687,
"쏘": 688,
"쏙": 689,
"쏟": 690,
"쏠": 691,
"쑤": 692,
"쑥": 693,
"쓰": 694,
"쓴": 695,
"쓸": 696,
"씀": 697,
"씁": 698,
"씌": 699,
"씨": 700,
"씩": 701,
"씬": 702,
"씹": 703,
"씻": 704,
"아": 705,
"악": 706,
"안": 707,
"앉": 708,
"않": 709,
"알": 710,
"앓": 711,
"암": 712,
"압": 713,
"앗": 714,
"았": 715,
"앙": 716,
"앞": 717,
"애": 718,
"액": 719,
"앤": 720,
"앨": 721,
"앱": 722,
"앵": 723,
"야": 724,
"약": 725,
"얀": 726,
"얄": 727,
"얇": 728,
"얌": 729,
"양": 730,
"얗": 731,
"얘": 732,
"어": 733,
"억": 734,
"언": 735,
"얹": 736,
"얻": 737,
"얼": 738,
"엄": 739,
"업": 740,
"없": 741,
"엇": 742,
"었": 743,
"엉": 744,
"엊": 745,
"엎": 746,
"에": 747,
"엑": 748,
"엔": 749,
"엘": 750,
"엠": 751,
"엥": 752,
"여": 753,
"역": 754,
"엮": 755,
"연": 756,
"열": 757,
"염": 758,
"엽": 759,
"엿": 760,
"였": 761,
"영": 762,
"옆": 763,
"예": 764,
"옛": 765,
"오": 766,
"옥": 767,
"온": 768,
"올": 769,
"옮": 770,
"옵": 771,
"옷": 772,
"옹": 773,
"와": 774,
"왁": 775,
"완": 776,
"왓": 777,
"왔": 778,
"왕": 779,
"왜": 780,
"왠": 781,
"외": 782,
"왼": 783,
"요": 784,
"욕": 785,
"욜": 786,
"용": 787,
"우": 788,
"욱": 789,
"운": 790,
"울": 791,
"움": 792,
"웃": 793,
"웅": 794,
"워": 795,
"웍": 796,
"원": 797,
"월": 798,
"웠": 799,
"웨": 800,
"웬": 801,
"위": 802,
"유": 803,
"육": 804,
"윤": 805,
"율": 806,
"윳": 807,
"융": 808,
"으": 809,
"은": 810,
"을": 811,
"음": 812,
"응": 813,
"의": 814,
"이": 815,
"익": 816,
"인": 817,
"일": 818,
"읽": 819,
"잃": 820,
"임": 821,
"입": 822,
"잇": 823,
"있": 824,
"잉": 825,
"잊": 826,
"잌": 827,
"잎": 828,
"자": 829,
"작": 830,
"잔": 831,
"잖": 832,
"잘": 833,
"잠": 834,
"잡": 835,
"잣": 836,
"잤": 837,
"장": 838,
"재": 839,
"쟁": 840,
"저": 841,
"적": 842,
"전": 843,
"절": 844,
"젊": 845,
"점": 846,
"접": 847,
"젓": 848,
"정": 849,
"젖": 850,
"제": 851,
"젝": 852,
"젠": 853,
"져": 854,
"졌": 855,
"조": 856,
"족": 857,
"존": 858,
"졸": 859,
"좀": 860,
"좁": 861,
"종": 862,
"좋": 863,
"좌": 864,
"죄": 865,
"죠": 866,
"주": 867,
"죽": 868,
"준": 869,
"줄": 870,
"줌": 871,
"중": 872,
"줘": 873,
"줬": 874,
"쥐": 875,
"즈": 876,
"즉": 877,
"즌": 878,
"즐": 879,
"즘": 880,
"즙": 881,
"증": 882,
"지": 883,
"직": 884,
"진": 885,
"질": 886,
"짐": 887,
"집": 888,
"짓": 889,
"징": 890,
"짜": 891,
"짝": 892,
"짠": 893,
"짧": 894,
"짬": 895,
"짰": 896,
"짱": 897,
"째": 898,
"쨌": 899,
"쨍": 900,
"쩌": 901,
"쩍": 902,
"쩔": 903,
"쩜": 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,
"처": 939,
"척": 940,
"천": 941,
"철": 942,
"첨": 943,
"첩": 944,
"첫": 945,
"청": 946,
"체": 947,
"쳐": 948,
"쳤": 949,
"초": 950,
"촉": 951,
"촌": 952,
"총": 953,
"촬": 954,
"최": 955,
"추": 956,
"축": 957,
"춘": 958,
"출": 959,
"춤": 960,
"춥": 961,
"춧": 962,
"충": 963,
"춰": 964,
"췄": 965,
"췌": 966,
"취": 967,
"츄": 968,
"츠": 969,
"측": 970,
"츰": 971,
"층": 972,
"치": 973,
"칙": 974,
"친": 975,
"칠": 976,
"칡": 977,
"침": 978,
"칫": 979,
"칭": 980,
"카": 981,
"칵": 982,
"칸": 983,
"칼": 984,
"캉": 985,
"캐": 986,
"캔": 987,
"캠": 988,
"캡": 989,
"캤": 990,
"캬": 991,
"커": 992,
"컨": 993,
"컬": 994,
"컴": 995,
"컵": 996,
"컷": 997,
"컸": 998,
"케": 999,
"켓": 1000,
"켜": 1001,
"켰": 1002,
"코": 1003,
"콕": 1004,
"콘": 1005,
"콜": 1006,
"콤": 1007,
"콧": 1008,
"콩": 1009,
"쾌": 1010,
"쿠": 1011,
"쿨": 1012,
"쿼": 1013,
"쿽": 1014,
"퀴": 1015,
"큐": 1016,
"큘": 1017,
"크": 1018,
"큰": 1019,
"클": 1020,
"큼": 1021,
"키": 1022,
"킨": 1023,
"킬": 1024,
"킹": 1025,
"타": 1026,
"탁": 1027,
"탄": 1028,
"탈": 1029,
"탐": 1030,
"탑": 1031,
"탓": 1032,
"탔": 1033,
"탕": 1034,
"태": 1035,
"택": 1036,
"탬": 1037,
"탱": 1038,
"터": 1039,
"턱": 1040,
"턴": 1041,
"털": 1042,
"텀": 1043,
"텁": 1044,
"텃": 1045,
"텅": 1046,
"테": 1047,
"텍": 1048,
"텐": 1049,
"텔": 1050,
"템": 1051,
"텨": 1052,
"토": 1053,
"톡": 1054,
"톤": 1055,
"톨": 1056,
"톱": 1057,
"통": 1058,
"퇴": 1059,
"투": 1060,
"툭": 1061,
"툴": 1062,
"퉁": 1063,
"튀": 1064,
"튈": 1065,
"튜": 1066,
"트": 1067,
"특": 1068,
"튼": 1069,
"튿": 1070,
"틀": 1071,
"틈": 1072,
"티": 1073,
"틱": 1074,
"틴": 1075,
"틸": 1076,
"팀": 1077,
"팁": 1078,
"팅": 1079,
"파": 1080,
"팍": 1081,
"팎": 1082,
"판": 1083,
"팔": 1084,
"팠": 1085,
"팡": 1086,
"팥": 1087,
"패": 1088,
"팬": 1089,
"팰": 1090,
"퍼": 1091,
"펄": 1092,
"펌": 1093,
"펍": 1094,
"페": 1095,
"펜": 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,
"피": 1119,
"픽": 1120,
"핀": 1121,
"필": 1122,
"핍": 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,
"훈": 1177,
"훌": 1178,
"훑": 1179,
"훨": 1180,
"훼": 1181,
"휘": 1182,
"휙": 1183,
"휠": 1184,
"휴": 1185,
"흉": 1186,
"흐": 1187,
"흔": 1188,
"흘": 1189,
"흙": 1190,
"흠": 1191,
"흡": 1192,
"흥": 1193,
"흩": 1194,
"희": 1195,
"흰": 1196,
"히": 1197,
"힌": 1198,
"힐": 1199,
"힘": 1200
}