Gummybear05's picture
Upload tokenizer
0ae5aaf verified
raw
history blame
16.9 kB
{
"(": 1,
")": 2,
"[PAD]": 1201,
"[UNK]": 1200,
"n": 3,
"p": 4,
"s": 5,
"|": 0,
"가": 6,
"각": 7,
"간": 8,
"갇": 9,
"갈": 10,
"갉": 11,
"감": 12,
"갑": 13,
"값": 14,
"갓": 15,
"갔": 16,
"강": 17,
"갖": 18,
"같": 19,
"개": 20,
"객": 21,
"갠": 22,
"갱": 23,
"갸": 24,
"걀": 25,
"걔": 26,
"거": 27,
"걱": 28,
"건": 29,
"걷": 30,
"걸": 31,
"검": 32,
"겁": 33,
"것": 34,
"겉": 35,
"겊": 36,
"게": 37,
"겐": 38,
"겟": 39,
"겠": 40,
"겨": 41,
"격": 42,
"겪": 43,
"견": 44,
"결": 45,
"겸": 46,
"겹": 47,
"겼": 48,
"경": 49,
"곁": 50,
"계": 51,
"고": 52,
"곡": 53,
"곤": 54,
"곧": 55,
"골": 56,
"곰": 57,
"곱": 58,
"곳": 59,
"공": 60,
"곶": 61,
"과": 62,
"관": 63,
"광": 64,
"괜": 65,
"괭": 66,
"괴": 67,
"굉": 68,
"교": 69,
"구": 70,
"국": 71,
"군": 72,
"굳": 73,
"굴": 74,
"굵": 75,
"굶": 76,
"굽": 77,
"굿": 78,
"궁": 79,
"궂": 80,
"궈": 81,
"권": 82,
"귀": 83,
"귄": 84,
"규": 85,
"균": 86,
"그": 87,
"극": 88,
"근": 89,
"글": 90,
"긁": 91,
"금": 92,
"급": 93,
"긋": 94,
"긍": 95,
"기": 96,
"긴": 97,
"길": 98,
"김": 99,
"깁": 100,
"깃": 101,
"깄": 102,
"깊": 103,
"까": 104,
"깍": 105,
"깐": 106,
"깔": 107,
"깜": 108,
"깝": 109,
"깥": 110,
"깨": 111,
"깬": 112,
"깼": 113,
"꺼": 114,
"꺽": 115,
"껀": 116,
"껌": 117,
"껍": 118,
"껏": 119,
"껑": 120,
"께": 121,
"껴": 122,
"꼈": 123,
"꼬": 124,
"꼭": 125,
"꼼": 126,
"꼽": 127,
"꽁": 128,
"꽂": 129,
"꽃": 130,
"꽝": 131,
"꽤": 132,
"꾀": 133,
"꾸": 134,
"꾹": 135,
"꾼": 136,
"꿀": 137,
"꿈": 138,
"꿉": 139,
"꿍": 140,
"꿔": 141,
"꿨": 142,
"뀌": 143,
"뀐": 144,
"뀔": 145,
"끄": 146,
"끈": 147,
"끊": 148,
"끌": 149,
"끓": 150,
"끔": 151,
"끗": 152,
"끝": 153,
"끼": 154,
"끽": 155,
"낀": 156,
"낄": 157,
"낌": 158,
"나": 159,
"낙": 160,
"낚": 161,
"난": 162,
"날": 163,
"낡": 164,
"남": 165,
"납": 166,
"낫": 167,
"났": 168,
"낭": 169,
"낮": 170,
"낯": 171,
"낳": 172,
"내": 173,
"낸": 174,
"낼": 175,
"냄": 176,
"냈": 177,
"냉": 178,
"냐": 179,
"냥": 180,
"너": 181,
"넉": 182,
"넌": 183,
"널": 184,
"넓": 185,
"넘": 186,
"넣": 187,
"네": 188,
"넷": 189,
"녀": 190,
"녁": 191,
"년": 192,
"념": 193,
"녔": 194,
"녕": 195,
"노": 196,
"녹": 197,
"논": 198,
"놀": 199,
"놈": 200,
"농": 201,
"높": 202,
"놓": 203,
"놔": 204,
"놨": 205,
"뇌": 206,
"뇨": 207,
"누": 208,
"눅": 209,
"눈": 210,
"눌": 211,
"눗": 212,
"눠": 213,
"눴": 214,
"뉘": 215,
"뉴": 216,
"늄": 217,
"느": 218,
"는": 219,
"늘": 220,
"늙": 221,
"능": 222,
"늦": 223,
"늪": 224,
"늬": 225,
"니": 226,
"닌": 227,
"닐": 228,
"님": 229,
"닙": 230,
"닝": 231,
"다": 232,
"닥": 233,
"닦": 234,
"단": 235,
"닫": 236,
"달": 237,
"닭": 238,
"닮": 239,
"담": 240,
"답": 241,
"닷": 242,
"당": 243,
"닿": 244,
"대": 245,
"댁": 246,
"댄": 247,
"댐": 248,
"댕": 249,
"더": 250,
"덕": 251,
"던": 252,
"덜": 253,
"덟": 254,
"덤": 255,
"덥": 256,
"덧": 257,
"덩": 258,
"덮": 259,
"데": 260,
"덴": 261,
"델": 262,
"도": 263,
"독": 264,
"돈": 265,
"돋": 266,
"돌": 267,
"돕": 268,
"돗": 269,
"동": 270,
"돼": 271,
"됐": 272,
"되": 273,
"된": 274,
"될": 275,
"됨": 276,
"됩": 277,
"두": 278,
"둑": 279,
"둔": 280,
"둘": 281,
"둡": 282,
"둥": 283,
"둬": 284,
"뒀": 285,
"뒤": 286,
"뒷": 287,
"드": 288,
"득": 289,
"든": 290,
"듣": 291,
"들": 292,
"듬": 293,
"듯": 294,
"등": 295,
"디": 296,
"딘": 297,
"딜": 298,
"딤": 299,
"딨": 300,
"딩": 301,
"딪": 302,
"따": 303,
"딱": 304,
"딴": 305,
"딸": 306,
"땀": 307,
"땅": 308,
"때": 309,
"땐": 310,
"땜": 311,
"땠": 312,
"땡": 313,
"떠": 314,
"떡": 315,
"떤": 316,
"떨": 317,
"떴": 318,
"떻": 319,
"떼": 320,
"또": 321,
"똑": 322,
"똘": 323,
"똥": 324,
"뚜": 325,
"뚝": 326,
"뚫": 327,
"뛰": 328,
"뜀": 329,
"뜨": 330,
"뜩": 331,
"뜬": 332,
"뜯": 333,
"뜰": 334,
"뜸": 335,
"뜻": 336,
"띄": 337,
"띕": 338,
"띠": 339,
"띵": 340,
"라": 341,
"락": 342,
"란": 343,
"랄": 344,
"람": 345,
"랍": 346,
"랏": 347,
"랐": 348,
"랑": 349,
"랗": 350,
"래": 351,
"랙": 352,
"랜": 353,
"램": 354,
"랩": 355,
"랫": 356,
"랬": 357,
"랭": 358,
"랴": 359,
"략": 360,
"량": 361,
"러": 362,
"럭": 363,
"런": 364,
"럴": 365,
"럼": 366,
"럽": 367,
"럿": 368,
"렀": 369,
"렁": 370,
"렇": 371,
"레": 372,
"렉": 373,
"렌": 374,
"렘": 375,
"려": 376,
"력": 377,
"련": 378,
"렬": 379,
"렴": 380,
"렵": 381,
"렷": 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,
"뤄": 401,
"류": 402,
"륙": 403,
"륜": 404,
"률": 405,
"륨": 406,
"륭": 407,
"르": 408,
"른": 409,
"를": 410,
"름": 411,
"릅": 412,
"릇": 413,
"릉": 414,
"릎": 415,
"리": 416,
"릭": 417,
"린": 418,
"릴": 419,
"림": 420,
"립": 421,
"릿": 422,
"링": 423,
"마": 424,
"막": 425,
"만": 426,
"많": 427,
"말": 428,
"맑": 429,
"맘": 430,
"맙": 431,
"맛": 432,
"망": 433,
"맞": 434,
"맡": 435,
"매": 436,
"맥": 437,
"맨": 438,
"맵": 439,
"맷": 440,
"맹": 441,
"머": 442,
"먹": 443,
"먼": 444,
"멀": 445,
"멈": 446,
"멋": 447,
"멍": 448,
"메": 449,
"멘": 450,
"멜": 451,
"멤": 452,
"멧": 453,
"멩": 454,
"며": 455,
"면": 456,
"멸": 457,
"명": 458,
"몇": 459,
"모": 460,
"목": 461,
"몬": 462,
"몰": 463,
"몸": 464,
"못": 465,
"몽": 466,
"묘": 467,
"무": 468,
"묵": 469,
"묶": 470,
"문": 471,
"묻": 472,
"물": 473,
"뭉": 474,
"뭐": 475,
"뭔": 476,
"뭘": 477,
"뮤": 478,
"므": 479,
"미": 480,
"믹": 481,
"민": 482,
"믿": 483,
"밀": 484,
"밉": 485,
"밌": 486,
"밍": 487,
"밑": 488,
"바": 489,
"박": 490,
"밖": 491,
"반": 492,
"받": 493,
"발": 494,
"밝": 495,
"밟": 496,
"밤": 497,
"밥": 498,
"방": 499,
"밭": 500,
"배": 501,
"백": 502,
"밴": 503,
"밸": 504,
"뱃": 505,
"버": 506,
"벅": 507,
"번": 508,
"벌": 509,
"범": 510,
"법": 511,
"벗": 512,
"베": 513,
"벤": 514,
"벨": 515,
"벳": 516,
"벼": 517,
"벽": 518,
"변": 519,
"별": 520,
"볍": 521,
"병": 522,
"볕": 523,
"보": 524,
"복": 525,
"볶": 526,
"본": 527,
"볼": 528,
"봄": 529,
"봅": 530,
"봇": 531,
"봉": 532,
"봐": 533,
"봤": 534,
"봬": 535,
"뵈": 536,
"부": 537,
"북": 538,
"분": 539,
"불": 540,
"붉": 541,
"붐": 542,
"붓": 543,
"붕": 544,
"붙": 545,
"뷔": 546,
"뷰": 547,
"브": 548,
"블": 549,
"비": 550,
"빅": 551,
"빈": 552,
"빌": 553,
"빔": 554,
"빕": 555,
"빗": 556,
"빙": 557,
"빛": 558,
"빠": 559,
"빡": 560,
"빨": 561,
"빴": 562,
"빵": 563,
"빼": 564,
"빽": 565,
"뺐": 566,
"뺨": 567,
"뻐": 568,
"뻔": 569,
"뻗": 570,
"뻥": 571,
"뼈": 572,
"뼛": 573,
"뽀": 574,
"뽑": 575,
"뽕": 576,
"뾰": 577,
"뿌": 578,
"뿍": 579,
"뿐": 580,
"뿜": 581,
"쁘": 582,
"쁜": 583,
"쁠": 584,
"삐": 585,
"사": 586,
"삭": 587,
"산": 588,
"살": 589,
"삶": 590,
"삼": 591,
"샀": 592,
"상": 593,
"새": 594,
"색": 595,
"샐": 596,
"샘": 597,
"생": 598,
"샤": 599,
"샴": 600,
"샵": 601,
"샷": 602,
"섀": 603,
"서": 604,
"석": 605,
"섞": 606,
"선": 607,
"설": 608,
"섬": 609,
"섭": 610,
"섯": 611,
"섰": 612,
"성": 613,
"세": 614,
"센": 615,
"셀": 616,
"셈": 617,
"셋": 618,
"셔": 619,
"션": 620,
"셨": 621,
"셰": 622,
"소": 623,
"속": 624,
"손": 625,
"솔": 626,
"솜": 627,
"송": 628,
"쇄": 629,
"쇠": 630,
"쇼": 631,
"숍": 632,
"수": 633,
"숙": 634,
"순": 635,
"숟": 636,
"술": 637,
"숨": 638,
"숫": 639,
"숭": 640,
"숯": 641,
"숱": 642,
"쉐": 643,
"쉬": 644,
"쉴": 645,
"쉽": 646,
"슈": 647,
"슐": 648,
"슘": 649,
"스": 650,
"슥": 651,
"슨": 652,
"슬": 653,
"슴": 654,
"습": 655,
"슷": 656,
"승": 657,
"시": 658,
"식": 659,
"신": 660,
"싣": 661,
"실": 662,
"싫": 663,
"심": 664,
"십": 665,
"싱": 666,
"싶": 667,
"싸": 668,
"싹": 669,
"싼": 670,
"쌀": 671,
"쌈": 672,
"쌌": 673,
"쌓": 674,
"쌤": 675,
"써": 676,
"썩": 677,
"썬": 678,
"썰": 679,
"썼": 680,
"쎄": 681,
"쏘": 682,
"쏙": 683,
"쏟": 684,
"쏠": 685,
"쐬": 686,
"쑤": 687,
"쑥": 688,
"쓰": 689,
"쓴": 690,
"쓸": 691,
"씀": 692,
"씁": 693,
"씨": 694,
"씩": 695,
"씬": 696,
"씹": 697,
"씻": 698,
"아": 699,
"악": 700,
"안": 701,
"앉": 702,
"않": 703,
"알": 704,
"앓": 705,
"암": 706,
"압": 707,
"앗": 708,
"았": 709,
"앙": 710,
"앞": 711,
"애": 712,
"액": 713,
"앤": 714,
"앨": 715,
"앱": 716,
"앵": 717,
"야": 718,
"약": 719,
"얀": 720,
"얄": 721,
"얇": 722,
"얌": 723,
"양": 724,
"얘": 725,
"어": 726,
"억": 727,
"언": 728,
"얹": 729,
"얻": 730,
"얼": 731,
"엄": 732,
"업": 733,
"없": 734,
"엇": 735,
"었": 736,
"엉": 737,
"엊": 738,
"엌": 739,
"엎": 740,
"에": 741,
"엑": 742,
"엔": 743,
"엘": 744,
"엠": 745,
"엣": 746,
"엥": 747,
"여": 748,
"역": 749,
"연": 750,
"열": 751,
"염": 752,
"엽": 753,
"엿": 754,
"였": 755,
"영": 756,
"옆": 757,
"예": 758,
"옛": 759,
"오": 760,
"옥": 761,
"온": 762,
"올": 763,
"옮": 764,
"옵": 765,
"옷": 766,
"옹": 767,
"와": 768,
"왁": 769,
"완": 770,
"왓": 771,
"왔": 772,
"왕": 773,
"왜": 774,
"왠": 775,
"외": 776,
"왼": 777,
"요": 778,
"욕": 779,
"용": 780,
"우": 781,
"욱": 782,
"운": 783,
"울": 784,
"움": 785,
"웃": 786,
"웅": 787,
"워": 788,
"웍": 789,
"원": 790,
"월": 791,
"웠": 792,
"웨": 793,
"웬": 794,
"위": 795,
"유": 796,
"육": 797,
"윤": 798,
"율": 799,
"윳": 800,
"융": 801,
"으": 802,
"은": 803,
"을": 804,
"읊": 805,
"음": 806,
"읍": 807,
"응": 808,
"의": 809,
"이": 810,
"익": 811,
"인": 812,
"일": 813,
"읽": 814,
"잃": 815,
"임": 816,
"입": 817,
"잇": 818,
"있": 819,
"잉": 820,
"잊": 821,
"잌": 822,
"잎": 823,
"자": 824,
"작": 825,
"잔": 826,
"잖": 827,
"잘": 828,
"잠": 829,
"잡": 830,
"잣": 831,
"잤": 832,
"장": 833,
"재": 834,
"쟁": 835,
"저": 836,
"적": 837,
"전": 838,
"절": 839,
"젊": 840,
"점": 841,
"접": 842,
"젓": 843,
"정": 844,
"젖": 845,
"제": 846,
"젝": 847,
"젠": 848,
"져": 849,
"졌": 850,
"조": 851,
"족": 852,
"존": 853,
"졸": 854,
"좀": 855,
"좁": 856,
"종": 857,
"좋": 858,
"좌": 859,
"죄": 860,
"죠": 861,
"주": 862,
"죽": 863,
"준": 864,
"줄": 865,
"줌": 866,
"중": 867,
"줘": 868,
"줬": 869,
"쥐": 870,
"즈": 871,
"즉": 872,
"즌": 873,
"즐": 874,
"즘": 875,
"즙": 876,
"증": 877,
"지": 878,
"직": 879,
"진": 880,
"질": 881,
"짐": 882,
"집": 883,
"짓": 884,
"징": 885,
"짚": 886,
"짜": 887,
"짝": 888,
"짧": 889,
"짬": 890,
"짰": 891,
"짱": 892,
"째": 893,
"쨌": 894,
"쨍": 895,
"쩌": 896,
"쩍": 897,
"쩐": 898,
"쩔": 899,
"쩜": 900,
"쩡": 901,
"쪄": 902,
"쪘": 903,
"쪼": 904,
"쪽": 905,
"쫀": 906,
"쫄": 907,
"쫌": 908,
"쫓": 909,
"쫙": 910,
"쬐": 911,
"쭈": 912,
"쭉": 913,
"쭤": 914,
"쯤": 915,
"찌": 916,
"찍": 917,
"찐": 918,
"찔": 919,
"찜": 920,
"찝": 921,
"찢": 922,
"차": 923,
"착": 924,
"찬": 925,
"찮": 926,
"찰": 927,
"참": 928,
"찹": 929,
"찻": 930,
"창": 931,
"찾": 932,
"채": 933,
"책": 934,
"챙": 935,
"챠": 936,
"처": 937,
"척": 938,
"천": 939,
"철": 940,
"첨": 941,
"첫": 942,
"청": 943,
"체": 944,
"쳇": 945,
"쳐": 946,
"쳤": 947,
"초": 948,
"촉": 949,
"촌": 950,
"총": 951,
"촬": 952,
"최": 953,
"추": 954,
"축": 955,
"춘": 956,
"출": 957,
"춤": 958,
"춥": 959,
"춧": 960,
"충": 961,
"춰": 962,
"췄": 963,
"취": 964,
"츄": 965,
"츠": 966,
"측": 967,
"층": 968,
"치": 969,
"칙": 970,
"친": 971,
"칠": 972,
"칡": 973,
"침": 974,
"칫": 975,
"칭": 976,
"카": 977,
"칵": 978,
"칸": 979,
"칼": 980,
"캉": 981,
"캐": 982,
"캔": 983,
"캠": 984,
"캡": 985,
"캬": 986,
"커": 987,
"컥": 988,
"컨": 989,
"컬": 990,
"컴": 991,
"컵": 992,
"컷": 993,
"컸": 994,
"케": 995,
"켓": 996,
"켜": 997,
"켰": 998,
"코": 999,
"콕": 1000,
"콘": 1001,
"콜": 1002,
"콤": 1003,
"콧": 1004,
"콩": 1005,
"쾌": 1006,
"쿄": 1007,
"쿠": 1008,
"쿨": 1009,
"쿽": 1010,
"퀴": 1011,
"큐": 1012,
"큘": 1013,
"크": 1014,
"큰": 1015,
"클": 1016,
"큼": 1017,
"키": 1018,
"킨": 1019,
"킬": 1020,
"킹": 1021,
"타": 1022,
"탁": 1023,
"탄": 1024,
"탈": 1025,
"탐": 1026,
"탑": 1027,
"탓": 1028,
"탔": 1029,
"탕": 1030,
"태": 1031,
"택": 1032,
"탱": 1033,
"터": 1034,
"턱": 1035,
"턴": 1036,
"털": 1037,
"텀": 1038,
"텁": 1039,
"텃": 1040,
"텅": 1041,
"테": 1042,
"텍": 1043,
"텐": 1044,
"텔": 1045,
"템": 1046,
"텨": 1047,
"토": 1048,
"톡": 1049,
"톤": 1050,
"톨": 1051,
"톱": 1052,
"통": 1053,
"퇴": 1054,
"투": 1055,
"툭": 1056,
"툴": 1057,
"퉁": 1058,
"튀": 1059,
"튈": 1060,
"튜": 1061,
"트": 1062,
"특": 1063,
"튼": 1064,
"틀": 1065,
"틈": 1066,
"티": 1067,
"틱": 1068,
"틴": 1069,
"틸": 1070,
"팀": 1071,
"팁": 1072,
"팅": 1073,
"파": 1074,
"팍": 1075,
"팎": 1076,
"판": 1077,
"팔": 1078,
"팟": 1079,
"팠": 1080,
"팡": 1081,
"패": 1082,
"팩": 1083,
"팬": 1084,
"팰": 1085,
"팽": 1086,
"퍼": 1087,
"펄": 1088,
"펍": 1089,
"페": 1090,
"펙": 1091,
"펜": 1092,
"펭": 1093,
"펴": 1094,
"편": 1095,
"펼": 1096,
"폈": 1097,
"평": 1098,
"폐": 1099,
"포": 1100,
"폭": 1101,
"폰": 1102,
"폴": 1103,
"폼": 1104,
"표": 1105,
"푸": 1106,
"푹": 1107,
"푼": 1108,
"풀": 1109,
"품": 1110,
"풍": 1111,
"퓨": 1112,
"프": 1113,
"픈": 1114,
"플": 1115,
"픔": 1116,
"피": 1117,
"픽": 1118,
"핀": 1119,
"필": 1120,
"핏": 1121,
"핑": 1122,
"하": 1123,
"학": 1124,
"한": 1125,
"할": 1126,
"함": 1127,
"합": 1128,
"핫": 1129,
"항": 1130,
"해": 1131,
"핵": 1132,
"핸": 1133,
"햄": 1134,
"햇": 1135,
"했": 1136,
"행": 1137,
"향": 1138,
"허": 1139,
"헌": 1140,
"헐": 1141,
"험": 1142,
"헛": 1143,
"헝": 1144,
"헤": 1145,
"헬": 1146,
"헹": 1147,
"혀": 1148,
"혁": 1149,
"현": 1150,
"혈": 1151,
"협": 1152,
"혔": 1153,
"형": 1154,
"혜": 1155,
"호": 1156,
"혹": 1157,
"혼": 1158,
"홀": 1159,
"홈": 1160,
"홉": 1161,
"홍": 1162,
"화": 1163,
"확": 1164,
"환": 1165,
"활": 1166,
"황": 1167,
"회": 1168,
"획": 1169,
"횟": 1170,
"횡": 1171,
"효": 1172,
"후": 1173,
"훅": 1174,
"훈": 1175,
"훌": 1176,
"훑": 1177,
"훤": 1178,
"훨": 1179,
"훼": 1180,
"휘": 1181,
"휙": 1182,
"휠": 1183,
"휴": 1184,
"흐": 1185,
"흑": 1186,
"흔": 1187,
"흘": 1188,
"흙": 1189,
"흠": 1190,
"흡": 1191,
"흥": 1192,
"흩": 1193,
"희": 1194,
"흰": 1195,
"히": 1196,
"힌": 1197,
"힐": 1198,
"힘": 1199
}