Upload tokenizer
d373b3a | { |
| "[PAD]": 800, |
| "[UNK]": 799, |
| "|": 0, |
| "가": 1, |
| "각": 2, |
| "간": 3, |
| "갈": 4, |
| "감": 5, |
| "갑": 6, |
| "값": 7, |
| "갔": 8, |
| "강": 9, |
| "갖": 10, |
| "같": 11, |
| "개": 12, |
| "객": 13, |
| "걀": 14, |
| "걔": 15, |
| "거": 16, |
| "걱": 17, |
| "건": 18, |
| "걷": 19, |
| "걸": 20, |
| "검": 21, |
| "겁": 22, |
| "것": 23, |
| "게": 24, |
| "겠": 25, |
| "겨": 26, |
| "격": 27, |
| "겪": 28, |
| "결": 29, |
| "겹": 30, |
| "경": 31, |
| "계": 32, |
| "고": 33, |
| "곡": 34, |
| "곤": 35, |
| "골": 36, |
| "곰": 37, |
| "곳": 38, |
| "공": 39, |
| "곶": 40, |
| "과": 41, |
| "관": 42, |
| "광": 43, |
| "괜": 44, |
| "괴": 45, |
| "교": 46, |
| "구": 47, |
| "국": 48, |
| "군": 49, |
| "굳": 50, |
| "굴": 51, |
| "굽": 52, |
| "궁": 53, |
| "궈": 54, |
| "권": 55, |
| "귀": 56, |
| "균": 57, |
| "그": 58, |
| "극": 59, |
| "근": 60, |
| "글": 61, |
| "금": 62, |
| "급": 63, |
| "기": 64, |
| "긴": 65, |
| "길": 66, |
| "김": 67, |
| "깃": 68, |
| "깊": 69, |
| "까": 70, |
| "깐": 71, |
| "깔": 72, |
| "깝": 73, |
| "깨": 74, |
| "깬": 75, |
| "꺼": 76, |
| "껍": 77, |
| "껏": 78, |
| "꼬": 79, |
| "꼭": 80, |
| "꼴": 81, |
| "꽤": 82, |
| "꾸": 83, |
| "꿀": 84, |
| "꿈": 85, |
| "꿍": 86, |
| "뀌": 87, |
| "끄": 88, |
| "끈": 89, |
| "끌": 90, |
| "끓": 91, |
| "끔": 92, |
| "끗": 93, |
| "끝": 94, |
| "끼": 95, |
| "낄": 96, |
| "낌": 97, |
| "나": 98, |
| "낙": 99, |
| "난": 100, |
| "날": 101, |
| "남": 102, |
| "났": 103, |
| "낭": 104, |
| "낮": 105, |
| "낳": 106, |
| "내": 107, |
| "낼": 108, |
| "냄": 109, |
| "냈": 110, |
| "냉": 111, |
| "냐": 112, |
| "냥": 113, |
| "너": 114, |
| "넉": 115, |
| "넌": 116, |
| "널": 117, |
| "넘": 118, |
| "넣": 119, |
| "네": 120, |
| "넷": 121, |
| "녀": 122, |
| "년": 123, |
| "념": 124, |
| "노": 125, |
| "녹": 126, |
| "놀": 127, |
| "놈": 128, |
| "농": 129, |
| "높": 130, |
| "놓": 131, |
| "놨": 132, |
| "뇌": 133, |
| "뇨": 134, |
| "누": 135, |
| "눅": 136, |
| "눈": 137, |
| "뉴": 138, |
| "느": 139, |
| "는": 140, |
| "늘": 141, |
| "늙": 142, |
| "능": 143, |
| "늦": 144, |
| "니": 145, |
| "닌": 146, |
| "닐": 147, |
| "님": 148, |
| "닛": 149, |
| "닝": 150, |
| "다": 151, |
| "닥": 152, |
| "닦": 153, |
| "단": 154, |
| "닫": 155, |
| "달": 156, |
| "닭": 157, |
| "담": 158, |
| "답": 159, |
| "당": 160, |
| "대": 161, |
| "댓": 162, |
| "더": 163, |
| "던": 164, |
| "덟": 165, |
| "덤": 166, |
| "덥": 167, |
| "데": 168, |
| "도": 169, |
| "독": 170, |
| "돈": 171, |
| "돌": 172, |
| "동": 173, |
| "돼": 174, |
| "됐": 175, |
| "되": 176, |
| "된": 177, |
| "될": 178, |
| "두": 179, |
| "둔": 180, |
| "둘": 181, |
| "둬": 182, |
| "뒀": 183, |
| "뒤": 184, |
| "드": 185, |
| "득": 186, |
| "든": 187, |
| "듣": 188, |
| "들": 189, |
| "듬": 190, |
| "듯": 191, |
| "등": 192, |
| "디": 193, |
| "딨": 194, |
| "딪": 195, |
| "따": 196, |
| "딱": 197, |
| "딴": 198, |
| "딸": 199, |
| "땀": 200, |
| "때": 201, |
| "땐": 202, |
| "땜": 203, |
| "떠": 204, |
| "떡": 205, |
| "떤": 206, |
| "떨": 207, |
| "떻": 208, |
| "떼": 209, |
| "또": 210, |
| "똑": 211, |
| "똘": 212, |
| "뚝": 213, |
| "뚫": 214, |
| "뛰": 215, |
| "뜨": 216, |
| "뜩": 217, |
| "뜻": 218, |
| "라": 219, |
| "락": 220, |
| "란": 221, |
| "랄": 222, |
| "람": 223, |
| "랍": 224, |
| "랐": 225, |
| "랑": 226, |
| "래": 227, |
| "랜": 228, |
| "램": 229, |
| "랫": 230, |
| "랬": 231, |
| "량": 232, |
| "러": 233, |
| "런": 234, |
| "럴": 235, |
| "럼": 236, |
| "럽": 237, |
| "렇": 238, |
| "레": 239, |
| "려": 240, |
| "력": 241, |
| "련": 242, |
| "렴": 243, |
| "렸": 244, |
| "령": 245, |
| "로": 246, |
| "록": 247, |
| "론": 248, |
| "롭": 249, |
| "료": 250, |
| "루": 251, |
| "룩": 252, |
| "룰": 253, |
| "룸": 254, |
| "류": 255, |
| "륙": 256, |
| "륨": 257, |
| "륭": 258, |
| "르": 259, |
| "른": 260, |
| "를": 261, |
| "름": 262, |
| "릇": 263, |
| "릎": 264, |
| "리": 265, |
| "린": 266, |
| "릴": 267, |
| "림": 268, |
| "립": 269, |
| "마": 270, |
| "막": 271, |
| "만": 272, |
| "많": 273, |
| "말": 274, |
| "맘": 275, |
| "맛": 276, |
| "망": 277, |
| "맞": 278, |
| "맡": 279, |
| "매": 280, |
| "맥": 281, |
| "맨": 282, |
| "맺": 283, |
| "머": 284, |
| "먹": 285, |
| "먼": 286, |
| "멋": 287, |
| "멍": 288, |
| "메": 289, |
| "며": 290, |
| "면": 291, |
| "명": 292, |
| "몇": 293, |
| "모": 294, |
| "목": 295, |
| "몬": 296, |
| "몰": 297, |
| "몸": 298, |
| "못": 299, |
| "몽": 300, |
| "무": 301, |
| "묶": 302, |
| "문": 303, |
| "묻": 304, |
| "물": 305, |
| "뭐": 306, |
| "뭔": 307, |
| "뭘": 308, |
| "미": 309, |
| "믹": 310, |
| "민": 311, |
| "믿": 312, |
| "밀": 313, |
| "및": 314, |
| "밑": 315, |
| "바": 316, |
| "박": 317, |
| "밖": 318, |
| "반": 319, |
| "받": 320, |
| "발": 321, |
| "밤": 322, |
| "밥": 323, |
| "밧": 324, |
| "방": 325, |
| "밭": 326, |
| "배": 327, |
| "백": 328, |
| "뱃": 329, |
| "버": 330, |
| "번": 331, |
| "벌": 332, |
| "범": 333, |
| "법": 334, |
| "벙": 335, |
| "베": 336, |
| "벼": 337, |
| "변": 338, |
| "별": 339, |
| "병": 340, |
| "볕": 341, |
| "보": 342, |
| "복": 343, |
| "볶": 344, |
| "본": 345, |
| "볼": 346, |
| "봇": 347, |
| "봉": 348, |
| "봐": 349, |
| "봤": 350, |
| "부": 351, |
| "북": 352, |
| "분": 353, |
| "불": 354, |
| "붕": 355, |
| "붙": 356, |
| "뷰": 357, |
| "브": 358, |
| "블": 359, |
| "비": 360, |
| "빅": 361, |
| "빈": 362, |
| "빌": 363, |
| "빔": 364, |
| "빙": 365, |
| "빛": 366, |
| "빠": 367, |
| "빨": 368, |
| "빵": 369, |
| "빼": 370, |
| "뽑": 371, |
| "뽕": 372, |
| "뿌": 373, |
| "뿐": 374, |
| "쁘": 375, |
| "쁜": 376, |
| "사": 377, |
| "삭": 378, |
| "산": 379, |
| "살": 380, |
| "삶": 381, |
| "삼": 382, |
| "삿": 383, |
| "샀": 384, |
| "상": 385, |
| "새": 386, |
| "색": 387, |
| "생": 388, |
| "샵": 389, |
| "서": 390, |
| "석": 391, |
| "섞": 392, |
| "선": 393, |
| "설": 394, |
| "섬": 395, |
| "섭": 396, |
| "성": 397, |
| "세": 398, |
| "센": 399, |
| "셀": 400, |
| "셈": 401, |
| "셔": 402, |
| "셨": 403, |
| "소": 404, |
| "속": 405, |
| "손": 406, |
| "솔": 407, |
| "송": 408, |
| "쇼": 409, |
| "수": 410, |
| "숙": 411, |
| "순": 412, |
| "술": 413, |
| "숭": 414, |
| "숲": 415, |
| "쉐": 416, |
| "쉬": 417, |
| "쉽": 418, |
| "스": 419, |
| "슨": 420, |
| "슬": 421, |
| "슴": 422, |
| "습": 423, |
| "슷": 424, |
| "승": 425, |
| "시": 426, |
| "식": 427, |
| "신": 428, |
| "실": 429, |
| "싫": 430, |
| "심": 431, |
| "십": 432, |
| "싱": 433, |
| "싶": 434, |
| "싸": 435, |
| "싹": 436, |
| "싼": 437, |
| "쌀": 438, |
| "쌓": 439, |
| "써": 440, |
| "썩": 441, |
| "썼": 442, |
| "쎄": 443, |
| "쐬": 444, |
| "쑤": 445, |
| "쑥": 446, |
| "쓰": 447, |
| "쓴": 448, |
| "쓸": 449, |
| "씁": 450, |
| "씨": 451, |
| "씩": 452, |
| "씬": 453, |
| "씻": 454, |
| "씼": 455, |
| "아": 456, |
| "악": 457, |
| "안": 458, |
| "앉": 459, |
| "않": 460, |
| "알": 461, |
| "암": 462, |
| "압": 463, |
| "았": 464, |
| "앞": 465, |
| "애": 466, |
| "액": 467, |
| "앤": 468, |
| "앱": 469, |
| "야": 470, |
| "약": 471, |
| "얄": 472, |
| "양": 473, |
| "얘": 474, |
| "어": 475, |
| "억": 476, |
| "언": 477, |
| "얻": 478, |
| "얼": 479, |
| "엄": 480, |
| "업": 481, |
| "없": 482, |
| "엇": 483, |
| "었": 484, |
| "엉": 485, |
| "에": 486, |
| "엑": 487, |
| "엔": 488, |
| "엘": 489, |
| "엠": 490, |
| "여": 491, |
| "역": 492, |
| "연": 493, |
| "열": 494, |
| "염": 495, |
| "였": 496, |
| "영": 497, |
| "예": 498, |
| "옛": 499, |
| "오": 500, |
| "옥": 501, |
| "온": 502, |
| "올": 503, |
| "옷": 504, |
| "와": 505, |
| "완": 506, |
| "왈": 507, |
| "왔": 508, |
| "왕": 509, |
| "왜": 510, |
| "왠": 511, |
| "외": 512, |
| "요": 513, |
| "욕": 514, |
| "용": 515, |
| "우": 516, |
| "욱": 517, |
| "운": 518, |
| "울": 519, |
| "움": 520, |
| "웃": 521, |
| "웅": 522, |
| "워": 523, |
| "원": 524, |
| "월": 525, |
| "웠": 526, |
| "위": 527, |
| "유": 528, |
| "육": 529, |
| "윤": 530, |
| "율": 531, |
| "으": 532, |
| "은": 533, |
| "을": 534, |
| "음": 535, |
| "응": 536, |
| "의": 537, |
| "이": 538, |
| "익": 539, |
| "인": 540, |
| "일": 541, |
| "읽": 542, |
| "임": 543, |
| "입": 544, |
| "잇": 545, |
| "있": 546, |
| "잎": 547, |
| "자": 548, |
| "작": 549, |
| "잔": 550, |
| "잖": 551, |
| "잘": 552, |
| "잠": 553, |
| "잡": 554, |
| "장": 555, |
| "재": 556, |
| "쟁": 557, |
| "저": 558, |
| "적": 559, |
| "전": 560, |
| "절": 561, |
| "젊": 562, |
| "점": 563, |
| "접": 564, |
| "정": 565, |
| "제": 566, |
| "젠": 567, |
| "져": 568, |
| "졌": 569, |
| "조": 570, |
| "족": 571, |
| "존": 572, |
| "졸": 573, |
| "좀": 574, |
| "좁": 575, |
| "종": 576, |
| "좋": 577, |
| "죄": 578, |
| "죠": 579, |
| "주": 580, |
| "죽": 581, |
| "준": 582, |
| "줄": 583, |
| "중": 584, |
| "줘": 585, |
| "줬": 586, |
| "즈": 587, |
| "즘": 588, |
| "증": 589, |
| "지": 590, |
| "직": 591, |
| "진": 592, |
| "질": 593, |
| "짐": 594, |
| "집": 595, |
| "짓": 596, |
| "징": 597, |
| "짜": 598, |
| "짝": 599, |
| "짠": 600, |
| "짬": 601, |
| "짱": 602, |
| "쨌": 603, |
| "쩌": 604, |
| "쩐": 605, |
| "쩔": 606, |
| "쪼": 607, |
| "쪽": 608, |
| "쫓": 609, |
| "쯤": 610, |
| "찌": 611, |
| "찍": 612, |
| "찜": 613, |
| "찝": 614, |
| "차": 615, |
| "착": 616, |
| "찬": 617, |
| "찮": 618, |
| "찰": 619, |
| "참": 620, |
| "창": 621, |
| "찾": 622, |
| "채": 623, |
| "책": 624, |
| "챙": 625, |
| "처": 626, |
| "척": 627, |
| "천": 628, |
| "철": 629, |
| "첨": 630, |
| "첫": 631, |
| "청": 632, |
| "체": 633, |
| "쳐": 634, |
| "초": 635, |
| "촉": 636, |
| "촌": 637, |
| "촘": 638, |
| "총": 639, |
| "최": 640, |
| "추": 641, |
| "축": 642, |
| "출": 643, |
| "충": 644, |
| "춰": 645, |
| "취": 646, |
| "츠": 647, |
| "측": 648, |
| "층": 649, |
| "치": 650, |
| "친": 651, |
| "칠": 652, |
| "침": 653, |
| "칩": 654, |
| "칫": 655, |
| "칭": 656, |
| "카": 657, |
| "칵": 658, |
| "칼": 659, |
| "캠": 660, |
| "커": 661, |
| "컴": 662, |
| "컵": 663, |
| "컸": 664, |
| "케": 665, |
| "켓": 666, |
| "켜": 667, |
| "코": 668, |
| "콘": 669, |
| "콤": 670, |
| "콧": 671, |
| "콩": 672, |
| "쿄": 673, |
| "퀄": 674, |
| "큐": 675, |
| "크": 676, |
| "큰": 677, |
| "클": 678, |
| "큼": 679, |
| "키": 680, |
| "킨": 681, |
| "킬": 682, |
| "킹": 683, |
| "타": 684, |
| "탁": 685, |
| "탄": 686, |
| "탈": 687, |
| "탑": 688, |
| "탕": 689, |
| "태": 690, |
| "터": 691, |
| "턱": 692, |
| "턴": 693, |
| "텀": 694, |
| "텃": 695, |
| "테": 696, |
| "텐": 697, |
| "토": 698, |
| "톱": 699, |
| "통": 700, |
| "퇴": 701, |
| "투": 702, |
| "튜": 703, |
| "트": 704, |
| "특": 705, |
| "튼": 706, |
| "틀": 707, |
| "티": 708, |
| "틱": 709, |
| "팀": 710, |
| "팅": 711, |
| "파": 712, |
| "판": 713, |
| "팔": 714, |
| "팡": 715, |
| "패": 716, |
| "팩": 717, |
| "퍼": 718, |
| "퍽": 719, |
| "페": 720, |
| "편": 721, |
| "폈": 722, |
| "평": 723, |
| "포": 724, |
| "폭": 725, |
| "폰": 726, |
| "폼": 727, |
| "표": 728, |
| "푸": 729, |
| "푼": 730, |
| "풀": 731, |
| "품": 732, |
| "풋": 733, |
| "풍": 734, |
| "퓨": 735, |
| "프": 736, |
| "픈": 737, |
| "플": 738, |
| "픔": 739, |
| "피": 740, |
| "필": 741, |
| "핑": 742, |
| "하": 743, |
| "학": 744, |
| "한": 745, |
| "할": 746, |
| "함": 747, |
| "합": 748, |
| "항": 749, |
| "해": 750, |
| "핸": 751, |
| "햇": 752, |
| "했": 753, |
| "행": 754, |
| "향": 755, |
| "허": 756, |
| "헌": 757, |
| "험": 758, |
| "헤": 759, |
| "헹": 760, |
| "혀": 761, |
| "현": 762, |
| "혈": 763, |
| "형": 764, |
| "혜": 765, |
| "호": 766, |
| "혹": 767, |
| "혼": 768, |
| "홀": 769, |
| "홈": 770, |
| "홍": 771, |
| "화": 772, |
| "확": 773, |
| "환": 774, |
| "활": 775, |
| "황": 776, |
| "회": 777, |
| "획": 778, |
| "횟": 779, |
| "효": 780, |
| "후": 781, |
| "훅": 782, |
| "훈": 783, |
| "훌": 784, |
| "훨": 785, |
| "휴": 786, |
| "흐": 787, |
| "흔": 788, |
| "흘": 789, |
| "흙": 790, |
| "흠": 791, |
| "흡": 792, |
| "흥": 793, |
| "희": 794, |
| "흰": 795, |
| "히": 796, |
| "힌": 797, |
| "힘": 798 |
| } |
|
|