jaeyeon's picture
add tokenizer
02697c4
{
"[PAD]": 507,
"[UNK]": 506,
"|": 0,
"ใ„ฑ": 1,
"ใ„ด": 2,
"ใ„ท": 3,
"ใ„น": 4,
"ใ…": 5,
"ใ…‚": 6,
"๊ฐ€": 7,
"๊ฐ": 8,
"๊ฐ„": 9,
"๊ฐˆ": 10,
"๊ฐ": 11,
"๊ฐ‘": 12,
"๊ฐ’": 13,
"๊ฐ”": 14,
"๊ฐ•": 15,
"๊ฐ™": 16,
"๊ฐœ": 17,
"๊ฐฏ": 18,
"๊ฑฐ": 19,
"๊ฑด": 20,
"๊ฑธ": 21,
"๊ฒ€": 22,
"๊ฒ": 23,
"๊ฒƒ": 24,
"๊ฒŒ": 25,
"๊ฒ ": 26,
"๊ฒจ": 27,
"๊ฒฐ": 28,
"๊ฒฝ": 29,
"๊ณ„": 30,
"๊ณ ": 31,
"๊ณก": 32,
"๊ณค": 33,
"๊ณจ": 34,
"๊ณฑ": 35,
"๊ณณ": 36,
"๊ณต": 37,
"๊ณผ": 38,
"๊ด€": 39,
"๊ต‰": 40,
"๊ต": 41,
"๊ตฌ": 42,
"๊ตญ": 43,
"๊ตณ": 44,
"๊ถ": 45,
"๊ท€": 46,
"๊ท“": 47,
"๊ทœ": 48,
"๊ทธ": 49,
"๊ทผ": 50,
"๊ทฟ": 51,
"๊ธˆ": 52,
"๊ธ‰": 53,
"๊ธฐ": 54,
"๊ธด": 55,
"๊ธธ": 56,
"๊น€": 57,
"๊นŒ": 58,
"๊น": 59,
"๊นฅ": 60,
"๊บผ": 61,
"๊ป": 62,
"๊ป˜": 63,
"๊ผญ": 64,
"๊ผผ": 65,
"๊พธ": 66,
"๊พผ": 67,
"๊ฟ”": 68,
"๋€Œ": 69,
"๋Š": 70,
"๋“": 71,
"๋": 72,
"๋ผ": 73,
"๋‚˜": 74,
"๋‚œ": 75,
"๋‚ ": 76,
"๋‚ฉ": 77,
"๋‚ซ": 78,
"๋‚ฌ": 79,
"๋‚ฎ": 80,
"๋‚ด": 81,
"๋‚ธ": 82,
"๋‚ผ": 83,
"๋ƒ„": 84,
"๋ƒˆ": 85,
"๋ƒ": 86,
"๋„ˆ": 87,
"๋„ฃ": 88,
"๋„ค": 89,
"๋„ท": 90,
"๋…": 91,
"๋…•": 92,
"๋…น": 93,
"๋†": 94,
"๋†’": 95,
"๋†“": 96,
"๋†จ": 97,
"๋ˆ„": 98,
"๋ˆˆ": 99,
"๋ˆŒ": 100,
"๋Š": 101,
"๋Š”": 102,
"๋Š˜": 103,
"๋‹ˆ": 104,
"๋‹Œ": 105,
"๋‹˜": 106,
"๋‹ค": 107,
"๋‹จ": 108,
"๋‹ฌ": 109,
"๋‹ด": 110,
"๋‹ต": 111,
"๋‹ท": 112,
"๋‹น": 113,
"๋Œ€": 114,
"๋”": 115,
"๋˜": 116,
"๋ฉ": 117,
"๋ฐ": 118,
"๋ธ": 119,
"๋„": 120,
"๋Œ": 121,
"๋™": 122,
"๋ผ": 123,
"๋": 124,
"๋˜": 125,
"๋œ": 126,
"๋ ": 127,
"๋ฉ": 128,
"๋‘": 129,
"๋‘”": 130,
"๋‘˜": 131,
"๋‘ฌ": 132,
"๋’ท": 133,
"๋“œ": 134,
"๋“ ": 135,
"๋“ค": 136,
"๋“ฑ": 137,
"๋””": 138,
"๋”ฐ": 139,
"๋•€": 140,
"๋•Œ": 141,
"๋– ": 142,
"๋–ค": 143,
"๋–จ": 144,
"๋–ป": 145,
"๋˜": 146,
"๋˜‘": 147,
"๋œจ": 148,
"๋œป": 149,
"๋„": 150,
"๋ผ": 151,
"๋ž€": 152,
"๋žŒ": 153,
"๋ž": 154,
"๋ž‘": 155,
"๋ž˜": 156,
"๋žœ": 157,
"๋žฌ": 158,
"๋Ÿ‰": 159,
"๋Ÿฌ": 160,
"๋Ÿฐ": 161,
"๋Ÿด": 162,
"๋Ÿผ": 163,
"๋ €": 164,
"๋ ‡": 165,
"๋ Œ": 166,
"๋ ค": 167,
"๋ ฅ": 168,
"๋ จ": 169,
"๋ ธ": 170,
"๋ก€": 171,
"๋กœ": 172,
"๋ก": 173,
"๋ก ": 174,
"๋ฃŒ": 175,
"๋ฃจ": 176,
"๋ฅ˜": 177,
"๋ฅด": 178,
"๋ฅธ": 179,
"๋ฅผ": 180,
"๋ฆ„": 181,
"๋ฆฌ": 182,
"๋ฆฐ": 183,
"๋ฆผ": 184,
"๋ฆฝ": 185,
"๋งˆ": 186,
"๋ง‰": 187,
"๋งŒ": 188,
"๋งŽ": 189,
"๋ง": 190,
"๋ง‘": 191,
"๋งž": 192,
"๋งก": 193,
"๋งค": 194,
"๋งบ": 195,
"๋จธ": 196,
"๋จน": 197,
"๋จผ": 198,
"๋ฉ€": 199,
"๋ฉ‰": 200,
"๋ฉฐ": 201,
"๋ฉด": 202,
"๋ช…": 203,
"๋ช‡": 204,
"๋ชจ": 205,
"๋ชฐ": 206,
"๋ชป": 207,
"๋ฌด": 208,
"๋ฌถ": 209,
"๋ฌธ": 210,
"๋ฌป": 211,
"๋ฌผ": 212,
"๋ญ": 213,
"๋ฏธ": 214,
"๋ฐ€": 215,
"๋ฐ‘": 216,
"๋ฐ”": 217,
"๋ฐ–": 218,
"๋ฐ˜": 219,
"๋ฐ›": 220,
"๋ฐœ": 221,
"๋ฐฉ": 222,
"๋ฐฐ": 223,
"๋ฐฑ": 224,
"๋ฒˆ": 225,
"๋ฒ•": 226,
"๋ฒ—": 227,
"๋ฒณ": 228,
"๋ฒผ": 229,
"๋ฒฝ": 230,
"๋ณ€": 231,
"๋ณ•": 232,
"๋ณด": 233,
"๋ณธ": 234,
"๋ณผ": 235,
"๋ด…": 236,
"๋ด‰": 237,
"๋ด": 238,
"๋ดค": 239,
"๋ถ€": 240,
"๋ถ„": 241,
"๋ถˆ": 242,
"๋ถ™": 243,
"๋ธŒ": 244,
"๋น„": 245,
"๋นˆ": 246,
"๋น ": 247,
"๋นจ": 248,
"๋บ„": 249,
"๋ฝ€": 250,
"๋ฟ": 251,
"๋ฟœ": 252,
"์‚ฌ": 253,
"์‚ญ": 254,
"์‚ฐ": 255,
"์‚ด": 256,
"์‚ผ": 257,
"์ƒ": 258,
"์ƒˆ": 259,
"์ƒ‰": 260,
"์ƒ˜": 261,
"์ƒ": 262,
"์ƒค": 263,
"์„œ": 264,
"์„": 265,
"์„ž": 266,
"์„ ": 267,
"์„ค": 268,
"์„ญ": 269,
"์„ฏ": 270,
"์„ฑ": 271,
"์„ธ": 272,
"์…”": 273,
"์…จ": 274,
"์†Œ": 275,
"์†": 276,
"์†": 277,
"์†ก": 278,
"์ˆ˜": 279,
"์ˆœ": 280,
"์ˆ ": 281,
"์‰ฌ": 282,
"์‰ฝ": 283,
"์Šค": 284,
"์Šจ": 285,
"์Šฌ": 286,
"์Šต": 287,
"์Šน": 288,
"์‹œ": 289,
"์‹": 290,
"์‹ ": 291,
"์‹ค": 292,
"์‹ฌ": 293,
"์‹ญ": 294,
"์ผ": 295,
"์“ด": 296,
"์“ธ": 297,
"์”จ": 298,
"์”ฉ": 299,
"์•„": 300,
"์•ˆ": 301,
"์•Š": 302,
"์•Œ": 303,
"์•”": 304,
"์••": 305,
"์•˜": 306,
"์• ": 307,
"์•ก": 308,
"์•ค": 309,
"์•ผ": 310,
"์•ฝ": 311,
"์–‘": 312,
"์–˜": 313,
"์–ด": 314,
"์–ต": 315,
"์–ธ": 316,
"์–ป": 317,
"์–ผ": 318,
"์—†": 319,
"์—‡": 320,
"์—ˆ": 321,
"์—": 322,
"์—”": 323,
"์—ฌ": 324,
"์—ญ": 325,
"์—ฐ": 326,
"์—ด": 327,
"์—ผ": 328,
"์˜€": 329,
"์˜": 330,
"์˜ˆ": 331,
"์˜ค": 332,
"์˜จ": 333,
"์˜ฌ": 334,
"์˜ณ": 335,
"์˜ท": 336,
"์™€": 337,
"์™”": 338,
"์™œ": 339,
"์™ธ": 340,
"์š”": 341,
"์šฉ": 342,
"์šฐ": 343,
"์šด": 344,
"์šธ": 345,
"์›€": 346,
"์›Œ": 347,
"์›": 348,
"์›”": 349,
"์› ": 350,
"์œ„": 351,
"์œ ": 352,
"์œก": 353,
"์œต": 354,
"์œผ": 355,
"์€": 356,
"์„": 357,
"์Œ": 358,
"์": 359,
"์‘": 360,
"์˜": 361,
"์ด": 362,
"์ธ": 363,
"์ผ": 364,
"์ฝ": 365,
"์ž„": 366,
"์ž…": 367,
"์žˆ": 368,
"์ž‰": 369,
"์žŽ": 370,
"์ž": 371,
"์ž‘": 372,
"์ž˜": 373,
"์ž ": 374,
"์žฅ": 375,
"์žฌ": 376,
"์ €": 377,
"์ ": 378,
"์ „": 379,
"์ ˆ": 380,
"์ ": 381,
"์ •": 382,
"์ –": 383,
"์ œ": 384,
"์ ธ": 385,
"์กŒ": 386,
"์กฐ": 387,
"์กด": 388,
"์ข€": 389,
"์ข…": 390,
"์ข‹": 391,
"์ฃ ": 392,
"์ฃผ": 393,
"์ค€": 394,
"์ค„": 395,
"์ค‘": 396,
"์ฆ‰": 397,
"์ฆ": 398,
"์ฆ": 399,
"์ง€": 400,
"์ง": 401,
"์ง„": 402,
"์งˆ": 403,
"์ง‘": 404,
"์งš": 405,
"์ง": 406,
"์งญ": 407,
"์งฑ": 408,
"์งธ": 409,
"์จ": 410,
"์ชผ": 411,
"์ซ™": 412,
"์ฌ": 413,
"์ญ‰": 414,
"์ฐจ": 415,
"์ฐฌ": 416,
"์ฐฐ": 417,
"์ฐฝ": 418,
"์ฐพ": 419,
"์ฑ…": 420,
"์ฒ˜": 421,
"์ฒ ": 422,
"์ฒซ": 423,
"์ฒด": 424,
"์ณ": 425,
"์ตธ": 426,
"์ถ”": 427,
"์ถ•": 428,
"์ถœ": 429,
"์ถฉ": 430,
"์ธก": 431,
"์ธต": 432,
"์น˜": 433,
"์น™": 434,
"์นœ": 435,
"์น ": 436,
"์นญ": 437,
"์บ˜": 438,
"์ปค": 439,
"์ปต": 440,
"์ปท": 441,
"์ผ€": 442,
"์ผœ": 443,
"์ผฐ": 444,
"์ฝ”": 445,
"ํ": 446,
"ํฌ": 447,
"ํผ": 448,
"ํ‚ค": 449,
"ํ‚จ": 450,
"ํ‚ฌ": 451,
"ํƒ€": 452,
"ํƒ„": 453,
"ํƒˆ": 454,
"ํƒ•": 455,
"ํƒœ": 456,
"ํƒ": 457,
"ํ„ฐ": 458,
"ํ…": 459,
"ํ†ค": 460,
"ํ†ต": 461,
"ํˆฌ": 462,
"ํŠน": 463,
"ํ‹€": 464,
"ํ‹ฐ": 465,
"ํŒŒ": 466,
"ํŒ": 467,
"ํŒ”": 468,
"ํŒฝ": 469,
"ํผ": 470,
"ํŽด": 471,
"ํŽธ": 472,
"ํฌ": 473,
"ํ‘œ": 474,
"ํ’€": 475,
"ํ’": 476,
"ํ”„": 477,
"ํ”ผ": 478,
"ํ•„": 479,
"ํ•˜": 480,
"ํ•™": 481,
"ํ•œ": 482,
"ํ• ": 483,
"ํ•จ": 484,
"ํ•ฉ": 485,
"ํ•ญ": 486,
"ํ•ด": 487,
"ํ–‡": 488,
"ํ–ˆ": 489,
"ํ–ฅ": 490,
"ํ—˜": 491,
"ํ˜„": 492,
"ํ˜•": 493,
"ํ™”": 494,
"ํ™•": 495,
"ํ™œ": 496,
"ํ™ฉ": 497,
"ํšŒ": 498,
"ํšŸ": 499,
"ํ›„": 500,
"ํ˜": 501,
"ํก": 502,
"ํžˆ": 503,
"ํžŒ": 504,
"ํž˜": 505
}