{ "version": "1.0", "truncation": { "direction": "Right", "max_length": 1024, "strategy": "LongestFirst", "stride": 0 }, "padding": { "strategy": { "Fixed": 1024 }, "direction": "Right", "pad_to_multiple_of": null, "pad_id": 1, "pad_type_id": 0, "pad_token": "[PAD]" }, "added_tokens": [ { "id": 0, "content": "[BOS]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 1, "content": "[PAD]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 2, "content": "[EOS]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 3, "content": "[UNK]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 4, "content": "[CLS]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 5, "content": "[SEP]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 6, "content": "[MASK]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true } ], "normalizer": null, "pre_tokenizer": { "type": "Split", "pattern": { "Regex": "." }, "behavior": "Isolated", "invert": false }, "post_processor": { "type": "TemplateProcessing", "single": [ { "Sequence": { "id": "A", "type_id": 0 } } ], "pair": [ { "Sequence": { "id": "A", "type_id": 0 } }, { "Sequence": { "id": "B", "type_id": 1 } } ], "special_tokens": {} }, "decoder": null, "model": { "type": "WordLevel", "vocab": { "[BOS]": 0, "[PAD]": 1, "[EOS]": 2, "[UNK]": 3, "[CLS]": 4, "[SEP]": 5, "[MASK]": 6, " ": 7, "e": 8, "i": 9, "a": 10, "n": 11, "r": 12, "t": 13, "s": 14, "l": 15, "o": 16, "d": 17, "u": 18, "h": 19, "m": 20, "c": 21, "k": 22, "g": 23, "y": 24, "b": 25, "ı": 26, ",": 27, "f": 28, "p": 29, ".": 30, "v": 31, "z": 32, "w": 33, "ü": 34, "ş": 35, "S": 36, "A": 37, "ç": 38, "T": 39, "ğ": 40, "ö": 41, "B": 42, "M": 43, "E": 44, "D": 45, "I": 46, "P": 47, "-": 48, "G": 49, "H": 50, "'": 51, "K": 52, "C": 53, "F": 54, "W": 55, "R": 56, "0": 57, "L": 58, "ä": 59, "\"": 60, "N": 61, "1": 62, "2": 63, "O": 64, "j": 65, "U": 66, "x": 67, "V": 68, ":": 69, ")": 70, "(": 71, "ß": 72, "J": 73, "3": 74, "5": 75, "Y": 76, "4": 77, "Z": 78, "İ": 79, "9": 80, "q": 81, "6": 82, "*": 83, "8": 84, "7": 85, "/": 86, "?": 87, ";": 88, "!": 89, "X": 90, "Ö": 91, "Ç": 92, "Ü": 93, "Ş": 94, "Q": 95, "%": 96, "\t": 97, "–": 98, "~": 99, "_": 100, "&": 101, "$": 102, "+": 103, "#": 104, "[": 105, "]": 106, "â": 107, "…": 108, " ": 109, "Ä": 110, "•": 111, "é": 112, "—": 113, "\\": 114, "|": 115, "}": 116, ">": 117, "{": 118, "®": 119, "à": 120, "@": 121, "€": 122, "=": 123, "°": 124, "û": 125, "™": 126, "á": 127, "î": 128, "Ã": 129, "Ğ": 130, "»": 131, "ó": 132, "₺": 133, "Œ": 134, "í": 135, "‹": 136, "َ": 137, "­": 138, "›": 139, "¶": 140, "·": 141, "²": 142, "`": 143, "è": 144, "ا": 145, "£": 146, "ñ": 147, "´": 148, "ل": 149, "●": 150, "ô": 151, "«": 152, "×": 153, "и": 154, "ý": 155, "É": 156, "م": 157, "ê": 158, "ú": 159, "ã": 160, "å": 161, "ي": 162, "š": 163, "Ÿ": 164, "و": 165, "ن": 166, "′": 167, "ِ": 168, "ُ": 169, "→": 170, "ر": 171, "ë": 172, "ْ": 173, "ā": 174, "^": 175, "д": 176, "§": 177, "ï": 178, "č": 179, "<": 180, "ه": 181, "★": 182, "ć": 183, "ب": 184, "♥": 185, "©": 186, "¤": 187, "±": 188, "✓": 189, "µ": 190, "″": 191, "د": 192, "✔": 193, "½": 194, "ت": 195, "ø": 196, "¼": 197, "л": 198, "ع": 199, "ّ": 200, "̇": 201, "‑": 202, "℃": 203, "س": 204, "º": 205, "Å": 206, "ł": 207, "Á": 208, "Ì": 209, "Â": 210, "ð": 211, "þ": 212, "ˆ": 213, "Ý": 214, "Š": 215, "ō": 216, "ق": 217, "ι": 218, "י": 219, "я": 220, "ة": 221, "ف": 222, "₂": 223, "ו": 224, "ă": 225, "†": 226, "ك": 227, "‎": 228, "−": 229, "³": 230, "ń": 231, " ": 232, "➤": 233, "Ø": 234, "б": 235, "ž": 236, "ی": 237, "π": 238, "أ": 239, "ح": 240, "Ô": 241, "п": 242, "ə": 243, "¹": 244, "з": 245, "Č": 246, "ج": 247, "■": 248, "λ": 249, "й": 250, "ī": 251, "õ": 252, "ς": 253, "ы": 254, "₹": 255, "Ž": 256, "ц": 257, "ز": 258, "►": 259, "": 260, "ř": 261, "א": 262, "ش": 263, "Ω": 264, "✅": 265, "・": 266, "ě": 267, "ș": 268, "σ": 269, "ж": 270, "ч": 271, "ा": 272, "ū": 273, "ה": 274, "♦": 275, "्": 276, "¬": 277, "ذ": 278, "₪": 279, "≥": 280, "ò": 281, "√": 282, "⭐": 283, "ό": 284, "ל": 285, "נ": 286, "ิ": 287, "Ó": 288, "ى": 289, "👉": 290, "ר": 291, "ص": 292, "◆": 293, "❤": 294, "æ": 295, "ί": 296, "≤": 297, "œ": 298, "،": 299, "ē": 300, "ד": 301, "ע": 302, "Í": 303, "ő": 304, "خ": 305, "ि": 306, "¡": 307, "פ": 308, "เ": 309, "―": 310, "👍": 311, "🙂": 312, "ˈ": 313, "ً": 314, "ש": 315, "إ": 316, "र": 317, "ม": 318, "⚡": 319, "ー": 320, "Î": 321, "Ł": 322, "έ": 323, "न": 324, "่": 325, "◉": 326, "😊": 327, "Φ": 328, "ύ": 329, "П": 330, "ک": 331, "क": 332, "​": 333, "‡": 334, "₽": 335, "№": 336, "⇒": 337, "♂": 338, "の": 339, "ш": 340, "ח": 341, "آ": 342, "ض": 343, "ط": 344, "น": 345, "โ": 346, " ": 347, "✨": 348, "ù": 349, "े": 350, "▪": 351, "☆": 352, "☞": 353, "✿": 354, "的": 355, "È": 356, "Ñ": 357, "ę": 358, "ן": 359, "ी": 360, "ᅠ": 361, "イ": 362, "ス": 363, "˚": 364, "ά": 365, "ή": 366, "φ": 367, "מ": 368, "า": 369, "ი": 370, "‐": 371, "⠀": 372, "📌": 373, "¥": 374, "đ": 375, "δ": 376, "ю": 377, "ט": 378, "ء": 379, "ـ": 380, "↑": 381, "➢": 382, "日": 383, "À": 384, "÷": 385, "ą": 386, "ф": 387, "ַ": 388, "ב": 389, "त": 390, "ル": 391, "ン": 392, "㎡": 393, "¨": 394, "¸": 395, "ś": 396, "ג": 397, "ת": 398, "ल": 399, "∙": 400, "💡": 401, "ż": 402, "И": 403, "қ": 404, "ह": 405, "າ": 406, "🌟": 407, "😉": 408, "ì": 409, "ļ": 410, "Д": 411, "ь": 412, "ա": 413, "ק": 414, "ٍ": 415, "म": 416, "व": 417, "ส": 418, "↓": 419, "⌘": 420, "②": 421, "─": 422, "⚈": 423, "🚀": 424, "ª": 425, "¾": 426, "Ā": 427, "ث": 428, "स": 429, "ນ": 430, "‰": 431, "③": 432, "█": 433, "▶": 434, "ハ": 435, "マ": 436, "人": 437, "🙋": 438, "🙌": 439, "Đ": 440, "ţ": 441, "Б": 442, "Я": 443, "ם": 444, "ร": 445, "ა": 446, "※": 447, "△": 448, "✗": 449, "く": 450, "さ": 451, "ら": 452, "前": 453, "🌐": 454, "¦": 455, "Õ": 456, "Ú": 457, "ű": 458, "ų": 459, "ź": 460, "а": 461, "е": 462, "щ": 463, "ظ": 464, "ग": 465, "द": 466, "ว": 467, "อ": 468, "❀": 469, "⦁": 470, "か": 471, "ア": 472, "本": 473, "🎉": 474, "🏼": 475, "💰": 476, "ė": 477, "ɑ": 478, "Γ": 479, "Π": 480, "θ": 481, "υ": 482, "ώ": 483, "З": 484, "ъ": 485, "ր": 486, "ु": 487, "ต": 488, "່": 489, "ს": 490, "❗": 491, "い": 492, "に": 493, "ヤ": 494, "中": 495, "法": 496, "🎯": 497, "🔸": 498, "Þ": 499, "ň": 500, "ț": 501, "ʁ": 502, "ν": 503, "כ": 504, "ס": 505, "غ": 506, "پ": 507, "प": 508, "य": 509, "ो": 510, "ก": 511, "ฟ": 512, "້": 513, "თ": 514, "ნ": 515, "⃣": 516, "ℓ": 517, "≈": 518, "①": 519, "☀": 520, "☑": 521, "⠙": 522, "ト": 523, "场": 524, "月": 525, "神": 526, "Ă": 527, "į": 528, "ɛ": 529, "ʒ": 530, "̃": 531, "α": 532, "о": 533, "ז": 534, "צ": 535, "ؤ": 536, "ं": 537, "श": 538, "ະ": 539, "․": 540, "⁄": 541, "④": 542, "▼": 543, "♣": 544, "は": 545, "ッ": 546, "バ": 547, "了": 548, "文": 549, "🎊": 550, "👀": 551, "👈": 552, "👎": 553, "💼": 554, "🔴": 555, "😀": 556, "Æ": 557, "Û": 558, "ɔ": 559, "ʻ": 560, "Ф": 561, "н": 562, "э": 563, "ئ": 564, "ٌ": 565, "گ": 566, "ર": 567, "พ": 568, "ย": 569, "ອ": 570, "်": 571, "ვ": 572, "ḥ": 573, "₱": 574, "○": 575, "ク": 576, "コ": 577, "在": 578, "売": 579, "発": 580, "기": 581, "스": 582, "🍟": 583, "🏻": 584, "👆": 585, "👤": 586, "📱": 587, "🔍": 588, "¢": 589, "Ê": 590, "Ï": 591, "Ģ": 592, "Ś": 593, "ů": 594, "ο": 595, "Г": 596, "Л": 597, "ٱ": 598, "ज": 599, "ड": 600, "ท": 601, "ป": 602, "ล": 603, "ງ": 604, "ຍ": 605, "ມ": 606, "წ": 607, "ọ": 608, "ụ": 609, "▲": 610, "☰": 611, "☼": 612, "♀": 613, "➡": 614, "゜": 615, "カ": 616, "グ": 617, "デ": 618, "ロ": 619, "大": 620, "影": 621, "新": 622, "가": 623, "개": 624, "보": 625, "이": 626, "전": 627, "👨": 628, "🔥": 629, "😂": 630, "Ġ": 631, "ɾ": 632, "ʹ": 633, "ː": 634, "Η": 635, "κ": 636, "ρ": 637, "Ц": 638, "ָ": 639, "چ": 640, "ण": 641, "ี": 642, "๐": 643, "ກ": 644, "ລ": 645, "ສ": 646, "ຫ": 647, "ເ": 648, "ແ": 649, "ბ": 650, "Ḥ": 651, "ṣ": 652, "ế": 653, "ộ": 654, "‒": 655, "⁰": 656, "⁴": 657, "₮": 658, "⊞": 659, "⋅": 660, "◾": 661, "☝": 662, "⚠": 663, "✪": 664, "✰": 665, "❱": 666, "⟶": 667, "》": 668, "ざ": 669, "た": 670, "や": 671, "゚": 672, "ィ": 673, "フ": 674, "ラ": 675, "个": 676, "什": 677, "体": 678, "地": 679, "奈": 680, "川": 681, "很": 682, "要": 683, "超": 684, "车": 685, "高": 686, "어": 687, "🍏": 688, "👌": 689, "💾": 690, "📊": 691, "🔹": 692, "😄": 693, "🙏": 694, "🤦": 695, "🥈": 696, "Ć": 697, "ď": 698, "Ż": 699, "β": 700, "τ": 701, "в": 702, "р": 703, "т": 704, "ө": 705, "ո": 706, "ٰ": 707, "ہ": 708, "۟": 709, "۱": 710, "۹": 711, "च": 712, "ব": 713, "্": 714, "ਿ": 715, "્": 716, "บ": 717, "฿": 718, "์": 719, "ດ": 720, "ບ": 721, "ວ": 722, "း": 723, "ậ": 724, "∞": 725, "⑤": 726, "☎": 727, "⚙": 728, "✚": 729, "✯": 730, "❌": 731, "す": 732, "み": 733, "も": 734, "る": 735, "キ": 736, "ジ": 737, "ド": 738, "ニ": 739, "ュ": 740, "例": 741, "包": 742, "区": 743, "名": 744, "国": 745, "好": 746, "学": 747, "店": 748, "攻": 749, "方": 750, "是": 751, "有": 752, "机": 753, "澳": 754, "特": 755, "理": 756, "用": 757, "电": 758, "略": 759, "离": 760, "色": 761, "語": 762, "赌": 763, "门": 764, "院": 765, "龍": 766, "더": 767, "상": 768, "세": 769, "월": 770, "의": 771, "호": 772, "🇹": 773, "🌊": 774, "🌍": 775, "💬": 776, "💸": 777, "📚": 778, "📝": 779, "😍": 780, "🤔": 781, "¯": 782, "¿": 783, "Ē": 784, "Ě": 785, "ĝ": 786, "ġ": 787, "ħ": 788, "ǎ": 789, "Ș": 790, "ɪ": 791, "ʺ": 792, "ʿ": 793, "ˌ": 794, "́": 795, "̈": 796, "̧": 797, "̲": 798, "Θ": 799, "γ": 800, "η": 801, "χ": 802, "Н": 803, "Ч": 804, "к": 805, "м": 806, "Ս": 807, "ս": 808, "ւ": 809, "ڪ": 810, "ۭ": 811, "अ": 812, "ए": 813, "ट": 814, "फ": 815, "भ": 816, "ष": 817, "ू": 818, "য": 819, "া": 820, "ি": 821, "ে": 822, "ન": 823, "ે": 824, "ട": 825, "ോ": 826, "്": 827, "ක": 828, "න": 829, "ර": 830, "ස": 831, "්": 832, "ั": 833, "ู": 834, "ຈ": 835, "ຕ": 836, "ັ": 837, "ີ": 838, "ື": 839, "ົ": 840, "ခ": 841, "მ": 842, "რ": 843, "უ": 844, "ქ": 845, "ስ": 846, "ን": 847, "ệ": 848, "ἀ": 849, "Ῐ": 850, "⁚": 851, "⁺": 852, "₃": 853, "₴": 854, "↵": 855, "⋮": 856, "⏎": 857, "⑥": 858, "Ⓡ": 859, "├": 860, "◪": 861, "♠": 862, "♫": 863, "✖": 864, "❥": 865, "❶": 866, "➔": 867, "➕": 868, "〓": 869, "が": 870, "し": 871, "な": 872, "ま": 873, "り": 874, "タ": 875, "プ": 876, "ム": 877, "メ": 878, "モ": 879, "三": 880, "为": 881, "之": 882, "于": 883, "产": 884, "件": 885, "全": 886, "关": 887, "台": 888, "员": 889, "品": 890, "备": 891, "字": 892, "市": 893, "年": 894, "我": 895, "接": 896, "数": 897, "最": 898, "東": 899, "案": 900, "民": 901, "清": 902, "物": 903, "生": 904, "看": 905, "租": 906, "站": 907, "简": 908, "问": 909, "食": 910, "다": 911, "로": 912, "요": 913, "지": 914, "하": 915, "🇷": 916, "🌺": 917, "🍃": 918, "🎮": 919, "🏆": 920, "👇": 921, "💖": 922, "💳": 923, "🔋": 924, "🔒": 925, "😁": 926, "😒": 927, "🟠": 928, "🤡": 929, "🧍": 930, "Ë": 931, "Ð": 932, "ķ": 933, "Ő": 934, "Ř": 935, "ŭ": 936, "Ź": 937, "ǀ": 938, "ǐ": 939, "ǧ": 940, "ʊ": 941, "˘": 942, "̆": 943, "͡": 944, "Α": 945, "Β": 946, "Δ": 947, "Λ": 948, "Μ": 949, "Τ": 950, "ε": 951, "ζ": 952, "μ": 953, "К": 954, "Э": 955, "г": 956, "с": 957, "њ": 958, "ў": 959, "ҫ": 960, "ү": 961, "բ": 962, "ի": 963, "ն": 964, "ּ": 965, "ץ": 966, "ۆ": 967, "ە": 968, "ۢ": 969, "आ": 970, "ई": 971, "ध": 972, "এ": 973, "ক": 974, "ট": 975, "ন": 976, "স": 977, "ੱ": 978, "ટ": 979, "క": 980, "మ": 981, "య": 982, "ర": 983, "ా": 984, "ి": 985, "ർ": 986, "ง": 987, "จ": 988, "ด": 989, "ุ": 990, "ທ": 991, "ພ": 992, "ິ": 993, "ໃ": 994, "ໍ": 995, "༚": 996, "က": 997, "တ": 998, "ာ": 999, "ု": 1000, "ြ": 1001, "ሳ": 1002, "ተ": 1003, "ጨ": 1004, "ả": 1005, "ễ": 1006, "‪": 1007, "₉": 1008, "℉": 1009, "⅛": 1010, "⅜": 1011, "Ⅱ": 1012, "↗": 1013, "∆": 1014, "∇": 1015, "⏩": 1016, "⑦": 1017, "Ⓢ": 1018, "▎": 1019, "◊": 1020, "◎": 1021, "◦": 1022, "☄": 1023, "☪": 1024, "♋": 1025, "♛": 1026, "⚽": 1027, "✈": 1028, "✌": 1029, "✏": 1030, "❎": 1031, "❖": 1032, "あ": 1033, "お": 1034, "け": 1035, "と": 1036, "わ": 1037, "ん": 1038, "エ": 1039, "ピ": 1040, "ボ": 1041, "ミ": 1042, "ャ": 1043, "リ": 1044, "不": 1045, "么": 1046, "以": 1047, "位": 1048, "供": 1049, "克": 1050, "免": 1051, "入": 1052, "具": 1053, "典": 1054, "内": 1055, "出": 1056, "后": 1057, "商": 1058, "圳": 1059, "女": 1060, "定": 1061, "屋": 1062, "師": 1063, "干": 1064, "开": 1065, "式": 1066, "您": 1067, "房": 1068, "提": 1069, "斯": 1070, "時": 1071, "服": 1072, "期": 1073, "查": 1074, "横": 1075, "浜": 1076, "深": 1077, "火": 1078, "点": 1079, "町": 1080, "県": 1081, "真": 1082, "种": 1083, "約": 1084, "网": 1085, "美": 1086, "者": 1087, "舒": 1088, "装": 1089, "视": 1090, "语": 1091, "费": 1092, "距": 1093, "路": 1094, "过": 1095, "近": 1096, "酒": 1097, "金": 1098, "钱": 1099, "销": 1100, "长": 1101, "間": 1102, "预": 1103, "题": 1104, "鶴": 1105, "ꔂ": 1106, "그": 1107, "나": 1108, "리": 1109, "문": 1110, "비": 1111, "서": 1112, "설": 1113, "수": 1114, "제": 1115, "텔": 1116, "한": 1117, "🇧": 1118, "🇮": 1119, "🇺": 1120, "🌴": 1121, "🍰": 1122, "🎥": 1123, "👋": 1124, "💙": 1125, "💚": 1126, "💜": 1127, "💠": 1128, "📅": 1129, "📋": 1130, "🕰": 1131, "🕵": 1132, "😏": 1133, "🚫": 1134, "🤪": 1135, "🥉": 1136, "": 1137, "Ò": 1138, "ĉ": 1139, "ċ": 1140, "ĺ": 1141, "ņ": 1142, "Ō": 1143, "ŕ": 1144, "Ů": 1145, "Ə": 1146, "ƙ": 1147, "ư": 1148, "ǒ": 1149, "ɩ": 1150, "ʃ": 1151, "ʘ": 1152, "ʽ": 1153, "ˀ": 1154, "΄": 1155, "Έ": 1156, "Ε": 1157, "Ζ": 1158, "Ι": 1159, "Κ": 1160, "Ν": 1161, "Ξ": 1162, "Ο": 1163, "Ρ": 1164, "Σ": 1165, "Υ": 1166, "Χ": 1167, "Ψ": 1168, "Љ": 1169, "А": 1170, "Е": 1171, "Й": 1172, "Ш": 1173, "х": 1174, "џ": 1175, "Վ": 1176, "գ": 1177, "կ": 1178, "ճ": 1179, "մ": 1180, "յ": 1181, "վ": 1182, "տ": 1183, "ף": 1184, "؛": 1185, "ں": 1186, "ے": 1187, "ۗ": 1188, "ۥ": 1189, "ߋ": 1190, "इ": 1191, "उ": 1192, "ब": 1193, "़": 1194, "ै": 1195, "।": 1196, "ং": 1197, "খ": 1198, "ম": 1199, "ী": 1200, "ু": 1201, "ਆ": 1202, "ਥ": 1203, "ਦ": 1204, "ਰ": 1205, "ਵ": 1206, "ਸ": 1207, "ਹ": 1208, "ੇ": 1209, "ੋ": 1210, "એ": 1211, "ત": 1212, "પ": 1213, "ફ": 1214, "મ": 1215, "ા": 1216, "િ": 1217, "ો": 1218, "ள": 1219, "త": 1220, "ు": 1221, "్": 1222, "സ": 1223, "ി": 1224, "ൽ": 1225, "ං": 1226, "ණ": 1227, "ය": 1228, "ค": 1229, "ถ": 1230, "ธ": 1231, "็": 1232, "ຄ": 1233, "ຊ": 1234, "ຟ": 1235, "ຮ": 1236, "ໄ": 1237, "င": 1238, "စ": 1239, "ည": 1240, "ဖ": 1241, "ိ": 1242, "ျ": 1243, "ე": 1244, "კ": 1245, "ო": 1246, "መ": 1247, "ር": 1248, "ቢ": 1249, "ከ": 1250, "ው": 1251, "ገ": 1252, "ጥ": 1253, "ᐈ": 1254, "ᐉ": 1255, "ᴼ": 1256, "ᴾ": 1257, "ᴿ": 1258, "ḍ": 1259, "Ṣ": 1260, "ṭ": 1261, "ạ": 1262, "ẽ": 1263, "ề": 1264, "ị": 1265, "ố": 1266, "ứ": 1267, "Ἶ": 1268, "ῆ": 1269, "‧": 1270, "‬": 1271, "‿": 1272, "⁃": 1273, "⁠": 1274, "⁵": 1275, "⁶": 1276, "⁹": 1277, "₄": 1278, "₅": 1279, "₈": 1280, "₦": 1281, "₩": 1282, "₵": 1283, "₿": 1284, "⅓": 1285, "ⅼ": 1286, "↘": 1287, "↞": 1288, "↠": 1289, "⇛": 1290, "⇣": 1291, "∩": 1292, "⏱": 1293, "⏳": 1294, "Ⓔ": 1295, "Ⓛ": 1296, "Ⓜ": 1297, "Ⓩ": 1298, "│": 1299, "┬": 1300, "╝": 1301, "▸": 1302, "◀": 1303, "◇": 1304, "◗": 1305, "◘": 1306, "◻": 1307, "☉": 1308, "☕": 1309, "♑": 1310, "♞": 1311, "♪": 1312, "♬": 1313, "♭": 1314, "⛵": 1315, "✊": 1316, "✕": 1317, "✤": 1318, "✦": 1319, "❁": 1320, "❄": 1321, "❉": 1322, "❓": 1323, "❝": 1324, "➊": 1325, "➣": 1326, "➥": 1327, "⠃": 1328, "⠘": 1329, "⠿": 1330, "⬆": 1331, "「": 1332, "〘": 1333, "〙": 1334, "う": 1335, "き": 1336, "ぎ": 1337, "こ": 1338, "ご": 1339, "め": 1340, "よ": 1341, "を": 1342, "オ": 1343, "ガ": 1344, "ギ": 1345, "ザ": 1346, "シ": 1347, "チ": 1348, "ツ": 1349, "テ": 1350, "ネ": 1351, "ヒ": 1352, "ベ": 1353, "ペ": 1354, "レ": 1355, "一": 1356, "上": 1357, "丝": 1358, "乐": 1359, "书": 1360, "二": 1361, "们": 1362, "伊": 1363, "但": 1364, "作": 1365, "侵": 1366, "信": 1367, "元": 1368, "六": 1369, "兹": 1370, "到": 1371, "力": 1372, "加": 1373, "务": 1374, "动": 1375, "可": 1376, "君": 1377, "和": 1378, "售": 1379, "固": 1380, "坡": 1381, "城": 1382, "場": 1383, "士": 1384, "外": 1385, "多": 1386, "失": 1387, "契": 1388, "如": 1389, "子": 1390, "孟": 1391, "安": 1392, "审": 1393, "宣": 1394, "宮": 1395, "害": 1396, "家": 1397, "容": 1398, "寺": 1399, "尔": 1400, "就": 1401, "展": 1402, "山": 1403, "岬": 1404, "州": 1405, "工": 1406, "巨": 1407, "广": 1408, "床": 1409, "应": 1410, "度": 1411, "录": 1412, "形": 1413, "役": 1414, "律": 1415, "得": 1416, "忍": 1417, "总": 1418, "情": 1419, "意": 1420, "感": 1421, "成": 1422, "戯": 1423, "所": 1424, "手": 1425, "技": 1426, "播": 1427, "放": 1428, "料": 1429, "旁": 1430, "曼": 1431, "朝": 1432, "权": 1433, "条": 1434, "来": 1435, "植": 1436, "様": 1437, "樂": 1438, "比": 1439, "氷": 1440, "汁": 1441, "求": 1442, "活": 1443, "济": 1444, "消": 1445, "涼": 1446, "炎": 1447, "独": 1448, "猎": 1449, "王": 1450, "登": 1451, "百": 1452, "直": 1453, "码": 1454, "破": 1455, "空": 1456, "竜": 1457, "級": 1458, "索": 1459, "纠": 1460, "纷": 1461, "经": 1462, "耀": 1463, "联": 1464, "能": 1465, "自": 1466, "舞": 1467, "若": 1468, "英": 1469, "螃": 1470, "蟹": 1471, "表": 1472, "规": 1473, "觉": 1474, "解": 1475, "谢": 1476, "谷": 1477, "賞": 1478, "购": 1479, "輸": 1480, "边": 1481, "这": 1482, "退": 1483, "适": 1484, "遊": 1485, "部": 1486, "链": 1487, "関": 1488, "间": 1489, "限": 1490, "雷": 1491, "需": 1492, "非": 1493, "频": 1494, "馬": 1495, "马": 1496, "鮭": 1497, "麼": 1498, "黑": 1499, "ꔉ": 1500, "감": 1501, "국": 1502, "금": 1503, "년": 1504, "늘": 1505, "드": 1506, "명": 1507, "바": 1508, "사": 1509, "산": 1510, "선": 1511, "성": 1512, "아": 1513, "오": 1514, "왕": 1515, "질": 1516, "참": 1517, "크": 1518, "태": 1519, "택": 1520, "트": 1521, "피": 1522, "희": 1523, "🃏": 1524, "🇪": 1525, "🇬": 1526, "🇵": 1527, "🌄": 1528, "🌦": 1529, "🌩": 1530, "🌪": 1531, "🌳": 1532, "🌸": 1533, "🌹": 1534, "🍎": 1535, "🍴": 1536, "🍸": 1537, "🍽": 1538, "🎓": 1539, "🎛": 1540, "🏀": 1541, "🏅": 1542, "🏠": 1543, "🏢": 1544, "🏿": 1545, "🐛": 1546, "👑": 1547, "👦": 1548, "👩": 1549, "💋": 1550, "💐": 1551, "💔": 1552, "💕": 1553, "💧": 1554, "💨": 1555, "💫": 1556, "💹": 1557, "📂": 1558, "📈": 1559, "📍": 1560, "📜": 1561, "🔌": 1562, "🔓": 1563, "🔗": 1564, "🔧": 1565, "🔬": 1566, "🔽": 1567, "🕒": 1568, "🕹": 1569, "🖇": 1570, "🖊": 1571, "🖐": 1572, "🗓": 1573, "😅": 1574, "😇": 1575, "🙁": 1576, "🚘": 1577, "🚶": 1578, "🛒": 1579, "🟩": 1580, "🤩": 1581, "🥂": 1582, "🥇": 1583, "🥡": 1584, "🥫": 1585, "🥳": 1586, "🧠": 1587, "Ĉ": 1588, "Ď": 1589, "ĕ": 1590, "Ę": 1591, "Ħ": 1592, "Ī": 1593, "ĵ": 1594, "Ķ": 1595, "Ĺ": 1596, "Ľ": 1597, "ľ": 1598, "Ń": 1599, "Ň": 1600, "Ŗ": 1601, "ŝ": 1602, "Ť": 1603, "ť": 1604, "Ū": 1605, "Ű": 1606, "ƫ": 1607, "ƶ": 1608, "ǔ": 1609, "Ǩ": 1610, "ȃ": 1611, "Ț": 1612, "Ƀ": 1613, "ɒ": 1614, "ɡ": 1615, "ɣ": 1616, "ɨ": 1617, "ɻ": 1618, "ʖ": 1619, "ʙ": 1620, "ˇ": 1621, "˙": 1622, "ˮ": 1623, "˹": 1624, "˺": 1625, "̂": 1626, "̨": 1627, "̵": 1628, "͜": 1629, "͵": 1630, "ΐ": 1631, "ξ": 1632, "ψ": 1633, "ω": 1634, "Ђ": 1635, "Є": 1636, "Ѕ": 1637, "І": 1638, "Ј": 1639, "Џ": 1640, "В": 1641, "Ж": 1642, "М": 1643, "О": 1644, "Р": 1645, "С": 1646, "Т": 1647, "У": 1648, "Х": 1649, "Щ": 1650, "Ы": 1651, "Ь": 1652, "Ю": 1653, "у": 1654, "ѐ": 1655, "ђ": 1656, "є": 1657, "ѕ": 1658, "і": 1659, "ј": 1660, "љ": 1661, "ғ": 1662, "Ҫ": 1663, "ә": 1664, "ӯ": 1665, "Կ": 1666, "՛": 1667, "՝": 1668, "ե": 1669, "ը": 1670, "թ": 1671, "պ": 1672, "ք": 1673, "։": 1674, "ְ": 1675, "ֹ": 1676, "ׁ": 1677, "؟": 1678, "ٹ": 1679, "ڇ": 1680, "ڑ": 1681, "ښ": 1682, "ھ": 1683, "ێ": 1684, "۔": 1685, "ۖ": 1686, "ۚ": 1687, "۰": 1688, "۲": 1689, "۸": 1690, "݃": 1691, "ޑ": 1692, "ޮ": 1693, "ओ": 1694, "ख": 1695, "ङ": 1696, "छ": 1697, "ठ": 1698, "थ": 1699, "ळ": 1700, "ृ": 1701, "॥": 1702, "२": 1703, "४": 1704, "७": 1705, "অ": 1706, "জ": 1707, "ড": 1708, "দ": 1709, "ধ": 1710, "ফ": 1711, "র": 1712, "শ": 1713, "হ": 1714, "়": 1715, "ো": 1716, "ਉ": 1717, "ਕ": 1718, "ਗ": 1719, "ਚ": 1720, "ਨ": 1721, "ਪ": 1722, "ਬ": 1723, "ਲ": 1724, "ੀ": 1725, "ੌ": 1726, "੍": 1727, "ੜ": 1728, "ં": 1729, "અ": 1730, "ઈ": 1731, "ઉ": 1732, "ક": 1733, "જ": 1734, "ડ": 1735, "બ": 1736, "લ": 1737, "વ": 1738, "શ": 1739, "સ": 1740, "ી": 1741, "உ": 1742, "்": 1743, "ం": 1744, "ట": 1745, "ఫ": 1746, "స": 1747, "ీ": 1748, "ే": 1749, "ക": 1750, "ദ": 1751, "പ": 1752, "ഫ": 1753, "മ": 1754, "ള": 1755, "ญ": 1756, "ฏ": 1757, "ณ": 1758, "ะ": 1759, "ึ": 1760, "ื": 1761, "แ": 1762, "ไ": 1763, "้": 1764, "ຂ": 1765, "ຖ": 1766, "ຜ": 1767, "ຢ": 1768, "ຸ": 1769, "ູ": 1770, "ຼ": 1771, "ပ": 1772, "လ": 1773, "သ": 1774, "დ": 1775, "ტ": 1776, "ህ": 1777, "ላ": 1778, "ሌ": 1779, "ል": 1780, "ማ": 1781, "ሪ": 1782, "ሲ": 1783, "ቃ": 1784, "ቄ": 1785, "ቅ": 1786, "በ": 1787, "ታ": 1788, "ት": 1789, "ኋ": 1790, "ኖ": 1791, "ኪ": 1792, "ያ": 1793, "ይ": 1794, "ᴜ": 1795, "ᵻ": 1796, "ḗ": 1797, "Ḫ": 1798, "ḫ": 1799, "ḯ": 1800, "ḳ": 1801, "Ẓ": 1802, "ẞ": 1803, "ấ": 1804, "ầ": 1805, "ắ": 1806, "Ẹ": 1807, "Ế": 1808, "ể": 1809, "Ọ": 1810, "ổ": 1811, "ớ": 1812, "ử": 1813, "ỹ": 1814, "ἄ": 1815, "ὁ": 1816, "ὐ": 1817, "ᾶ": 1818, "ῖ": 1819, "ῥ": 1820, "⁷": 1821, "⁸": 1822, "₁": 1823, "₣": 1824, "⅔": 1825, "Ⅰ": 1826, "Ⅳ": 1827, "ⅴ": 1828, "↩": 1829, "⇢": 1830, "⇾": 1831, "∅": 1832, "∎": 1833, "∥": 1834, "∧": 1835, "∨": 1836, "≙": 1837, "≠": 1838, "≡": 1839, "⊂": 1840, "⊆": 1841, "⎯": 1842, "⏰": 1843, "⑵": 1844, "Ⓒ": 1845, "ⓘ": 1846, "┼": 1847, "░": 1848, "▢": 1849, "▫": 1850, "☔": 1851, "☛": 1852, "☢": 1853, "☺": 1854, "☻": 1855, "♔": 1856, "♵": 1857, "⚒": 1858, "⚓": 1859, "⚖": 1860, "⛅": 1861, "⛈": 1862, "✂": 1863, "✉": 1864, "✝": 1865, "❇": 1866, "➙": 1867, "➛": 1868, "➜": 1869, "➝": 1870, "➠": 1871, "⟪": 1872, "⢠": 1873, "⦿": 1874, "ⱱ": 1875, "」": 1876, "ず": 1877, "そ": 1878, "ぞ": 1879, "だ": 1880, "っ": 1881, "て": 1882, "で": 1883, "ど": 1884, "ひ": 1885, "ほ": 1886, "ゆ": 1887, "ゥ": 1888, "ェ": 1889, "ゲ": 1890, "サ": 1891, "ズ": 1892, "ナ": 1893, "ヌ": 1894, "パ": 1895, "ビ": 1896, "ブ": 1897, "ホ": 1898, "ポ": 1899, "ワ": 1900, "万": 1901, "下": 1902, "且": 1903, "东": 1904, "串": 1905, "主": 1906, "乌": 1907, "也": 1908, "买": 1909, "予": 1910, "事": 1911, "云": 1912, "亚": 1913, "亦": 1914, "亿": 1915, "仙": 1916, "代": 1917, "令": 1918, "价": 1919, "任": 1920, "优": 1921, "会": 1922, "伝": 1923, "传": 1924, "佑": 1925, "何": 1926, "佳": 1927, "便": 1928, "保": 1929, "修": 1930, "倍": 1931, "假": 1932, "做": 1933, "健": 1934, "傾": 1935, "儀": 1936, "儿": 1937, "先": 1938, "光": 1939, "八": 1940, "公": 1941, "兰": 1942, "兵": 1943, "其": 1944, "円": 1945, "再": 1946, "况": 1947, "几": 1948, "分": 1949, "利": 1950, "别": 1951, "創": 1952, "功": 1953, "助": 1954, "勘": 1955, "務": 1956, "化": 1957, "北": 1958, "區": 1959, "十": 1960, "午": 1961, "华": 1962, "南": 1963, "博": 1964, "厅": 1965, "又": 1966, "及": 1967, "反": 1968, "取": 1969, "古": 1970, "只": 1971, "号": 1972, "司": 1973, "合": 1974, "吐": 1975, "吞": 1976, "含": 1977, "听": 1978, "呆": 1979, "告": 1980, "呢": 1981, "周": 1982, "唯": 1983, "善": 1984, "回": 1985, "图": 1986, "國": 1987, "圓": 1988, "土": 1989, "圣": 1990, "均": 1991, "坦": 1992, "垂": 1993, "基": 1994, "塔": 1995, "壁": 1996, "夜": 1997, "太": 1998, "奇": 1999, "她": 2000, "妈": 2001, "姆": 2002, "孔": 2003, "季": 2004, "孫": 2005, "學": 2006, "它": 2007, "宅": 2008, "宛": 2009, "客": 2010, "宾": 2011, "密": 2012, "富": 2013, "対": 2014, "少": 2015, "屬": 2016, "岛": 2017, "島": 2018, "币": 2019, "帝": 2020, "带": 2021, "帮": 2022, "常": 2023, "平": 2024, "幸": 2025, "幽": 2026, "库": 2027, "康": 2028, "建": 2029, "引": 2030, "彙": 2031, "彼": 2032, "待": 2033, "後": 2034, "微": 2035, "德": 2036, "応": 2037, "快": 2038, "性": 2039, "息": 2040, "恶": 2041, "應": 2042, "或": 2043, "户": 2044, "才": 2045, "扱": 2046, "招": 2047, "挑": 2048, "换": 2049, "据": 2050, "排": 2051, "搜": 2052, "摩": 2053, "擇": 2054, "散": 2055, "敬": 2056, "斐": 2057, "族": 2058, "晋": 2059, "智": 2060, "暂": 2061, "暗": 2062, "暴": 2063, "更": 2064, "术": 2065, "材": 2066, "极": 2067, "果": 2068, "格": 2069, "械": 2070, "業": 2071, "模": 2072, "樹": 2073, "機": 2074, "欣": 2075, "正": 2076, "毎": 2077, "汉": 2078, "汽": 2079, "沈": 2080, "沙": 2081, "沟": 2082, "海": 2083, "港": 2084, "演": 2085, "潘": 2086, "灣": 2087, "灰": 2088, "災": 2089, "無": 2090, "然": 2091, "營": 2092, "爆": 2093, "片": 2094, "版": 2095, "琳": 2096, "由": 2097, "申": 2098, "畢": 2099, "疗": 2100, "疫": 2101, "皓": 2102, "盡": 2103, "着": 2104, "研": 2105, "示": 2106, "禍": 2107, "福": 2108, "私": 2109, "科": 2110, "称": 2111, "程": 2112, "穢": 2113, "究": 2114, "立": 2115, "童": 2116, "笑": 2117, "等": 2118, "答": 2119, "签": 2120, "管": 2121, "範": 2122, "籍": 2123, "类": 2124, "精": 2125, "糖": 2126, "系": 2127, "細": 2128, "終": 2129, "絡": 2130, "継": 2131, "続": 2132, "網": 2133, "編": 2134, "约": 2135, "级": 2136, "线": 2137, "终": 2138, "绎": 2139, "统": 2140, "缤": 2141, "缺": 2142, "置": 2143, "群": 2144, "義": 2145, "習": 2146, "翻": 2147, "耳": 2148, "聯": 2149, "臨": 2150, "臺": 2151, "興": 2152, "航": 2153, "良": 2154, "节": 2155, "苹": 2156, "茨": 2157, "荣": 2158, "营": 2159, "著": 2160, "蘇": 2161, "號": 2162, "行": 2163, "術": 2164, "衛": 2165, "裂": 2166, "裝": 2167, "見": 2168, "規": 2169, "见": 2170, "角": 2171, "言": 2172, "計": 2173, "訊": 2174, "詞": 2175, "詢": 2176, "詳": 2177, "請": 2178, "讓": 2179, "订": 2180, "证": 2181, "词": 2182, "译": 2183, "说": 2184, "请": 2185, "读": 2186, "谚": 2187, "豊": 2188, "豪": 2189, "資": 2190, "贵": 2191, "资": 2192, "赞": 2193, "赤": 2194, "趣": 2195, "身": 2196, "載": 2197, "輕": 2198, "輯": 2199, "转": 2200, "载": 2201, "还": 2202, "远": 2203, "送": 2204, "选": 2205, "通": 2206, "週": 2207, "逸": 2208, "道": 2209, "選": 2210, "邮": 2211, "郭": 2212, "都": 2213, "醇": 2214, "醣": 2215, "釋": 2216, "量": 2217, "銷": 2218, "鋼": 2219, "錬": 2220, "铁": 2221, "門": 2222, "開": 2223, "閣": 2224, "闘": 2225, "闪": 2226, "防": 2227, "阳": 2228, "阴": 2229, "际": 2230, "降": 2231, "险": 2232, "隆": 2233, "隙": 2234, "隣": 2235, "集": 2236, "零": 2237, "霍": 2238, "青": 2239, "面": 2240, "額": 2241, "類": 2242, "風": 2243, "风": 2244, "餐": 2245, "饰": 2246, "首": 2247, "鬆": 2248, "魔": 2249, "麻": 2250, "黃": 2251, "黄": 2252, "默": 2253, "齐": 2254, "간": 2255, "검": 2256, "것": 2257, "게": 2258, "결": 2259, "고": 2260, "글": 2261, "끉": 2262, "내": 2263, "너": 2264, "널": 2265, "녕": 2266, "는": 2267, "단": 2268, "대": 2269, "댓": 2270, "도": 2271, "동": 2272, "두": 2273, "들": 2274, "딘": 2275, "뛰": 2276, "라": 2277, "람": 2278, "려": 2279, "론": 2280, "롯": 2281, "류": 2282, "르": 2283, "름": 2284, "립": 2285, "링": 2286, "마": 2287, "막": 2288, "맛": 2289, "먹": 2290, "메": 2291, "몇": 2292, "모": 2293, "무": 2294, "물": 2295, "밀": 2296, "반": 2297, "버": 2298, "병": 2299, "부": 2300, "분": 2301, "브": 2302, "셀": 2303, "소": 2304, "숨": 2305, "슬": 2306, "심": 2307, "싱": 2308, "안": 2309, "야": 2310, "약": 2311, "엄": 2312, "었": 2313, "에": 2314, "엔": 2315, "역": 2316, "연": 2317, "영": 2318, "예": 2319, "용": 2320, "우": 2321, "운": 2322, "은": 2323, "인": 2324, "있": 2325, "자": 2326, "장": 2327, "저": 2328, "정": 2329, "조": 2330, "주": 2331, "짓": 2332, "채": 2333, "천": 2334, "추": 2335, "충": 2336, "카": 2337, "케": 2338, "퀴": 2339, "큐": 2340, "키": 2341, "탄": 2342, "탕": 2343, "터": 2344, "테": 2345, "토": 2346, "튀": 2347, "티": 2348, "틸": 2349, "파": 2350, "폭": 2351, "품": 2352, "할": 2353, "함": 2354, "해": 2355, "화": 2356, "후": 2357, "히": 2358, "️": 2359, "𝕏": 2360, "🆕": 2361, "🇯": 2362, "🇰": 2363, "🇱": 2364, "🇸": 2365, "🌀": 2366, "🌈": 2367, "🌎": 2368, "🌙": 2369, "🌾": 2370, "🌿": 2371, "🍭": 2372, "🍷": 2373, "🎁": 2374, "🎂": 2375, "🎆": 2376, "🎖": 2377, "🎣": 2378, "🎧": 2379, "🎨": 2380, "🎭": 2381, "🎵": 2382, "🏴": 2383, "🐑": 2384, "🐔": 2385, "🐘": 2386, "🐝": 2387, "🐴": 2388, "🐶": 2389, "👏": 2390, "💥": 2391, "💪": 2392, "💯": 2393, "💵": 2394, "💻": 2395, "📁": 2396, "📏": 2397, "📞": 2398, "📦": 2399, "📲": 2400, "📷": 2401, "📼": 2402, "🔄": 2403, "🔞": 2404, "🕊": 2405, "🕌": 2406, "🕗": 2407, "🕳": 2408, "🖥": 2409, "🗞": 2410, "🗺": 2411, "😃": 2412, "😆": 2413, "😎": 2414, "😘": 2415, "😛": 2416, "😞": 2417, "😬": 2418, "😳": 2419, "🚅": 2420, "🚗": 2421, "🚨": 2422, "🚩": 2423, "🛏": 2424, "🛡": 2425, "🤑": 2426, "🤝": 2427, "🤨": 2428, "🤲": 2429, "🥘": 2430, "🥚": 2431, "🥦": 2432, "🥩": 2433, "🥶": 2434, "🧐": 2435, "🧑": 2436, "🧟": 2437, "🧨": 2438, "🧳": 2439, "𠇊": 2440, "𧨠": 2441 }, "unk_token": "[UNK]" } }