{ "version": "1.0", "truncation": null, "padding": null, "added_tokens": [ { "id": 0, "content": "<|padding|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 1, "content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 698, "content": "<|unk|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true } ], "normalizer": null, "pre_tokenizer": { "type": "ByteLevel", "add_prefix_space": true, "trim_offsets": true, "use_regex": true }, "post_processor": { "type": "ByteLevel", "add_prefix_space": true, "trim_offsets": true, "use_regex": true }, "decoder": { "type": "ByteLevel", "add_prefix_space": true, "trim_offsets": true, "use_regex": true }, "model": { "type": "WordPiece", "unk_token": "<|unk|>", "continuing_subword_prefix": "##", "max_input_chars_per_word": 100, "vocab": { "<|padding|>": 0, "<|endoftext|>": 1, "Ġd": 2, "d": 3, "##d": 4, "Ġĩ": 5, "ĩ": 6, "##ĩ": 7, "Ġº": 8, "º": 9, "##º": 10, "5": 11, "##5": 12, "Ġć": 13, "ć": 14, "##ć": 15, "?": 16, "##?": 17, "ĠĮ": 18, "Į": 19, "##Į": 20, "ĠV": 21, "V": 22, "##V": 23, ",": 24, "##,": 25, "ĠĐ": 26, "Đ": 27, "##Đ": 28, "ĠU": 29, "U": 30, "##U": 31, "Ġä": 32, "ä": 33, "##ä": 34, "`": 35, "##`": 36, "ĠÜ": 37, "Ü": 38, "##Ü": 39, "Ġk": 40, "k": 41, "##k": 42, "Ġâ": 43, "â": 44, "##â": 45, "Ġb": 46, "b": 47, "##b": 48, "@": 49, "##@": 50, "Ġæ": 51, "æ": 52, "##æ": 53, "¾": 54, "##¾": 55, "Ġþ": 56, "þ": 57, "##þ": 58, "Ġj": 59, "j": 60, "##j": 61, "Ġf": 62, "f": 63, "##f": 64, "Ġú": 65, "ú": 66, "##ú": 67, "1": 68, "##1": 69, "Ġª": 70, "ª": 71, "##ª": 72, "Ġm": 73, "m": 74, "##m": 75, "$": 76, "##$": 77, "¦": 78, "##¦": 79, "2": 80, "##2": 81, "ĠIJ": 82, "IJ": 83, "##IJ": 84, "¯": 85, "##¯": 86, "ĠD": 87, "D": 88, "##D": 89, "Ġÿ": 90, "ÿ": 91, "##ÿ": 92, "ĠĄ": 93, "Ą": 94, "##Ą": 95, "}": 96, "##}": 97, "ĠĻ": 98, "Ļ": 99, "##Ļ": 100, ".": 101, "##.": 102, "©": 103, "##©": 104, "ĠY": 105, "Y": 106, "##Y": 107, "ĠĖ": 108, "Ė": 109, "##Ė": 110, "Ġŀ": 111, "ŀ": 112, "##ŀ": 113, "Ġę": 114, "ę": 115, "##ę": 116, "0": 117, "##0": 118, "Ġò": 119, "ò": 120, "##ò": 121, "Ġđ": 122, "đ": 123, "##đ": 124, "ĠÐ": 125, "Ð": 126, "##Ð": 127, "ĠØ": 128, "Ø": 129, "##Ø": 130, "~": 131, "##~": 132, "Ġó": 133, "ó": 134, "##ó": 135, "Ġē": 136, "ē": 137, "##ē": 138, "ĠĹ": 139, "Ĺ": 140, "##Ĺ": 141, "®": 142, "##®": 143, "ĠÛ": 144, "Û": 145, "##Û": 146, "Ġċ": 147, "ċ": 148, "##ċ": 149, "Ġð": 150, "ð": 151, "##ð": 152, "Ġij": 153, "ij": 154, "##ij": 155, "Ġs": 156, "s": 157, "##s": 158, "Ġq": 159, "q": 160, "##q": 161, "«": 162, "##«": 163, "ĠR": 164, "R": 165, "##R": 166, "ĠM": 167, "M": 168, "##M": 169, "²": 170, "##²": 171, "°": 172, "##°": 173, "Ġc": 174, "c": 175, "##c": 176, "£": 177, "##£": 178, "¥": 179, "##¥": 180, "ĠC": 181, "C": 182, "##C": 183, "ĠT": 184, "T": 185, "##T": 186, "ĠÞ": 187, "Þ": 188, "##Þ": 189, "Ġn": 190, "n": 191, "##n": 192, "ĠĂ": 193, "Ă": 194, "##Ă": 195, "Ġķ": 196, "ķ": 197, "##ķ": 198, "¿": 199, "##¿": 200, "|": 201, "##|": 202, "ĠZ": 203, "Z": 204, "##Z": 205, "Ġü": 206, "ü": 207, "##ü": 208, "ĠĨ": 209, "Ĩ": 210, "##Ĩ": 211, "Ġģ": 212, "ģ": 213, "##ģ": 214, "ĠÌ": 215, "Ì": 216, "##Ì": 217, "½": 218, "##½": 219, "»": 220, "##»": 221, "¸": 222, "##¸": 223, "ĠG": 224, "G": 225, "##G": 226, "ĠÒ": 227, "Ò": 228, "##Ò": 229, "×": 230, "##×": 231, "Ġă": 232, "ă": 233, "##ă": 234, "ĠĪ": 235, "Ī": 236, "##Ī": 237, "Ġî": 238, "î": 239, "##î": 240, "Ġg": 241, "g": 242, "##g": 243, "¤": 244, "##¤": 245, "ĠÇ": 246, "Ç": 247, "##Ç": 248, "4": 249, "##4": 250, "´": 251, "##´": 252, "§": 253, "##§": 254, "ĠÈ": 255, "È": 256, "##È": 257, "Ġè": 258, "è": 259, "##è": 260, "Ġt": 261, "t": 262, "##t": 263, "Ġā": 264, "ā": 265, "##ā": 266, "{": 267, "##{": 268, "ĠA": 269, "A": 270, "##A": 271, "ĠĢ": 272, "Ģ": 273, "##Ģ": 274, "Ġļ": 275, "ļ": 276, "##ļ": 277, "#": 278, "###": 279, "ĠI": 280, "I": 281, "##I": 282, "ĠÕ": 283, "Õ": 284, "##Õ": 285, "Ġá": 286, "á": 287, "##á": 288, "±": 289, "##±": 290, "Ġğ": 291, "ğ": 292, "##ğ": 293, "ĠÉ": 294, "É": 295, "##É": 296, "ĠĆ": 297, "Ć": 298, "##Ć": 299, "ĠĴ": 300, "Ĵ": 301, "##Ĵ": 302, "Ġù": 303, "ù": 304, "##ù": 305, "]": 306, "##]": 307, "Ġû": 308, "û": 309, "##û": 310, "ĠÓ": 311, "Ó": 312, "##Ó": 313, "ĠĜ": 314, "Ĝ": 315, "##Ĝ": 316, "Ġy": 317, "y": 318, "##y": 319, "³": 320, "##³": 321, "[": 322, "##[": 323, "Ġħ": 324, "ħ": 325, "##ħ": 326, "Ġĸ": 327, "ĸ": 328, "##ĸ": 329, "ĠŁ": 330, "Ł": 331, "##Ł": 332, "Ġį": 333, "į": 334, "##į": 335, "_": 336, "##_": 337, ":": 338, "##:": 339, "-": 340, "##-": 341, "ĠW": 342, "W": 343, "##W": 344, "ĠÁ": 345, "Á": 346, "##Á": 347, "Ġã": 348, "ã": 349, "##ã": 350, "ĠÆ": 351, "Æ": 352, "##Æ": 353, "ĠĚ": 354, "Ě": 355, "##Ě": 356, "Ġĥ": 357, "ĥ": 358, "##ĥ": 359, "¨": 360, "##¨": 361, "ĠL": 362, "L": 363, "##L": 364, "Ġô": 365, "ô": 366, "##ô": 367, "Ġĵ": 368, "ĵ": 369, "##ĵ": 370, "ĠĦ": 371, "Ħ": 372, "##Ħ": 373, "ĠÀ": 374, "À": 375, "##À": 376, "ĠÎ": 377, "Î": 378, "##Î": 379, "ĠĀ": 380, "Ā": 381, "##Ā": 382, "ĠĘ": 383, "Ę": 384, "##Ę": 385, "9": 386, "##9": 387, "ĠF": 388, "F": 389, "##F": 390, "ĠĊ": 391, "Ċ": 392, "##Ċ": 393, "ĠÄ": 394, "Ä": 395, "##Ä": 396, "ĠE": 397, "E": 398, "##E": 399, "¬": 400, "##¬": 401, "'": 402, "##'": 403, ">": 404, "##>": 405, "ĠX": 406, "X": 407, "##X": 408, "Ġı": 409, "ı": 410, "##ı": 411, "Ġď": 412, "ď": 413, "##ď": 414, "ĠB": 415, "B": 416, "##B": 417, "Ġą": 418, "ą": 419, "##ą": 420, "ĠÃ": 421, "Ã": 422, "##Ã": 423, "Ġo": 424, "o": 425, "##o": 426, "¹": 427, "##¹": 428, "Ġa": 429, "a": 430, "##a": 431, "Ġr": 432, "r": 433, "##r": 434, "8": 435, "##8": 436, ")": 437, "##)": 438, ";": 439, "##;": 440, "ĠQ": 441, "Q": 442, "##Q": 443, "Ġx": 444, "x": 445, "##x": 446, "·": 447, "##·": 448, "ĠÏ": 449, "Ï": 450, "##Ï": 451, "Ġë": 452, "ë": 453, "##ë": 454, "ĠĿ": 455, "Ŀ": 456, "##Ŀ": 457, "Ġö": 458, "ö": 459, "##ö": 460, "ĠĔ": 461, "Ĕ": 462, "##Ĕ": 463, "Ġç": 464, "ç": 465, "##ç": 466, "Ġu": 467, "u": 468, "##u": 469, "Ġľ": 470, "ľ": 471, "##ľ": 472, "Ġé": 473, "é": 474, "##é": 475, "Ġà": 476, "à": 477, "##à": 478, "Ġñ": 479, "ñ": 480, "##ñ": 481, "3": 482, "##3": 483, "Ġĉ": 484, "ĉ": 485, "##ĉ": 486, "Ġł": 487, "ł": 488, "##ł": 489, "Ġz": 490, "z": 491, "##z": 492, "Ġí": 493, "í": 494, "##í": 495, "Ġw": 496, "w": 497, "##w": 498, "ĠĶ": 499, "Ķ": 500, "##Ķ": 501, "ĠŃ": 502, "Ń": 503, "##Ń": 504, "ĠÚ": 505, "Ú": 506, "##Ú": 507, "+": 508, "##+": 509, "ĠÊ": 510, "Ê": 511, "##Ê": 512, "Ġĕ": 513, "ĕ": 514, "##ĕ": 515, "¼": 516, "##¼": 517, "ĠĎ": 518, "Ď": 519, "##Ď": 520, "Ġė": 521, "ė": 522, "##ė": 523, "ĠÅ": 524, "Å": 525, "##Å": 526, "Ġß": 527, "ß": 528, "##ß": 529, "ĠJ": 530, "J": 531, "##J": 532, "Ġµ": 533, "µ": 534, "##µ": 535, "ĠĬ": 536, "Ĭ": 537, "##Ĭ": 538, "Ġý": 539, "ý": 540, "##ý": 541, "=": 542, "##=": 543, "ĠÝ": 544, "Ý": 545, "##Ý": 546, "Ġě": 547, "ě": 548, "##ě": 549, "Ġč": 550, "č": 551, "##č": 552, "ĠK": 553, "K": 554, "##K": 555, "ĠO": 556, "O": 557, "##O": 558, "ĠÑ": 559, "Ñ": 560, "##Ñ": 561, "^": 562, "##^": 563, "*": 564, "##*": 565, "ĠĒ": 566, "Ē": 567, "##Ē": 568, "!": 569, "##!": 570, "Ġĭ": 571, "ĭ": 572, "##ĭ": 573, "ĠS": 574, "S": 575, "##S": 576, "Ġİ": 577, "İ": 578, "##İ": 579, "Ġø": 580, "ø": 581, "##ø": 582, "ĠÍ": 583, "Í": 584, "##Í": 585, "ĠH": 586, "H": 587, "##H": 588, "Ġì": 589, "ì": 590, "##ì": 591, "Ġe": 592, "e": 593, "##e": 594, "¶": 595, "##¶": 596, "(": 597, "##(": 598, "Ġõ": 599, "õ": 600, "##õ": 601, "ĠĈ": 602, "Ĉ": 603, "##Ĉ": 604, "Ġī": 605, "ī": 606, "##ī": 607, "Ġġ": 608, "ġ": 609, "##ġ": 610, "/": 611, "##/": 612, "ĠÂ": 613, "Â": 614, "##Â": 615, "Ġv": 616, "v": 617, "##v": 618, "%": 619, "##%": 620, "ĠÙ": 621, "Ù": 622, "##Ù": 623, "&": 624, "##&": 625, "ĠË": 626, "Ë": 627, "##Ë": 628, "Ġh": 629, "h": 630, "##h": 631, "Ġĝ": 632, "ĝ": 633, "##ĝ": 634, "ĠÔ": 635, "Ô": 636, "##Ô": 637, "Ġï": 638, "ï": 639, "##ï": 640, "ĠP": 641, "P": 642, "##P": 643, "ĠĤ": 644, "Ĥ": 645, "##Ĥ": 646, "Ġp": 647, "p": 648, "##p": 649, "Ġ": 650, "##Ġ": 651, "\\": 652, "##\\": 653, "ĠÖ": 654, "Ö": 655, "##Ö": 656, "<": 657, "##<": 658, "¢": 659, "##¢": 660, "Ġå": 661, "å": 662, "##å": 663, "ĠČ": 664, "Č": 665, "##Č": 666, "Ġê": 667, "ê": 668, "##ê": 669, "ĠN": 670, "N": 671, "##N": 672, "7": 673, "##7": 674, "ĠĞ": 675, "Ğ": 676, "##Ğ": 677, "Ġĺ": 678, "ĺ": 679, "##ĺ": 680, "\"": 681, "##\"": 682, "¡": 683, "##¡": 684, "Ġl": 685, "l": 686, "##l": 687, "ĠĽ": 688, "Ľ": 689, "##Ľ": 690, "Ġi": 691, "i": 692, "##i": 693, "6": 694, "##6": 695, "÷": 696, "##÷": 697, "<|unk|>": 698, "##ng": 699, "##pi": 700, "##ó": 701, "##ħ": 702, "##in": 703, "##é": 704, "##ga": 705, "##ÃŃ": 706, "##ku": 707, "##an": 708, "##ah": 709, "##as": 710, "##ºŃ": 711, "##bo": 712, "##ka": 713, "##iÃ": 714, "##og": 715, "##ag": 716, "##sa": 717, "##ik": 718, "##de": 719, "##ad": 720, "##asa": 721, "##mi": 722, "##al": 723, "##³w": 724, "##nt": 725, "##ÙĦ": 726, "##ibo": 727, "##ro": 728, "##ak": 729, "##os": 730, "##id": 731, "##ĢĻ": 732, "##§h": 733, "##ĊĊ": 734, "##ig": 735, "##00": 736, ":/": 737, "##ir": 738, "##ib": 739, "##op": 740, "##§Ã": 741, "##ab": 742, "##la": 743, "##ul": 744, "##ż": 745, "##es": 746, "##lag": 747, "##na": 748, "##da": 749, "##ina": 750, "##ta": 751, "##ac": 752, "##ar": 753, "##ep": 754, "##Ãł": 755, "##tro": 756, "##en": 757, "##tz": 758, "##§a": 759, "##©s": 760, "##á": 761, "##pan": 762, "##em": 763, "##¹´": 764, "##it": 765, "##ä": 766, "##lo": 767, "##ala": 768, "##ba": 769, "##te": 770, "##//": 771, "##aka": 772, "##ri": 773, "##hi": 774, "##at": 775, "##ti": 776, "##¼j": 777, "##ö": 778, "##ra": 779, "##ang": 780, "##ten": 781, "##ahi": 782, "##ko": 783, "##pa": 784, "##oz": 785, "##un": 786, "##ı": 787, "##lu": 788, "##sar": 789, "##er": 790, "##ngan": 791, "##zten": 792, "##im": 793, "##re": 794, "##mu": 795, "##to": 796, "##eh": 797, "##tr": 798, "##aba": 799, "##ĦØ": 800, "##zt": 801, "##gs": 802, "##ts": 803, "##gsa": 804, "##rr": 805, "##him": 806, "##den": 807, "##ngang": 808, "##za": 809, "##Ä¡": 810, "##ao": 811, "##asad": 812, "##alag": 813, "##rt": 814, "##dp": 815, "##ire": 816, "##ek": 817, "##ió": 818, "##az": 819, "##et": 820, "##á»": 821, "##np": 822, "##err": 823, "##ki": 824, "##ni": 825, "##il": 826, "##ho": 827, "##sad": 828, "##gan": 829, "##on": 830, "##bi": 831, "##kar": 832, "##ĪÙ": 833, "##nd": 834, "##³n": 835, "##¶m": 836, "##ahin": 837, "##aci": 838, "##ue": 839, "##or": 840, "##rri": 841, "##ny": 842, "##od": 843, "##aga": 844, "##¶z": 845, "##ert": 846, "##ou": 847, "##is": 848, "##dl": 849, "an": 850, "##bab": 851, "##ci": 852, "##Ñı": 853, "##¡s": 854, "##iy": 855, "##ren": 856, "##±Å": 857, "##gw": 858, "##jo": 859, "##©g": 860, "##erri": 861, "##sÃ": 862, "Ġda": 863, "##nai": 864, "##oa": 865, "##big": 866, "##ÙĦØ": 867, "##kÃ": 868, "##ÅŁ": 869, "##ch": 870, "##ros": 871, "##do": 872, "##el": 873, "20": 874, "##ĊĊĊĊ": 875, "##eka": 876, "##ĭi": 877, "##..": 878, "##iren": 879, "##tu": 880, "##̬": 881, "##ags": 882, "##dla": 883, "##aw": 884, "##tod": 885, "##iz": 886, "##uk": 887, "##¡r": 888, "##li": 889, "##kk": 890, "##ijĺ": 891, "Ġsa": 892, "##¤n": 893, "##agat": 894, "##hin": 895, "##br": 896, "##ila": 897, "##rts": 898, "##ako": 899, "##ur": 900, "##le": 901, "##ai": 902, "##ªu": 903, "##Ã¥": 904, "##¡g": 905, "##ay": 906, "##ke": 907, "##adp": 908, "##bag": 909, "##¼jo": 910, "##ia": 911, "##ale": 912, "##ºŃt": 913, "##ha": 914, "##me": 915, "##alo": 916, "##ug": 917, "##po": 918, "##dto": 919, "##au": 920, "##wa": 921, "##ie": 922, "##bot": 923, "##ma": 924, "##inai": 925, "##gang": 926, "##º©": 927, "##gi": 928, "ĊĊ": 929, "##epa": 930, "##gat": 931, "##ong": 932, "##tso": 933, "##erts": 934, "##rÃ": 935, "##ez": 936, "##êu": 937, "##yo": 938, "##»į": 939, "##um": 940, "##ss": 941, "##Ńpo": 942, "##am": 943, "##ŁÄ": 944, "##ae": 945, "##oga": 946, "##kö": 947, "##mm": 948, "##ero": 949, "##ll": 950, "##mb": 951, "##us": 952, "##tt": 953, "##ب": 954, "##tÃ": 955, "ha": 956, "##ua": 957, "##xx": 958, "Ġkina": 959, "##alags": 960, "##mÃ": 961, "##zj": 962, "##eg": 963, "##si": 964, "##abo": 965, "##ui": 966, "##oÃ": 967, "##ali": 968, "##ate": 969, "##ég": 970, "##eme": 971, "##¿t": 972, "##ihan": 973, "##iha": 974, "##sh": 975, "##nda": 976, "##ing": 977, "##sy": 978, "##±z": 979, "##nh": 980, "##ebi": 981, "##hÃ": 982, "##akar": 983, "##gt": 984 } } }