Upload tokenizer
52bcb83
verified
|
{ |
|
"<pad>": 0, |
|
"<s>": 1, |
|
"</s>": 2, |
|
"<unk>": 3, |
|
"<sep>": 4, |
|
"<cls>": 5, |
|
"<mask>": 6, |
|
"ఒ": 7, |
|
"ţ": 8, |
|
"ѳ": 9, |
|
"̉": 10, |
|
"Ф": 11, |
|
"·": 12, |
|
" ": 13, |
|
"Й": 14, |
|
"Ѣ": 15, |
|
"ђ": 16, |
|
"ὸ": 17, |
|
"γ": 18, |
|
"Ђ": 19, |
|
"$": 20, |
|
"¿": 21, |
|
"έ": 22, |
|
"Т": 23, |
|
"я": 24, |
|
"✔": 25, |
|
"̈": 26, |
|
"∠": 27, |
|
"∫": 28, |
|
"Z": 29, |
|
"←": 30, |
|
"ќ": 31, |
|
"š": 32, |
|
"♥": 33, |
|
"ń": 34, |
|
"щ": 35, |
|
"Ъ": 36, |
|
"ש": 37, |
|
"Ј": 38, |
|
"ů": 39, |
|
"ת": 40, |
|
"對": 41, |
|
"м": 42, |
|
"О": 43, |
|
"": 44, |
|
"¹": 45, |
|
"ř": 46, |
|
"„": 47, |
|
"û": 48, |
|
"А": 49, |
|
"н": 50, |
|
"ј": 51, |
|
"Ц": 52, |
|
",": 53, |
|
"ʼ": 54, |
|
"∀": 55, |
|
"舞": 56, |
|
"ѝ": 57, |
|
"Ў": 58, |
|
"ャ": 59, |
|
"(": 60, |
|
"ѐ": 61, |
|
"Ї": 62, |
|
"@": 63, |
|
"з": 64, |
|
"ί": 65, |
|
"ð": 66, |
|
"H": 67, |
|
"内": 68, |
|
"'": 69, |
|
"б": 70, |
|
"Š": 71, |
|
"Ä": 72, |
|
"ī": 73, |
|
"ύ": 74, |
|
"♂": 75, |
|
"": 76, |
|
"Ё": 77, |
|
"‹": 78, |
|
"?": 79, |
|
"P": 80, |
|
"ѵ": 81, |
|
"算": 82, |
|
"˙": 83, |
|
"φ": 84, |
|
"ґ": 85, |
|
"К": 86, |
|
"e": 87, |
|
"ö": 88, |
|
"Ж": 89, |
|
"с": 90, |
|
"д": 91, |
|
"ゼ": 92, |
|
"p": 93, |
|
"Н": 94, |
|
"ῦ": 95, |
|
"W": 96, |
|
"歓": 97, |
|
"ľ": 98, |
|
"/": 99, |
|
"ψ": 100, |
|
"": 101, |
|
"1": 102, |
|
"ὐ": 103, |
|
"だ": 104, |
|
"ר": 105, |
|
"ῷ": 106, |
|
"が": 107, |
|
"─": 108, |
|
"ル": 109, |
|
"Ω": 110, |
|
"加": 111, |
|
"": 112, |
|
"¸": 113, |
|
"й": 114, |
|
"%": 115, |
|
"三": 116, |
|
"✨": 117, |
|
"ћ": 118, |
|
"ȁ": 119, |
|
"ŭ": 120, |
|
"伎": 121, |
|
"ἄ": 122, |
|
"Р": 123, |
|
"ç": 124, |
|
"S": 125, |
|
"̀": 126, |
|
"Τ": 127, |
|
"ό": 128, |
|
"à": 129, |
|
"\t": 130, |
|
"▸": 131, |
|
"4": 132, |
|
"ŋ": 133, |
|
"⅝": 134, |
|
"ү": 135, |
|
"q": 136, |
|
"∪": 137, |
|
"松": 138, |
|
"!": 139, |
|
"ן": 140, |
|
"Ӂ": 141, |
|
"+": 142, |
|
"零": 143, |
|
"έ": 144, |
|
"ΰ": 145, |
|
"⅛": 146, |
|
"Ξ": 147, |
|
"カ": 148, |
|
"â": 149, |
|
"Ч": 150, |
|
"ж": 151, |
|
"¬": 152, |
|
"\"": 153, |
|
"ϊ": 154, |
|
"Ç": 155, |
|
"–": 156, |
|
"💥": 157, |
|
"☺": 158, |
|
"З": 159, |
|
"˛": 160, |
|
"fi": 161, |
|
"\u0005": 162, |
|
"Ì": 163, |
|
"": 164, |
|
"7": 165, |
|
"行": 166, |
|
"k": 167, |
|
"ו": 168, |
|
"½": 169, |
|
"§": 170, |
|
"す": 171, |
|
"へ": 172, |
|
"µ": 173, |
|
"ü": 174, |
|
"土": 175, |
|
"Θ": 176, |
|
"ë": 177, |
|
"⅜": 178, |
|
"‚": 179, |
|
"һ": 180, |
|
"き": 181, |
|
"_": 182, |
|
"ă": 183, |
|
"ύ": 184, |
|
"ї": 185, |
|
"—": 186, |
|
"·": 187, |
|
"Ê": 188, |
|
"ρ": 189, |
|
":": 190, |
|
"8": 191, |
|
"ú": 192, |
|
"《": 193, |
|
"A": 194, |
|
"Υ": 195, |
|
"\u0002": 196, |
|
"ѓ": 197, |
|
"Ż": 198, |
|
"ә": 199, |
|
"ό": 200, |
|
"ス": 201, |
|
">": 202, |
|
"ś": 203, |
|
"K": 204, |
|
"њ": 205, |
|
"к": 206, |
|
"²": 207, |
|
"": 208, |
|
"Γ": 209, |
|
"5": 210, |
|
"●": 211, |
|
"R": 212, |
|
"ф": 213, |
|
"Π": 214, |
|
"ᾳ": 215, |
|
"能": 216, |
|
"Ρ": 217, |
|
"Â": 218, |
|
"č": 219, |
|
"è": 220, |
|
"": 221, |
|
"ἱ": 222, |
|
"!": 223, |
|
"M": 224, |
|
"❄": 225, |
|
"t": 226, |
|
"も": 227, |
|
"ξ": 228, |
|
"ή": 229, |
|
"Í": 230, |
|
"I": 231, |
|
"ы": 232, |
|
"ё": 233, |
|
"️": 234, |
|
"É": 235, |
|
"Ã": 236, |
|
"ɪ": 237, |
|
"o": 238, |
|
"": 239, |
|
"ώ": 240, |
|
"ϑ": 241, |
|
"*": 242, |
|
"Я": 243, |
|
"э": 244, |
|
"Ē": 245, |
|
"Ř": 246, |
|
"˗": 247, |
|
"": 248, |
|
"″": 249, |
|
"õ": 250, |
|
"O": 251, |
|
"Ϊ": 252, |
|
"ー": 253, |
|
"χ": 254, |
|
"ю": 255, |
|
"ν": 256, |
|
"|": 257, |
|
"た": 258, |
|
"−": 259, |
|
"う": 260, |
|
"џ": 261, |
|
"Č": 262, |
|
"П": 263, |
|
"√": 264, |
|
"歪": 265, |
|
" ": 266, |
|
"l": 267, |
|
"ò": 268, |
|
"℅": 269, |
|
"р": 270, |
|
"þ": 271, |
|
"ュ": 272, |
|
"z": 273, |
|
"”": 274, |
|
"ş": 275, |
|
"ê": 276, |
|
"À": 277, |
|
"α": 278, |
|
"座": 279, |
|
"→": 280, |
|
"X": 281, |
|
"⠀": 282, |
|
"δ": 283, |
|
"ὼ": 284, |
|
"ὑ": 285, |
|
"Ы": 286, |
|
"‘": 287, |
|
"ä": 288, |
|
"ň": 289, |
|
"": 290, |
|
"b": 291, |
|
"ė": 292, |
|
"¡": 293, |
|
"c": 294, |
|
"•": 295, |
|
"י": 296, |
|
"ク": 297, |
|
"ῖ": 298, |
|
"め": 299, |
|
"歌": 300, |
|
"♡": 301, |
|
"ħ": 302, |
|
"w": 303, |
|
"⅓": 304, |
|
"ű": 305, |
|
"Ý": 306, |
|
"у": 307, |
|
"n": 308, |
|
"": 309, |
|
" ": 310, |
|
"↔": 311, |
|
"Ѕ": 312, |
|
" ": 313, |
|
"": 314, |
|
"ά": 315, |
|
"Ó": 316, |
|
"j": 317, |
|
"字": 318, |
|
"子": 319, |
|
"Δ": 320, |
|
" ": 321, |
|
"ï": 322, |
|
"灯": 323, |
|
"下": 324, |
|
"r": 325, |
|
"Ü": 326, |
|
"g": 327, |
|
"ῤ": 328, |
|
"∙": 329, |
|
"ң": 330, |
|
"♠": 331, |
|
"ő": 332, |
|
"о": 333, |
|
"⅞": 334, |
|
"‡": 335, |
|
"┴": 336, |
|
"¼": 337, |
|
"ø": 338, |
|
"↑": 339, |
|
"‰": 340, |
|
"v": 341, |
|
"{": 342, |
|
"ш": 343, |
|
"Λ": 344, |
|
"口": 345, |
|
"∥": 346, |
|
"□": 347, |
|
"ā": 348, |
|
"を": 349, |
|
"´": 350, |
|
"Ќ": 351, |
|
"€": 352, |
|
"": 353, |
|
"λ": 354, |
|
"Å": 355, |
|
"¾": 356, |
|
"\b": 357, |
|
"º": 358, |
|
"ô": 359, |
|
"№": 360, |
|
"ž": 361, |
|
"\n": 362, |
|
"ę": 363, |
|
"֠": 364, |
|
"∧": 365, |
|
"ż": 366, |
|
"³": 367, |
|
"′": 368, |
|
"æ": 369, |
|
"Φ": 370, |
|
"ū": 371, |
|
"ϕ": 372, |
|
"́": 373, |
|
"È": 374, |
|
"ム": 375, |
|
"ὁ": 376, |
|
"`": 377, |
|
"Ú": 378, |
|
"™": 379, |
|
"Б": 380, |
|
")": 381, |
|
"ч": 382, |
|
"ἶ": 383, |
|
"►": 384, |
|
"Ь": 385, |
|
"6": 386, |
|
"戦": 387, |
|
"T": 388, |
|
"Ν": 389, |
|
"ま": 390, |
|
"F": 391, |
|
"≈": 392, |
|
"⅔": 393, |
|
"ý": 394, |
|
"π": 395, |
|
"ί": 396, |
|
"Ε": 397, |
|
"ì": 398, |
|
"火": 399, |
|
"ζ": 400, |
|
"9": 401, |
|
"&": 402, |
|
"Q": 403, |
|
"": 404, |
|
"¶": 405, |
|
"Χ": 406, |
|
"Ѵ": 407, |
|
"ὺ": 408, |
|
"C": 409, |
|
"Ѓ": 410, |
|
"×": 411, |
|
"₂": 412, |
|
"U": 413, |
|
"Ѳ": 414, |
|
"Є": 415, |
|
"ď": 416, |
|
"¦": 417, |
|
"Э": 418, |
|
"β": 419, |
|
"»": 420, |
|
"ἀ": 421, |
|
"±": 422, |
|
"ω": 423, |
|
"†": 424, |
|
"«": 425, |
|
"῾": 426, |
|
"Κ": 427, |
|
"ロ": 428, |
|
"i": 429, |
|
"Ѹ": 430, |
|
"灸": 431, |
|
"~": 432, |
|
"Œ": 433, |
|
"\u0010": 434, |
|
"�": 435, |
|
"ἡ": 436, |
|
"Ө": 437, |
|
"υ": 438, |
|
"体": 439, |
|
"に": 440, |
|
"Х": 441, |
|
"ὴ": 442, |
|
"よ": 443, |
|
"á": 444, |
|
"撃": 445, |
|
"\f": 446, |
|
"Ω": 447, |
|
";": 448, |
|
"І": 449, |
|
"=": 450, |
|
"ǐ": 451, |
|
"シ": 452, |
|
"ğ": 453, |
|
"В": 454, |
|
"מ": 455, |
|
"≠": 456, |
|
"#": 457, |
|
"җ": 458, |
|
"ө": 459, |
|
"˝": 460, |
|
"ἁ": 461, |
|
"Ζ": 462, |
|
"ÿ": 463, |
|
"■": 464, |
|
"΄": 465, |
|
"ὶ": 466, |
|
"L": 467, |
|
"п": 468, |
|
"®": 469, |
|
"״": 470, |
|
"2": 471, |
|
"<": 472, |
|
"…": 473, |
|
"0": 474, |
|
"x": 475, |
|
"τ": 476, |
|
"爪": 477, |
|
"ὦ": 478, |
|
"y": 479, |
|
"ὕ": 480, |
|
"і": 481, |
|
"ь": 482, |
|
"Д": 483, |
|
"љ": 484, |
|
"ϋ": 485, |
|
"ε": 486, |
|
"σ": 487, |
|
"ñ": 488, |
|
"ć": 489, |
|
"Σ": 490, |
|
"ц": 491, |
|
"䋚": 492, |
|
"í": 493, |
|
"“": 494, |
|
"Е": 495, |
|
"°": 496, |
|
"▲": 497, |
|
"т": 498, |
|
"ź": 499, |
|
"и": 500, |
|
"Љ": 501, |
|
"ó": 502, |
|
"-": 503, |
|
"迎": 504, |
|
"Ґ": 505, |
|
"E": 506, |
|
"Æ": 507, |
|
"Β": 508, |
|
"♦": 509, |
|
"£": 510, |
|
"Ѡ": 511, |
|
" ": 512, |
|
"ι": 513, |
|
"Ά": 514, |
|
"У": 515, |
|
"ὰ": 516, |
|
"Ô": 517, |
|
"\u000e": 518, |
|
"ה": 519, |
|
"Ł": 520, |
|
"η": 521, |
|
"Έ": 522, |
|
"а": 523, |
|
"]": 524, |
|
"ã": 525, |
|
"G": 526, |
|
"ъ": 527, |
|
"θ": 528, |
|
"х": 529, |
|
"h": 530, |
|
"א": 531, |
|
"ἕ": 532, |
|
"ϰ": 533, |
|
"J": 534, |
|
"}": 535, |
|
"Ø": 536, |
|
"り": 537, |
|
"-": 538, |
|
"г": 539, |
|
"ἐ": 540, |
|
"♀": 541, |
|
"л": 542, |
|
"面": 543, |
|
"ĕ": 544, |
|
"ο": 545, |
|
"ל": 546, |
|
".": 547, |
|
"a": 548, |
|
"る": 549, |
|
"μ": 550, |
|
"": 551, |
|
"ː": 552, |
|
"ı": 553, |
|
" ": 554, |
|
"М": 555, |
|
"ị": 556, |
|
"―": 557, |
|
"в": 558, |
|
"᾽": 559, |
|
"ў": 560, |
|
"Г": 561, |
|
"😇": 562, |
|
"ť": 563, |
|
"Л": 564, |
|
"↓": 565, |
|
"é": 566, |
|
"え": 567, |
|
"ς": 568, |
|
"ʙ": 569, |
|
"藁": 570, |
|
"Ο": 571, |
|
"チ": 572, |
|
"ב": 573, |
|
"Y": 574, |
|
"m": 575, |
|
"Ò": 576, |
|
"С": 577, |
|
"ē": 578, |
|
"\\": 579, |
|
"ホ": 580, |
|
"い": 581, |
|
"(": 582, |
|
" ": 583, |
|
"÷": 584, |
|
"ˆ": 585, |
|
"N": 586, |
|
"Ш": 587, |
|
"ą": 588, |
|
"Ι": 589, |
|
"¤": 590, |
|
"ῥ": 591, |
|
"抗": 592, |
|
"ѣ": 593, |
|
"Μ": 594, |
|
"": 595, |
|
"́": 596, |
|
"Џ": 597, |
|
"ł": 598, |
|
"s": 599, |
|
"╦": 600, |
|
"ΐ": 601, |
|
"B": 602, |
|
"є": 603, |
|
"": 604, |
|
"育": 605, |
|
"å": 606, |
|
"ῆ": 607, |
|
"u": 608, |
|
" ": 609, |
|
"^": 610, |
|
"е": 611, |
|
"ά": 612, |
|
"3": 613, |
|
"Ö": 614, |
|
"Ю": 615, |
|
"電": 616, |
|
"Ž": 617, |
|
"Α": 618, |
|
"Щ": 619, |
|
"ὔ": 620, |
|
"ù": 621, |
|
"[": 622, |
|
"♣": 623, |
|
"Ś": 624, |
|
"ῳ": 625, |
|
"Њ": 626, |
|
"V": 627, |
|
"œ": 628, |
|
"Ş": 629, |
|
"‑": 630, |
|
"Η": 631, |
|
"d": 632, |
|
"ˈ": 633, |
|
"∂": 634, |
|
"Ћ": 635, |
|
"ß": 636, |
|
"đ": 637, |
|
"И": 638, |
|
"κ": 639, |
|
" ": 640, |
|
"の": 641, |
|
"ῶ": 642, |
|
")": 643, |
|
"ě": 644, |
|
"ѕ": 645, |
|
"î": 646, |
|
"半": 647, |
|
"≥": 648, |
|
"\u0004": 649, |
|
"⅟": 650, |
|
"D": 651, |
|
"‒": 652, |
|
"’": 653, |
|
"›": 654, |
|
"f": 655, |
|
"©": 656, |
|
"ꐜ": 657, |
|
"+а": 658, |
|
"+е": 659, |
|
"+ё": 660, |
|
"+и": 661, |
|
"+о": 662, |
|
"+у": 663, |
|
"+ы": 664, |
|
"+э": 665, |
|
"+ю": 666, |
|
"+я": 667 |
|
} |