hf-transformers-bot's picture
Upload tiny models for OwlViTForObjectDetection
bda4316
Raw History Blame Contribute Delete
33.5 kB
{ "version": "1.0", "truncation": null, "padding": null, "added_tokens": [ { "id": 0, "content": "!", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 1, "content": "<|startoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": true }, { "id": 2, "content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": true } ], "normalizer": { "type": "Sequence", "normalizers": [ { "type": "NFC" }, { "type": "Replace", "pattern": { "Regex": "\\s+" }, "content": " " }, { "type": "Lowercase" } ] }, "pre_tokenizer": { "type": "Sequence", "pretokenizers": [ { "type": "Split", "pattern": { "Regex": "'s|'t|'re|'ve|'m|'ll|'d|[\\p{L}]+|[\\p{N}]|[^\\s\\p{L}\\p{N}]+" }, "behavior": "Removed", "invert": true }, { "type": "ByteLevel", "add_prefix_space": false, "trim_offsets": true, "use_regex": true } ] }, "post_processor": { "type": "RobertaProcessing", "sep": [ "<|endoftext|>", 2 ], "cls": [ "<|startoftext|>", 1 ], "trim_offsets": false, "add_prefix_space": false }, "decoder": { "type": "ByteLevel", "add_prefix_space": true, "trim_offsets": true, "use_regex": true }, "model": { "type": "BPE", "dropout": null, "unk_token": "<|endoftext|>", "continuing_subword_prefix": "", "end_of_word_suffix": "</w>", "fuse_unk": false, "vocab": { "!": 0, "<|startoftext|>": 1, "<|endoftext|>": 2, "\"": 3, "#": 4, "$": 5, "%": 6, "&": 7, "'": 8, "(": 9, ")": 10, "*": 11, "+": 12, ",": 13, "-": 14, ".": 15, "/": 16, "0": 17, "1": 18, "2": 19, "3": 20, "4": 21, "5": 22, "6": 23, "7": 24, "8": 25, "9": 26, ":": 27, ";": 28, "<": 29, "=": 30, ">": 31, "?": 32, "@": 33, "[": 34, "\\": 35, "]": 36, "^": 37, "_": 38, "`": 39, "a": 40, "b": 41, "c": 42, "d": 43, "e": 44, "f": 45, "g": 46, "h": 47, "i": 48, "j": 49, "k": 50, "l": 51, "m": 52, "n": 53, "o": 54, "p": 55, "q": 56, "r": 57, "s": 58, "t": 59, "u": 60, "v": 61, "w": 62, "x": 63, "y": 64, "z": 65, "|": 66, "}": 67, "~": 68, "¡": 69, "¢": 70, "£": 71, "¤": 72, "¥": 73, "¦": 74, "§": 75, "¨": 76, "©": 77, "ª": 78, "«": 79, "¬": 80, "®": 81, "¯": 82, "°": 83, "±": 84, "²": 85, "³": 86, "´": 87, "µ": 88, "¶": 89, "·": 90, "¸": 91, "¹": 92, "º": 93, "»": 94, "¼": 95, "½": 96, "¾": 97, "¿": 98, "Â": 99, "Ã": 100, "Ä": 101, "Å": 102, "Æ": 103, "Ç": 104, "È": 105, "É": 106, "Ê": 107, "Ë": 108, "Ì": 109, "Í": 110, "Î": 111, "Ï": 112, "Ð": 113, "Ñ": 114, "Ö": 115, "×": 116, "Ø": 117, "Ù": 118, "Ü": 119, "à": 120, "á": 121, "â": 122, "ã": 123, "ä": 124, "å": 125, "æ": 126, "ç": 127, "è": 128, "é": 129, "ë": 130, "ì": 131, "ï": 132, "Ģ": 133, "ģ": 134, "Ĥ": 135, "ĥ": 136, "Ħ": 137, "ħ": 138, "Ĩ": 139, "ĩ": 140, "Ī": 141, "ī": 142, "Ĭ": 143, "ĭ": 144, "Į": 145, "į": 146, "İ": 147, "ı": 148, "IJ": 149, "ij": 150, "Ĵ": 151, "ĵ": 152, "Ķ": 153, "ķ": 154, "ĸ": 155, "Ĺ": 156, "ĺ": 157, "Ļ": 158, "ļ": 159, "Ľ": 160, "ľ": 161, "Ŀ": 162, "ŀ": 163, "Ł": 164, "ł": 165, "Ń": 166, "e</w>": 167, "n</w>": 168, "s</w>": 169, "o</w>": 170, "g</w>": 171, "a</w>": 172, "r</w>": 173, "t</w>": 174, "w</w>": 175, "d</w>": 176, "y</w>": 177, "i</w>": 178, "p</w>": 179, "l</w>": 180, "h</w>": 181, "f</w>": 182, "k</w>": 183, "c</w>": 184, "v</w>": 185, "m</w>": 186, "x</w>": 187, "z</w>": 188, "u</w>": 189, "ľ</w>": 190, "[</w>": 191, "ģ</w>": 192, "|</w>": 193, "¼</w>": 194, "j</w>": 195, "į</w>": 196, "²</w>": 197, "b</w>": 198, "ĩ</w>": 199, "Ļ</w>": 200, "¿</w>": 201, "¡</w>": 202, "'</w>": 203, "></w>": 204, "¢</w>": 205, "±</w>": 206, "·</w>": 207, "¶</w>": 208, "«</w>": 209, "¤</w>": 210, "©</w>": 211, "½</w>": 212, "³</w>": 213, "Ń</w>": 214, "\\</w>": 215, "+</w>": 216, "¸</w>": 217, "¨</w>": 218, "Ł</w>": 219, "ĺ</w>": 220, "Ľ</w>": 221, "¹</w>": 222, "Ĩ</w>": 223, "Ģ</w>": 224, "Ĺ</w>": 225, "°</w>": 226, "-</w>": 227, "Ĥ</w>": 228, "Į</w>": 229, "ħ</w>": 230, "Ĭ</w>": 231, "§</w>": 232, "IJ</w>": 233, "`</w>": 234, "q</w>": 235, "ķ</w>": 236, "µ</w>": 237, "ī</w>": 238, "º</w>": 239, "!</w>": 240, "¯</w>": 241, "Ŀ</w>": 242, "Ħ</w>": 243, "ł</w>": 244, "%</w>": 245, "£</w>": 246, "¦</w>": 247, "ŀ</w>": 248, "¾</w>": 249, "´</w>": 250, "ĵ</w>": 251, "^</w>": 252, "Ķ</w>": 253, "ª</w>": 254, "»</w>": 255, "0</w>": 256, "5</w>": 257, "ĸ</w>": 258, "ļ</w>": 259, "İ</w>": 260, "=</w>": 261, "Ĵ</w>": 262, "Ī</w>": 263, "ĥ</w>": 264, "¥</w>": 265, "®</w>": 266, "3</w>": 267, "¬</w>": 268, ".</w>": 269, "1</w>": 270, "ĭ</w>": 271, "ij</w>": 272, "@</w>": 273, "&</w>": 274, "ı</w>": 275, "~</w>": 276, "8</w>": 277, "}</w>": 278, "*</w>": 279, ";</w>": 280, "\"</w>": 281, "2</w>": 282, "(</w>": 283, ")</w>": 284, "4</w>": 285, "9</w>": 286, "/</w>": 287, ":</w>": 288, "#</w>": 289, ",</w>": 290, "$</w>": 291, "]</w>": 292, "<</w>": 293, "_</w>": 294, "?</w>": 295, "6</w>": 296, "7</w>": 297, "th": 298, "the</w>": 299, "in": 300, "an": 301, "ed</w>": 302, "er": 303, "re": 304, "ar": 305, "ti": 306, "on": 307, "en": 308, "of</w>": 309, "or": 310, "and</w>": 311, "er</w>": 312, "on</w>": 313, "in</w>": 314, "ing</w>": 315, "st": 316, "ro": 317, "al": 318, "it": 319, "to</w>": 320, "as</w>": 321, "at": 322, "es</w>": 323, "ou": 324, "hi": 325, "ac": 326, "si": 327, "at</w>": 328, "ri": 329, "al</w>": 330, "el": 331, "an</w>": 332, "am": 333, "or</w>": 334, "st</w>": 335, "li": 336, "ur": 337, "ec": 338, "om": 339, "di": 340, "was</w>": 341, "ly</w>": 342, "en</w>": 343, "ea": 344, "ch": 345, "un": 346, "tion</w>": 347, "la": 348, "is</w>": 349, "fi": 350, "ol": 351, "de": 352, "-@</w>": 353, "@-@</w>": 354, "ra": 355, "vi": 356, "le</w>": 357, "lo": 358, "sh": 359, "em": 360, "be": 361, "that</w>": 362, "'s</w>": 363, "con": 364, "ma": 365, "for</w>": 366, "ha": 367, "su": 368, "by</w>": 369, "ith</w>": 370, "ve</w>": 371, "with</w>": 372, "se</w>": 373, "ch</w>": 374, "the": 375, "ent": 376, "po": 377, "ce</w>": 378, "il": 379, "se": 380, "ent</w>": 381, "le": 382, "com": 383, "sp": 384, "ere</w>": 385, "pro": 386, "no": 387, "bu": 388, "wh": 389, "it</w>": 390, "th</w>": 391, "ver": 392, "ne": 393, "ca": 394, "is": 395, "for": 396, "ag": 397, "ers</w>": 398, "mo": 399, "gh": 400, "fro": 401, "ted</w>": 402, "from</w>": 403, "tion": 404, "op": 405, "his</w>": 406, "ad": 407, "ab": 408, "ic": 409, "he</w>": 410, "oun": 411, "as": 412, "ts</w>": 413, "sc": 414, "de</w>": 415, "ow": 416, "ex": 417, "whi": 418, "ru": 419, "ter</w>": 420, "ap": 421, "ds</w>": 422, "were</w>": 423, "pre": 424, "du": 425, "gu": 426, "par": 427, "ir": 428, "bo": 429, "ther</w>": 430, "qu": 431, "lu": 432, "ter": 433, "tw": 434, "es": 435, "rec": 436, "per": 437, "ta": 438, "ate</w>": 439, "ver</w>": 440, "ated</w>": 441, "ding</w>": 442, "ity</w>": 443, "man": 444, "ear": 445, "sed</w>": 446, "ded</w>": 447, "au": 448, "all</w>": 449, "ame</w>": 450, "ci": 451, "one</w>": 452, "ing": 453, "are</w>": 454, "af": 455, "ir</w>": 456, "ation</w>": 457, "âĢ": 458, "had</w>": 459, "tr": 460, "ul": 461, "ld</w>": 462, "which</w>": 463, "wa": 464, "im": 465, "lea": 466, "be</w>": 467, "to": 468, "tim": 469, "fir": 470, "wor": 471, "ong</w>": 472, "por": 473, "mar": 474, "me": 475, "ally</w>": 476, "so</w>": 477, "out</w>": 478, "tions</w>": 479, "its</w>": 480, "gh</w>": 481, "ge</w>": 482, "ber</w>": 483, "fe": 484, "pu": 485, "ser": 486, "der": 487, "pl": 488, "ss</w>": 489, "ine</w>": 490, "inc": 491, "mi": 492, "ght</w>": 493, "go": 494, "this</w>": 495, "tur": 496, "da": 497, "rou": 498, "but</w>": 499, "um": 500, "son</w>": 501, "we": 502, "ved</w>": 503, "sion</w>": 504, "ke</w>": 505, "pla": 506, "their</w>": 507, "ies</w>": 508, "first</w>": 509, "sa": 510, "oc": 511, "att": 512, "of": 513, "pe": 514, "not</w>": 515, "gi": 516, "na": 517, "ary</w>": 518, "mu": 519, "led</w>": 520, "âĢĵ</w>": 521, "her</w>": 522, "ran": 523, "co": 524, "they</w>": 525, "der</w>": 526, "ali": 527, "also</w>": 528, "ore</w>": 529, "ep": 530, "ould</w>": 531, "after</w>": 532, "shi": 533, "us</w>": 534, "et</w>": 535, "tic": 536, "stor": 537, "wi": 538, "ev": 539, "other</w>": 540, "sh</w>": 541, "ting</w>": 542, "ard</w>": 543, "te": 544, "two</w>": 545, "ni": 546, "have</w>": 547, "our": 548, "comm": 549, "te</w>": 550, "ack</w>": 551, "oo": 552, "fin": 553, "sec": 554, "ents</w>": 555, "has</w>": 556, "comp": 557, "bec": 558, "ks</w>": 559, "cont": 560, "land</w>": 561, "been</w>": 562, "ence</w>": 563, "king</w>": 564, "el</w>": 565, "age</w>": 566, "low": 567, "min": 568, ".@</w>": 569, "@.@</w>": 570, "ome</w>": 571, "ment</w>": 572, "char": 573, "ge": 574, "ater</w>": 575, "nor": 576, "ho": 577, "ous</w>": 578, "who</w>": 579, "ear</w>": 580, "spec": 581, "col": 582, "ely</w>": 583, "ty</w>": 584, "jo": 585, "uring</w>": 586, "duc": 587, "bri": 588, "str": 589, "can": 590, "ori": 591, "tra": 592, "pa": 593, "she</w>": 594, "do": 595, "tive</w>": 596, "mon": 597, "new</w>": 598, "rit": 599, "time</w>": 600, "ons</w>": 601, "so": 602, "man</w>": 603, "dec": 604, "cent": 605, "lan": 606, "pi": 607, "our</w>": 608, "inter": 609, "fer": 610, "gra": 611, "gre": 612, "res</w>": 613, "inclu": 614, "mil": 615, "during</w>": 616, "own</w>": 617, "pres": 618, "ju": 619, "ned</w>": 620, "ell</w>": 621, ",@</w>": 622, "@,@</w>": 623, "ite</w>": 624, "gen": 625, "when</w>": 626, "sig": 627, "bi": 628, "ren": 629, "fa": 630, "ga": 631, "play": 632, "eng": 633, "tional</w>": 634, "ound</w>": 635, "thou": 636, "more</w>": 637, "ree</w>": 638, "ember</w>": 639, "ei": 640, "sou": 641, "sur": 642, "sti": 643, "car": 644, "form": 645, "lar": 646, "ses</w>": 647, "ten": 648, "into</w>": 649, "tu": 650, "ces</w>": 651, "most</w>": 652, "ked</w>": 653, "way</w>": 654, "cre": 655, "coun": 656, "up</w>": 657, "les</w>": 658, "ace</w>": 659, "als</w>": 660, "ke": 661, "would</w>": 662, "ant</w>": 663, "ber": 664, "fu": 665, "ited</w>": 666, "pri": 667, "while</w>": 668, "over</w>": 669, "ings</w>": 670, "re</w>": 671, "fil": 672, "sy": 673, "est": 674, "able</w>": 675, "wn</w>": 676, "sea": 677, "ach": 678, "sing</w>": 679, "ins</w>": 680, "tic</w>": 681, "id</w>": 682, "only</w>": 683, "ates</w>": 684, "tri": 685, "ving</w>": 686, "ba": 687, "vel": 688, "ance</w>": 689, "sta": 690, "ern</w>": 691, "fol": 692, "een</w>": 693, "ined</w>": 694, "stru": 695, "uni": 696, "game</w>": 697, "lar</w>": 698, "sel": 699, "bli": 700, "used</w>": 701, "ning</w>": 702, "ps</w>": 703, "ties</w>": 704, "kno": 705, "cor": 706, "ft</w>": 707, "recor": 708, "ble</w>": 709, "vie": 710, "ys</w>": 711, "wil": 712, "ical</w>": 713, "app": 714, "tro": 715, "three</w>": 716, "cla": 717, "old</w>": 718, "shed</w>": 719, "hea": 720, "about</w>": 721, "writ": 722, "than</w>": 723, "ste": 724, "later</w>": 725, "ari": 726, "dy</w>": 727, "publi": 728, "loc": 729, "aga": 730, "throu": 731, "ssi": 732, "end</w>": 733, "may</w>": 734, "ang": 735, "ach</w>": 736, "ves</w>": 737, "og": 738, "him</w>": 739, "betw": 740, "though</w>": 741, "between</w>": 742, "um</w>": 743, "star": 744, "scri": 745, "rea": 746, "ond</w>": 747, "ship</w>": 748, "ok</w>": 749, "hel": 750, "song</w>": 751, "chi": 752, "cap": 753, "ever</w>": 754, "day</w>": 755, "cri": 756, "some</w>": 757, "bro": 758, "no</w>": 759, "there</w>": 760, "ans</w>": 761, "all": 762, "num": 763, "red</w>": 764, "ears</w>": 765, "sts</w>": 766, "any</w>": 767, "war": 768, "ph": 769, "pp": 770, "gin": 771, "struc": 772, "amer": 773, "produc": 774, "sch": 775, "ces": 776, "ure</w>": 777, "ating</w>": 778, "emp": 779, "tor": 780, "season</w>": 781, "fore</w>": 782, "ic</w>": 783, "city</w>": 784, "gro": 785, "follow": 786, "sub": 787, "bel": 788, "year</w>": 789, "can</w>": 790, "sin": 791, "where</w>": 792, "and": 793, "made</w>": 794, "relea": 795, "sm": 796, "bl": 797, "ten</w>": 798, "with": 799, "son": 800, "many</w>": 801, "are": 802, "ed": 803, "how": 804, "americ": 805, "ury</w>": 806, "stu": 807, "musi": 808, "cu": 809, "nam": 810, "ement</w>": 811, "such</w>": 812, "albu": 813, "buil": 814, "before</w>": 815, "ef": 816, "arm": 817, "ton</w>": 818, "them</w>": 819, "cal": 820, "bar": 821, "des</w>": 822, "mat": 823, "gener": 824, "od</w>": 825, "series</w>": 826, "cer": 827, "sho": 828, "enti": 829, "her": 830, "over": 831, "ann": 832, "well</w>": 833, "world</w>": 834, "gan</w>": 835, "est</w>": 836, "second</w>": 837, "ters</w>": 838, "side</w>": 839, "tran": 840, "line</w>": 841, "ture</w>": 842, "port</w>": 843, "being</w>": 844, "years</w>": 845, "both</w>": 846, "indi": 847, "these</w>": 848, "national</w>": 849, "histor": 850, "fe</w>": 851, "vo": 852, "sted</w>": 853, "ani": 854, "bas": 855, "poin": 856, "sing": 857, "film</w>": 858, "pen": 859, "sup": 860, "mis": 861, "cro": 862, "stri": 863, "lin": 864, "tre": 865, "war</w>": 866, "however</w>": 867, "ying</w>": 868, "ling</w>": 869, "yp": 870, "ected</w>": 871, "direc": 872, "vision</w>": 873, "album</w>": 874, "then</w>": 875, "ll</w>": 876, "sever": 877, "through</w>": 878, "known</w>": 879, "bor": 880, "cul": 881, "clu": 882, "ster</w>": 883, "south</w>": 884, "ry</w>": 885, "ect</w>": 886, "low</w>": 887, "pr": 888, "sk": 889, "iso": 890, "north</w>": 891, "part</w>": 892, "fac": 893, "tly</w>": 894, "peri": 895, "eu": 896, "batt": 897, "state</w>": 898, "ced</w>": 899, "consi": 900, "inf": 901, "poli": 902, "olog": 903, "early</w>": 904, "posi": 905, "ames</w>": 906, "win": 907, "devel": 908, "ob": 909, "ve": 910, "ven</w>": 911, "oper": 912, "ger": 913, "offi": 914, "charac": 915, "ms</w>": 916, "high": 917, "ad</w>": 918, "tho": 919, "several</w>": 920, "dre": 921, "descri": 922, "ale</w>": 923, "number</w>": 924, "air": 925, "including</w>": 926, "inst</w>": 927, "against</w>": 928, "ls</w>": 929, "sul": 930, "episo": 931, "cam": 932, "dif": 933, "soci": 934, "became</w>": 935, "like</w>": 936, "tel": 937, "four</w>": 938, "âĢĶ</w>": 939, "hou": 940, "joh": 941, "united</w>": 942, "inv": 943, "under</w>": 944, "nov": 945, "tiv": 946, "suc": 947, "ations</w>": 948, "ack": 949, "tor</w>": 950, "ron": 951, "und</w>": 952, "ws</w>": 953, "fo": 954, "gr": 955, "develop": 956, "although</w>": 957, "contin": 958, "west</w>": 959, "origin": 960, "music</w>": 961, "ors</w>": 962, "don</w>": 963, "century</w>": 964, "ward</w>": 965, "work</w>": 966, "me</w>": 967, "ami": 968, "cha": 969, "very</w>": 970, "har": 971, "dis": 972, "zed</w>": 973, "do</w>": 974, "gs</w>": 975, "tow": 976, "sol": 977, "following</w>": 978, "lion</w>": 979, "rema": 980, "ns</w>": 981, "tish</w>": 982, "chur": 983, "som": 984, "mp": 985, "tle</w>": 986, "gover": 987, "del": 988, "comple": 989, "cur": 990, "use</w>": 991, "back</w>": 992, "hu": 993, "stern</w>": 994, "began</w>": 995, "fiel": 996, "ause</w>": 997, "dra": 998, "pas": 999, "bil": 1000, "cation</w>": 1001, "dent</w>": 1002, "bed</w>": 1003, "because</w>": 1004, "ant": 1005, "eam</w>": 1006, "phi": 1007, "yo": 1008, "continu": 1009, "tain</w>": 1010, "try</w>": 1011, "fre": 1012, "peop": 1013, "called</w>": 1014, "found</w>": 1015, "episode</w>": 1016, "desig": 1017, "mor": 1018, "set</w>": 1019, "ley</w>": 1020, "east</w>": 1021, "trac": 1022, "cra": 1023 }, "merges": [ "t h", "th e</w>", "i n", "a n", "e d</w>", "e r", "r e", "a r", "t i", "o n", "e n", "o f</w>", "o r", "an d</w>", "e r</w>", "o n</w>", "i n</w>", "in g</w>", "s t", "r o", "a l", "i t", "t o</w>", "a s</w>", "a t", "e s</w>", "o u", "h i", "a c", "s i", "a t</w>", "r i", "a l</w>", "e l", "a n</w>", "a m", "o r</w>", "s t</w>", "l i", "u r", "e c", "o m", "d i", "w as</w>", "l y</w>", "e n</w>", "e a", "c h", "u n", "ti on</w>", "l a", "i s</w>", "f i", "o l", "d e", "- @</w>", "@ -@</w>", "r a", "v i", "l e</w>", "l o", "s h", "e m", "b e", "th at</w>", "' s</w>", "c on", "m a", "f or</w>", "h a", "s u", "b y</w>", "it h</w>", "v e</w>", "w ith</w>", "s e</w>", "c h</w>", "th e", "en t", "p o", "c e</w>", "i l", "s e", "en t</w>", "l e", "c om", "s p", "er e</w>", "p ro", "n o", "b u", "w h", "i t</w>", "t h</w>", "v er", "n e", "c a", "i s", "f or", "a g", "er s</w>", "m o", "g h", "f ro", "t ed</w>", "fro m</w>", "ti on", "o p", "hi s</w>", "a d", "a b", "i c", "h e</w>", "ou n", "a s", "t s</w>", "s c", "d e</w>", "o w", "e x", "w hi", "r u", "t er</w>", "a p", "d s</w>", "w ere</w>", "p re", "d u", "g u", "p ar", "i r", "b o", "th er</w>", "q u", "l u", "t er", "t w", "e s", "re c", "p er", "t a", "at e</w>", "v er</w>", "at ed</w>", "d ing</w>", "it y</w>", "m an", "e ar", "s ed</w>", "d ed</w>", "a u", "al l</w>", "am e</w>", "c i", "on e</w>", "in g", "ar e</w>", "a f", "i r</w>", "a tion</w>", "â Ģ", "ha d</w>", "t r", "u l", "l d</w>", "whi ch</w>", "w a", "i m", "l ea", "b e</w>", "t o", "ti m", "fi r", "w or", "on g</w>", "p or", "m ar", "m e", "al ly</w>", "s o</w>", "ou t</w>", "tion s</w>", "it s</w>", "g h</w>", "g e</w>", "b er</w>", "f e", "p u", "s er", "d er", "p l", "s s</w>", "in e</w>", "in c", "m i", "gh t</w>", "g o", "th is</w>", "t ur", "d a", "ro u", "bu t</w>", "u m", "s on</w>", "w e", "v ed</w>", "si on</w>", "k e</w>", "p la", "the ir</w>", "i es</w>", "fir st</w>", "s a", "o c", "at t", "o f", "p e", "no t</w>", "g i", "n a", "ar y</w>", "m u", "l ed</w>", "âĢ ĵ</w>", "h er</w>", "r an", "c o", "the y</w>", "d er</w>", "al i", "al so</w>", "or e</w>", "e p", "ou ld</w>", "af ter</w>", "s hi", "u s</w>", "e t</w>", "ti c", "st or", "w i", "e v", "o ther</w>", "s h</w>", "t ing</w>", "ar d</w>", "t e", "tw o</w>", "n i", "ha ve</w>", "ou r", "com m", "t e</w>", "ac k</w>", "o o", "f in", "s ec", "ent s</w>", "h as</w>", "com p", "b ec", "k s</w>", "con t", "l and</w>", "be en</w>", "en ce</w>", "k ing</w>", "e l</w>", "ag e</w>", "lo w", "m in", ". @</w>", "@ .@</w>", "om e</w>", "m ent</w>", "ch ar", "g e", "at er</w>", "n or", "h o", "ou s</w>", "wh o</w>", "ea r</w>", "sp ec", "c ol", "el y</w>", "t y</w>", "j o", "ur ing</w>", "du c", "b ri", "st r", "c an", "or i", "t ra", "p a", "sh e</w>", "d o", "ti ve</w>", "m on", "ne w</w>", "r it", "tim e</w>", "on s</w>", "s o", "m an</w>", "d ec", "c ent", "l an", "p i", "ou r</w>", "in ter", "f er", "g ra", "g re", "re s</w>", "inc lu", "m il", "d uring</w>", "ow n</w>", "pre s", "j u", "n ed</w>", "el l</w>", ", @</w>", "@ ,@</w>", "it e</w>", "g en", "wh en</w>", "si g", "b i", "re n", "f a", "g a", "pla y", "en g", "tion al</w>", "oun d</w>", "th ou", "m ore</w>", "re e</w>", "em ber</w>", "e i", "s ou", "s ur", "s ti", "c ar", "for m", "l ar", "s es</w>", "t en", "in to</w>", "t u", "c es</w>", "mo st</w>", "k ed</w>", "wa y</w>", "c re", "c oun", "u p</w>", "l es</w>", "ac e</w>", "al s</w>", "k e", "w ould</w>", "an t</w>", "b er", "f u", "it ed</w>", "p ri", "whi le</w>", "o ver</w>", "ing s</w>", "r e</w>", "fi l", "s y", "e st", "ab le</w>", "w n</w>", "s ea", "ac h", "s ing</w>", "in s</w>", "ti c</w>", "i d</w>", "on ly</w>", "at es</w>", "t ri", "v ing</w>", "b a", "v el", "an ce</w>", "st a", "er n</w>", "f ol", "e en</w>", "in ed</w>", "st ru", "un i", "g ame</w>", "la r</w>", "s el", "b li", "u sed</w>", "n ing</w>", "p s</w>", "ti es</w>", "k no", "c or", "f t</w>", "rec or", "b le</w>", "vi e", "y s</w>", "w il", "ic al</w>", "ap p", "t ro", "th ree</w>", "c la", "ol d</w>", "sh ed</w>", "h ea", "ab out</w>", "w rit", "th an</w>", "st e", "l ater</w>", "ar i", "d y</w>", "pu bli", "lo c", "ag a", "th rou", "s si", "en d</w>", "ma y</w>", "an g", "ac h</w>", "v es</w>", "o g", "hi m</w>", "be tw", "thou gh</w>", "betw een</w>", "u m</w>", "st ar", "sc ri", "re a", "on d</w>", "shi p</w>", "o k</w>", "h el", "s ong</w>", "c hi", "ca p", "e ver</w>", "da y</w>", "c ri", "s ome</w>", "b ro", "n o</w>", "th ere</w>", "an s</w>", "al l", "n um", "r ed</w>", "ear s</w>", "st s</w>", "an y</w>", "w ar", "p h", "p p", "g in", "stru c", "am er", "pro duc", "s ch", "c es", "ur e</w>", "at ing</w>", "em p", "t or", "sea son</w>", "for e</w>", "i c</w>", "c ity</w>", "g ro", "fol low", "su b", "b el", "y ear</w>", "c an</w>", "s in", "wh ere</w>", "an d", "ma de</w>", "re lea", "s m", "b l", "t en</w>", "wi th", "s on", "man y</w>", "a re", "e d", "h ow", "amer ic", "ur y</w>", "st u", "mu si", "c u", "n am", "em ent</w>", "su ch</w>", "al bu", "bu il", "be fore</w>", "e f", "ar m", "t on</w>", "the m</w>", "c al", "b ar", "d es</w>", "m at", "gen er", "o d</w>", "ser ies</w>", "c er", "sh o", "en ti", "h er", "o ver", "an n", "w ell</w>", "wor ld</w>", "g an</w>", "e st</w>", "sec ond</w>", "t ers</w>", "si de</w>", "tr an", "l ine</w>", "tur e</w>", "por t</w>", "be ing</w>", "y ears</w>", "bo th</w>", "in di", "the se</w>", "na tional</w>", "hi stor", "f e</w>", "v o", "st ed</w>", "an i", "b as", "po in", "s ing", "fil m</w>", "p en", "su p", "m is", "c ro", "st ri", "l in", "t re", "wa r</w>", "how ever</w>", "y ing</w>", "l ing</w>", "y p", "ec ted</w>", "di rec", "vi sion</w>", "albu m</w>", "th en</w>", "l l</w>", "se ver", "throu gh</w>", "kno wn</w>", "b or", "c ul", "c lu", "st er</w>", "sou th</w>", "r y</w>", "ec t</w>", "lo w</w>", "p r", "s k", "is o", "nor th</w>", "par t</w>", "f ac", "t ly</w>", "per i", "e u", "b att", "st ate</w>", "c ed</w>", "con si", "in f", "po li", "ol og", "ear ly</w>", "po si", "am es</w>", "w in", "de vel", "o b", "v e", "v en</w>", "op er", "g er", "of fi", "char ac", "m s</w>", "hi gh", "a d</w>", "th o", "sever al</w>", "d re", "de scri", "al e</w>", "num ber</w>", "a ir", "inclu ding</w>", "in st</w>", "aga inst</w>", "l s</w>", "su l", "ep iso", "c am", "di f", "so ci", "bec ame</w>", "li ke</w>", "t el", "f our</w>", "âĢ Ķ</w>", "h ou", "jo h", "un ited</w>", "in v", "un der</w>", "no v", "ti v", "su c", "a tions</w>", "ac k", "t or</w>", "r on", "un d</w>", "w s</w>", "f o", "g r", "devel op", "al though</w>", "cont in", "we st</w>", "ori gin", "musi c</w>", "or s</w>", "d on</w>", "cent ury</w>", "w ard</w>", "wor k</w>", "m e</w>", "am i", "ch a", "ver y</w>", "h ar", "di s", "z ed</w>", "d o</w>", "g s</w>", "t ow", "s ol", "follow ing</w>", "li on</w>", "re ma", "n s</w>", "ti sh</w>", "ch ur", "s om", "m p", "t le</w>", "go ver", "d el", "comp le", "c ur", "u se</w>", "b ack</w>", "h u", "st ern</w>", "be gan</w>", "fi el", "au se</w>", "d ra", "p as", "b il", "ca tion</w>", "d ent</w>", "b ed</w>", "bec ause</w>", "an t", "ea m</w>", "p hi", "y o", "contin u", "ta in</w>", "tr y</w>", "f re", "pe op", "cal led</w>", "f ound</w>", "episo de</w>", "de sig", "m or", "se t</w>", "le y</w>", "ea st</w>", "tr ac", "c ra" ] } }
{
"version": "1.0",
"truncation": null,
"padding": null,
"added_tokens": [
{
"id": 0,
"content": "!",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 1,
"content": "<|startoftext|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": true,
"special": true
},
{
"id": 2,
"content": "<|endoftext|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": true,
"special": true
}
],
"normalizer": {
"type": "Sequence",
"normalizers": [
{
"type": "NFC"
},
{
"type": "Replace",
"pattern": {
"Regex": "\\s+"
},
"content": " "
},
{
"type": "Lowercase"
}
]
},
"pre_tokenizer": {
"type": "Sequence",
"pretokenizers": [
{
"type": "Split",
"pattern": {
"Regex": "'s|'t|'re|'ve|'m|'ll|'d|[\\p{L}]+|[\\p{N}]|[^\\s\\p{L}\\p{N}]+"
},
"behavior": "Removed",
"invert": true
},
{
"type": "ByteLevel",
"add_prefix_space": false,
"trim_offsets": true,
"use_regex": true
}
]
},
"post_processor": {
"type": "RobertaProcessing",
"sep": [
"<|endoftext|>",
2
],
"cls": [
"<|startoftext|>",
1
],
"trim_offsets": false,
"add_prefix_space": false
},
"decoder": {
"type": "ByteLevel",
"add_prefix_space": true,
"trim_offsets": true,
"use_regex": true
},
"model": {
"type": "BPE",
"dropout": null,
"unk_token": "<|endoftext|>",
"continuing_subword_prefix": "",
"end_of_word_suffix": "</w>",
"fuse_unk": false,
"vocab": {
"!": 0,
"<|startoftext|>": 1,
"<|endoftext|>": 2,