{ "version": "1.0", "truncation": null, "padding": null, "added_tokens": [ { "id": 0, "content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 1, "content": "<|im_start|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 2, "content": "<|im_end|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 3, "content": "<|object_ref_start|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 4, "content": "<|object_ref_end|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 5, "content": "<|box_start|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 6, "content": "<|box_end|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 7, "content": "<|quad_start|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 8, "content": "<|quad_end|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 9, "content": "<|vision_start|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 10, "content": "<|vision_end|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 11, "content": "<|vision_pad|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 12, "content": "<|image_pad|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 13, "content": "<|video_pad|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 14, "content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 15, "content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 16, "content": "<|fim_prefix|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 17, "content": "<|fim_middle|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 18, "content": "<|fim_suffix|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 19, "content": "<|fim_pad|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 20, "content": "<|repo_name|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 21, "content": "<|file_sep|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 22, "content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 23, "content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 24, "content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 25, "content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 26, "content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 27, "content": "[BOS]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 28, "content": "[PAD]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true } ], "normalizer": { "type": "NFC" }, "pre_tokenizer": { "type": "Sequence", "pretokenizers": [ { "type": "Split", "pattern": { "Regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?\\p{L}+|\\p{N}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+" }, "behavior": "Isolated", "invert": false }, { "type": "ByteLevel", "add_prefix_space": false, "trim_offsets": true, "use_regex": false } ] }, "post_processor": { "type": "ByteLevel", "add_prefix_space": false, "trim_offsets": false, "use_regex": false }, "decoder": { "type": "ByteLevel", "add_prefix_space": true, "trim_offsets": true, "use_regex": true }, "model": { "type": "BPE", "dropout": null, "unk_token": null, "continuing_subword_prefix": "", "end_of_word_suffix": "", "fuse_unk": false, "byte_fallback": false, "ignore_merges": false, "vocab": { "<|endoftext|>": 0, "<|im_start|>": 1, "<|im_end|>": 2, "<|object_ref_start|>": 3, "<|object_ref_end|>": 4, "<|box_start|>": 5, "<|box_end|>": 6, "<|quad_start|>": 7, "<|quad_end|>": 8, "<|vision_start|>": 9, "<|vision_end|>": 10, "<|vision_pad|>": 11, "<|image_pad|>": 12, "<|video_pad|>": 13, "": 14, "": 15, "<|fim_prefix|>": 16, "<|fim_middle|>": 17, "<|fim_suffix|>": 18, "<|fim_pad|>": 19, "<|repo_name|>": 20, "<|file_sep|>": 21, "": 22, "": 23, "": 24, "": 25, "": 26, "[BOS]": 27, "[PAD]": 28, "!": 29, "\"": 30, "#": 31, "$": 32, "%": 33, "&": 34, "'": 35, "(": 36, ")": 37, "*": 38, "+": 39, ",": 40, "-": 41, ".": 42, "/": 43, "0": 44, "1": 45, "2": 46, "3": 47, "4": 48, "5": 49, "6": 50, "7": 51, "8": 52, "9": 53, ":": 54, ";": 55, "<": 56, "=": 57, ">": 58, "?": 59, "@": 60, "A": 61, "B": 62, "C": 63, "D": 64, "E": 65, "F": 66, "G": 67, "H": 68, "I": 69, "J": 70, "K": 71, "L": 72, "M": 73, "N": 74, "O": 75, "P": 76, "Q": 77, "R": 78, "S": 79, "T": 80, "U": 81, "V": 82, "W": 83, "X": 84, "Y": 85, "Z": 86, "[": 87, "\\": 88, "]": 89, "^": 90, "_": 91, "`": 92, "a": 93, "b": 94, "c": 95, "d": 96, "e": 97, "f": 98, "g": 99, "h": 100, "i": 101, "j": 102, "k": 103, "l": 104, "m": 105, "n": 106, "o": 107, "p": 108, "q": 109, "r": 110, "s": 111, "t": 112, "u": 113, "v": 114, "w": 115, "x": 116, "y": 117, "z": 118, "{": 119, "|": 120, "}": 121, "~": 122, "¡": 123, "¢": 124, "£": 125, "¤": 126, "¥": 127, "¦": 128, "§": 129, "¨": 130, "©": 131, "ª": 132, "«": 133, "¬": 134, "®": 135, "¯": 136, "°": 137, "±": 138, "²": 139, "³": 140, "´": 141, "µ": 142, "¶": 143, "·": 144, "¸": 145, "¹": 146, "º": 147, "»": 148, "¼": 149, "½": 150, "¾": 151, "¿": 152, "À": 153, "Á": 154, "Â": 155, "Ã": 156, "Ä": 157, "Å": 158, "Æ": 159, "Ç": 160, "È": 161, "É": 162, "Ê": 163, "Ë": 164, "Ì": 165, "Í": 166, "Î": 167, "Ï": 168, "Ð": 169, "Ñ": 170, "Ò": 171, "Ó": 172, "Ô": 173, "Õ": 174, "Ö": 175, "×": 176, "Ø": 177, "Ù": 178, "Ú": 179, "Û": 180, "Ü": 181, "Ý": 182, "Þ": 183, "ß": 184, "à": 185, "á": 186, "â": 187, "ã": 188, "ä": 189, "å": 190, "æ": 191, "ç": 192, "è": 193, "é": 194, "ê": 195, "ë": 196, "ì": 197, "í": 198, "î": 199, "ï": 200, "ð": 201, "ñ": 202, "ò": 203, "ó": 204, "ô": 205, "õ": 206, "ö": 207, "÷": 208, "ø": 209, "ù": 210, "ú": 211, "û": 212, "ü": 213, "ý": 214, "þ": 215, "ÿ": 216, "Ā": 217, "ā": 218, "Ă": 219, "ă": 220, "Ą": 221, "ą": 222, "Ć": 223, "ć": 224, "Ĉ": 225, "ĉ": 226, "Ċ": 227, "ċ": 228, "Č": 229, "č": 230, "Ď": 231, "ď": 232, "Đ": 233, "đ": 234, "Ē": 235, "ē": 236, "Ĕ": 237, "ĕ": 238, "Ė": 239, "ė": 240, "Ę": 241, "ę": 242, "Ě": 243, "ě": 244, "Ĝ": 245, "ĝ": 246, "Ğ": 247, "ğ": 248, "Ġ": 249, "ġ": 250, "Ģ": 251, "ģ": 252, "Ĥ": 253, "ĥ": 254, "Ħ": 255, "ħ": 256, "Ĩ": 257, "ĩ": 258, "Ī": 259, "ī": 260, "Ĭ": 261, "ĭ": 262, "Į": 263, "į": 264, "İ": 265, "ı": 266, "IJ": 267, "ij": 268, "Ĵ": 269, "ĵ": 270, "Ķ": 271, "ķ": 272, "ĸ": 273, "Ĺ": 274, "ĺ": 275, "Ļ": 276, "ļ": 277, "Ľ": 278, "ľ": 279, "Ŀ": 280, "ŀ": 281, "Ł": 282, "ł": 283, "Ń": 284, "Ġt": 285, "he": 286, "Ġa": 287, "in": 288, "Ġthe": 289, "er": 290, "on": 291, "Ġ,": 292, "re": 293, "Ġs": 294, "ed": 295, "Ġo": 296, "nd": 297, "Ġw": 298, "at": 299, "Ġ.": 300, "or": 301, "it": 302, "is": 303, "Ġc": 304, "es": 305, "Ġf": 306, "en": 307, "Ġof": 308, "ar": 309, "al": 310, "Ġin": 311, "Ġb": 312, "an": 313, "Ġp": 314, "ing": 315, "as": 316, "Ġand": 317, "ic": 318, "Ġto": 319, "Ġm": 320, "ro": 321, "Ġd": 322, "Ġh": 323, "ion": 324, "le": 325, "ĠT": 326, "ou": 327, "Ġre": 328, "Ġ=": 329, "ĠA": 330, "Ġ\"": 331, "ĠS": 332, "Ġth": 333, "ent": 334, "il": 335, "st": 336, "Ġ@": 337, "el": 338, "ĠC": 339, "ĠĊ": 340, "ol": 341, "Ġl": 342, "Ġn": 343, "om": 344, "Ġe": 345, "ct": 346, "am": 347, "ad": 348, "Ġg": 349, "Ġwas": 350, "ur": 351, "Ġon": 352, "ĠThe": 353, "ĠI": 354, "im": 355, "-@": 356, "Ġ@-@": 357, "Ġbe": 358, "ly": 359, "ĠM": 360, "id": 361, "Ġfor": 362, "ir": 363, "ch": 364, "ĠB": 365, "iv": 366, "ot": 367, "Ġ'": 368, "ith": 369, "ation": 370, "ra": 371, "ig": 372, "Ġas": 373, "et": 374, "ow": 375, "us": 376, "ut": 377, "Ġst": 378, "ce": 379, "Ġwith": 380, "ĠP": 381, "ers": 382, "Ġhe": 383, "Ġthat": 384, "ay": 385, "Ġis": 386, "ĠH": 387, "ul": 388, "ĠG": 389, "ĠF": 390, "Ġal": 391, "ĠR": 392, "ĠN": 393, "ist": 394, "um": 395, "em": 396, "Ġwh": 397, "ĠW": 398, "est": 399, "Ġby": 400, "un": 401, "Ġan": 402, "ver": 403, "os": 404, "th": 405, "Ġ)": 406, "Ġ(": 407, "ter": 408, "Ġcon": 409, "ĠJ": 410, "rom": 411, "ĠD": 412, "Ġat": 413, "Ġse": 414, "and": 415, "od": 416, "ĠL": 417, "av": 418, "Ġit": 419, "Ġde": 420, "ag": 421, "her": 422, "ies": 423, "pe": 424, "ĠE": 425, "ain": 426, "ck": 427, "Ġhis": 428, "ri": 429, "Ġfrom": 430, "ere": 431, "res": 432, "ort": 433, "Ġpro": 434, "if": 435, "Ġcom": 436, "ew": 437, "ity": 438, "Ġwere": 439, "Ġv": 440, "ate": 441, "ĠIn": 442, "Ġsu": 443, "ĠO": 444, "op": 445, "Ġor": 446, "ich": 447, "ore": 448, "all": 449, "igh": 450, "ated": 451, "ord": 452, "se": 453, "ill": 454, "art": 455, "Ġex": 456, "ab": 457, "pt": 458, "Ġch": 459, "Ġsh": 460, "ld": 461, "Ġpl": 462, "pp": 463, "ak": 464, "Ġare": 465, "ber": 466, "gh": 467, "ess": 468, "ud": 469, "Ġâ": 470, "ant": 471, "ard": 472, "rou": 473, "ong": 474, "ĠU": 475, "ru": 476, "ia": 477, "qu": 478, "Ġwhich": 479, "ĠâĢ": 480, "ame": 481, "ment": 482, "ĠCh": 483, "Ġle": 484, "rit": 485, "Ġhad": 486, "ial": 487, "ian": 488, "og": 489, "red": 490, "ĠK": 491, "ĠSt": 492, "ive": 493, "oc": 494, "ip": 495, "ov": 496, "Ġ;": 497, "Ġr": 498, "ish": 499, "ost": 500, "our": 501, "Ġar": 502, "Ġu": 503, "Ġnot": 504, "ear": 505, "ight": 506, "ast": 507, "ac": 508, "Ġy": 509, "Ġk": 510, "ave": 511, "ary": 512, "ell": 513, "ther": 514, "ction": 515, "ical": 516, "nt": 517, "own": 518, "cc": 519, "Ġinc": 520, "ine": 521, "ge": 522, "ide": 523, "ust": 524, "ĠâĢĵ": 525, "Ġher": 526, "so": 527, "ap": 528, "ue": 529, "ure": 530, "ork": 531, "ran": 532, "out": 533, "Ġalso": 534, "Ġtheir": 535, "Ġhas": 536, "wo": 537, "Ġun": 538, "ous": 539, "ff": 540, "ign": 541, "fter": 542, "ĠV": 543, "ub": 544, "Ġrec": 545, "ome": 546, "Ġcl": 547, ".@": 548, "Ġ@.@": 549, "Ġcont": 550, "irst": 551, "ĠHe": 552, "Ġte": 553, "ition": 554, "ater": 555, "Ġper": 556, "ass": 557, "ack": 558, "ations": 559, "ie": 560, "Ġits": 561, "Ġab": 562, "pl": 563, "Ġone": 564, "Ġint": 565, "Ġsc": 566, "Ġfirst": 567, "ond": 568, "ime": 569, "hed": 570, "Ġ:": 571, "orm": 572, "ult": 573, "ould": 574, "ory": 575, "Ġwho": 576, "Ġwhe": 577, "ĠTh": 578, "per": 579, "Ġbut": 580, "Ġhave": 581, "Ġtwo": 582, "nder": 583, "ĠAl": 584, "ect": 585, "Ġthis": 586, "ok": 587, "ark": 588, "uring": 589, "du": 590, "ire": 591, "ough": 592, "ual": 593, "Ġall": 594, "ĠY": 595, "iz": 596, "mer": 597, "Ġus": 598, "ach": 599, "oll": 600, "Ġbeen": 601, "Ġplay": 602, "Ġres": 603, "ree": 604, "Ġshe": 605, ",@": 606, "Ġ@,@": 607, "age": 608, "Ġoff": 609, "ey": 610, "Ġcomp": 611, "Ġag": 612, "ason": 613, "port": 614, "oin": 615, "Ġad": 616, "Ġyear": 617, "Ġim": 618, "ĠIt": 619, "ence": 620, "Ġpart": 621, "Ġdes": 622, "ke": 623, "ric": 624, "are": 625, "ry": 626, "lud": 627, "Ġbec": 628, "te": 629, "Ġj": 630, "Ġother": 631, "ely": 632, "Ġdis": 633, "ph": 634, "Ġman": 635, "ound": 636, "old": 637, "Ġspe": 638, "act": 639, "Ġro": 640, "Ġafter": 641, "ance": 642, "ath": 643, "Ġen": 644, "ited": 645, "ĠUn": 646, "Ġgo": 647, "ib": 648, "ile": 649, "Ġthey": 650, "ite": 651, "man": 652, "ities": 653, "Ġover": 654, "ced": 655, "ents": 656, "ors": 657, "round": 658, "ilm": 659, "Ġinclud": 660, "Ġpre": 661, "ĠRe": 662, "vi": 663, "olog": 664, "ted": 665, "ade": 666, "ied": 667, "ose": 668, "ase": 669, "Ġcomm": 670, "Ġtime": 671, "Ġser": 672, "inal": 673, "Ġseason": 674, "ased": 675, "Ġout": 676, "ice": 677, "ĠAr": 678, "ates": 679, "ress": 680, "Ġup": 681, "ĠSe": 682, "ft": 683, "Ġthem": 684, "ubl": 685, "les": 686, "ild": 687, "Ġsp": 688, "Ġev": 689, "Ġmore": 690, "land": 691, "bum": 692, "fer": 693, "ces": 694, "Ġnew": 695, "gan": 696, "rough": 697, "able": 698, "ron": 699, "ts": 700, "ĠDe": 701, "ace": 702, "Ġne": 703, "Ġgod": 704, "ock": 705, "Ġalbum": 706, "rib": 707, "ward": 708, "Ġrem": 709, "Ġsec": 710, "Ġunder": 711, "wn": 712, "Ġwork": 713, "ered": 714, "ĠSh": 715, "ind": 716, "ens": 717, "Ġrel": 718, "Ġfilm": 719, "use": 720, "Ġhim": 721, "ings": 722, "ount": 723, "Ġrecord": 724, "Ġspec": 725, "ĠWhe": 726, "Ġinto": 727, "arn": 728, "reat": 729, "hip": 730, "one": 731, "orn": 732, "Ġinter": 733, "urn": 734, "ail": 735, "Ġfe": 736, "ember": 737, "Ġcons": 738, "form": 739, "ix": 740, "ved": 741, "Ġmost": 742, "Ġreg": 743, "ational": 744, "ern": 745, "arly": 746, "ĠPol": 747, "Ġact": 748, "oy": 749, "ink": 750, "ames": 751, "ordan": 752, "ĠJordan": 753, "ĠOn": 754, "Ġair": 755, "ĠAs": 756, "Ġduring": 757, "ĠBrit": 758, "ions": 759, "aw": 760, "Ġco": 761, "Ġfl": 762, "ee": 763, "oth": 764, "ae": 765, "vel": 766, "Ġtra": 767, "ons": 768, "ang": 769, "ick": 770, "Ġass": 771, "Ġatt": 772, "Ġra": 773, "oss": 774, "Ġsub": 775, "Ġkn": 776, "Ġonly": 777, "Ġagain": 778, "way": 779, "ans": 780, "Ġme": 781, "Ġnum": 782, "Ġform": 783, "iss": 784, "Ġpubl": 785, "ng": 786, "ished": 787, "arg": 788, "Ġret": 789, "Ġrele": 790, "Ġwould": 791, "een": 792, "ve": 793, "Ġfour": 794, "ict": 795, "Ġthree": 796, "erson": 797, "tle": 798, "Ġprodu": 799, "Ġmon": 800, "Ġteam": 801, "ook": 802, "orth": 803, "ĠShe": 804, "Ġend": 805, "ars": 806, "Ġbet": 807, "vest": 808, "Ġbu": 809, "Ġsecond": 810, "Ġthan": 811, "ste": 812, "ĠIs": 813, "ĠInd": 814, "Ġbeing": 815, "Ġdec": 816, "ood": 817, "Ġcan": 818, "ener": 819, "Ġthrough": 820, "Ġabout": 821, "Ġcent": 822, "cted": 823, "Ġapp": 824, "Ġwhen": 825, "Ġlater": 826, "ower": 827, "ull": 828, "ony": 829, "ole": 830, "eler": 831, "Ġacc": 832, "Ġpe": 833, "ake": 834, "ike": 835, "ily": 836, "rist": 837, "Ġac": 838, "Ġind": 839, "ĠWheeler": 840, "ĠLe": 841, "outh": 842, "ĠCom": 843, "usic": 844, "ular": 845, "ious": 846, "ween": 847, "Ġsome": 848, "urch": 849, "end": 850, "ism": 851, "chae": 852, "ĠNew": 853, "chaeolog": 854, "aid": 855, "Ġwrit": 856, "als": 857, "Ġdo": 858, "Ġsuch": 859, "ollow": 860, "ally": 861, "ten": 862, "Ġam": 863, "ins": 864, "Ġpol": 865, "Ġmade": 866, "ific": 867, "Ġmet": 868, "Ġgame": 869, "iel": 870, "Ġhist": 871, "ute": 872, "ĠGal": 873, "Ġwhere": 874, "fore": 875, "ating": 876, "Ġrep": 877, "resent": 878, "ject": 879, "Ġsy": 880, "orld": 881, "Ġpr": 882, "Ġbl": 883, "amp": 884, "iet": 885, "ob": 886, "Ġap": 887, "though": 888, "ove": 889, "ĠBritish": 890, "Ġbetween": 891, "veston": 892, "ĠGalveston": 893, "erman": 894, "row": 895, "Ġant": 896, "Ġship": 897, "ĠChrist": 898, "az": 899, "ool": 900, "Ġthere": 901, "Ġsign": 902, "ĠBl": 903, "Ġsur": 904, "ised": 905, "ired": 906, "ĠYork": 907, "led": 908, "Ġcity": 909, "ĠAll": 910, "up": 911, "Ġchar": 912, "Ġsong": 913, "Ġcall": 914, "ĠGerman": 915, "Ġmany": 916, "Ġnumber": 917, "Ġhigh": 918, "ug": 919, "ics": 920, "ican": 921, "Ġmin": 922, "Ġloc": 923, "Ġno": 924, "Ġwhile": 925, "air": 926, "Ġqu": 927, "Ġboth": 928, "Ġele": 929, "rans": 930, "Ġsupp": 931, "ever": 932, "ĠTown": 933, "ivers": 934, "ife": 935, "Ġlead": 936, "Ġused": 937, "hes": 938, "ived": 939, "veral": 940, "Ġthen": 941, "Ġso": 942, "Ġyears": 943, "Ġgods": 944, "gy": 945, "ren": 946, "Ġlong": 947, "Ġdesc": 948, "Ġbel": 949, "oh": 950, "view": 951, "ause": 952, "ale": 953, "ros": 954, "other": 955, "elf": 956, "ning": 957, "ral": 958, "Ġfollow": 959, "ĠUnited": 960, "Ġdif": 961, "ĠAmer": 962, "very": 963, "ures": 964, "Ġsch": 965, "Ġday": 966, "Ġent": 967, "Ġwell": 968, "Ġmain": 969, "ĠThis": 970, "Ġtr": 971, "Ġdef": 972, "Ġob": 973, "Ġcre": 974, "tern": 975, "ty": 976, "ĠCl": 977, "Ġem": 978, "Ġbefore": 979, "ists": 980, "ĠMar": 981, "raft": 982, "Ġbecame": 983, "Ġthese": 984, "emb": 985, "Ġperform": 986, "Ġagainst": 987, "ah": 988, "ople": 989, "ized": 990, "ield": 991, "Ġappe": 992, "stru": 993, "Ġdep": 994, "Ġoper": 995, "Ġpop": 996, "Ġknown": 997, "stein": 998, "io": 999, "ys": 1000, "ĠZ": 1001, "Ġcar": 1002, "Ġcol": 1003, "ident": 1004, "owever": 1005, "cept": 1006, "Ġremain": 1007, "son": 1008, "Ġstud": 1009, "Ġincluding": 1010, "Ġ%": 1011, "ĠAnd": 1012, "Ġorig": 1013, "irect": 1014, "ĠPolish": 1015, "Ġsaid": 1016, "ĠAt": 1017, "ury": 1018, "Ġbegan": 1019, "Ġdisc": 1020, "ton": 1021, "Ġsm": 1022, "Ġcare": 1023 }, "merges": [ [ "Ġ", "t" ], [ "h", "e" ], [ "Ġ", "a" ], [ "i", "n" ], [ "Ġt", "he" ], [ "e", "r" ], [ "o", "n" ], [ "Ġ", "," ], [ "r", "e" ], [ "Ġ", "s" ], [ "e", "d" ], [ "Ġ", "o" ], [ "n", "d" ], [ "Ġ", "w" ], [ "a", "t" ], [ "Ġ", "." ], [ "o", "r" ], [ "i", "t" ], [ "i", "s" ], [ "Ġ", "c" ], [ "e", "s" ], [ "Ġ", "f" ], [ "e", "n" ], [ "Ġo", "f" ], [ "a", "r" ], [ "a", "l" ], [ "Ġ", "in" ], [ "Ġ", "b" ], [ "a", "n" ], [ "Ġ", "p" ], [ "in", "g" ], [ "a", "s" ], [ "Ġa", "nd" ], [ "i", "c" ], [ "Ġt", "o" ], [ "Ġ", "m" ], [ "r", "o" ], [ "Ġ", "d" ], [ "Ġ", "h" ], [ "i", "on" ], [ "l", "e" ], [ "Ġ", "T" ], [ "o", "u" ], [ "Ġ", "re" ], [ "Ġ", "=" ], [ "Ġ", "A" ], [ "Ġ", "\"" ], [ "Ġ", "S" ], [ "Ġt", "h" ], [ "en", "t" ], [ "i", "l" ], [ "s", "t" ], [ "Ġ", "@" ], [ "e", "l" ], [ "Ġ", "C" ], [ "Ġ", "Ċ" ], [ "o", "l" ], [ "Ġ", "l" ], [ "Ġ", "n" ], [ "o", "m" ], [ "Ġ", "e" ], [ "c", "t" ], [ "a", "m" ], [ "a", "d" ], [ "Ġ", "g" ], [ "Ġw", "as" ], [ "u", "r" ], [ "Ġ", "on" ], [ "ĠT", "he" ], [ "Ġ", "I" ], [ "i", "m" ], [ "-", "@" ], [ "Ġ@", "-@" ], [ "Ġb", "e" ], [ "l", "y" ], [ "Ġ", "M" ], [ "i", "d" ], [ "Ġf", "or" ], [ "i", "r" ], [ "c", "h" ], [ "Ġ", "B" ], [ "i", "v" ], [ "o", "t" ], [ "Ġ", "'" ], [ "it", "h" ], [ "at", "ion" ], [ "r", "a" ], [ "i", "g" ], [ "Ġa", "s" ], [ "e", "t" ], [ "o", "w" ], [ "u", "s" ], [ "u", "t" ], [ "Ġs", "t" ], [ "c", "e" ], [ "Ġw", "ith" ], [ "Ġ", "P" ], [ "er", "s" ], [ "Ġ", "he" ], [ "Ġth", "at" ], [ "a", "y" ], [ "Ġ", "is" ], [ "Ġ", "H" ], [ "u", "l" ], [ "Ġ", "G" ], [ "Ġ", "F" ], [ "Ġa", "l" ], [ "Ġ", "R" ], [ "Ġ", "N" ], [ "is", "t" ], [ "u", "m" ], [ "e", "m" ], [ "Ġw", "h" ], [ "Ġ", "W" ], [ "es", "t" ], [ "Ġb", "y" ], [ "u", "n" ], [ "Ġa", "n" ], [ "v", "er" ], [ "o", "s" ], [ "t", "h" ], [ "Ġ", ")" ], [ "Ġ", "(" ], [ "t", "er" ], [ "Ġc", "on" ], [ "Ġ", "J" ], [ "ro", "m" ], [ "Ġ", "D" ], [ "Ġa", "t" ], [ "Ġs", "e" ], [ "a", "nd" ], [ "o", "d" ], [ "Ġ", "L" ], [ "a", "v" ], [ "Ġ", "it" ], [ "Ġd", "e" ], [ "a", "g" ], [ "he", "r" ], [ "i", "es" ], [ "p", "e" ], [ "Ġ", "E" ], [ "a", "in" ], [ "c", "k" ], [ "Ġh", "is" ], [ "r", "i" ], [ "Ġf", "rom" ], [ "er", "e" ], [ "re", "s" ], [ "or", "t" ], [ "Ġp", "ro" ], [ "i", "f" ], [ "Ġc", "om" ], [ "e", "w" ], [ "it", "y" ], [ "Ġw", "ere" ], [ "Ġ", "v" ], [ "at", "e" ], [ "ĠI", "n" ], [ "Ġs", "u" ], [ "Ġ", "O" ], [ "o", "p" ], [ "Ġo", "r" ], [ "ic", "h" ], [ "o", "re" ], [ "al", "l" ], [ "ig", "h" ], [ "at", "ed" ], [ "or", "d" ], [ "s", "e" ], [ "il", "l" ], [ "ar", "t" ], [ "Ġe", "x" ], [ "a", "b" ], [ "p", "t" ], [ "Ġc", "h" ], [ "Ġs", "h" ], [ "l", "d" ], [ "Ġp", "l" ], [ "p", "p" ], [ "a", "k" ], [ "Ġa", "re" ], [ "b", "er" ], [ "g", "h" ], [ "es", "s" ], [ "u", "d" ], [ "Ġ", "â" ], [ "an", "t" ], [ "ar", "d" ], [ "ro", "u" ], [ "on", "g" ], [ "Ġ", "U" ], [ "r", "u" ], [ "i", "a" ], [ "q", "u" ], [ "Ġwh", "ich" ], [ "Ġâ", "Ģ" ], [ "am", "e" ], [ "m", "ent" ], [ "ĠC", "h" ], [ "Ġ", "le" ], [ "r", "it" ], [ "Ġh", "ad" ], [ "i", "al" ], [ "i", "an" ], [ "o", "g" ], [ "re", "d" ], [ "Ġ", "K" ], [ "ĠS", "t" ], [ "iv", "e" ], [ "o", "c" ], [ "i", "p" ], [ "o", "v" ], [ "Ġ", ";" ], [ "Ġ", "r" ], [ "is", "h" ], [ "o", "st" ], [ "ou", "r" ], [ "Ġa", "r" ], [ "Ġ", "u" ], [ "Ġn", "ot" ], [ "e", "ar" ], [ "igh", "t" ], [ "as", "t" ], [ "a", "c" ], [ "Ġ", "y" ], [ "Ġ", "k" ], [ "av", "e" ], [ "ar", "y" ], [ "el", "l" ], [ "t", "her" ], [ "ct", "ion" ], [ "ic", "al" ], [ "n", "t" ], [ "ow", "n" ], [ "c", "c" ], [ "Ġin", "c" ], [ "in", "e" ], [ "g", "e" ], [ "id", "e" ], [ "u", "st" ], [ "ĠâĢ", "ĵ" ], [ "Ġhe", "r" ], [ "s", "o" ], [ "a", "p" ], [ "u", "e" ], [ "u", "re" ], [ "or", "k" ], [ "r", "an" ], [ "ou", "t" ], [ "Ġal", "so" ], [ "Ġthe", "ir" ], [ "Ġh", "as" ], [ "w", "o" ], [ "Ġ", "un" ], [ "ou", "s" ], [ "f", "f" ], [ "ig", "n" ], [ "f", "ter" ], [ "Ġ", "V" ], [ "u", "b" ], [ "Ġre", "c" ], [ "om", "e" ], [ "Ġc", "l" ], [ ".", "@" ], [ "Ġ@", ".@" ], [ "Ġcon", "t" ], [ "ir", "st" ], [ "ĠH", "e" ], [ "Ġt", "e" ], [ "it", "ion" ], [ "at", "er" ], [ "Ġp", "er" ], [ "as", "s" ], [ "a", "ck" ], [ "ation", "s" ], [ "i", "e" ], [ "Ġit", "s" ], [ "Ġa", "b" ], [ "p", "l" ], [ "Ġon", "e" ], [ "Ġin", "t" ], [ "Ġs", "c" ], [ "Ġf", "irst" ], [ "on", "d" ], [ "im", "e" ], [ "he", "d" ], [ "Ġ", ":" ], [ "or", "m" ], [ "ul", "t" ], [ "ou", "ld" ], [ "or", "y" ], [ "Ġwh", "o" ], [ "Ġw", "he" ], [ "ĠT", "h" ], [ "p", "er" ], [ "Ġb", "ut" ], [ "Ġh", "ave" ], [ "Ġt", "wo" ], [ "nd", "er" ], [ "ĠA", "l" ], [ "e", "ct" ], [ "Ġth", "is" ], [ "o", "k" ], [ "ar", "k" ], [ "ur", "ing" ], [ "d", "u" ], [ "i", "re" ], [ "ou", "gh" ], [ "u", "al" ], [ "Ġal", "l" ], [ "Ġ", "Y" ], [ "i", "z" ], [ "m", "er" ], [ "Ġ", "us" ], [ "a", "ch" ], [ "ol", "l" ], [ "Ġbe", "en" ], [ "Ġpl", "ay" ], [ "Ġre", "s" ], [ "re", "e" ], [ "Ġs", "he" ], [ ",", "@" ], [ "Ġ@", ",@" ], [ "ag", "e" ], [ "Ġof", "f" ], [ "e", "y" ], [ "Ġcom", "p" ], [ "Ġa", "g" ], [ "as", "on" ], [ "p", "ort" ], [ "o", "in" ], [ "Ġa", "d" ], [ "Ġy", "ear" ], [ "Ġ", "im" ], [ "ĠI", "t" ], [ "en", "ce" ], [ "Ġp", "art" ], [ "Ġd", "es" ], [ "k", "e" ], [ "r", "ic" ], [ "a", "re" ], [ "r", "y" ], [ "l", "ud" ], [ "Ġbe", "c" ], [ "t", "e" ], [ "Ġ", "j" ], [ "Ġo", "ther" ], [ "el", "y" ], [ "Ġd", "is" ], [ "p", "h" ], [ "Ġm", "an" ], [ "ou", "nd" ], [ "ol", "d" ], [ "Ġs", "pe" ], [ "a", "ct" ], [ "Ġ", "ro" ], [ "Ġa", "fter" ], [ "an", "ce" ], [ "at", "h" ], [ "Ġ", "en" ], [ "it", "ed" ], [ "ĠU", "n" ], [ "Ġg", "o" ], [ "i", "b" ], [ "i", "le" ], [ "Ġthe", "y" ], [ "it", "e" ], [ "m", "an" ], [ "it", "ies" ], [ "Ġo", "ver" ], [ "c", "ed" ], [ "ent", "s" ], [ "or", "s" ], [ "rou", "nd" ], [ "il", "m" ], [ "Ġinc", "lud" ], [ "Ġp", "re" ], [ "ĠR", "e" ], [ "v", "i" ], [ "ol", "og" ], [ "t", "ed" ], [ "ad", "e" ], [ "i", "ed" ], [ "os", "e" ], [ "as", "e" ], [ "Ġcom", "m" ], [ "Ġt", "ime" ], [ "Ġs", "er" ], [ "in", "al" ], [ "Ġse", "ason" ], [ "as", "ed" ], [ "Ġo", "ut" ], [ "ic", "e" ], [ "ĠA", "r" ], [ "at", "es" ], [ "res", "s" ], [ "Ġu", "p" ], [ "ĠS", "e" ], [ "f", "t" ], [ "Ġthe", "m" ], [ "ub", "l" ], [ "l", "es" ], [ "il", "d" ], [ "Ġs", "p" ], [ "Ġe", "v" ], [ "Ġm", "ore" ], [ "l", "and" ], [ "b", "um" ], [ "f", "er" ], [ "c", "es" ], [ "Ġn", "ew" ], [ "g", "an" ], [ "rou", "gh" ], [ "ab", "le" ], [ "r", "on" ], [ "t", "s" ], [ "ĠD", "e" ], [ "a", "ce" ], [ "Ġn", "e" ], [ "Ġg", "od" ], [ "o", "ck" ], [ "Ġal", "bum" ], [ "ri", "b" ], [ "w", "ard" ], [ "Ġre", "m" ], [ "Ġse", "c" ], [ "Ġu", "nder" ], [ "w", "n" ], [ "Ġw", "ork" ], [ "er", "ed" ], [ "ĠS", "h" ], [ "in", "d" ], [ "en", "s" ], [ "Ġre", "l" ], [ "Ġf", "ilm" ], [ "us", "e" ], [ "Ġh", "im" ], [ "ing", "s" ], [ "ou", "nt" ], [ "Ġrec", "ord" ], [ "Ġspe", "c" ], [ "ĠW", "he" ], [ "Ġint", "o" ], [ "ar", "n" ], [ "re", "at" ], [ "h", "ip" ], [ "on", "e" ], [ "or", "n" ], [ "Ġin", "ter" ], [ "ur", "n" ], [ "a", "il" ], [ "Ġf", "e" ], [ "em", "ber" ], [ "Ġcon", "s" ], [ "f", "orm" ], [ "i", "x" ], [ "v", "ed" ], [ "Ġm", "ost" ], [ "Ġre", "g" ], [ "ation", "al" ], [ "er", "n" ], [ "ar", "ly" ], [ "ĠP", "ol" ], [ "Ġa", "ct" ], [ "o", "y" ], [ "in", "k" ], [ "am", "es" ], [ "ord", "an" ], [ "ĠJ", "ordan" ], [ "ĠO", "n" ], [ "Ġa", "ir" ], [ "ĠA", "s" ], [ "Ġd", "uring" ], [ "ĠB", "rit" ], [ "ion", "s" ], [ "a", "w" ], [ "Ġc", "o" ], [ "Ġf", "l" ], [ "e", "e" ], [ "ot", "h" ], [ "a", "e" ], [ "v", "el" ], [ "Ġt", "ra" ], [ "on", "s" ], [ "an", "g" ], [ "ic", "k" ], [ "Ġas", "s" ], [ "Ġat", "t" ], [ "Ġ", "ra" ], [ "os", "s" ], [ "Ġsu", "b" ], [ "Ġk", "n" ], [ "Ġon", "ly" ], [ "Ġag", "ain" ], [ "w", "ay" ], [ "an", "s" ], [ "Ġm", "e" ], [ "Ġn", "um" ], [ "Ġfor", "m" ], [ "is", "s" ], [ "Ġp", "ubl" ], [ "n", "g" ], [ "is", "hed" ], [ "ar", "g" ], [ "Ġre", "t" ], [ "Ġre", "le" ], [ "Ġw", "ould" ], [ "e", "en" ], [ "v", "e" ], [ "Ġf", "our" ], [ "ic", "t" ], [ "Ġth", "ree" ], [ "ers", "on" ], [ "t", "le" ], [ "Ġpro", "du" ], [ "Ġm", "on" ], [ "Ġte", "am" ], [ "o", "ok" ], [ "or", "th" ], [ "ĠS", "he" ], [ "Ġe", "nd" ], [ "ar", "s" ], [ "Ġbe", "t" ], [ "v", "est" ], [ "Ġb", "u" ], [ "Ġsec", "ond" ], [ "Ġth", "an" ], [ "st", "e" ], [ "ĠI", "s" ], [ "ĠI", "nd" ], [ "Ġbe", "ing" ], [ "Ġde", "c" ], [ "o", "od" ], [ "Ġc", "an" ], [ "en", "er" ], [ "Ġth", "rough" ], [ "Ġab", "out" ], [ "Ġc", "ent" ], [ "ct", "ed" ], [ "Ġa", "pp" ], [ "Ġwhe", "n" ], [ "Ġl", "ater" ], [ "ow", "er" ], [ "ul", "l" ], [ "on", "y" ], [ "o", "le" ], [ "el", "er" ], [ "Ġa", "cc" ], [ "Ġp", "e" ], [ "ak", "e" ], [ "i", "ke" ], [ "il", "y" ], [ "r", "ist" ], [ "Ġa", "c" ], [ "Ġin", "d" ], [ "ĠWhe", "eler" ], [ "ĠL", "e" ], [ "ou", "th" ], [ "ĠC", "om" ], [ "us", "ic" ], [ "ul", "ar" ], [ "i", "ous" ], [ "w", "een" ], [ "Ġs", "ome" ], [ "ur", "ch" ], [ "e", "nd" ], [ "is", "m" ], [ "ch", "ae" ], [ "ĠN", "ew" ], [ "chae", "olog" ], [ "a", "id" ], [ "Ġw", "rit" ], [ "al", "s" ], [ "Ġd", "o" ], [ "Ġsu", "ch" ], [ "oll", "ow" ], [ "al", "ly" ], [ "t", "en" ], [ "Ġa", "m" ], [ "in", "s" ], [ "Ġp", "ol" ], [ "Ġm", "ade" ], [ "if", "ic" ], [ "Ġm", "et" ], [ "Ġg", "ame" ], [ "i", "el" ], [ "Ġh", "ist" ], [ "ut", "e" ], [ "ĠG", "al" ], [ "Ġwhe", "re" ], [ "f", "ore" ], [ "at", "ing" ], [ "Ġre", "p" ], [ "res", "ent" ], [ "j", "ect" ], [ "Ġs", "y" ], [ "or", "ld" ], [ "Ġp", "r" ], [ "Ġb", "l" ], [ "am", "p" ], [ "i", "et" ], [ "o", "b" ], [ "Ġa", "p" ], [ "th", "ough" ], [ "ov", "e" ], [ "ĠBrit", "ish" ], [ "Ġbet", "ween" ], [ "vest", "on" ], [ "ĠGal", "veston" ], [ "er", "man" ], [ "ro", "w" ], [ "Ġan", "t" ], [ "Ġsh", "ip" ], [ "ĠCh", "rist" ], [ "a", "z" ], [ "o", "ol" ], [ "Ġthe", "re" ], [ "Ġs", "ign" ], [ "ĠB", "l" ], [ "Ġs", "ur" ], [ "is", "ed" ], [ "i", "red" ], [ "ĠY", "ork" ], [ "l", "ed" ], [ "Ġc", "ity" ], [ "ĠAl", "l" ], [ "u", "p" ], [ "Ġch", "ar" ], [ "Ġs", "ong" ], [ "Ġc", "all" ], [ "ĠG", "erman" ], [ "Ġman", "y" ], [ "Ġnum", "ber" ], [ "Ġh", "igh" ], [ "u", "g" ], [ "ic", "s" ], [ "ic", "an" ], [ "Ġm", "in" ], [ "Ġl", "oc" ], [ "Ġn", "o" ], [ "Ġwh", "ile" ], [ "a", "ir" ], [ "Ġ", "qu" ], [ "Ġb", "oth" ], [ "Ġe", "le" ], [ "ran", "s" ], [ "Ġsu", "pp" ], [ "e", "ver" ], [ "ĠT", "own" ], [ "iv", "ers" ], [ "if", "e" ], [ "Ġle", "ad" ], [ "Ġus", "ed" ], [ "he", "s" ], [ "iv", "ed" ], [ "ver", "al" ], [ "Ġthe", "n" ], [ "Ġs", "o" ], [ "Ġyear", "s" ], [ "Ġgod", "s" ], [ "g", "y" ], [ "re", "n" ], [ "Ġl", "ong" ], [ "Ġdes", "c" ], [ "Ġb", "el" ], [ "o", "h" ], [ "vi", "ew" ], [ "a", "use" ], [ "al", "e" ], [ "ro", "s" ], [ "ot", "her" ], [ "el", "f" ], [ "n", "ing" ], [ "r", "al" ], [ "Ġf", "ollow" ], [ "ĠUn", "ited" ], [ "Ġd", "if" ], [ "ĠA", "mer" ], [ "ver", "y" ], [ "u", "res" ], [ "Ġs", "ch" ], [ "Ġd", "ay" ], [ "Ġ", "ent" ], [ "Ġw", "ell" ], [ "Ġm", "ain" ], [ "ĠTh", "is" ], [ "Ġt", "r" ], [ "Ġde", "f" ], [ "Ġo", "b" ], [ "Ġc", "re" ], [ "ter", "n" ], [ "t", "y" ], [ "ĠC", "l" ], [ "Ġe", "m" ], [ "Ġbe", "fore" ], [ "ist", "s" ], [ "ĠM", "ar" ], [ "ra", "ft" ], [ "Ġbec", "ame" ], [ "Ġthe", "se" ], [ "em", "b" ], [ "Ġper", "form" ], [ "Ġagain", "st" ], [ "a", "h" ], [ "op", "le" ], [ "iz", "ed" ], [ "iel", "d" ], [ "Ġap", "pe" ], [ "st", "ru" ], [ "Ġde", "p" ], [ "Ġo", "per" ], [ "Ġp", "op" ], [ "Ġkn", "own" ], [ "ste", "in" ], [ "i", "o" ], [ "y", "s" ], [ "Ġ", "Z" ], [ "Ġc", "ar" ], [ "Ġc", "ol" ], [ "id", "ent" ], [ "ow", "ever" ], [ "ce", "pt" ], [ "Ġrem", "ain" ], [ "s", "on" ], [ "Ġst", "ud" ], [ "Ġinclud", "ing" ], [ "Ġ", "%" ], [ "ĠA", "nd" ], [ "Ġor", "ig" ], [ "ire", "ct" ], [ "ĠPol", "ish" ], [ "Ġs", "aid" ], [ "ĠA", "t" ], [ "ur", "y" ], [ "Ġbe", "gan" ], [ "Ġdis", "c" ], [ "t", "on" ], [ "Ġs", "m" ], [ "Ġc", "are" ] ] } }