{ "version": "1.0", "truncation": null, "padding": null, "added_tokens": [ { "id": 0, "content": "<|begin_of_text|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 1, "content": "<|end_of_text|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 2, "content": "<|im_start|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 3, "content": "<|im_end|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 4, "content": "<|eot_id|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 5, "content": "<|start|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 6, "content": "<|channel|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 7, "content": "<|message|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 8, "content": "<|end|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 9, "content": "<|fitm_start|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 10, "content": "<|fitm_end|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 11, "content": "<|fitm_hole|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 12, "content": "<|pad|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 13, "content": "<|reserved_special_2|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 14, "content": "<|reserved_special_3|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 15, "content": "<|reserved_special_4|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 16, "content": "<|reserved_special_5|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 17, "content": "<|reserved_special_6|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 18, "content": "<|reserved_special_7|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 19, "content": "<|reserved_special_8|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 20, "content": "<|reserved_special_9|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 21, "content": "<|reserved_special_10|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 22, "content": "<|reserved_special_11|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 23, "content": "<|reserved_special_12|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 24, "content": "<|reserved_special_13|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 25, "content": "<|reserved_special_14|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 26, "content": "<|reserved_special_15|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 27, "content": "<|reserved_special_16|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 28, "content": "<|reserved_special_17|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 29, "content": "<|reserved_special_18|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 1024, "content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": false }, { "id": 1025, "content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": false } ], "normalizer": { "type": "Sequence", "normalizers": [] }, "pre_tokenizer": { "type": "Sequence", "pretokenizers": [ { "type": "Digits", "individual_digits": false }, { "type": "Split", "pattern": { "Regex": "\\p{Nd}{1,510}(?=(?>\\p{Nd}{510})*(?:\\P{Nd}|$))|\\G\\p{Nd}{510}" }, "behavior": "Isolated", "invert": false }, { "type": "Split", "pattern": { "Regex": "\\A\\p{Nd}{1,2}(?=\\p{Nd}{3}+\\z)" }, "behavior": "Isolated", "invert": false }, { "type": "Split", "pattern": { "Regex": "\\A\\p{Nd}{3}|\\G\\p{Nd}{3}" }, "behavior": "Isolated", "invert": false }, { "type": "Split", "pattern": { "Regex": "(?:[\\u4E00-\\u9FFF\\u3040-\\u309F\\u30A0-\\u30FF\\u3400-\\u4DBF\\uf900-\\uFAFF\\uFF65-\\uFF9F\\u2F00-\\u2FDF]+|[\\u0E00-\\u0E7F]+|[\\u0E80-\\u0EFF]+|[\\u1780-\\u17FF]+|[\\u1000-\\u109F\\uAA60-\\uAA7F\\uA9E0-\\uA9FF]+|[\\uAC00-\\uD7AF\\u1100-\\u11FF]+)" }, "behavior": "Isolated", "invert": false }, { "type": "Split", "pattern": { "Regex": "[!\"#$%&'()*+,\\-./:;<=>?@\\[\\\\\\]^_`{|}~][A-Za-z]+|[^\r\n\\p{L}\\p{P}\\p{S}]?[\\p{L}\\p{M}]+| ?[\\p{P}\\p{S}]+[\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": "Sequence", "processors": [ { "type": "ByteLevel", "add_prefix_space": true, "trim_offsets": false, "use_regex": true }, { "type": "TemplateProcessing", "single": [ { "SpecialToken": { "id": "<|begin_of_text|>", "type_id": 0 } }, { "Sequence": { "id": "A", "type_id": 0 } } ], "pair": [ { "SpecialToken": { "id": "<|begin_of_text|>", "type_id": 0 } }, { "Sequence": { "id": "A", "type_id": 0 } }, { "SpecialToken": { "id": "<|begin_of_text|>", "type_id": 0 } }, { "Sequence": { "id": "B", "type_id": 0 } } ], "special_tokens": { "<|begin_of_text|>": { "id": "<|begin_of_text|>", "ids": [ 0 ], "tokens": [ "<|begin_of_text|>" ] } } } ] }, "decoder": { "type": "ByteLevel", "add_prefix_space": true, "trim_offsets": true, "use_regex": true }, "model": { "type": "BPE", "dropout": null, "unk_token": null, "continuing_subword_prefix": null, "end_of_word_suffix": null, "fuse_unk": false, "byte_fallback": false, "ignore_merges": false, "vocab": { "<|begin_of_text|>": 0, "<|end_of_text|>": 1, "<|im_start|>": 2, "<|im_end|>": 3, "<|eot_id|>": 4, "<|start|>": 5, "<|channel|>": 6, "<|message|>": 7, "<|end|>": 8, "<|fitm_start|>": 9, "<|fitm_end|>": 10, "<|fitm_hole|>": 11, "<|pad|>": 12, "<|reserved_special_2|>": 13, "<|reserved_special_3|>": 14, "<|reserved_special_4|>": 15, "<|reserved_special_5|>": 16, "<|reserved_special_6|>": 17, "<|reserved_special_7|>": 18, "<|reserved_special_8|>": 19, "<|reserved_special_9|>": 20, "<|reserved_special_10|>": 21, "<|reserved_special_11|>": 22, "<|reserved_special_12|>": 23, "<|reserved_special_13|>": 24, "<|reserved_special_14|>": 25, "<|reserved_special_15|>": 26, "<|reserved_special_16|>": 27, "<|reserved_special_17|>": 28, "<|reserved_special_18|>": 29, "!": 30, "\"": 31, "#": 32, "$": 33, "%": 34, "&": 35, "'": 36, "(": 37, ")": 38, "*": 39, "+": 40, ",": 41, "-": 42, ".": 43, "/": 44, "0": 45, "1": 46, "2": 47, "3": 48, "4": 49, "5": 50, "6": 51, "7": 52, "8": 53, "9": 54, ":": 55, ";": 56, "<": 57, "=": 58, ">": 59, "?": 60, "@": 61, "A": 62, "B": 63, "C": 64, "D": 65, "E": 66, "F": 67, "G": 68, "H": 69, "I": 70, "J": 71, "K": 72, "L": 73, "M": 74, "N": 75, "O": 76, "P": 77, "Q": 78, "R": 79, "S": 80, "T": 81, "U": 82, "V": 83, "W": 84, "X": 85, "Y": 86, "Z": 87, "[": 88, "\\": 89, "]": 90, "^": 91, "_": 92, "`": 93, "a": 94, "b": 95, "c": 96, "d": 97, "e": 98, "f": 99, "g": 100, "h": 101, "i": 102, "j": 103, "k": 104, "l": 105, "m": 106, "n": 107, "o": 108, "p": 109, "q": 110, "r": 111, "s": 112, "t": 113, "u": 114, "v": 115, "w": 116, "x": 117, "y": 118, "z": 119, "{": 120, "|": 121, "}": 122, "~": 123, "¡": 124, "¢": 125, "£": 126, "¤": 127, "¥": 128, "¦": 129, "§": 130, "¨": 131, "©": 132, "ª": 133, "«": 134, "¬": 135, "®": 136, "¯": 137, "°": 138, "±": 139, "²": 140, "³": 141, "´": 142, "µ": 143, "¶": 144, "·": 145, "¸": 146, "¹": 147, "º": 148, "»": 149, "¼": 150, "½": 151, "¾": 152, "¿": 153, "À": 154, "Á": 155, "Â": 156, "Ã": 157, "Ä": 158, "Å": 159, "Æ": 160, "Ç": 161, "È": 162, "É": 163, "Ê": 164, "Ë": 165, "Ì": 166, "Í": 167, "Î": 168, "Ï": 169, "Ð": 170, "Ñ": 171, "Ò": 172, "Ó": 173, "Ô": 174, "Õ": 175, "Ö": 176, "×": 177, "Ø": 178, "Ù": 179, "Ú": 180, "Û": 181, "Ü": 182, "Ý": 183, "Þ": 184, "ß": 185, "à": 186, "á": 187, "â": 188, "ã": 189, "ä": 190, "å": 191, "æ": 192, "ç": 193, "è": 194, "é": 195, "ê": 196, "ë": 197, "ì": 198, "í": 199, "î": 200, "ï": 201, "ð": 202, "ñ": 203, "ò": 204, "ó": 205, "ô": 206, "õ": 207, "ö": 208, "÷": 209, "ø": 210, "ù": 211, "ú": 212, "û": 213, "ü": 214, "ý": 215, "þ": 216, "ÿ": 217, "Ā": 218, "ā": 219, "Ă": 220, "ă": 221, "Ą": 222, "ą": 223, "Ć": 224, "ć": 225, "Ĉ": 226, "ĉ": 227, "Ċ": 228, "ċ": 229, "Č": 230, "č": 231, "Ď": 232, "ď": 233, "Đ": 234, "đ": 235, "Ē": 236, "ē": 237, "Ĕ": 238, "ĕ": 239, "Ė": 240, "ė": 241, "Ę": 242, "ę": 243, "Ě": 244, "ě": 245, "Ĝ": 246, "ĝ": 247, "Ğ": 248, "ğ": 249, "Ġ": 250, "ġ": 251, "Ģ": 252, "ģ": 253, "Ĥ": 254, "ĥ": 255, "Ħ": 256, "ħ": 257, "Ĩ": 258, "ĩ": 259, "Ī": 260, "ī": 261, "Ĭ": 262, "ĭ": 263, "Į": 264, "į": 265, "İ": 266, "ı": 267, "IJ": 268, "ij": 269, "Ĵ": 270, "ĵ": 271, "Ķ": 272, "ķ": 273, "ĸ": 274, "Ĺ": 275, "ĺ": 276, "Ļ": 277, "ļ": 278, "Ľ": 279, "ľ": 280, "Ŀ": 281, "ŀ": 282, "Ł": 283, "ł": 284, "Ń": 285, "Ġt": 286, "he": 287, "Ġa": 288, "in": 289, "Ġthe": 290, "er": 291, "on": 292, "Ġ,": 293, "re": 294, "Ġs": 295, "ed": 296, "Ġo": 297, "nd": 298, "Ġw": 299, "at": 300, "Ġ.": 301, "or": 302, "it": 303, "is": 304, "Ġc": 305, "es": 306, "Ġf": 307, "en": 308, "Ġof": 309, "ar": 310, "al": 311, "Ġin": 312, "Ġb": 313, "an": 314, "Ġp": 315, "ing": 316, "as": 317, "Ġand": 318, "ic": 319, "Ġto": 320, "Ġm": 321, "ro": 322, "Ġd": 323, "Ġh": 324, "ion": 325, "le": 326, "ĠT": 327, "ou": 328, "Ġre": 329, "Ġ=": 330, "ĠA": 331, "Ġ\"": 332, "ĠS": 333, "Ġth": 334, "ent": 335, "il": 336, "st": 337, "Ġ@": 338, "el": 339, "ĠC": 340, "ĠĊ": 341, "ol": 342, "Ġl": 343, "Ġn": 344, "om": 345, "Ġe": 346, "ct": 347, "am": 348, "ad": 349, "Ġg": 350, "Ġwas": 351, "ur": 352, "Ġon": 353, "ĠThe": 354, "ĠI": 355, "im": 356, "-@": 357, "Ġ@-@": 358, "Ġbe": 359, "ly": 360, "ĠM": 361, "id": 362, "Ġfor": 363, "ir": 364, "ch": 365, "ĠB": 366, "iv": 367, "ot": 368, "Ġ'": 369, "ith": 370, "ation": 371, "ra": 372, "ig": 373, "Ġas": 374, "et": 375, "ow": 376, "us": 377, "ut": 378, "Ġst": 379, "ce": 380, "Ġwith": 381, "ĠP": 382, "ers": 383, "Ġhe": 384, "Ġthat": 385, "ay": 386, "Ġis": 387, "ĠH": 388, "ul": 389, "ĠG": 390, "ĠF": 391, "Ġal": 392, "ĠR": 393, "ĠN": 394, "ist": 395, "um": 396, "em": 397, "Ġwh": 398, "ĠW": 399, "est": 400, "Ġby": 401, "un": 402, "Ġan": 403, "ver": 404, "os": 405, "th": 406, "Ġ)": 407, "Ġ(": 408, "ter": 409, "Ġcon": 410, "ĠJ": 411, "rom": 412, "ĠD": 413, "Ġat": 414, "Ġse": 415, "and": 416, "od": 417, "ĠL": 418, "av": 419, "Ġit": 420, "00": 421, "Ġde": 422, "ag": 423, "her": 424, "ies": 425, "pe": 426, "ĠE": 427, "ain": 428, "ck": 429, "Ġhis": 430, "ri": 431, "Ġfrom": 432, "ere": 433, "res": 434, "ort": 435, "Ġpro": 436, "if": 437, "Ġcom": 438, "ew": 439, "ity": 440, "Ġwere": 441, "Ġv": 442, "ate": 443, "ĠIn": 444, "Ġsu": 445, "ĠO": 446, "op": 447, "Ġor": 448, "ich": 449, "ore": 450, "all": 451, "igh": 452, "ated": 453, "ord": 454, "se": 455, "ill": 456, "art": 457, "Ġex": 458, "ab": 459, "pt": 460, "Ġch": 461, "Ġsh": 462, "ld": 463, "Ġpl": 464, "pp": 465, "ak": 466, "Ġare": 467, "ber": 468, "gh": 469, "ess": 470, "ud": 471, "Ġâ": 472, "ant": 473, "ard": 474, "rou": 475, "ong": 476, "ĠU": 477, "ru": 478, "ia": 479, "qu": 480, "Ġwhich": 481, "ĠâĢ": 482, "ame": 483, "ment": 484, "ĠCh": 485, "Ġle": 486, "rit": 487, "Ġhad": 488, "ial": 489, "ian": 490, "og": 491, "red": 492, "ĠK": 493, "ĠSt": 494, "ive": 495, "oc": 496, "ip": 497, "ov": 498, "Ġ;": 499, "Ġr": 500, "ish": 501, "ost": 502, "our": 503, "Ġar": 504, "Ġu": 505, "Ġnot": 506, "ear": 507, "ight": 508, "ast": 509, "ac": 510, "Ġy": 511, "Ġk": 512, "ave": 513, "ary": 514, "ell": 515, "ther": 516, "ction": 517, "ical": 518, "nt": 519, "own": 520, "cc": 521, "Ġinc": 522, "ine": 523, "ge": 524, "ide": 525, "ust": 526, "ĠâĢĵ": 527, "Ġher": 528, "so": 529, "ap": 530, "ue": 531, "ure": 532, "ork": 533, "ran": 534, "out": 535, "Ġalso": 536, "Ġtheir": 537, "Ġhas": 538, "wo": 539, "Ġun": 540, "ous": 541, "ff": 542, "ign": 543, "fter": 544, "ĠV": 545, "ub": 546, "Ġrec": 547, "ome": 548, "01": 549, "Ġcl": 550, ".@": 551, "Ġ@.@": 552, "Ġcont": 553, "irst": 554, "ĠHe": 555, "Ġte": 556, "ition": 557, "ater": 558, "Ġper": 559, "ass": 560, "ack": 561, "ations": 562, "ie": 563, "Ġits": 564, "Ġab": 565, "pl": 566, "Ġone": 567, "Ġint": 568, "Ġsc": 569, "Ġfirst": 570, "ond": 571, "ime": 572, "hed": 573, "Ġ:": 574, "orm": 575, "ult": 576, "ould": 577, "ory": 578, "Ġwho": 579, "Ġwhe": 580, "ĠTh": 581, "per": 582, "Ġbut": 583, "Ġhave": 584, "Ġtwo": 585, "nder": 586, "ĠAl": 587, "ect": 588, "Ġthis": 589, "ok": 590, "ark": 591, "uring": 592, "du": 593, "ire": 594, "ough": 595, "ual": 596, "Ġall": 597, "ĠY": 598, "iz": 599, "mer": 600, "Ġus": 601, "ach": 602, "oll": 603, "Ġbeen": 604, "Ġplay": 605, "Ġres": 606, "ree": 607, "Ġshe": 608, ",@": 609, "Ġ@,@": 610, "age": 611, "Ġoff": 612, "ey": 613, "Ġcomp": 614, "Ġag": 615, "ason": 616, "port": 617, "oin": 618, "Ġad": 619, "Ġyear": 620, "Ġim": 621, "ĠIt": 622, "ence": 623, "Ġpart": 624, "Ġdes": 625, "ke": 626, "ric": 627, "are": 628, "ry": 629, "lud": 630, "Ġbec": 631, "te": 632, "Ġj": 633, "Ġother": 634, "ely": 635, "Ġdis": 636, "ph": 637, "Ġman": 638, "ound": 639, "old": 640, "Ġspe": 641, "act": 642, "Ġro": 643, "Ġafter": 644, "ance": 645, "ath": 646, "Ġen": 647, "ited": 648, "ĠUn": 649, "Ġgo": 650, "ib": 651, "ile": 652, "Ġthey": 653, "ite": 654, "man": 655, "ities": 656, "Ġover": 657, "ced": 658, "ents": 659, "ors": 660, "round": 661, "ilm": 662, "Ġinclud": 663, "Ġpre": 664, "ĠRe": 665, "vi": 666, "olog": 667, "ted": 668, "ade": 669, "ied": 670, "ose": 671, "ase": 672, "Ġcomm": 673, "Ġtime": 674, "Ġser": 675, "inal": 676, "Ġseason": 677, "99": 678, "ased": 679, "Ġout": 680, "ice": 681, "ĠAr": 682, "ates": 683, "ress": 684, "Ġup": 685, "ĠSe": 686, "ft": 687, "Ġthem": 688, "ubl": 689, "les": 690, "ild": 691, "Ġsp": 692, "Ġev": 693, "Ġmore": 694, "land": 695, "bum": 696, "fer": 697, "ces": 698, "Ġnew": 699, "gan": 700, "rough": 701, "able": 702, "ron": 703, "ts": 704, "ĠDe": 705, "ace": 706, "Ġne": 707, "Ġgod": 708, "ock": 709, "Ġalbum": 710, "rib": 711, "ward": 712, "Ġrem": 713, "Ġsec": 714, "Ġunder": 715, "wn": 716, "Ġwork": 717, "ered": 718, "ĠSh": 719, "ind": 720, "ens": 721, "Ġrel": 722, "Ġfilm": 723, "use": 724, "Ġhim": 725, "ings": 726, "ount": 727, "Ġrecord": 728, "Ġspec": 729, "ĠWhe": 730, "Ġinto": 731, "arn": 732, "reat": 733, "hip": 734, "one": 735, "orn": 736, "Ġinter": 737, "urn": 738, "ail": 739, "Ġfe": 740, "ember": 741, "Ġcons": 742, "form": 743, "ix": 744, "ved": 745, "Ġmost": 746, "Ġreg": 747, "ational": 748, "ern": 749, "arly": 750, "ĠPol": 751, "Ġact": 752, "oy": 753, "ink": 754, "ames": 755, "ordan": 756, "ĠJordan": 757, "ĠOn": 758, "Ġair": 759, "ĠAs": 760, "Ġduring": 761, "ĠBrit": 762, "ions": 763, "aw": 764, "Ġco": 765, "Ġfl": 766, "ee": 767, "oth": 768, "ae": 769, "vel": 770, "Ġtra": 771, "ons": 772, "ang": 773, "ick": 774, "Ġass": 775, "Ġatt": 776, "Ġra": 777, "oss": 778, "Ġsub": 779, "Ġkn": 780, "Ġonly": 781, "Ġagain": 782, "way": 783, "000": 784, "ans": 785, "Ġme": 786, "Ġnum": 787, "Ġform": 788, "iss": 789, "Ġpubl": 790, "ng": 791, "ished": 792, "arg": 793, "Ġret": 794, "Ġrele": 795, "Ġwould": 796, "een": 797, "ve": 798, "Ġfour": 799, "ict": 800, "Ġthree": 801, "erson": 802, "tle": 803, "Ġprodu": 804, "Ġmon": 805, "Ġteam": 806, "ook": 807, "orth": 808, "ĠShe": 809, "Ġend": 810, "ars": 811, "Ġbet": 812, "vest": 813, "Ġbu": 814, "Ġsecond": 815, "Ġthan": 816, "ste": 817, "ĠIs": 818, "ĠInd": 819, "Ġbeing": 820, "Ġdec": 821, "ood": 822, "Ġcan": 823, "ener": 824, "Ġthrough": 825, "Ġabout": 826, "Ġcent": 827, "cted": 828, "Ġapp": 829, "Ġwhen": 830, "Ġlater": 831, "ower": 832, "ull": 833, "ony": 834, "ole": 835, "eler": 836, "Ġacc": 837, "Ġpe": 838, "ake": 839, "ike": 840, "ily": 841, "rist": 842, "Ġac": 843, "Ġind": 844, "ĠWheeler": 845, "ĠLe": 846, "outh": 847, "ĠCom": 848, "usic": 849, "ular": 850, "ious": 851, "ween": 852, "Ġsome": 853, "urch": 854, "end": 855, "ism": 856, "chae": 857, "ĠNew": 858, "chaeolog": 859, "aid": 860, "Ġwrit": 861, "als": 862, "Ġdo": 863, "Ġsuch": 864, "ollow": 865, "ally": 866, "ten": 867, "Ġam": 868, "ins": 869, "Ġpol": 870, "Ġmade": 871, "ific": 872, "Ġmet": 873, "Ġgame": 874, "iel": 875, "Ġhist": 876, "ute": 877, "ĠGal": 878, "Ġwhere": 879, "fore": 880, "ating": 881, "Ġrep": 882, "resent": 883, "ject": 884, "Ġsy": 885, "orld": 886, "Ġpr": 887, "Ġbl": 888, "amp": 889, "iet": 890, "ob": 891, "Ġap": 892, "though": 893, "ove": 894, "ĠBritish": 895, "Ġbetween": 896, "veston": 897, "ĠGalveston": 898, "erman": 899, "row": 900, "Ġant": 901, "Ġship": 902, "ĠChrist": 903, "az": 904, "ool": 905, "Ġthere": 906, "Ġsign": 907, "ĠBl": 908, "Ġsur": 909, "ised": 910, "ired": 911, "ĠYork": 912, "94": 913, "led": 914, "Ġcity": 915, "ĠAll": 916, "98": 917, "up": 918, "Ġchar": 919, "Ġsong": 920, "Ġcall": 921, "ĠGerman": 922, "Ġmany": 923, "Ġnumber": 924, "Ġhigh": 925, "ug": 926, "ics": 927, "ican": 928, "Ġmin": 929, "Ġloc": 930, "Ġno": 931, "Ġwhile": 932, "air": 933, "Ġqu": 934, "Ġboth": 935, "Ġele": 936, "rans": 937, "Ġsupp": 938, "ever": 939, "ĠTown": 940, "ivers": 941, "ife": 942, "Ġlead": 943, "Ġused": 944, "hes": 945, "ived": 946, "veral": 947, "Ġthen": 948, "Ġso": 949, "Ġyears": 950, "Ġgods": 951, "gy": 952, "ren": 953, "Ġlong": 954, "Ġdesc": 955, "91": 956, "Ġbel": 957, "oh": 958, "view": 959, "ause": 960, "ale": 961, "ros": 962, "other": 963, "elf": 964, "ning": 965, "ral": 966, "Ġfollow": 967, "ĠUnited": 968, "Ġdif": 969, "ĠAmer": 970, "very": 971, "ures": 972, "Ġsch": 973, "Ġday": 974, "Ġent": 975, "Ġwell": 976, "Ġmain": 977, "ĠThis": 978, "Ġtr": 979, "Ġdef": 980, "20": 981, "Ġob": 982, "Ġcre": 983, "tern": 984, "ty": 985, "ĠCl": 986, "Ġem": 987, "Ġbefore": 988, "ists": 989, "ĠMar": 990, "raft": 991, "Ġbecame": 992, "Ġthese": 993, "emb": 994, "Ġperform": 995, "Ġagainst": 996, "ah": 997, "ople": 998, "ized": 999, "ield": 1000, "Ġappe": 1001, "stru": 1002, "Ġdep": 1003, "30": 1004, "Ġoper": 1005, "Ġpop": 1006, "Ġknown": 1007, "stein": 1008, "io": 1009, "ys": 1010, "ĠZ": 1011, "Ġcar": 1012, "Ġcol": 1013, "ident": 1014, "owever": 1015, "cept": 1016, "Ġremain": 1017, "son": 1018, "Ġstud": 1019, "Ġincluding": 1020, "Ġ%": 1021, "ĠAnd": 1022, "Ġorig": 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" ], [ "0", "0" ], [ "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" ], [ "0", "1" ], [ "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" ], [ "9", "9" ], [ "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" ], [ "00", "0" ], [ "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" ], [ "9", "4" ], [ "l", "ed" ], [ "Ġc", "ity" ], [ "ĠAl", "l" ], [ "9", "8" ], [ "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" ], [ "9", "1" ], [ "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" ], [ "2", "0" ], [ "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" ], [ "3", "0" ], [ "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" ] ] } }