{ "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": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 2, "content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 3, "content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true } ], "normalizer": null, "pre_tokenizer": { "type": "ByteLevel", "add_prefix_space": false, "trim_offsets": true, "use_regex": true }, "post_processor": { "type": "TemplateProcessing", "single": [ { "Sequence": { "id": "A", "type_id": 0 } } ], "pair": [ { "Sequence": { "id": "A", "type_id": 0 } }, { "Sequence": { "id": "B", "type_id": 1 } } ], "special_tokens": {} }, "decoder": { "type": "ByteLevel", "add_prefix_space": true, "trim_offsets": true, "use_regex": true }, "model": { "type": "BPE", "dropout": null, "unk_token": "", "continuing_subword_prefix": null, "end_of_word_suffix": null, "fuse_unk": false, "byte_fallback": false, "ignore_merges": false, "vocab": { "": 0, "": 1, "": 2, "": 3, "!": 4, "\"": 5, "$": 6, "&": 7, "'": 8, ",": 9, "-": 10, ".": 11, "0": 12, "1": 13, "2": 14, "3": 15, "4": 16, "5": 17, "6": 18, "7": 19, "8": 20, "9": 21, ":": 22, ";": 23, "?": 24, "A": 25, "B": 26, "C": 27, "D": 28, "E": 29, "F": 30, "G": 31, "H": 32, "I": 33, "J": 34, "K": 35, "L": 36, "M": 37, "N": 38, "O": 39, "P": 40, "Q": 41, "R": 42, "S": 43, "T": 44, "U": 45, "V": 46, "W": 47, "X": 48, "Y": 49, "Z": 50, "a": 51, "b": 52, "c": 53, "d": 54, "e": 55, "f": 56, "g": 57, "h": 58, "i": 59, "j": 60, "k": 61, "l": 62, "m": 63, "n": 64, "o": 65, "p": 66, "q": 67, "r": 68, "s": 69, "t": 70, "u": 71, "v": 72, "w": 73, "x": 74, "y": 75, "z": 76, "¡": 77, "¢": 78, "¦": 79, "©": 80, "«": 81, "¬": 82, "±": 83, "³": 84, "»": 85, "Â": 86, "Ã": 87, "Å": 88, "Ë": 89, "â": 90, "Ċ": 91, "Ġ": 92, "Ģ": 93, "Ĥ": 94, "ĥ": 95, "Ħ": 96, "ĵ": 97, "ľ": 98, "Ŀ": 99, "he": 100, "Ġt": 101, "Ġa": 102, "Ġs": 103, "Ġw": 104, "nd": 105, "Ġthe": 106, "ed": 107, "in": 108, "Ġand": 109, "Ġto": 110, "Ġb": 111, "Ġwa": 112, "Ġh": 113, "re": 114, "it": 115, "ou": 116, "Ġf": 117, "er": 118, "Ġl": 119, "Ġhe": 120, "Ġc": 121, "Ġwas": 122, "Ġd": 123, "Ġp": 124, "Ġm": 125, "Ġo": 126, "ing": 127, "om": 128, "ar": 129, "ay": 130, "is": 131, "Ġg": 132, "ĠT": 133, "id": 134, "at": 135, "il": 136, "en": 137, "Ġsa": 138, "ne": 139, "Ġha": 140, "im": 141, "ĠS": 142, "an": 143, "or": 144, "Ġit": 145, "Ġth": 146, "ll": 147, "le": 148, "ĠThe": 149, "et": 150, "ĠH": 151, "Ġher": 152, "on": 153, "ir": 154, "ver": 155, "Ġin": 156, "Ġn": 157, "ĠHe": 158, "Ġe": 159, "ot": 160, "ĠShe": 161, "ld": 162, "ut": 163, "Ġu": 164, "ow": 165, "ck": 166, "Ġbe": 167, "ce": 168, "Ġshe": 169, "Ġsaid": 170, "ig": 171, "Ġst": 172, "oo": 173, "Ġso": 174, "pp": 175, "Ġr": 176, "am": 177, "Ġ\"": 178, "ke": 179, "ve": 180, "Ġy": 181, "Ġof": 182, "ith": 183, "st": 184, "ked": 185, "Ġhis": 186, "Ġwith": 187, "very": 188, "Ġday": 189, "ĠI": 190, "ri": 191, "nt": 192, "Ġpl": 193, "ad": 194, "Ġthat": 195, "Ġup": 196, "ily": 197, "ĠThey": 198, "Ġhad": 199, "Ġyou": 200, "ĠL": 201, "ould": 202, "el": 203, "itt": 204, "Ġon": 205, "The": 206, "es": 207, "ent": 208, "Ġplay": 209, "ly": 210, "Ġfor": 211, "my": 212, "Ġthey": 213, "Ġwe": 214, "Ġmom": 215, "'s": 216, "un": 217, "ound": 218, "out": 219, "ittle": 220, "ĠĊ": 221, "Ġlittle": 222, "Ġhapp": 223, "ch": 224, "her": 225, "ime": 226, "Ġthere": 227, "Ġtime": 228, "Ġsh": 229, "all": 230, "Ġvery": 231, "Ġli": 232, "Ġwh": 233, "ĠB": 234, "ht": 235, "Ġne": 236, "Ġre": 237, "Ġsm": 238, "al": 239, "Ġwant": 240, "ome": 241, "se": 242, "end": 243, "Ġdo": 244, "ack": 245, "ĠLily": 246, "Ġk": 247, "Ġas": 248, "On": 249, "Ġhappy": 250, "Ġbig": 251, "Ġan": 252, "Ġbut": 253, "Once": 254, "ra": 255, "Ġsaw": 256, "One": 257, "riend": 258, "Ġfriend": 259, "ved": 260, "'t": 261, "Ġloo": 262, "ake": 263, "ide": 264, "ore": 265, "ug": 266, "ec": 267, "irl": 268, "ĠM": 269, "ter": 270, "Ġgirl": 271, "ĠIt": 272, "ry": 273, "Ġbo": 274, "Ġnot": 275, "Ġupon": 276, "Ġlo": 277, "Ġwere": 278, "Ġex": 279, "Ġhim": 280, "!\"": 281, "Ġgo": 282, ".\"": 283, "Ġout": 284, "ard": 285, "Ġj": 286, "ĠJ": 287, "Ġsp": 288, "Ġwanted": 289, "fu": 290, "Ġsmil": 291, "Ġcould": 292, "Ġar": 293, "Ġtoo": 294, "way": 295, "hen": 296, "Ġis": 297, "Ġse": 298, "ind": 299, "ĠTim": 300, "ill": 301, "hing": 302, "ur": 303, "ain": 304, "ic": 305, "Ġat": 306, "art": 307, "ĠA": 308, "hed": 309, "Ġall": 310, "Ġwent": 311, "â": 312, "âĤ": 313, "âĤ¬": 314, "ful": 315, "rom": 316, "um": 317, "ight": 318, "Ġnam": 319, "Ġthem": 320, "lp": 321, "Ġaround": 322, "Ġfriends": 323, "Ġsmiled": 324, "Ġdid": 325, "oug": 326, "Ġhelp": 327, "Ġback": 328, "ood": 329, "ark": 330, "Ġcl": 331, "Ġhave": 332, "omet": 333, "Ġasked": 334, "ss": 335, "Ġtheir": 336, "?\"": 337, "Ġca": 338, "Ġcan": 339, "Ġfun": 340, "Ġnamed": 341, "Ġlooked": 342, "side": 343, "elt": 344, "Ġboy": 345, "Ġal": 346, "Ġle": 347, "Ġloved": 348, "ure": 349, "Ġsomet": 350, "Ġstart": 351, "ĠOne": 352, "Ġfelt": 353, "Ġfe": 354, "ro": 355, "ick": 356, "one": 357, "get": 358, "Ġwould": 359, "ie": 360, "Ġare": 361, "ame": 362, "dd": 363, "Ġno": 364, "ited": 365, "Ġsc": 366, "Ġman": 367, "ice": 368, "Ġexc": 369, "Ġwor": 370, "ree": 371, "Ġlike": 372, "king": 373, "ong": 374, "Ġsomething": 375, "Ġro": 376, "ĠTimmy": 377, "ird": 378, "Ġstarted": 379, "gether": 380, "Ġsome": 381, "op": 382, "Ġag": 383, "Ġsee": 384, "Ġbird": 385, "Ġme": 386, "ĠW": 387, "Ġfa": 388, "ade": 389, "Ġtogether": 390, "ag": 391, "pped": 392, "own": 393, "Ġran": 394, "Ġaway": 395, "Ġwhat": 396, "Ġtoy": 397, "ings": 398, "pl": 399, "ĠBen": 400, "ĠE": 401, "oud": 402, "ared": 403, "Ġexcited": 404, "Ġthen": 405, "Ġmake": 406, "You": 407, "Ġmu": 408, "ble": 409, "if": 410, "Ġbr": 411, "ally": 412, "ĠTom": 413, "Ġmade": 414, "hat": 415, "Ġhome": 416, "Ġco": 417, "as": 418, "qu": 419, "Ġwal": 420, "Ġwhen": 421, "Ġagain": 422, "Ġfound": 423, "Ġch": 424, "Ġpark": 425, ",\"": 426, "Ġfrom": 427, "Ġla": 428, "Ġnew": 429, "ell": 430, "ought": 431, "Ġwho": 432, "ĠBut": 433, "Ġdec": 434, "Ġot": 435, "ep": 436, "ous": 437, "Ġput": 438, "Ġget": 439, "Ġplaying": 440, "Ġsad": 441, "Ġother": 442, "Ġcar": 443, "Ġevery": 444, "Ġone": 445, "udd": 446, "Ġfl": 447, "Ġpr": 448, "Ġhug": 449, "Ġsay": 450, "ny": 451, "Ġgot": 452, "ided": 453, "Ġbu": 454, "ave": 455, "Ġdecided": 456, "ried": 457, "bb": 458, "Ġv": 459, "ach": 460, "Ġthings": 461, "Ġold": 462, "Ġgood": 463, "ust": 464, "Ġsw": 465, "eci": 466, "Ġcame": 467, "Ġthan": 468, "ouse": 469, "Ġbec": 470, "ĠD": 471, "Ġfeel": 472, "Ġdown": 473, "Ġfind": 474, "ways": 475, "Ġkn": 476, "udden": 477, "Ġbl": 478, "Ġke": 479, "Ġalways": 480, "Ġlot": 481, "ecial": 482, "Ġspecial": 483, "Ġgr": 484, "Ġtree": 485, "uddenly": 486, "ĠF": 487, "Ġpo": 488, "ant": 489, "Ġab": 490, "Ġscared": 491, "nder": 492, "Lily": 493, "Ġkne": 494, "Ġcare": 495, "Ġthought": 496, "Ġgra": 497, "Ġdidn": 498, "ook": 499, "ist": 500, "ched": 501, "Ġint": 502, "ite": 503, "Ġdad": 504, "Ġtake": 505, "Ġtook": 506, "ĠYou": 507, "Ġabout": 508, "Ġliked": 509, "ened": 510, "ue": 511 }, "merges": [ [ "h", "e" ], [ "Ġ", "t" ], [ "Ġ", "a" ], [ "Ġ", "s" ], [ "Ġ", "w" ], [ "n", "d" ], [ "Ġt", "he" ], [ "e", "d" ], [ "i", "n" ], [ "Ġa", "nd" ], [ "Ġt", "o" ], [ "Ġ", "b" ], [ "Ġw", "a" ], [ "Ġ", "h" ], [ "r", "e" ], [ "i", "t" ], [ "o", "u" ], [ "Ġ", "f" ], [ "e", "r" ], [ "Ġ", "l" ], [ "Ġ", "he" ], [ "Ġ", "c" ], [ "Ġwa", "s" ], [ "Ġ", "d" ], [ "Ġ", "p" ], [ "Ġ", "m" ], [ "Ġ", "o" ], [ "in", "g" ], [ "o", "m" ], [ "a", "r" ], [ "a", "y" ], [ "i", "s" ], [ "Ġ", "g" ], [ "Ġ", "T" ], [ "i", "d" ], [ "a", "t" ], [ "i", "l" ], [ "e", "n" ], [ "Ġs", "a" ], [ "n", "e" ], [ "Ġh", "a" ], [ "i", "m" ], [ "Ġ", "S" ], [ "a", "n" ], [ "o", "r" ], [ "Ġ", "it" ], [ "Ġt", "h" ], [ "l", "l" ], [ "l", "e" ], [ "ĠT", "he" ], [ "e", "t" ], [ "Ġ", "H" ], [ "Ġhe", "r" ], [ "o", "n" ], [ "i", "r" ], [ "v", "er" ], [ "Ġ", "in" ], [ "Ġ", "n" ], [ "ĠH", "e" ], [ "Ġ", "e" ], [ "o", "t" ], [ "ĠS", "he" ], [ "l", "d" ], [ "u", "t" ], [ "Ġ", "u" ], [ "o", "w" ], [ "c", "k" ], [ "Ġb", "e" ], [ "c", "e" ], [ "Ġs", "he" ], [ "Ġsa", "id" ], [ "i", "g" ], [ "Ġs", "t" ], [ "o", "o" ], [ "Ġs", "o" ], [ "p", "p" ], [ "Ġ", "r" ], [ "a", "m" ], [ "Ġ", "\"" ], [ "k", "e" ], [ "v", "e" ], [ "Ġ", "y" ], [ "Ġo", "f" ], [ "it", "h" ], [ "s", "t" ], [ "k", "ed" ], [ "Ġh", "is" ], [ "Ġw", "ith" ], [ "ver", "y" ], [ "Ġd", "ay" ], [ "Ġ", "I" ], [ "r", "i" ], [ "n", "t" ], [ "Ġp", "l" ], [ "a", "d" ], [ "Ġth", "at" ], [ "Ġu", "p" ], [ "il", "y" ], [ "ĠThe", "y" ], [ "Ġha", "d" ], [ "Ġy", "ou" ], [ "Ġ", "L" ], [ "ou", "ld" ], [ "e", "l" ], [ "it", "t" ], [ "Ġo", "n" ], [ "T", "he" ], [ "e", "s" ], [ "en", "t" ], [ "Ġpl", "ay" ], [ "l", "y" ], [ "Ġf", "or" ], [ "m", "y" ], [ "Ġthe", "y" ], [ "Ġw", "e" ], [ "Ġm", "om" ], [ "'", "s" ], [ "u", "n" ], [ "ou", "nd" ], [ "ou", "t" ], [ "itt", "le" ], [ "Ġ", "Ċ" ], [ "Ġl", "ittle" ], [ "Ġha", "pp" ], [ "c", "h" ], [ "he", "r" ], [ "im", "e" ], [ "Ġthe", "re" ], [ "Ġt", "ime" ], [ "Ġs", "h" ], [ "a", "ll" ], [ "Ġ", "very" ], [ "Ġl", "i" ], [ "Ġw", "h" ], [ "Ġ", "B" ], [ "h", "t" ], [ "Ġ", "ne" ], [ "Ġ", "re" ], [ "Ġs", "m" ], [ "a", "l" ], [ "Ġwa", "nt" ], [ "om", "e" ], [ "s", "e" ], [ "e", "nd" ], [ "Ġd", "o" ], [ "a", "ck" ], [ "ĠL", "ily" ], [ "Ġ", "k" ], [ "Ġa", "s" ], [ "O", "n" ], [ "Ġhapp", "y" ], [ "Ġb", "ig" ], [ "Ġa", "n" ], [ "Ġb", "ut" ], [ "On", "ce" ], [ "r", "a" ], [ "Ġsa", "w" ], [ "O", "ne" ], [ "ri", "end" ], [ "Ġf", "riend" ], [ "v", "ed" ], [ "'", "t" ], [ "Ġl", "oo" ], [ "a", "ke" ], [ "id", "e" ], [ "o", "re" ], [ "u", "g" ], [ "e", "c" ], [ "ir", "l" ], [ "Ġ", "M" ], [ "t", "er" ], [ "Ġg", "irl" ], [ "ĠI", "t" ], [ "r", "y" ], [ "Ġb", "o" ], [ "Ġn", "ot" ], [ "Ġup", "on" ], [ "Ġl", "o" ], [ "Ġwe", "re" ], [ "Ġe", "x" ], [ "Ġh", "im" ], [ "!", "\"" ], [ "Ġg", "o" ], [ ".", "\"" ], [ "Ġ", "out" ], [ "ar", "d" ], [ "Ġ", "j" ], [ "Ġ", "J" ], [ "Ġs", "p" ], [ "Ġwant", "ed" ], [ "f", "u" ], [ "Ġsm", "il" ], [ "Ġc", "ould" ], [ "Ġa", "r" ], [ "Ġto", "o" ], [ "w", "ay" ], [ "he", "n" ], [ "Ġ", "is" ], [ "Ġs", "e" ], [ "i", "nd" ], [ "ĠT", "im" ], [ "il", "l" ], [ "h", "ing" ], [ "u", "r" ], [ "a", "in" ], [ "i", "c" ], [ "Ġa", "t" ], [ "ar", "t" ], [ "Ġ", "A" ], [ "he", "d" ], [ "Ġa", "ll" ], [ "Ġw", "ent" ], [ "Ã", "¢" ], [ "â", "Ĥ" ], [ "âĤ", "¬" ], [ "fu", "l" ], [ "r", "om" ], [ "u", "m" ], [ "ig", "ht" ], [ "Ġn", "am" ], [ "Ġthe", "m" ], [ "l", "p" ], [ "Ġar", "ound" ], [ "Ġfriend", "s" ], [ "Ġsmil", "ed" ], [ "Ġd", "id" ], [ "ou", "g" ], [ "Ġhe", "lp" ], [ "Ġb", "ack" ], [ "oo", "d" ], [ "ar", "k" ], [ "Ġc", "l" ], [ "Ġha", "ve" ], [ "om", "et" ], [ "Ġas", "ked" ], [ "s", "s" ], [ "Ġthe", "ir" ], [ "?", "\"" ], [ "Ġc", "a" ], [ "Ġc", "an" ], [ "Ġf", "un" ], [ "Ġnam", "ed" ], [ "Ġloo", "ked" ], [ "s", "ide" ], [ "el", "t" ], [ "Ġbo", "y" ], [ "Ġa", "l" ], [ "Ġl", "e" ], [ "Ġlo", "ved" ], [ "u", "re" ], [ "Ġs", "omet" ], [ "Ġst", "art" ], [ "Ġ", "One" ], [ "Ġf", "elt" ], [ "Ġf", "e" ], [ "r", "o" ], [ "i", "ck" ], [ "o", "ne" ], [ "g", "et" ], [ "Ġw", "ould" ], [ "i", "e" ], [ "Ġa", "re" ], [ "am", "e" ], [ "d", "d" ], [ "Ġn", "o" ], [ "it", "ed" ], [ "Ġs", "c" ], [ "Ġm", "an" ], [ "i", "ce" ], [ "Ġex", "c" ], [ "Ġw", "or" ], [ "re", "e" ], [ "Ġli", "ke" ], [ "k", "ing" ], [ "on", "g" ], [ "Ġsomet", "hing" ], [ "Ġr", "o" ], [ "ĠTim", "my" ], [ "ir", "d" ], [ "Ġstart", "ed" ], [ "get", "her" ], [ "Ġs", "ome" ], [ "o", "p" ], [ "Ġa", "g" ], [ "Ġse", "e" ], [ "Ġb", "ird" ], [ "Ġm", "e" ], [ "Ġ", "W" ], [ "Ġf", "a" ], [ "ad", "e" ], [ "Ġto", "gether" ], [ "a", "g" ], [ "pp", "ed" ], [ "ow", "n" ], [ "Ġr", "an" ], [ "Ġa", "way" ], [ "Ġwh", "at" ], [ "Ġto", "y" ], [ "ing", "s" ], [ "p", "l" ], [ "ĠB", "en" ], [ "Ġ", "E" ], [ "ou", "d" ], [ "ar", "ed" ], [ "Ġexc", "ited" ], [ "Ġthe", "n" ], [ "Ġm", "ake" ], [ "Y", "ou" ], [ "Ġm", "u" ], [ "b", "le" ], [ "i", "f" ], [ "Ġb", "r" ], [ "all", "y" ], [ "ĠT", "om" ], [ "Ġm", "ade" ], [ "h", "at" ], [ "Ġh", "ome" ], [ "Ġc", "o" ], [ "a", "s" ], [ "q", "u" ], [ "Ġwa", "l" ], [ "Ġw", "hen" ], [ "Ġag", "ain" ], [ "Ġf", "ound" ], [ "Ġc", "h" ], [ "Ġp", "ark" ], [ ",", "\"" ], [ "Ġf", "rom" ], [ "Ġl", "a" ], [ "Ġne", "w" ], [ "e", "ll" ], [ "oug", "ht" ], [ "Ġwh", "o" ], [ "ĠB", "ut" ], [ "Ġd", "ec" ], [ "Ġo", "t" ], [ "e", "p" ], [ "ou", "s" ], [ "Ġp", "ut" ], [ "Ġg", "et" ], [ "Ġplay", "ing" ], [ "Ġsa", "d" ], [ "Ġot", "her" ], [ "Ġc", "ar" ], [ "Ġe", "very" ], [ "Ġo", "ne" ], [ "u", "dd" ], [ "Ġf", "l" ], [ "Ġp", "r" ], [ "Ġh", "ug" ], [ "Ġs", "ay" ], [ "n", "y" ], [ "Ġg", "ot" ], [ "id", "ed" ], [ "Ġb", "u" ], [ "a", "ve" ], [ "Ġdec", "ided" ], [ "ri", "ed" ], [ "b", "b" ], [ "Ġ", "v" ], [ "a", "ch" ], [ "Ġth", "ings" ], [ "Ġo", "ld" ], [ "Ġg", "ood" ], [ "u", "st" ], [ "Ġs", "w" ], [ "ec", "i" ], [ "Ġc", "ame" ], [ "Ġth", "an" ], [ "ou", "se" ], [ "Ġbe", "c" ], [ "Ġ", "D" ], [ "Ġfe", "el" ], [ "Ġd", "own" ], [ "Ġf", "ind" ], [ "way", "s" ], [ "Ġk", "n" ], [ "udd", "en" ], [ "Ġb", "l" ], [ "Ġ", "ke" ], [ "Ġal", "ways" ], [ "Ġl", "ot" ], [ "eci", "al" ], [ "Ġsp", "ecial" ], [ "Ġg", "r" ], [ "Ġt", "ree" ], [ "udden", "ly" ], [ "Ġ", "F" ], [ "Ġp", "o" ], [ "an", "t" ], [ "Ġa", "b" ], [ "Ġsc", "ared" ], [ "nd", "er" ], [ "L", "ily" ], [ "Ġk", "ne" ], [ "Ġca", "re" ], [ "Ġth", "ought" ], [ "Ġg", "ra" ], [ "Ġdid", "n" ], [ "oo", "k" ], [ "is", "t" ], [ "c", "hed" ], [ "Ġin", "t" ], [ "it", "e" ], [ "Ġd", "ad" ], [ "Ġt", "ake" ], [ "Ġtoo", "k" ], [ "Ġ", "You" ], [ "Ġab", "out" ], [ "Ġli", "ked" ], [ "en", "ed" ], [ "u", "e" ] ] } }