Hugging Face's logo

nz
/
BPE_GPT2_TinyStoriesV2_cleaned_1024

Transformers
Inference Endpoints
Model card Files Community
BPE_GPT2_TinyStoriesV2_cleaned_1024 / tokenizer.json
nz's picture
nz
Upload tokenizer
a599f27 verified
raw
history blame contribute delete
32 kB
{
"version": "1.0",
"truncation": null,
"padding": null,
"added_tokens": [
{
"id": 0,
"content": "<|endoftext|>",
"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": "ByteLevel",
"add_prefix_space": true,
"trim_offsets": true,
"use_regex": true
},
"decoder": null,
"model": {
"type": "BPE",
"dropout": null,
"unk_token": "<|endoftext|>",
"continuing_subword_prefix": null,
"end_of_word_suffix": null,
"fuse_unk": false,
"byte_fallback": false,
"ignore_merges": false,
"vocab": {
"<|endoftext|>": 0,
"\u0000": 1,
"\u0001": 2,
"\u0002": 3,
"\u0003": 4,
"\u0004": 5,
"\u0005": 6,
"\u0006": 7,
"\u0007": 8,
"\b": 9,
"\t": 10,
"\n": 11,
"\u000b": 12,
"\f": 13,
"\r": 14,
"\u000e": 15,
"\u000f": 16,
"\u0010": 17,
"\u0011": 18,
"\u0012": 19,
"\u0013": 20,
"\u0014": 21,
"\u0015": 22,
"\u0016": 23,
"\u0017": 24,
"\u0018": 25,
"\u0019": 26,
"\u001a": 27,
"\u001b": 28,
"\u001c": 29,
"\u001d": 30,
"\u001e": 31,
"\u001f": 32,
" ": 33,
"!": 34,
"\"": 35,
"#": 36,
"$": 37,
"%": 38,
"&": 39,
"'": 40,
"(": 41,
")": 42,
"*": 43,
"+": 44,
",": 45,
"-": 46,
".": 47,
"/": 48,
"0": 49,
"1": 50,
"2": 51,
"3": 52,
"4": 53,
"5": 54,
"6": 55,
"7": 56,
"8": 57,
"9": 58,
":": 59,
";": 60,
"<": 61,
"=": 62,
">": 63,
"?": 64,
"@": 65,
"A": 66,
"B": 67,
"C": 68,
"D": 69,
"E": 70,
"F": 71,
"G": 72,
"H": 73,
"I": 74,
"J": 75,
"K": 76,
"L": 77,
"M": 78,
"N": 79,
"O": 80,
"P": 81,
"Q": 82,
"R": 83,
"S": 84,
"T": 85,
"U": 86,
"V": 87,
"W": 88,
"X": 89,
"Y": 90,
"Z": 91,
"[": 92,
"\\": 93,
"]": 94,
"^": 95,
"_": 96,
"`": 97,
"a": 98,
"b": 99,
"c": 100,
"d": 101,
"e": 102,
"f": 103,
"g": 104,
"h": 105,
"i": 106,
"j": 107,
"k": 108,
"l": 109,
"m": 110,
"n": 111,
"o": 112,
"p": 113,
"q": 114,
"r": 115,
"s": 116,
"t": 117,
"u": 118,
"v": 119,
"w": 120,
"x": 121,
"y": 122,
"z": 123,
"{": 124,
"|": 125,
"}": 126,
"~": 127,
"": 128,
"€": 129,
"": 130,
"‚": 131,
"ƒ": 132,
"„": 133,
"…": 134,
"†": 135,
"‡": 136,
"ˆ": 137,
"‰": 138,
"Š": 139,
"‹": 140,
"Œ": 141,
"": 142,
"Ž": 143,
"": 144,
"": 145,
"‘": 146,
"’": 147,
"“": 148,
"”": 149,
"•": 150,
"–": 151,
"—": 152,
"˜": 153,
"™": 154,
"š": 155,
"›": 156,
"œ": 157,
"": 158,
"ž": 159,
"Ÿ": 160,
" ": 161,
"¡": 162,
"¢": 163,
"£": 164,
"¤": 165,
"¥": 166,
"¦": 167,
"§": 168,
"¨": 169,
"©": 170,
"ª": 171,
"«": 172,
"¬": 173,
"­": 174,
"®": 175,
"¯": 176,
"°": 177,
"±": 178,
"²": 179,
"³": 180,
"´": 181,
"µ": 182,
"¶": 183,
"·": 184,
"¸": 185,
"¹": 186,
"º": 187,
"»": 188,
"¼": 189,
"½": 190,
"¾": 191,
"¿": 192,
"À": 193,
"Á": 194,
"Â": 195,
"Ã": 196,
"Ä": 197,
"Å": 198,
"Æ": 199,
"Ç": 200,
"È": 201,
"É": 202,
"Ê": 203,
"Ë": 204,
"Ì": 205,
"Í": 206,
"Î": 207,
"Ï": 208,
"Ð": 209,
"Ñ": 210,
"Ò": 211,
"Ó": 212,
"Ô": 213,
"Õ": 214,
"Ö": 215,
"×": 216,
"Ø": 217,
"Ù": 218,
"Ú": 219,
"Û": 220,
"Ü": 221,
"Ý": 222,
"Þ": 223,
"ß": 224,
"à": 225,
"á": 226,
"â": 227,
"ã": 228,
"ä": 229,
"å": 230,
"æ": 231,
"ç": 232,
"è": 233,
"é": 234,
"ê": 235,
"ë": 236,
"ì": 237,
"í": 238,
"î": 239,
"ï": 240,
"ð": 241,
"ñ": 242,
"ò": 243,
"ó": 244,
"ô": 245,
"õ": 246,
"ö": 247,
"÷": 248,
"ø": 249,
"ù": 250,
"ú": 251,
"û": 252,
"ü": 253,
"ý": 254,
"þ": 255,
"ÿ": 256,
"Ċ": 257,
"Ġ": 258,
"Ġt": 259,
"he": 260,
"Ġa": 261,
"Ġs": 262,
"nd": 263,
"Ġw": 264,
"Ġthe": 265,
"ed": 266,
"Ġb": 267,
"Ġto": 268,
"Ġand": 269,
"Ġh": 270,
"Ġf": 271,
"ĠT": 272,
"in": 273,
"Ġwa": 274,
"re": 275,
"it": 276,
"ou": 277,
"Ġl": 278,
"Ġd": 279,
"Ġc": 280,
"Ġp": 281,
"ay": 282,
"Ġm": 283,
"er": 284,
"Ġwas": 285,
"ĠThe": 286,
"om": 287,
"Ġhe": 288,
"is": 289,
"Ġn": 290,
"ar": 291,
"im": 292,
"on": 293,
"Ġsa": 294,
"id": 295,
"ll": 296,
"Ġha": 297,
"Ġg": 298,
"at": 299,
"ĠS": 300,
"ing": 301,
"ot": 302,
"en": 303,
"an": 304,
"le": 305,
"or": 306,
"end": 307,
"ir": 308,
"of": 309,
"am": 310,
"et": 311,
"ĠH": 312,
"Ġit": 313,
"Ġth": 314,
"ig": 315,
"ĠThey": 316,
"Ġin": 317,
"il": 318,
"Ġpl": 319,
"Ġ\"": 320,
"ĠHe": 321,
"ow": 322,
"ri": 323,
"ver": 324,
"ut": 325,
"Ġu": 326,
"Ġbe": 327,
"Ġplay": 328,
"Ġsaid": 329,
"ith": 330,
"Ġday": 331,
"Ġwith": 332,
"pp": 333,
"On": 334,
"Ġy": 335,
"oo": 336,
"ked": 337,
"Ġr": 338,
"ex": 339,
"Ġher": 340,
"ce": 341,
"ĠI": 342,
"ĠTim": 343,
"ĠShe": 344,
"ld": 345,
"Ġhis": 346,
"Ġst": 347,
"ke": 348,
"Ġbig": 349,
"nt": 350,
"ck": 351,
"very": 352,
"Ġyou": 353,
"st": 354,
"ve": 355,
"Ġhapp": 356,
"un": 357,
"Ġon": 358,
"riend": 359,
"Ġfriend": 360,
"all": 361,
"ily": 362,
"ext": 363,
"ĠL": 364,
"Ġthey": 365,
"oft": 366,
"Ġwe": 367,
"Ġhad": 368,
"Ġnot": 369,
"Ġli": 370,
"Ġup": 371,
"her": 372,
"Ġwant": 373,
"Ġof": 374,
"itt": 375,
"<|": 376,
"|>": 377,
"endoft": 378,
"endoftext": 379,
"ad": 380,
"se": 381,
"ĠB": 382,
"Ġdo": 383,
"Ġe": 384,
"Ġhappy": 385,
"Ġvery": 386,
"ent": 387,
"ĠM": 388,
"'s": 389,
"es": 390,
"Ġsaw": 391,
"One": 392,
"Ġthat": 393,
"ould": 394,
"Ġmom": 395,
"Ġfor": 396,
"ittle": 397,
"Ġsh": 398,
"Ġlittle": 399,
"Ġshe": 400,
".\"": 401,
"ime": 402,
"Ġnam": 403,
"ch": 404,
"Ġtime": 405,
"Ġk": 406,
"ound": 407,
"Ġso": 408,
"Ġthere": 409,
"Ġnamed": 410,
"Ġbo": 411,
"Ġsm": 412,
"ĠLily": 413,
"Ġwere": 414,
"Ġwanted": 415,
"Ġne": 416,
"!\"": 417,
"Ġbut": 418,
"Ġfriends": 419,
"out": 420,
"ved": 421,
"ĠTom": 422,
"The": 423,
"ird": 424,
"ht": 425,
"el": 426,
"Ġbird": 427,
"Ġan": 428,
"al": 429,
"ake": 430,
"Ġtoo": 431,
"ĠIt": 432,
"ug": 433,
"ome": 434,
"Ġwent": 435,
"ide": 436,
"Ġhel": 437,
"Once": 438,
"Ġwh": 439,
"Ġall": 440,
"Ġis": 441,
"Ġhelp": 442,
"ue": 443,
"Ġlo": 444,
"Ġloo": 445,
"ter": 446,
"Ġupon": 447,
"ĠA": 448,
"ry": 449,
"ore": 450,
"Ġfun": 451,
"ind": 452,
"Ġtoy": 453,
"get": 454,
"ame": 455,
"ill": 456,
"Ġas": 457,
"Ġat": 458,
"ra": 459,
"Ġdid": 460,
"Ġj": 461,
"gether": 462,
"Ġre": 463,
"ur": 464,
"Ġo": 465,
"Ġtogether": 466,
"Ġse": 467,
"Ġcat": 468,
"ack": 469,
"Ġtre": 470,
"ly": 471,
"ood": 472,
"ic": 473,
"Ġdog": 474,
"ted": 475,
"Ġcould": 476,
"Ġcan": 477,
"Ġtheir": 478,
"ard": 479,
"ark": 480,
"?\"": 481,
"ec": 482,
"Ġplayed": 483,
"Ġball": 484,
"Ġgir": 485,
"Ġro": 486,
"Ġhim": 487,
"Ġgirl": 488,
"way": 489,
"hed": 490,
"Ġgo": 491,
"my": 492,
"Ġle": 493,
"Ġare": 494,
"'t": 495,
"Ġout": 496,
"Ġfr": 497,
"ain": 498,
"Ġkn": 499,
"hen": 500,
"Ġthem": 501,
"um": 502,
"ax": 503,
"Ġsad": 504,
"Ġboy": 505,
"Ġtree": 506,
"ul": 507,
"other": 508,
"Ġman": 509,
"Ġhave": 510,
"Ġloved": 511,
"Ġcl": 512,
"Ġfound": 513,
"Ġlooked": 514,
"oug": 515,
"ĠSue": 516,
"Ġsp": 517,
"Ġstar": 518,
"one": 519,
"Ġsc": 520,
"hing": 521,
"Ġback": 522,
"ĠMax": 523,
"own": 524,
"are": 525,
"Ġlike": 526,
"Ġbec": 527,
"side": 528,
"ful": 529,
"Ġme": 530,
"Ġpark": 531,
"ong": 532,
"Ġcar": 533,
"ight": 534,
"op": 535,
"ĠOne": 536,
"elt": 537,
"Ġliked": 538,
"Ġwould": 539,
"Ġla": 540,
"Ġmake": 541,
"Ġfa": 542,
"Ġfelt": 543,
"round": 544,
"You": 545,
"ell": 546,
"ĠW": 547,
"Ġsee": 548,
"ĠBut": 549,
"omet": 550,
"Ġasked": 551,
"Ġnew": 552,
"ag": 553,
"ĠSam": 554,
"ouse": 555,
"Ġcame": 556,
"ared": 557,
"Ġstarted": 558,
"Ġno": 559,
"ice": 560,
"ĠBen": 561,
"ought": 562,
"Ġother": 563,
"Ġal": 564,
"iled": 565,
"Ġag": 566,
"Ġsmall": 567,
"Ġgood": 568,
"Ġsomet": 569,
"Ġbr": 570,
"ss": 571,
"ried": 572,
"ade": 573,
"Ġsmiled": 574,
"ings": 575,
"Ġsay": 576,
"ob": 577,
"pot": 578,
"Ġfind": 579,
"Ġwor": 580,
"ia": 581,
"ty": 582,
"Ġaway": 583,
"Ġput": 584,
"Ġmade": 585,
"Ġthought": 586,
"ened": 587,
"Ġfrom": 588,
"Ġwhat": 589,
"Ġhome": 590,
"Ġsomething": 591,
"Ġplaying": 592,
"Ġex": 593,
"Ġco": 594,
"Ġevery": 595,
"ook": 596,
"Ġwal": 597,
"uc": 598,
"Ġmu": 599,
"ach": 600,
"ĠSpot": 601,
"arn": 602,
"ĠF": 603,
"Ġran": 604,
"ile": 605,
"ie": 606,
"ave": 607,
"Ġagain": 608,
"Ġlaug": 609,
"Ġhouse": 610,
"Ġsome": 611,
"ĠJ": 612,
"Ġdown": 613,
"Ġfl": 614,
"dd": 615,
"Ġtook": 616,
"Ġscared": 617,
"Ġtoys": 618,
"king": 619,
"Ġlearn": 620,
"ny": 621,
"Ġpr": 622,
"Ġbox": 623,
"ure": 624,
"Ġwill": 625,
"if": 626,
"ret": 627,
"ĠYou": 628,
"ab": 629,
"ick": 630,
"ep": 631,
"Ġthings": 632,
"Ġmy": 633,
"Ġyour": 634,
"Ġaround": 635,
"Ġbl": 636,
"Ġlived": 637,
"oud": 638,
"ish": 639,
"uck": 640,
"Ġwhen": 641,
"Ġsun": 642,
",\"": 643,
"Ġfe": 644,
"Ġthen": 645,
"as": 646,
"Ġsw": 647,
"Ġch": 648,
"us": 649,
"pped": 650,
"ĠMia": 651,
"Ġab": 652,
"ank": 653,
"Tim": 654,
"ucy": 655,
"ump": 656,
"Ġget": 657,
"Ġlot": 658,
"Th": 659,
"ist": 660,
"oth": 661,
"Ġtried": 662,
"ap": 663,
"Ġknow": 664,
"Ġgot": 665,
"Ġsays": 666,
"Ġkne": 667,
"Ġwho": 668,
"Ġmany": 669,
"ited": 670,
"ust": 671,
"nder": 672,
"Ġint": 673,
"Ġabout": 674,
"Lily": 675,
"Ġpret": 676,
"Ġred": 677,
"Ġany": 678,
"Ġdec": 679,
"ive": 680,
"ĠD": 681,
"Ġknew": 682,
"ace": 683,
"Ġmore": 684,
"ous": 685,
"ise": 686,
"Ġpic": 687,
"au": 688,
"Ġcare": 689,
"Ġv": 690,
"Ġlearned": 691,
"ally": 692,
"ĠLucy": 693,
"Ġbecame": 694,
"qu": 695,
"Ġwater": 696,
"Ġhug": 697,
"fter": 698,
"Ġbest": 699,
"Ġpo": 700,
"ause": 701,
"Ġgre": 702,
"Ġop": 703,
"ways": 704,
"urp": 705,
"Ġlaughed": 706,
"Ġoutside": 707,
"Ġalways": 708,
"Ġexc": 709,
"Ġun": 710,
"Ġlook": 711,
"ĠBob": 712,
"Ġbecause": 713,
"Ġshow": 714,
"Ġdecid": 715,
"Ġroom": 716,
"ant": 717,
"ĠSo": 718,
"Ġeat": 719,
"fe": 720,
"Ġho": 721,
"Ġdecided": 722,
"Ġinto": 723,
"Ġjump": 724,
"ite": 725,
"ĠAnd": 726,
"Ġboth": 727,
"Ġpe": 728,
"ers": 729,
"ĠMom": 730,
"Ġdad": 731,
"They": 732,
"Ġke": 733,
"udd": 734,
"Ġone": 735,
"Ġfast": 736,
"Ġnice": 737,
"nn": 738,
"Ġrun": 739,
"Ġthis": 740,
"Tom": 741,
"Yes": 742,
"Ġlong": 743,
"Ġfeel": 744,
"Ġexcited": 745,
"ĠE": 746,
"Ġtold": 747,
"Ġsk": 748,
"Ġam": 749,
"urpr": 750,
"Ġinside": 751,
"Ġtr": 752,
"ull": 753,
"our": 754,
"Ġsurpr": 755,
"Ġpretty": 756,
"Ġmo": 757,
"iny": 758,
"ink": 759,
"Ġsor": 760,
"Wh": 761,
"Ġtake": 762,
"og": 763,
"Ġgave": 764,
"lew": 765,
"Ġrock": 766,
"Ġsl": 767,
"Ġeach": 768,
"Ġmuch": 769,
"Ġstr": 770,
"imal": 771,
"Ġhow": 772,
"Ġgra": 773,
"Ġanimal": 774,
"nna": 775,
"ara": 776,
"Ġneed": 777,
"ged": 778,
"Ġtow": 779,
"etter": 780,
"Ġthan": 781,
"But": 782,
"ven": 783,
"Ġor": 784,
"Ġunder": 785,
"ĠC": 786,
"ess": 787,
"Ġsorry": 788,
"Ġold": 789,
"ised": 790,
"ge": 791,
"ro": 792,
"urt": 793,
"Ġfish": 794,
"Ġcle": 795,
"Ġwalked": 796,
"Ġbear": 797,
"and": 798,
"Ġclo": 799,
"ase": 800,
"ast": 801,
"Ġhand": 802,
"urn": 803,
"Ġkind": 804,
"ĠHis": 805,
"ĠWe": 806,
"Ġhappened": 807,
"Ġflow": 808,
"Ġfood": 809,
"here": 810,
"Ġlist": 811,
"Ġhig": 812,
"Ġanimals": 813,
"Ġjust": 814,
"Ġte": 815,
"Ġdidn": 816,
"Ġnear": 817,
"Ġide": 818,
"Ġsky": 819,
"Ġwat": 820,
"rom": 821,
"Ġtry": 822,
"ine": 823,
"Ġsn": 824,
"Ġfi": 825,
"ched": 826,
"ĠAmy": 827,
"ving": 828,
"Ġbug": 829,
"Ġidea": 830,
"Ġbetter": 831,
"Ġus": 832,
"pl": 833,
"gry": 834,
"Ġits": 835,
"pec": 836,
"Ġheard": 837,
"Ġtw": 838,
"Ġlet": 839,
"ff": 840,
"able": 841,
"ate": 842,
"Ġshare": 843,
"Ġcareful": 844,
"Thank": 845,
"Ġen": 846,
"more": 847,
"Ġanymore": 848,
"Ġfly": 849,
"Ġflew": 850,
"Ġstor": 851,
"Ġif": 852,
"Mom": 853,
"ial": 854,
"Ġlots": 855,
"ĠTh": 856,
"Ġcom": 857,
"Ġspec": 858,
"Ġdan": 859,
"Ġspecial": 860,
"ion": 861,
"Ġby": 862,
"Ġnever": 863,
"ream": 864,
"lf": 865,
"Ġwind": 866,
"Ġbu": 867,
"Ġclean": 868,
"Ġfo": 869,
"Ġtal": 870,
"Ġdon": 871,
"Ġgr": 872,
"ort": 873,
"rm": 874,
"Ġend": 875,
"ople": 876,
"Ġlove": 877,
"ĠThen": 878,
"Ġeven": 879,
"ber": 880,
"Ġmag": 881,
"Ġshiny": 882,
"Ġhard": 883,
"Ġcake": 884,
"Ġfore": 885,
"Ġover": 886,
"ak": 887,
"Ġcol": 888,
"Ġbook": 889,
"udden": 890,
"Ġturn": 891,
"Ġsafe": 892,
"Ġfam": 893,
"Ġafter": 894,
"Ġbad": 895,
"pected": 896,
"Ġpeople": 897,
"Ġsurprised": 898,
"Ġhigh": 899,
"Ġproud": 900,
"ady": 901,
"ĠAnna": 902,
"Ġhurt": 903,
"imb": 904,
"ĠEvery": 905,
"Let": 906,
"expected": 907,
"Ġunexpected": 908,
"uddenly": 909,
"Ġpicked": 910,
"Ġground": 911,
"Ġcu": 912,
"Ġclimb": 913,
"Ġdoor": 914,
"Ġcome": 915,
"arden": 916,
"Ġgarden": 917,
"Ġopened": 918,
"ble": 919,
"Ġloud": 920,
"As": 921,
"Ġgl": 922,
"Ġche": 923,
"Ġim": 924,
"ild": 925,
"'m": 926,
"Ġgive": 927,
"ail": 928,
"Ġcolor": 929,
"Ġblue": 930,
"Ġway": 931,
"Ġever": 932,
"Ġthanked": 933,
"ĠFrom": 934,
"Ġstill": 935,
"Ġfar": 936,
"Ġhugged": 937,
"ĠHer": 938,
"ip": 939,
"ĠWhen": 940,
"Ġcall": 941,
"No": 942,
"Ġmagic": 943,
"ĠSara": 944,
"ummy": 945,
"ĠK": 946,
"age": 947,
"Ġoff": 948,
"iz": 949,
"Ġjumped": 950,
"ough": 951,
"Ġpar": 952,
"Ġfamily": 953,
"Ġshould": 954,
"Ġkid": 955,
"ool": 956,
"uff": 957,
"Ġsmile": 958,
"hes": 959,
"Ġplace": 960,
"ĠIn": 961,
"kay": 962,
"Ġwalk": 963,
"Ġgreat": 964,
"Ġnow": 965,
"Ġstrong": 966,
"ct": 967,
"em": 968,
"Ġstay": 969,
"itty": 970,
"ture": 971,
"Ġqu": 972,
"Ġforest": 973,
"Ġunt": 974,
"Ġsto": 975,
"aut": 976,
"ane": 977,
"Ġbro": 978,
"Ġbra": 979,
"oon": 980,
"Ġsqu": 981,
"ĠP": 982,
"Ġboat": 983,
"Ġstick": 984,
"Ġuntil": 985,
"Ġfrog": 986,
"Ġbeaut": 987,
"dy": 988,
"Ġnext": 989,
"lease": 990,
"Ġhappily": 991,
"ning": 992,
"Ġlisten": 993,
"Ġkids": 994,
"Ġtra": 995,
"Ġhelped": 996,
"aking": 997,
"Ġapp": 998,
"iful": 999,
"Ġbeautiful": 1000,
"Ġshowed": 1001,
"th": 1002,
"ies": 1003,
"Ġdra": 1004,
"Ġstory": 1005,
"unny": 1006,
"Ġtown": 1007,
"by": 1008,
"Ġimp": 1009,
"rel": 1010,
"Ġwhile": 1011,
"Ġclos": 1012,
"be": 1013,
"oy": 1014,
"Ġrain": 1015,
"Ġpicture": 1016,
"ress": 1017,
"pt": 1018,
"Ġbeing": 1019,
"Ġeveryone": 1020,
"Ġrem": 1021,
"Ġhat": 1022,
"Ġmor": 1023
},
"merges": [
"Ġ t",
"h e",
"Ġ a",
"Ġ s",
"n d",
"Ġ w",
"Ġt he",
"e d",
"Ġ b",
"Ġt o",
"Ġa nd",
"Ġ h",
"Ġ f",
"Ġ T",
"i n",
"Ġw a",
"r e",
"i t",
"o u",
"Ġ l",
"Ġ d",
"Ġ c",
"Ġ p",
"a y",
"Ġ m",
"e r",
"Ġwa s",
"ĠT he",
"o m",
"Ġ he",
"i s",
"Ġ n",
"a r",
"i m",
"o n",
"Ġs a",
"i d",
"l l",
"Ġh a",
"Ġ g",
"a t",
"Ġ S",
"in g",
"o t",
"e n",
"a n",
"l e",
"o r",
"e nd",
"i r",
"o f",
"a m",
"e t",
"Ġ H",
"Ġ it",
"Ġt h",
"i g",
"ĠThe y",
"Ġ in",
"i l",
"Ġp l",
"Ġ \"",
"ĠH e",
"o w",
"r i",
"v er",
"u t",
"Ġ u",
"Ġb e",
"Ġpl ay",
"Ġsa id",
"it h",
"Ġd ay",
"Ġw ith",
"p p",
"O n",
"Ġ y",
"o o",
"k ed",
"Ġ r",
"e x",
"Ġhe r",
"c e",
"Ġ I",
"ĠT im",
"ĠS he",
"l d",
"Ġh is",
"Ġs t",
"k e",
"Ġb ig",
"n t",
"c k",
"ver y",
"Ġy ou",
"s t",
"v e",
"Ġha pp",
"u n",
"Ġ on",
"ri end",
"Ġf riend",
"a ll",
"il y",
"ex t",
"Ġ L",
"Ġthe y",
"of t",
"Ġw e",
"Ġha d",
"Ġn ot",
"Ġl i",
"Ġu p",
"he r",
"Ġwa nt",
"Ġ of",
"it t",
"< |",
"| >",
"end oft",
"endoft ext",
"a d",
"s e",
"Ġ B",
"Ġd o",
"Ġ e",
"Ġhapp y",
"Ġ very",
"en t",
"Ġ M",
"' s",
"e s",
"Ġsa w",
"On e",
"Ġth at",
"ou ld",
"Ġm om",
"Ġf or",
"itt le",
"Ġs h",
"Ġl ittle",
"Ġs he",
". \"",
"im e",
"Ġn am",
"c h",
"Ġt ime",
"Ġ k",
"ou nd",
"Ġs o",
"Ġthe re",
"Ġnam ed",
"Ġb o",
"Ġs m",
"ĠL ily",
"Ġwe re",
"Ġwant ed",
"Ġn e",
"! \"",
"Ġb ut",
"Ġfriend s",
"ou t",
"v ed",
"ĠT om",
"T he",
"ir d",
"h t",
"e l",
"Ġb ird",
"Ġa n",
"a l",
"a ke",
"Ġto o",
"ĠI t",
"u g",
"om e",
"Ġw ent",
"id e",
"Ġhe l",
"On ce",
"Ġw h",
"Ġa ll",
"Ġ is",
"Ġhel p",
"u e",
"Ġl o",
"Ġl oo",
"t er",
"Ġup on",
"Ġ A",
"r y",
"o re",
"Ġf un",
"i nd",
"Ġto y",
"g et",
"am e",
"i ll",
"Ġa s",
"Ġa t",
"r a",
"Ġd id",
"Ġ j",
"get her",
"Ġ re",
"u r",
"Ġ o",
"Ġto gether",
"Ġs e",
"Ġc at",
"a ck",
"Ġt re",
"l y",
"oo d",
"i c",
"Ġdo g",
"t ed",
"Ġc ould",
"Ġc an",
"Ġthe ir",
"ar d",
"ar k",
"? \"",
"e c",
"Ġplay ed",
"Ġb all",
"Ġg ir",
"Ġr o",
"Ġh im",
"Ġgir l",
"w ay",
"he d",
"Ġg o",
"m y",
"Ġl e",
"Ġa re",
"' t",
"Ġ out",
"Ġf r",
"a in",
"Ġk n",
"he n",
"Ġthe m",
"u m",
"a x",
"Ġsa d",
"Ġbo y",
"Ġtre e",
"u l",
"ot her",
"Ġm an",
"Ġha ve",
"Ġlo ved",
"Ġc l",
"Ġf ound",
"Ġloo ked",
"ou g",
"ĠS ue",
"Ġs p",
"Ġst ar",
"on e",
"Ġs c",
"h ing",
"Ġb ack",
"ĠM ax",
"ow n",
"a re",
"Ġli ke",
"Ġbe c",
"s ide",
"f ul",
"Ġm e",
"Ġp ark",
"on g",
"Ġc ar",
"ig ht",
"o p",
"Ġ One",
"el t",
"Ġli ked",
"Ġw ould",
"Ġl a",
"Ġm ake",
"Ġf a",
"Ġf elt",
"r ound",
"Y ou",
"e ll",
"Ġ W",
"Ġse e",
"ĠB ut",
"om et",
"Ġas ked",
"Ġne w",
"a g",
"ĠS am",
"ou se",
"Ġc ame",
"ar ed",
"Ġstar ted",
"Ġn o",
"i ce",
"ĠB en",
"oug ht",
"Ġ other",
"Ġa l",
"il ed",
"Ġa g",
"Ġsm all",
"Ġg ood",
"Ġs omet",
"Ġb r",
"s s",
"ri ed",
"ad e",
"Ġsm iled",
"ing s",
"Ġs ay",
"o b",
"p ot",
"Ġf ind",
"Ġw or",
"i a",
"t y",
"Ġa way",
"Ġp ut",
"Ġm ade",
"Ġth ought",
"en ed",
"Ġfr om",
"Ġwh at",
"Ġh ome",
"Ġsomet hing",
"Ġplay ing",
"Ġ ex",
"Ġc o",
"Ġe very",
"oo k",
"Ġwa l",
"u c",
"Ġm u",
"a ch",
"ĠS pot",
"ar n",
"Ġ F",
"Ġr an",
"i le",
"i e",
"a ve",
"Ġag ain",
"Ġla ug",
"Ġh ouse",
"Ġs ome",
"Ġ J",
"Ġd own",
"Ġf l",
"d d",
"Ġtoo k",
"Ġsc ared",
"Ġtoy s",
"k ing",
"Ġle arn",
"n y",
"Ġp r",
"Ġbo x",
"u re",
"Ġw ill",
"i f",
"re t",
"Ġ You",
"a b",
"i ck",
"e p",
"Ġth ings",
"Ġm y",
"Ġyou r",
"Ġa round",
"Ġb l",
"Ġli ved",
"ou d",
"is h",
"u ck",
"Ġw hen",
"Ġs un",
", \"",
"Ġf e",
"Ġthe n",
"a s",
"Ġs w",
"Ġc h",
"u s",
"pp ed",
"ĠM ia",
"Ġa b",
"an k",
"T im",
"uc y",
"um p",
"Ġg et",
"Ġl ot",
"T h",
"is t",
"ot h",
"Ġt ried",
"a p",
"Ġkn ow",
"Ġg ot",
"Ġsay s",
"Ġkn e",
"Ġwh o",
"Ġman y",
"it ed",
"u st",
"nd er",
"Ġin t",
"Ġab out",
"L ily",
"Ġp ret",
"Ġr ed",
"Ġan y",
"Ġd ec",
"i ve",
"Ġ D",
"Ġkne w",
"a ce",
"Ġm ore",
"ou s",
"is e",
"Ġp ic",
"a u",
"Ġc are",
"Ġ v",
"Ġlearn ed",
"all y",
"ĠL ucy",
"Ġbec ame",
"q u",
"Ġwa ter",
"Ġh ug",
"f ter",
"Ġbe st",
"Ġp o",
"au se",
"Ġg re",
"Ġo p",
"way s",
"ur p",
"Ġlaug hed",
"Ġout side",
"Ġal ways",
"Ġex c",
"Ġu n",
"Ġloo k",
"ĠB ob",
"Ġbec ause",
"Ġsh ow",
"Ġdec id",
"Ġro om",
"an t",
"ĠS o",
"Ġe at",
"f e",
"Ġh o",
"Ġdecid ed",
"Ġint o",
"Ġj ump",
"it e",
"ĠA nd",
"Ġb oth",
"Ġp e",
"er s",
"ĠM om",
"Ġd ad",
"The y",
"Ġ ke",
"u dd",
"Ġon e",
"Ġfa st",
"Ġn ice",
"n n",
"Ġr un",
"Ġth is",
"T om",
"Y es",
"Ġl ong",
"Ġfe el",
"Ġexc ited",
"Ġ E",
"Ġto ld",
"Ġs k",
"Ġa m",
"urp r",
"Ġin side",
"Ġt r",
"u ll",
"ou r",
"Ġs urpr",
"Ġpret ty",
"Ġm o",
"in y",
"in k",
"Ġs or",
"W h",
"Ġt ake",
"o g",
"Ġg ave",
"le w",
"Ġro ck",
"Ġs l",
"Ġe ach",
"Ġmu ch",
"Ġst r",
"im al",
"Ġh ow",
"Ġg ra",
"Ġan imal",
"nn a",
"ar a",
"Ġne ed",
"g ed",
"Ġto w",
"et ter",
"Ġth an",
"B ut",
"v en",
"Ġ or",
"Ġu nder",
"Ġ C",
"es s",
"Ġsor ry",
"Ġo ld",
"is ed",
"g e",
"r o",
"ur t",
"Ġf ish",
"Ġc le",
"Ġwal ked",
"Ġbe ar",
"a nd",
"Ġcl o",
"a se",
"a st",
"Ġha nd",
"ur n",
"Ġk ind",
"ĠH is",
"ĠW e",
"Ġhapp ened",
"Ġfl ow",
"Ġf ood",
"he re",
"Ġl ist",
"Ġh ig",
"Ġanimal s",
"Ġj ust",
"Ġt e",
"Ġdid n",
"Ġne ar",
"Ġ ide",
"Ġsk y",
"Ġwa t",
"r om",
"Ġt ry",
"in e",
"Ġs n",
"Ġf i",
"c hed",
"ĠA my",
"v ing",
"Ġb ug",
"Ġide a",
"Ġb etter",
"Ġu s",
"p l",
"g ry",
"Ġit s",
"p ec",
"Ġhe ard",
"Ġt w",
"Ġl et",
"f f",
"ab le",
"at e",
"Ġsh are",
"Ġcare ful",
"Th ank",
"Ġ en",
"m ore",
"Ġany more",
"Ġf ly",
"Ġf lew",
"Ġst or",
"Ġ if",
"M om",
"i al",
"Ġlot s",
"ĠT h",
"Ġc om",
"Ġsp ec",
"Ġd an",
"Ġspec ial",
"i on",
"Ġb y",
"Ġne ver",
"re am",
"l f",
"Ġw ind",
"Ġb u",
"Ġcle an",
"Ġf o",
"Ġt al",
"Ġd on",
"Ġg r",
"or t",
"r m",
"Ġ end",
"op le",
"Ġlo ve",
"ĠThe n",
"Ġe ven",
"b er",
"Ġm ag",
"Ġsh iny",
"Ġh ard",
"Ġc ake",
"Ġf ore",
"Ġo ver",
"a k",
"Ġco l",
"Ġb ook",
"udd en",
"Ġt urn",
"Ġsa fe",
"Ġf am",
"Ġa fter",
"Ġb ad",
"pec ted",
"Ġpe ople",
"Ġsurpr ised",
"Ġhig h",
"Ġpr oud",
"ad y",
"ĠA nna",
"Ġh urt",
"im b",
"ĠE very",
"L et",
"ex pected",
"Ġun expected",
"udden ly",
"Ġpic ked",
"Ġg round",
"Ġc u",
"Ġcl imb",
"Ġdo or",
"Ġc ome",
"ard en",
"Ġg arden",
"Ġop ened",
"b le",
"Ġl oud",
"A s",
"Ġg l",
"Ġc he",
"Ġ im",
"il d",
"' m",
"Ġg ive",
"a il",
"Ġcol or",
"Ġbl ue",
"Ġwa y",
"Ġe ver",
"Ġthan ked",
"ĠF rom",
"Ġst ill",
"Ġf ar",
"Ġhug ged",
"ĠH er",
"i p",
"ĠW hen",
"Ġc all",
"N o",
"Ġmag ic",
"ĠS ara",
"um my",
"Ġ K",
"ag e",
"Ġof f",
"i z",
"Ġjump ed",
"oug h",
"Ġp ar",
"Ġfam ily",
"Ġsh ould",
"Ġk id",
"oo l",
"u ff",
"Ġsm ile",
"he s",
"Ġpl ace",
"ĠI n",
"k ay",
"Ġwal k",
"Ġgre at",
"Ġn ow",
"Ġstr ong",
"c t",
"e m",
"Ġst ay",
"itt y",
"t ure",
"Ġ qu",
"Ġfore st",
"Ġu nt",
"Ġst o",
"a ut",
"an e",
"Ġbr o",
"Ġb ra",
"o on",
"Ġs qu",
"Ġ P",
"Ġbo at",
"Ġst ick",
"Ġunt il",
"Ġfr og",
"Ġbe aut",
"d y",
"Ġn ext",
"le ase",
"Ġhapp ily",
"n ing",
"Ġlist en",
"Ġkid s",
"Ġt ra",
"Ġhelp ed",
"a king",
"Ġa pp",
"i ful",
"Ġbeaut iful",
"Ġshow ed",
"t h",
"i es",
"Ġd ra",
"Ġstor y",
"un ny",
"Ġtow n",
"b y",
"Ġim p",
"re l",
"Ġwh ile",
"Ġclo s",
"b e",
"o y",
"Ġr ain",
"Ġpic ture",
"re ss",
"p t",
"Ġbe ing",
"Ġevery one",
"Ġre m",
"Ġha t",
"Ġm or"
]
}
}