Upload tokenizer files (vocab, config, README)

special_tokens_map.json

@@ -1,3 +1,6 @@
 {
-  "unk_token": "<unk>"
+  "pad_token": "<pad>",
+  "unk_token": "<unk>",
+  "bos_token": "<bos>",
+  "eos_token": "<eos>"
 }

tokenizer.json

@@ -0,0 +1,1061 @@
+{
+  "version": "1.0",
+  "truncation": null,
+  "padding": null,
+  "added_tokens": [
+    {
+      "id": 0,
+      "content": "<pad>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false
+    },
+    {
+      "id": 1,
+      "content": "<unk>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false
+    },
+    {
+      "id": 2,
+      "content": "<bos>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false
+    },
+    {
+      "id": 3,
+      "content": "<eos>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false
+    }
+  ],
+  "normalizer": {
+    "type": "Sequence",
+    "normalizers": [
+      {
+        "type": "NFC"
+      }
+    ]
+  },
+  "pre_tokenizer": {
+    "type": "Whitespace"
+  },
+  "post_processor": null,
+  "decoder": {
+    "type": "WordPiece",
+    "unk_token": "<unk>"
+  },
+  "model": {
+    "type": "WordLevel",
+    "vocab": {
+      "<pad>": 0,
+      "<unk>": 1,
+      "<bos>": 2,
+      "<eos>": 3,
+      "the": 4,
+      ",": 5,
+      ".": 6,
+      "of": 7,
+      "and": 8,
+      "@": 9,
+      "in": 10,
+      "to": 11,
+      "a": 12,
+      "=": 13,
+      "was": 14,
+      "\"": 15,
+      "-": 16,
+      "The": 17,
+      "'": 18,
+      "for": 19,
+      "with": 20,
+      "that": 21,
+      "as": 22,
+      "s": 23,
+      "were": 24,
+      "by": 25,
+      ")": 26,
+      "(": 27,
+      "on": 28,
+      "is": 29,
+      "from": 30,
+      "at": 31,
+      "are": 32,
+      "gods": 33,
+      ";": 34,
+      "an": 35,
+      "which": 36,
+      "be": 37,
+      "their": 38,
+      "his": 39,
+      "had": 40,
+      "her": 41,
+      "In": 42,
+      "it": 43,
+      "or": 44,
+      "\u2013": 45,
+      "not": 46,
+      "deities": 47,
+      "one": 48,
+      "but": 49,
+      "also": 50,
+      "he": 51,
+      "who": 52,
+      "other": 53,
+      "GA": 54,
+      "has": 55,
+      "first": 56,
+      "game": 57,
+      "aircraft": 58,
+      "its": 59,
+      "two": 60,
+      "have": 61,
+      "this": 62,
+      ":": 63,
+      "she": 64,
+      "god": 65,
+      "all": 66,
+      "more": 67,
+      "they": 68,
+      "Egyptian": 69,
+      "time": 70,
+      "1": 71,
+      "She": 72,
+      "into": 73,
+      "team": 74,
+      "after": 75,
+      "He": 76,
+      "could": 77,
+      "year": 78,
+      "than": 79,
+      "been": 80,
+      "these": 81,
+      "season": 82,
+      "A": 83,
+      "It": 84,
+      "Valkyria": 85,
+      "during": 86,
+      "only": 87,
+      "2": 88,
+      "some": 89,
+      "being": 90,
+      "Little": 91,
+      "over": 92,
+      "when": 93,
+      "many": 94,
+      "such": 95,
+      "would": 96,
+      "most": 97,
+      "divine": 98,
+      "them": 99,
+      "Rock": 100,
+      "four": 101,
+      "Cullen": 102,
+      "up": 103,
+      "made": 104,
+      "Barker": 105,
+      "album": 106,
+      "4": 107,
+      "between": 108,
+      "Blue": 109,
+      "Jackets": 110,
+      "UK": 111,
+      "Fernandez": 112,
+      "about": 113,
+      "before": 114,
+      "work": 115,
+      "while": 116,
+      "I": 117,
+      "gold": 118,
+      "Chronicles": 119,
+      "can": 120,
+      "out": 121,
+      "world": 122,
+      "Columbus": 123,
+      "ship": 124,
+      "games": 125,
+      "used": 126,
+      "three": 127,
+      "000": 128,
+      "operations": 129,
+      "both": 130,
+      "like": 131,
+      "NHL": 132,
+      "through": 133,
+      "under": 134,
+      "\u2014": 135,
+      "no": 136,
+      "part": 137,
+      "This": 138,
+      "played": 139,
+      "3": 140,
+      "same": 141,
+      "7": 142,
+      "new": 143,
+      "form": 144,
+      "5": 145,
+      "dollar": 146,
+      "where": 147,
+      "There": 148,
+      "so": 149,
+      "him": 150,
+      "there": 151,
+      "war": 152,
+      "number": 153,
+      "said": 154,
+      "well": 155,
+      "Blackie": 156,
+      "human": 157,
+      "Kingdom": 158,
+      "Slayer": 159,
+      "each": 160,
+      "They": 161,
+      "became": 162,
+      "built": 163,
+      "called": 164,
+      "deity": 165,
+      "against": 166,
+      "although": 167,
+      "later": 168,
+      "South": 169,
+      "6": 170,
+      "early": 171,
+      "Arkansas": 172,
+      "including": 173,
+      "often": 174,
+      "N": 175,
+      "air": 176,
+      "British": 177,
+      "Egyptians": 178,
+      "points": 179,
+      "John": 180,
+      "years": 181,
+      "any": 182,
+      "long": 183,
+      "/": 184,
+      "small": 185,
+      "per": 186,
+      "second": 187,
+      "flying": 188,
+      "After": 189,
+      "around": 190,
+      "single": 191,
+      "class": 192,
+      "place": 193,
+      "following": 194,
+      "several": 195,
+      "United": 196,
+      "St": 197,
+      "New": 198,
+      "Atlanta": 199,
+      "down": 200,
+      "end": 201,
+      "Tower": 202,
+      "tower": 203,
+      "may": 204,
+      "commercial": 205,
+      "These": 206,
+      "important": 207,
+      "Egypt": 208,
+      "role": 209,
+      "began": 210,
+      "development": 211,
+      "along": 212,
+      "character": 213,
+      "within": 214,
+      "then": 215,
+      "did": 216,
+      "building": 217,
+      "state": 218,
+      "Navy": 219,
+      "record": 220,
+      "ships": 221,
+      "pilots": 222,
+      "aerodromes": 223,
+      "Zr\u00ednyi": 224,
+      "military": 225,
+      "received": 226,
+      "November": 227,
+      "As": 228,
+      "order": 229,
+      "day": 230,
+      "Flower": 231,
+      "Arsenal": 232,
+      "name": 233,
+      "women": 234,
+      "described": 235,
+      "given": 236,
+      "national": 237,
+      "power": 238,
+      "Austro": 239,
+      "Hungarian": 240,
+      "Heaven": 241,
+      "aviation": 242,
+      "2011": 243,
+      "series": 244,
+      "May": 245,
+      "original": 246,
+      "main": 247,
+      "found": 248,
+      "last": 249,
+      "just": 250,
+      "took": 251,
+      "live": 252,
+      "On": 253,
+      "life": 254,
+      "12": 255,
+      "species": 256,
+      "believed": 257,
+      "transport": 258,
+      "CAA": 259,
+      "player": 260,
+      "off": 261,
+      "m": 262,
+      "another": 263,
+      "history": 264,
+      "Fairies": 265,
+      "t": 266,
+      "family": 267,
+      "career": 268,
+      "Erzherzog": 269,
+      "temples": 270,
+      "Amun": 271,
+      "different": 272,
+      "known": 273,
+      "due": 274,
+      "song": 275,
+      "February": 276,
+      "arsenal": 277,
+      "activities": 278,
+      "back": 279,
+      "religious": 280,
+      "mm": 281,
+      "religion": 282,
+      "War": 283,
+      "While": 284,
+      "previous": 285,
+      "based": 286,
+      "present": 287,
+      "stated": 288,
+      "light": 289,
+      "much": 290,
+      "World": 291,
+      "10": 292,
+      "way": 293,
+      "local": 294,
+      "But": 295,
+      "15": 296,
+      "even": 297,
+      "Gambia": 298,
+      "trade": 299,
+      "inch": 300,
+      "Some": 301,
+      "Ra": 302,
+      "third": 303,
+      "take": 304,
+      "those": 305,
+      "system": 306,
+      "make": 307,
+      "until": 308,
+      "events": 309,
+      "Building": 310,
+      "came": 311,
+      "8": 312,
+      "use": 313,
+      "guns": 314,
+      "Union": 315,
+      "training": 316,
+      "contract": 317,
+      "track": 318,
+      "humans": 319,
+      "carbonaria": 320,
+      "III": 321,
+      "released": 322,
+      "During": 323,
+      "names": 324,
+      "do": 325,
+      "considered": 326,
+      "designed": 327,
+      "particular": 328,
+      "include": 329,
+      "named": 330,
+      "James": 331,
+      "States": 332,
+      "troops": 333,
+      "gun": 334,
+      "19": 335,
+      "sister": 336,
+      "9": 337,
+      "start": 338,
+      "represented": 339,
+      "Italian": 340,
+      "Ferdinand": 341,
+      "Horus": 342,
+      "Aviation": 343,
+      "II": 344,
+      "theme": 345,
+      "franchise": 346,
+      "13": 347,
+      "own": 348,
+      "continued": 349,
+      "forms": 350,
+      "others": 351,
+      "since": 352,
+      "$": 353,
+      "0": 354,
+      "American": 355,
+      "people": 356,
+      "[": 357,
+      "]": 358,
+      "All": 359,
+      "km": 360,
+      "mother": 361,
+      "private": 362,
+      "Association": 363,
+      "nature": 364,
+      "SMS": 365,
+      "Max": 366,
+      "maat": 367,
+      "goddess": 368,
+      "texts": 369,
+      "fungus": 370,
+      "outside": 371,
+      "large": 372,
+      "characters": 373,
+      "members": 374,
+      "carried": 375,
+      "if": 376,
+      "throughout": 377,
+      "five": 378,
+      "home": 379,
+      "times": 380,
+      "General": 381,
+      "support": 382,
+      "fire": 383,
+      "required": 384,
+      "best": 385,
+      "play": 386,
+      "When": 387,
+      "produced": 388,
+      "leading": 389,
+      "2012": 390,
+      "June": 391,
+      "established": 392,
+      "sent": 393,
+      "away": 394,
+      "signed": 395,
+      "Most": 396,
+      "common": 397,
+      "20": 398,
+      "remained": 399,
+      "National": 400,
+      "Her": 401,
+      "\u2019": 402,
+      "late": 403,
+      "ft": 404,
+      "feet": 405,
+      "win": 406,
+      "Although": 407,
+      "appeared": 408,
+      "draft": 409,
+      "However": 410,
+      "88": 411,
+      "rituals": 412,
+      "Isis": 413,
+      "cent": 414,
+      "airspace": 415,
+      "cup": 416,
+      "January": 417,
+      "story": 418,
+      "returned": 419,
+      "release": 420,
+      "control": 421,
+      "specific": 422,
+      "elements": 423,
+      "limited": 424,
+      "At": 425,
+      "position": 426,
+      "next": 427,
+      "written": 428,
+      "involved": 429,
+      "music": 430,
+      "felt": 431,
+      "public": 432,
+      "still": 433,
+      "23": 434,
+      "Club": 435,
+      "men": 436,
+      "held": 437,
+      "18": 438,
+      "River": 439,
+      "south": 440,
+      "now": 441,
+      "band": 442,
+      "Croydon": 443,
+      "death": 444,
+      "24": 445,
+      "conducted": 446,
+      "football": 447,
+      "maskray": 448,
+      "cm": 449,
+      "group": 450,
+      "high": 451,
+      "Roman": 452,
+      "sun": 453,
+      "Carey": 454,
+      "port": 455,
+      "struck": 456,
+      "India": 457,
+      "roles": 458,
+      "film": 459,
+      "CAT": 460,
+      "flight": 461,
+      "creation": 462,
+      "sector": 463,
+      "airports": 464,
+      "pilot": 465,
+      "noise": 466,
+      "coin": 467,
+      "developed": 468,
+      "praised": 469,
+      "players": 470,
+      "With": 471,
+      "city": 472,
+      "major": 473,
+      "action": 474,
+      "recorded": 475,
+      "general": 476,
+      "art": 477,
+      "set": 478,
+      "half": 479,
+      "goals": 480,
+      "For": 481,
+      "giving": 482,
+      "started": 483,
+      "included": 484,
+      "month": 485,
+      "less": 486,
+      "father": 487,
+      "area": 488,
+      "goal": 489,
+      "published": 490,
+      "Christian": 491,
+      "sometimes": 492,
+      "never": 493,
+      "17": 494,
+      "across": 495,
+      "final": 496,
+      "range": 497,
+      "Nash": 498,
+      "loss": 499,
+      "2013": 500,
+      "Got": 501,
+      "inches": 502,
+      "industry": 503,
+      "Lightning": 504,
+      "cult": 505,
+      "images": 506,
+      "temple": 507,
+      "EASA": 508,
+      "aerodrome": 509,
+      "Mint": 510,
+      "Nameless": 511,
+      "black": 512,
+      "2010": 513,
+      "forces": 514,
+      "using": 515,
+      "top": 516,
+      "once": 517,
+      "either": 518,
+      "without": 519,
+      "become": 520,
+      "numbers": 521,
+      "works": 522,
+      "force": 523,
+      "however": 524,
+      "full": 525,
+      "popular": 526,
+      "design": 527,
+      "G": 528,
+      "originally": 529,
+      "issue": 530,
+      "August": 531,
+      "point": 532,
+      "behind": 533,
+      "C": 534,
+      "further": 535,
+      "country": 536,
+      "performed": 537,
+      "11": 538,
+      "North": 539,
+      "larger": 540,
+      "Book": 541,
+      "Society": 542,
+      "children": 543,
+      "planning": 544,
+      "though": 545,
+      "2006": 546,
+      "round": 547,
+      "scoring": 548,
+      "terms": 549,
+      "Penguins": 550,
+      "observatory": 551,
+      "Be": 552,
+      "Way": 553,
+      "Savannah": 554,
+      "civil": 555,
+      "performance": 556,
+      "business": 557,
+      "fleet": 558,
+      "operation": 559,
+      "focus": 560,
+      "kings": 561,
+      "creator": 562,
+      "Osiris": 563,
+      "King": 564,
+      "flights": 565,
+      "airfields": 566,
+      "growth": 567,
+      "battle": 568,
+      "To": 569,
+      "certain": 570,
+      "themselves": 571,
+      "command": 572,
+      "lives": 573,
+      "addition": 574,
+      "despite": 575,
+      "thought": 576,
+      "By": 577,
+      "review": 578,
+      "songs": 579,
+      "Two": 580,
+      "six": 581,
+      "Civil": 582,
+      "arms": 583,
+      "State": 584,
+      "allowed": 585,
+      "personal": 586,
+      "various": 587,
+      "1862": 588,
+      "near": 589,
+      "strong": 590,
+      "shot": 591,
+      "Sanford": 592,
+      "above": 593,
+      "purposes": 594,
+      "moved": 595,
+      "few": 596,
+      "child": 597,
+      "level": 598,
+      "influence": 599,
+      "things": 600,
+      "society": 601,
+      "cover": 602,
+      "international": 603,
+      "hours": 604,
+      "plain": 605,
+      "complex": 606,
+      "size": 607,
+      "Hockey": 608,
+      "deal": 609,
+      "York": 610,
+      "former": 611,
+      "BC": 612,
+      "metres": 613,
+      "Fingal": 614,
+      "speed": 615,
+      "connected": 616,
+      "difficult": 617,
+      "Sri": 618,
+      "Ancona": 619,
+      "goddesses": 620,
+      "worship": 621,
+      "traditional": 622,
+      "Private": 623,
+      "standards": 624,
+      "playing": 625,
+      "video": 626,
+      "gameplay": 627,
+      "making": 628,
+      "opening": 629,
+      "help": 630,
+      "always": 631,
+      "move": 632,
+      "foreign": 633,
+      "great": 634,
+      "combined": 635,
+      "created": 636,
+      "seven": 637,
+      "available": 638,
+      "April": 639,
+      "overall": 640,
+      "500": 641,
+      "particularly": 642,
+      "generally": 643,
+      "provided": 644,
+      "noted": 645,
+      "period": 646,
+      "Museum": 647,
+      "how": 648,
+      "self": 649,
+      "served": 650,
+      "hold": 651,
+      "28": 652,
+      "me": 653,
+      "official": 654,
+      "March": 655,
+      "head": 656,
+      "ordnance": 657,
+      "consisted": 658,
+      "Confederate": 659,
+      "activity": 660,
+      "naval": 661,
+      "surrounding": 662,
+      "significant": 663,
+      "finally": 664,
+      "16": 665,
+      "1923": 666,
+      "competition": 667,
+      "1918": 668,
+      "FIFA": 669,
+      "1998": 670,
+      "Cup": 671,
+      "scored": 672,
+      "greater": 673,
+      "21": 674,
+      "estimated": 675,
+      "term": 676,
+      "Star": 677,
+      "Carter": 678,
+      "clock": 679,
+      "million": 680,
+      "Mason": 681,
+      "line": 682,
+      "streak": 683,
+      "reached": 684,
+      "road": 685,
+      "put": 686,
+      "Pope": 687,
+      "result": 688,
+      "according": 689,
+      "monitors": 690,
+      "myth": 691,
+      "king": 692,
+      "sky": 693,
+      "gliders": 694,
+      "Geopyxis": 695,
+      "Patterson": 696,
+      "PlayStation": 697,
+      "real": 698,
+      "low": 699,
+      "missions": 700,
+      "minor": 701,
+      "Each": 702,
+      "heavy": 703,
+      "types": 704,
+      "Army": 705,
+      "meaning": 706,
+      "himself": 707,
+      "weapons": 708,
+      "young": 709,
+      "mostly": 710,
+      "proposed": 711,
+      "again": 712,
+      "beginning": 713,
+      "upon": 714,
+      "Its": 715,
+      "worked": 716,
+      "similar": 717,
+      "September": 718,
+      "appearance": 719,
+      "too": 720,
+      "left": 721,
+      "His": 722,
+      "located": 723,
+      "MacArthur": 724,
+      "US": 725,
+      "newly": 726,
+      "B": 727,
+      "club": 728,
+      "officers": 729,
+      "rumors": 730,
+      "rifles": 731,
+      "caliber": 732,
+      "old": 733,
+      "nearly": 734,
+      "among": 735,
+      "lead": 736,
+      "placed": 737,
+      "&": 738,
+      "continue": 739,
+      "Frederick": 740,
+      "ones": 741,
+      "professional": 742,
+      "themed": 743,
+      "wife": 744,
+      "little": 745,
+      "25": 746,
+      "wrote": 747,
+      "closed": 748,
+      "services": 749,
+      "Old": 750,
+      "2007": 751,
+      "2008": 752,
+      "access": 753,
+      "2009": 754,
+      "usually": 755,
+      "1990": 756,
+      "League": 757,
+      "Draft": 758,
+      "Kings": 759,
+      "fans": 760,
+      "free": 761,
+      "goaltender": 762,
+      "losing": 763,
+      "debut": 764,
+      "seen": 765,
+      "regulation": 766,
+      "silver": 767,
+      "fixed": 768,
+      "blockade": 769,
+      "crew": 770,
+      "controlled": 771,
+      "armor": 772,
+      "kg": 773,
+      "means": 774,
+      "e": 775,
+      "formed": 776,
+      "battleships": 777,
+      "offerings": 778,
+      "myths": 779,
+      "represent": 780,
+      "example": 781,
+      "Blood": 782,
+      "fly": 783,
+      "engaged": 784,
+      "Pilot": 785,
+      "glider": 786,
+      "European": 787,
+      "gliding": 788,
+      "Aircraft": 789,
+      "recreational": 790,
+      "fruitbodies": 791,
+      "Longacre": 792,
+      "nation": 793,
+      "Second": 794,
+      "multiple": 795,
+      "2014": 796,
+      "return": 797,
+      "route": 798,
+      "rest": 799,
+      "units": 800,
+      "having": 801,
+      "act": 802,
+      "turns": 803,
+      "movement": 804,
+      "Gallian": 805,
+      "soldiers": 806,
+      "One": 807,
+      "towards": 808,
+      "ancient": 809,
+      "chance": 810,
+      "gave": 811,
+      "majority": 812,
+      "material": 813,
+      "An": 814,
+      "guitar": 815,
+      "modern": 816,
+      "instruments": 817,
+      "pre": 818,
+      "People": 819,
+      "owned": 820,
+      "aspects": 821,
+      "featured": 822,
+      "damaged": 823,
+      "S": 824,
+      "\u00c6sthetic": 825,
+      "remaining": 826,
+      "14": 827,
+      "ammunition": 828,
+      "instead": 829,
+      "Totten": 830,
+      "1861": 831,
+      "completed": 832,
+      "because": 833,
+      "That": 834,
+      "issued": 835,
+      "oil": 836,
+      "miles": 837,
+      "attempted": 838,
+      "brought": 839,
+      "days": 840,
+      "Dunnington": 841,
+      "bill": 842,
+      "Children": 843,
+      "Mary": 844,
+      "Dorothy": 845,
+      "amateur": 846,
+      "spent": 847,
+      "won": 848,
+      "give": 849,
+      "attack": 850,
+      "Set": 851,
+      "shaped": 852,
+      "disc": 853,
+      "base": 854,
+      "close": 855,
+      "region": 856,
+      "resulted": 857,
+      "pick": 858,
+      "fired": 859,
+      "Rick": 860,
+      "Howson": 861,
+      "prior": 862,
+      "50": 863,
+      "tied": 864,
+      "playoff": 865,
+      "might": 866,
+      "100": 867,
+      "break": 868,
+      "earlier": 869,
+      "Vatican": 870,
+      "observations": 871,
+      "stage": 872,
+      "says": 873,
+      "71": 874,
+      "acting": 875,
+      "Bulloch": 876,
+      "primary": 877,
+      "pound": 878,
+      "success": 879,
+      "ground": 880,
+      "opposite": 881,
+      "cancer": 882,
+      "introduced": 883,
+      "Karl": 884,
+      "bombardment": 885,
+      "wing": 886,
+      "rarely": 887,
+      "beliefs": 888,
+      "characteristics": 889,
+      "combinations": 890,
+      "Atenism": 891,
+      "depicted": 892,
+      "belief": 893,
+      "earth": 894,
+      "chaos": 895,
+      "Hathor": 896,
+      "ba": 897,
+      "increasingly": 898,
+      "Reign": 899,
+      "albums": 900,
+      "registered": 901,
+      "Licence": 902,
+      "facilities": 903,
+      "coins": 904,
+      "McKay": 905,
+      "unit": 906,
+      "features": 907,
+      "positive": 908,
+      "very": 909,
+      "turn": 910,
+      "assigned": 911,
+      "something": 912,
+      "remain": 913,
+      "entire": 914,
+      "composed": 915,
+      "becomes": 916,
+      "evidence": 917,
+      "short": 918,
+      "armed": 919,
+      "separate": 920,
+      "ways": 921,
+      "staff": 922,
+      "response": 923,
+      "what": 924,
+      "parts": 925,
+      "body": 926,
+      "needed": 927,
+      "essential": 928,
+      "engine": 929,
+      "anime": 930,
+      "Music": 931,
+      "production": 932,
+      "need": 933,
+      "initially": 934,
+      "lyrics": 935,
+      "According": 936,
+      "style": 937,
+      "latter": 938,
+      "returning": 939,
+      "issues": 940,
+      "planned": 941,
+      "title": 942,
+      "eventually": 943,
+      "History": 944,
+      "1997": 945,
+      "commander": 946,
+      "Governor": 947,
+      "Major": 948,
+      "increased": 949,
+      "30": 950,
+      "federal": 951,
+      "government": 952,
+      "transferred": 953,
+      "Captain": 954,
+      "should": 955,
+      "necessary": 956,
+      "subject": 957,
+      "morning": 958,
+      "percussion": 959,
+      "supply": 960,
+      "turned": 961,
+      "opened": 962,
+      "remainder": 963,
+      "W": 964,
+      "ironclad": 965,
+      "scope": 966,
+      "briefly": 967,
+      "added": 968,
+      "smaller": 969,
+      "October": 970,
+      "side": 971,
+      "Great": 972,
+      "century": 973,
+      "Later": 974,
+      "shell": 975,
+      "association": 976,
+      "designated": 977,
+      "Art": 978,
+      "Spring": 979,
+      "collaboration": 980,
+      "died": 981,
+      "critic": 982,
+      "show": 983,
+      "Following": 984,
+      "schools": 985,
+      "\u00a3": 986,
+      "studio": 987,
+      "Andrew": 988,
+      "enough": 989,
+      "sacred": 990,
+      "taking": 991,
+      "Warne": 992,
+      "comes": 993,
+      "1988": 994,
+      "Louis": 995,
+      "regional": 996,
+      "Another": 997,
+      "levels": 998,
+      "Australia": 999
+    },
+    "unk_token": "<unk>"
+  }
+}

tokenizer_config.json

@@ -1,5 +1,8 @@
 {
   "model_max_length": 512,
   "tokenizer_class": "PreTrainedTokenizerFast",
-  "unk_token": "<unk>"
+  "pad_token": "<pad>",
+  "unk_token": "<unk>",
+  "bos_token": "<bos>",
+  "eos_token": "<eos>"
 }

vocab.json

@@ -1,1002 +1,1002 @@
 {
-  "<unk>": 0,
-  "the": 1,
-  ",": 2,
-  ".": 3,
-  "of": 4,
-  "and": 5,
-  "@": 6,
-  "in": 7,
-  "to": 8,
-  "a": 9,
-  "=": 10,
-  "was": 11,
-  "\"": 12,
-  "-": 13,
-  "The": 14,
-  "'": 15,
-  "for": 16,
-  "with": 17,
-  "that": 18,
-  "as": 19,
-  "s": 20,
-  "were": 21,
-  "by": 22,
-  ")": 23,
-  "(": 24,
-  "on": 25,
-  "is": 26,
-  "from": 27,
-  "at": 28,
-  "are": 29,
-  "gods": 30,
-  ";": 31,
-  "an": 32,
-  "which": 33,
-  "be": 34,
-  "their": 35,
-  "his": 36,
-  "had": 37,
-  "her": 38,
-  "In": 39,
-  "it": 40,
-  "or": 41,
-  "\u2013": 42,
-  "not": 43,
-  "deities": 44,
-  "one": 45,
-  "but": 46,
-  "also": 47,
-  "he": 48,
-  "who": 49,
-  "other": 50,
-  "GA": 51,
-  "has": 52,
-  "first": 53,
-  "game": 54,
-  "aircraft": 55,
-  "its": 56,
-  "two": 57,
-  "have": 58,
-  "this": 59,
-  ":": 60,
-  "she": 61,
-  "god": 62,
-  "all": 63,
-  "more": 64,
-  "they": 65,
-  "Egyptian": 66,
-  "time": 67,
-  "1": 68,
-  "She": 69,
-  "into": 70,
-  "team": 71,
-  "after": 72,
-  "He": 73,
-  "could": 74,
-  "year": 75,
-  "than": 76,
-  "been": 77,
-  "these": 78,
-  "season": 79,
-  "A": 80,
-  "It": 81,
-  "Valkyria": 82,
-  "during": 83,
-  "only": 84,
-  "2": 85,
-  "some": 86,
-  "being": 87,
-  "Little": 88,
-  "over": 89,
-  "when": 90,
-  "many": 91,
-  "such": 92,
-  "would": 93,
-  "most": 94,
-  "divine": 95,
-  "them": 96,
-  "Rock": 97,
-  "four": 98,
-  "Cullen": 99,
-  "up": 100,
-  "made": 101,
-  "Barker": 102,
-  "album": 103,
-  "4": 104,
-  "between": 105,
-  "Blue": 106,
-  "Jackets": 107,
-  "UK": 108,
-  "Fernandez": 109,
-  "about": 110,
-  "before": 111,
-  "work": 112,
-  "while": 113,
-  "I": 114,
-  "gold": 115,
-  "Chronicles": 116,
-  "can": 117,
-  "out": 118,
-  "world": 119,
-  "Columbus": 120,
-  "ship": 121,
-  "games": 122,
-  "used": 123,
-  "three": 124,
-  "000": 125,
-  "operations": 126,
-  "both": 127,
-  "like": 128,
-  "NHL": 129,
-  "through": 130,
-  "under": 131,
-  "\u2014": 132,
-  "no": 133,
-  "part": 134,
-  "This": 135,
-  "played": 136,
-  "3": 137,
-  "same": 138,
-  "7": 139,
-  "new": 140,
-  "form": 141,
-  "5": 142,
-  "dollar": 143,
-  "where": 144,
-  "There": 145,
-  "so": 146,
-  "him": 147,
-  "there": 148,
-  "war": 149,
-  "number": 150,
-  "said": 151,
-  "well": 152,
-  "Blackie": 153,
-  "human": 154,
-  "Kingdom": 155,
-  "Slayer": 156,
-  "each": 157,
-  "They": 158,
-  "became": 159,
-  "built": 160,
-  "called": 161,
-  "deity": 162,
-  "against": 163,
-  "although": 164,
-  "later": 165,
-  "South": 166,
-  "6": 167,
-  "early": 168,
-  "Arkansas": 169,
-  "including": 170,
-  "often": 171,
-  "N": 172,
-  "air": 173,
-  "British": 174,
-  "Egyptians": 175,
-  "points": 176,
-  "John": 177,
-  "years": 178,
-  "any": 179,
-  "long": 180,
-  "/": 181,
-  "small": 182,
-  "per": 183,
-  "second": 184,
-  "flying": 185,
-  "After": 186,
-  "around": 187,
-  "single": 188,
-  "class": 189,
-  "place": 190,
-  "following": 191,
-  "several": 192,
-  "United": 193,
-  "St": 194,
-  "New": 195,
-  "Atlanta": 196,
-  "down": 197,
-  "end": 198,
-  "Tower": 199,
-  "tower": 200,
-  "may": 201,
-  "commercial": 202,
-  "These": 203,
-  "important": 204,
-  "Egypt": 205,
-  "role": 206,
-  "began": 207,
-  "development": 208,
-  "along": 209,
-  "character": 210,
-  "within": 211,
-  "then": 212,
-  "did": 213,
-  "building": 214,
-  "state": 215,
-  "Navy": 216,
-  "record": 217,
-  "ships": 218,
-  "pilots": 219,
-  "aerodromes": 220,
-  "Zr\u00ednyi": 221,
-  "military": 222,
-  "received": 223,
-  "November": 224,
-  "As": 225,
-  "order": 226,
-  "day": 227,
-  "Flower": 228,
-  "Arsenal": 229,
-  "name": 230,
-  "women": 231,
-  "described": 232,
-  "given": 233,
-  "national": 234,
-  "power": 235,
-  "Austro": 236,
-  "Hungarian": 237,
-  "Heaven": 238,
-  "aviation": 239,
-  "2011": 240,
-  "series": 241,
-  "May": 242,
-  "original": 243,
-  "main": 244,
-  "found": 245,
-  "last": 246,
-  "just": 247,
-  "took": 248,
-  "live": 249,
-  "On": 250,
-  "life": 251,
-  "12": 252,
-  "species": 253,
-  "believed": 254,
-  "transport": 255,
-  "CAA": 256,
-  "player": 257,
-  "off": 258,
-  "m": 259,
-  "another": 260,
-  "history": 261,
-  "Fairies": 262,
-  "t": 263,
-  "family": 264,
-  "career": 265,
-  "Erzherzog": 266,
-  "temples": 267,
-  "Amun": 268,
-  "different": 269,
-  "known": 270,
-  "due": 271,
-  "song": 272,
-  "February": 273,
-  "arsenal": 274,
-  "activities": 275,
-  "back": 276,
-  "religious": 277,
-  "mm": 278,
-  "religion": 279,
-  "War": 280,
-  "While": 281,
-  "previous": 282,
-  "based": 283,
-  "present": 284,
-  "stated": 285,
-  "light": 286,
-  "much": 287,
-  "World": 288,
-  "10": 289,
-  "way": 290,
-  "local": 291,
-  "But": 292,
-  "15": 293,
-  "even": 294,
-  "Gambia": 295,
-  "trade": 296,
-  "inch": 297,
-  "Some": 298,
-  "Ra": 299,
-  "third": 300,
-  "take": 301,
-  "those": 302,
-  "system": 303,
-  "make": 304,
-  "until": 305,
-  "events": 306,
-  "Building": 307,
-  "came": 308,
-  "8": 309,
-  "use": 310,
-  "guns": 311,
-  "Union": 312,
-  "training": 313,
-  "contract": 314,
-  "track": 315,
-  "humans": 316,
-  "carbonaria": 317,
-  "III": 318,
-  "released": 319,
-  "During": 320,
-  "names": 321,
-  "do": 322,
-  "considered": 323,
-  "designed": 324,
-  "particular": 325,
-  "include": 326,
-  "named": 327,
-  "James": 328,
-  "States": 329,
-  "troops": 330,
-  "gun": 331,
-  "19": 332,
-  "sister": 333,
-  "9": 334,
-  "start": 335,
-  "represented": 336,
-  "Italian": 337,
-  "Ferdinand": 338,
-  "Horus": 339,
-  "Aviation": 340,
-  "II": 341,
-  "theme": 342,
-  "franchise": 343,
-  "13": 344,
-  "own": 345,
-  "continued": 346,
-  "forms": 347,
-  "others": 348,
-  "since": 349,
-  "$": 350,
-  "0": 351,
-  "American": 352,
-  "people": 353,
-  "[": 354,
-  "]": 355,
-  "All": 356,
-  "km": 357,
-  "mother": 358,
-  "private": 359,
-  "Association": 360,
-  "nature": 361,
-  "SMS": 362,
-  "Max": 363,
-  "maat": 364,
-  "goddess": 365,
-  "texts": 366,
-  "fungus": 367,
-  "outside": 368,
-  "large": 369,
-  "characters": 370,
-  "members": 371,
-  "carried": 372,
-  "if": 373,
-  "throughout": 374,
-  "five": 375,
-  "home": 376,
-  "times": 377,
-  "General": 378,
-  "support": 379,
-  "fire": 380,
-  "required": 381,
-  "best": 382,
-  "play": 383,
-  "When": 384,
-  "produced": 385,
-  "leading": 386,
-  "2012": 387,
-  "June": 388,
-  "established": 389,
-  "sent": 390,
-  "away": 391,
-  "signed": 392,
-  "Most": 393,
-  "common": 394,
-  "20": 395,
-  "remained": 396,
-  "National": 397,
-  "Her": 398,
-  "\u2019": 399,
-  "late": 400,
-  "ft": 401,
-  "feet": 402,
-  "win": 403,
-  "Although": 404,
-  "appeared": 405,
-  "draft": 406,
-  "However": 407,
-  "88": 408,
-  "rituals": 409,
-  "Isis": 410,
-  "cent": 411,
-  "airspace": 412,
-  "cup": 413,
-  "January": 414,
-  "story": 415,
-  "returned": 416,
-  "release": 417,
-  "control": 418,
-  "specific": 419,
-  "elements": 420,
-  "limited": 421,
-  "At": 422,
-  "position": 423,
-  "next": 424,
-  "written": 425,
-  "involved": 426,
-  "music": 427,
-  "felt": 428,
-  "public": 429,
-  "still": 430,
-  "23": 431,
-  "Club": 432,
-  "men": 433,
-  "held": 434,
-  "18": 435,
-  "River": 436,
-  "south": 437,
-  "now": 438,
-  "band": 439,
-  "Croydon": 440,
-  "death": 441,
-  "24": 442,
-  "conducted": 443,
-  "football": 444,
-  "maskray": 445,
-  "cm": 446,
-  "group": 447,
-  "high": 448,
-  "Roman": 449,
-  "sun": 450,
-  "Carey": 451,
-  "port": 452,
-  "struck": 453,
-  "India": 454,
-  "roles": 455,
-  "film": 456,
-  "CAT": 457,
-  "flight": 458,
-  "creation": 459,
-  "sector": 460,
-  "airports": 461,
-  "pilot": 462,
-  "noise": 463,
-  "coin": 464,
-  "developed": 465,
-  "praised": 466,
-  "players": 467,
-  "With": 468,
-  "city": 469,
-  "major": 470,
-  "action": 471,
-  "recorded": 472,
-  "general": 473,
-  "art": 474,
-  "set": 475,
-  "half": 476,
-  "goals": 477,
-  "For": 478,
-  "giving": 479,
-  "started": 480,
-  "included": 481,
-  "month": 482,
-  "less": 483,
-  "father": 484,
-  "area": 485,
-  "goal": 486,
-  "published": 487,
-  "Christian": 488,
-  "sometimes": 489,
-  "never": 490,
-  "17": 491,
-  "across": 492,
-  "final": 493,
-  "range": 494,
-  "Nash": 495,
-  "loss": 496,
-  "2013": 497,
-  "Got": 498,
-  "inches": 499,
-  "industry": 500,
-  "Lightning": 501,
-  "cult": 502,
-  "images": 503,
-  "temple": 504,
-  "EASA": 505,
-  "aerodrome": 506,
-  "Mint": 507,
-  "Nameless": 508,
-  "black": 509,
-  "2010": 510,
-  "forces": 511,
-  "using": 512,
-  "top": 513,
-  "once": 514,
-  "either": 515,
-  "without": 516,
-  "become": 517,
-  "numbers": 518,
-  "works": 519,
-  "force": 520,
-  "however": 521,
-  "full": 522,
-  "popular": 523,
-  "design": 524,
-  "G": 525,
-  "originally": 526,
-  "issue": 527,
-  "August": 528,
-  "point": 529,
-  "behind": 530,
-  "C": 531,
-  "further": 532,
-  "country": 533,
-  "performed": 534,
-  "11": 535,
-  "North": 536,
-  "larger": 537,
-  "Book": 538,
-  "Society": 539,
-  "children": 540,
-  "planning": 541,
-  "though": 542,
-  "2006": 543,
-  "round": 544,
-  "scoring": 545,
-  "terms": 546,
-  "Penguins": 547,
-  "observatory": 548,
-  "Be": 549,
-  "Way": 550,
-  "Savannah": 551,
-  "civil": 552,
-  "performance": 553,
-  "business": 554,
-  "fleet": 555,
-  "operation": 556,
-  "focus": 557,
-  "kings": 558,
-  "creator": 559,
-  "Osiris": 560,
-  "King": 561,
-  "flights": 562,
-  "airfields": 563,
-  "growth": 564,
-  "battle": 565,
-  "To": 566,
-  "certain": 567,
-  "themselves": 568,
-  "command": 569,
-  "lives": 570,
-  "addition": 571,
-  "despite": 572,
-  "thought": 573,
-  "By": 574,
-  "review": 575,
-  "songs": 576,
-  "Two": 577,
-  "six": 578,
-  "Civil": 579,
-  "arms": 580,
-  "State": 581,
-  "allowed": 582,
-  "personal": 583,
-  "various": 584,
-  "1862": 585,
-  "near": 586,
-  "strong": 587,
-  "shot": 588,
-  "Sanford": 589,
-  "above": 590,
-  "purposes": 591,
-  "moved": 592,
-  "few": 593,
-  "child": 594,
-  "level": 595,
-  "influence": 596,
-  "things": 597,
-  "society": 598,
-  "cover": 599,
-  "international": 600,
-  "hours": 601,
-  "plain": 602,
-  "complex": 603,
-  "size": 604,
-  "Hockey": 605,
-  "deal": 606,
-  "York": 607,
-  "former": 608,
-  "BC": 609,
-  "metres": 610,
-  "Fingal": 611,
-  "speed": 612,
-  "connected": 613,
-  "difficult": 614,
-  "Sri": 615,
-  "Ancona": 616,
-  "goddesses": 617,
-  "worship": 618,
-  "traditional": 619,
-  "Private": 620,
-  "standards": 621,
-  "playing": 622,
-  "video": 623,
-  "gameplay": 624,
-  "making": 625,
-  "opening": 626,
-  "help": 627,
-  "always": 628,
-  "move": 629,
-  "foreign": 630,
-  "great": 631,
-  "combined": 632,
-  "created": 633,
-  "seven": 634,
-  "available": 635,
-  "April": 636,
-  "overall": 637,
-  "500": 638,
-  "particularly": 639,
-  "generally": 640,
-  "provided": 641,
-  "noted": 642,
-  "period": 643,
-  "Museum": 644,
-  "how": 645,
-  "self": 646,
-  "served": 647,
-  "hold": 648,
-  "28": 649,
-  "me": 650,
-  "official": 651,
-  "March": 652,
-  "head": 653,
-  "ordnance": 654,
-  "consisted": 655,
-  "Confederate": 656,
-  "activity": 657,
-  "naval": 658,
-  "surrounding": 659,
-  "significant": 660,
-  "finally": 661,
-  "16": 662,
-  "1923": 663,
-  "competition": 664,
-  "1918": 665,
-  "FIFA": 666,
-  "1998": 667,
-  "Cup": 668,
-  "scored": 669,
-  "greater": 670,
-  "21": 671,
-  "estimated": 672,
-  "term": 673,
-  "Star": 674,
-  "Carter": 675,
-  "clock": 676,
-  "million": 677,
-  "Mason": 678,
-  "line": 679,
-  "streak": 680,
-  "reached": 681,
-  "road": 682,
-  "put": 683,
-  "Pope": 684,
-  "result": 685,
-  "according": 686,
-  "monitors": 687,
-  "myth": 688,
-  "king": 689,
-  "sky": 690,
-  "gliders": 691,
-  "Geopyxis": 692,
-  "Patterson": 693,
-  "PlayStation": 694,
-  "real": 695,
-  "low": 696,
-  "missions": 697,
-  "minor": 698,
-  "Each": 699,
-  "heavy": 700,
-  "types": 701,
-  "Army": 702,
-  "meaning": 703,
-  "himself": 704,
-  "weapons": 705,
-  "young": 706,
-  "mostly": 707,
-  "proposed": 708,
-  "again": 709,
-  "beginning": 710,
-  "upon": 711,
-  "Its": 712,
-  "worked": 713,
-  "similar": 714,
-  "September": 715,
-  "appearance": 716,
-  "too": 717,
-  "left": 718,
-  "His": 719,
-  "located": 720,
-  "MacArthur": 721,
-  "US": 722,
-  "newly": 723,
-  "B": 724,
-  "club": 725,
-  "officers": 726,
-  "rumors": 727,
-  "rifles": 728,
-  "caliber": 729,
-  "old": 730,
-  "nearly": 731,
-  "among": 732,
-  "lead": 733,
-  "placed": 734,
-  "&": 735,
-  "continue": 736,
-  "Frederick": 737,
-  "ones": 738,
-  "professional": 739,
-  "themed": 740,
-  "wife": 741,
-  "little": 742,
-  "25": 743,
-  "wrote": 744,
-  "closed": 745,
-  "services": 746,
-  "Old": 747,
-  "2007": 748,
-  "2008": 749,
-  "access": 750,
-  "2009": 751,
-  "usually": 752,
-  "1990": 753,
-  "League": 754,
-  "Draft": 755,
-  "Kings": 756,
-  "fans": 757,
-  "free": 758,
-  "goaltender": 759,
-  "losing": 760,
-  "debut": 761,
-  "seen": 762,
-  "regulation": 763,
-  "silver": 764,
-  "fixed": 765,
-  "blockade": 766,
-  "crew": 767,
-  "controlled": 768,
-  "armor": 769,
-  "kg": 770,
-  "means": 771,
-  "e": 772,
-  "formed": 773,
-  "battleships": 774,
-  "offerings": 775,
-  "myths": 776,
-  "represent": 777,
-  "example": 778,
-  "Blood": 779,
-  "fly": 780,
-  "engaged": 781,
-  "Pilot": 782,
-  "glider": 783,
-  "European": 784,
-  "gliding": 785,
-  "Aircraft": 786,
-  "recreational": 787,
-  "fruitbodies": 788,
-  "Longacre": 789,
-  "nation": 790,
-  "Second": 791,
-  "multiple": 792,
-  "2014": 793,
-  "return": 794,
-  "route": 795,
-  "rest": 796,
-  "units": 797,
-  "having": 798,
-  "act": 799,
-  "turns": 800,
-  "movement": 801,
-  "Gallian": 802,
-  "soldiers": 803,
-  "One": 804,
-  "towards": 805,
-  "ancient": 806,
-  "chance": 807,
-  "gave": 808,
-  "majority": 809,
-  "material": 810,
-  "An": 811,
-  "guitar": 812,
-  "modern": 813,
-  "instruments": 814,
-  "pre": 815,
-  "People": 816,
-  "owned": 817,
-  "aspects": 818,
-  "featured": 819,
-  "damaged": 820,
-  "S": 821,
-  "\u00c6sthetic": 822,
-  "remaining": 823,
-  "14": 824,
-  "ammunition": 825,
-  "instead": 826,
-  "Totten": 827,
-  "1861": 828,
-  "completed": 829,
-  "because": 830,
-  "That": 831,
-  "issued": 832,
-  "oil": 833,
-  "miles": 834,
-  "attempted": 835,
-  "brought": 836,
-  "days": 837,
-  "Dunnington": 838,
-  "bill": 839,
-  "Children": 840,
-  "Mary": 841,
-  "Dorothy": 842,
-  "amateur": 843,
-  "spent": 844,
-  "won": 845,
-  "give": 846,
-  "attack": 847,
-  "Set": 848,
-  "shaped": 849,
-  "disc": 850,
-  "base": 851,
-  "close": 852,
-  "region": 853,
-  "resulted": 854,
-  "pick": 855,
-  "fired": 856,
-  "Rick": 857,
-  "Howson": 858,
-  "prior": 859,
-  "50": 860,
-  "tied": 861,
-  "playoff": 862,
-  "might": 863,
-  "100": 864,
-  "break": 865,
-  "earlier": 866,
-  "Vatican": 867,
-  "observations": 868,
-  "stage": 869,
-  "says": 870,
-  "71": 871,
-  "acting": 872,
-  "Bulloch": 873,
-  "primary": 874,
-  "pound": 875,
-  "success": 876,
-  "ground": 877,
-  "opposite": 878,
-  "cancer": 879,
-  "introduced": 880,
-  "Karl": 881,
-  "bombardment": 882,
-  "wing": 883,
-  "rarely": 884,
-  "beliefs": 885,
-  "characteristics": 886,
-  "combinations": 887,
-  "Atenism": 888,
-  "depicted": 889,
-  "belief": 890,
-  "earth": 891,
-  "chaos": 892,
-  "Hathor": 893,
-  "ba": 894,
-  "increasingly": 895,
-  "Reign": 896,
-  "albums": 897,
-  "registered": 898,
-  "Licence": 899,
-  "facilities": 900,
-  "coins": 901,
-  "McKay": 902,
-  "unit": 903,
-  "features": 904,
-  "positive": 905,
-  "very": 906,
-  "turn": 907,
-  "assigned": 908,
-  "something": 909,
-  "remain": 910,
-  "entire": 911,
-  "composed": 912,
-  "becomes": 913,
-  "evidence": 914,
-  "short": 915,
-  "armed": 916,
-  "separate": 917,
-  "ways": 918,
-  "staff": 919,
-  "response": 920,
-  "what": 921,
-  "parts": 922,
-  "body": 923,
-  "needed": 924,
-  "essential": 925,
-  "engine": 926,
-  "anime": 927,
-  "Music": 928,
-  "production": 929,
-  "need": 930,
-  "initially": 931,
-  "lyrics": 932,
-  "According": 933,
-  "style": 934,
-  "latter": 935,
-  "returning": 936,
-  "issues": 937,
-  "planned": 938,
-  "title": 939,
-  "eventually": 940,
-  "History": 941,
-  "1997": 942,
-  "commander": 943,
-  "Governor": 944,
-  "Major": 945,
-  "increased": 946,
-  "30": 947,
-  "federal": 948,
-  "government": 949,
-  "transferred": 950,
-  "Captain": 951,
-  "should": 952,
-  "necessary": 953,
-  "subject": 954,
-  "morning": 955,
-  "percussion": 956,
-  "supply": 957,
-  "turned": 958,
-  "opened": 959,
-  "remainder": 960,
-  "W": 961,
-  "ironclad": 962,
-  "scope": 963,
-  "briefly": 964,
-  "added": 965,
-  "smaller": 966,
-  "October": 967,
-  "side": 968,
-  "Great": 969,
-  "century": 970,
-  "Later": 971,
-  "shell": 972,
-  "association": 973,
-  "designated": 974,
-  "Art": 975,
-  "Spring": 976,
-  "collaboration": 977,
-  "died": 978,
-  "critic": 979,
-  "show": 980,
-  "Following": 981,
-  "schools": 982,
-  "\u00a3": 983,
-  "studio": 984,
-  "Andrew": 985,
-  "enough": 986,
-  "sacred": 987,
-  "taking": 988,
-  "Warne": 989,
-  "comes": 990,
-  "1988": 991,
-  "Louis": 992,
-  "regional": 993,
-  "Another": 994,
-  "levels": 995,
-  "Australia": 996,
-  "pattern": 997,
-  "able": 998,
-  "International": 999
+  "<pad>": 0,
+  "<unk>": 1,
+  "<bos>": 2,
+  "<eos>": 3,
+  "the": 4,
+  ",": 5,
+  ".": 6,
+  "of": 7,
+  "and": 8,
+  "@": 9,
+  "in": 10,
+  "to": 11,
+  "a": 12,
+  "=": 13,
+  "was": 14,
+  "\"": 15,
+  "-": 16,
+  "The": 17,
+  "'": 18,
+  "for": 19,
+  "with": 20,
+  "that": 21,
+  "as": 22,
+  "s": 23,
+  "were": 24,
+  "by": 25,
+  ")": 26,
+  "(": 27,
+  "on": 28,
+  "is": 29,
+  "from": 30,
+  "at": 31,
+  "are": 32,
+  "gods": 33,
+  ";": 34,
+  "an": 35,
+  "which": 36,
+  "be": 37,
+  "their": 38,
+  "his": 39,
+  "had": 40,
+  "her": 41,
+  "In": 42,
+  "it": 43,
+  "or": 44,
+  "\u2013": 45,
+  "not": 46,
+  "deities": 47,
+  "one": 48,
+  "but": 49,
+  "also": 50,
+  "he": 51,
+  "who": 52,
+  "other": 53,
+  "GA": 54,
+  "has": 55,
+  "first": 56,
+  "game": 57,
+  "aircraft": 58,
+  "its": 59,
+  "two": 60,
+  "have": 61,
+  "this": 62,
+  ":": 63,
+  "she": 64,
+  "god": 65,
+  "all": 66,
+  "more": 67,
+  "they": 68,
+  "Egyptian": 69,
+  "time": 70,
+  "1": 71,
+  "She": 72,
+  "into": 73,
+  "team": 74,
+  "after": 75,
+  "He": 76,
+  "could": 77,
+  "year": 78,
+  "than": 79,
+  "been": 80,
+  "these": 81,
+  "season": 82,
+  "A": 83,
+  "It": 84,
+  "Valkyria": 85,
+  "during": 86,
+  "only": 87,
+  "2": 88,
+  "some": 89,
+  "being": 90,
+  "Little": 91,
+  "over": 92,
+  "when": 93,
+  "many": 94,
+  "such": 95,
+  "would": 96,
+  "most": 97,
+  "divine": 98,
+  "them": 99,
+  "Rock": 100,
+  "four": 101,
+  "Cullen": 102,
+  "up": 103,
+  "made": 104,
+  "Barker": 105,
+  "album": 106,
+  "4": 107,
+  "between": 108,
+  "Blue": 109,
+  "Jackets": 110,
+  "UK": 111,
+  "Fernandez": 112,
+  "about": 113,
+  "before": 114,
+  "work": 115,
+  "while": 116,
+  "I": 117,
+  "gold": 118,
+  "Chronicles": 119,
+  "can": 120,
+  "out": 121,
+  "world": 122,
+  "Columbus": 123,
+  "ship": 124,
+  "games": 125,
+  "used": 126,
+  "three": 127,
+  "000": 128,
+  "operations": 129,
+  "both": 130,
+  "like": 131,
+  "NHL": 132,
+  "through": 133,
+  "under": 134,
+  "\u2014": 135,
+  "no": 136,
+  "part": 137,
+  "This": 138,
+  "played": 139,
+  "3": 140,
+  "same": 141,
+  "7": 142,
+  "new": 143,
+  "form": 144,
+  "5": 145,
+  "dollar": 146,
+  "where": 147,
+  "There": 148,
+  "so": 149,
+  "him": 150,
+  "there": 151,
+  "war": 152,
+  "number": 153,
+  "said": 154,
+  "well": 155,
+  "Blackie": 156,
+  "human": 157,
+  "Kingdom": 158,
+  "Slayer": 159,
+  "each": 160,
+  "They": 161,
+  "became": 162,
+  "built": 163,
+  "called": 164,
+  "deity": 165,
+  "against": 166,
+  "although": 167,
+  "later": 168,
+  "South": 169,
+  "6": 170,
+  "early": 171,
+  "Arkansas": 172,
+  "including": 173,
+  "often": 174,
+  "N": 175,
+  "air": 176,
+  "British": 177,
+  "Egyptians": 178,
+  "points": 179,
+  "John": 180,
+  "years": 181,
+  "any": 182,
+  "long": 183,
+  "/": 184,
+  "small": 185,
+  "per": 186,
+  "second": 187,
+  "flying": 188,
+  "After": 189,
+  "around": 190,
+  "single": 191,
+  "class": 192,
+  "place": 193,
+  "following": 194,
+  "several": 195,
+  "United": 196,
+  "St": 197,
+  "New": 198,
+  "Atlanta": 199,
+  "down": 200,
+  "end": 201,
+  "Tower": 202,
+  "tower": 203,
+  "may": 204,
+  "commercial": 205,
+  "These": 206,
+  "important": 207,
+  "Egypt": 208,
+  "role": 209,
+  "began": 210,
+  "development": 211,
+  "along": 212,
+  "character": 213,
+  "within": 214,
+  "then": 215,
+  "did": 216,
+  "building": 217,
+  "state": 218,
+  "Navy": 219,
+  "record": 220,
+  "ships": 221,
+  "pilots": 222,
+  "aerodromes": 223,
+  "Zr\u00ednyi": 224,
+  "military": 225,
+  "received": 226,
+  "November": 227,
+  "As": 228,
+  "order": 229,
+  "day": 230,
+  "Flower": 231,
+  "Arsenal": 232,
+  "name": 233,
+  "women": 234,
+  "described": 235,
+  "given": 236,
+  "national": 237,
+  "power": 238,
+  "Austro": 239,
+  "Hungarian": 240,
+  "Heaven": 241,
+  "aviation": 242,
+  "2011": 243,
+  "series": 244,
+  "May": 245,
+  "original": 246,
+  "main": 247,
+  "found": 248,
+  "last": 249,
+  "just": 250,
+  "took": 251,
+  "live": 252,
+  "On": 253,
+  "life": 254,
+  "12": 255,
+  "species": 256,
+  "believed": 257,
+  "transport": 258,
+  "CAA": 259,
+  "player": 260,
+  "off": 261,
+  "m": 262,
+  "another": 263,
+  "history": 264,
+  "Fairies": 265,
+  "t": 266,
+  "family": 267,
+  "career": 268,
+  "Erzherzog": 269,
+  "temples": 270,
+  "Amun": 271,
+  "different": 272,
+  "known": 273,
+  "due": 274,
+  "song": 275,
+  "February": 276,
+  "arsenal": 277,
+  "activities": 278,
+  "back": 279,
+  "religious": 280,
+  "mm": 281,
+  "religion": 282,
+  "War": 283,
+  "While": 284,
+  "previous": 285,
+  "based": 286,
+  "present": 287,
+  "stated": 288,
+  "light": 289,
+  "much": 290,
+  "World": 291,
+  "10": 292,
+  "way": 293,
+  "local": 294,
+  "But": 295,
+  "15": 296,
+  "even": 297,
+  "Gambia": 298,
+  "trade": 299,
+  "inch": 300,
+  "Some": 301,
+  "Ra": 302,
+  "third": 303,
+  "take": 304,
+  "those": 305,
+  "system": 306,
+  "make": 307,
+  "until": 308,
+  "events": 309,
+  "Building": 310,
+  "came": 311,
+  "8": 312,
+  "use": 313,
+  "guns": 314,
+  "Union": 315,
+  "training": 316,
+  "contract": 317,
+  "track": 318,
+  "humans": 319,
+  "carbonaria": 320,
+  "III": 321,
+  "released": 322,
+  "During": 323,
+  "names": 324,
+  "do": 325,
+  "considered": 326,
+  "designed": 327,
+  "particular": 328,
+  "include": 329,
+  "named": 330,
+  "James": 331,
+  "States": 332,
+  "troops": 333,
+  "gun": 334,
+  "19": 335,
+  "sister": 336,
+  "9": 337,
+  "start": 338,
+  "represented": 339,
+  "Italian": 340,
+  "Ferdinand": 341,
+  "Horus": 342,
+  "Aviation": 343,
+  "II": 344,
+  "theme": 345,
+  "franchise": 346,
+  "13": 347,
+  "own": 348,
+  "continued": 349,
+  "forms": 350,
+  "others": 351,
+  "since": 352,
+  "$": 353,
+  "0": 354,
+  "American": 355,
+  "people": 356,
+  "[": 357,
+  "]": 358,
+  "All": 359,
+  "km": 360,
+  "mother": 361,
+  "private": 362,
+  "Association": 363,
+  "nature": 364,
+  "SMS": 365,
+  "Max": 366,
+  "maat": 367,
+  "goddess": 368,
+  "texts": 369,
+  "fungus": 370,
+  "outside": 371,
+  "large": 372,
+  "characters": 373,
+  "members": 374,
+  "carried": 375,
+  "if": 376,
+  "throughout": 377,
+  "five": 378,
+  "home": 379,
+  "times": 380,
+  "General": 381,
+  "support": 382,
+  "fire": 383,
+  "required": 384,
+  "best": 385,
+  "play": 386,
+  "When": 387,
+  "produced": 388,
+  "leading": 389,
+  "2012": 390,
+  "June": 391,
+  "established": 392,
+  "sent": 393,
+  "away": 394,
+  "signed": 395,
+  "Most": 396,
+  "common": 397,
+  "20": 398,
+  "remained": 399,
+  "National": 400,
+  "Her": 401,
+  "\u2019": 402,
+  "late": 403,
+  "ft": 404,
+  "feet": 405,
+  "win": 406,
+  "Although": 407,
+  "appeared": 408,
+  "draft": 409,
+  "However": 410,
+  "88": 411,
+  "rituals": 412,
+  "Isis": 413,
+  "cent": 414,
+  "airspace": 415,
+  "cup": 416,
+  "January": 417,
+  "story": 418,
+  "returned": 419,
+  "release": 420,
+  "control": 421,
+  "specific": 422,
+  "elements": 423,
+  "limited": 424,
+  "At": 425,
+  "position": 426,
+  "next": 427,
+  "written": 428,
+  "involved": 429,
+  "music": 430,
+  "felt": 431,
+  "public": 432,
+  "still": 433,
+  "23": 434,
+  "Club": 435,
+  "men": 436,
+  "held": 437,
+  "18": 438,
+  "River": 439,
+  "south": 440,
+  "now": 441,
+  "band": 442,
+  "Croydon": 443,
+  "death": 444,
+  "24": 445,
+  "conducted": 446,
+  "football": 447,
+  "maskray": 448,
+  "cm": 449,
+  "group": 450,
+  "high": 451,
+  "Roman": 452,
+  "sun": 453,
+  "Carey": 454,
+  "port": 455,
+  "struck": 456,
+  "India": 457,
+  "roles": 458,
+  "film": 459,
+  "CAT": 460,
+  "flight": 461,
+  "creation": 462,
+  "sector": 463,
+  "airports": 464,
+  "pilot": 465,
+  "noise": 466,
+  "coin": 467,
+  "developed": 468,
+  "praised": 469,
+  "players": 470,
+  "With": 471,
+  "city": 472,
+  "major": 473,
+  "action": 474,
+  "recorded": 475,
+  "general": 476,
+  "art": 477,
+  "set": 478,
+  "half": 479,
+  "goals": 480,
+  "For": 481,
+  "giving": 482,
+  "started": 483,
+  "included": 484,
+  "month": 485,
+  "less": 486,
+  "father": 487,
+  "area": 488,
+  "goal": 489,
+  "published": 490,
+  "Christian": 491,
+  "sometimes": 492,
+  "never": 493,
+  "17": 494,
+  "across": 495,
+  "final": 496,
+  "range": 497,
+  "Nash": 498,
+  "loss": 499,
+  "2013": 500,
+  "Got": 501,
+  "inches": 502,
+  "industry": 503,
+  "Lightning": 504,
+  "cult": 505,
+  "images": 506,
+  "temple": 507,
+  "EASA": 508,
+  "aerodrome": 509,
+  "Mint": 510,
+  "Nameless": 511,
+  "black": 512,
+  "2010": 513,
+  "forces": 514,
+  "using": 515,
+  "top": 516,
+  "once": 517,
+  "either": 518,
+  "without": 519,
+  "become": 520,
+  "numbers": 521,
+  "works": 522,
+  "force": 523,
+  "however": 524,
+  "full": 525,
+  "popular": 526,
+  "design": 527,
+  "G": 528,
+  "originally": 529,
+  "issue": 530,
+  "August": 531,
+  "point": 532,
+  "behind": 533,
+  "C": 534,
+  "further": 535,
+  "country": 536,
+  "performed": 537,
+  "11": 538,
+  "North": 539,
+  "larger": 540,
+  "Book": 541,
+  "Society": 542,
+  "children": 543,
+  "planning": 544,
+  "though": 545,
+  "2006": 546,
+  "round": 547,
+  "scoring": 548,
+  "terms": 549,
+  "Penguins": 550,
+  "observatory": 551,
+  "Be": 552,
+  "Way": 553,
+  "Savannah": 554,
+  "civil": 555,
+  "performance": 556,
+  "business": 557,
+  "fleet": 558,
+  "operation": 559,
+  "focus": 560,
+  "kings": 561,
+  "creator": 562,
+  "Osiris": 563,
+  "King": 564,
+  "flights": 565,
+  "airfields": 566,
+  "growth": 567,
+  "battle": 568,
+  "To": 569,
+  "certain": 570,
+  "themselves": 571,
+  "command": 572,
+  "lives": 573,
+  "addition": 574,
+  "despite": 575,
+  "thought": 576,
+  "By": 577,
+  "review": 578,
+  "songs": 579,
+  "Two": 580,
+  "six": 581,
+  "Civil": 582,
+  "arms": 583,
+  "State": 584,
+  "allowed": 585,
+  "personal": 586,
+  "various": 587,
+  "1862": 588,
+  "near": 589,
+  "strong": 590,
+  "shot": 591,
+  "Sanford": 592,
+  "above": 593,
+  "purposes": 594,
+  "moved": 595,
+  "few": 596,
+  "child": 597,
+  "level": 598,
+  "influence": 599,
+  "things": 600,
+  "society": 601,
+  "cover": 602,
+  "international": 603,
+  "hours": 604,
+  "plain": 605,
+  "complex": 606,
+  "size": 607,
+  "Hockey": 608,
+  "deal": 609,
+  "York": 610,
+  "former": 611,
+  "BC": 612,
+  "metres": 613,
+  "Fingal": 614,
+  "speed": 615,
+  "connected": 616,
+  "difficult": 617,
+  "Sri": 618,
+  "Ancona": 619,
+  "goddesses": 620,
+  "worship": 621,
+  "traditional": 622,
+  "Private": 623,
+  "standards": 624,
+  "playing": 625,
+  "video": 626,
+  "gameplay": 627,
+  "making": 628,
+  "opening": 629,
+  "help": 630,
+  "always": 631,
+  "move": 632,
+  "foreign": 633,
+  "great": 634,
+  "combined": 635,
+  "created": 636,
+  "seven": 637,
+  "available": 638,
+  "April": 639,
+  "overall": 640,
+  "500": 641,
+  "particularly": 642,
+  "generally": 643,
+  "provided": 644,
+  "noted": 645,
+  "period": 646,
+  "Museum": 647,
+  "how": 648,
+  "self": 649,
+  "served": 650,
+  "hold": 651,
+  "28": 652,
+  "me": 653,
+  "official": 654,
+  "March": 655,
+  "head": 656,
+  "ordnance": 657,
+  "consisted": 658,
+  "Confederate": 659,
+  "activity": 660,
+  "naval": 661,
+  "surrounding": 662,
+  "significant": 663,
+  "finally": 664,
+  "16": 665,
+  "1923": 666,
+  "competition": 667,
+  "1918": 668,
+  "FIFA": 669,
+  "1998": 670,
+  "Cup": 671,
+  "scored": 672,
+  "greater": 673,
+  "21": 674,
+  "estimated": 675,
+  "term": 676,
+  "Star": 677,
+  "Carter": 678,
+  "clock": 679,
+  "million": 680,
+  "Mason": 681,
+  "line": 682,
+  "streak": 683,
+  "reached": 684,
+  "road": 685,
+  "put": 686,
+  "Pope": 687,
+  "result": 688,
+  "according": 689,
+  "monitors": 690,
+  "myth": 691,
+  "king": 692,
+  "sky": 693,
+  "gliders": 694,
+  "Geopyxis": 695,
+  "Patterson": 696,
+  "PlayStation": 697,
+  "real": 698,
+  "low": 699,
+  "missions": 700,
+  "minor": 701,
+  "Each": 702,
+  "heavy": 703,
+  "types": 704,
+  "Army": 705,
+  "meaning": 706,
+  "himself": 707,
+  "weapons": 708,
+  "young": 709,
+  "mostly": 710,
+  "proposed": 711,
+  "again": 712,
+  "beginning": 713,
+  "upon": 714,
+  "Its": 715,
+  "worked": 716,
+  "similar": 717,
+  "September": 718,
+  "appearance": 719,
+  "too": 720,
+  "left": 721,
+  "His": 722,
+  "located": 723,
+  "MacArthur": 724,
+  "US": 725,
+  "newly": 726,
+  "B": 727,
+  "club": 728,
+  "officers": 729,
+  "rumors": 730,
+  "rifles": 731,
+  "caliber": 732,
+  "old": 733,
+  "nearly": 734,
+  "among": 735,
+  "lead": 736,
+  "placed": 737,
+  "&": 738,
+  "continue": 739,
+  "Frederick": 740,
+  "ones": 741,
+  "professional": 742,
+  "themed": 743,
+  "wife": 744,
+  "little": 745,
+  "25": 746,
+  "wrote": 747,
+  "closed": 748,
+  "services": 749,
+  "Old": 750,
+  "2007": 751,
+  "2008": 752,
+  "access": 753,
+  "2009": 754,
+  "usually": 755,
+  "1990": 756,
+  "League": 757,
+  "Draft": 758,
+  "Kings": 759,
+  "fans": 760,
+  "free": 761,
+  "goaltender": 762,
+  "losing": 763,
+  "debut": 764,
+  "seen": 765,
+  "regulation": 766,
+  "silver": 767,
+  "fixed": 768,
+  "blockade": 769,
+  "crew": 770,
+  "controlled": 771,
+  "armor": 772,
+  "kg": 773,
+  "means": 774,
+  "e": 775,
+  "formed": 776,
+  "battleships": 777,
+  "offerings": 778,
+  "myths": 779,
+  "represent": 780,
+  "example": 781,
+  "Blood": 782,
+  "fly": 783,
+  "engaged": 784,
+  "Pilot": 785,
+  "glider": 786,
+  "European": 787,
+  "gliding": 788,
+  "Aircraft": 789,
+  "recreational": 790,
+  "fruitbodies": 791,
+  "Longacre": 792,
+  "nation": 793,
+  "Second": 794,
+  "multiple": 795,
+  "2014": 796,
+  "return": 797,
+  "route": 798,
+  "rest": 799,
+  "units": 800,
+  "having": 801,
+  "act": 802,
+  "turns": 803,
+  "movement": 804,
+  "Gallian": 805,
+  "soldiers": 806,
+  "One": 807,
+  "towards": 808,
+  "ancient": 809,
+  "chance": 810,
+  "gave": 811,
+  "majority": 812,
+  "material": 813,
+  "An": 814,
+  "guitar": 815,
+  "modern": 816,
+  "instruments": 817,
+  "pre": 818,
+  "People": 819,
+  "owned": 820,
+  "aspects": 821,
+  "featured": 822,
+  "damaged": 823,
+  "S": 824,
+  "\u00c6sthetic": 825,
+  "remaining": 826,
+  "14": 827,
+  "ammunition": 828,
+  "instead": 829,
+  "Totten": 830,
+  "1861": 831,
+  "completed": 832,
+  "because": 833,
+  "That": 834,
+  "issued": 835,
+  "oil": 836,
+  "miles": 837,
+  "attempted": 838,
+  "brought": 839,
+  "days": 840,
+  "Dunnington": 841,
+  "bill": 842,
+  "Children": 843,
+  "Mary": 844,
+  "Dorothy": 845,
+  "amateur": 846,
+  "spent": 847,
+  "won": 848,
+  "give": 849,
+  "attack": 850,
+  "Set": 851,
+  "shaped": 852,
+  "disc": 853,
+  "base": 854,
+  "close": 855,
+  "region": 856,
+  "resulted": 857,
+  "pick": 858,
+  "fired": 859,
+  "Rick": 860,
+  "Howson": 861,
+  "prior": 862,
+  "50": 863,
+  "tied": 864,
+  "playoff": 865,
+  "might": 866,
+  "100": 867,
+  "break": 868,
+  "earlier": 869,
+  "Vatican": 870,
+  "observations": 871,
+  "stage": 872,
+  "says": 873,
+  "71": 874,
+  "acting": 875,
+  "Bulloch": 876,
+  "primary": 877,
+  "pound": 878,
+  "success": 879,
+  "ground": 880,
+  "opposite": 881,
+  "cancer": 882,
+  "introduced": 883,
+  "Karl": 884,
+  "bombardment": 885,
+  "wing": 886,
+  "rarely": 887,
+  "beliefs": 888,
+  "characteristics": 889,
+  "combinations": 890,
+  "Atenism": 891,
+  "depicted": 892,
+  "belief": 893,
+  "earth": 894,
+  "chaos": 895,
+  "Hathor": 896,
+  "ba": 897,
+  "increasingly": 898,
+  "Reign": 899,
+  "albums": 900,
+  "registered": 901,
+  "Licence": 902,
+  "facilities": 903,
+  "coins": 904,
+  "McKay": 905,
+  "unit": 906,
+  "features": 907,
+  "positive": 908,
+  "very": 909,
+  "turn": 910,
+  "assigned": 911,
+  "something": 912,
+  "remain": 913,
+  "entire": 914,
+  "composed": 915,
+  "becomes": 916,
+  "evidence": 917,
+  "short": 918,
+  "armed": 919,
+  "separate": 920,
+  "ways": 921,
+  "staff": 922,
+  "response": 923,
+  "what": 924,
+  "parts": 925,
+  "body": 926,
+  "needed": 927,
+  "essential": 928,
+  "engine": 929,
+  "anime": 930,
+  "Music": 931,
+  "production": 932,
+  "need": 933,
+  "initially": 934,
+  "lyrics": 935,
+  "According": 936,
+  "style": 937,
+  "latter": 938,
+  "returning": 939,
+  "issues": 940,
+  "planned": 941,
+  "title": 942,
+  "eventually": 943,
+  "History": 944,
+  "1997": 945,
+  "commander": 946,
+  "Governor": 947,
+  "Major": 948,
+  "increased": 949,
+  "30": 950,
+  "federal": 951,
+  "government": 952,
+  "transferred": 953,
+  "Captain": 954,
+  "should": 955,
+  "necessary": 956,
+  "subject": 957,
+  "morning": 958,
+  "percussion": 959,
+  "supply": 960,
+  "turned": 961,
+  "opened": 962,
+  "remainder": 963,
+  "W": 964,
+  "ironclad": 965,
+  "scope": 966,
+  "briefly": 967,
+  "added": 968,
+  "smaller": 969,
+  "October": 970,
+  "side": 971,
+  "Great": 972,
+  "century": 973,
+  "Later": 974,
+  "shell": 975,
+  "association": 976,
+  "designated": 977,
+  "Art": 978,
+  "Spring": 979,
+  "collaboration": 980,
+  "died": 981,
+  "critic": 982,
+  "show": 983,
+  "Following": 984,
+  "schools": 985,
+  "\u00a3": 986,
+  "studio": 987,
+  "Andrew": 988,
+  "enough": 989,
+  "sacred": 990,
+  "taking": 991,
+  "Warne": 992,
+  "comes": 993,
+  "1988": 994,
+  "Louis": 995,
+  "regional": 996,
+  "Another": 997,
+  "levels": 998,
+  "Australia": 999
 }