Upload 3 files

Browse files

Files changed (3) hide show

special_tokens_map.json +30 -0
tokenizer.json +1133 -0
tokenizer_config.json +19 -0

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,30 @@

+{
+  "bos_token": {
+    "content": "<|void|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|void|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|void|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|void|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json ADDED Viewed

	@@ -0,0 +1,1133 @@

+{
+  "version": "1.0",
+  "truncation": null,
+  "padding": null,
+  "added_tokens": [
+    {
+      "id": 0,
+      "content": "<|void|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  ],
+  "normalizer": null,
+  "pre_tokenizer": {
+    "type": "Sequence",
+    "pretokenizers": [
+      {
+        "type": "Digits",
+        "individual_digits": true
+      },
+      {
+        "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": {
+    "type": "ByteLevel",
+    "add_prefix_space": true,
+    "trim_offsets": true,
+    "use_regex": true
+  },
+  "model": {
+    "type": "BPE",
+    "dropout": 0.9,
+    "unk_token": "<|void|>",
+    "continuing_subword_prefix": null,
+    "end_of_word_suffix": null,
+    "fuse_unk": true,
+    "byte_fallback": false,
+    "ignore_merges": false,
+    "vocab": {
+      "<|void|>": 0,
+      "!": 1,
+      "\"": 2,
+      "#": 3,
+      "$": 4,
+      "%": 5,
+      "&": 6,
+      "'": 7,
+      "(": 8,
+      ")": 9,
+      "*": 10,
+      "+": 11,
+      ",": 12,
+      "-": 13,
+      ".": 14,
+      "/": 15,
+      "0": 16,
+      "1": 17,
+      "2": 18,
+      "3": 19,
+      "4": 20,
+      "5": 21,
+      "6": 22,
+      "7": 23,
+      "8": 24,
+      "9": 25,
+      ":": 26,
+      ";": 27,
+      "<": 28,
+      "=": 29,
+      ">": 30,
+      "?": 31,
+      "@": 32,
+      "A": 33,
+      "B": 34,
+      "C": 35,
+      "D": 36,
+      "E": 37,
+      "F": 38,
+      "G": 39,
+      "H": 40,
+      "I": 41,
+      "J": 42,
+      "K": 43,
+      "L": 44,
+      "M": 45,
+      "N": 46,
+      "O": 47,
+      "P": 48,
+      "Q": 49,
+      "R": 50,
+      "S": 51,
+      "T": 52,
+      "U": 53,
+      "V": 54,
+      "W": 55,
+      "X": 56,
+      "Y": 57,
+      "Z": 58,
+      "[": 59,
+      "\\": 60,
+      "]": 61,
+      "^": 62,
+      "_": 63,
+      "`": 64,
+      "a": 65,
+      "b": 66,
+      "c": 67,
+      "d": 68,
+      "e": 69,
+      "f": 70,
+      "g": 71,
+      "h": 72,
+      "i": 73,
+      "j": 74,
+      "k": 75,
+      "l": 76,
+      "m": 77,
+      "n": 78,
+      "o": 79,
+      "p": 80,
+      "q": 81,
+      "r": 82,
+      "s": 83,
+      "t": 84,
+      "u": 85,
+      "v": 86,
+      "w": 87,
+      "x": 88,
+      "y": 89,
+      "z": 90,
+      "{": 91,
+      "|": 92,
+      "}": 93,
+      "~": 94,
+      "¡": 95,
+      "¢": 96,
+      "£": 97,
+      "¤": 98,
+      "¥": 99,
+      "¦": 100,
+      "§": 101,
+      "¨": 102,
+      "©": 103,
+      "ª": 104,
+      "«": 105,
+      "¬": 106,
+      "®": 107,
+      "¯": 108,
+      "°": 109,
+      "±": 110,
+      "²": 111,
+      "³": 112,
+      "´": 113,
+      "µ": 114,
+      "¶": 115,
+      "·": 116,
+      "¸": 117,
+      "¹": 118,
+      "º": 119,
+      "»": 120,
+      "¼": 121,
+      "½": 122,
+      "¾": 123,
+      "¿": 124,
+      "À": 125,
+      "Á": 126,
+      "Â": 127,
+      "Ã": 128,
+      "Ä": 129,
+      "Å": 130,
+      "Æ": 131,
+      "Ç": 132,
+      "È": 133,
+      "É": 134,
+      "Ê": 135,
+      "Ë": 136,
+      "Ì": 137,
+      "Í": 138,
+      "Î": 139,
+      "Ï": 140,
+      "Ð": 141,
+      "Ñ": 142,
+      "Ò": 143,
+      "Ó": 144,
+      "Ô": 145,
+      "Õ": 146,
+      "Ö": 147,
+      "×": 148,
+      "Ø": 149,
+      "Ù": 150,
+      "Ú": 151,
+      "Û": 152,
+      "Ü": 153,
+      "Ý": 154,
+      "Þ": 155,
+      "ß": 156,
+      "à": 157,
+      "á": 158,
+      "â": 159,
+      "ã": 160,
+      "ä": 161,
+      "å": 162,
+      "æ": 163,
+      "ç": 164,
+      "è": 165,
+      "é": 166,
+      "ê": 167,
+      "ë": 168,
+      "ì": 169,
+      "í": 170,
+      "î": 171,
+      "ï": 172,
+      "ð": 173,
+      "ñ": 174,
+      "ò": 175,
+      "ó": 176,
+      "ô": 177,
+      "õ": 178,
+      "ö": 179,
+      "÷": 180,
+      "ø": 181,
+      "ù": 182,
+      "ú": 183,
+      "û": 184,
+      "ü": 185,
+      "ý": 186,
+      "þ": 187,
+      "ÿ": 188,
+      "Ā": 189,
+      "ā": 190,
+      "Ă": 191,
+      "ă": 192,
+      "Ą": 193,
+      "ą": 194,
+      "Ć": 195,
+      "ć": 196,
+      "Ĉ": 197,
+      "ĉ": 198,
+      "Ċ": 199,
+      "ċ": 200,
+      "Č": 201,
+      "č": 202,
+      "Ď": 203,
+      "ď": 204,
+      "Đ": 205,
+      "đ": 206,
+      "Ē": 207,
+      "ē": 208,
+      "Ĕ": 209,
+      "ĕ": 210,
+      "Ė": 211,
+      "ė": 212,
+      "Ę": 213,
+      "ę": 214,
+      "Ě": 215,
+      "ě": 216,
+      "Ĝ": 217,
+      "ĝ": 218,
+      "Ğ": 219,
+      "ğ": 220,
+      "Ġ": 221,
+      "ġ": 222,
+      "Ģ": 223,
+      "ģ": 224,
+      "Ĥ": 225,
+      "ĥ": 226,
+      "Ħ": 227,
+      "ħ": 228,
+      "Ĩ": 229,
+      "ĩ": 230,
+      "Ī": 231,
+      "ī": 232,
+      "Ĭ": 233,
+      "ĭ": 234,
+      "Į": 235,
+      "į": 236,
+      "İ": 237,
+      "ı": 238,
+      "Ĳ": 239,
+      "ĳ": 240,
+      "Ĵ": 241,
+      "ĵ": 242,
+      "Ķ": 243,
+      "ķ": 244,
+      "ĸ": 245,
+      "Ĺ": 246,
+      "ĺ": 247,
+      "Ļ": 248,
+      "ļ": 249,
+      "Ľ": 250,
+      "ľ": 251,
+      "Ŀ": 252,
+      "ŀ": 253,
+      "Ł": 254,
+      "ł": 255,
+      "Ń": 256,
+      "Ġt": 257,
+      "Ġa": 258,
+      "in": 259,
+      "he": 260,
+      "on": 261,
+      "ti": 262,
+      "re": 263,
+      "Ġthe": 264,
+      "er": 265,
+      "Ġc": 266,
+      "nd": 267,
+      "es": 268,
+      "Ġo": 269,
+      "Ġs": 270,
+      "tion": 271,
+      "en": 272,
+      "al": 273,
+      "or": 274,
+      "is": 275,
+      "at": 276,
+      "ing": 277,
+      "Ġand": 278,
+      "ĠĠ": 279,
+      "Ġp": 280,
+      "an": 281,
+      "Ġin": 282,
+      "le": 283,
+      "it": 284,
+      "Ġof": 285,
+      "Ġf": 286,
+      "ro": 287,
+      "Ġd": 288,
+      "Ġm": 289,
+      "ic": 290,
+      "Ġw": 291,
+      "Ġto": 292,
+      "ec": 293,
+      "ar": 294,
+      "ed": 295,
+      "Ġb": 296,
+      "us": 297,
+      "Ġe": 298,
+      "ation": 299,
+      "ent": 300,
+      "mp": 301,
+      "Ġre": 302,
+      "lo": 303,
+      "as": 304,
+      "ac": 305,
+      "ve": 306,
+      "Ġis": 307,
+      "Ġco": 308,
+      "st": 309,
+      "Ġth": 310,
+      "et": 311,
+      "ou": 312,
+      "##": 313,
+      "ĠT": 314,
+      "Ġpro": 315,
+      "de": 316,
+      "Ġn": 317,
+      "ment": 318,
+      "Ġcon": 319,
+      "uc": 320,
+      "ul": 321,
+      "il": 322,
+      "Ġh": 323,
+      "ol": 324,
+      "ce": 325,
+      "ig": 326,
+      "Ġus": 327,
+      "ut": 328,
+      "Ġfor": 329,
+      "Ġst": 330,
+      "Ġcan": 331,
+      "``": 332,
+      "ter": 333,
+      "Ġex": 334,
+      "un": 335,
+      "ĠĠĠ": 336,
+      "am": 337,
+      "ate": 338,
+      "ur": 339,
+      "qu": 340,
+      "Ġv": 341,
+      "Ġ`": 342,
+      "Ġi": 343,
+      "Ġas": 344,
+      "ab": 345,
+      "Ġal": 346,
+      "ly": 347,
+      "Ġbe": 348,
+      "Ġthat": 349,
+      "se": 350,
+      "ĠS": 351,
+      "si": 352,
+      "ith": 353,
+      "In": 354,
+      "ĠC": 355,
+      "Ġl": 356,
+      "ge": 357,
+      "em": 358,
+      "ity": 359,
+      "Ġan": 360,
+      "ess": 361,
+      "vi": 362,
+      "Ġde": 363,
+      "ts": 364,
+      "res": 365,
+      "ri": 366,
+      "pp": 367,
+      "Ġmo": 368,
+      "Ġy": 369,
+      "Ġg": 370,
+      "Ġare": 371,
+      "ers": 372,
+      "ff": 373,
+      "Ġit": 374,
+      "and": 375,
+      "um": 376,
+      "om": 377,
+      "ations": 378,
+      "ot": 379,
+      "ap": 380,
+      "tic": 381,
+      "mple": 382,
+      "ĠThe": 383,
+      "Ġwe": 384,
+      "Ġyou": 385,
+      "ĠA": 386,
+      "Ġon": 387,
+      "Ġ-": 388,
+      "Ġor": 389,
+      "ver": 390,
+      "ain": 391,
+      "Ġwith": 392,
+      "im": 393,
+      "ir": 394,
+      "ction": 395,
+      "ection": 396,
+      "ow": 397,
+      "Ġ[": 398,
+      "ign": 399,
+      "ay": 400,
+      "ad": 401,
+      "ure": 402,
+      "yst": 403,
+      "iz": 404,
+      "ect": 405,
+      "Ġen": 406,
+      "ĠE": 407,
+      "her": 408,
+      "per": 409,
+      "ystem": 410,
+      "el": 411,
+      "```": 412,
+      "ine": 413,
+      "ort": 414,
+      "his": 415,
+      "low": 416,
+      "](": 417,
+      "od": 418,
+      "](#": 419,
+      "ĠP": 420,
+      "Ġch": 421,
+      "Ġ=": 422,
+      "ĠI": 423,
+      "ĠĠĠĠ": 424,
+      "ant": 425,
+      "lic": 426,
+      "ial": 427,
+      "Ġimp": 428,
+      "ren": 429,
+      "ĠThis": 430,
+      "for": 431,
+      "ill": 432,
+      "Ġapp": 433,
+      "Ġdi": 434,
+      "ch": 435,
+      "unction": 436,
+      "th": 437,
+      "cess": 438,
+      "age": 439,
+      "ak": 440,
+      "ĠD": 441,
+      "Ġsystem": 442,
+      "ari": 443,
+      "duc": 444,
+      "Ġcont": 445,
+      "ech": 446,
+      "ata": 447,
+      "cl": 448,
+      "Ġint": 449,
+      "ance": 450,
+      "ise": 451,
+      "ub": 452,
+      "Ġcomp": 453,
+      "if": 454,
+      "Ġu": 455,
+      "able": 456,
+      "form": 457,
+      "Ġcom": 458,
+      "Ġthis": 459,
+      "ĠM": 460,
+      "tive": 461,
+      "ruc": 462,
+      "Ġr": 463,
+      "so": 464,
+      "ave": 465,
+      "Ġfunction": 466,
+      "Ġ(": 467,
+      "ĠF": 468,
+      "ud": 469,
+      "Ġused": 470,
+      "ĠR": 471,
+      "Ġad": 472,
+      "gr": 473,
+      "ĠIn": 474,
+      "Ġres": 475,
+      "Ġsuc": 476,
+      "Ġwill": 477,
+      "Ġby": 478,
+      "erc": 479,
+      "id": 480,
+      "alu": 481,
+      "Ġle": 482,
+      "act": 483,
+      "Ġne": 484,
+      "ist": 485,
+      "Ġwh": 486,
+      "ĠB": 487,
+      "'s": 488,
+      "ct": 489,
+      "ĠW": 490,
+      "all": 491,
+      "xerc": 492,
+      "ical": 493,
+      "nder": 494,
+      "Ġtr": 495,
+      "ion": 496,
+      "enti": 497,
+      "Ġexa": 498,
+      "Ġdata": 499,
+      "igh": 500,
+      "Ġvari": 501,
+      "yp": 502,
+      "ater": 503,
+      "Ġuse": 504,
+      "ous": 505,
+      "Ġsuch": 506,
+      "Ġhave": 507,
+      "rin": 508,
+      "Ġcomm": 509,
+      "ble": 510,
+      "Ġdes": 511,
+      "ution": 512,
+      "Ġsp": 513,
+      "echn": 514,
+      "ach": 515,
+      "Ġac": 516,
+      "ip": 517,
+      "rom": 518,
+      "###": 519,
+      "ments": 520,
+      "Ġalso": 521,
+      "ges": 522,
+      "xercise": 523,
+      "red": 524,
+      "Ġexample": 525,
+      "tim": 526,
+      "ors": 527,
+      "ics": 528,
+      "Ġexp": 529,
+      "eren": 530,
+      "les": 531,
+      "di": 532,
+      "Ġse": 533,
+      "ile": 534,
+      "ass": 535,
+      "eth": 536,
+      "xt": 537,
+      "log": 538,
+      "velo": 539,
+      "ethod": 540,
+      "Ġyour": 541,
+      "The": 542,
+      "ork": 543,
+      "ies": 544,
+      "apter": 545,
+      "Ġtheir": 546,
+      "hen": 547,
+      "Ġeff": 548,
+      "ust": 549,
+      "est": 550,
+      "ĠO": 551,
+      "ame": 552,
+      "Ġprocess": 553,
+      "Ġdiff": 554,
+      "stand": 555,
+      "Ġvalu": 556,
+      "Ġunder": 557,
+      "op": 558,
+      "Ġop": 559,
+      "ĠH": 560,
+      "velop": 561,
+      "del": 562,
+      "ties": 563,
+      "Ġprovi": 564,
+      "Ġdis": 565,
+      "ms": 566,
+      "ther": 567,
+      "Ġcode": 568,
+      "Ġpar": 569,
+      "ron": 570,
+      "Ġtechn": 571,
+      "ich": 572,
+      "Ġk": 573,
+      "os": 574,
+      "ack": 575,
+      "Ġfrom": 576,
+      "Ġ'": 577,
+      "sion": 578,
+      "Ġusing": 579,
+      "yn": 580,
+      "ans": 581,
+      "Ġmethod": 582,
+      "te": 583,
+      "Ġhe": 584,
+      "Ġ\"": 585,
+      "etw": 586,
+      "put": 587,
+      "umb": 588,
+      "Ġele": 589,
+      "Ġwhich": 590,
+      "ase": 591,
+      "ĠĠĠĠĠ": 592,
+      "ated": 593,
+      "iqu": 594,
+      "der": 595,
+      "Ġcl": 596,
+      "ility": 597,
+      "olution": 598,
+      "ĠL": 599,
+      "ĠIt": 600,
+      "Ġat": 601,
+      "lications": 602,
+      "Ġdifferen": 603,
+      "Ġdesign": 604,
+      ":-": 605,
+      "ces": 606,
+      "Ġro": 607,
+      "Ġits": 608,
+      "ult": 609,
+      "oc": 610,
+      "Ġallow": 611,
+      "ĠĠĠĠĠĠĠ": 612,
+      "are": 613,
+      "Ġsystems": 614,
+      "aly": 615,
+      "Ġper": 616,
+      "tions": 617,
+      "Ġsh": 618,
+      "Ġinter": 619,
+      "Ġhas": 620,
+      "Ġar": 621,
+      "ves": 622,
+      "gor": 623,
+      "ating": 624,
+      "Ġtyp": 625,
+      "Ġunderstand": 626,
+      "cep": 627,
+      "Ġcre": 628,
+      "Ġpl": 629,
+      "ence": 630,
+      "ld": 631,
+      "gram": 632,
+      "Ġdevelop": 633,
+      "####": 634,
+      "ory": 635,
+      "our": 636,
+      "Ġmore": 637,
+      "ject": 638,
+      "Ġman": 639,
+      "Ġsc": 640,
+      "Ġincl": 641,
+      "',": 642,
+      "ization": 643,
+      "ruct": 644,
+      "gorith": 645,
+      "Ġimport": 646,
+      "ll": 647,
+      "ace": 648,
+      "Ġqu": 649,
+      "Ġinto": 650,
+      "ĠG": 651,
+      "Ġthese": 652,
+      "ific": 653,
+      "rint": 654,
+      "ug": 655,
+      "ary": 656,
+      "rib": 657,
+      "ential": 658,
+      "ents": 659,
+      "ual": 660,
+      "Ġmak": 661,
+      "Ġmodel": 662,
+      "Ġdifferent": 663,
+      "ures": 664,
+      "Ġob": 665
+    },
+    "merges": [
+      "Ġ t",
+      "Ġ a",
+      "i n",
+      "h e",
+      "o n",
+      "t i",
+      "r e",
+      "Ġt he",
+      "e r",
+      "Ġ c",
+      "n d",
+      "e s",
+      "Ġ o",
+      "Ġ s",
+      "ti on",
+      "e n",
+      "a l",
+      "o r",
+      "i s",
+      "a t",
+      "in g",
+      "Ġa nd",
+      "Ġ Ġ",
+      "Ġ p",
+      "a n",
+      "Ġ in",
+      "l e",
+      "i t",
+      "Ġo f",
+      "Ġ f",
+      "r o",
+      "Ġ d",
+      "Ġ m",
+      "i c",
+      "Ġ w",
+      "Ġt o",
+      "e c",
+      "a r",
+      "e d",
+      "Ġ b",
+      "u s",
+      "Ġ e",
+      "a tion",
+      "en t",
+      "m p",
+      "Ġ re",
+      "l o",
+      "a s",
+      "a c",
+      "v e",
+      "Ġ is",
+      "Ġc o",
+      "s t",
+      "Ġt h",
+      "e t",
+      "o u",
+      "# #",
+      "Ġ T",
+      "Ġp ro",
+      "d e",
+      "Ġ n",
+      "m ent",
+      "Ġc on",
+      "u c",
+      "u l",
+      "i l",
+      "Ġ h",
+      "o l",
+      "c e",
+      "i g",
+      "Ġ us",
+      "u t",
+      "Ġf or",
+      "Ġs t",
+      "Ġc an",
+      "` `",
+      "t er",
+      "Ġe x",
+      "u n",
+      "ĠĠ Ġ",
+      "a m",
+      "at e",
+      "u r",
+      "q u",
+      "Ġ v",
+      "Ġ `",
+      "Ġ i",
+      "Ġa s",
+      "a b",
+      "Ġa l",
+      "l y",
+      "Ġb e",
+      "Ġth at",
+      "s e",
+      "Ġ S",
+      "s i",
+      "it h",
+      "I n",
+      "Ġ C",
+      "Ġ l",
+      "g e",
+      "e m",
+      "it y",
+      "Ġa n",
+      "es s",
+      "v i",
+      "Ġd e",
+      "t s",
+      "re s",
+      "r i",
+      "p p",
+      "Ġm o",
+      "Ġ y",
+      "Ġ g",
+      "Ġa re",
+      "er s",
+      "f f",
+      "Ġ it",
+      "a nd",
+      "u m",
+      "o m",
+      "ation s",
+      "o t",
+      "a p",
+      "ti c",
+      "mp le",
+      "ĠT he",
+      "Ġw e",
+      "Ġy ou",
+      "Ġ A",
+      "Ġ on",
+      "Ġ -",
+      "Ġo r",
+      "v er",
+      "a in",
+      "Ġw ith",
+      "i m",
+      "i r",
+      "c tion",
+      "ec tion",
+      "o w",
+      "Ġ [",
+      "ig n",
+      "a y",
+      "a d",
+      "u re",
+      "y st",
+      "i z",
+      "ec t",
+      "Ġ en",
+      "Ġ E",
+      "he r",
+      "p er",
+      "yst em",
+      "e l",
+      "`` `",
+      "in e",
+      "or t",
+      "h is",
+      "lo w",
+      "] (",
+      "o d",
+      "]( #",
+      "Ġ P",
+      "Ġc h",
+      "Ġ =",
+      "Ġ I",
+      "ĠĠ ĠĠ",
+      "an t",
+      "l ic",
+      "i al",
+      "Ġi mp",
+      "re n",
+      "ĠT his",
+      "f or",
+      "il l",
+      "Ġa pp",
+      "Ġd i",
+      "c h",
+      "un ction",
+      "t h",
+      "c ess",
+      "a ge",
+      "a k",
+      "Ġ D",
+      "Ġs ystem",
+      "ar i",
+      "d uc",
+      "Ġcon t",
+      "ec h",
+      "at a",
+      "c l",
+      "Ġin t",
+      "an ce",
+      "is e",
+      "u b",
+      "Ġco mp",
+      "i f",
+      "Ġ u",
+      "ab le",
+      "for m",
+      "Ġco m",
+      "Ġth is",
+      "Ġ M",
+      "ti ve",
+      "r uc",
+      "Ġ r",
+      "s o",
+      "a ve",
+      "Ġf unction",
+      "Ġ (",
+      "Ġ F",
+      "u d",
+      "Ġus ed",
+      "Ġ R",
+      "Ġa d",
+      "g r",
+      "Ġ In",
+      "Ġre s",
+      "Ġs uc",
+      "Ġw ill",
+      "Ġb y",
+      "er c",
+      "i d",
+      "al u",
+      "Ġ le",
+      "ac t",
+      "Ġn e",
+      "is t",
+      "Ġw h",
+      "Ġ B",
+      "' s",
+      "c t",
+      "Ġ W",
+      "al l",
+      "x erc",
+      "ic al",
+      "nd er",
+      "Ġt r",
+      "i on",
+      "en ti",
+      "Ġex a",
+      "Ġd ata",
+      "ig h",
+      "Ġv ari",
+      "y p",
+      "at er",
+      "Ġus e",
+      "o us",
+      "Ġsuc h",
+      "Ġh ave",
+      "r in",
+      "Ġcom m",
+      "b le",
+      "Ġd es",
+      "u tion",
+      "Ġs p",
+      "ech n",
+      "ac h",
+      "Ġa c",
+      "i p",
+      "ro m",
+      "## #",
+      "ment s",
+      "Ġal so",
+      "g es",
+      "xerc ise",
+      "re d",
+      "Ġexa mple",
+      "ti m",
+      "or s",
+      "ic s",
+      "Ġex p",
+      "e ren",
+      "l es",
+      "d i",
+      "Ġs e",
+      "i le",
+      "as s",
+      "et h",
+      "x t",
+      "lo g",
+      "ve lo",
+      "eth od",
+      "Ġyou r",
+      "T he",
+      "or k",
+      "i es",
+      "ap ter",
+      "Ġthe ir",
+      "he n",
+      "Ġe ff",
+      "us t",
+      "es t",
+      "Ġ O",
+      "am e",
+      "Ġpro cess",
+      "Ġdi ff",
+      "st and",
+      "Ġv alu",
+      "Ġu nder",
+      "o p",
+      "Ġo p",
+      "Ġ H",
+      "velo p",
+      "de l",
+      "ti es",
+      "Ġpro vi",
+      "Ġd is",
+      "m s",
+      "t her",
+      "Ġco de",
+      "Ġp ar",
+      "r on",
+      "Ġt echn",
+      "ic h",
+      "Ġ k",
+      "o s",
+      "ac k",
+      "Ġf rom",
+      "Ġ '",
+      "si on",
+      "Ġus ing",
+      "y n",
+      "an s",
+      "Ġm ethod",
+      "t e",
+      "Ġ he",
+      "Ġ \"",
+      "et w",
+      "p ut",
+      "um b",
+      "Ġe le",
+      "Ġwh ich",
+      "as e",
+      "ĠĠ ĠĠĠ",
+      "at ed",
+      "i qu",
+      "d er",
+      "Ġc l",
+      "il ity",
+      "ol ution",
+      "Ġ L",
+      "ĠI t",
+      "Ġa t",
+      "lic ations",
+      "Ġdiff eren",
+      "Ġdes ign",
+      ": -",
+      "c es",
+      "Ġ ro",
+      "Ġit s",
+      "ul t",
+      "o c",
+      "Ġal low",
+      "ĠĠĠĠ ĠĠĠ",
+      "a re",
+      "Ġsystem s",
+      "al y",
+      "Ġp er",
+      "tion s",
+      "Ġs h",
+      "Ġin ter",
+      "Ġh as",
+      "Ġa r",
+      "v es",
+      "g or",
+      "at ing",
+      "Ġt yp",
+      "Ġunder stand",
+      "ce p",
+      "Ġc re",
+      "Ġp l",
+      "en ce",
+      "l d",
+      "gr am",
+      "Ġde velop",
+      "## ##",
+      "or y",
+      "ou r",
+      "Ġmo re",
+      "j ect",
+      "Ġm an",
+      "Ġs c",
+      "Ġin cl",
+      "' ,",
+      "iz ation",
+      "ruc t",
+      "gor ith",
+      "Ġimp ort",
+      "l l",
+      "ac e",
+      "Ġ qu",
+      "Ġint o",
+      "Ġ G",
+      "Ġthe se",
+      "if ic",
+      "rin t",
+      "u g",
+      "ar y",
+      "ri b",
+      "enti al",
+      "ent s",
+      "u al",
+      "Ġm ak",
+      "Ġmo del",
+      "Ġdifferen t",
+      "u res",
+      "Ġo b"
+    ]
+  }
+}

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,19 @@

+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|void|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|void|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|void|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|void|>",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<|void|>"
+}