tokenizer.json

{
  "version": "1.0",
  "truncation": null,
  "padding": null,
  "added_tokens": [
    {
      "id": 0,
      "content": "<unk>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": true,
      "special": true
    },
    {
      "id": 1,
      "content": "<|start_story|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": true,
      "special": true
    },
    {
      "id": 2,
      "content": "<|end_story|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": true,
      "special": true
    }
  ],
  "normalizer": {
    "type": "Sequence",
    "normalizers": [
      {
        "type": "Prepend",
        "prepend": "▁"
      },
      {
        "type": "Replace",
        "pattern": {
          "String": " "
        },
        "content": "▁"
      }
    ]
  },
  "pre_tokenizer": null,
  "post_processor": {
    "type": "TemplateProcessing",
    "single": [
      {
        "SpecialToken": {
          "id": "<|start_story|>",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      }
    ],
    "pair": [
      {
        "SpecialToken": {
          "id": "<|start_story|>",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      },
      {
        "SpecialToken": {
          "id": "<|start_story|>",
          "type_id": 1
        }
      },
      {
        "Sequence": {
          "id": "B",
          "type_id": 1
        }
      }
    ],
    "special_tokens": {
      "<|start_story|>": {
        "id": "<|start_story|>",
        "ids": [
          1
        ],
        "tokens": [
          "<|start_story|>"
        ]
      }
    }
  },
  "decoder": {
    "type": "Sequence",
    "decoders": [
      {
        "type": "Replace",
        "pattern": {
          "String": "▁"
        },
        "content": " "
      },
      {
        "type": "ByteFallback"
      },
      {
        "type": "Fuse"
      },
      {
        "type": "Strip",
        "content": " ",
        "start": 1,
        "stop": 0
      }
    ]
  },
  "model": {
    "type": "BPE",
    "dropout": null,
    "unk_token": "<unk>",
    "continuing_subword_prefix": null,
    "end_of_word_suffix": null,
    "fuse_unk": true,
    "byte_fallback": true,
    "ignore_merges": false,
    "vocab": {
      "<unk>": 0,
      "<|start_story|>": 1,
      "<|end_story|>": 2,
      "\n": 3,
      "!": 4,
      "\"": 5,
      "$": 6,
      "'": 7,
      ",": 8,
      "-": 9,
      ".": 10,
      "0": 11,
      "1": 12,
      "2": 13,
      "3": 14,
      "4": 15,
      "5": 16,
      "6": 17,
      "7": 18,
      "8": 19,
      "9": 20,
      ":": 21,
      ";": 22,
      "<": 23,
      ">": 24,
      "?": 25,
      "A": 26,
      "B": 27,
      "C": 28,
      "D": 29,
      "E": 30,
      "F": 31,
      "G": 32,
      "H": 33,
      "I": 34,
      "J": 35,
      "K": 36,
      "L": 37,
      "M": 38,
      "N": 39,
      "O": 40,
      "P": 41,
      "Q": 42,
      "R": 43,
      "S": 44,
      "T": 45,
      "U": 46,
      "V": 47,
      "W": 48,
      "X": 49,
      "Y": 50,
      "Z": 51,
      "_": 52,
      "a": 53,
      "b": 54,
      "c": 55,
      "d": 56,
      "e": 57,
      "f": 58,
      "g": 59,
      "h": 60,
      "i": 61,
      "j": 62,
      "k": 63,
      "l": 64,
      "m": 65,
      "n": 66,
      "o": 67,
      "p": 68,
      "q": 69,
      "r": 70,
      "s": 71,
      "t": 72,
      "u": 73,
      "v": 74,
      "w": 75,
      "x": 76,
      "y": 77,
      "z": 78,
      "|": 79,
      "▁": 80,
      "e▁": 81,
      "d▁": 82,
      "th": 83,
      ".▁": 84,
      "▁a": 85,
      "t▁": 86,
      "y▁": 87,
      "to": 88,
      "s▁": 89,
      "nd▁": 90,
      "er": 91,
      "ed▁": 92,
      "the▁": 93,
      ",▁": 94,
      "wa": 95,
      "in": 96,
      "he▁": 97,
      "to▁": 98,
      "ou": 99,
      "▁and▁": 100,
      "ar": 101,
      "en": 102,
      ".▁T": 103,
      "▁a▁": 104,
      "ha": 105,
      "om": 106,
      "sa": 107,
      "▁the▁": 108,
      "he": 109,
      "im": 110,
      "on": 111,
      "g▁": 112,
      "ll": 113,
      "st": 114,
      "was▁": 115,
      "an": 116,
      "or": 117,
      "ay": 118,
      "it": 119,
      "er▁": 120,
      "id": 121,
      ".\n": 122,
      "re": 123,
      "is▁": 124,
      "pl": 125,
      "ir": 126,
      "am": 127,
      "ed▁to▁": 128,
      "il": 129,
      "wi": 130,
      "the": 131,
      "ri": 132,
      "lo": 133,
      "a▁": 134,
      "and▁": 135,
      ".▁H": 136,
      "hey▁": 137,
      ".▁S": 138,
      "o▁": 139,
      ".▁He▁": 140,
      "▁h": 141,
      "no": 142,
      "at▁": 143,
      ".▁They▁": 144,
      "ere▁": 145,
      "with": 146,
      "On": 147,
      "un": 148,
      "ing▁": 149,
      "ver": 150,
      "pp": 151,
      ".▁The▁": 152,
      "\"▁": 153,
      "ck": 154,
      "ry": 155,
      "bi": 156,
      "art": 157,
      "li": 158,
      "ll▁": 159,
      ",▁\"": 160,
      "le": 161,
      "sto": 162,
      ".▁She▁": 163,
      "be": 164,
      "day": 165,
      "start": 166,
      "it▁": 167,
      "ut▁": 168,
      "sh": 169,
      "om▁": 170,
      "ok": 171,
      "w▁": 172,
      "you": 173,
      "said": 174,
      "ma": 175,
      "ing": 176,
      "le▁": 177,
      "se": 178,
      "bo": 179,
      "ld▁": 180,
      "happ": 181,
      "im▁": 182,
      "end": 183,
      "fri": 184,
      "do": 185,
      "gh": 186,
      "of": 187,
      "ba": 188,
      "up": 189,
      "ay▁": 190,
      "ch": 191,
      "ed": 192,
      "very▁": 193,
      "an▁": 194,
      "ne": 195,
      "for": 196,
      "was": 197,
      "had▁": 198,
      "wan": 199,
      "l▁": 200,
      "ce▁": 201,
      "big▁": 202,
      "en▁": 203,
      "said,▁\"": 204,
      "story": 205,
      "friend": 206,
      "itt": 207,
      "<|": 208,
      "_story": 209,
      "|>": 210,
      "▁<|": 211,
      "start_story": 212,
      "▁<|start_story": 213,
      "▁<|start_story|>": 214,
      "e,▁": 215,
      "Lil": 216,
      "they▁": 217,
      "ve▁": 218,
      "ro": 219,
      "play": 220,
      "not▁": 221,
      ".▁I": 222,
      "One▁": 223,
      "ge": 224,
      "ittle▁": 225,
      "was▁a▁": 226,
      "ke▁": 227,
      "'s▁": 228,
      "little▁": 229,
      "tim": 230,
      "his▁": 231,
      "at": 232,
      "es": 233,
      "that▁": 234,
      "One▁day": 235,