tokenizer.json

{
  "version": "1.0",
  "truncation": null,
  "padding": null,
  "added_tokens": [
    {
      "id": 0,
      "content": "<pad>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": {
    "type": "Lowercase"
  },
  "pre_tokenizer": {
    "type": "Split",
    "pattern": {
      "Regex": "."
    },
    "behavior": "Isolated",
    "invert": false
  },
  "post_processor": null,
  "decoder": null,
  "model": {
    "type": "WordLevel",
    "vocab": {
      "\n": 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,
      "A": 32,
      "B": 33,
      "C": 34,
      "D": 35,
      "E": 36,
      "F": 37,
      "G": 38,
      "H": 39,
      "I": 40,
      "J": 41,
      "K": 42,
      "L": 43,
      "M": 44,
      "N": 45,
      "O": 46,
      "P": 47,
      "Q": 48,
      "R": 49,
      "S": 50,
      "T": 51,
      "U": 52,
      "V": 53,
      "W": 54,
      "X": 55,
      "Y": 56,
      "Z": 57,
      "[": 58,
      "\\": 59,
      "]": 60,
      "_": 61,
      "a": 62,
      "b": 63,
      "c": 64,
      "d": 65,
      "e": 66,
      "f": 67,
      "g": 68,
      "h": 69,
      "i": 70,
      "j": 71,
      "k": 72,
      "l": 73,
      "m": 74,
      "n": 75,
      "o": 76,
      "p": 77,
      "q": 78,
      "r": 79,
      "s": 80,
      "t": 81,
      "u": 82,
      "v": 83,
      "w": 84,
      "x": 85,
      "y": 86,
      "z": 87,
      "{": 88,
      "}": 89,
      "<pad>": 0
    },
    "unk_token": "<pad>"
  }
}