tokenizer.json

{
  "version": "1.0",
  "truncation": {
    "direction": "Right",
    "max_length": 100,
    "strategy": "LongestFirst",
    "stride": 0
  },
  "padding": null,
  "added_tokens": [
    {
      "id": 0,
      "content": "<pad>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 1,
      "content": "<s>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 2,
      "content": "</s>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 3,
      "content": "<unk>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": {
    "type": "Sequence",
    "normalizers": [
      {
        "type": "Replace",
        "pattern": {
          "String": " "
        },
        "content": ""
      },
      {
        "type": "Replace",
        "pattern": {
          "String": "ſ"
        },
        "content": "s"
      },
      {
        "type": "Replace",
        "pattern": {
          "String": "aͤ"
        },
        "content": "ä"
      },
      {
        "type": "Replace",
        "pattern": {
          "String": "oͤ"
        },
        "content": "ö"
      },
      {
        "type": "Replace",
        "pattern": {
          "String": "uͤ"
        },
        "content": "ü"
      }
    ]
  },
  "pre_tokenizer": null,
  "post_processor": {
    "type": "RobertaProcessing",
    "sep": [
      "</s>",
      2
    ],
    "cls": [
      "<s>",
      1
    ],
    "trim_offsets": true,
    "add_prefix_space": true
  },
  "decoder": {
    "type": "BPEDecoder",
    "suffix": "</w>"
  },
  "model": {
    "type": "BPE",
    "dropout": null,
    "unk_token": "<unk>",
    "continuing_subword_prefix": null,
    "end_of_word_suffix": null,
    "fuse_unk": false,
    "byte_fallback": false,
    "ignore_merges": false,
    "vocab": {
      "<pad>": 0,
      "<s>": 1,
      "</s>": 2,
      "<unk>": 3,
      "!": 4,
      "&": 5,
      "'": 6,
      "(": 7,
      ")": 8,
      "*": 9,
      ",": 10,
      "-": 11,
      ".": 12,
      "0": 13,
      "1": 14,
      "2": 15,
      "3": 16,
      "4": 17,
      "5": 18,
      "6": 19,
      "7": 20,
      "8": 21,
      "9": 22,
      ":": 23,
      ";": 24,
      "=": 25,
      ">": 26,
      "?": 27,
      "A": 28,
      "B": 29,
      "C": 30,
      "D": 31,
      "E": 32,
      "F": 33,
      "G": 34,
      "H": 35,
      "I": 36,
      "J": 37,
      "K": 38,
      "L": 39,
      "M": 40,
      "N": 41,
      "O": 42,
      "P": 43,
      "Q": 44,
      "R": 45,
      "S": 46,
      "T": 47,
      "U": 48,
      "V": 49,
      "W": 50,
      "X": 51,
      "Y": 52,
      "Z": 53,
      "[": 54,
      "a": 55,
      "b": 56,
      "c": 57,
      "d": 58,
      "e": 59,
      "f": 60,
      "g": 61,
      "h": 62,
      "i": 63,
      "j": 64,
      "k": 65,
      "l": 66,
      "m": 67,
      "n": 68,
      "o": 69,
      "p": 70,
      "q": 71,
      "r": 72,
      "s": 73,
      "t": 74,
      "u": 75,
      "v": 76,
      "w": 77,
      "x": 78,
      "y": 79,
      "z": 80,
      "«": 81,
      "°": 82,
      "»": 83,
      "½": 84,
      "Ä": 85,
      "Ç": 86,
      "É": 87,
      "Ö": 88,
      "Ü": 89,
      "ß": 90,
      "à": 91,
      "â": 92,
      "ä": 93,
      "ç": 94,
      "è": 95,
      "é": 96,
      "ê": 97,
      "ë": 98,
      "î": 99,
      "ñ": 100,
      "ô": 101,
      "ö": 102,
      "û": 103,
      "ü": 104,
      "ē": 105,
      "ĕ": 106,
      "‒": 107,
      "–": 108,
      "—": 109,
      "‘": 110,
      "’": 111,
      "‚": 112,
      "‛": 113,
      "“": 114,
      "”": 115,
      "„": 116,
      "″": 117,
      "⁊": 118,
      "▁": 119,
      "░": 120,
      "ꝛ": 121
    },
    "merges": []
  }
}