tokenizer.json

{
  "version": "1.0",
  "truncation": null,
  "padding": {
    "strategy": "BatchLongest",
    "direction": "Right",
    "pad_to_multiple_of": null,
    "pad_id": 2,
    "pad_type_id": 0,
    "pad_token": " "
  },
  "added_tokens": [
    {
      "id": 0,
      "content": "^",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 1,
      "content": "_",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 2,
      "content": " ",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 3,
      "content": "§",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 4,
      "content": "°",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": null,
  "pre_tokenizer": null,
  "post_processor": {
    "type": "TemplateProcessing",
    "single": [
      {
        "SpecialToken": {
          "id": "^",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      },
      {
        "SpecialToken": {
          "id": "_",
          "type_id": 0
        }
      }
    ],
    "pair": [
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "B",
          "type_id": 1
        }
      }
    ],
    "special_tokens": {
      "^": {
        "id": "^",
        "ids": [
          0
        ],
        "tokens": [
          "^"
        ]
      },
      "_": {
        "id": "_",
        "ids": [
          1
        ],
        "tokens": [
          "_"
        ]
      }
    }
  },
  "decoder": {
    "type": "WordPiece",
    "prefix": "##",
    "cleanup": false
  },
  "model": {
    "type": "WordPiece",
    "unk_token": "§",
    "continuing_subword_prefix": "##",
    "max_input_chars_per_word": 1024,
    "vocab": {
      "^": 0,
      "_": 1,
      " ": 2,
      "§": 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,
      "B": 22,
      "C": 23,
      "F": 24,
      "H": 25,
      "I": 26,
      "N": 27,
      "O": 28,
      "P": 29,
      "S": 30,
      "[": 31,
      "]": 32,
      "b": 33,
      "c": 34,
      "e": 35,
      "i": 36,
      "l": 37,
      "n": 38,
      "o": 39,
      "p": 40,
      "r": 41,
      "s": 42,
      "##c": 43,
      "##1": 44,
      "##(": 45,
      "##C": 46,
      "##=": 47,
      "##2": 48,
      "##O": 49,
      "##)": 50,
      "##n": 51,
      "##-": 52,
      "##l": 53,
      "##N": 54,
      "##S": 55,
      "##3": 56,
      "##[": 57,
      "##H": 58,
      "##]": 59,
      "##+": 60,
      "##o": 61,
      "##F": 62,
      "##4": 63,
      "##B": 64,
      "###": 65,
      "##r": 66,
      "##I": 67,
      "##s": 68,
      "##5": 69,
      "##P": 70,
      "##6": 71,
      "##e": 72,
      "##7": 73,
      "##i": 74,
      "##8": 75,
      "##9": 76,
      "##p": 77,
      "##%": 78,
      "##0": 79,
      "##b": 80,
      "##cc": 81,
      "##CC": 82,
      "##O)": 83,
      "##C(": 84,
      "##c1": 85,
      "##=O)": 86,
      "##c(": 87,
      "##c2": 88,
      "##C)": 89,
      "##c1cc": 90,
      "##C(=O)": 91,
      "##c3": 92,
      "##c2cc": 93,
      "##)cc": 94,
      "##(=O)": 95,
      "##C1": 96,
      "##c1ccc(": 97,
      "##(C)": 98,
      "##c3cc": 99,
      "##2)": 100,
      "##F)": 101,
      "##CCCC": 102,
      "##C(=O)N": 103,
      "##c1cccc": 104,
      "##C2": 105,
      "##c2cccc": 106,
      "##CN": 107,
      "##Cl": 108,
      "##C(C)": 109,
      "##cn": 110,
      "##)cc1": 111,
      "##c4": 112,
      "##CCN": 113,
      "##3)": 114,
      "CO": 115,
      "##=C(": 116,
      "##n1": 117,
      "##c2ccccc2": 118,
      "##nc(": 119,
      "##c2ccc(": 120,
      "##c1ccccc1": 121,
      "##CC1": 122,
      "##CO": 123,
      "##c3cccc": 124,
      "##[n": 125,
      "##NC(=O)": 126,
      "##N)": 127,
      "##H]": 128,
      "##[nH]": 129,
      "##S(=O)": 130,
      "##(C": 131,
      "##S(=O)(=O)": 132,
      "##Cl)": 133,
      "O=C(": 134,
      "##(F)": 135,
      "##c3ccccc3": 136,
      "##OC)": 137,
      "##CC(=O)": 138,
      "##C3": 139,
      "##cccc": 140,
      "##CC(": 141,
      "##n2": 142,
      "##c1cc(": 143,
      "##c2c(": 144,
      "##c1n": 145,
      "##c3ccc(": 146,
      "##cc1": 147,
      "##CCN(": 148,
      "##N1": 149,
      "##CCO": 150,
      "##C(F)": 151,
      "##CC2": 152,
      "##F)cc": 153,
      "##c2)": 154,
      "##cc(": 155,
      "##c2ccccc2)": 156,
      "##c2n": 157,
      "##C(F)(F)": 158,
      "##C(O)": 159,
      "##Cl)cc": 160,
      "##C=": 161,
      "##c(=O)": 162,
      "##+]": 163,
      "##c1cccc(": 164,
      "##4)": 165,
      "##OC": 166,
      "COc1ccc(": 167,
      "##c1)": 168,
      "##=N": 169,
      "##C(C": 170,
      "##=O": 171,
      "##c2cc(": 172,
      "##N2": 173,
      "##CCCN": 174,
      "##c(-": 175,
      "##-]": 176,
      "CC(C)": 177,
      "##[N": 178,
      "##O-]": 179,
      "##[O-]": 180
    }
  }
}