{
  "version": "1.0",
  "truncation": null,
  "padding": null,
  "added_tokens": [
    {
      "id": 0,
      "special": true,
      "content": "[PAD]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false
    },
    {
      "id": 1,
      "special": true,
      "content": "[UNK]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false
    },
    {
      "id": 2,
      "special": true,
      "content": "[CLS]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false
    },
    {
      "id": 3,
      "special": true,
      "content": "[SEP]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false
    },
    {
      "id": 4,
      "special": true,
      "content": "[MASK]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false
    }
  ],
  "normalizer": {
    "type": "BertNormalizer",
    "clean_text": true,
    "handle_chinese_chars": true,
    "strip_accents": true,
    "lowercase": false
  },
  "pre_tokenizer": {
    "type": "Sequence",
    "pretokenizers": [
      {
        "type": "WhitespaceSplit"
      },
      {
        "type": "Split",
        "pattern": {
          "Regex": "(\\[[^\\]]+]|Br?|Cl?|N|O|S|P|F|I|b|c|n|o|s|p|\\(|\\)|\\.|=|#|-|\\+|\\\\|\\/|:|~|@|\\?|>>?|\\*|\\$|\\%[0-9]{2}|[0-9])"
        },
        "behavior": "Isolated",
        "invert": false
      }
    ]
  },
  "post_processor": {
    "type": "TemplateProcessing",
    "single": [
      {
        "SpecialToken": {
          "id": "[CLS]",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      },
      {
        "SpecialToken": {
          "id": "[SEP]",
          "type_id": 0
        }
      }
    ],
    "pair": [
      {
        "SpecialToken": {
          "id": "[CLS]",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      },
      {
        "SpecialToken": {
          "id": "[SEP]",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "B",
          "type_id": 1
        }
      },
      {
        "SpecialToken": {
          "id": "[SEP]",
          "type_id": 1
        }
      }
    ],
    "special_tokens": {
      "[CLS]": {
        "id": "[CLS]",
        "ids": [
          2
        ],
        "tokens": [
          "[CLS]"
        ]
      },
      "[SEP]": {
        "id": "[SEP]",
        "ids": [
          3
        ],
        "tokens": [
          "[SEP]"
        ]
      }
    }
  },
  "decoder": {
    "type": "WordPiece",
    "prefix": "##",
    "cleanup": true
  },
  "model": {
    "type": "WordPiece",
    "unk_token": "[UNK]",
    "continuing_subword_prefix": "##",
    "max_input_chars_per_word": 100,
    "vocab": {
      "[PAD]": 0,
      "[UNK]": 1,
      "[CLS]": 2,
      "[SEP]": 3,
      "[MASK]": 4,
      "=": 5,
      "F": 6,
      "N": 7,
      "1": 8,
      "n": 9,
      "O": 10,
      "C": 11,
      "S": 12,
      "c": 13,
      "3": 14,
      "Cl": 15,
      "o": 16,
      "[nH]": 17,
      "s": 18,
      "-": 19,
      "2": 20,
      "4": 21,
      "[C@H]": 22,
      ")": 23,
      "(": 24,
      "Br": 25,
      "#": 26,
      "[C@@H]": 27,
      "[C@]": 28,
      "[C@@]": 29,
      "[O-]": 30,
      "[N+]": 31,
      "[C]": 32,
      "I": 33,
      "5": 34,
      "[C-]": 35,
      "[CH]": 36,
      "/": 37,
      "[S@]": 38,
      "[S@@]": 39,
      "[SH]": 40,
      "[Si]": 41,
      "[n+]": 42,
      "[C+]": 43,
      "[S@H]": 44,
      "[Fe]": 45,
      "[S@@H]": 46,
      "B": 47,
      "[O]": 48,
      "[S-]": 49,
      "[P@H]": 50,
      "[PH]": 51,
      "6": 52,
      "[O+]": 53,
      "[P@@H]": 54,
      "[NH+]": 55,
      "[S]": 56,
      "\\": 57,
      "[P@]": 58,
      "[P@@]": 59,
      "[N]": 60,
      "P": 61,
      "[S+]": 62,
      "[P]": 63,
      "[IH]": 64,
      "[se]": 65,
      "[C@+]": 66,
      "[Si@]": 67,
      "[c-]": 68,
      "7": 69,
      "[C@-]": 70,
      "[Si@@]": 71,
      "[Se]": 72,
      "[Si@H]": 73,
      "[S@+]": 74,
      "[N-]": 75,
      "[CnH]": 76,
      "[c+]": 77,
      "[P+]": 78,
      "[Si@@H]": 79,
      "[SiH]": 80,
      "[P-]": 81,
      "[I]": 82,
      "[S@-]": 83,
      "[CH+]": 84,
      "[C@H+]": 85,
      "[I+]": 86,
      "[C@@-]": 87,
      "8": 88,
      "[Si-]": 89,
      "[C@@H+]": 90,
      "[I-]": 91,
      "[CH-]": 92,
      "[P@+]": 93,
      "[Cn]": 94,
      "[C@@+]": 95,
      "[SnH]": 96,
      "[Se@]": 97,
      "[S@@+]": 98,
      "[Se@@]": 99,
      "[Si+]": 100,
      "9": 101,
      "[InH]": 102,
      "[Ce]": 103,
      "[I@@]": 104,
      "[P@-]": 105,
      "[Se-]": 106,
      "[Sc]": 107,
      "[SH+]": 108,
      "[I@@H]": 109,
      "[I@H]": 110,
      "[c]": 111,
      "[SH-]": 112,
      "[N@]": 113,
      "[I@]": 114,
      "[N@@]": 115,
      "[P@@-]": 116,
      "%10": 117,
      "[nH+]": 118,
      "[Ne]": 119,
      "[Si@+]": 120,
      "[Cl+]": 121,
      "[Br+]": 122,
      "[N@H+]": 123,
      "[S@@-]": 124,
      "[N@+]": 125,
      "[n-]": 126,
      "[NH2+]": 127,
      "[B]": 128,
      "[Cn+]": 129,
      "[N@@H+]": 130,
      "[s+]": 131,
      "[si]": 132,
      "[N@@+]": 133,
      "p": 134,
      "[P@@+]": 135,
      "[Sc@H]": 136,
      "[cH+]": 137,
      "[ScH]": 138,
      "[Fe+]": 139,
      "[o+]": 140,
      "[cH-]": 141,
      "[NH]": 142,
      "[Se+]": 143,
      "[Fe-]": 144,
      "[I@+]": 145,
      "[Sc@]": 146,
      "[B-]": 147,
      "[SeH]": 148,
      "[Se@+]": 149,
      "[FeH]": 150,
      "[Fe@@]": 151,
      "[Cn-]": 152,
      "[S@@H+]": 153,
      "%11": 154,
      "[S@H-]": 155,
      "[S@@H-]": 156,
      "[CH2-]": 157,
      "[CnH-]": 158,
      "[In]": 159,
      "[S@H+]": 160,
      "[pH]": 161,
      "[PH+]": 162,
      "[Fe@@H]": 163,
      "[PH-]": 164,
      "b": 165,
      "[Si@-]": 166,
      "[si-]": 167,
      "[sH+]": 168,
      "[Fe@H]": 169,
      "[P@@H-]": 170,
      "[Sn+]": 171,
      "[P@@H+]": 172,
      "[P@H+]": 173,
      "[P@H-]": 174,
      "[Se@H]": 175,
      "[Se@-]": 176,
      "[Sc@@H]": 177,
      "[I@-]": 178,
      "[Sn]": 179,
      "[IH-]": 180,
      "[IH+]": 181,
      "[F+]": 182,
      "[Fe@]": 183,
      "[Sn@]": 184,
      "[CnH+]": 185,
      "[Si@H-]": 186,
      "[NH-]": 187,
      "[Si@H+]": 188,
      "[Sc-]": 189,
      "[Se@@H]": 190,
      "[Sn-]": 191,
      "[se+]": 192,
      "[Si@@+]": 193,
      "[SiH+]": 194,
      "[PH2-]": 195,
      "[CeH]": 196,
      "[SH3]": 197,
      "[CH2]": 198,
      "[Sc+]": 199,
      "[Si@@-]": 200
    }
  }
}