tokenizer.json

{
  "version": "1.0",
  "truncation": null,
  "padding": null,
  "added_tokens": [
    {
      "id": 112,
      "content": "[UNK]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 113,
      "content": "[PAD]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 114,
      "content": "[MASK]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 115,
      "content": "[SEP]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 116,
      "content": "[CLS]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": {
    "type": "Sequence",
    "normalizers": []
  },
  "pre_tokenizer": {
    "type": "WhitespaceSplit"
  },
  "post_processor": null,
  "decoder": {
    "type": "WordPiece",
    "prefix": "##",
    "cleanup": true
  },
  "model": {
    "type": "WordLevel",
    "vocab": {
      "<boc>": 0,
      "<eoc>": 1,
      "<sepc>": 2,
      "<bog>": 3,
      "<eog>": 4,
      "<sepg>": 5,
      "IDX_0": 6,
      "IDX_1": 7,
      "IDX_2": 8,
      "IDX_3": 9,
      "IDX_4": 10,
      "IDX_5": 11,
      "IDX_6": 12,
      "IDX_7": 13,
      "IDX_8": 14,
      "IDX_9": 15,
      "IDX_10": 16,
      "IDX_11": 17,
      "IDX_12": 18,
      "IDX_13": 19,
      "IDX_14": 20,
      "IDX_15": 21,
      "IDX_16": 22,
      "IDX_17": 23,
      "IDX_18": 24,
      "IDX_19": 25,
      "IDX_20": 26,
      "IDX_21": 27,
      "IDX_22": 28,
      "IDX_23": 29,
      "IDX_24": 30,
      "IDX_25": 31,
      "IDX_26": 32,
      "IDX_27": 33,
      "IDX_28": 34,
      "IDX_29": 35,
      "IDX_30": 36,
      "IDX_31": 37,
      "IDX_32": 38,
      "IDX_33": 39,
      "IDX_34": 40,
      "IDX_35": 41,
      "IDX_36": 42,
      "IDX_37": 43,
      "IDX_38": 44,
      "IDX_39": 45,
      "IDX_40": 46,
      "IDX_41": 47,
      "IDX_42": 48,
      "IDX_43": 49,
      "IDX_44": 50,
      "IDX_45": 51,
      "IDX_46": 52,
      "IDX_47": 53,
      "IDX_48": 54,
      "IDX_49": 55,
      "IDX_50": 56,
      "IDX_51": 57,
      "IDX_52": 58,
      "IDX_53": 59,
      "IDX_54": 60,
      "IDX_55": 61,
      "IDX_56": 62,
      "IDX_57": 63,
      "IDX_58": 64,
      "IDX_59": 65,
      "IDX_60": 66,
      "IDX_61": 67,
      "IDX_62": 68,
      "IDX_63": 69,
      "IDX_64": 70,
      "IDX_65": 71,
      "IDX_66": 72,
      "IDX_67": 73,
      "IDX_68": 74,
      "IDX_69": 75,
      "IDX_70": 76,
      "IDX_71": 77,
      "IDX_72": 78,
      "IDX_73": 79,
      "IDX_74": 80,
      "IDX_75": 81,
      "IDX_76": 82,
      "IDX_77": 83,
      "IDX_78": 84,
      "IDX_79": 85,
      "IDX_80": 86,
      "IDX_81": 87,
      "IDX_82": 88,
      "IDX_83": 89,
      "IDX_84": 90,
      "IDX_85": 91,
      "IDX_86": 92,
      "IDX_87": 93,
      "IDX_88": 94,
      "IDX_89": 95,
      "ATOM_C": 96,
      "ATOM_N": 97,
      "ATOM_O": 98,
      "ATOM_F": 99,
      "ATOM_B": 100,
      "ATOM_Br": 101,
      "ATOM_Cl": 102,
      "ATOM_I": 103,
      "ATOM_P": 104,
      "ATOM_S": 105,
      "ATOM_Se": 106,
      "ATOM_Si": 107,
      "BOND_SINGLE": 108,
      "BOND_DOUBLE": 109,
      "BOND_TRIPLE": 110,
      "BOND_AROMATIC": 111
    },
    "unk_token": "[UNK]"
  }
}