tmp-spec-checkpoint-84000/tokenizer.json

{
  "version": "1.0",
  "truncation": null,
  "padding": null,
  "added_tokens": [
    {
      "id": 0,
      "content": "<unk>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 1,
      "content": "<pad>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 2,
      "content": "<bos>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 3,
      "content": "<eos>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": null,
  "pre_tokenizer": {
    "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": "<bos>",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      },
      {
        "SpecialToken": {
          "id": "<eos>",
          "type_id": 0
        }
      }
    ],
    "pair": [
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "B",
          "type_id": 1
        }
      }
    ],
    "special_tokens": {
      "<bos>": {
        "id": "<bos>",
        "ids": [
          2
        ],
        "tokens": [
          "<bos>"
        ]
      },
      "<eos>": {
        "id": "<eos>",
        "ids": [
          3
        ],
        "tokens": [
          "<eos>"
        ]
      }
    }
  },
  "decoder": {
    "type": "BPEDecoder",
    "suffix": "</w>"
  },
  "model": {
    "type": "WordLevel",
    "vocab": {
      "<unk>": 0,
      "<pad>": 1,
      "<bos>": 2,
      "<eos>": 3,
      "C": 4,
      "c": 5,
      "(": 6,
      ")": 7,
      "1": 8,
      "O": 9,
      "N": 10,
      "2": 11,
      "=": 12,
      "n": 13,
      "[C@H]": 14,
      "[C@@H]": 15,
      "3": 16,
      "F": 17,
      "o": 18,
      "[nH]": 19,
      "s": 20,
      "S": 21,
      "#": 22,
      "Cl": 23,
      "4": 24,
      "-": 25,
      "/": 26,
      "[C@]": 27,
      "[C@@]": 28,
      "[O-]": 29,
      "[N+]": 30,
      "\\": 31,
      "Br": 32,
      "[S@+]": 33,
      "5": 34,
      "[S@@+]": 35,
      "[n+]": 36,
      "I": 37,
      "[S+]": 38,
      "[Si]": 39,
      "[S@]": 40,
      "6": 41,
      "[S@@]": 42,
      "P": 43,
      "B": 44,
      "[CH]": 45,
      "[C]": 46,
      "7": 47,
      "[N-]": 48,
      "[CH2]": 49,
      "[O]": 50,
      "[P@]": 51,
      "[C-]": 52,
      "[P@@]": 53,
      "[N@+]": 54,
      "8": 55,
      "[N@@+]": 56,
      "[cH-]": 57,
      "[CH-]": 58,
      "[s+]": 59,
      "[B-]": 60,
      "9": 61,
      "[Sn]": 62,
      "[o+]": 63,
      "[NH+]": 64,
      "[OH+]": 65,
      "%10": 66,
      ".": 67,
      "[P@@H]": 68,
      "[B@-]": 69,
      "[B@@-]": 70,
      "[NH-]": 71,
      "[P+]": 72,
      "[SH]": 73,
      "[Sn+2]": 74,
      "[NH2+]": 75,
      "[BH3-]": 76,
      "[N]": 77,
      "[P@H]": 78,
      "[Sn+]": 79,
      "[Br+]": 80,
      "[NH]": 81,
      "[O+]": 82,
      "[O-2]": 83,
      "[P@+]": 84,
      "[P@@+]": 85,
      "[PH]": 86,
      "[Sn+3]": 87,
      "[nH+]": 88
    },
    "unk_token": "<unk>"
  }
}