tmp-spec-checkpoint-35000/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,
      ")": 4,
      "C": 5,
      "c": 6,
      "O": 7,
      "=": 8,
      "N": 9,
      "n": 10,
      "6": 11,
      "5": 12,
      "[C@H]": 13,
      "[C@@H]": 14,
      "F": 15,
      "4": 16,
      "3": 17,
      "S": 18,
      "s": 19,
      "Cl": 20,
      "[nH]": 21,
      "o": 22,
      "9": 23,
      "[C@]": 24,
      "[C@@]": 25,
      "#": 26,
      "7": 27,
      "Br": 28,
      "8": 29,
      "-": 30,
      "/": 31,
      "%10": 32,
      "[N+]": 33,
      "[O-]": 34,
      "I": 35,
      "[N-]": 36,
      "P": 37,
      "[S@]": 38,
      "[S@@]": 39,
      "[n+]": 40,
      "%11": 41,
      "[Si]": 42,
      "%13": 43,
      "[S+]": 44,
      "B": 45,
      "%14": 46,
      "%12": 47,
      "[P@]": 48,
      "[P@@]": 49,
      "[N@]": 50,
      "%15": 51,
      "[N@@]": 52,
      "%18": 53,
      "%17": 54,
      "[B-]": 55,
      "%16": 56,
      "%19": 57,
      "%20": 58,
      "[NH+]": 59,
      "[N@@H+]": 60,
      "[NH2+]": 61,
      "%21": 62,
      "[N@H+]": 63,
      "%22": 64,
      "[O]": 65,
      "[NH3+]": 66,
      "[PH]": 67,
      "%23": 68,
      "%24": 69,
      "[Si@]": 70,
      "[Si@@]": 71,
      "[n-]": 72,
      "[N@+]": 73,
      "[nH+]": 74,
      "%26": 75,
      "[N@@+]": 76,
      "[Sn]": 77,
      "[s+]": 78,
      "%25": 79,
      "[Se]": 80,
      ".": 81,
      "[Cl-]": 82,
      "%27": 83,
      "%28": 84,
      "[N]": 85,
      "[C-]": 86,
      "[C]": 87,
      "[S@@+]": 88,
      "%29": 89,
      "[O+]": 90,
      "[SH]": 91,
      "[Si@H]": 92,
      "[NH]": 93,
      "[P+]": 94,
      "[P@@H]": 95,
      "[Si@@H]": 96,
      "[c-]": 97,
      "[o+]": 98
    },
    "unk_token": "<unk>"
  }
}