tmp-spec-checkpoint-40000/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,
      ".": 5,
      "1": 6,
      "c": 7,
      "O": 8,
      "=": 9,
      "(": 10,
      ")": 11,
      "N": 12,
      "5": 13,
      "6": 14,
      "4": 15,
      "7": 16,
      "8": 17,
      "3": 18,
      "2": 19,
      "n": 20,
      "9": 21,
      "F": 22,
      "%10": 23,
      "%11": 24,
      "S": 25,
      "s": 26,
      "Cl": 27,
      "[nH]": 28,
      "o": 29,
      "#": 30,
      "Br": 31,
      "%12": 32,
      "[N+]": 33,
      "[O-]": 34,
      "%13": 35,
      "I": 36,
      "[N-]": 37,
      "P": 38,
      "[n+]": 39,
      "%14": 40,
      "-": 41,
      "[Si]": 42,
      "[S+]": 43,
      "%15": 44,
      "B": 45,
      "%16": 46,
      "[NH+]": 47,
      "[B-]": 48,
      "%17": 49,
      "[NH2+]": 50,
      "[O]": 51,
      "[NH3+]": 52,
      "[PH]": 53,
      "[n-]": 54,
      "%18": 55,
      "[nH+]": 56,
      "[Sn]": 57,
      "[s+]": 58,
      "%19": 59,
      "[Se]": 60,
      "[Cl-]": 61,
      "%20": 62,
      "[N]": 63,
      "[C-]": 64,
      "[C]": 65,
      "[SiH]": 66,
      "%21": 67,
      "[O+]": 68,
      "[SH]": 69,
      "[NH]": 70,
      "[P+]": 71,
      "[c-]": 72,
      "[o+]": 73
    },
    "unk_token": "<unk>"
  }
}