tokenizer.json

{
  "version": "1.0",
  "truncation": null,
  "padding": {
    "strategy": "BatchLongest",
    "direction": "Right",
    "pad_to_multiple_of": null,
    "pad_id": 2,
    "pad_type_id": 0,
    "pad_token": "<PAD>"
  },
  "added_tokens": [
    {
      "id": 0,
      "content": "<CLS>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 1,
      "content": "<EOS>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 2,
      "content": "<PAD>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 3,
      "content": "<UNK>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": null,
  "pre_tokenizer": {
    "type": "Split",
    "pattern": {
      "String": "]"
    },
    "behavior": "MergedWithPrevious",
    "invert": false
  },
  "post_processor": {
    "type": "TemplateProcessing",
    "single": [
      {
        "SpecialToken": {
          "id": "<CLS>",
          "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": {
      "<CLS>": {
        "id": "<CLS>",
        "ids": [
          0
        ],
        "tokens": [
          "<CLS>"
        ]
      },
      "<EOS>": {
        "id": "<EOS>",
        "ids": [
          1
        ],
        "tokens": [
          "<EOS>"
        ]
      }
    }
  },
  "decoder": null,
  "model": {
    "type": "WordLevel",
    "vocab": {
      "<CLS>": 0,
      "<EOS>": 1,
      "<PAD>": 2,
      "<UNK>": 3,
      "[C]": 4,
      "[=C]": 5,
      "[Ring1]": 6,
      "[Branch1]": 7,
      "[N]": 8,
      "[=Branch1]": 9,
      "[O]": 10,
      "[=O]": 11,
      "[Ring2]": 12,
      "[Branch2]": 13,
      "[=N]": 14,
      "[S]": 15,
      "[#Branch1]": 16,
      "[=Branch2]": 17,
      "[F]": 18,
      "[#Branch2]": 19,
      "[#C]": 20,
      "[Cl]": 21,
      "[P]": 22,
      "[NH1]": 23,
      "[=Ring1]": 24,
      "[O-1]": 25,
      "[N+1]": 26,
      "[Br]": 27,
      "[#N]": 28,
      "[=Ring2]": 29,
      "[=S]": 30,
      "[=N+1]": 31,
      "[I]": 32,
      "[S+1]": 33,
      "[B]": 34,
      "[Si]": 35,
      "[=N-1]": 36,
      "[=P]": 37,
      "[Se]": 38,
      "[H]": 39,
      "[N-1]": 40,
      "[C-1]": 41,
      "[#N+1]": 42,
      "[P+1]": 43,
      "[OH0]": 44,
      "[B-1]": 45,
      "[PH1]": 46,
      "[S-1]": 47,
      "[=O+1]": 48,
      "[=S+1]": 49,
      "[=Se]": 50,
      "[NH3+1]": 51,
      "[C+1]": 52,
      "[NH1+1]": 53,
      "[BH2-1]": 54,
      "[NH2+1]": 55,
      "[O+1]": 56,
      "[SeH1]": 57,
      "[SH1]": 58,
      "[SiH2]": 59,
      "[=SH1]": 60,
      "[=Se+1]": 61,
      "[=OH1+1]": 62,
      "[=PH1]": 63,
      "[#C-1]": 64,
      "[=NH1+1]": 65,
      "[=NH2+1]": 66,
      "[BH3-1]": 67,
      "[CH1-1]": 68,
      "[I+1]": 69,
      "[CH1+1]": 70,
      "[NH1-1]": 71,
      "[BH1-1]": 72,
      "[SiH1]": 73,
      "[Se+1]": 74,
      "[=C-1]": 75,
      "[F+1]": 76,
      "[=B]": 77,
      "[=Si]": 78,
      "[BH0]": 79,
      "[CH1]": 80,
      "[CH2+1]": 81,
      "[Cl+1]": 82,
      "[NH0]": 83,
      "[#O+1]": 84,
      "[Br+2]": 85,
      "[Br-1]": 86,
      "[CH2]": 87,
      "[Cl+2]": 88,
      "[Cl+3]": 89,
      "[Cl-1]": 90,
      "[F-1]": 91,
      "[I+2]": 92,
      "[I+3]": 93,
      "[PH2+1]": 94,
      "[Se-1]": 95,
      "[SeH2]": 96,
      "[Si-1]": 97,
      "[SiH1-1]": 98
    },
    "unk_token": "<UNK>"
  }
}