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": "[CLS]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 2,
      "content": "[SEP]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 3,
      "content": "[PAD]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 4,
      "content": "[MASK]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": null,
  "pre_tokenizer": {
    "type": "Split",
    "pattern": {
      "Regex": "\\[|\\]"
    },
    "behavior": "Removed",
    "invert": false
  },
  "post_processor": {
    "type": "TemplateProcessing",
    "single": [
      {
        "SpecialToken": {
          "id": "[CLS]",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      },
      {
        "SpecialToken": {
          "id": "[SEP]",
          "type_id": 0
        }
      }
    ],
    "pair": [
      {
        "SpecialToken": {
          "id": "[CLS]",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      },
      {
        "SpecialToken": {
          "id": "[SEP]",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "B",
          "type_id": 1
        }
      },
      {
        "SpecialToken": {
          "id": "[SEP]",
          "type_id": 1
        }
      }
    ],
    "special_tokens": {
      "[CLS]": {
        "id": "[CLS]",
        "ids": [
          1
        ],
        "tokens": [
          "[CLS]"
        ]
      },
      "[SEP]": {
        "id": "[SEP]",
        "ids": [
          2
        ],
        "tokens": [
          "[SEP]"
        ]
      }
    }
  },
  "decoder": null,
  "model": {
    "type": "WordLevel",
    "vocab": {
      "[UNK]": 0,
      "[CLS]": 1,
      "[SEP]": 2,
      "[PAD]": 3,
      "[MASK]": 4,
      "#B": 5,
      "#B-1": 6,
      "#Branch1": 7,
      "#Branch2": 8,
      "#Branch3": 9,
      "#C": 10,
      "#C+1": 11,
      "#C-1": 12,
      "#N": 13,
      "#N+1": 14,
      "#O+1": 15,
      "#P": 16,
      "#P+1": 17,
      "#P-1": 18,
      "#S": 19,
      "#S+1": 20,
      "#S-1": 21,
      "=B": 22,
      "=B+1": 23,
      "=B-1": 24,
      "=Branch1": 25,
      "=Branch2": 26,
      "=Branch3": 27,
      "=C": 28,
      "=C+1": 29,
      "=C-1": 30,
      "=N": 31,
      "=N+1": 32,
      "=N-1": 33,
      "=O": 34,
      "=O+1": 35,
      "=P": 36,
      "=P+1": 37,
      "=P-1": 38,
      "=Ring1": 39,
      "=Ring2": 40,
      "=Ring3": 41,
      "=S": 42,
      "=S+1": 43,
      "=S-1": 44,
      "B": 45,
      "B+1": 46,
      "B-1": 47,
      "Br": 48,
      "Branch1": 49,
      "Branch2": 50,
      "Branch3": 51,
      "C": 52,
      "C+1": 53,
      "C-1": 54,
      "Cl": 55,
      "F": 56,
      "H": 57,
      "I": 58,
      "N": 59,
      "N+1": 60,
      "N-1": 61,
      "O": 62,
      "O+1": 63,
      "O-1": 64,
      "P": 65,
      "P+1": 66,
      "P-1": 67,
      "Ring1": 68,
      "Ring2": 69,
      "Ring3": 70,
      "S": 71,
      "S+1": 72,
      "S-1": 73
    },
    "unk_token": "[UNK]"
  }
}