tokenizer.json

{
  "version": "1.0",
  "truncation": null,
  "padding": null,
  "added_tokens": [
    {
      "id": 0,
      "content": "<pad>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 1,
      "content": "<unk>",
      "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": {
    "type": "Sequence",
    "normalizers": [
      {
        "type": "Replace",
        "pattern": {
          "Regex": "\\([^\\)]*\\)"
        },
        "content": ""
      },
      {
        "type": "Replace",
        "pattern": {
          "Regex": "[WBKQRPN]"
        },
        "content": ""
      }
    ]
  },
  "pre_tokenizer": {
    "type": "Sequence",
    "pretokenizers": [
      {
        "type": "WhitespaceSplit"
      },
      {
        "type": "Split",
        "pattern": {
          "Regex": "."
        },
        "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": null,
  "model": {
    "type": "WordLevel",
    "vocab": {
      "<pad>": 0,
      "<unk>": 1,
      "<bos>": 2,
      "<eos>": 3,
      "a": 4,
      "b": 5,
      "c": 6,
      "d": 7,
      "e": 8,
      "f": 9,
      "g": 10,
      "h": 11,
      "1": 12,
      "2": 13,
      "3": 14,
      "4": 15,
      "5": 16,
      "6": 17,
      "7": 18,
      "8": 19,
      "W": 20,
      "B": 21,
      "K": 22,
      "Q": 23,
      "R": 24,
      "N": 25,
      "P": 26
    },
    "unk_token": "<unk>"
  }
}