tokenizer.json

{
  "version": "1.0",
  "truncation": null,
  "padding": null,
  "added_tokens": [
    {
      "id": 9,
      "content": ";",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": null,
  "pre_tokenizer": {
    "type": "Split",
    "pattern": {
      "Regex": "."
    },
    "behavior": "Isolated",
    "invert": false
  },
  "post_processor": {
    "type": "TemplateProcessing",
    "single": [
      {
        "SpecialToken": {
          "id": ";",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      }
    ],
    "pair": [
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "B",
          "type_id": 1
        }
      }
    ],
    "special_tokens": {
      "": {
        "id": "",
        "ids": [
          0
        ],
        "tokens": [
          ""
        ]
      },
      ";": {
        "id": ";",
        "ids": [
          9
        ],
        "tokens": [
          ";"
        ]
      }
    }
  },
  "decoder": {
    "type": "Sequence",
    "decoders": [
      {
        "type": "Replace",
        "pattern": {
          "String": " "
        },
        "content": "▁"
      },
      {
        "type": "Replace",
        "pattern": {
          "String": "▁"
        },
        "content": " "
      }
    ]
  },
  "model": {
    "type": "WordLevel",
    "vocab": {
      " ": 0,
      "1": 1,
      "2": 2,
      "3": 3,
      "4": 4,
      "5": 5,
      "6": 6,
      "7": 7,
      "8": 8,
      ";": 9,
      "#": 10,
      "a": 11,
      "b": 12,
      "c": 13,
      "d": 14,
      "e": 15,
      "f": 16,
      "g": 17,
      "h": 18,
      "n": 19,
      "r": 20,
      "q": 21,
      "k": 22
    },
    "unk_token": " "
  }
}