tokenizer.json

{
  "version": "1.0",
  "truncation": null,
  "padding": {
    "strategy": "BatchLongest",
    "direction": "Right",
    "pad_to_multiple_of": 16,
    "pad_id": 0,
    "pad_type_id": 0,
    "pad_token": "-"
  },
  "added_tokens": [
    {
      "id": 0,
      "content": "-",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 1,
      "content": "[",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 2,
      "content": "]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": null,
  "pre_tokenizer": {
    "type": "Split",
    "pattern": {
      "String": ""
    },
    "behavior": "Removed",
    "invert": false
  },
  "post_processor": {
    "type": "TemplateProcessing",
    "single": [
      {
        "SpecialToken": {
          "id": "[",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      },
      {
        "SpecialToken": {
          "id": "]",
          "type_id": 0
        }
      }
    ],
    "pair": [
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "B",
          "type_id": 1
        }
      }
    ],
    "special_tokens": {
      "-": {
        "id": "-",
        "ids": [
          0
        ],
        "tokens": [
          "-"
        ]
      },
      "[": {
        "id": "[",
        "ids": [
          1
        ],
        "tokens": [
          "["
        ]
      },
      "]": {
        "id": "]",
        "ids": [
          2
        ],
        "tokens": [
          "]"
        ]
      }
    }
  },
  "decoder": {
    "type": "Fuse"
  },
  "model": {
    "type": "WordLevel",
    "vocab": {
      "-": 0,
      "[": 1,
      "]": 2,
      "A": 3,
      "C": 4,
      "D": 5,
      "E": 6,
      "F": 7,
      "G": 8,
      "H": 9,
      "I": 10,
      "K": 11,
      "L": 12,
      "M": 13,
      "N": 14,
      "P": 15,
      "Q": 16,
      "R": 17,
      "S": 18,
      "T": 19,
      "V": 20,
      "W": 21,
      "Y": 22
    },
    "unk_token": "<unk>"
  }
}