tokenizer.json

{
  "version": "1.0",
  "truncation": null,
  "padding": null,
  "added_tokens": [
    {
      "id": 21,
      "content": "$",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 22,
      "content": ".",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 23,
      "content": "?",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 24,
      "content": "|",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 25,
      "content": "*",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": {
    "type": "BertNormalizer",
    "clean_text": true,
    "handle_chinese_chars": false,
    "strip_accents": null,
    "lowercase": false
  },
  "pre_tokenizer": {
    "type": "BertPreTokenizer"
  },
  "post_processor": {
    "type": "TemplateProcessing",
    "single": [
      {
        "SpecialToken": {
          "id": "*",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      },
      {
        "SpecialToken": {
          "id": "|",
          "type_id": 0
        }
      }
    ],
    "pair": [
      {
        "SpecialToken": {
          "id": "*",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      },
      {
        "SpecialToken": {
          "id": "|",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "B",
          "type_id": 1
        }
      },
      {
        "SpecialToken": {
          "id": "|",
          "type_id": 1
        }
      }
    ],
    "special_tokens": {
      "*": {
        "id": "*",
        "ids": [
          25
        ],
        "tokens": [
          "*"
        ]
      },
      "|": {
        "id": "|",
        "ids": [
          24
        ],
        "tokens": [
          "|"
        ]
      }
    }
  },
  "decoder": {
    "type": "WordPiece",
    "prefix": "##",
    "cleanup": true
  },
  "model": {
    "type": "WordPiece",
    "unk_token": "?",
    "continuing_subword_prefix": "##",
    "max_input_chars_per_word": 100,
    "vocab": {
      "R": 0,
      "H": 1,
      "K": 2,
      "D": 3,
      "E": 4,
      "S": 5,
      "T": 6,
      "N": 7,
      "Q": 8,
      "C": 9,
      "U": 10,
      "G": 11,
      "P": 12,
      "A": 13,
      "V": 14,
      "I": 15,
      "L": 16,
      "M": 17,
      "F": 18,
      "Y": 19,
      "W": 20,
      "$": 21,
      ".": 22,
      "?": 23,
      "|": 24,
      "*": 25
    }
  }
}