tokenizer.json

{
  "version": "1.0",
  "truncation": null,
  "padding": null,
  "added_tokens": [
    {
      "id": 0,
      "content": "N",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 1,
      "content": "E",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 2,
      "content": "F",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": {
    "type": "Sequence",
    "normalizers": [
      {
        "type": "NFD"
      },
      {
        "type": "Strip",
        "strip_left": true,
        "strip_right": true
      }
    ]
  },
  "pre_tokenizer": {
    "type": "Split",
    "pattern": {
      "Regex": "[a-zA-Z]"
    },
    "behavior": "Isolated",
    "invert": false
  },
  "post_processor": null,
  "decoder": {
    "type": "WordPiece",
    "prefix": "",
    "cleanup": true
  },
  "model": {
    "type": "WordPiece",
    "unk_token": "N",
    "continuing_subword_prefix": "##",
    "max_input_chars_per_word": 100,
    "vocab": {
      "N": 0,
      "E": 1,
      "F": 2,
      "A": 3,
      "C": 4,
      "G": 5,
      "T": 6
    }
  }
}