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": "<MASK>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 2,
      "content": "<CLS>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 3,
      "content": "<SEP>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 4,
      "content": "<EOS>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 5,
      "content": "<UNK>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": null,
  "pre_tokenizer": {
    "type": "Split",
    "pattern": {
      "String": ""
    },
    "behavior": "Isolated",
    "invert": false
  },
  "post_processor": {
    "type": "TemplateProcessing",
    "single": [
      {
        "SpecialToken": {
          "id": "<CLS>",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      },
      {
        "SpecialToken": {
          "id": "<EOS>",
          "type_id": 0
        }
      }
    ],
    "pair": [
      {
        "SpecialToken": {
          "id": "<CLS>",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      },
      {
        "SpecialToken": {
          "id": "<SEP>",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "B",
          "type_id": 0
        }
      },
      {
        "SpecialToken": {
          "id": "<EOS>",
          "type_id": 0
        }
      }
    ],
    "special_tokens": {
      "<CLS>": {
        "id": "<CLS>",
        "ids": [
          2
        ],
        "tokens": [
          "<CLS>"
        ]
      },
      "<EOS>": {
        "id": "<EOS>",
        "ids": [
          4
        ],
        "tokens": [
          "<EOS>"
        ]
      },
      "<SEP>": {
        "id": "<SEP>",
        "ids": [
          3
        ],
        "tokens": [
          "<SEP>"
        ]
      }
    }
  },
  "decoder": null,
  "model": {
    "type": "WordLevel",
    "vocab": {
      "<PAD>": 0,
      "<MASK>": 1,
      "<CLS>": 2,
      "<SEP>": 3,
      "<EOS>": 4,
      "<UNK>": 5,
      "A": 6,
      "C": 7,
      "D": 8,
      "E": 9,
      "F": 10,
      "G": 11,
      "H": 12,
      "I": 13,
      "K": 14,
      "L": 15,
      "M": 16,
      "N": 17,
      "P": 18,
      "Q": 19,
      "R": 20,
      "S": 21,
      "T": 22,
      "V": 23,
      "W": 24,
      "Y": 25,
      "X": 26,
      "B": 27,
      "Z": 28
    },
    "unk_token": "<UNK>"
  }
}