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": "<cls>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 2,
      "content": "<sep>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 3,
      "content": "<unk>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 4,
      "content": "<mask>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": null,
  "pre_tokenizer": null,
  "post_processor": {
    "type": "TemplateProcessing",
    "single": [
      {
        "SpecialToken": {
          "id": "<cls>",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      },
      {
        "SpecialToken": {
          "id": "<sep>",
          "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": 1
        }
      },
      {
        "SpecialToken": {
          "id": "<sep>",
          "type_id": 1
        }
      }
    ],
    "special_tokens": {
      "<cls>": {
        "id": "<cls>",
        "ids": [
          1
        ],
        "tokens": [
          "<cls>"
        ]
      },
      "<sep>": {
        "id": "<sep>",
        "ids": [
          2
        ],
        "tokens": [
          "<sep>"
        ]
      }
    }
  },
  "decoder": {
    "type": "BPEDecoder",
    "suffix": "</w>"
  },
  "model": {
    "type": "BPE",
    "dropout": null,
    "unk_token": null,
    "continuing_subword_prefix": null,
    "end_of_word_suffix": null,
    "fuse_unk": false,
    "byte_fallback": false,
    "vocab": {
      "<pad>": 0,
      "<cls>": 1,
      "<sep>": 2,
      "<unk>": 3,
      "<mask>": 4,
      "A": 5,
      "B": 6,
      "C": 7,
      "D": 8,
      "E": 9,
      "F": 10,
      "G": 11,
      "H": 12,
      "I": 13,
      "K": 14,
      "L": 15,
      "M": 16,
      "N": 17,
      "O": 18,
      "P": 19,
      "Q": 20,
      "R": 21,
      "S": 22,
      "T": 23,
      "U": 24,
      "V": 25,
      "W": 26,
      "X": 27,
      "Y": 28,
      "Z": 29,
      "AA": 30,
      "LL": 31,
      "SS": 32,
      "LA": 33,
      "LS": 34,
      "GG": 35,
      "LV": 36,
      "LR": 37,
      "LE": 38,
      "LG": 39,
      "LT": 40,
      "AV": 41,
      "AG": 42,
      "LP": 43,
      "LD": 44,
      "LI": 45,
      "AS": 46,
      "EE": 47,
      "RR": 48,
      "LK": 49
    },
    "merges": [
      "A A",
      "L L",
      "S S",
      "L A",
      "L S",
      "G G",
      "L V",
      "L R",
      "L E",
      "L G",
      "L T",
      "A V",
      "A G",
      "L P",
      "L D",
      "L I",
      "A S",
      "E E",
      "R R",
      "L K"
    ]
  }
}