tokenizer.json

{
  "version": "1.0",
  "truncation": null,
  "padding": null,
  "added_tokens": [
    {
      "id": 0,
      "content": "[UNK]",
      "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": "[PAD]",
      "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
    },
    {
      "id": 5,
      "content": "[BOS]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 6,
      "content": "[EOS]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": null,
  "pre_tokenizer": {
    "type": "Whitespace"
  },
  "post_processor": {
    "type": "TemplateProcessing",
    "single": [
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      },
      {
        "SpecialToken": {
          "id": "[CLS]",
          "type_id": 0
        }
      }
    ],
    "pair": [
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      },
      {
        "SpecialToken": {
          "id": "[CLS]",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "B",
          "type_id": 1
        }
      },
      {
        "SpecialToken": {
          "id": "[EOS]",
          "type_id": 1
        }
      }
    ],
    "special_tokens": {
      "[CLS]": {
        "id": "[CLS]",
        "ids": [
          0
        ],
        "tokens": [
          "[CLS]"
        ]
      },
      "[EOS]": {
        "id": "[EOS]",
        "ids": [
          1
        ],
        "tokens": [
          "[EOS]"
        ]
      }
    }
  },
  "decoder": null,
  "model": {
    "type": "BPE",
    "dropout": null,
    "unk_token": "[UNK]",
    "continuing_subword_prefix": null,
    "end_of_word_suffix": null,
    "fuse_unk": false,
    "byte_fallback": false,
    "vocab": {
      "[UNK]": 0,
      "[CLS]": 1,
      "[SEP]": 2,
      "[PAD]": 3,
      "[MASK]": 4,
      "[BOS]": 5,
      "[EOS]": 6,
      "+": 7,
      "-": 8,
      "0": 9,
      "1": 10,
      "2": 11,
      "3": 12,
      "4": 13,
      "5": 14,
      "6": 15,
      "7": 16,
      "8": 17,
      "9": 18,
      "=": 19,
      "99": 20,
      "10": 21,
      "98": 22,
      "11": 23,
      "97": 24,
      "12": 25,
      "96": 26,
      "13": 27,
      "95": 28,
      "14": 29,
      "94": 30,
      "15": 31,
      "93": 32,
      "16": 33,
      "92": 34,
      "17": 35,
      "91": 36,
      "18": 37,
      "19": 38,
      "90": 39,
      "20": 40,
      "89": 41,
      "21": 42,
      "88": 43,
      "22": 44,
      "87": 45,
      "23": 46,
      "86": 47,
      "85": 48,
      "24": 49,
      "25": 50,
      "84": 51,
      "26": 52,
      "83": 53,
      "27": 54,
      "82": 55
    },
    "merges": [
      "9 9",
      "1 0",
      "9 8",
      "1 1",
      "9 7",
      "1 2",
      "9 6",
      "1 3",
      "9 5",
      "1 4",
      "9 4",
      "1 5",
      "9 3",
      "1 6",
      "9 2",
      "1 7",
      "9 1",
      "1 8",
      "1 9",
      "9 0",
      "2 0",
      "8 9",
      "2 1",
      "8 8",
      "2 2",
      "8 7",
      "2 3",
      "8 6",
      "8 5",
      "2 4",
      "2 5",
      "8 4",
      "2 6",
      "8 3",
      "2 7",
      "8 2"
    ]
  }
}