minicoderx-tokenizer/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": "<s>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 2,
      "content": "</s>",
      "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": {
    "type": "Sequence",
    "normalizers": [
      {
        "type": "NFD"
      },
      {
        "type": "Lowercase"
      },
      {
        "type": "StripAccents"
      }
    ]
  },
  "pre_tokenizer": {
    "type": "Whitespace"
  },
  "post_processor": {
    "type": "TemplateProcessing",
    "single": [
      {
        "SpecialToken": {
          "id": "<s>",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      },
      {
        "SpecialToken": {
          "id": "</s>",
          "type_id": 0
        }
      }
    ],
    "pair": [
      {
        "SpecialToken": {
          "id": "<s>",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      },
      {
        "SpecialToken": {
          "id": "</s>",
          "type_id": 0
        }
      },
      {
        "SpecialToken": {
          "id": "</s>",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "B",
          "type_id": 0
        }
      },
      {
        "SpecialToken": {
          "id": "</s>",
          "type_id": 0
        }
      }
    ],
    "special_tokens": {
      "</s>": {
        "id": "</s>",
        "ids": [
          2
        ],
        "tokens": [
          "</s>"
        ]
      },
      "<s>": {
        "id": "<s>",
        "ids": [
          1
        ],
        "tokens": [
          "<s>"
        ]
      }
    }
  },
  "decoder": null,
  "model": {
    "type": "BPE",
    "dropout": null,
    "unk_token": null,
    "continuing_subword_prefix": null,
    "end_of_word_suffix": null,
    "fuse_unk": false,
    "byte_fallback": false,
    "ignore_merges": false,
    "vocab": {
      "<pad>": 0,
      "<s>": 1,
      "</s>": 2,
      "<unk>": 3,
      "<mask>": 4,
      "!": 5,
      "\"": 6,
      "(": 7,
      ")": 8,
      "+": 9,
      ",": 10,
      ":": 11,
      "a": 12,
      "b": 13,
      "c": 14,
      "d": 15,
      "e": 16,
      "f": 17,
      "h": 18,
      "i": 19,
      "l": 20,
      "n": 21,
      "o": 22,
      "p": 23,
      "r": 24,
      "s": 25,
      "t": 26,
      "u": 27,
      "w": 28,
      "as": 29,
      "el": 30,
      "hel": 31,
      "ld": 32,
      "lo": 33,
      "or": 34,
      "wor": 35,
      "ass": 36,
      "hello": 37,
      "world": 38,
      "!\"": 39,
      "(\"": 40,
      "):": 41,
      "ad": 42,
      "cl": 43,
      "de": 44,
      "et": 45,
      "in": 46,
      "pr": 47,
      "pass": 48,
      "rn": 49,
      "ret": 50,
      "urn": 51,
      "helloworld": 52,
      "!\")": 53,
      "add": 54,
      "class": 55,
      "def": 56,
      "int": 57,
      "print": 58,
      "return": 59
    },
    "merges": [
      [
        "a",
        "s"
      ],
      [
        "e",
        "l"
      ],
      [
        "h",
        "el"
      ],
      [
        "l",
        "d"
      ],
      [
        "l",
        "o"
      ],
      [
        "o",
        "r"
      ],
      [
        "w",
        "or"
      ],
      [
        "as",
        "s"
      ],
      [
        "hel",
        "lo"
      ],
      [
        "wor",
        "ld"
      ],
      [
        "!",
        "\""
      ],
      [
        "(",
        "\""
      ],
      [
        ")",
        ":"
      ],
      [
        "a",
        "d"
      ],
      [
        "c",
        "l"
      ],
      [
        "d",
        "e"
      ],
      [
        "e",
        "t"
      ],
      [
        "i",
        "n"
      ],
      [
        "p",
        "r"
      ],
      [
        "p",
        "ass"
      ],
      [
        "r",
        "n"
      ],
      [
        "r",
        "et"
      ],
      [
        "u",
        "rn"
      ],
      [
        "hello",
        "world"
      ],
      [
        "!\"",
        ")"
      ],
      [
        "ad",
        "d"
      ],
      [
        "cl",
        "ass"
      ],
      [
        "de",
        "f"
      ],
      [
        "in",
        "t"
      ],
      [
        "pr",
        "int"
      ],
      [
        "ret",
        "urn"
      ]
    ]
  }
}