Method __init__

lm-eval-harness/lm_eval/api/task.py:186–221

:param data_dir: str Stores the path to a local folder containing the `Task`'s data files. Use this to specify the path to manually downloaded data (usually when the dataset is not publicly accessible). :param cache_dir: str The direct

(
        self,
        data_dir=None,
        cache_dir=None,
        download_mode=None,
        config=None,
    )

    OUTPUT_TYPE: str = None

    def __init__(
        self,
        data_dir=None,
        cache_dir=None,
        download_mode=None,
        config=None,
    ) -> None:
        """
        :param data_dir: str
            Stores the path to a local folder containing the `Task`'s data files.
            Use this to specify the path to manually downloaded data (usually when
            the dataset is not publicly accessible).
        :param cache_dir: str
            The directory to read/write the `Task` dataset. This follows the
            HuggingFace `datasets` API with the default cache directory located at:
                `~/.cache/huggingface/datasets`
            NOTE: You can change the cache location globally for a given process
            to another directory:
                `export HF_DATASETS_CACHE="/path/to/another/directory"`
        :param download_mode: datasets.DownloadMode
            How to treat pre-existing `Task` downloads and data.
            - `datasets.DownloadMode.REUSE_DATASET_IF_EXISTS`
                Reuse download and reuse dataset.
            - `datasets.DownloadMode.REUSE_CACHE_IF_EXISTS`
                Reuse download with fresh dataset.
            - `datasets.DownloadMode.FORCE_REDOWNLOAD`
                Fresh download and fresh dataset.
        """
        self.download(data_dir, cache_dir, download_mode)
        self._training_docs = None
        self._fewshot_docs = None
        self._instances = None

        self._config = TaskConfig({**config}) if config else TaskConfig()

        self._filters = [build_filter_ensemble("none", [["take_first", None]])]

    def download(self, data_dir=None, cache_dir=None, download_mode=None) -> None:
        """Downloads and returns the task dataset.