utils.config_utils#

Module Contents#

Functions#

API#

utils.config_utils.build_downloader(
downloader_config_file: str,
default_download_dir: str | None = None,
) tuple[nemo_curator.download.DocumentDownloader, nemo_curator.download.DocumentIterator, nemo_curator.download.DocumentExtractor, dict]#
utils.config_utils.build_filter(
filter_config: dict,
) nemo_curator.Filter | nemo_curator.ScoreFilter#
utils.config_utils.build_filter_pipeline(
filter_config_file: str,
) nemo_curator.Sequential#