This is a migrated version of BeIR/arguana that is compatible with datasets library 4.0.0+.
This dataset contains the arguana dataset from the BEIR benchmark, converted from the old script-based format to Parquet format.
Dataset Structure
Queries
Split 'corpus': 8,674 examples… See the full description on the dataset page:
https://huggingface.co/datasets/Hyukkyu/beir-arguana.