nthakur-backup/bge-retrieval-data-3-datasets-20K-replaced

--- dataset_info: features: - name: query_id dtype: string - name: query dtype: string - name: positive_passages list: - name: docid dtype: string - name: text dtype: string - name: title dtype: string - name: negative_passages list: - name: docid dtype: string - name: text dtype: string - name: title dtype: string - name: subset dtype: string splits: - name: train num_bytes: 368816887 num_examples: 20865 download_size: 216575214 dataset_size: 368816887 configs: - config_name: default data_files: - split: train path: data/train-* ---