mixedbread-ai/public_ohr_v2_academic

--- dataset_info: - config_name: corpus features: - name: corpus-id dtype: string - name: image dtype: image splits: - name: train num_bytes: 424933802.625 num_examples: 1011 download_size: 403482936 dataset_size: 424933802.625 - config_name: default features: - name: query-id dtype: string - name: corpus-id dtype: string - name: score dtype: int64 splits: - name: train num_bytes: 109568 num_examples: 1296 download_size: 54602 dataset_size: 109568 - config_name: queries features: - name: query-id dtype: string - name: query dtype: string splits: - name: train num_bytes: 202633 num_examples: 1179 download_size: 125581 dataset_size: 202633 configs: - config_name: corpus data_files: - split: train path: corpus/train-* - config_name: default data_files: - split: train path: data/train-* - config_name: queries data_files: - split: train path: queries/train-* ---