mixedbread-ai/public_ohr_v2_law

--- dataset_info: - config_name: corpus features: - name: corpus-id dtype: string - name: image dtype: image splits: - name: train num_bytes: 403798480.625 num_examples: 1187 download_size: 363193076 dataset_size: 403798480.625 - config_name: default features: - name: query-id dtype: string - name: corpus-id dtype: string - name: score dtype: int64 splits: - name: train num_bytes: 145198 num_examples: 1274 download_size: 58480 dataset_size: 145198 - config_name: queries features: - name: query-id dtype: string - name: query dtype: string splits: - name: train num_bytes: 192841 num_examples: 1142 download_size: 118619 dataset_size: 192841 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-* ---