mixedbread-ai/public_ohr_v2_administration

--- dataset_info: - config_name: corpus features: - name: corpus-id dtype: string - name: image dtype: image splits: - name: train num_bytes: 514341460.375 num_examples: 1341 download_size: 476429590 dataset_size: 514341460.375 - config_name: default features: - name: query-id dtype: string - name: corpus-id dtype: string - name: score dtype: int64 splits: - name: train num_bytes: 142228 num_examples: 1558 download_size: 65169 dataset_size: 142228 - config_name: queries features: - name: query-id dtype: string - name: query dtype: string splits: - name: train num_bytes: 236356 num_examples: 1332 download_size: 143344 dataset_size: 236356 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-* ---