mixedbread-ai/public_ohr_v2_textbook

--- dataset_info: - config_name: corpus features: - name: corpus-id dtype: string - name: image dtype: image splits: - name: train num_bytes: 466520775.0 num_examples: 678 download_size: 425593470 dataset_size: 466520775.0 - config_name: default features: - name: query-id dtype: string - name: corpus-id dtype: string - name: score dtype: int64 splits: - name: train num_bytes: 119569 num_examples: 1138 download_size: 55112 dataset_size: 119569 - config_name: queries features: - name: query-id dtype: string - name: query dtype: string splits: - name: train num_bytes: 169875 num_examples: 1125 download_size: 113676 dataset_size: 169875 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-* ---