davloo/v1

--- dataset_info: - config_name: chunked features: - name: document_id dtype: string - name: document_text dtype: string - name: document_filename dtype: string - name: document_metadata struct: - name: file_size dtype: int64 - name: document_summary dtype: string - name: summarization_model dtype: string - name: chunks list: - name: chunk_id dtype: string - name: chunk_text dtype: string - name: multihop_chunks list: - name: chunk_ids list: string - name: chunks_text list: string splits: - name: train num_bytes: 7786 num_examples: 1 download_size: 42076 dataset_size: 7786 - config_name: ingested features: - name: document_id dtype: string - name: document_text dtype: string - name: document_filename dtype: string - name: document_metadata struct: - name: file_size dtype: int64 splits: - name: train num_bytes: 2596 num_examples: 1 download_size: 14327 dataset_size: 2596 - config_name: prepared_lighteval features: - name: question dtype: string - name: additional_instructions dtype: string - name: ground_truth_answer dtype: string - name: gold list: int64 - name: choices list: string - name: question_category dtype: string - name: kind dtype: string - name: estimated_difficulty dtype: int64 - name: citations list: string - name: document_id dtype: string - name: chunk_ids list: string - name: question_generating_model dtype: string - name: chunks list: 'null' - name: document dtype: string - name: document_summary dtype: string splits: - name: train num_bytes: 4191 num_examples: 6 download_size: 11028 dataset_size: 4191 - config_name: summarized features: - name: document_id dtype: string - name: document_text dtype: string - name: document_filename dtype: string - name: document_metadata struct: - name: file_size dtype: int64 - name: document_summary dtype: string - name: summarization_model dtype: string splits: - name: train num_bytes: 2618 num_examples: 1 download_size: 15168 dataset_size: 2618 configs: - config_name: chunked data_files: - split: train path: chunked/train-* - config_name: ingested data_files: - split: train path: ingested/train-* - config_name: prepared_lighteval data_files: - split: train path: prepared_lighteval/train-* - config_name: summarized data_files: - split: train path: summarized/train-* ---