Name: pkappelerOrg/yourbench_example
Creator: pkappelerOrg
Published: 2025-03-26 08:40:45
License: 暂无描述

下载链接：

https://hf-mirror.com/datasets/pkappelerOrg/yourbench_example

下载链接

链接失效反馈

官方服务：

资源简介：

--- 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: raw_document_summary dtype: string - 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 sequence: string - name: chunks_text sequence: string - name: chunk_info_metrics list: - name: avg_token_length dtype: float64 - name: bigram_diversity dtype: float64 - name: flesch_reading_ease dtype: float64 - name: gunning_fog dtype: float64 - name: perplexity dtype: float64 - name: token_count dtype: float64 - name: unique_token_ratio dtype: float64 - name: chunking_model dtype: string splits: - name: train num_bytes: 85018 num_examples: 2 download_size: 64284 dataset_size: 85018 - 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: 18022 num_examples: 2 download_size: 13452 dataset_size: 18022 - config_name: lighteval features: - name: question dtype: string - name: ground_truth_answer dtype: string - name: question_category dtype: string - name: kind dtype: string - name: estimated_difficulty dtype: int64 - name: citations sequence: string - name: document_id dtype: string - name: chunk_ids sequence: string - name: question_generating_model dtype: string - name: chunks sequence: string - name: document dtype: string splits: - name: train num_bytes: 553258 num_examples: 50 download_size: 44242 dataset_size: 553258 - config_name: multi_hop_questions features: - name: document_id dtype: string - name: source_chunk_ids sequence: string - name: question dtype: string - name: self_answer dtype: string - name: estimated_difficulty dtype: int64 - name: self_assessed_question_type dtype: string - name: generating_model dtype: string - name: thought_process dtype: string - name: citations sequence: string - name: raw_response dtype: string splits: - name: train num_bytes: 89215 num_examples: 10 download_size: 28013 dataset_size: 89215 - config_name: single_shot_questions features: - name: chunk_id dtype: string - name: document_id dtype: string - name: question dtype: string - name: self_answer dtype: string - name: estimated_difficulty dtype: int64 - name: self_assessed_question_type dtype: string - name: generating_model dtype: string - name: thought_process dtype: string - name: raw_response dtype: string - name: citations sequence: string splits: - name: train num_bytes: 235536 num_examples: 40 download_size: 46497 dataset_size: 235536 - 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: raw_document_summary dtype: string - name: document_summary dtype: string - name: summarization_model dtype: string splits: - name: train num_bytes: 23129 num_examples: 2 download_size: 28027 dataset_size: 23129 configs: - config_name: chunked data_files: - split: train path: chunked/train-* - config_name: ingested data_files: - split: train path: ingested/train-* - config_name: lighteval data_files: - split: train path: lighteval/train-* - config_name: multi_hop_questions data_files: - split: train path: multi_hop_questions/train-* - config_name: single_shot_questions data_files: - split: train path: single_shot_questions/train-* - config_name: summarized data_files: - split: train path: summarized/train-* ---

应用场景：