gagan3012/LongBench

--- dataset_info: - config_name: 2wikimqa_ar features: - name: input dtype: string - name: context dtype: string - name: answers list: string - name: length dtype: int32 - name: dataset dtype: string - name: language dtype: string - name: all_classes list: string - name: _id dtype: string - name: input_ar dtype: string - name: answers_ar sequence: string - name: context_ar dtype: string splits: - name: test num_bytes: 14789049 num_examples: 200 download_size: 8011297 dataset_size: 14789049 - config_name: hotpotqa_ar features: - name: input dtype: string - name: context dtype: string - name: answers list: string - name: length dtype: int32 - name: dataset dtype: string - name: language dtype: string - name: all_classes list: string - name: _id dtype: string - name: input_ar dtype: string - name: answers_ar sequence: string - name: context_ar dtype: string splits: - name: test num_bytes: 28544820 num_examples: 200 download_size: 15025719 dataset_size: 28544820 - config_name: multifieldqa_en_ar features: - name: input dtype: string - name: context dtype: string - name: answers list: string - name: length dtype: int32 - name: dataset dtype: string - name: language dtype: string - name: all_classes list: string - name: _id dtype: string - name: input_ar dtype: string - name: answers_ar sequence: string splits: - name: test num_bytes: 4458347 num_examples: 150 download_size: 1864752 dataset_size: 4458347 - config_name: musique_ar features: - name: input dtype: string - name: context dtype: string - name: answers list: string - name: length dtype: int32 - name: dataset dtype: string - name: language dtype: string - name: all_classes list: string - name: _id dtype: string - name: input_ar dtype: string - name: answers_ar sequence: string - name: context_ar dtype: string splits: - name: test num_bytes: 35195736 num_examples: 200 download_size: 18409597 dataset_size: 35195736 - config_name: narrativeqa_ar features: - name: input dtype: string - name: context dtype: string - name: answers list: string - name: length dtype: int32 - name: dataset dtype: string - name: language dtype: string - name: all_classes list: string - name: _id dtype: string - name: input_ar dtype: string - name: answers_ar sequence: string - name: context_ar dtype: string splits: - name: test num_bytes: 52355382 num_examples: 200 download_size: 3206743 dataset_size: 52355382 - config_name: qasper_ar features: - name: input dtype: string - name: context dtype: string - name: answers list: string - name: length dtype: int32 - name: dataset dtype: string - name: language dtype: string - name: all_classes list: string - name: _id dtype: string - name: input_ar dtype: string - name: answers_ar sequence: string - name: context_ar dtype: string splits: - name: test num_bytes: 12015032 num_examples: 200 download_size: 4410764 dataset_size: 12015032 - config_name: trec_ar features: - name: input dtype: string - name: context dtype: string - name: answers list: string - name: length dtype: int32 - name: dataset dtype: string - name: language dtype: string - name: all_classes list: string - name: _id dtype: string - name: input_ar dtype: string - name: answers_ar sequence: string - name: context_ar dtype: string splits: - name: test num_bytes: 14819270 num_examples: 200 download_size: 6149046 dataset_size: 14819270 - config_name: triviaqa_ar features: - name: input dtype: string - name: context dtype: string - name: answers list: string - name: length dtype: int32 - name: dataset dtype: string - name: language dtype: string - name: all_classes list: string - name: _id dtype: string - name: input_ar dtype: string - name: answers_ar sequence: string - name: context_ar dtype: string splits: - name: test num_bytes: 25650475 num_examples: 200 download_size: 14066687 dataset_size: 25650475 configs: - config_name: 2wikimqa_ar data_files: - split: test path: 2wikimqa_ar/test-* - config_name: hotpotqa_ar data_files: - split: test path: hotpotqa_ar/test-* - config_name: multifieldqa_en_ar data_files: - split: test path: multifieldqa_en_ar/test-* - config_name: musique_ar data_files: - split: test path: musique_ar/test-* - config_name: narrativeqa_ar data_files: - split: test path: narrativeqa_ar/test-* - config_name: qasper_ar data_files: - split: test path: qasper_ar/test-* - config_name: trec_ar data_files: - split: test path: trec_ar/test-* - config_name: triviaqa_ar data_files: - split: test path: triviaqa_ar/test-* ---

原始信息汇总

数据集概述

数据集配置

2wikimqa_ar

• 特征:
  • input: string
  • context: string
  • answers: list of string
  • length: int32
  • dataset: string
  • language: string
  • all_classes: list of string
  • _id: string
  • input_ar: string
  • answers_ar: sequence of string
  • context_ar: string
• 分割:
  • test:
    • num_bytes: 14789049
    • num_examples: 200
• 下载大小: 8011297
• 数据集大小: 14789049

hotpotqa_ar

• 特征:
  • input: string
  • context: string
  • answers: list of string
  • length: int32
  • dataset: string
  • language: string
  • all_classes: list of string
  • _id: string
  • input_ar: string
  • answers_ar: sequence of string
  • context_ar: string
• 分割:
  • test:
    • num_bytes: 28544820
    • num_examples: 200
• 下载大小: 15025719
• 数据集大小: 28544820

multifieldqa_en_ar

• 特征:
  • input: string
  • context: string
  • answers: list of string
  • length: int32
  • dataset: string
  • language: string
  • all_classes: list of string
  • _id: string
  • input_ar: string
  • answers_ar: sequence of string
• 分割:
  • test:
    • num_bytes: 4458347
    • num_examples: 150
• 下载大小: 1864752
• 数据集大小: 4458347

musique_ar

• 特征:
  • input: string
  • context: string
  • answers: list of string
  • length: int32
  • dataset: string
  • language: string
  • all_classes: list of string
  • _id: string
  • input_ar: string
  • answers_ar: sequence of string
  • context_ar: string
• 分割:
  • test:
    • num_bytes: 35195736
    • num_examples: 200
• 下载大小: 18409597
• 数据集大小: 35195736

narrativeqa_ar

• 特征:
  • input: string
  • context: string
  • answers: list of string
  • length: int32
  • dataset: string
  • language: string
  • all_classes: list of string
  • _id: string
  • input_ar: string
  • answers_ar: sequence of string
  • context_ar: string
• 分割:
  • test:
    • num_bytes: 52355382
    • num_examples: 200
• 下载大小: 3206743
• 数据集大小: 52355382

qasper_ar

• 特征:
  • input: string
  • context: string
  • answers: list of string
  • length: int32
  • dataset: string
  • language: string
  • all_classes: list of string
  • _id: string
  • input_ar: string
  • answers_ar: sequence of string
  • context_ar: string
• 分割:
  • test:
    • num_bytes: 12015032
    • num_examples: 200
• 下载大小: 4410764
• 数据集大小: 12015032

trec_ar

• 特征:
  • input: string
  • context: string
  • answers: list of string
  • length: int32
  • dataset: string
  • language: string
  • all_classes: list of string
  • _id: string
  • input_ar: string
  • answers_ar: sequence of string
  • context_ar: string
• 分割:
  • test:
    • num_bytes: 14819270
    • num_examples: 200
• 下载大小: 6149046
• 数据集大小: 14819270

triviaqa_ar

• 特征:
  • input: string
  • context: string
  • answers: list of string
  • length: int32
  • dataset: string
  • language: string
  • all_classes: list of string
  • _id: string
  • input_ar: string
  • answers_ar: sequence of string
  • context_ar: string
• 分割:
  • test:
    • num_bytes: 25650475
    • num_examples: 200
• 下载大小: 14066687
• 数据集大小: 25650475