five

open-llm-leaderboard/details_ALBADDAWI__DeepCode-7B-Aurora-v12

收藏
Hugging Face2024-04-15 更新2024-06-12 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_ALBADDAWI__DeepCode-7B-Aurora-v12
下载链接
链接失效反馈
官方服务:
资源简介:
该数据集是在Open LLM Leaderboard上对模型ALBADDAWI/DeepCode-7B-Aurora-v12进行评估时自动创建的。它由63个配置组成,每个配置对应一个评估任务。数据集是从1次运行中创建的,每次运行在每个配置中作为一个特定的分割,使用运行的时间戳命名。train分割始终指向最新的结果。一个额外的配置results存储了所有运行的聚合结果,用于计算和显示Open LLM Leaderboard上的聚合指标。

该数据集是在Open LLM Leaderboard上对模型ALBADDAWI/DeepCode-7B-Aurora-v12进行评估时自动创建的。它由63个配置组成,每个配置对应一个评估任务。数据集是从1次运行中创建的,每次运行在每个配置中作为一个特定的分割,使用运行的时间戳命名。train分割始终指向最新的结果。一个额外的配置results存储了所有运行的聚合结果,用于计算和显示Open LLM Leaderboard上的聚合指标。
提供机构:
open-llm-leaderboard
原始信息汇总

数据集概述

数据集名称

  • pretty_name: Evaluation run of ALBADDAWI/DeepCode-7B-Aurora-v12

数据集描述

  • dataset_summary: 该数据集是在评估模型ALBADDAWI/DeepCode-7B-Aurora-v12运行期间自动创建的。数据集包含63个配置,每个配置对应一个评估任务。数据集由1次运行创建,每次运行可以在每个配置中找到特定的分割,分割名称使用运行的时间戳。"train"分割始终指向最新结果。此外,还有一个名为"results"的配置,存储所有运行的聚合结果,用于计算并在Open LLM Leaderboard上显示聚合指标。

数据集加载示例

python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_ALBADDAWI__DeepCode-7B-Aurora-v12", "harness_winogrande_5", split="train")

最新结果

  • latest_results: 最新结果来自2024-04-15T12:09:06.672545的运行,包含多个任务的评估结果,如准确率(acc)、标准误差(acc_stderr)等。

数据集配置详情

配置列表

  • config_name: harness_arc_challenge_25

    • data_files:
      • split: 2024_04_15T12_09_06.672545
        • path: /details_harness|arc:challenge|25_2024-04-15T12-09-06.672545.parquet
      • split: latest
        • path: /details_harness|arc:challenge|25_2024-04-15T12-09-06.672545.parquet
  • config_name: harness_gsm8k_5

    • data_files:
      • split: 2024_04_15T12_09_06.672545
        • path: /details_harness|gsm8k|5_2024-04-15T12-09-06.672545.parquet
      • split: latest
        • path: /details_harness|gsm8k|5_2024-04-15T12-09-06.672545.parquet
  • config_name: harness_hellaswag_10

    • data_files:
      • split: 2024_04_15T12_09_06.672545
        • path: /details_harness|hellaswag|10_2024-04-15T12-09-06.672545.parquet
      • split: latest
        • path: /details_harness|hellaswag|10_2024-04-15T12-09-06.672545.parquet
  • config_name: harness_hendrycksTest_5

    • data_files:
      • split: 2024_04_15T12_09_06.672545
        • path:
          • /details_harness|hendrycksTest-abstract_algebra|5_2024-04-15T12-09-06.672545.parquet
          • /details_harness|hendrycksTest-anatomy|5_2024-04-15T12-09-06.672545.parquet
          • /details_harness|hendrycksTest-astronomy|5_2024-04-15T12-09-06.672545.parquet
          • /details_harness|hendrycksTest-business_ethics|5_2024-04-15T12-09-06.672545.parquet
          • /details_harness|hendrycksTest-clinical_knowledge|5_2024-04-15T12-09-06.672545.parquet
          • /details_harness|hendrycksTest-college_biology|5_2024-04-15T12-09-06.672545.parquet
          • /details_harness|hendrycksTest-college_chemistry|5_2024-04-15T12-09-06.672545.parquet
          • /details_harness|hendrycksTest-college_computer_science|5_2024-04-15T12-09-06.672545.parquet
          • /details_harness|hendrycksTest-college_mathematics|5_2024-04-15T12-09-06.672545.parquet
          • /details_harness|hendrycksTest-college_medicine|5_2024-04-15T12-09-06.672545.parquet
          • /details_harness|hendrycksTest-college_physics|5_2024-04-15T12-09-06.672545.parquet
          • /details_harness|hendrycksTest-computer_security|5_2024-04-15T12-09-06.672545.parquet
          • /details_harness|hendrycksTest-conceptual_physics|5_2024-04-15T12-09-06.672545.parquet
          • /details_harness|hendrycksTest-econometrics|5_2024-04-15T12-09-06.672545.parquet
          • /details_harness|hendrycksTest-electrical_engineering|5_2024-04-15T12-09-06.672545.parquet
          • /details_harness|hendrycksTest-elementary_mathematics|5_2024-04-15T12-09-06.672545.parquet
          • /details_harness|hendrycksTest-formal_logic|5_2024-04-15T12-09-06.672545.parquet
          • /details_harness|hendrycksTest-global_facts|5_2024-04-15T12-09-06.672545.parquet
      • split: latest
        • path:
          • /details_harness|hendrycksTest-abstract_algebra|5_2024-04-15T12-09-06.672545.parquet
          • /details_harness|hendrycksTest-anatomy|5_2024-04-15T12-09-06.672545.parquet
          • /details_harness|hendrycksTest-astronomy|5_2024-04-15T12-09-06.672545.parquet
          • /details_harness|hendrycksTest-business_ethics|5_2024-04-15T12-09-06.672545.parquet
          • /details_harness|hendrycksTest-clinical_knowledge|5_2024-04-15T12-09-06.672545.parquet
          • /details_harness|hendrycksTest-college_biology|5_2024-04-15T12-09-06.672545.parquet
          • /details_harness|hendrycksTest-college_chemistry|5_2024-04-15T12-09-06.672545.parquet
          • /details_harness|hendrycksTest-college_computer_science|5_2024-04-15T12-09-06.672545.parquet
          • /details_harness|hendrycksTest-college_mathematics|5_2024-04-15T12-09-06.672545.parquet
          • /details_harness|hendrycksTest-college_medicine|5_2024-04-15T12-09-06.672545.parquet
          • /details_harness|hendrycksTest-college_physics|5_2024-04-15T12-09-06.672545.parquet
          • /details_harness|hendrycksTest-computer_security|5_2024-04-15T12-09-06.672545.parquet
          • /details_harness|hendrycksTest-conceptual_physics|5_2024-04-15T12-09-06.672545.parquet
          • /details_harness|hendrycksTest-econometrics|5_2024-04-15T12-09-06.672545.parquet
          • /details_harness|hendrycksTest-electrical_engineering|5_2024-04-15T12-09-06.672545.parquet
          • /details_harness|hendrycksTest-elementary_mathematics|5_2024-04-15T12-09-06.672545.parquet
          • /details_harness|hendrycksTest-formal_logic|5_2024-04-15T12-09-06.672545.parquet
          • /details_harness|hendrycksTest-global_facts|5_2024-04-15T12-09-06.672545.parquet
5,000+
优质数据集
54 个
任务类型
进入经典数据集
二维码
社区交流群

面向社区/商业的数据集话题

二维码
科研交流群

面向高校/科研机构的开源数据集话题

数据驱动未来

携手共赢发展

商业合作