five

open-llm-leaderboard/details_MysteriousAI__Mia-1B

收藏
Hugging Face2024-04-06 更新2024-06-11 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_MysteriousAI__Mia-1B
下载链接
链接失效反馈
官方服务:
资源简介:
该数据集是在评估模型MysteriousAI/Mia-1B时自动创建的,用于在Open LLM Leaderboard上进行评估。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次运行生成,每次运行的结果可以在每个配置的特定分割中找到,分割名称使用运行的时间戳命名。train分割始终指向最新的结果。此外,还有一个名为results的配置,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。

该数据集是在评估模型MysteriousAI/Mia-1B时自动创建的,用于在Open LLM Leaderboard上进行评估。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次运行生成,每次运行的结果可以在每个配置的特定分割中找到,分割名称使用运行的时间戳命名。train分割始终指向最新的结果。此外,还有一个名为results的配置,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 MysteriousAI/Mia-1B

数据集来源

数据集组成

  • 配置数量: 63
  • 配置内容: 每个配置对应一个评估任务。
  • 数据集创建: 从1次运行中创建,每次运行作为特定分割存在,分割名使用运行时间戳。
  • 特殊配置: 配置"results"存储所有聚合的运行结果,用于计算和显示聚合指标。

数据集加载示例

python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_MysteriousAI__Mia-1B", "harness_winogrande_5", split="train")

最新结果

配置详情

配置列表

  • harness_arc_challenge_25
  • harness_gsm8k_5
  • harness_hellaswag_10
  • harness_hendrycksTest_5

数据文件路径

  • harness_arc_challenge_25:

    • split: 2024_04_06T03_28_57.602483
      • path: /details_harness|arc:challenge|25_2024-04-06T03-28-57.602483.parquet
    • split: latest
      • path: /details_harness|arc:challenge|25_2024-04-06T03-28-57.602483.parquet
  • harness_gsm8k_5:

    • split: 2024_04_06T03_28_57.602483
      • path: /details_harness|gsm8k|5_2024-04-06T03-28-57.602483.parquet
    • split: latest
      • path: /details_harness|gsm8k|5_2024-04-06T03-28-57.602483.parquet
  • harness_hellaswag_10:

    • split: 2024_04_06T03_28_57.602483
      • path: /details_harness|hellaswag|10_2024-04-06T03-28-57.602483.parquet
    • split: latest
      • path: /details_harness|hellaswag|10_2024-04-06T03-28-57.602483.parquet
  • harness_hendrycksTest_5:

    • split: 2024_04_06T03_28_57.602483
      • path: /details_harness|hendrycksTest-abstract_algebra|5_2024-04-06T03-28-57.602483.parquet
        • /details_harness|hendrycksTest-anatomy|5_2024-04-06T03-28-57.602483.parquet
        • /details_harness|hendrycksTest-astronomy|5_2024-04-06T03-28-57.602483.parquet
        • /details_harness|hendrycksTest-business_ethics|5_2024-04-06T03-28-57.602483.parquet
        • /details_harness|hendrycksTest-clinical_knowledge|5_2024-04-06T03-28-57.602483.parquet
        • /details_harness|hendrycksTest-college_biology|5_2024-04-06T03-28-57.602483.parquet
        • /details_harness|hendrycksTest-college_chemistry|5_2024-04-06T03-28-57.602483.parquet
        • /details_harness|hendrycksTest-college_computer_science|5_2024-04-06T03-28-57.602483.parquet
        • /details_harness|hendrycksTest-college_mathematics|5_2024-04-06T03-28-57.602483.parquet
        • /details_harness|hendrycksTest-college_medicine|5_2024-04-06T03-28-57.602483.parquet
        • /details_harness|hendrycksTest-college_physics|5_2024-04-06T03-28-57.602483.parquet
        • /details_harness|hendrycksTest-computer_security|5_2024-04-06T03-28-57.602483.parquet
        • /details_harness|hendrycksTest-conceptual_physics|5_2024-04-06T03-28-57.602483.parquet
        • /details_harness|hendrycksTest-econometrics|5_2024-04-06T03-28-57.602483.parquet
        • /details_harness|hendrycksTest-electrical_engineering|5_2024-04-06T03-28-57.602483.parquet
        • /details_harness|hendrycksTest-elementary_mathematics|5_2024-04-06T03-28-57.602483.parquet
        • /details_harness|hendrycksTest-formal_logic|5_2024-04-06T03-28-57.602483.parquet
        • /details_harness|hendrycksTest-global_facts|5_2024-04-06T03-28-57.602483.parquet
    • split: latest
      • path: /details_harness|hendrycksTest-abstract_algebra|5_2024-04-06T03-28-57.602483.parquet
        • /details_harness|hendrycksTest-anatomy|5_2024-04-06T03-28-57.602483.parquet
        • /details_harness|hendrycksTest-astronomy|5_2024-04-06T03-28-57.602483.parquet
        • /details_harness|hendrycksTest-business_ethics|5_2024-04-06T03-28-57.602483.parquet
        • /details_harness|hendrycksTest-clinical_knowledge|5_2024-04-06T03-28-57.602483.parquet
        • /details_harness|hendrycksTest-college_biology|5_2024-04-06T03-28-57.602483.parquet
        • /details_harness|hendrycksTest-college_chemistry|5_2024-04-06T03-28-57.602483.parquet
        • /details_harness|hendrycksTest-college_computer_science|5_2024-04-06T03-28-57.602483.parquet
        • /details_harness|hendrycksTest-college_mathematics|5_2024-04-06T03-28-57.602483.parquet
        • /details_harness|hendrycksTest-college_medicine|5_2024-04-06T03-28-57.602483.parquet
        • /details_harness|hendrycksTest-college_physics|5_2024-04-06T03-28-57.602483.parquet
        • /details_harness|hendrycksTest-computer_security|5_2024-04-06T03-28-57.602483.parquet
        • /details_harness|hendrycksTest-conceptual_physics|5_2024-04-06T03-28-57.602483.parquet
        • /details_harness|hendrycksTest-econometrics|5_2024-04-06T03-28-57.602483.parquet
        • /details_harness|hendrycksTest-electrical_engineering|5_2024-04-06T03-28-57.602483.parquet
        • /details_harness|hendrycksTest-elementary_mathematics|5_2024-04-06T03-28-57.602483.parquet
        • /details_harness|hendrycksTest-formal_logic|5_2024-04-06T03-28-57.602483.parquet
        • /details_harness|hendrycksTest-global_facts|5_2024-04-06T03-28-57.602483.parquet

数据集使用说明

  • 使用load_dataset函数加载数据集,指定数据集名称、配置名称和分割类型。
  • 数据集包含多个分割,其中"train"分割指向最新结果。
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