five

open-llm-leaderboard/details_allknowingroger__MultiverseEx26-7B-slerp

收藏
Hugging Face2024-04-10 更新2024-04-19 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_allknowingroger__MultiverseEx26-7B-slerp
下载链接
链接失效反馈
官方服务:
资源简介:
该数据集是在模型 allknowingroger/MultiverseEx26-7B-slerp 在 Open LLM Leaderboard 上的评估运行期间自动创建的。数据集由 63 个配置组成,每个配置对应一个被评估的任务。数据集是从 1 次运行中生成的,每次运行在每个配置中表示为特定的分割,train 分割始终指向最新结果。一个名为 results 的额外配置存储了运行的所有聚合结果,用于计算和显示 Open LLM Leaderboard 上的聚合指标。README 还包含一个 Python 代码片段,展示了如何从运行中加载详细信息,并提供了特定运行的最新结果。
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 allknowingroger/MultiverseEx26-7B-slerp

数据集描述

数据集组成

  • 配置数量: 63个配置
  • 数据来源: 来自1次运行
  • 数据分割: 每个配置中包含特定分割,分割名称基于运行的时间戳。"train"分割指向最新结果。
  • 额外配置: “results”配置存储了所有聚合的运行结果,用于计算和显示Open LLM Leaderboard上的聚合指标。

数据集加载示例

python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_allknowingroger__MultiverseEx26-7B-slerp", "harness_winogrande_5", split="train")

最新结果

  • 结果来源: 来自2024-04-10T21:45:43.672625的运行
  • 结果内容: 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_10T21_45_43.672625
        • path: /details_harness|arc:challenge|25_2024-04-10T21-45-43.672625.parquet
      • split: latest
        • path: /details_harness|arc:challenge|25_2024-04-10T21-45-43.672625.parquet
  • config_name: harness_gsm8k_5

    • data_files:
      • split: 2024_04_10T21_45_43.672625
        • path: /details_harness|gsm8k|5_2024-04-10T21-45-43.672625.parquet
      • split: latest
        • path: /details_harness|gsm8k|5_2024-04-10T21-45-43.672625.parquet
  • config_name: harness_hellaswag_10

    • data_files:
      • split: 2024_04_10T21_45_43.672625
        • path: /details_harness|hellaswag|10_2024-04-10T21-45-43.672625.parquet
      • split: latest
        • path: /details_harness|hellaswag|10_2024-04-10T21-45-43.672625.parquet
  • config_name: harness_hendrycksTest_5

    • data_files:
      • split: 2024_04_10T21_45_43.672625
        • path:
          • /details_harness|hendrycksTest-abstract_algebra|5_2024-04-10T21-45-43.672625.parquet
          • /details_harness|hendrycksTest-anatomy|5_2024-04-10T21-45-43.672625.parquet
          • /details_harness|hendrycksTest-astronomy|5_2024-04-10T21-45-43.672625.parquet
          • /details_harness|hendrycksTest-business_ethics|5_2024-04-10T21-45-43.672625.parquet
          • /details_harness|hendrycksTest-clinical_knowledge|5_2024-04-10T21-45-43.672625.parquet
          • /details_harness|hendrycksTest-college_biology|5_2024-04-10T21-45-43.672625.parquet
          • /details_harness|hendrycksTest-college_chemistry|5_2024-04-10T21-45-43.672625.parquet
          • /details_harness|hendrycksTest-college_computer_science|5_2024-04-10T21-45-43.672625.parquet
          • /details_harness|hendrycksTest-college_mathematics|5_2024-04-10T21-45-43.672625.parquet
          • /details_harness|hendrycksTest-college_medicine|5_2024-04-10T21-45-43.672625.parquet
          • /details_harness|hendrycksTest-college_physics|5_2024-04-10T21-45-43.672625.parquet
          • /details_harness|hendrycksTest-computer_security|5_2024-04-10T21-45-43.672625.parquet
          • /details_harness|hendrycksTest-conceptual_physics|5_2024-04-10T21-45-43.672625.parquet
          • /details_harness|hendrycksTest-econometrics|5_2024-04-10T21-45-43.672625.parquet
          • /details_harness|hendrycksTest-electrical_engineering|5_2024-04-10T21-45-43.672625.parquet
          • /details_harness|hendrycksTest-elementary_mathematics|5_2024-04-10T21-45-43.672625.parquet
          • /details_harness|hendrycksTest-formal_logic|5_2024-04-10T21-45-43.672625.parquet
          • /details_harness|hendrycksTest-global_facts|5_2024-04-10T21-45-43.672625.parquet
      • split: latest
        • path:
          • /details_harness|hendrycksTest-abstract_algebra|5_2024-04-10T21-45-43.672625.parquet
          • /details_harness|hendrycksTest-anatomy|5_2024-04-10T21-45-43.672625.parquet
          • /details_harness|hendrycksTest-astronomy|5_2024-04-10T21-45-43.672625.parquet
          • /details_harness|hendrycksTest-business_ethics|5_2024-04-10T21-45-43.672625.parquet
          • /details_harness|hendrycksTest-clinical_knowledge|5_2024-04-10T21-45-43.672625.parquet
          • /details_harness|hendrycksTest-college_biology|5_2024-04-10T21-45-43.672625.parquet
          • /details_harness|hendrycksTest-college_chemistry|5_2024-04-10T21-45-43.672625.parquet
          • /details_harness|hendrycksTest-college_computer_science|5_2024-04-10T21-45-43.672625.parquet
          • /details_harness|hendrycksTest-college_mathematics|5_2024-04-10T21-45-43.672625.parquet
          • /details_harness|hendrycksTest-college_medicine|5_2024-04-10T21-45-43.672625.parquet
          • /details_harness|hendrycksTest-college_physics|5_2024-04-10T21-45-43.672625.parquet
          • /details_harness|hendrycksTest-computer_security|5_2024-04-10T21-45-43.672625.parquet
          • /details_harness|hendrycksTest-conceptual_physics|5_2024-04-10T21-45-43.672625.parquet
          • /details_harness|hendrycksTest-econometrics|5_2024-04-10T21-45-43.672625.parquet
          • /details_harness|hendrycksTest-electrical_engineering|5_2024-04-10T21-45-43.672625.parquet
          • /details_harness|hendrycksTest-elementary_mathematics|5_2024-04-10T21-45-43.672625.parquet
          • /details_harness|hendrycksTest-formal_logic|5_2024-04-10T21-45-43.672625.parquet
          • /details_harness|hendrycksTest-global_facts|5_2024-04-10T21-45-43.672625.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