five

open-llm-leaderboard-old/details_Inv__Konstanta-7B

收藏
Hugging Face2024-02-03 更新2024-06-22 收录
下载链接：
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_Inv__Konstanta-7B
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Inv/Konstanta-7B的评估运行期间自动创建的，用于在Open LLM Leaderboard上进行评估。数据集由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，每次运行都可以在特定配置中找到，分割以运行的时间戳命名。train分割始终指向最新结果。此外，results配置存储了所有运行的聚合结果，并用于计算和显示Open LLM Leaderboard上的聚合指标。

该数据集是在模型Inv/Konstanta-7B的评估运行期间自动创建的，用于在Open LLM Leaderboard上进行评估。数据集由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，每次运行都可以在特定配置中找到，分割以运行的时间戳命名。train分割始终指向最新结果。此外，results配置存储了所有运行的聚合结果，并用于计算和显示Open LLM Leaderboard上的聚合指标。
提供机构：
open-llm-leaderboard-old
原始信息汇总

数据集概述

数据集名称

Evaluation run of Inv/Konstanta-7B

数据集描述

该数据集是在模型 Inv/Konstanta-7B 在 Open LLM Leaderboard 上的评估运行期间自动创建的。

数据集组成

数据集由 63 个配置组成，每个配置对应一个评估任务。数据集从 1 次运行中创建，每个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" 分割总是指向最新的结果。

额外配置

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）。

数据加载示例

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

最新结果

这些是最新的结果，来自 2024-02-03T22:20:39.657096 的运行。

配置详情

  • config_name: harness_arc_challenge_25

    • data_files:
      • split: 2024_02_03T22_20_39.657096
        • path: **/details_harness|arc:challenge|25_2024-02-03T22-20-39.657096.parquet
      • split: latest
        • path: **/details_harness|arc:challenge|25_2024-02-03T22-20-39.657096.parquet

  • config_name: harness_gsm8k_5

    • data_files:
      • split: 2024_02_03T22_20_39.657096
        • path: **/details_harness|gsm8k|5_2024-02-03T22-20-39.657096.parquet
      • split: latest
        • path: **/details_harness|gsm8k|5_2024-02-03T22-20-39.657096.parquet

  • config_name: harness_hellaswag_10

    • data_files:
      • split: 2024_02_03T22_20_39.657096
        • path: **/details_harness|hellaswag|10_2024-02-03T22-20-39.657096.parquet
      • split: latest
        • path: **/details_harness|hellaswag|10_2024-02-03T22-20-39.657096.parquet

  • config_name: harness_hendrycksTest_5

    • data_files:
      • split: 2024_02_03T22_20_39.657096
        • path:
          • **/details_harness|hendrycksTest-abstract_algebra|5_2024-02-03T22-20-39.657096.parquet
          • **/details_harness|hendrycksTest-anatomy|5_2024-02-03T22-20-39.657096.parquet
          • **/details_harness|hendrycksTest-astronomy|5_2024-02-03T22-20-39.657096.parquet
          • **/details_harness|hendrycksTest-business_ethics|5_2024-02-03T22-20-39.657096.parquet
          • **/details_harness|hendrycksTest-clinical_knowledge|5_2024-02-03T22-20-39.657096.parquet
          • **/details_harness|hendrycksTest-college_biology|5_2024-02-03T22-20-39.657096.parquet
          • **/details_harness|hendrycksTest-college_chemistry|5_2024-02-03T22-20-39.657096.parquet
          • **/details_harness|hendrycksTest-college_computer_science|5_2024-02-03T22-20-39.657096.parquet
          • **/details_harness|hendrycksTest-college_mathematics|5_2024-02-03T22-20-39.657096.parquet
          • **/details_harness|hendrycksTest-college_medicine|5_2024-02-03T22-20-39.657096.parquet
          • **/details_harness|hendrycksTest-college_physics|5_2024-02-03T22-20-39.657096.parquet
          • **/details_harness|hendrycksTest-computer_security|5_2024-02-03T22-20-39.657096.parquet
          • **/details_harness|hendrycksTest-conceptual_physics|5_2024-02-03T22-20-39.657096.parquet
          • **/details_harness|hendrycksTest-econometrics|5_2024-02-03T22-20-39.657096.parquet
          • **/details_harness|hendrycksTest-electrical_engineering|5_2024-02-03T22-20-39.657096.parquet
          • **/details_harness|hendrycksTest-elementary_mathematics|5_2024-02-03T22-20-39.657096.parquet
          • **/details_harness|hendrycksTest-formal_logic|5_2024-02-03T22-20-39.657096.parquet
          • **/details_harness|hendrycksTest-global_facts|5_2024-02-03T22-20-39.657096.parquet
          • **/details_harness|hendrycksTest-high_school_biology|5_2024-02-03T22-20-39.657096.parquet
          • **/details_harness|hendrycksTest-high_school_chemistry|5_2024-02-03T22-20-39.657096.parquet
          • **/details_harness|hendrycksTest-high_school_computer_science|5_2024-02-03T22-20-39.657096.parquet
          • **/details_harness|hendrycksTest-high_school_european_history|5_2024-02-03T22-20-39.657096.parquet
          • **/details_harness|hendrycksTest-high_school_geography|5_2024-02-03T22-20-39.657096.parquet
          • **/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-02-03T22-20-39.657096.parquet
          • **/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-02-03T22-20-39.657096.parquet
          • **/details_harness|hendrycksTest-high_school_mathematics|5_2024-02-03T22-20-39.657096.parquet
          • **/details_harness|hendrycksTest-high_school_microeconomics|5_2024-02-03T22-20-39.657096.parquet
          • **/details_harness|hendrycksTest-high_school_physics|5_2024-02-03T22-20-39.657096.parquet
          • **/details_harness|hendrycksTest-high_school_psychology|5_2024-02-03T22-20-39.657096.parquet
          • **/details_harness|hendrycksTest-high_school_statistics|5_2024-02-03T22-20-39.657096.parquet
          • **/details_harness|hendrycksTest-high_school_us_history|5_2024-02-03T22-20-39.657096.parquet
          • **/details_harness|hendrycksTest-high_school_world_history|5_2024-02-03T22-20-39.657096.parquet
          • **/details_harness|hendrycksTest-human_aging|5_2024-02-03T22-20-39.657096.parquet
          • **/details_harness|hendrycksTest-human_sexuality|5_2024-02-03T22-20-39.657096.parquet
          • **/details_harness|hendrycksTest-international_law|5_2024-02-03T22-20-39.657096.parquet
          • **/details_harness|hendrycksTest-jurisprudence|5_2024-02-03T22-20-39.657096.parquet
          • **/details_harness|hendrycksTest-logical_fallacies|5_2024-02-03T22-20-39.657096.parquet
          • **/details_harness|hendrycksTest-machine_learning|5_2024-02-03T22-20-39.657096.parquet
          • **/details_harness|hendrycksTest-management|5_2024-02-03T22-20-39.657096.parquet
          • **/details_harness|hendrycksTest-marketing|5_2024-02-03T22-20-39.657096.parquet
          • **/details_harness|hendrycksTest-medical_genetics|5_2024-02-03T22-20-39.657096.parquet
          • **/details_harness|hendrycksTest-miscellaneous|5_2024-02-03T22-20-39.657096.parquet
          • **/details_harness|hendrycksTest-moral_disputes|5_2024-02-03T22-20-39.657096.parquet
          • **/details_harness|hendrycksTest-moral_scenarios|5_2024-02-03T22-20-39.657096.parquet
          • **/details_harness|hendrycksTest-nutrition|5_2024-02-03T22-20-39.657096.parquet
          • **/details_harness|hendrycksTest-philosophy|5_2024-02-03T22-20-39.657096.parquet
          • **/details_harness|hendrycksTest-prehistory|5_2024-02-03T22-20-39.657096.parquet
          • **/details_harness|hendrycksTest-professional_accounting|5_2024-02-03T22-20-39.657096.parquet
          • **/details_harness|hendrycksTest-professional_law|5_2024-02-03T22-20-39.657096.parquet
          • **/details_harness|hendrycksTest-professional_medicine|5_2024-02-03T22-20-39.657096.parquet
          • **/details_harness|hendrycksTest-professional_psychology|5_2024-02-03T22-20-39.657096.parquet
          • **/details_harness|hendrycksTest-public_relations|5_2024-02-03T22-20-39.657096.parquet
          • **/details_harness|hendrycksTest-security_studies|5_2024-02-03T22-20-39.657096.parquet
          • **/details_harness|hendrycksTest-sociology|5_2024-02-03T22-20-39.657096.parquet
          • **/details_harness|hendrycksTest-us_foreign_policy|5_2024-02-03T22-20-39.657096.parquet
          • **/details_harness|hendrycksTest-virology|5_2024-02-03T22-20-39.657096.parquet
          • **/details_harness|hendrycksTest-world_religions|5_2024-02-03T22-20-39.657096.parquet
      • split: latest
        • path:
          • **/details_harness|hendrycksTest-abstract_algebra|5_2024-02-03T22-20-39.657096.parquet
          • **/details_harness|hendrycksTest-anatomy|5_2024-02-03T22-20-39.657096.parquet
          • **/details_harness|hendrycksTest-astronomy|5_2024-02-03T22-20-39.657096.parquet
          • **/details_harness|hendrycksTest-business_ethics|5_2024-02-03T22-20-39.657096.parquet
5,000+
优质数据集
54 个
任务类型
进入经典数据集
关于我们
遇见数据集——让每个数据集都被发现，让每一次遇见都有价值。
数发科官网www.sfktec.com.cn
联系我们
youjian
selectdataset@iotsh.com.cn
商业合作
数据驱动未来，携手共赢发展
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