open-llm-leaderboard-old/details_Kukedlc__MyModelsMerge-7b
收藏Hugging Face2024-03-29 更新2024-06-22 收录
下载链接：
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_Kukedlc__MyModelsMerge-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Open LLM Leaderboard上对模型Kukedlc/MyModelsMerge-7b进行评估时自动创建的。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，并用于计算和显示Open LLM Leaderboard上的聚合指标。
该数据集是在Open LLM Leaderboard上对模型Kukedlc/MyModelsMerge-7b进行评估时自动创建的。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，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
数据集基本信息
- 名称: Evaluation run of Kukedlc/MyModelsMerge-7b
- 来源: 自动创建于模型 Kukedlc/MyModelsMerge-7b 在 Open LLM Leaderboard 的评估运行中。
数据集结构
- 配置数量: 63
- 配置对应任务: 每个配置对应一个评估任务。
- 数据来源: 数据集由1次运行创建，每个运行结果作为特定分割存储，分割名称使用运行的时间戳。
- 最新结果: "train" 分割始终指向最新结果。
- 结果汇总: 额外的 "results" 配置存储所有运行的汇总结果，用于计算和显示在 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_Kukedlc__MyModelsMerge-7b", "harness_winogrande_5", split="train")
最新结果
- 时间戳: 2024-03-29T18:56:24.886013
- 详细结果: 包含多个任务的准确率（acc）、标准化准确率（acc_norm）、误差（stderr）等指标。
配置详情
-
配置名称: harness_arc_challenge_25
- 数据文件:
- 分割: 2024_03_29T18_56_24.886013
- 路径: **/details_harness|arc:challenge|25_2024-03-29T18-56-24.886013.parquet
- 分割: latest
- 路径: **/details_harness|arc:challenge|25_2024-03-29T18-56-24.886013.parquet
- 分割: 2024_03_29T18_56_24.886013
- 数据文件:
-
配置名称: harness_gsm8k_5
- 数据文件:
- 分割: 2024_03_29T18_56_24.886013
- 路径: **/details_harness|gsm8k|5_2024-03-29T18-56-24.886013.parquet
- 分割: latest
- 路径: **/details_harness|gsm8k|5_2024-03-29T18-56-24.886013.parquet
- 分割: 2024_03_29T18_56_24.886013
- 数据文件:
-
配置名称: harness_hellaswag_10
- 数据文件:
- 分割: 2024_03_29T18_56_24.886013
- 路径: **/details_harness|hellaswag|10_2024-03-29T18-56-24.886013.parquet
- 分割: latest
- 路径: **/details_harness|hellaswag|10_2024-03-29T18-56-24.886013.parquet
- 分割: 2024_03_29T18_56_24.886013
- 数据文件:
-
配置名称: harness_hendrycksTest_5
- 数据文件:
- 分割: 2024_03_29T18_56_24.886013
- 路径:
- **/details_harness|hendrycksTest-abstract_algebra|5_2024-03-29T18-56-24.886013.parquet
- **/details_harness|hendrycksTest-anatomy|5_2024-03-29T18-56-24.886013.parquet
- **/details_harness|hendrycksTest-astronomy|5_2024-03-29T18-56-24.886013.parquet
- **/details_harness|hendrycksTest-business_ethics|5_2024-03-29T18-56-24.886013.parquet
- **/details_harness|hendrycksTest-clinical_knowledge|5_2024-03-29T18-56-24.886013.parquet
- **/details_harness|hendrycksTest-college_biology|5_2024-03-29T18-56-24.886013.parquet
- **/details_harness|hendrycksTest-college_chemistry|5_2024-03-29T18-56-24.886013.parquet
- **/details_harness|hendrycksTest-college_computer_science|5_2024-03-29T18-56-24.886013.parquet
- **/details_harness|hendrycksTest-college_mathematics|5_2024-03-29T18-56-24.886013.parquet
- **/details_harness|hendrycksTest-college_medicine|5_2024-03-29T18-56-24.886013.parquet
- **/details_harness|hendrycksTest-college_physics|5_2024-03-29T18-56-24.886013.parquet
- **/details_harness|hendrycksTest-computer_security|5_2024-03-29T18-56-24.886013.parquet
- **/details_harness|hendrycksTest-conceptual_physics|5_2024-03-29T18-56-24.886013.parquet
- **/details_harness|hendrycksTest-econometrics|5_2024-03-29T18-56-24.886013.parquet
- **/details_harness|hendrycksTest-electrical_engineering|5_2024-03-29T18-56-24.886013.parquet
- **/details_harness|hendrycksTest-elementary_mathematics|5_2024-03-29T18-56-24.886013.parquet
- **/details_harness|hendrycksTest-formal_logic|5_2024-03-29T18-56-24.886013.parquet
- **/details_harness|hendrycksTest-global_facts|5_2024-03-29T18-56-24.886013.parquet
- **/details_harness|hendrycksTest-high_school_biology|5_2024-03-29T18-56-24.886013.parquet
- **/details_harness|hendrycksTest-high_school_chemistry|5_2024-03-29T18-56-24.886013.parquet
- **/details_harness|hendrycksTest-high_school_computer_science|5_2024-03-29T18-56-24.886013.parquet
- **/details_harness|hendrycksTest-high_school_european_history|5_2024-03-29T18-56-24.886013.parquet
- **/details_harness|hendrycksTest-high_school_geography|5_2024-03-29T18-56-24.886013.parquet
- **/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-03-29T18-56-24.886013.parquet
- **/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-03-29T18-56-24.886013.parquet
- **/details_harness|hendrycksTest-high_school_mathematics|5_2024-03-29T18-56-24.886013.parquet
- **/details_harness|hendrycksTest-high_school_microeconomics|5_2024-03-29T18-56-24.886013.parquet
- **/details_harness|hendrycksTest-high_school_physics|5_2024-03-29T18-56-24.886013.parquet
- **/details_harness|hendrycksTest-high_school_psychology|5_2024-03-29T18-56-24.886013.parquet
- **/details_harness|hendrycksTest-high_school_statistics|5_2024-03-29T18-56-24.886013.parquet
- **/details_harness|hendrycksTest-high_school_us_history|5_2024-03-29T18-56-24.886013.parquet
- **/details_harness|hendrycksTest-high_school_world_history|5_2024-03-29T18-56-24.886013.parquet
- **/details_harness|hendrycksTest-human_aging|5_2024-03-29T18-56-24.886013.parquet
- **/details_harness|hendrycksTest-human_sexuality|5_2024-03-29T18-56-24.886013.parquet
- **/details_harness|hendrycksTest-international_law|5_2024-03-29T18-56-24.886013.parquet
- **/details_harness|hendrycksTest-jurisprudence|5_2024-03-29T18-56-24.886013.parquet
- **/details_harness|hendrycksTest-logical_fallacies|5_2024-03-29T18-56-24.886013.parquet
- **/details_harness|hendrycksTest-machine_learning|5_2024-03-29T18-56-24.886013.parquet
- **/details_harness|hendrycksTest-management|5_2024-03-29T18-56-24.886013.parquet
- **/details_harness|hendrycksTest-marketing|5_2024-03-29T18-56-24.886013.parquet
- **/details_harness|hendrycksTest-medical_genetics|5_2024-03-29T18-56-24.886013.parquet
- **/details_harness|hendrycksTest-miscellaneous|5_2024-03-29T18-56-24.886013.parquet
- **/details_harness|hendrycksTest-moral_disputes|5_2024-03-29T18-56-24.886013.parquet
- **/details_harness|hendrycksTest-moral_scenarios|5_2024-03-29T18-56-24.886013.parquet
- **/details_harness|hendrycksTest-nutrition|5_2024-03-29T18-56-24.886013.parquet
- **/details_harness|hendrycksTest-philosophy|5_2024-03-29T18-56-24.886013.parquet
- **/details_harness|hendrycksTest-prehistory|5_2024-03-29T18-56-24.886013.parquet
- **/details_harness|hendrycksTest-professional_accounting|5_2024-03-29T18-56-24.886013.parquet
- **/details_harness|hendrycksTest-professional_law|5_2024-03-29T18-56-24.886013.parquet
- **/details_harness|hendrycksTest-professional_medicine|5_2024-03-29T18-56-24.886013.parquet
- **/details_harness|hendrycksTest-professional_psychology|5_2024-03-29T18-56-24.886013.parquet
- **/details_harness|hendrycksTest-public_relations|5_2024-03-29T18-56-24.886013.parquet
- **/details_harness|hendrycksTest-security_studies|5_2024-03-29T18-56-24.886013.parquet
- **/details_harness|hendrycksTest-sociology|5_2024-03-29T18-56-24.886013.parquet
- **/details_harness|hendrycksTest-us_foreign_policy|5_2024-03-29T18-56-24.886013.parquet
- **/details_harness|hendrycksTest-virology|5_2024-03-29T18-56-24.886013.parquet
- **/details_harness|hendrycksTest-world_religions|5_2024-03-29T18-56-24.886013.parquet
- 路径:
- 分割: latest
- 路径:
- **/details_harness|hendrycksTest-abstract_algebra|5_2024-03-29T18-56-24.886013.parquet
- **/details_harness|hendrycksTest-anatomy|5_2024-03-29T18-56-24.886013.parquet
- **/details_harness|hendrycksTest-astronomy|5_2024-03-29T18-56-24.886013.parquet
- **/details_har
- 路径:
- 分割: 2024_03_29T18_56_24.886013
- 数据文件:
