open-llm-leaderboard/details_LeroyDyer__Mixtral_AI_Cyber_2.0
收藏Hugging Face2024-03-28 更新2024-06-11 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_LeroyDyer__Mixtral_AI_Cyber_2.0
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LeroyDyer/Mixtral_AI_Cyber_2.0时自动创建的,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,每次运行的结果存储为特定的分割,分割名称使用运行的时间戳。此外,数据集还包含一个名为"results"的配置,用于存储所有运行的聚合结果。README还提供了加载数据集的具体代码示例,并展示了最新的评估结果。
该数据集是在评估模型LeroyDyer/Mixtral_AI_Cyber_2.0时自动创建的,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,每次运行的结果存储为特定的分割,分割名称使用运行的时间戳。此外,数据集还包含一个名为"results"的配置,用于存储所有运行的聚合结果。README还提供了加载数据集的具体代码示例,并展示了最新的评估结果。
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 LeroyDyer/Mixtral_AI_Cyber_2.0
数据集描述
- dataset_summary: 该数据集是在评估模型LeroyDyer/Mixtral_AI_Cyber_2.0的过程中自动创建的,评估过程在Open LLM Leaderboard上进行。
数据集组成
- 数据结构: 由63个配置组成,每个配置对应一个评估任务。
- 数据来源: 数据集来源于1次运行,每次运行作为一个特定的分割存储,分割名称为运行的时间戳。
- 特殊配置: 包含一个名为"results"的额外配置,用于存储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。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_LeroyDyer__Mixtral_AI_Cyber_2.0", "harness_winogrande_5", split="train")
最新结果
- 结果来源: 最新结果来自run 2024-03-28T10:38:15.886070。
- 结果内容: 包括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_03_28T10_38_15.886070
- path: /details_harness|arc:challenge|25_2024-03-28T10-38-15.886070.parquet
- split: latest
- path: /details_harness|arc:challenge|25_2024-03-28T10-38-15.886070.parquet
- split: 2024_03_28T10_38_15.886070
- data_files:
-
config_name: harness_gsm8k_5
- data_files:
- split: 2024_03_28T10_38_15.886070
- path: /details_harness|gsm8k|5_2024-03-28T10-38-15.886070.parquet
- split: latest
- path: /details_harness|gsm8k|5_2024-03-28T10-38-15.886070.parquet
- split: 2024_03_28T10_38_15.886070
- data_files:
-
config_name: harness_hellaswag_10
- data_files:
- split: 2024_03_28T10_38_15.886070
- path: /details_harness|hellaswag|10_2024-03-28T10-38-15.886070.parquet
- split: latest
- path: /details_harness|hellaswag|10_2024-03-28T10-38-15.886070.parquet
- split: 2024_03_28T10_38_15.886070
- data_files:
-
config_name: harness_hendrycksTest_5
- data_files:
- split: 2024_03_28T10_38_15.886070
- path:
- /details_harness|hendrycksTest-abstract_algebra|5_2024-03-28T10-38-15.886070.parquet
- /details_harness|hendrycksTest-anatomy|5_2024-03-28T10-38-15.886070.parquet
- /details_harness|hendrycksTest-astronomy|5_2024-03-28T10-38-15.886070.parquet
- /details_harness|hendrycksTest-business_ethics|5_2024-03-28T10-38-15.886070.parquet
- /details_harness|hendrycksTest-clinical_knowledge|5_2024-03-28T10-38-15.886070.parquet
- /details_harness|hendrycksTest-college_biology|5_2024-03-28T10-38-15.886070.parquet
- /details_harness|hendrycksTest-college_chemistry|5_2024-03-28T10-38-15.886070.parquet
- /details_harness|hendrycksTest-college_computer_science|5_2024-03-28T10-38-15.886070.parquet
- /details_harness|hendrycksTest-college_mathematics|5_2024-03-28T10-38-15.886070.parquet
- /details_harness|hendrycksTest-college_medicine|5_2024-03-28T10-38-15.886070.parquet
- /details_harness|hendrycksTest-college_physics|5_2024-03-28T10-38-15.886070.parquet
- /details_harness|hendrycksTest-computer_security|5_2024-03-28T10-38-15.886070.parquet
- /details_harness|hendrycksTest-conceptual_physics|5_2024-03-28T10-38-15.886070.parquet
- /details_harness|hendrycksTest-econometrics|5_2024-03-28T10-38-15.886070.parquet
- /details_harness|hendrycksTest-electrical_engineering|5_2024-03-28T10-38-15.886070.parquet
- /details_harness|hendrycksTest-elementary_mathematics|5_2024-03-28T10-38-15.886070.parquet
- /details_harness|hendrycksTest-formal_logic|5_2024-03-28T10-38-15.886070.parquet
- /details_harness|hendrycksTest-global_facts|5_2024-03-28T10-38-15.886070.parquet
- /details_harness|hendrycksTest-high_school_biology|5_2024-03-28T10-38-15.886070.parquet
- path:
- split: latest
- path:
- /details_harness|hendrycksTest-abstract_algebra|5_2024-03-28T10-38-15.886070.parquet
- /details_harness|hendrycksTest-anatomy|5_2024-03-28T10-38-15.886070.parquet
- /details_harness|hendrycksTest-astronomy|5_2024-03-28T10-38-15.886070.parquet
- /details_harness|hendrycksTest-business_ethics|5_2024-03-28T10-38-15.886070.parquet
- /details_harness|hendrycksTest-clinical_knowledge|5_2024-03-28T10-38-15.886070.parquet
- /details_harness|hendrycksTest-college_biology|5_2024-03-28T10-38-15.886070.parquet
- /details_harness|hendrycksTest-college_chemistry|5_2024-03-28T10-38-15.886070.parquet
- /details_harness|hendrycksTest-college_computer_science|5_2024-03-28T10-38-15.886070.parquet
- /details_harness|hendrycksTest-college_mathematics|5_2024-03-28T10-38-15.886070.parquet
- /details_harness|hendrycksTest-college_medicine|5_2024-03-28T10-38-15.886070.parquet
- /details_harness|hendrycksTest-college_physics|5_2024-03-28T10-38-15.886070.parquet
- /details_harness|hendrycksTest-computer_security|5_2024-03-28T10-38-15.886070.parquet
- /details_harness|hendrycksTest-conceptual_physics|5_2024-03-28T10-38-15.886070.parquet
- /details_harness|hendrycksTest-econometrics|5_2024-03-28T10-38-15.886070.parquet
- /details_harness|hendrycksTest-electrical_engineering|5_2024-03-28T10-38-15.886070.parquet
- /details_harness|hendrycksTest-elementary_mathematics|5_2024-03-28T10-38-15.886070.parquet
- /details_harness|hendrycksTest-formal_logic|5_2024-03-28T10-38-15.886070.parquet
- /details_harness|hendrycksTest-global_facts|5_2024-03-28T10-38-15.886070.parquet
- /details_harness|hendrycksTest-high_school_biology|5_2024-03-28T10-38-15.886070.parquet
- path:
- split: 2024_03_28T10_38_15.886070
- data_files:



