OALL/details_yunconglong__MoE_13B_DPO

该数据集是在模型yunconglong/MoE_13B_DPO的评估运行过程中自动创建的。数据集由136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，分割名称使用运行的时间戳。train分割始终指向最新结果。此外，还有一个results配置存储了所有运行的聚合结果。

The dataset is automatically created during the evaluation run of the model yunconglong/MoE_13B_DPO. It consists of 136 configurations, each corresponding to an evaluated task. The dataset has been created from one run, with each run being a specific split named by the timestamp of the run. The train split always points to the latest results. An additional results configuration stores all the aggregated results of the run. The dataset includes detailed accuracy metrics for various tasks, indicating the performance of the model on different aspects of Arabic culture, history, and other domains.