OALL/details_Navid-AI__Yehia-7B-preview_v2_alrage

在模型Navid-AI/Yehia-7B-preview评估过程中自动创建的数据集，包含一个配置，每个配置对应于一个评估任务。数据集由两次运行创建，每次运行都作为一个特定的时间戳命名的配置中的split。train split始终指向最新的结果。此外，还有一个results配置，用于存储所有运行聚合的结果。Dataset automatically created during the evaluation of model Navid-AI/Yehia-7B-preview, containing one configuration corresponding to each evaluated task. The dataset is created from two runs, each run as a specific split named with a timestamp in the configuration. The train split always points to the latest results. Additionally, there is a results configuration that stores the aggregated results of all runs.