OALL/details_meta-llama__Llama-3.1-8B

这是一个自动创建的评估数据集，用于评估模型meta-llama/Llama-3.1-8B。数据集由136个配置组成，每个配置对应一个评估任务。数据集是从一次运行中创建的，每次运行的每个结果都作为特定拆分存储，并使用运行的戳记命名。还有一个名为results的附加配置，用于存储所有运行的聚合结果。可以使用datasets库中的load_dataset函数加载数据集。README中还包含了如何从特定运行加载数据的示例，并提供了一个指向最新结果的链接。

This is an automatically created evaluation dataset for the model meta-llama/Llama-3.1-8B. The dataset consists of 136 configurations, each corresponding to an evaluated task. The dataset was created from a single run, with each runs results stored as a specific split named by the timestamp. There is also an additional configuration called results that stores aggregated results. The dataset can be loaded using the load_dataset function from the datasets library. The README also includes examples of how to load data from a specific run and provides a link to the latest results.