OALL/details_Sakalti__ultiima-78B-V2

这是一个在评估模型 [Sakalti/ultiima-78B-V2](https://huggingface.co/Sakalti/ultiima-78B-V2) 时自动创建的数据集。数据集由 136 个配置组成，每个配置对应一个评估任务。它包括来自 1 次运行的成果，每次运行的数据按特定的时间戳分割。train 分割始终指向最新的结果。还有一个额外的配置 results 存储所有聚合的运行结果。文件中还提供了如何使用 Python 的 datasets 库加载数据集详细信息的示例。它还提供了来自特定运行的最新结果，显示各种任务和社区的性能指标。

Dataset automatically created during the evaluation run of model [Sakalti/ultiima-78B-V2](https://huggingface.co/Sakalti/ultiima-78B-V2). The dataset is composed of 136 configurations, each one corresponding to one of the evaluated tasks. It includes results from 1 run(s), with each runs data split available under specific timestamps. The train split always points to the latest results. There is also an additional configuration results that stores all aggregated results. The file includes examples of how to load the dataset details using the datasets library in Python. It also provides the latest results from a specific run, showing performance metrics for various tasks and communities.