OALL/details_failspy__Codestral-22B-v0.1-abliterated-v3

该数据集是在模型 failspy/Codestral-22B-v0.1-abliterated-v3 的评估运行期间自动创建的。数据集由136个配置组成，每个配置对应一个被评估的任务。数据集是从1次运行中创建的，每次运行在每个配置中表示为特定的分割，分割名称使用运行的时间戳。train 分割始终指向最新的结果。另外，results 配置存储了所有运行的聚合结果。README 还提供了一个如何使用 Python 中的 datasets 库加载运行细节的示例。

Dataset automatically created during the evaluation run of model [failspy/Codestral-22B-v0.1-abliterated-v3]. It is composed of 136 configurations, each corresponding to one of the evaluated tasks. The dataset has been created from one run, with each run represented as a specific split named using the timestamp of the run. The train split always points to the latest results. An additional configuration named results stores all the aggregated results of the run. The dataset includes detailed results from various tasks, each with accuracy metrics and standard errors.