OALL/details_TareksLab__Thalassic-Alpha-LLaMa-70B

数据集是在评估模型[TareksLab/Thalassic-Alpha-LLaMa-70B](https://huggingface.co/TareksLab/Thalassic-Alpha-LLaMa-70B)时自动创建的。数据集由136个配置组成，每个配置对应一个评估任务。数据集由1次运行创建，每次运行都可以作为一个特定的分割找到，分割的名称使用运行的时戳。"train"分割始终指向最新的结果。还有一个额外的配置"results"存储了所有运行的综合结果。文件还包括使用Python和Hugging Face数据集库加载数据运行详情的示例。最新运行的结果也包括在内，包括各种任务的准确性和标准误差。

Dataset automatically created during the evaluation run of model [TareksLab/Thalassic-Alpha-LLaMa-70B](https://huggingface.co/TareksLab/Thalassic-Alpha-LLaMa-70B). The dataset is composed of 136 configurations, each corresponding to one of the evaluated tasks. The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run. The "train" split is always pointing to the latest results. An additional configuration "results" store all the aggregated results of the run. To load the details from a run, you can for instance do the following: python
from datasets import load_dataset
data = load_dataset("OALL/details_TareksLab__Thalassic-Alpha-LLaMa-70B", "lighteval_xstory_cloze_ar_0_2025_02_07T04_23_40_239486_parquet", split="train")