LVSTCK/piqa-mk

PIQA MK版本数据集是PIQA数据集的马其顿语改编版本，原始数据集由Aleksa Gordić整理（英语到塞尔维亚语）。此数据集通过Google翻译API从塞尔维亚语翻译为马其顿语。它包含马其顿语的问题回答任务，目的是为了基准和评估大型语言模型在马其顿语中的表现。数据集只提供了测试分割，翻译可能存在小错误。

The PIQA MK version dataset is a Macedonian adaptation of the PIQA dataset, originally curated (English -> Serbian) by Aleksa Gordić. This dataset has been translated from Serbian to Macedonian using the Google Translate API. It contains question-answering tasks in Macedonian and is intended for benchmarking and evaluating large language models in Macedonian. Only the test split is provided, and the translation may contain minor inaccuracies.