hynky/mmlu_okapi
收藏Hugging Face2024-07-11 更新2024-07-13 收录
下载链接：
https://hf-mirror.com/datasets/hynky/mmlu_okapi
下载链接
链接失效反馈官方服务：
资源简介：
MMLU是一个基准测试，用于测量文本模型的多任务准确性。该测试涵盖了57个任务，包括基础数学、美国历史、计算机科学、法律等。要在该测试中获得高准确率，模型必须具备广泛的世界知识和问题解决能力。通过全面评估模型在学术和专业理解上的广度和深度，MMLU可用于分析模型在多个任务中的表现，并识别重要的不足之处。
The okapi_mmlu dataset is a multilingual translation of the Measuring Massive Multitask Language Understanding (MMLU), used to evaluate the accuracy of text models across multiple tasks. This benchmark covers 57 domains including elementary mathematics, US history, computer science, law, and more, requiring models to possess extensive world knowledge and problem-solving abilities. The dataset is curated by Dac Lai et al. and is licensed under CC BY NC 4.0 (allowing only non-commercial use).
提供机构：
hynky
