LifelongAlignment/aifgen
收藏Hugging Face2025-05-16 更新2025-11-01 收录
下载链接：
https://hf-mirror.com/datasets/LifelongAlignment/aifgen
下载链接
链接失效反馈官方服务：
资源简介：
这是一个用于终身强化学习在语言模型上进行基准测试的静态RLHF数据集集合。数据集包含了摘要和问答任务，涵盖了科学和技术等主题。数据集使用AIF-Gen框架和gpt-4o-mini模型生成。
This is a collection of static RLHF datasets for benchmarking Lifelong Reinforcement Learning on language models. The dataset includes summarization and question-answering tasks covering topics such as science and technology. The datasets are generated using the AIF-Gen framework and the gpt-4o-mini model.
提供机构：
LifelongAlignment
