AlignmentResearch/JailbreakCompletions
收藏Hugging Face2025-03-13 更新2025-04-12 收录
下载链接：
https://hf-mirror.com/datasets/AlignmentResearch/JailbreakCompletions
下载链接
链接失效反馈官方服务：
资源简介：
该数据集包含了文本内容及其相关特征，用于训练模型识别文本内容是否为良性或有害。数据集分为三个子集：默认子集、负面子集和正面子集，每个子集都包含训练集和验证集。
The dataset includes text content and its related features for training models to identify whether the content is benign or harmful. The dataset is divided into three subsets: default, negative, and positive, each with a training set and a validation set.
提供机构：
AlignmentResearch
