Asap7772/wildjailbreak_llamagen_safety_score
收藏Hugging Face2025-01-17 更新2025-02-15 收录
下载链接：
https://hf-mirror.com/datasets/Asap7772/wildjailbreak_llamagen_safety_score
下载链接
链接失效反馈官方服务：
资源简介：
该数据集包含了多个文本相关的特征，如vanilla、adversarial、completion等，以及用于训练的文本数据（responses）、安全响应数据（guard_responses）、奖励值（rewards）和安全分数（safety_score）。数据集分为训练集，共有261559个示例，文件大小为10185239663字节。
The dataset includes multiple text-related features such as vanilla, adversarial, completion, etc., as well as text data for training (responses), secure response data (guard_responses), reward values (rewards), and safety scores (safety_score). The dataset is split into a training set with a total of 261559 examples and a file size of 10185239663 bytes.
提供机构：
Asap7772
