jplhughes2/alignment-faking-synthetic-chat-dataset-recall-10k-docs-0k-benign-0k-refusals
收藏Hugging Face2025-02-03 更新2025-02-15 收录
下载链接：
https://hf-mirror.com/datasets/jplhughes2/alignment-faking-synthetic-chat-dataset-recall-10k-docs-0k-benign-0k-refusals
下载链接
链接失效反馈官方服务：
资源简介：
该数据集包含两个主要字段：prompt和completion，均为文本类型。数据集被划分为训练集，共有10000个示例，大小为35665898字节。数据集的配置信息中，使用了默认配置，并且训练数据存储在特定的路径下。
The dataset includes two main fields: prompt and completion, both of which are text types. The dataset is split into a training set with a total of 10,000 examples, with a size of 35665898 bytes. In terms of configuration, the default configuration is used, and the training data is stored in a specific path.
提供机构：
jplhughes2
