selfcorrexp2/Hanning_Llama3-sft-less-corr-rr60k-3eptmp07_vllmexp
收藏Hugging Face2025-01-07 更新2025-04-26 收录
下载链接：
https://hf-mirror.com/datasets/selfcorrexp2/Hanning_Llama3-sft-less-corr-rr60k-3eptmp07_vllmexp
下载链接
链接失效反馈官方服务：
资源简介：
该数据集包含多个字段，如索引、提示文本、答案序列、真实标签、代理标签和第二轮奖励序列。数据集分为训练集，共有5000个示例。每个示例包含了用于训练模型的丰富信息。
The dataset includes multiple fields such as index, prompt text, answer sequence, ground truth label, proxy label, and second round reward sequence. The dataset is split into a training set with a total of 5,000 examples. Each example contains rich information for training models.
提供机构：
selfcorrexp2
