selfcorrexp2/llama3_sft_balanced_rr60k_train_on_corr_ep3tmp07_vllmexp
收藏Hugging Face2025-01-07 更新2025-04-26 收录
下载链接:
https://hf-mirror.com/datasets/selfcorrexp2/llama3_sft_balanced_rr60k_train_on_corr_ep3tmp07_vllmexp
下载链接
链接失效反馈官方服务:
资源简介:
这个数据集包含了一个索引字段、提示文本、答案序列、真实标签、代理标签以及第二轮奖励字段。它被划分为训练集,共有1000个示例,数据集大小为2565799字节。
The dataset includes an index field, prompt text, answer sequence, ground truth label, proxy label, and second round reward field. It is split into a training set with a total of 1000 examples and a dataset size of 2565799 bytes.
提供机构:
selfcorrexp2


