selfcorrexp2/llama3_sft_balanced_corr_rr0k_ep3_train_on_reasoning_more_datatmp10_vllmexp3
收藏Hugging Face2025-01-23 更新2025-04-26 收录
下载链接：
https://hf-mirror.com/datasets/selfcorrexp2/llama3_sft_balanced_corr_rr0k_ep3_train_on_reasoning_more_datatmp10_vllmexp3
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，包括索引、提示文本、奖励序列、答案序列、真实标签、代理标签和次级奖励序列。数据集分为训练集，共有15000个样本，总文件大小为41497038字节，下载大小为16448479字节。
The dataset contains multiple fields including index, prompt text, reward sequence, answer sequence, ground truth label, proxy label, and secondary reward sequence. The dataset is split into a training set with a total of 15,000 samples, with a total file size of 41,497,038 bytes and a download size of 16,448,479 bytes.
提供机构：
selfcorrexp2
