haoranli-ml/AIME2025_Qwen3-4B-Instruct_rl_16384budget_16rollouts_0.8temp
收藏Hugging Face2025-11-08 更新2025-11-15 收录
下载链接：
https://hf-mirror.com/datasets/haoranli-ml/AIME2025_Qwen3-4B-Instruct_rl_16384budget_16rollouts_0.8temp
下载链接
链接失效反馈官方服务：
资源简介：
这是一个包含问题、答案、分词提示、响应、奖励、最大奖励和平均奖励等字段的数据集，被划分为AIME2025部分，共有30个示例，数据集大小为10640302字节，下载大小为4315671字节。
This dataset includes fields such as problem, answer, tokenized prompt, responses, rewards, max reward, and mean reward, divided into the AIME2025 section with a total of 30 examples, the dataset size is 10640302 bytes, and the download size is 4315671 bytes.
提供机构：
haoranli-ml
