haoranli-ml/AIME2025_Qwen3-4B-Instruct_rl_32768budget_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_32768budget_16rollouts_0.8temp
下载链接
链接失效反馈官方服务：
资源简介：
该数据集包含了问题、答案、分词后的提示、一系列响应、每个响应对应的奖励、最大奖励和平均奖励。数据集分为AIME2025部分，共有29个示例，数据集大小为11771339字节。
The dataset includes problem, answer, tokenized prompt, a series of responses, rewards for each response, maximum reward, and mean reward. It is split into AIME2025 section with 29 examples, and the dataset size is 11771339 bytes.
提供机构：
haoranli-ml
