haoranli-ml/AIME2025_Qwen3-4B-Instruct_shallow-summed-sft_rl_16384budget_16rollouts_0.8temp
收藏Hugging Face2025-11-09 更新2025-11-15 收录
下载链接：
https://hf-mirror.com/datasets/haoranli-ml/AIME2025_Qwen3-4B-Instruct_shallow-summed-sft_rl_16384budget_16rollouts_0.8temp
下载链接
链接失效反馈官方服务：
资源简介：
该数据集包含问题、答案、分词后的提示、多个响应、每个响应的奖励、最大奖励和平均奖励等字段。它被分为AIME2025部分，包含30个示例，数据集大小为14,245,284字节。
The dataset includes fields for problems, answers, tokenized prompts, multiple responses, rewards for each response, maximum reward, and mean reward. It is split into the AIME2025 section, containing 30 examples, with a dataset size of 14,245,284 bytes.
提供机构：
haoranli-ml
