mlfoundations-dev/DeepSeek-R1-Distill-Qwen-7B_eval_03-07-25_17-55_0981
收藏Hugging Face2025-03-07 更新2025-04-12 收录
下载链接：
https://hf-mirror.com/datasets/mlfoundations-dev/DeepSeek-R1-Distill-Qwen-7B_eval_03-07-25_17-55_0981
下载链接
链接失效反馈官方服务：
资源简介：
该数据集包含对DeepSeek-R1-Distill-Qwen-7B模型在不同数学和问答数据集上的评估输出。具体包括AIME24、AIME25、AMC23、GPQADiamond和MATH500五个数据集的准确度结果。
This dataset contains precomputed model outputs for evaluating the DeepSeek-R1-Distill-Qwen-7B model on various math and QA datasets, specifically including accuracy results on AIME24, AIME25, AMC23, GPQADiamond, and MATH500.
提供机构：
mlfoundations-dev
