mlfoundations-dev/DeepSeek-R1-Distill-Qwen-7B_eval_03-07-25_17-46_2870
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_17-46_2870
下载链接
链接失效反馈官方服务:
资源简介:
这是用于评估的预计算模型输出数据集。它包含了AIME24指标的平均准确度为37.33% ± 3.18%,并且基于5次运行的结果。
This dataset consists of precomputed model outputs for evaluation purposes. It includes an average accuracy of 37.33% ± 3.18% for the AIME24 metric based on 5 runs.
提供机构:
mlfoundations-dev



