mlfoundations-dev/OpenThinker-7B_1743027973_eval_f912
收藏Hugging Face2025-03-26 更新2025-04-12 收录
下载链接:
https://hf-mirror.com/datasets/mlfoundations-dev/OpenThinker-7B_1743027973_eval_f912
下载链接
链接失效反馈官方服务:
资源简介:
该数据集是针对OpenThinker-7B模型在GPQADiamond任务上的评估结果,包含三次独立运行的数据,每次运行198个问题,平均准确率为24.92%。
This dataset contains precomputed outputs for evaluating the OpenThinker-7B model on the GPQADiamond task, including data from three independent runs, each with 198 questions, and an average accuracy of 24.92%.
提供机构:
mlfoundations-dev



