Y11
@seclink
找工作、找面试题、改简历、模拟面试。关注：
创业（冷启动） ｜ 认知心理学｜智能体 ｜ 强化学习 ｜ AWS RoboMaker、ROS、Gazebo ｜ 具身智能 ｜ 大模型后训练 （数据标注 ｜ 数据采集 ） ｜ 大模型专家评测
building：
Joined January 2011
748 Following 32K Followers
我们发现，将模型蒸馏至架构非常相似的目标模型，其性能远优于蒸馏至与教师模型架构迥异的模型。
"we found that distilling a model into an architecture that is very close performs much better than one that is very different to the teacher model."
