1 code implementation • 13 Aug 2023 • Hongrong Cheng, Miao Zhang, Javen Qinfeng Shi
Modern deep neural networks, particularly recent large language models, come with massive model sizes that require significant computational and storage resources.
1 code implementation • 13 Aug 2023 • Hongrong Cheng, Miao Zhang, Javen Qinfeng Shi
It motivates us to develop a technique to evaluate true loss changes without retraining, with which channels to prune can be selected more reliably and confidently.