FFSplit: Split Feed-Forward Network for Optimizing Accuracy-Efficiency Trade-off in Language Model Inference
arXiv (Cornell University)(2024)
关键词
Pretrained Models,Model Compression,Language Modeling,Neural Machine Translation,Topic Modeling
AI 理解论文
溯源树
样例

生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要