Efficient Pruning of Large Language Model with Adaptive Estimation Fusion

arXiv:2403.10799v1 Announce Type: cross
Abstract: Large language models (LLMs) have become crucial for many generative downstream tasks, leading to an inevitable trend and significant challenge to deploy them efficiently on resource-constrained devices. Structured pruning is a widely used method to address this challenge. However, when dealing with the complex structure of the multiple decoder layers, general methods often employ common estimation approaches for pruning. These approaches lead to a decline in accuracy for specific downstream tasks. In this paper, we …

abstract arxiv become challenge cs.ai cs.cl cs.lg deploy devices fusion generative however language language model language models large language large language model large language models llms pruning tasks them trend type