Efficient Pruning of Large Language Model with Adaptive Estimation Fusion

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 introduce a simple yet efficient method that adaptively models the importance of each substructure. Meanwhile, it can adaptively fuse coarse-grained and finegrained estimations based on the results from complex and multilayer structures. All aspects of our design seamlessly integrate into the endto-end pruning framework. Our experimental results, compared with state-of-the-art methods on mainstream datasets, demonstrate average accuracy improvements of 1.1%, 1.02%, 2.0%, and 1.2% for LLaMa-7B,Vicuna-7B, Baichuan-7B, and Bloom-7b1, respectively.