Pruning General Large Language Models into Customized Expert Models

Large language models (LLMs) have revolutionized natural language processing, yet their substantial model sizes often require substantial computational resources. To preserve computing resources and accelerate inference speed, it is crucial to prune redundant parameters, especially for experienced users who often need compact expert models tailored to specific downstream scenarios. However, most existing pruning methods focus on preserving the model's general capabilities, often requiring extensive post-training or suffering from degraded performance due to coarse-grained pruning. In this work, we design a underlineCustom underlinePruning method (textttCus-Prun) to prune a large general model into a smaller lightweight expert model, which is positioned along the "language", "domain" and "task" dimensions. By identifying and pruning irrelevant neurons of each dimension, textttCus-Prun creates expert models without any post-training. Our experiments demonstrate that textttCus-Prun consistently outperforms other methods, achieving minimal loss in both expert and general capabilities across various models from different model families and sizes.