This paper proposes EvoP, an evolutionary pruning framework, to address the problem of deploying large-scale language models (LLMs) in resource-constrained environments. To overcome the heuristic strategies and data feature neglect of existing model pruning methods, EvoP introduces a cluster-based correction dataset sampling (CCDS) strategy to generate diverse correction datasets and an evolutionary pruning pattern search (EPPS) method to identify optimal pruning patterns. Experiments on various LLMs and subtasks demonstrate the effectiveness of EvoP, demonstrating its practical and scalable solution for deploying LLMs in real-world applications.
