<ul><li>PortLLM is a training-free framework for personalizing evolving large language models (LLMs).</li><li>The framework creates an initial lightweight model update patch to capture domain-specific knowledge.</li><li>PortLLM allows for the continual personalization of evolved LLMs at minimal cost.</li><li>Experimental results show that PortLLM achieves comparable performance to fine-tuning with significant reductions in GPU memory usage.</li></ul>

PortLLM: Personalizing Evolving Large Language Models with Training-Free and Portable Model Patches

Discover more