Dr. Weizhe Li, Graduate Data Science Programs: Information Hub.
The Large Language Models (LLMs) have been emerged as a potential model for general AI. However, the training or finetune the LLMs is still challenging task especially for research labs that have limited GPU resources. This project is to explore the techniques to train and finetune the open source LLM model from Meta AI, Llama 2 model efficiently using single GPU. This project will be very helpful for the application and deployment of LLMs for both research and industry.