Best Practices for Using local Large Language Models with the UM High-Performance Computing Cluster

Overview

This session will demonstrate the process of setting up an open-source Large Language Model (LLM) on the ARMIS2 High-Performance Computing (HPC) cluster. Materials will be provided that cover how to gain access to ARMIS2 as a researcher, how to instantiate and interact with a localized LLM, and best practices for safely using Protected Health Information (PHI) in compliance with institutional policies.