Friday, September 26, 11am-12pm

Large language models (LLMs) are rapidly gaining popularity due to their impressive performance across a wide range of disciplines, from the humanities to the physical sciences. However, effectively utilizing LLMs often requires significant computational resources. This RC Short Course* is designed to help researchers take full advantage of CU Research Computing (CURC) resources to deploy and run LLMs efficiently. The session will provide a high-level overview of CURC systems suited for LLM workloads, followed by practical guidance on the installation, configuration, and use of popular tools such as Hugging Face and Ollama for downloading and running state-of-the-art models.

This session is intended for users with a basic understanding of programming and some familiarity with Linux command-line environment.

*What is an RC Short Course? An RC Short Course is a training that provides an in-depth understanding of a concept, system, or tool. You can expect to leave a "Short Course" with a solid grasp of the topic.