As the excitement around ChatGPT and other large language models (LLMs) continues to grow, many are exploring how to leverage these technologies in their own domains to achieve more targeted and advanced responses. Among the emerging techniques, Retrieval-Augmented Generation (RAG) stands out as one of the most impactful. In this 2-hour lecture, I will introduce...
As artificial intelligence (AI), machine learning (ML), and Large Language Models (LLM) technologies continue to evolve, they offer new possibilities for humanities research, from large-scale text and image analysis to generative AI applications that synthesize and extrapolate knowledge. This workshop introduces key AI/ML/LLM concepts, including neural networks, large language models, and large image models, while...
This workshop will cover running Large Language Models (LLMs) on the Hoffman2 HPC cluster using Ollama for inference and Open WebUI for an easy-to-use interface. Participants will learn how to set up and manage LLM workloads on HPC resources, optimize performance, and interact with models through a web-based UI. The session includes a live demo,...
Are you interested in using LLMs for research? In this 90 minute hands-on workshop, you will learn how to install and deploy an open-source LLM on your local environment, create a Retrieval Augmented Generation (RAG) model with visual builders from Diffy and AWS Bedrock and learn prompt-engineering techniques to reduce the occurrence of hallucination and...
This follow-up to the previous “Introduction to AI/ML/LLM for Humanities and Social Science” workshop builds upon the skills and techniques of using and implementing AI to discuss the technology’s social, ethical, and political ramifications, along with guidelines to using AI for research and teaching. The workshop will address critical ethical concerns surrounding AI, including bias, the network...