15-422/642 Machine Learning and Systems: Guest Lecture - Tim Dettmers April 16, 2025 3:30pm — 4:30pm Location: In Person - Rashid Auditorium, Gates Hillman 4401 Speaker: TIM DETTMERS , Research Scientist, Allen Institute for AI, and, Assistant Professor, Machine Learning Department, Carnegie Mellon University https://timdettmers.com/about/ Efficient Foundation Models via Quantization The ever-increasing scale of foundation models, such as ChatGPT and AlphaFold, has revolutionized AI and science more generally. However, increasing scale also steadily raises computational barriers, blocking almost everyone from studying, adapting, or otherwise using these models for anything beyond static API queries. In this talk, I will present research that significantly lowers these barriers for a wide range of use cases, including quantized inference algorithms that are used to make predictions after training and fine-tuning approaches — such as QLoRA — that adapt a trained model to new data. I will also talk about the different requirements when models are deployed for private use vs for company use and how this altered the effectiveness of quantization algorithms. — Tim Dettmers is a Research Scientist at the Allen Institute for AI and an Assistant Professor at Carnegie Mellon University. His work focuses on making foundation models, such as ChatGPT, accessible to researchers and practitioners by reducing their resource requirements. His main focus is to develop high-quality agent systems that are open-source and can be run on consumer hardware, such as laptops. His research won oral, spotlight, and best paper awards at conferences such as ICLR and NeurIPS and was awarded the Block Award and Madrona Prize. He created the bitsandbytes open-source library for efficient foundation models, which is growing at 2.2 million installations per month, and for which he received Google Open Source and PyTorch Foundation awards. Faculty Host: Tianqi Chen Add event to Google Add event to iCal
