Customizing Your Models: RAG, Fine-Tuning, and Pre-Training

Explore techniques for tailoring and improving the performance of AI and Large Language Models in specific domains or tasks in this 40-minute talk by Jonathan Frankle, Chief Scientist of Neural Networks at Databricks. Learn about the AI maturity curve and discover when to apply prompt engineering, Retrieval Augmented Generation (RAG), fine-tuning, and pre-training. Gain insights from a world-class AI researcher on achieving highly performant AI systems. Access additional resources like the LLM Compact Guide and Big Book of MLOps to further your understanding of AI customization techniques.