Evaluating Large Language Models

On the fourth episode of Practically Intelligent, Sinan and Akshay sit down with the esteemed Nathan Lambert, a prominent Machine Learning researcher and analyst. With his keen goal of understanding and developing safe and societally beneficial autonomous systems, Nathan shares valuable insights from his experience as a Research Scientist at HuggingFace 🤗. We dive deep into the nuances of evaluating large language models (LLMs) and the role of the HuggingFace's Open LLM Leaderboard.