707: Vicuña, Gorilla, Chatbot Arena and Socially Beneficial LLMs, with Prof. Joey Gonzalez
Super Data Science: ML & AI Podcast with Jon Krohn
00:00
Exploring Long Context Windows in Models and Evaluating Model Performance
Delve into the importance of long context windows in models, discussing challenges like computational requirements and sparsification techniques. Learn about evaluating models' performance in finding hidden keywords within contexts, challenges in model retrieval methods, and the impact of Language Model Systems (LMS) in education. The chapter also touches upon using GPT chat interface for learning in coding and discusses the significance of open source versus closed source in research and development.
Transcript
Play full episode
