Model Selection Advice
Percy advises starting with simpler models like llama Mistral or mixed roll for fine tuning, emphasizing the importance of having a flexible evaluation framework for swapping in new models. Lukas agrees on the necessity of a robust evaluation setup for effective experimentation in deploying LLMs within a company.In this clip
From this podcast
Gradient Dissent - A Machine Learning Podcast
Shaping AI Benchmarks with Together AI Co-Founder Percy Liang
Related Questions