Fine Tuning Insights
Thomas discusses the potential of starting with zero or few-shot learning for fine-tuning AI models, suggesting that dramatic improvements can be achieved with as few as 100 to 1,000 examples. He also reflects on the challenges of managing large-scale AI projects, emphasizing the importance of safety standards and timely publication in a competitive environment.In this clip
From this podcast
Super Data Science: ML & AI Podcast with Jon Krohn
713: Llama 2, Toolformer and BLOOM: Open-Source LLMs — with Meta's Dr. Thomas Scialom
Related Questions
Have you seen any good techniques for automatically optimizing few-shot examples for large language models (LLMs) in the episode Building Real-World LLM Products with Fine-Tuning and More with Hamel Husain - 694?
How are large language models (LLMs) trained, as discussed in the episode 670: LLaMA: GPT-3 performance, 10x smaller — with Jon Krohn (@JonKrohnLearns) and the clip Llama Model Insights?