767: Open-Source LLM Libraries and Techniques, with Dr. Sebastian Raschka
Super Data Science: ML & AI Podcast with Jon Krohn
00:00
Training Large Language Models Without Human Feedback
The chapter explores alternatives to reinforcement learning from human feedback (RLHF) for training large language models (LLMs), including instruction fine-tuning and reinforcement learning from AI feedback (RAIF) where feedback is provided by AI models like GPT. Various techniques like RLHF, DPO, and KTO are discussed, offering ways to train language models without human involvement and tackle challenges in evaluating conversational abilities and preferences.
Transcript
Play full episode
