Reinforcement Learning from Human Feedback

This short course, offered in collaboration with Google Cloud, delves into the concept of Reinforcement Learning from Human Feedback (RLHF). It focuses on how RLHF is used to align large language models (LLMs) with human values and preferences, particularly through fine-tuning models like Llama 2.

Intermediate knowledge of Python and an interest in advanced AI training techniques.

Participants will gain practical experience in applying RLHF techniques, using datasets for preference and prompt training, and evaluating model improvements.