AI Safety Technical Course 4 - GRPO & LLMs

This lecture will cover GRPO & LLMs.  

In this lecture:
Entropy
KL divergence
Objective function
RLHF Training
LoRA Fine-Tuning and Training
GRPO Training
To receive the certificate, you must complete the notebooks and attend this lecture, as in-person attendance is mandatory.

However, we will stream the lecture online for those who cannot attend in person.
Google Meet Link:
meet.google.com/qig-ivbq-vqn

We'll be serving pizzas and snacks during the lecture.
After the lecture, you're invited to join us for drinks on the house.
Course material is inspired by ARENA, leading UK program in AI Safety.