The course teaches how to fine-tune LLMs using Group Relative Policy Optimization (GRPO)—a reinforcement learning method that improves model reasoning with minimal data. Learn RFT concepts, reward design, LLM-as-a-judge evaluation, and deploy jobs on the Predibase platform.
reinforcement-learning machine-learning-algorithms language-model reward-design rft ai-training deeplearning-ai-courses ai-optimization multi-step-reasoning ai-evaluation rlhf llm-fine-tuning opensource-ai llm-as-judge predibase grpo llm-development token-level-control
-
Updated
Jun 13, 2025 - Jupyter Notebook