Post-Training: DPO, GRPO & RL for LLMs0%
0%
Curso de dominio
Post-Training: DPO, GRPO & RL for LLMs
0%
Pick the right post-training algorithm -- preference optimization, reasoning RL, and agent RL -- without drowning in research papers.
Parte de: Fundamentos de ingeniería de IA
6 módulos·~17 min