fine-tuning-with-trl - Post-training and preference alignment for LLMs with TRL
Post-Training TRL Reinforcement Learning Fine-Tuning
★ 0 · Updated 2026-09-24
Provides methods and workflows for LLM post-training, including SFT, DPO, PPO, GRPO, and reward modeling.
⚙ Execute supervised fine-tuning ⚙ Train reward models ⚙ Align models using DPO