TRL: Hugging Face's Transformer Reinforcement Learning Library
The alignment of large language models with human preferences is one of the most important challenges in AI development. TRL (huggingface/trl on …
Tags
DPO
DPO: Direct Preference Optimization for LLM Alignment Without RL
For most of the history of large language model alignment, the dominant paradigm has been Reinforcement Learning from Human Feedback (RLHF) …