TRL
Also written: Transformer Reinforcement Learning
Hugging Face's library for SFT, DPO and related training methods (the name stands for Transformer Reinforcement Learning). It is most often used for supervised fine-tuning through `SFTTrainer`.
Also written: Transformer Reinforcement Learning
Hugging Face's library for SFT, DPO and related training methods (the name stands for Transformer Reinforcement Learning). It is most often used for supervised fine-tuning through `SFTTrainer`.