Documentation Hugging Face

DPO Trainer

Hugging Face

Reference documentation for the direct preference optimization trainer.

Hugging FacePublic source

In this reference

Reference documentation for the direct preference optimization trainer.

DPO Trainer [Documentation]. Hugging Face. https://huggingface.co/docs/trl/dpo_trainer

View BibTeX

@misc{dpo_trainer,
  title = {{DPO Trainer}},
  howpublished = {Hugging Face},
  url = {https://huggingface.co/docs/trl/dpo_trainer}
}