Finetuning
Finetuning
A LoRA fine-tuning framework for large language models, used as a standalone tool and as the DeepFellow fine-tuning worker.
DF-Finetune trains LoRA adapters for large language models on top of the Hugging Face Trainer and PEFT libraries. Run it directly from the command line against a local dataset, or deploy it as a background worker that claims and trains fine-tuning jobs submitted through DeepFellow Server's fine-tuning API.
We use cookies on our website. We use them to ensure proper functioning of the site and, if you agree, for purposes such as analytics, marketing, and targeting ads.