News for hackers. Stuff that matters.
Re:DyLoRA: Parameter Efficient Tuning of Pre-Trained Models by kernelsanderz on Monday April 10, 2023 @06:21PM (#35518097)
Adding this to the huggingface peft library would be amazing. That's the main library that people using LoRA are currently using. https://github.com/huggingface/peft/issues/289
Re:DyLoRA: Parameter Efficient Tuning of Pre-Trained Models by brucethemoose2 on Monday April 10, 2023 @10:15PM (#35519909)
The stable diffusion community has, unfortunately, largely ignored peft because the training/inference scripts largely ignored diffusers.