peft
peft copied to clipboard
Implementation of adapter?
Parameter-efficient transfer learning for NLP May I ask why you opt not to implement the "adapter" from this paper? Is it due to performance or anything else?
Hello, we are in the process of adding it
Also looking forward to the implementation!
@pacman100 Is this still open? I'd love to help out if so
mark
Hi,
Any plans to integrate the bottleneck adapters such as Adapter_H and Adapter_P into PEFT library?