I am interested in applying LoRA to this model architecture. I see OpenDelta mentioned in the code and I am able to define a parameter efficient method as an argument in the train.sh scripts. Though OpenDelta appears to be having trouble adding LoRA to custom TASTEModel class. Have you explored adding LoRA to TASTE with any success?
Hi,
I am interested in applying LoRA to this model architecture. I see OpenDelta mentioned in the code and I am able to define a parameter efficient method as an argument in the train.sh scripts. Though OpenDelta appears to be having trouble adding LoRA to custom TASTEModel class. Have you explored adding LoRA to TASTE with any success?
Thank you!