Prompt-Tuning
Prompt-Tuning copied to clipboard
Implementation of "The Power of Scale for Parameter-Efficient Prompt Tuning"
Hi @mkshing, I just wanted to check in, is there desire to update this library to be able to work with NeoX models like Dolly 2? Cheers, Simon
Hi mkshing, you mention "In the inference phase, you need to input ids to the model by using model.forward() so that you cannot use model.generate() attribute. ". Possible to elaborate...
QA task
Hey have you tried to apply this method to QA task?