Isaac

> > Hi, > > I am trying to implement autendoer in pytorch and I did write the model which I suppose is excatly what is present in this repo....

https://stackoverflow.com/questions/65098604/catch2-installation-on-ubuntu-20-04-include-catch2-catch-hpp >

Hi, does a single Image work? like, applying this SSA on other datasets if we don't obtain the JSON files?

I encountered this issue as well

> 应该是的，已经可以了 ~~Could you kindly share how did you solve this issue? For my cases, this error especially raise when the "prompt-text" is not detected.~~ solved.

@BenjaminBossan Hi Ben, Thank you for directing me here; it seems like the exact issue I am looking for. Since this function has not been officially merged into the main...

> @BenjaminBossan Hi Ben, > > Thank you for directing me here; it seems like the exact issue I am looking for. Since this function has not been officially merged...

> > Not sure if it's a problem with the lora_alpha parameter, since it works fine when lora_alpha=1. However, choosing 2*rank seems to destroy the model's performance. Perhaps bigger alpha...