oliverban
oliverban
> You can't just delete a dll file like that because that will mean sigverif.exe will now fail. It requires all the signed files presence. So how do we defeat...
> So to clarify, the changes I had to apply was in **generate.py**: > > ``` > model = PeftModel.from_pretrained( > model, "tloen/alpaca-lora-7b", > torch_dtype=torch.float16 > ) > ``` >...
> I installed version 18.5 and surprisingly it gave me the option to choose my brand account. Then I just updated the app to the latest version. Thanks for the...
I got this as well just a couple of days ago while doing an upscale in img2img! Sorry I can't help you further, just chiming in so that you know...
This happens here to. I'm also on torch 2.0. Randomly hangs during generation and the GPU spikes to 100% and stays there without any fluctuations.
Mozoloa, thanks for the workaround but just a patch from devs seems like a must. Why the wait?
I don't get it. How are people getting these MASSIVE speeds anyways. And is CPU really a bottleneck for this stuff as well? I know so little! I have a...
> > I don't get it. How are people getting these MASSIVE speeds anyways. And is CPU really a bottleneck for this stuff as well? I know so little! I...
> Oh, I forgot to mention DDIM, and 20 steps for them. Your it/s sound way too low and I highly suspect something is wrecked somewhere when a 3060ti is...
> > > Number one: Are you running cuDNN v8.7 or higher? Number two: Are you using xformers or sdp? Even though your 4.4 GHz CPU isn't that fast, for...