Alan Yu
Alan Yu
Having this issue as well... Has this project been abandoned?
I'm experiencing the first issue as well, did you manage to resolve it?
would like to see a fix, i set the hotkey to ctrl+shift+v to use it with live preview but would prefer not having that hotkey being taken up
Any updates on this @XuanWang-Amos?
> It means torch_dtype=torch.float32 doesn't work @lywinged do you know why that is the case?
> > It means torch_dtype=torch.float32 doesn't work > > is there any way to solve this? > > I didn’t find the solution yet, using fp16 now. I think this...
From an associated issue in another repo: >When loading the model using device_map="auto" on a GPU with insufficient VRAM, Transformers tries to offload the rest of the model onto the...
> This error is caused by Accelerate auto-offloading weights to either the cpu or disk because of insufficient memory on the GPU. > > @zas97 can you try manually offloading...
@orangetin Not sure if `float32` will solve this particular issue since that's been the cause of my issue (unrelated to this project, more specific to just the `accelerate` package). I've...
@Michaelvll @concretevitamin can you guys provide a link to an existing PR which adds a cloud provider so I can use it as an example to work off of? I'd...