Cyberes
Cyberes
I'm having the same issue. This bug report is from 2020.
On the DeepSpeed Sparse Attention doc page, there's this: >Note: Currently, DeepSpeed Sparse Attention can be used only on NVIDIA V100 or A100 GPUs using Torch >= 1.6 and CUDA...
From #512: > I see that I indeed set server.name in the Sydent config to example.com rather than sydent.example.com. When I configured it I wasn't sure if server.name was supposed...
> manually resume training from a previous checkpoint Are you doing this with `train_dreambooth.py` by setting `--pretrained_model_name_or_path` or `model.from_pretrained()` to the last DreamBooth checkpoint?
Ok cool. I wasn't sure if I could do that with `--pretrained_model_name_or_path`. > I don't know how it affects the final quality though for dreambooth specifically. I'll train a model...
I'm getting an error when continuing from a dreambooth model immediately after training finishes during what I assume is the saving process. ``` Traceback (most recent call last): File "train_dreambooth.py",...
You ignored the bug report template.
Please tell us what troubleshooting steps you went through to diagnose this issue so we can better help you. You ignored the bug report template.
Actually, seems to be related to https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/2711
Try updating pip.