Angel Tsvetkov
Angel Tsvetkov
I confirm this bug too- for SDXL models do any (empty) txt2img before to do img2img fixes it!
> Open `cmd_windows.bat` and enter this command: > > ``` > python -m pip install deepspeed-0.9.3+unknown-cp310-cp310-win_amd64.whl > ``` > > Keep in mind that, while you can install deepspeed on...
FInally i managed to start the deep speed via the following command in the "webui.py" file: run_cmd("python ..\installer_files\env\scripts\ds --num_gpus=1 server.py --deepspeed --model-menu --chat", environment=True) # put your flags here! but...
The above error is resolved after changed dist_backend=None to dist_backend='gloo' on line 562 in "C:\oobabooga_windows\installer_files\env\Lib\site-packages\deepspeed\comm\comm.py" But it is not enough because of the next raised error: "RuntimeError: a leaf Variable...
I also have the NCCL error: raise RuntimeError("Distributed package doesn't have NCCL " "built in") untimeError: Distributed package doesn't have NCCL built in
Finally and i, after changed dist_backend=None to dist_backend='gloo' on line 562 in "C:\oobabooga_windows\installer_files\env\Lib\site-packages\deepspeed\comm\comm.py" end up with the same error: "RuntimeError: a leaf Variable that requires grad is being used in...
> Has anyone managed to solve the problem? So many high-quality computers (seemingly) that fail to upload simple models, > > Even when there is enough memory? means a systemic...
> I'm playing around with Qdrant as a vector store index using sentence-transformer embeddings from HuggingFace. > > However, when I try to create an index, I get an error...
> There are two models, the embed model and the llm > > You'll need to set both in the service context, and pass your service context into the index...
> The colab notebook I linked uses local huggingface embeddings... Your colab notebook example requires open_api key which is the opposite of the question ... AuthenticationError Traceback (most recent call...