llama.cpp
llama.cpp copied to clipboard
Docker “--all-in-one” fails with ModuleNotFoundError: No module named ‘tqdm’
On Win 10
> docker run -v /llama/models:/models ghcr.io/ggerganov/llama.cpp:full –all-in-one “/models/” 7B
Downloading model…
Traceback (most recent call last):
File “/app/./download-pth.py”, line 3, in <module>
from tqdm import tqdm
ModuleNotFoundError: No module named ‘tqdm’
My guess is putting tqdm
at the end of .devops/full.Dockerfile might solve the issue but I don't how to rebuild the image ;/
Please confirm that the problem is fixed after the pull request is merged
Why would you merge before knowing it fixes the problem in the first place?
I have the same problem and am happy to test. I'm just not sure how to build the docker image locally
I have the same problem and am happy to test. I'm just not sure how to build the docker image locally
Me too, the actions on the PR suggest that the change has been pushed to docker, but I can't figure out how to pull it
Ok, I think I got it and it seems to be working.
I believe the action doesn't actually push the image anywhere and is only for testing whether the build even succeeds. Just after the build command the log says WARNING: No output specified with docker-container driver. Build result will only remain in the build cache. To push result image into registry use --push or to load image into docker use --load
I was able to build the image locally with: docker build -f .devops/full.Dockerfile .
Nice one, it seems to fix the issue for me, it is now downloading consolidated.00.pth