-
Notifications
You must be signed in to change notification settings - Fork 103
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Get 503 Error When Pulling Model #646
Comments
At a minimum on a 503 response we shouldn't populate the model store with this little file |
fwiw, |
I updated the reporducer to show that when you delete the weird thing, you can download the real model again |
I think the 503 is unrelated to the first pull based on my minimal testing. |
Yeah the: https://ollama.com/library/deepseek-r1:7b behaviour, that's kinda expected, we support plain-old pulls via https:// protocol. |
Although I probably will open a PR anyway to detect:
or
prefix and switch to ollama protocol. Because it's not tricky to parse 😄 |
As a note for later; I think that |
RamaLama equivalent: |
Reproducer
ramalama pull https://ollama.com/library/deepseek-r1:7b
ramalama pull ollama://deepseek-r1:7b
ramalama rm https://ollama.com/library/deepseek-r1:7b
The text was updated successfully, but these errors were encountered: