Patrick Devine

Thanks for reporting this, @horiacristescu. What type of GPU are you using? I'm assuming if you reinstalled you got the newest version? Do the other quantized versions work? I just...

Hey @horiacristescu , sorry for the really slow response on this. Are you still seeing the system freezes? I'm wondering if you are deep into swap on your machine? You...

LMK if this answers each of your questions and if we can close out the issue.

@AmarkanthJinna did you try the instructions mentioned above? It's also possible that you'll need to get your company to open up the proxy.

@morandalex with the Zephyr model it looks like you're running out of memory on the GPU (it looks like the GPU only has 4GB of ram), whereas it seems like...

@Ch-i to delete the old one, just `rm ~/.ollama/history`.

This is essentially what Ollama does. It tries to offload as many layers of the model as possible into the GPU, and then if there is not enough space, will...

Going to go ahead and close out the issue.

See #2179

Looks fine. You should probably stick a note in the README and the docs about how to get the official python client.