Patrick Devine
Patrick Devine
I think I misinterpreted what your request was. Are you asking to store all of your models in the cloud and then run then from there (but on your local...
The long load time is because the model is being loaded into memory when you start the REPL. I'm guessing the problem is related to Docker Desktop's IO speed. You...
As @easp mentioned, you can just restart the service. If you are using it through Mac/Windows you can stop the service in the task bar and re-launch, and if you're...
This is a dupe of #1736
One other thing that I noticed is that the `ollama create` command seems to get messed up when you're trying to specify the Modelfile location.
@EliasPereirah I think this should answer your question, so I'm going to go ahead and close. Feel free to reopen it if there's still an issue!
Going to go ahead and close the issue.
Hey @electricalgorithm , we're actually counting pulls the same way as Docker counts them, i.e. if the manifest gets pulled it counts as a pull. The reason why is because...
Hey @owenzhao , thanks for the issue. You can always pull again w/ `ollama pull llama2`. I've been looking at some ways to make this easier (maybe `ollama pull --upgrade-all`)...
Can you try running it in the REPL and adding: ``` /set parameter stop )