Ollama Notes

Installation and Set-up

• Use curl -fsSL https://ollama.com/install.sh | sh

  • WARNING: This will take a while!

• Once done, docker commit modelworks-container modelworks-image

• Then you can run docker run -it --name modelworks -p 7860:7860 modelworks-image to access it again

• To run Ollama, type ollama serve

• After that, open a new shell and use ollama run [insert model variable here]

Updating Ollama

• Run curl -fsSL https://ollama.com/install.sh | sh again to get the latest version of Ollama

Useful Information

• You can read more about the models (and what variables you'd need to type) at Ollama's Library page.
• Remember you need an instance of Ollama running in the background for you to use it.
  • This can be through ollama serve or any other method.