| # Start Ollama server in the background | |
| /bin/ollama serve & | |
| # Wait for a moment to ensure the server is up | |
| sleep 5 | |
| # Create the model from the Modelfile (the name 'mycustomgemma' can be anything) | |
| ollama create kivelo -f Modelfile | |
| # Keep the container running | |
| wait | |