Run your own code with Llama3.1 and ollama locally

For full instructions go to: docs.sublayer.com/docs/guides/running-local-llama31-with-ollama Here we learn how to run llama3.1 locally using ollama, and use llama3.1 through the api using Sublayer. We'll show how to swap out gpt-4 to use llama3.1 in an existing project called "historical_event_finder". And then we'll create a new Dr. Seuss Styled Poem Maker from scratch that uses our locally running llama3.1 model.