Set up a Llama2 endpoint for your LLM app in OctoAI

Docker AI/ML Hackathon 2023: OctoML Workshop

Learn how to set up your own Llama2 endpoint in OctoAI to build a simple LLM application using the RAG framework. The OctoML team will walk through how to clone a model template to create your own endpoint, define your cost, latency, and hardware preferences, and test your LLM in a sample application.

Link to the OctoML GitHub repo: