Set Up a Llama2 Endpoint for Your LLM App in OctoAI

Learn to set up a Llama2 endpoint in OctoAI for building a simple LLM application using the RAG framework in this 58-minute workshop from the Docker AI/ML Hackathon 2023. Follow along as the OctoML team demonstrates how to clone a model template, create a custom endpoint, define cost, latency, and hardware preferences, and test the LLM in a sample application. Access the accompanying GitHub repository for hands-on practice and additional resources.