This talk explores utilizing OpenSource large Language Models (LLMs) with personal data on-premise or on your local computer, ensuring data privacy without having the need to use services like ChatGPT.

In a brief introduction we will dive into user-friendly model training methods like embeddings and low rank adaptations. Following that we will do a live coding segment where we will demonstrate how easy it is to integrate your text data into an OpenSource model, highlighting how one can easily adapt LLMs to personal datasets securely and efficiently on our own hardware like a MacBook.

Through practical insights, attendees will learn to harness the power of OpenSource LLMs for enhanced, privacy-preserving data interaction.