LLM Tutorials

Learn how to build secure, local AI applications that protect your sensitive data using a low/no-code automation framework.

Get step-by-step instructions on how to set up and run Llama 3.2 1B on your Android device using the Torchchat framework.

Learn how to use Runway Act-One through both the web interface and its API, and discover how to combine it with Runway Gen3-Alpha.

Learn to build AI chatbots with Streamlit, LangChain, and Neo4j. This tutorial covers creating UIs for LLM apps, implementing RAG, and deploying to Streamlit Cloud.

Learn how to build real-time AI applications with OpenAI's Realtime API. This tutorial covers WebSockets, Node.js setup, text/audio messaging, function calling, and deploying a React voice assistant demo.

Discover Microsoft's new LLM series and boost your model's accuracy from 65% to 86% by fine-tuning it on the E-commerce classification dataset.

Learn Speculative RAG, a technique that improves RAG through a two-step drafting and verification process, and apply your skills with a hands-on implementation using Hugging Face Transformers.

Fine-tuning the Llama 3.1 model to solve specialized algebra problems with high accuracy and detailed results using Unsloth.

Learn how to fine-tune GPT-4o with images by following this step-by-step tutorial, where you’ll discover how to improve GPT-4o’s ability to recognize Georgian churches.

Learn how to use the Llama 3.2 11B vision model with Gradio to create a multimodal web app that functions as a customer support assistant.

Learn how to distill LLMs with OpenAI's distillation tool. This tutorial provides a step-by-step guide using GPT-4o and GPT-4o-mini for generating Git commands.

Llama Stack is a set of standardized tools and APIs developed by Meta that simplifies the process of building and deploying large language model applications.