LLM Tutorials

Learn how to build a citation-grounded Streamlit document Q&A assistant with Nemotron 3 Nano, using lightweight keyword retrieval and either local Ollama runs or Ollama Cloud inference.

Cut through the hype. Learn to interpret LLM benchmarks, navigate open leaderboards, and run your own evaluations to find the best AI models for your needs.

Learn how to use Gemini 3 Flash to create a UI Studio that assembles dashboards via tool calls, structured outputs, and rapid knob-based iteration.

Learn how Google Workspace Studio lets you create AI agents to automate workflows in Gmail, Drive, and Sheets with an easy, hands-on beginner tutorial.

Learn the capabilities of Runway Gen 4.5 and find out whether it really is the best text-to-video AI out there.

Discover how Docker Model Runner simplifies local LLM execution, enhances privacy, reduces costs, and integrates seamlessly with existing Docker tools.

Learn how to fine-tune the Ministral 3 vision-language model for X-ray image classification using LoRA, Hugging Face tools, custom prompts, and TRL.

Build a wiki agent with Claude Opus 4.5 and Claude Code to analyze repos, auto-generate multi-file GitHub wiki docs, and publish them to your repository.

Learn how to use Mistral Large 3 and Streamlit to turn charts and PDFs into structured tables, insights, and multilingual summaries.

Learn how to use DeepSeek V3.2 Speciale and Streamlit to turn any CSV into an interactive analytics assistant.

A practical guide to implementing LoRA via Tinker AI to train Qwen3-8B on Chain-of-Thought (CoT) financial data, optimizing for generalization.

Learn how to use LangSmith Agent Builder to create an agent that reads Gmail, drafts replies, and logs actions, all without writing code.