Data Science Tutorials

A practical guide to hyperparameter tuning, covering how it works, the main search methods (grid, random, Bayesian), evaluation strategies, and how to run it in Python and R.

Learn how to run Bonsai 27B, a compact 1-bit Qwen3.6-27B model, locally using llama.cpp, an OpenAI-compatible API, a web UI, and the Pi coding agent.

A practical walkthrough of RAGFlow, the open-source platform for building production Retrieval Augmented Generation applications, covering its architecture, document parsing engine, retrieval strategies, agent workflows, and how it compares to LangChain and LlamaIndex.

Learn how to use the Claude Opus 5 API in Python. Build a bug-fixing agent with tools, then benchmark all five effort levels on pass rate, tokens, and cost.

Learn how to run Thinking Machines' Inkling locally. A complete guide to building experimental llama.cpp, downloading Unsloth GGUFs, and multi-GPU serving.

Learn how to turn a simple LLM prototype into a reliable, scheduled AI workflow with Apache Airflow.

Learn how to set up Grok Build, configure cross-session memory, safety settings, and project instructions, and use SpaceXAI’s coding agent to build an end-to-end machine learning project.

Learn how to track changes in Excel using Show Changes, Version History, and collaboration features.

Learn how Claude Code usage limits actually work, what silently consumes your quota, and the practical steps you can take to extend your available capacity before upgrading your plan.

Learn what Kimi K3 is, how to access it, and how it handles reasoning, tools, long context, and vision across five hands-on examples.

Hand a real coding task to GPT-5.6 Sol in Cursor and watch it plan, edit, test, and fix across files, with AGENTS.md and review passes keeping it on track.

Learn what the lognormal distribution is, how it relates to the normal distribution, and where it applies across finance, biology, and machine learning.