ai-engineering-from-scratch
Learn it. Build it. Ship it for others.
Learn to contribute to the AI curriculum with one commit per lesson. Package lessons atomically including code, docs, and tests in this guide for rohitg00/ai-engineering-from-scratch.
How Reinforcement Learning (PPO, DPO, RLHF) Aligns LLM Outputs: A Complete Technical GuideMaster reinforcement learning for LLM alignment with PPO, DPO, and RLHF. Learn how these techniques optimize models against human preferences for superior text generation. A technical guide.
Using the Agent Workbench for Real Repository Tasks: A Complete Implementation GuideSafely run autonomous AI agents in any Git repository with the Agent Workbench. This guide details its simple framework for real repository tasks, enabling declarative routing and durable state storage.
Comparison of Quantization Methods: INT8 vs GPTQ vs AWQ vs GGUFCompare INT8, GPTQ, AWQ, and GGUF quantization methods. Discover optimal techniques for GPU throughput, aggressive INT4 compression, and portable CPU inference for large language models.
Implementation of Distributed Training with FSDP and DeepSpeed in AI: A From-Scratch TutorialImplement distributed training FSDP and DeepSpeed in AI from scratch. Our tutorial reconstructs PyTorch FSDP and DeepSpeed ZeRO-3 mechanics for efficient AI model training.
Tracking Phase Prerequisites and Dependencies in the AI Engineering from Scratch CurriculumLearn how the AI Engineering from Scratch curriculum tracks phase prerequisites and dependencies using a DAG and interactive SVG roadmap. Master your AI learning path.
How Skill Installation Works in AI Engineering from Scratch: A Deep Dive into install_skills.pyExplore how skill installation works in AI Engineering from Scratch using install_skills.py. Learn about its four-stage pipeline for managing AI artifacts.
How the AI Engineering Quiz System Uses Pre/Check/Post Stages to Validate LearningExplore the AI Engineering quiz system's pre check and post stages for validating learning. Discover how this JSON-based approach ensures learner readiness comprehension and retention.
How site/build.js Generates site/data.js from Curriculum Data in AI Engineering from ScratchDiscover how site/build.js transforms curriculum Markdown files into site/data.js for the AI Engineering from Scratch project. Understand the data generation process.
Agent Memory Systems: MemGPT and Hybrid Memory (Mem0) Architecture ExplainedExplore agent memory systems like MemGPT and Mem0's hybrid architecture. Understand the prompt buffer, archival store, and multi-tier memory fusion for advanced AI.
Implementation Details of the Model Context Protocol (MCP) in AI Lessons: A Complete Technical GuideDiscover the implementation details of the Model Context Protocol MCP in AI lessons. This guide explains how the JSON-RPC 2.0 server exposes tools, resources, and prompts for LLMs.
How the CI/CD Pipeline Validates Lessons Using audit_lessons.pyLearn how the CI/CD pipeline uses audit_lessons.py to validate lessons. Enforce schema compliance and prevent errors on every push and pull request for robust AI engineering.
Have a question about this repo?
These articles cover the highlights, but your codebase questions are specific. Give your agent direct access to the source. Share this with your agent to get started:
curl -s "https://instagit.com/install.md" 
Maintain an open-source project? Get it listed too →