AI
AIshala
.

Learn AI

Courses
Topics
Skills
Roles

AI Jobs

Find Jobs
Career Paths

AI Community

Chapters
Events

AI Resources

Tools
By Provider
Guides
🌐
EN
Home
/
Courses
/
Let's Build GPT from Scratch
Andrej Karpathy
Andrej Karpathy

Let's Build GPT from Scratch

Karpathy builds a GPT model from scratch in code — the canonical hands-on intro to transformer training.
free
advanced

2 hrs

video-series

About this course

In this hands-on course, Andrej Karpathy—a leading figure in deep learning and AI education—walks you through building a GPT model entirely from scratch in code. Rather than treating transformers as a black box, you'll understand exactly how they work by implementing them yourself. This is the gold standard introduction to transformer training, perfect for anyone serious about moving beyond theory into practical understanding.

What you'll learn

  • Build a working GPT model from first principles, understanding every component
  • Implement transformer architecture: attention mechanisms, multi-head attention, and feed-forward layers
  • Train a neural network on real data and debug training loops like a professional
  • Understand tokenization, embedding, and positional encoding in depth
  • Generate text with your own trained model and improve output quality
  • Grasp the mathematical foundations behind modern large language models
  • Read and interpret research papers on transformers with confidence

Who this is for

You're ready for this course if you already know Python and have studied machine learning basics. You should be comfortable reading code and thinking mathematically, because you'll be writing the transformer from scratch—not just using a library.

  • AI researchers and engineers — build deep technical mastery of transformers before specializing further
  • Engineering students — get hands-on experience with cutting-edge AI that will set you apart in placements and internships

Prerequisites

Strong Python programming skills, basic understanding of neural networks (backpropagation, gradient descent), and comfort with linear algebra and calculus. This is an advanced course—it assumes you've already learned the fundamentals of deep learning.

Why this matters for Indian learners

India's AI job market is exploding. Major Indian tech companies (TCS, Infosys, Wipro) and startups across Bangalore, Hyderabad, and Mumbai are desperately hiring AI engineers who understand transformer models deeply. This course gives you the rare, genuine expertise that separates candidates who can *build* AI from those who just use off-the-shelf tools. For placements, freelancing, or starting your own AI venture, this knowledge is a major differentiator.

Frequently asked questions

Is this course really free?

Yes, completely free. Andrej Karpathy uploaded this to YouTube as a gift to the AI community. No hidden paywalls or premium versions.

How long will it take to complete?

The video is 2 hours, but expect to spend 3–4 weeks total if you're coding along (which you should). Plan for 1.5–2 hours per week of focused, uninterrupted work. You'll pause, rewind, and experiment—that's the whole point.

Will I get a certificate?

No official certificate comes with this course. But you'll have something better: a fully working GPT model you built yourself, which you can show employers and include in a portfolio.

At a glance

Provider
Andrej Karpathy
Level
Advanced
Duration
2 hrs
Format
Recorded
Language
En
Certificate
False
Price
free (0 )

More free courses

Other AIshala-vetted free courses
Hugging Face
Hugging Face

The LLM Course (updated from NLP Course)

Hugging Face's flagship LLM course (formerly the NLP Course), expanded with new chapters on fine-tuning LLMs and building reasoning models. Free, code-along, certificate available.
free
Certificate
15 hrs
intermediate
Hugging Face
Hugging Face

AI Agents Course

Hugging Face's free hands-on course on building AI agents with smolagents, LlamaIndex, and LangGraph. Includes a certificate of completion and an agent-vs-agent challenge.
free
Certificate
10 hrs
intermediate
Hugging Face
Hugging Face

Model Context Protocol (MCP) Course

Hugging Face's free course on Model Context Protocol (MCP) — Anthropic's open standard for connecting AI assistants to tools and data sources. Hands-on with practical implementations.
free
Certificate
4 hrs
intermediate
NVIDIA
NVIDIA

Generative AI Explained

NVIDIA DLI's free self-paced introduction to generative AI concepts, applications, and the challenges and opportunities of the field. Foundational for anyone new to GenAI.
free
Certificate
2 hrs
beginner
Anthropic
Anthropic

AI Capabilities and Limitations

Anthropic Academy's neutral generative-AI literacy course. Helps general audiences understand what current AI can and cannot do, with concrete examples and failure modes.
free
Certificate
1 hrs
beginner
Anthropic
Anthropic

Cowork — Claude for Non-Technical Roles

Anthropic Academy course aimed at analysts, legal, finance, and research professionals — how to use Claude effectively without writing code. Practical workflows for non-engineering roles.
free
Certificate
2 hrs
beginner
AI
AIshala
.

India's free AI learning hub. Aggregating the best free AI education on the internet, organized for Indian learners.

Learn

All Courses
Topics
By Provider
By Persona
Blog & Guides

Community

City Chapters
Events
Become Ambassador
Submit a Course

About

Our Mission
Contact
Partner with Us
Press Kit

Languages

English
हिन्दी (Q2 2026)
தமிழ் (Q3 2026)
తెలుగు (Q3 2026)
© 2026 AIshala. Made with ❤️ in India.
Twitter
LinkedIn
YouTube
GitHub