LLMs from Scratch: Build, Align & Fine-Tune with PyTorch

About this course

Dive into the most exhilarating and hands-on LLM course you'll ever experience! This isn't just learning—it's a journey that will transform you from an AI enthusiast into a creator working at the forefront of technology. AI expert Javier Ideami, the creator of one of the most successful AI related courses on Udemy, brings you a totally unique new experience around LLM technology.

What Makes This Course Unmissable:

Code Your Own AI Universe: 80% hands-on coding with Python and Pytorch. Build an LLM from scratch, line by line. Watch AI come alive through your fingertips. And then go beyond and code a compact version of an alignment process, the magic that makes ChatGPT, GPT 4, Claude and Gemini possible.

Fine-Tuning LLMs: Apply QLoRA to efficiently fine-tune and extend open source LLMs with new skills and capabilities.

Origami Meets AI: Be part of a world-first! Unravel deep learning mysteries through the art of paper folding.

Visual understanding: Combine the coding with visual exploration by going deep into the core of an LLM, seeing how its attention matrices evolve throughout training.

Deep Dive, Gradual Learning Curve: Only basic Python needed. We'll guide you through all the complex concepts around LLMs, from attention mechanisms to cross-entropy and beyond. By the end of the course, you will have gained advanced skills and knowledge about generative AI and LLMs.

Mind-Bending Finale: Cap it off with an optional guided meditation using the "generative AI" in your own brain. Mind = Blown!

Flexible requirements: Run everything on a humble 4GB GPU or anything more powerful. From Google Colab to your trusty laptop, flexibility is the mantra. On the cloud or local (Windows / Linux / Mac). All platforms and devices will work (with a minimum of 4GB of GPU memory)

Prices, discounts and availability are set by Udemy. We may earn a commission when you purchase through links on this site.