LLM Mastery: Hands-on Code, Align and Master LLMs

LLM Mastery: Hands-on Code, Align and Master LLMs, available at $54.99, has an average rating of 4.8, with 119 lectures, 2 quizzes, based on 31 reviews, and has 1250 subscribers.

You will learn about Code and train an LLM from scratch, line by line, understanding every concept in detail Understand and analyze in depth an advanced LLM architecture based on the Llama system Code and train an alignment process from scratch, to align an LLM with a preferred form of interaction Understand in great depth key concepts like the Attention Mechanisms, the Cross Entropy Loss, the way neural networks learn and many more Explore in depth insights about deep learning and neural networks through the use of Origami In addition to the coding, every section includes in-depth explanations of key concepts related to these architectures and generative AI This course is ideal for individuals who are AI Enthusiasts and Developers: Individuals with a passion for artificial intelligence and a basic knowledge of Python who want to dive deep into the world of LLMs and generative AI. or Tech Innovators and Creators: Aspiring AI developers who wish to be at the cutting edge of technology, learning to build and understand complex AI systems from the ground up. or Students and Professionals in AI: Those studying or working in AI-related fields who seek to enhance their practical skills and theoretical understanding of LLMs and deep learning. or Curious Minds with Creative Flair: Learners interested in a unique blend of technology and art, who are eager to explore deep learning concepts through innovative methods like origami. or Software engineers: interested in understanding and coding LLMs as well as implementing AI alignment techniques with LLMs or General: People that are curious about how LLMs work and want to understand them in great depth or General: People that want to stretch their generative AI experience using Python and Pytorch to program LLMs and alignment processes or General: People that want to know all the key parts of how ChatGPT, Gemini or Claude work internally, in order to get inspired about new ways of applying this technology or General: Those that want a deep introduction to Generative AI, deep learning and neural networks or General: Those that want to deeply understand how neural networks learn in a fun way and unique way through Origami It is particularly useful for AI Enthusiasts and Developers: Individuals with a passion for artificial intelligence and a basic knowledge of Python who want to dive deep into the world of LLMs and generative AI. or Tech Innovators and Creators: Aspiring AI developers who wish to be at the cutting edge of technology, learning to build and understand complex AI systems from the ground up. or Students and Professionals in AI: Those studying or working in AI-related fields who seek to enhance their practical skills and theoretical understanding of LLMs and deep learning. or Curious Minds with Creative Flair: Learners interested in a unique blend of technology and art, who are eager to explore deep learning concepts through innovative methods like origami. or Software engineers: interested in understanding and coding LLMs as well as implementing AI alignment techniques with LLMs or General: People that are curious about how LLMs work and want to understand them in great depth or General: People that want to stretch their generative AI experience using Python and Pytorch to program LLMs and alignment processes or General: People that want to know all the key parts of how ChatGPT, Gemini or Claude work internally, in order to get inspired about new ways of applying this technology or General: Those that want a deep introduction to Generative AI, deep learning and neural networks or General: Those that want to deeply understand how neural networks learn in a fun way and unique way through Origami.

Enroll now: LLM Mastery: Hands-on Code, Align and Master LLMs

Summary

Title: LLM Mastery: Hands-on Code, Align and Master LLMs

Price: $54.99

Average Rating: 4.8

Number of Lectures: 119

Number of Quizzes: 2

Number of Published Lectures: 119

Number of Published Quizzes: 2

Number of Curriculum Items: 121

Number of Published Curriculum Objects: 121

Original Price: €99.99

Quality Status: approved

Status: Live

What You Will Learn

Code and train an LLM from scratch, line by line, understanding every concept in detail
Understand and analyze in depth an advanced LLM architecture based on the Llama system
Code and train an alignment process from scratch, to align an LLM with a preferred form of interaction
Understand in great depth key concepts like the Attention Mechanisms, the Cross Entropy Loss, the way neural networks learn and many more
Explore in depth insights about deep learning and neural networks through the use of Origami
In addition to the coding, every section includes in-depth explanations of key concepts related to these architectures and generative AI

Who Should Attend

AI Enthusiasts and Developers: Individuals with a passion for artificial intelligence and a basic knowledge of Python who want to dive deep into the world of LLMs and generative AI.
Tech Innovators and Creators: Aspiring AI developers who wish to be at the cutting edge of technology, learning to build and understand complex AI systems from the ground up.
Students and Professionals in AI: Those studying or working in AI-related fields who seek to enhance their practical skills and theoretical understanding of LLMs and deep learning.
Curious Minds with Creative Flair: Learners interested in a unique blend of technology and art, who are eager to explore deep learning concepts through innovative methods like origami.
Software engineers: interested in understanding and coding LLMs as well as implementing AI alignment techniques with LLMs
General: People that are curious about how LLMs work and want to understand them in great depth
General: People that want to stretch their generative AI experience using Python and Pytorch to program LLMs and alignment processes
General: People that want to know all the key parts of how ChatGPT, Gemini or Claude work internally, in order to get inspired about new ways of applying this technology
General: Those that want a deep introduction to Generative AI, deep learning and neural networks
General: Those that want to deeply understand how neural networks learn in a fun way and unique way through Origami

Target Audiences

AI Enthusiasts and Developers: Individuals with a passion for artificial intelligence and a basic knowledge of Python who want to dive deep into the world of LLMs and generative AI.
Tech Innovators and Creators: Aspiring AI developers who wish to be at the cutting edge of technology, learning to build and understand complex AI systems from the ground up.
Students and Professionals in AI: Those studying or working in AI-related fields who seek to enhance their practical skills and theoretical understanding of LLMs and deep learning.
Curious Minds with Creative Flair: Learners interested in a unique blend of technology and art, who are eager to explore deep learning concepts through innovative methods like origami.
Software engineers: interested in understanding and coding LLMs as well as implementing AI alignment techniques with LLMs
General: People that are curious about how LLMs work and want to understand them in great depth
General: People that want to stretch their generative AI experience using Python and Pytorch to program LLMs and alignment processes
General: People that want to know all the key parts of how ChatGPT, Gemini or Claude work internally, in order to get inspired about new ways of applying this technology
General: Those that want a deep introduction to Generative AI, deep learning and neural networks
General: Those that want to deeply understand how neural networks learn in a fun way and unique way through Origami

Dive into the most exhilarating and hands-on LLM course you’ll ever experience! This isn’t just learning—it’s an adventure that will transform you from an AI enthusiast into a creator at the bleeding edge 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.
Origami Meets AI: Be part of a world-first! Unravel deep learning mysteries through the art of paper folding.
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)

Course Highlights:

Intro to Generative AI: Dive into the mesmerizing world of Generative AI, where machines create and innovate beyond imagination.
Code an LLM from Scratch: Code and nurture your very own LLM from scratch.
Unlocking an LLM Titan: Dissect an advanced LLM architecture. Peek behind the curtain of the most powerful AI systems on the planet.
Alignment. Code the Secret Sauce of the top LLMs: Code a cutting edge LLM alignment process. This is the crucial stage that makes ChatGPT, GPT 4, Claude and Gemini possible and we code together a cutting edge variation of it.
Origami AI: Fold your way to neural network nirvana. Experience a world-first fusion of ancient art and cutting-edge science to grasp deep learning like never before.
AI Meets Zen: Cap your journey with an optional mind-bending guided meditation. Explore the ultimate generative AI – the one in your own brain – in a profound finale that bridges technology and spirituality.

All in One / Why You Can’t Miss This:

The full package: You code both a small LLM as well as a cutting edge alignment technique. You also go deep into the understanding of a complex LLM architecture. In parallel you dive very deeply into all sorts of complex concepts around LLMs and deep learning, both during the coding and also during the unique Origami experience as well as the initial intro to Generative AI.
Uniqueness: Origami + AI = A learning experience you won’t find anywhere else. Understand key insights about Deep Learning and Neural Networks through the magic of paper folding.
Practical Hands-on Mastery: 80% Practical. Learn and Build, Train and Align.
Future-Proof Skills: Position yourself at the forefront of the AI revolution.
And there’s more: Added to all of that, the course connects you with free tools, articles and infographics produced by Ideami that enrich and accelerate your learning even more. Some of then, like the Loss Landscape explorer app, are unique tools in the world, created by Ideami for you.
Accessibility: Complex concepts explained so clearly, you’ll feel like an AI whisperer.

In summary

This isn’t just a course—it’s a ticket to the AI creator’s club. By the end, you’ll have coded an LLM, understood its deepest secrets, coded an alignment technique, dived deep into profound insights about deep learning and gained practical skills that will make you the AI guru in any room.

Ready to code the future, fold profound insights through origami and blow your own mind?Join us on this unparalleled journey to the heart of LLM technology. Enroll now and prepare for the most fun, deep, and transformative tech adventure of your life!

Course Curriculum

Chapter 1: Introduction to Generative AI

Lecture 1: Welcome to the course

Lecture 2: Why we will start by introducing Generative AI concepts

Lecture 3: Introducing myself

Lecture 4: Generative modelling, Evolution of Generative AI and Overview of applications

Lecture 5: Building Blocks of Machine Creativity: Machine Learning Foundations for Gen AI

Lecture 6: Architectures of Machine Imagination, from GANs to Diffusion and beyond

Lecture 7: Machine Creativity Meets Real-World Impact – Applications of Generative AI

Lecture 8: The Ethics of Machine Creativity: Challenges and Considerations in Generative AI

Lecture 9: Worlds Reimagined: Visions of the Future with Generative AI

Lecture 10: Summary and closing thoughts about this intro of GenAI

Chapter 2: Coding a small LLM from scratch, understanding all the key concepts involved

Lecture 1: Welcome to this section

Lecture 2: Where to do the coding – Intro

Lecture 3: Where to do the coding – Details

Lecture 4: Dealing with challenges, and reminder about coding options

Lecture 5: Setting up the coding environment

Lecture 6: How Jupyter Notebooks work

Lecture 7: Importing the necessary libraries

Lecture 8: Setting up our base files

Lecture 9: Setting up the parameters of the architecture

Lecture 10: Exploring the crucial hyperparameters

Lecture 11: Key parameters for an effective training process

Lecture 12: Introducing Logging

Lecture 13: Setting up logging

Lecture 14: Setting up the tokenizer and related functionality

Lecture 15: Splitting our data and creating our get batch function

Lecture 16: The Transformer Architecture

Lecture 17: Declaring the top layers of the LLM

Lecture 18: The forward function of the LLM

Lecture 19: The Cross Entropy Loss with Pytorch

Lecture 20: The Cross Entropy Loss recreated manually

Lecture 21: From Information to Cross-Entropy – Deep Dive

Lecture 22: Completing and verifying the manual cross entropy loss

Lecture 23: Generating new samples – Intro

Lecture 24: Creating the functionality to generate new samples

Lecture 25: Testing the sample generation functionality

Lecture 26: Coding the blocks of the LLM architecture

Lecture 27: Communication plus Computation

Lecture 28: Providing computational power to the LLM

Lecture 29: The Multi Head Attention Mechanism

Lecture 30: Attention is all you need

Lecture 31: Coding and understanding the attention head

Lecture 32: Understanding attention – deep manual dive

Lecture 33: Review and debugging example

Lecture 34: Evaluating the performance with more precision

Lecture 35: Setting up the Optimizer and Scheduler

Lecture 36: Loading checkpoints for Inference or to restart trainings

Lecture 37: Loading and testing a pre-trained checkpoint

Lecture 38: Coding the learning process – Intro

Lecture 39: The training loop

Lecture 40: Training our LLM

Lecture 41: Keeping in mind the scale of our LLM

Lecture 42: Training the tokenizer

Lecture 43: Encoding our dataset with the tokenizer

Lecture 44: Conclusions and what comes next

Chapter 3: Understanding the code and concepts of an Advanced LLM

Lecture 1: Welcome to a deep dive through an advanced LLM architecture

Lecture 2: Setting up a new environment and hosting the support files

Lecture 3: Declaring the main parameters of the model

Lecture 4: Main structure and loss calculation

Lecture 5: Advanced generation using extra parameters

Lecture 6: The main blocks of the architecture

Lecture 7: Analyzing the computational layers of the LLM

Lecture 8: An efficient attention implementation, part 1

Lecture 9: An efficient attention implementation, part 2

Lecture 10: Exploring rotary positional embeddings and other supporting functions

Lecture 11: Analyzing the inference code

Lecture 12: Preparing to run inference on the cloud and locally

Lecture 13: Inference on non-aligned vs aligned versions of the model

Lecture 14: Further reflections on the inference results

Chapter 4: Coding an alignment process from scratch, understanding all the key concepts

Lecture 1: The importance of alignment

Lecture 2: The pretraining and alignment datasets

Lecture 3: Importing the necessary libraries

Lecture 4: Setting up the parameters for the alignment process

Lecture 5: Setting up the chat template for the tokenizing process

Lecture 6: Filtering our alignment dataset

Lecture 7: Pre-processing and Tokenizing the alignment dataset

Lecture 8: Debugging and completing the pre-processing function

Lecture 9: Splitting the alignment data and creating our dataloaders

Lecture 10: Setting up the model and optimizer for the alignment training process

Lecture 11: Setting up our scheduler function

Lecture 12: Coding the training loop of the alignment process

Lecture 13: Coding the alignment loss calculation – part 1

Lecture 14: Understanding how we will favor aligned responses – Deep Dive

Lecture 15: Coding the alignment loss calculation – part 2

Lecture 16: Coding the alignment loss calculation – part 3

Lecture 17: Adding logging, checkpoint saving and launching the training

Lecture 18: Training and testing the alignment, analyzing and expanding the stats

Lecture 19: Adding new code to calculate more precise training and validation losses

Lecture 20: Comparing training and validation charts – Deep Dive

Lecture 21: Alignment wrap-up

Lecture 22: The path towards alignment

Lecture 23: Congrats, summary, and what's next

Chapter 5: Origami + AI: Learning key insights about neural networks and AI with Origami

Lecture 1: Welcome to this original origami based journey to the core of AI

Lecture 2: In Search of the Magical Mappings of Creativity, using Origami!

Lecture 3: The Search for the Perfect Mapping: datasets and dimensionality

Instructors

Javier Ideami
Multidisciplinary engineer, researcher & creative director

Rating Distribution

1 stars: 0 votes
2 stars: 0 votes
3 stars: 2 votes
4 stars: 4 votes
5 stars: 25 votes

Frequently Asked Questions

How long do I have access to the course materials?

You can view and review the lecture materials indefinitely, like an on-demand channel.

Can I take my courses with me wherever I go?

Definitely! If you have an internet connection, courses on Udemy are available on any device at any time. If you don’t have an internet connection, some instructors also let their students download course lectures. That’s up to the instructor though, so make sure you get on their good side!

Menu