We may earn an affiliate commission when you visit our partners.

Generative AI and LLMs

Architecture and Data Preparation

Joseph Santarcangelo and Roodra Pratap Kanwar

This IBM short course, a part of Generative AI Engineering Essentials with LLMs Professional Certificate, will teach you the basics of using generative AI and Large Language Models (LLMs). This course is suitable for existing and aspiring data scientists, machine learning engineers, deep-learning engineers, and AI engineers.

You will learn about the types of generative AI and its real-world applications. You will gain the knowledge to differentiate between various generative AI architectures and models, such as Recurrent Neural Networks (RNNs), Transformers, Generative Adversarial Networks (GANs), Variational AutoEncoders (VAEs), and Diffusion Models. You will learn the differences in the training approaches used for each model. You will be able to explain the use of LLMs, such as Generative Pre-Trained Transformers (GPT) and Bidirectional Encoder Representations from Transformers (BERT).

You will also learn about the tokenization process, tokenization methods, and the use of tokenizers for word-based, character-based, and subword-based tokenization. You will be able to explain how you can use data loaders for training generative AI models and list the PyTorch libraries for preparing and handling data within data loaders. The knowledge acquired will help you use the generative AI libraries in Hugging Face. It will also prepare you to implement tokenization and create an NLP data loader.

For this course, a basic knowledge of Python and PyTorch and an awareness of machine learning and neural networks would be an advantage, though not strictly required.

Enroll now

Or subscribe to Coursera Plus

And get unlimited access to Coursera

Two deals to help you save

Save money when you learn. Here are two deals and offers that may be relevant to this course.

All coupon codes, vouchers, and discounts are applied automatically unless otherwise noted.

Valid until December 2

Annual Subscription

Invest in your career growth and save. Start your annual subscription to Coursera Plus and access 10,000+ programs.

Valid until March 12, 2027

Save 40% Off 3 Months

Access thousands of top-rated learning programs with a Coursera Plus monthly subscription and take 40% off 3 months for a limited time.

What's inside

Syllabus

Generative AI Architecture

In this module, you will learn about the significance of generative AI models and how they are used across a wide range of fields for generating various types of content. You will learn about the architectures and models commonly used in generative AI and the differences in the training approaches of these models. You will learn how large language models (LLMs) are used to build NLP-based applications. You will build a simple chatbot using the transformers library from Hugging Face.

Traffic lights

Read about what's good

what should give you pause

and possible dealbreakers

Suitable for existing and aspiring data scientists, machine learning engineers, deep learning engineers, and AI engineers

Taught by Joseph Santarcangelo and Roodra Pratap Kanwar, who are recognized for their work in NLP

Part of Generative AI Engineering Essentials with LLMs Professional Certificate

Provides hands-on experience with Generative AI libraries in Hugging Face

Save this course

Create your own learning path. Save this course to your list so you can find it easily later.

Save

Reviews summary

Practical generative ai foundations

According to students, this course offers a largely positive introduction to Generative AI and LLMs, focusing on architecture and data preparation. Learners appreciate the comprehensive coverage of various generative AI models like Transformers and GANs, alongside practical tokenization methods and the use of PyTorch DataLoaders. The hands-on chatbot project with Hugging Face is highlighted as particularly useful for applying concepts. While it serves as a concise yet effective overview, learners suggest that prior basic knowledge of Python and PyTorch is beneficial for maximizing the learning experience.

Best suited for those with a solid ML/Python foundation.

"As an aspiring data scientist, I found the pace just right, especially with my prior ML knowledge."

"For someone new to PyTorch, I might recommend brushing up on basics first, even if not 'strictly required'."

"I think this course is perfect for machine learning engineers looking to specialize in generative AI."

Delivers essential concepts effectively in a short format.

"It's a great short course to get up to speed on the fundamentals of generative AI and LLMs."

"I found the modules to be 'bite-sized' and easy to digest, covering a lot without feeling rushed."

"While not exhaustive, it provided enough depth to understand core concepts and prepare for more advanced study."

Includes practical implementation with a simple chatbot.

"Building the simple chatbot using the transformers library was a great way to apply what I learned."

"The project gave me confidence in using Hugging Face for real-world applications."

"I appreciated the direct application of theory through the chatbot exercise."

Offers a solid foundational overview of generative AI models.

"I really appreciated the broad coverage of different generative AI architectures like GANs and Diffusion models."

"The course clearly explained the differences between various LLMs such as GPT and BERT."

"I now have a much clearer understanding of how various generative AI models are trained and applied."

Provides practical skills in tokenization and data handling.

"The tokenization module was incredibly hands-on, showing me how to implement it with different libraries."

"Learning about PyTorch DataLoader and creating custom collate functions was very valuable for my projects."

"I found the sections on Hugging Face libraries immediately applicable to building NLP systems."

Activities

Be better prepared before your course. Deepen your understanding during and after it. Supplement your coursework and achieve mastery of the topics covered in Generative AI and LLMs: Architecture and Data Preparation with these activities:

Review Python and PyTorch basics

Show steps

Reviewing these topics will help you refresh your understanding of the core concepts used in this course.

Browse courses on Python

Show steps

Go through online tutorials or documentation on Python and PyTorch.
Complete practice exercises or coding challenges to test your understanding.

Mentor a junior student in generative AI

Show steps

Mentoring others will reinforce your understanding of generative AI and help you develop your communication and leadership skills.

Browse courses on Generative AI

Show steps

Reach out to junior students or peers who are interested in generative AI.
Provide guidance on topics such as model selection, training techniques, and evaluation metrics.
Review their code, provide feedback, and help them troubleshoot any issues.

Attend a workshop on generative AI applications

Show steps

Attending a workshop will expose you to real-world use cases and industry best practices in generative AI.

Browse courses on Generative AI

Show steps

Research and identify upcoming workshops on generative AI.
Register for a workshop that aligns with your interests and learning goals.
Attend the workshop, actively participate in discussions, and take notes.

Four other activities

Expand to see all activities and additional details

Show all seven activities

Follow tutorials on generative AI models

Show steps

Following tutorials will provide you with hands-on experience in implementing and training generative AI models.

Browse courses on Generative AI

Show steps

Identify relevant tutorials from reputable sources such as Coursera, edX, or YouTube.
Go through the tutorials step-by-step, implementing the code and experimenting with different parameters.
Document your learnings and any challenges you faced during the tutorials.

Practice tokenization and data loading techniques

Show steps

Practicing these techniques will improve your proficiency in preparing data for generative AI models.

Browse courses on Tokenization

Show steps

Find datasets suitable for generative AI tasks, such as text generation or image synthesis.
Implement tokenization methods using libraries like spaCy or Hugging Face's Tokenizers.
Create data loaders using PyTorch's DataLoader class to handle data efficiently.
Experiment with different tokenization and data loading parameters to optimize your models.

Develop a research proposal on a generative AI topic

Show steps

Writing a research proposal will challenge you to think critically about generative AI's potential and applications.

Browse courses on Generative AI

Show steps

Identify a specific research question or problem you want to address.
Review existing literature and research on generative AI.
Develop a research methodology and plan for your proposed study.
Write a research proposal outlining your research question, methods, and expected outcomes.

Build a simple NLP application using a pre-trained language model

Show steps

Building an NLP application will allow you to apply your understanding of generative AI in a practical context.

Browse courses on NLP

Show steps

Choose a specific NLP task, such as text classification or question answering.
Select a pre-trained language model from Hugging Face or other providers.
Fine-tune the model on your dataset using transfer learning techniques.
Deploy your NLP application and evaluate its performance.

Career center

Learners who complete Generative AI and LLMs: Architecture and Data Preparation will develop knowledge and skills that may be useful to these careers:

Reading list

We've selected 50 books that we think will supplement your learning. Use these to develop background knowledge, enrich your coursework, and gain a deeper understanding of the topics covered in Generative AI and LLMs: Architecture and Data Preparation.

Natural Language Processing with Transformers,...

Save

Co-authored by creators of the Hugging Face ecosystem, the revised edition serves as the definitive practitioner manual for training, fine-tuning, and deploying encoder-decoder and decoder-only transformers. Readers dissect multi-head self-attention, tokenization pipelines, and model quantization through production PyTorch code.

Generative AI and LLMs

Two deals to help you save

What's inside

Syllabus

Traffic lights

Save this course

Reviews summary

Practical generative ai foundations

Activities

Career center

Reading list

Share

Similar courses

Coursera Buyer Protection & Guarantee

7-Day Free Trial & Free Audit

14-Day Refund Guarantee

Verified Academic & Industry Partner