This course teaches you the skills you need to get your first job as a generative AI architect or data scientist.

You will learn:

Job-ready generative AI architecture and data science skills in less than a month, plus practical experience and an industry-recognized credential that employers value.
Difference between generative AI architectures and models, such as RNNs, transformers, VAEs, GANs, and diffusion models.
Use of LLMs, such as GPT, BERT, BART, and T5 in language processing.
Implementation of tokenization to preprocess raw textual data using NLP libraries such as NLTK, spaCy, BertTokenizer, and XLNetTokenizer.
Creation of an NLP data loader using PyTorch to perform tokenization, numericalization, and padding of text data.

Course Overview

The demand for generative AI is expected to grow at 46.47% annually, resulting in a market volume of US$356bn by 2030 (Source: Statista, Feb 2024). The expansion of generative AI across industries emphasizes its potential for aspiring data scientists, machine learning engineers, and AI developers.

This course focuses on using large language models (LLMs), natural language processing (NLP), and general artificial intelligence (AI) skills that organizations desire.

In this course, you will learn about the types of generative AI and its real-world applications. You will gain knowledge of 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).

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

Throughout this short self-paced course, you will be presented with instructional guidance through videos followed by hands-on labs to practice what you learn. You will also complete a final project to showcase your generative AI architecture or data preparation skills.

If you’re looking to build a rewarding career in generative AI architecture or data science domain, this IBM Generative AI Architecture and Data Preparation for LLMs course will get you job-ready and give you the skills you need for rewarding career opportunities.

Course Syllabus

Module 1: Generative AI Architecture

Video: Overview of AI Engineering with LLMs Specialization
Video: Course Introduction
Reading: Course Overview
Reading: Helpful Tips for Course Completion
Video: Significance of Generative AI
Video: Generative AI Architectures and Models
Video: Generative AI for NLP
Reading: Basics of AI Hallucinations
Reading: Overview of Libraries and Tools
Lab: Exploring Generative AI Libraries
Reading: Summary and Highlights
Practice Quiz: Generative AI Overview and Architecture
Graded Quiz: Generative AI Architecture

Module 2: Data Preparation for LLMs

Video: Tokenization
Lab: Implementing Tokenization
Video: Overview of Data Loaders
Lab: Creating an NLP Data Loader
Reading: Summary and Highlights
Practice Quiz: Preparing Data
Graded Quiz: Data Preparation for LLMs
Cheat Sheet: Generative AI and LLMs: Architecture and Data Preparation
Course Glossary: Generative AI and LLMs: Architecture and Data Preparation

Recommended Skills Prior to Taking this Course

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.

Mastering Generative AI: LLM Architecture & Data Preparation

Language

Topic

Skills You Will Learn

Offered By

Estimated Effort

Platform

Last Update