Building and Deploying Generative AI Models

Building and Deploying Generative AI Models

This course is part of Generative AI Fundamentals Specialization

Instructors: Amreen Anbar

Access provided by SDNB College

3 modules

Gain insight into a topic and learn the fundamentals.

Intermediate level

Recommended experience

1 week to complete

at 10 hours a week

Flexible schedule

Learn at your own pace

3 modules

Gain insight into a topic and learn the fundamentals.

Intermediate level

Recommended experience

1 week to complete

at 10 hours a week

Flexible schedule

Learn at your own pace

What you'll learn

Construct and evaluate Transformer-based LLMs from scratch using PyTorch and industry metrics like ROUGE and BLEU.
Engineer Retrieval Augmented Generation (RAG) pipelines using LangChain to integrate current, domain-specific knowledge into models.
Deploy autonomous AI Agents to production environments on Google Cloud Platform (Vertex AI) using professional workflows.

Skills you'll gain

Tools you'll learn

Details to know

Shareable certificate

Add to your LinkedIn profile

Assessments

3 assignments

Taught in English

See how employees at top companies are mastering in-demand skills

Learn more about Coursera for Business

logos of Petrobras, TATA, Danone, Capgemini, P&G and L'Oreal

Build your subject-matter expertise

This course is part of the Generative AI Fundamentals Specialization

When you enroll in this course, you'll also be enrolled in this Specialization.

Learn new concepts from industry experts
Gain a foundational understanding of a subject or tool
Develop job-relevant skills with hands-on projects
Earn a shareable career certificate

There are 3 modules in this course

Transition from theoretical concepts to production-ready engineering in this hands-on course which is the final part in "Fundamentals of Generative AI" specialization. Designed for learners ready to move beyond the theory, this course focuses entirely on construction: you won't just learn about Large Language Models (LLMs); you will build, refine, and deploy them.

We start at the foundational level, coding different types of Transformer architectures from scratch using PyTorch. Through high-performance training with Automatic Mixed Precision and ROUGE/BLEU evaluation, you will learn the techniques to scale custom components into optimized systems. By utilizing pre-trained models and weighing performance trade-offs, you will gain the insight needed to select the most efficient path for large-scale deployment. Moving to applied architecture, you will master Retrieval Augmented Generation (RAG) using LangChain, learning to evaluate pipelines and apply advanced techniques such as different chunking strategies, reranking and compression, and query transformation. You'll also navigate model selection as well as the critical trade-offs between RAG and Fine-tuning. Finally, you will step into the future of AI by developing autonomous Agents. You will bridge the gap between development and production by setting up a professional workflow with Poetry and deploying a Summarizer AI Agent directly to the Google Cloud Platform (Vertex AI). By the end of this course, you will possess a tangible portfolio of code and a live deployment, proving your ability to engineer robust Generative AI solutions.

In this module, we dive deep into the Transformer architecture, its core mechanics, and different transformer architecture types (encoder-only, decoder-only, encoder-decoder). We gain hands-on experience by building and training a complete suite of PyTorch-based models from scratch. The module concludes with strategic deployment skills, teaching when to build custom models versus leveraging pre-trained models for efficiency and state-of-the-art results.

What's included

18 videos11 readings1 assignment

18 videos Total 113 minutes

Course Introduction 4 minutes
Meet your instructor: Amreen Anbar 1 minute
Meet your instructor: Anahita Doosti 1 minute
Meet your instructor: Soroush Razavi 1 minute
Transformer: Evolution Unveiled 8 minutes
Transformer: Types 8 minutes
Transformer: The Components 7 minutes
Setting The Stage: Environment, Libraries and Data 8 minutes
Looking beyond theory: Let’s Build a Transformer! 9 minutes
Looking beyond theory: Training and Text Generation 8 minutes
Building the Complete Encoder-Decoder Summarizer: Encoder, Decoder, and the Cross-Attention Mechanism 7 minutes
Building the Complete Encoder-Decoder Summarizer: Teacher Forcing, Loss, and Inference 7 minutes
Scaling the Architecture: From Character Tokens to BPE and Massive Data 8 minutes
Scaling the Architecture: High-Performance Optimization (AMP) and ROUGE Evaluation 9 minutes
Synthesis: Implementation of the Translator Transformer 9 minutes
Bypass the Training Wall: Powerful LLM Applications Without Massive Compute 5 minutes
A Resource-Efficient Approach: Using pre-trained models for Summarization 6 minutes
A Resource-Efficient Approach: Using Pre-trained Models for Translation 8 minutes

11 readings Total 290 minutes

The original paper, "Attention Is All You Need" 20 minutes
Interactive Transformer Explainer 30 minutes
Notebook 1 40 minutes
Notebook 2 40 minutes
Notebook 3 40 minutes
Dataset (cnn_dailymail) 10 minutes
Notebook 4 40 minutes
Dataset (wmt14) 10 minutes
ROUGE and BLEU Score for NLP Evaluation 20 minutes
Notebook 5 20 minutes
Notebook 6 20 minutes

1 assignment Total 30 minutes

Section 1 Quiz 30 minutes

Module 2 addresses the limitations of static knowledge and hallucinations in Large Language Models (LLMs) by introducing Retrieval Augmented Generation (RAG). Learners will progress from building fundamental pipelines with Ollama and LangChain to implementing production-ready systems by adding rigorous RAG evaluation and utilizing advanced techniques such as custom chunking strategies, vector stores, reranking, and query transformations to optimize context retrieval and response generation. The module concludes with an overview of another adaptation technique called finetuning and a comparison of RAG vs. finetuning.

What's included

13 videos2 readings1 assignment

13 videos Total 85 minutes

What is RAG? 6 minutes
Building a Minimal RAG from Scratch with Ollama (Part 1) 7 minutes
Building a Minimal RAG from Scratch with Ollama (Part 2) 5 minutes
An Improved RAG Pipeline with LangChain 7 minutes
RAG Evaluation and Metrics 7 minutes
Implementing RAG Evaluation 7 minutes
Document Loaders and Chunking Strategies 6 minutes
Vector Stores and Indexing 6 minutes
Reranking and Contextual Compression 7 minutes
Query Transformation 7 minutes
Pick the Right Models for your RAG 7 minutes
What is Finetuning? 5 minutes
RAG vs. Finetuning: Which one to choose? 7 minutes

2 readings Total 140 minutes

Coding Notebooks 20 minutes
Final RAG Results 120 minutes

1 assignment Total 30 minutes

Section 2 Quiz 30 minutes

Module 3 marks a pivotal transition from passive information retrieval to the dynamic realm of autonomous AI Agents, anchored by the "Understand, Think, Take Action" conceptual framework. Students will critically evaluate development ecosystems before applying these concepts to build a functional Summarizer Agent. The module emphasizes professional engineering standards, guiding learners through a complete lifecycle that includes environment management with Poetry, deployment to the Vertex AI Engine, and the implementation of robust performance monitoring using Google Cloud Platform’s logging and tracing tools.