When will I have access to the lectures and assignments?

To access the course materials, assignments and to earn a Certificate, you will need to purchase the Certificate experience when you enroll in a course. You can try a Free Trial instead, or apply for Financial Aid. The course may offer 'Full Course, No Certificate' instead. This option lets you see all course materials, submit required assessments, and get a final grade. This also means that you will not be able to purchase a Certificate experience.

What will I get if I subscribe to this Specialization?

When you enroll in the course, you get access to all of the courses in the Specialization, and you earn a certificate when you complete the work. Your electronic Certificate will be added to your Accomplishments page - from there, you can print your Certificate or add it to your LinkedIn profile.

Is financial aid available?

Yes. In select learning programs, you can apply for financial aid or a scholarship if you can’t afford the enrollment fee. If fin aid or scholarship is available for your learning program selection, you’ll find a link to apply on the description page.

Building and Deploying Generative AI Models

kurs ist nicht verfügbar in Deutsch (Deutschland)

Wir übersetzen es in weitere Sprachen.

Building and Deploying Generative AI Models

Dieser Kurs ist Teil von Spezialisierung „Generative AI Fundamentals“

Dozenten: Amreen Anbar

Bei enthalten

Mehr erfahren

3 Module

Verschaffen Sie sich einen Einblick in ein Thema und lernen Sie die Grundlagen.

Stufe Mittel

Empfohlene Erfahrung

1 Woche zu vervollständigen

unter 10 Stunden pro Woche

Flexibler Zeitplan

In Ihrem eigenen Lerntempo lernen

3 Module

Verschaffen Sie sich einen Einblick in ein Thema und lernen Sie die Grundlagen.

Stufe Mittel

Empfohlene Erfahrung

1 Woche zu vervollständigen

unter 10 Stunden pro Woche

Flexibler Zeitplan

In Ihrem eigenen Lerntempo lernen

Was Sie lernen werden

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.

Kompetenzen, die Sie erwerben

Kategorie: LLM Application
Kategorie: Artificial Intelligence and Machine Learning (AI/ML)
Kategorie: Development Environment
Kategorie: Agentic systems
Kategorie: Model Training
Kategorie: System Monitoring
Kategorie: Model Optimization
Kategorie: Generative AI Agents
Kategorie: Google Cloud Platform
Kategorie: Model Evaluation
Kategorie: Generative Model Architectures
Kategorie: Deep Learning
Kategorie: Large Language Modeling
Kategorie: Fine-tuning

Werkzeuge, die Sie lernen werden

Kategorie: LangChain
Kategorie: Agentic Workflows
Kategorie: Generative AI
Kategorie: Model Deployment
Kategorie: PyTorch (Machine Learning Library)
Kategorie: AI Workflows

Wichtige Details

Zertifikat zur Vorlage

Zu Ihrem LinkedIn-Profil hinzufügen

Kürzlich aktualisiert!

Dezember 2025

Bewertungen

3 Aufgaben

Unterrichtet in Englisch

Erfahren Sie, wie Mitarbeiter führender Unternehmen gefragte Kompetenzen erwerben.

Weitere Informationen zu Coursera für Unternehmen

Logos von Petrobras, TATA, Danone, Capgemini, P&G und L'Oreal

Erweitern Sie Ihre Fachkenntnisse

Dieser Kurs ist Teil der Spezialisierung Spezialisierung „Generative AI Fundamentals“

Wenn Sie sich für diesen Kurs anmelden, werden Sie auch für diese Spezialisierung angemeldet.

Lernen Sie neue Konzepte von Branchenexperten
Gewinnen Sie ein Grundverständnis bestimmter Themen oder Tools
Erwerben Sie berufsrelevante Kompetenzen durch praktische Projekte
Erwerben Sie ein Berufszertifikat zur Vorlage

In diesem Kurs gibt es 3 Module

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.

Moduldetails

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.

Das ist alles enthalten

18 Videos11 Lektüren1 Aufgabe

18 VideosInsgesamt 113 Minuten

Course Introduction4 Minuten
Meet your instructor: Amreen Anbar1 Minute
Meet your instructor: Anahita Doosti1 Minute
Meet your instructor: Soroush Razavi1 Minute
Transformer: Evolution Unveiled8 Minuten
Transformer: Types8 Minuten
Transformer: The Components7 Minuten
Setting The Stage: Environment, Libraries and Data8 Minuten
Looking beyond theory: Let’s Build a Transformer!9 Minuten
Looking beyond theory: Training and Text Generation8 Minuten
Building the Complete Encoder-Decoder Summarizer: Encoder, Decoder, and the Cross-Attention Mechanism7 Minuten
Building the Complete Encoder-Decoder Summarizer: Teacher Forcing, Loss, and Inference7 Minuten
Scaling the Architecture: From Character Tokens to BPE and Massive Data8 Minuten
Scaling the Architecture: High-Performance Optimization (AMP) and ROUGE Evaluation9 Minuten
Synthesis: Implementation of the Translator Transformer9 Minuten
Bypass the Training Wall: Powerful LLM Applications Without Massive Compute5 Minuten
A Resource-Efficient Approach: Using pre-trained models for Summarization 6 Minuten
A Resource-Efficient Approach: Using Pre-trained Models for Translation8 Minuten

11 LektürenInsgesamt 290 Minuten

The original paper, "Attention Is All You Need"20 Minuten
Interactive Transformer Explainer30 Minuten
Notebook 140 Minuten
Notebook 240 Minuten
Notebook 340 Minuten
Dataset (cnn_dailymail)10 Minuten
Notebook 440 Minuten
Dataset (wmt14)10 Minuten
ROUGE and BLEU Score for NLP Evaluation20 Minuten
Notebook 520 Minuten
Notebook 620 Minuten

1 AufgabeInsgesamt 30 Minuten

Section 1 Quiz30 Minuten

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.

Das ist alles enthalten

13 Videos2 Lektüren1 Aufgabe

13 VideosInsgesamt 85 Minuten

What is RAG?6 Minuten
Building a Minimal RAG from Scratch with Ollama (Part 1)7 Minuten
Building a Minimal RAG from Scratch with Ollama (Part 2)5 Minuten
An Improved RAG Pipeline with LangChain7 Minuten
RAG Evaluation and Metrics7 Minuten
Implementing RAG Evaluation7 Minuten
Document Loaders and Chunking Strategies6 Minuten
Vector Stores and Indexing6 Minuten
Reranking and Contextual Compression7 Minuten
Query Transformation7 Minuten
Pick the Right Models for your RAG7 Minuten
What is Finetuning?5 Minuten
RAG vs. Finetuning: Which one to choose?7 Minuten

2 LektürenInsgesamt 140 Minuten

Coding Notebooks 20 Minuten
Final RAG Results 120 Minuten

1 AufgabeInsgesamt 30 Minuten

Section 2 Quiz30 Minuten

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.