Introduction to Transformer Models for NLP: Unit 3

Introduction to Transformer Models for NLP: Unit 3

This course is part of Introduction to Transformer Models for NLP Specialization

Instructors: Pearson

Access provided by SGCSRC

1 module

Gain insight into a topic and learn the fundamentals.

Intermediate level

Recommended experience

5 hours to complete

Flexible schedule

Learn at your own pace

1 module

Gain insight into a topic and learn the fundamentals.

Intermediate level

Recommended experience

5 hours to complete

Flexible schedule

Learn at your own pace

What you'll learn

Understand and apply the T5 model’s end-to-end transformer architecture for advanced NLP tasks.
Fine-tune and evaluate transformer models for complex applications like abstractive summarization.
Leverage Vision Transformers and build custom image captioning systems by combining vision and language models.
Deploy, share, and operationalize transformer models using modern MLOps tools and cloud frameworks.

Skills you'll gain

Tools you'll learn

Details to know

Shareable certificate

Add to your LinkedIn profile

Assessments

5 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 Introduction to Transformer Models for NLP 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 is 1 module in this course

This course covers transformer models and their applications in natural language processing and computer vision. Topics include the T5 model, fine-tuning for tasks such as abstractive summarization, and the Vision Transformer. Students will learn to build an image captioning system by combining vision and language models. The course also provides practical instruction on deploying models, including MLOps practices, sharing models on HuggingFace, and cloud deployment with FastAPI. By the end of the course, students will have the knowledge and skills to implement, fine-tune, and deploy transformer models for various real-world tasks.

This module explores advanced transformer models and their applications across natural language processing and computer vision. Learners will examine the T5 model’s end-to-end architecture and cross-attention mechanism, apply and fine-tune T5 for complex NLP tasks, and discover how vision transformers extend these techniques to image processing and image captioning. The module concludes with practical strategies for deploying and sharing transformer models using MLOps principles, HuggingFace, and FastAPI, equipping students with both theoretical understanding and hands-on skills for state-of-the-art model development and deployment.