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 4 modules in this course
Master the complete workflow for fine-tuning transformer models using the Hugging Face ecosystem. This hands-on course takes you from navigating the Hugging Face Hub to deploying production-ready models.You'll start by learning to discover, evaluate, and select models and datasets from the Hub's vast repository. Then you'll build practical skills in loading and preprocessing data, including streaming techniques for datasets too large to fit in memory.The core of the course focuses on fine-tuning transformers using the Trainer API. You'll implement custom callbacks, configure training optimizations like mixed precision, and develop comprehensive evaluation pipelines with metrics including accuracy, F1, precision, and recall.The capstone project ties everything together: you'll build an end-to-end sentiment analysis system, from data preprocessing and augmentation through training, evaluation, and publishing your model to Hugging Face Hub with professional documentation.By course end, you'll have hands-on experience with the same tools and workflows used by ML teams at leading organizations, plus a published model in your portfolio.
Build robust data pipelines for transformer fine-tuning. Load datasets from multiple sources, apply transformations efficiently, and handle real-world data challenges like class imbalance.
What's included
17 videos10 readings1 assignment
Show info about module content
17 videos•Total 56 minutes
Course Introduction•1 minute
Introduction•0 minutes
Datasets Library Overview•6 minutes
Exploring Dataset Structure•5 minutes
Loading Datasets From HuggingFace•4 minutes
Loading Diverse Datasets•6 minutes
Summary•1 minute
Introduction•1 minute
Dataset Transformations•4 minutes
Batched Processing•4 minutes
Tokenization Strategy•7 minutes
Summary•1 minute
Introduction•1 minute
Custom Datasets•6 minutes
Data Augmentation•6 minutes
Handling Imbalanced Data•4 minutes
Summary•1 minute
10 readings•Total 22 minutes
About this course and your instructors•1 minute
Key Terms•1 minute
Lab•5 minutes
Reflection•1 minute
Key Terms•1 minute
Lab•5 minutes
Reflection•1 minute
Key Terms•1 minute
Lab•5 minutes
Reflection•1 minute
1 assignment•Total 30 minutes
Quiz: Introduction to Datasets•30 minutes
Training
Module 2•2 hours to complete
Module details
Fine-tune transformer models using the Trainer API. Configure training parameters, optimize performance with mixed precision, and monitor progress with callbacks and logging.
What's included
15 videos9 readings
Show info about module content
15 videos•Total 40 minutes
Introduction•1 minute
Trainer API Introduction•4 minutes
Inference API Introduction•4 minutes
Model Selection•5 minutes
Summary•1 minute
Introduction•1 minute
Understanding Metrics•4 minutes
Optimizer Selection•3 minutes
Mixed Precision Training•3 minutes
Summary•1 minute
Introduction•1 minute
Using Callbacks•5 minutes
Adding Specific Logging•5 minutes
Debugging Training•4 minutes
Summary•1 minute
9 readings•Total 90 minutes
Key Terms•10 minutes
Lab•10 minutes
Reflection•10 minutes
Key Terms•10 minutes
Lab•10 minutes
Reflection•10 minutes
Key Terms•10 minutes
Lab•10 minutes
Reflection•10 minutes
Publishing
Module 3•2 hours to complete
Module details
Share fine-tuned models with the community. Publish to Hugging Face Hub with proper documentation, and automate the training-to-deployment pipeline with GitHub Actions.
What's included
11 videos10 readings
Show info about module content
11 videos•Total 27 minutes
Introduction•0 minutes
HuggingFace Hub For Models•2 minutes
Authentication and Setup•5 minutes
Publishing to the Hub•4 minutes
Summary•1 minute
Introduction•1 minute
GitHub Actions Fundamentals•4 minutes
Automated Publishing Pipeline•4 minutes
Github Container Registry•3 minutes
Summary•1 minute
Course Conclusion•1 minute
10 readings•Total 100 minutes
Key Terms•10 minutes
Lab•10 minutes
Reflection•10 minutes
Key Terms•10 minutes
Lab•10 minutes
Reflection•10 minutes
Key Terms•10 minutes
Lab•10 minutes
Reflection•10 minutes
Next Steps•10 minutes
Capstone and Critical Assessment
Module 4•1 hour to complete
Module details
Build an end-to-end sentiment analysis system that fine-tunes a transformer model on custom data and deploys it to Hugging Face Hub. This capstone demonstrates mastery of the complete fine-tuning workflow.
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.