Shreshth V.
Before 365:
Business Analyst | Junglee Games
After 365:
Marketing Chief | TEDxNSUT
See all reviews
Online Course
Finetuning with Llama
with
Jaleed Khan, PhD
Learn to fine-tune, optimize, and deploy Llama models efficiently and responsibly with Hugging Face
1 students already enrolled
Skill level:
Intermediate
Duration:
2 hours
-
Lessons (2 hours)
-
Practice exams (10 minutes)
- Lessons (2 hours)
- Practice exams (10 minutes)
CPE credits:
4
CPE stands for Continuing Professional Education and represents the mandatory credits a wide range of
professionals must earn to maintain their licenses and stay current with regulations and best
practices. One CPE credit typically equals 50 minutes of learning. For more details, visit NASBA's
official website: www.nasbaregistry.org
CPE stands for Continuing Professional Education and represents the mandatory credits a wide range of
professionals must earn to maintain their licenses and stay current with regulations and best
practices. One CPE credit typically equals 50 minutes of learning. For more details, visit NASBA's
official website: www.nasbaregistry.org
Accredited
certificate
What you learn
- How to fine-tune Llama models with Hugging Face
- Efficient finetuning with LoRA, QLoRA, and quantization
- Deploying models as live APIs and applying ethical AI practices
Topics & tools
AILLMLLaMAGenerative AiLLM Fine-TuningLlama-Powered APILLM ApplicationsArtificial IntelligenceData PreprocessingMachine and Deep LearningData EngineeringIndustry SpecializationPython
Your instructor
Senior Research Scientist | Honorary Research Fellow at University of Oxford | Mentor
Track record
Bringing real-world expertise from leading global companies
Academic background
Doctorate (PhD), Artificial Intelligence
Media and recognition
- Invited Speaker, Knowledge Graph Conference (Cornell Tech, US, 2023)
- Lead author on 21 papers in top AI journals & conferences.
- 2,300+ academic citations for research on neurosymbolic and multimodal AI
Course OVERVIEW
Description
CPE Credits: 4
Field of Study: Information Technology
Delivery Method: QAS Self Study
Delivery Method: QAS Self Study
In this hands-on course, you’ll learn how to fine-tune Llama models with Hugging Face from start to finish. Begin by setting up your environment and preparing datasets, then train your first model using the Trainer workflow and evaluate it with ROUGE and BERTScore. Discover efficient methods like LoRA and QLoRA, and apply quantization with BitsAndBytes to run larger models on limited hardware. Finally, deploy your fine-tuned model as a live FastAPI/ngrok-powered API, and explore ethical practices for building safe, fair, and sustainable AI. Build, optimize, and responsibly deploy your own Llama-powered applications!
Prerequisites
- Python programming skills
- Basic understanding of GenAI and LLMs
- Interest in Customizing GenAI and LLMs
Advanced preparation
Curriculum
24 lessons
37 exercises
2 exams
- 2. Getting Started with Finetuning14 min
Learn what finetuning means, explore Llama models, and set up your Hugging Face environment.
14 minLearn what finetuning means, explore Llama models, and set up your Hugging Face environment.
What is Finetuning? FreeLlama Overview FreeSetting up Hugging Face Environment FreeExercise Free - 3. Data Preparation for Finetuning11 min
Choose, clean, split, and tokenize datasets to create high-quality training inputs.
11 minChoose, clean, split, and tokenize datasets to create high-quality training inputs.
Choosing & Loading Datasets FreePreprocessing Datasets FreeDataset Splitting, Saving and Tokenizing FreeExercise Free - 4. Finetuning with Hugging Face15 min
Run your first finetuning task, monitor training, and evaluate results with standard metrics.
15 minRun your first finetuning task, monitor training, and evaluate results with standard metrics.
Hugging Face Finetuning WorkflowYour First Finetuning TaskEvaluating Finetuned ModelsExercise - 5. Parameter-efficient Finetuning with LoRA12 min
Unlock faster, lighter finetuning using LoRA adapters for efficiency without performance loss.
12 minUnlock faster, lighter finetuning using LoRA adapters for efficiency without performance loss.
Understanding LoRAUsing LoRA in Hugging FaceEvaluating LoRA-finetuned ModelsExercise - 6. Efficient Finetuning with Quantization12 min
Apply quantization and QLoRA to train larger models on limited hardware.
12 minApply quantization and QLoRA to train larger models on limited hardware.
Introduction to QuantizationApplying Quantization with BitsAndBytesFinetuning Quantized Models with LoRAExercise - 7. Deploying Finetuned Models12 min
Deploy your Llama as a live API using FastAPI and ngrok, ready for real-world use.
12 minDeploy your Llama as a live API using FastAPI and ngrok, ready for real-world use.
Introduction to Model DeploymentCreating a Llama-powered APITesting Your APIExercise - 8. Ethical Considerations & Best Practices10 min
Understand fairness, bias, privacy, and responsible deployment of LLMs.
10 minUnderstand fairness, bias, privacy, and responsible deployment of LLMs.
Ethical FinetuningResponsible AI DeploymentExercise - 9. Conclusion6 min
Recap your learning and find resources for exploring advanced techniques and continuing your learning journey.
6 minRecap your learning and find resources for exploring advanced techniques and continuing your learning journey.
Course SummaryPractice examFurther Learning - 10. Course exam30 min30 minCourse exam
Free lessons
1.1 Welcome!
8 min
1.2 Course Resources
1 min
2.1 What is Finetuning?
4 min
2.2 Llama Overview
5 min
2.3 Setting up Hugging Face Environment
5 min
3.1 Choosing & Loading Datasets
4 min
94%
of AI and data science graduates
successfully change
or advance their careers.
9 in 10
people walk away career-ready
with practical data and AI skills.
#1 most reviewed
AI and data learning platform on Trustpilot.
ACCREDITED certificates
Craft a resume and LinkedIn profile you’re proud of—featuring certificates recognized by leading global
institutions.
Earn CPE-accredited credentials that showcase your dedication, growth, and essential skills—the qualities
employers value most.
Certificates are included with the Self-study learning plan.
How it WORKS
Student REVIEWS
