Master Language Models Fine-Tuning with Hugging Face
From beginner to expert in understanding, implementing, and optimizing fine-tuning techniques for large language models.
Course Overview
Learning Goals
Take learners from beginner to expert in fine-tuning large language models
Fast-Track Format
Smol but fast course designed for software developers and engineers
π What You'll Learn
π Study instruction tuning, supervised fine-tuning, and preference alignment in theory and practice.
π§βπ» Learn to use established fine-tuning frameworks and tools like TRL and Transformers.
πΎ Share your projects and explore fine-tuning applications created by the community.
π Participate in challenges where you will evaluate your fine-tuned models against other students.
π Earn a certificate of completion by completing assignments.
π§ Understand how to fine-tune language models effectively and build specialized AI applications using the latest fine-tuning techniques.
π 7-Unit Curriculum
π 7-Unit Curriculum
| Unit | Topic | Description | Release | Key Focus Areas |
|---|---|---|---|---|
| Unit 1 | π Instruction Tuning | SFT, chat templates, instruction following | Released | Supervised fine-tuning (SFT), Chat templates, Instruction following |
| Unit 2 | π Evaluation | Benchmarks and custom domain evaluation | September | Benchmarks, Custom domain evaluation |
| Unit 3 | ποΈ Preference Alignment | e.g., DPO | October | Direct Preference Optimization (DPO), Preference alignment techniques |
| Unit 4 | π Reinforcement Learning | Optimize with reinforcement policies | October | Reinforcement learning policies, Model optimization |
| Unit 5 | ποΈ Vision Language Models | Multimodal adaptation and use | November | Vision language models, Multimodal adaptation |
| Unit 6 | π§ͺ Synthetic Data | Generate datasets for custom domains | November | Generate datasets, Custom domains |
| Unit 7 | π Award Ceremony | Showcase and celebration | December | Project showcase, Course celebration |
What You Need
Prerequisites
Essential knowledge and skills to succeed in the course
Technical Requirements
Hardware and software needed for hands-on practice
Free Certification Paths
Fundamentals Certificate
Quick achievement for core concepts
Certificate of Completion
Full mastery demonstration
Course Philosophy
"Smol but fast - a concentrated learning experience that gets software developers and engineers from beginner to expert in LLM fine-tuning through practical, hands-on assignments and real-world challenges."β Ben Burtenshaw, ML Engineer at Hugging Face
π Course Details
β±Time Commitment
Flexible learning schedule designed for busy professionals
Investment
High-quality education accessible to everyone
π Additional Learning Resources
HF LLM Course
Foundational course for complete beginners
Discord Study Groups
Join collaborative learning community
Course Leaderboard
Track progress and compete with peers
Chris Prakoso
Augmented Humanity | Practical AI, Data & Analytics
Connect with me for hands-on LLM fine-tuning tutorials, Hugging Face ecosystem insights, and practical machine learning implementation strategies