All Courses
Open-Source AIIntermediate → SeniorNEW
Hugging Face Transformers
500,000+ pre-trained models, fine-tuning with the Trainer API, parameter-efficient fine-tuning with LoRA/QLoRA, sentence embeddings for RAG, and production deployment with Inference Endpoints.
4.9rating1,240 students4h total1 lessons
What you'll learn
Use pipeline() for 8 task types with zero custom code
Understand tokenization and chat templates for instruction models
Fine-tune models with the Trainer API on custom datasets
Fine-tune 7B+ models on a single GPU using LoRA and QLoRA
Produce sentence embeddings for semantic search and RAG
Deploy models to production with Hugging Face Inference Endpoints
Final Project
Fine-tune a sentiment classifier on your own dataset and deploy it as a production endpoint
Curriculum
1 lessons · 4hCourse Info
Lessons1 lessons
Total time4h
LevelIntermediate → Senior
Students1,240
Rating4.9 / 5.0