AI EngineeringAvailable
LLM Fine-Tuning Fundamentals
About this course
Fine-tuning adapts a foundation model to your domain without training from scratch. This course covers LoRA and QLoRA mechanics, dataset preparation, training on constrained hardware, evaluation, the Hugging Face PEFT ecosystem, and cost analysis.
What you will learn
- When fine-tuning is the right choice vs prompting or RAG
- LoRA and QLoRA: rank, alpha, and target modules
- Dataset preparation and instruction formatting
- Training on constrained hardware with 4-bit quantisation
- Evaluation: perplexity, human eval, domain benchmarks
- Hugging Face PEFT and TRL libraries
- Deploying fine-tuned models with vLLM and TGI
- Cost analysis: fine-tuning vs API calls over time
Your instructor
Ayodele Ajayi
Principal Engineer
Principal Engineer based in Kent, UK, with extensive experience across cloud-native security, platform engineering, and distributed systems. Ayodele has led engineering teams at scale and writes about what he learns — with a bias towards things that actually work in production.