Velamuvi AIAcademy
Generative AI

Fine-Tuning LLMs

Teach a model new behaviour. When to fine-tune, preparing data, LoRA and QLoRA, and evaluating the result.

  • Advanced
  • About 12 hours
  • 4 modules
  • 12 lessons
  • Free

This course is not released yet. We publish courses one at a time, each one complete. The full syllabus is below.

What you will learn

  • DecidingWhat Is Fine-Tuning?, Fine-Tune, RAG or Prompt?, Costs and Risks
  • DataBuilding a Training Dataset, Formatting Chat Data, Data Quality Checks
  • TrainingFull Fine-Tuning vs PEFT, LoRA and QLoRA, Fine-Tuning With Hugging Face and more
  • After TrainingEvaluating a Fine-Tuned Model, Serving Your Model

Course syllabus

Not released yet · full syllabus below

  1. 1

    Deciding

    3 lessons
    1. 1What Is Fine-Tuning?Soon
    2. 2Fine-Tune, RAG or Prompt?Soon
    3. 3Costs and RisksSoon
  2. 2

    Data

    3 lessons
    1. 4Building a Training DatasetSoon
    2. 5Formatting Chat DataSoon
    3. 6Data Quality ChecksSoon
  3. 3

    Training

    4 lessons
    1. 7Full Fine-Tuning vs PEFTSoon
    2. 8LoRA and QLoRASoon
    3. 9Fine-Tuning With Hugging FaceSoon
    4. 10Hosted Fine-Tuning APIsSoon
  4. 4

    After Training

    2 lessons
    1. 11Evaluating a Fine-Tuned ModelSoon
    2. 12Serving Your ModelSoon

Recommended next