Artificial Intelligence (AI) · Advanced level

Advanced level · Module 3 of 6 · 22 guided hours

Open Models and Customisation

Run open models locally and choose between prompting, retrieval and fine-tuning to adapt AI to an organisation's needs and languages.

Learning objectives

  • Run and evaluate open-weight models locally
  • Choose between prompting, retrieval and fine-tuning
  • Understand parameter-efficient fine-tuning and data requirements

Topics

  • open-weight models and licences
  • running models locally
  • quantised models on modest hardware
  • prompting vs RAG vs fine-tuning
  • parameter-efficient fine-tuning
  • local language data

Lessons

  1. Lesson 1 Running Open Models Locally

    Download and run open-weight language models on local hardware.

    open-weight modelslicences and acceptable usequantised model fileslocal inference

  2. Lesson 2 Prompting, Retrieval or Fine-Tuning?

    Choose the cheapest effective way to adapt a model to a task.

    promptingretrieval for knowledgefine-tuning for behaviourcost and maintenance

  3. Lesson 3 Parameter-Efficient Fine-Tuning

    Understand how adapters such as LoRA fine-tune large models cheaply, and what data they need.

    full vs parameter-efficient fine-tuningLoRA adapterstraining examplesevaluation before and after

  4. Lesson 4 AI for Local Languages

    Assess AI support for local languages and plan responsible improvement.

    language coverageevaluation in local languagescommunity dataconsent and ownership

Practical activity

Run a small open model locally, compare it with a hosted model on the capstone evaluation set and write a recommendation on customisation.

Expected outcomes

  • Practical experience with open models
  • Sound customisation decisions

Assessment

Comparison report and a customisation recommendation marked on evidence and reasoning.

Taught live by an instructor — online or in person. Free course lessons are for self-study and do not lead to a certificate — see registration options.