Natural Language Processing & Large Language Models

Overview

From classic text processing to fine-tuning and deploying large language models. You build chatbots, search systems and retrieval-augmented generation (RAG) applications over your own documents.

What you will be able to do

• Process and represent text: tokens, embeddings, vectors
• Build classification, extraction and search over text
• Use LLM APIs with structured outputs and tool use
• Build RAG systems with vector databases
• Fine-tune and evaluate open models responsibly

1. Text preprocessing and classic NLP
2. Embeddings and semantic search
3. Transformers and how LLMs are trained
4. Working with LLM APIs: prompting, structure, tools
5. Retrieval-augmented generation
6. Fine-tuning open models (LoRA)
7. Evaluation, safety and guardrails
8. Multilingual NLP: Hausa, Yoruba, Igbo and Pidgin

Tools you will use

Choose your class time

Every class covers the same lessons with the same tutors. Take it on campus, live online with recordings, or mix both week by week at no extra cost.

Weekend classes have fewer hours each week, so they run longer to cover the same course. Public holidays are made up on the following Friday. Next intake starts 3 November 2026. See all class times and intakes.

Fees and payment

Questions about this course

See all questions arrow_forward