NLP with Transformers

How language models actually work

Dr. Bilal Ahmed

Associate Professor · Language & Reasoning

About this course

Tokenisation, attention, positional encodings, pre-training objectives and fine-tuning — taught so that when you read a model card you understand every line. Includes a focus on Urdu and other low-resource languages, where the tricks that work for English often fail.

What you will be able to do

  • Explain self-attention and the transformer block from memory.
  • Choose and adapt tokenisers for multilingual text.
  • Fine-tune encoder and decoder models for classification and generation.

Curriculum

7 lessons · 2h 15m

  1. 01

    Representing text

  2. 02

    Attention and the transformer

    • Self-attention from scratch24 min
    • Lab · Attention weights35 min
    • Module quiz · Transformers8 min
  3. 03

    Fine-tuning

    • Encoders for classification15 min
    • Decoders and generation19 min