AI Lecture ReferencesPDFPublished
Large Language Models: Transformers, Attention and Fine-Tuning (PDF)
An introduction to language models, transformer architectures, attention, bias mitigation and fine-tuning.
About this resource
Explains language modelling and transformer architectures, self-attention, positional encoding, encoder-only, decoder-only and encoder-decoder models. Also introduces model bias, mitigation approaches and task-specific fine-tuning. Lecture topic: AI and machine-learning foundations.
AI and machine-learning foundationsfoundationsLLMstransformersattentionfine-tuning