About me

I’m a Computer Science student at the University of Cambridge.

My interests are in Deep Learning, with a particular focus on Natural Language Processing. In addition, I appreciate the awesome engineering1 behind the highly-performant deep learning systems!

Recently, I have been working with researchers from UCL NLP on BritLLM – a joint effort towards producing freely available Large2 Language Models for UK languages3. In my undergraduate dissertation, I focused on the problem of the poor availability of LLMs for low-resource languages and worked on language model adaptation methods for African languages. Currently, I’m working on Data-Efficient Task Unlearning in LMs, a method for increasing the safety of language models and removing their undesired capabilities.

Please, don’t hesitate to reach out or connect!

Notes

  1. Awesome Engineering! 

  2. As of the time of writing (2024-08-27), 3 billion parameters make the model be considered large

  3. Isn’t this just… English?! Explore our work to see what other languages are spoken in the UK!