GPT-style language model from scratch
buildingA decoder-only transformer in PyTorch, to understand what the libraries hide.
I'm an AI master's student and part-time ML engineer. I build with classical machine learning, MLOps and large language models, preferably running on hardware I control.
This is where I keep experiments and notes. Building something? Write to me.
A decoder-only transformer in PyTorch, to understand what the libraries hide.
Open-weight models running on my own hardware, sized to fit a 12GB GPU.
Turns an existing CV into a clean LaTeX PDF, and measures where the LLM extraction breaks.
I take on a few projects alongside my studies. One email is enough to start.
$ mail me