I'm a graduate of the B.Sc. in Electrical Engineering (minor in Computer Engineering) at Amirkabir University of Technology (Tehran Polytechnic).
I'm currently deepening my understanding of deep learning and LLMs by building a GPT-2-style decoder-only Transformer from scratch in JAX / Flax NNX β implementing self-attention, autoregressive generation, training, and evaluation, and comparing it against pretrained GPT-2.
### π« ContactThanks for stopping by! Feel free to explore my repos or reach out.