# Models

Paper replications and ML implementations, focused on architecture-first understanding of foundational deep learning research.

- [Attention Is All You Need](/models/attention-is-all-you-need) — A PyTorch implementation of the original encoder-decoder Transformer architecture for neural machine translation, including multi-head attention, sinusoidal positional encoding, greedy decoding, OPUS Books training, and CER/WER/BLEU evaluation. (PyTorch, Python)
- [Paper Replication Lab](/models/paper-replication-lab) — A paper-to-code collection of foundational ML implementations in PyTorch, covering autoencoders, LeNet, AlexNet, LSTM, and a LLaMA-style language model with training and inference utilities. (PyTorch, Python)