Engine 02: The Transformer

Transformer decoder built from scratch following Sebastien Raschka's Build a Large Language Model From Scratch. Covers the full architecture from tokenization to autoregressive generation.

Architecture(Right one-> decoder)

🎯 Objective

Build a standalone Transformer engine to master the architecture.

🛠️ Implementation Progress

Data - setup done ✅, got a short story from Wikipedia ("The Journey" by Edith Wharton)

Attention.py - done, full multi-head attention mechanism.

Transformer.ipynb - contains full decoder.