Layered neural network diagram showing low-rank adapter matrices branching off frozen weights.

Building a LoRA Training Loop From Scratch in Pure NumPy

Build a working LoRA fine-tuning loop in pure NumPy, computing every gradient by hand through low-rank adapters. A practical side project that demonstrates real systems understanding to hiring managers.

September 6, 2026 · 12 min · 2463 words · martinuke0
Code editor showing a Python tokenizer implementation with token merges and a vocabulary table.

Build a WordPiece Tokenizer From Scratch: A CV-Worthy NLP Project

Build a production-shaped WordPiece tokenizer in Python with subword merging, BERT special tokens, and a greedy decode path. Includes runnable code, tests, and a roadmap to senior-level extensions.

September 6, 2026 · 12 min · 2489 words · martinuke0
Feedback