Developed and pre-trained a 20.39M-parameter Punjabi GPT-style base model from scratch, including corpus preparation, tokenizer training, benchmark evaluation, and text generation, using a cleaned Punjabi corpus and local Apple Silicon GPU acceleration.

A tiny byte-level multi-head content classifier (~1.5M params, ~200KB ONNX, <6ms). Classifies code, text, markup, config, images, binary, secrets, 62 code languages, 30 text languages, 90 MIME types from raw bytes — no tokenizer needed.

Bio-inspired CNN modeling M/P/K pathways of the Lateral Geniculate Nucleus. From 76KB/15.5K params (33 FPS on Raspberry Pi) to full-scale and temporal variants. Matches ResNet18 with 52x fewer parameters. No pretraining required.