content-classification
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.
A new package that processes user-submitted text descriptions of gift-wrapped parcels and returns a structured analysis of the contents, wrapping quality, and potential surprises. It uses pattern matc
