eulogik / pico-type Star 2 Code Issues Pull requests 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. multilingual classifier open-source clipboard machine-learning language-detection pytorch byte-level onnx edge-ai multi-head code-detection content-classification onnx-runtime tiny-model Updated Jun 29, 2026 Makefile