Quantized GGUF build of
Janeodum/tsaro-e2b,
for on-device inference via llama.cpp and llama.rn.
Tsaro is a shared safety system for Northern Nigeria. This model is its
threat extraction component: it takes an unstructured report written in
Hausa, Pidgin, or English and returns a structured threat signal — threat
type, location, perpetrator and vehicle counts, direction of movement,
time references, and a confidence score.
In a React Native app via llama.rn, the model file is bundled or downloaded
on first run and loaded for offline extraction when the device has no
connectivity.
Built for community safety reporting in a specific regional context. Not a
general-purpose model. Outputs are extraction assistance, not verified
intelligence.
