kintsugi-model 0.1.3

Kintsugi Tier-2 model wrapper: a warm CPU scorer that fills summary+risk for the ambiguous band. Heuristic by default; real GGUF inference behind the `llama` feature.
Documentation 
1
2
3
4
5

# kintsugi-model

Tier-2 scorer for [Kintsugi](https://github.com/arrowassassin/kintsugi): heuristic by default, real CPU GGUF inference behind `--features llama`.

This is an internal crate. Install the [`kintsugi`](https://crates.io/crates/kintsugi) crate to get all binaries.