🔎 Ettin Reranker 68M — Cross-Encoder Reranking (runs on CPU)

Rerank a list of candidate passages by their relevance to a query using cross-encoder/ettin-reranker-68m-v1 — a tiny (68M) but strong cross-encoder. Enter a query and one passage per line; the model scores every (query, passage) pair and returns them sorted from most to least relevant.

⚙️ This demo runs entirely on CPU (no GPU / ZeroGPU). The model is small enough to rerank quickly on CPU.