Fine-tuned models

GNO ships gno-expansion-slim-retrieval-v1 as the expand role in slim-tuned (nDCG@10 0.925, Ask Recall@5 0.875). It does not train on your corpus.

GNO publishes gno-expansion-slim-retrieval-v1, a fine-tuned model that expands search queries before retrieval.

What this is

The expansion model rewrites or augments difficult queries before retrieval. It is the local expand GGUF in slim-tuned. Embeddings and standalone answers use other roles.

The numbers

• nDCG@10 0.925 on the canonical benchmark corpus
• Ask Recall@5 0.875 on the ask-style answer benchmark
• Shipped via Hugging Face, pulled on first run

Install it

gno models use slim-tuned
gno models pull --expand

Your documents are not used for training

You select or download the shipped model. GNO never trains on your indexed documents.

Benchmarks

To measure retrieval quality on your own documents, run gno bench against a fixture file of queries and expected results. See the benchmarks feature page for the fixture workflow and result metrics.

gno bench docs/examples/bench-fixture.json
gno bench fixture.json --json