Model profile
Starling 7B
2023-11-25release date
1eval lineages
Evidence summary
Published evidence spans 1 evals and 1 of 7 behavior components. Its strongest relative result is HarmBench (dr, #26 of 28); its weakest is HarmBench (dr, #26 of 28).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Hugging Face ↗berkeley-nest/Starling-LM-7B-alpha
- Official model page ↗Configuration-level model document · Reviewed official Hugging Face owner · official repository
- Release source ↗direct research preview identity date
Published eval results
Rank is within that sub-eval. Black marks the observed result; the grey dot marks the value implied by the global rank. Values stay on each source’s native scale.