system-one-mini
distilbert-base-uncased fine-tuned to return typed decisions, 69M parameters.
Community card
What this is
system-one-mini is a typed-decision model: given a document and a closed set of options, it returns one of those options with a probability across the whole set rather than free text.
Its card lists training data: DavidHatley/system-one-mini-data. That matters when you read any benchmark number about it, because a model tuned on a benchmark's own training split has an advantage over one that has never seen it.
What we have not measured
Everything. We have not run this model on our frozen test split, so we have no accuracy, no calibration error and no risk and coverage curve for it. The facts on this page come from its own repository metadata, read on 20 September 2026, and are accurate as far as that goes and no further. The one model we have measured end to end is Jev.
Sources
Every fact on this page traces to one of these, checked on the date shown. Download and like counts move; the rest of it should not.
- Hugging Face · DavidHatley/system-one-minichecked 20 September 2026
Page last verified 20 September 2026.
A public number is a shortlist, not a decision
The only benchmark that settles which model you ship is one built from your own historical decisions. We freeze that test set, run the candidates against it, and hand back the threshold your error budget supports.