decider-2b-toolcall-guard-lora
A LoRA adapter that turns decider-2b into a typed-decision model without shipping full weights.
Community card
What this is
An adapter rather than a full checkpoint. You need Mapika/decider-2b alongside it, and the licence of that base applies to you as well as this repository's own.
Its card lists training data: johannhartmann/toolcall-guard-v1. 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.
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.