open-jev
an open-source, from-first-principles reconstruction of the ideas behind TypeSafe AI's Jev, written in pytorch
Getting started
The model is untrained, so the values from this example are random. The useful guarantee is structural: a Choice answer can only be one of the options that were declared.
Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README · the project website.