Here's how to run Jev-style decision models directly on governed data with Databricks ๐
Serve open-weight models like SemIf-OpenJev on serverless GPUs with AI Runtime + Model Serving, then call them directly from SQL or Lakeflow jobs using ai_query to return structured classifications and probability scores.
โณ Pick your model
โณ Select Serverless GPU
โณ Click Run All
One importable notebook. Swap in your own data and decision criteria from there.