Jev System One Model Project

A Python library that turns Jev-style decision models into ordinary function calls: check returns a bool, classify picks one option, label picks every option that applies, and score rates on a scale, with probabilities behind every answer.

A Bangla-focused adaptation of Laya, the non-autoregressive typed-decision model: targeted data preparation, fine-tuning and evaluation for classification, routing and scoring on Bangla, Banglish and code-switched text, with the checkpoint still to come.

Training code for SearchJev, a fast calibrated System-1 model for search agents: given a search state and a decision schema, it returns typed predictions over legal field values in one forward pass of a Qwen3.5 backbone.

A frozen decision server that serves Gemma 4 31B — quantized to FP8 at startup — in TypeSafe's /v1/systemone format, reading the next-token distribution instead of generating tokens. It needs one FP8 NVIDIA GPU with 80 GB and has no authentication.

Python with a smart if: .jev files add the ~ question operator and jev/case blocks that Jev answers with a number or a label, never text. Files are rewritten to plain Python at import time; every ~ is one paid TypeSafe API call.

An open-source, locally executed decision engine in the spirit of Jev (TypeSafe AI): state becomes features, and Noul, Choice and Score heads return typed, calibrated probabilities without generating text. It ships a cheap-to-strong cascade and a full train-calibrate-evaluate-deploy cycle.