Xiaooolong/vev

Turn local language models into Jev-style structured decision models. Get results from text and images with prefill alone—no token-by-token decoding required.

A small open decision model: state + typed questions -> calibrated probabilities. A Jev / System One re-creation on Qwen3.5.

Open Jev-style typed-decision model that also takes images: photo + app state + typed questions in, calibrated probabilities out, locally.

Open, Jev-compatible System One decision server on DiffusionGemma

Typed decisions from a frozen language model and a small physics engine: calibrated probabilities, conformal sets, 73k context, images.

Fast multi-modal decision model

Structured decisions with DiffusionGemma and vLLM. Native image inputs, image choices, live camera sampling, and a compact one-step inference path.

Typed choices and probability distributions from text and images with llama.cpp, Ollama, and OpenRouter

Open decision models from 0.8B to 27B: a calibrated probability for every option in one pass, and a short thought only when unsure. Engine for vLLM, llama.cpp and MLX.