HITsz-TMG/JevEmbed

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.

An open System One decision model

Millisecond decisions, any domain: a 0.8B open "System 1" model that picks between your options with calibrated probabilities. One base, swappable LoRA adapters, on your own hardware.

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.

MTEB: State-of-the-art evaluation of embeddings across languages and modalities

Open Jev implementation with custom finetuning

A small, fast decision model, or system one model, for agentic workflows. Pick between options or rate on a scale faster than an LLM, with a calibrated confidence on every decision.

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

A family of System One-style models fine-tuned from Qwen3.5, designed for one-pass typed decisions with calibrated probabilities.