LLM2Jev
Adapt local language models into Jev-compatible structured decision engines with Choice, Score, and Noul outputs powered by prefill-only binary inference.
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.
How it uses Jev
Turn your LLM / MLLM into a Jev-style decision model. Zero training required.
Highlights
- No training or fine-tuning: use existing model weights to make Jev-style decisions with models supported by SGLang, Transformers, or MLX on Apple Silicon.
- Chat and decisions share a service and model: with the SGLang backend, chat and /v1/systemone use the same inference engine and loaded model.
- Chat and decisions share a client: Client and AsyncClient extend the OpenAI Python SDK with systemone.create() , preserving its existing interfaces, authentication, timeouts, and…
- Prefill-only scoring: Choice , Score , and Noul read yes/no logits without generating answers. Box generates normalized image coordinates.
- Text and image decisions: combine text and images in state or instructions for classification, evaluation, and action selection.
- Four question types in one request: mix Choice , Score , Noul , and Box to get option probabilities, rubric scores, yes/no probabilities, and image bounding boxes as typed Python…
Getting started
On Linux with a supported NVIDIA GPU, start one SGLang service for chat and decisions:
Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README.