SystemOne-ONNX

Independent training toolkit and open weights for System One decision models in the same category as Jev: 17M, 68M, and 400M models answering Choice, Noul, Score, and reranking questions, with Python and ONNX inference and a documented generalization gap to Jev 1.13 on the project's S1MB benchmark.

Open, CPU-sized Jev-style decision model: give it a situation, a question and options, and Decima returns calibrated probabilities in roughly 20-50 ms per decision as int8 ONNX, with no GPU, no API key and nothing leaving the machine.

The Jev architecture rebuilt from Qwen3-0.6B: a calibrated, type-safe decision model on an open backbone. No decoding loop — the state is encoded once, questions are scored in one parallel pass, and answers are a distribution over options declared before the call.

Gemma 3 270M fully fine-tuned as a probabilistic decision model: 0.761 accuracy and 0.1319 KL on the 400-case typed-decisions test set, reading letter-token logits one question per pass.

The fine-tuned Laya checkpoint for four typed-decision workflows: 0.766 accuracy on 2,000 held-out decisions, above Jev 1.13.0's published 0.727 and the teacher self-agreement ceiling it trained past.

A small, fast decision model — a system one model — for agentic workflows from Strands Labs: it picks between options or rates on a scale faster than an LLM and returns a calibrated confidence with every decision.