avbiswas/bev-train

Open-weight, Jev-inspired decision model finetuned on top of Qwen3.5 4B

Open Jev implementation with custom finetuning

Open infrastructure for training, evaluating, and deploying System 1 decision models across language and multimodal backbones.

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

Jeeves – Reasoning improves Jev-like decision models

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.

Jeva: System One Models from First Principles

Jev-like family of decision models built on top of Qwen3.5/3.8 you can train and run on your own