Jev Training

Open System One decision models (27B, 9B and 4B on Qwen chat bases, in bf16, GGUF and MLX) that answer Choice, Noul and Score questions with a probability for every option from one forward pass. The repo carries the trainer, data builders, evaluation harnesses and a record of every run.

Open recipe for calibrated decision models: an LLM teacher writes training data from a one-sentence task description, a LoRA plus decision head on Qwen3-4B-Base answers Choice, Score and Noul questions with calibrated probabilities, evaluated next to Jev on identical items.

Together AI's open recipe and weights for a Jev-inspired decision model fine-tuned on Qwen3.5-4B, with the full data pipeline, training config, and saved benchmark results.

A TypeSafe blog essay arguing that in ML the order that matters is doing the right task, then data, then compute, then algorithms, using the InstructGPT result as its example.

Train a small model that chooses among a changing list of text options, one probability per option in a single pass. Includes Doom, chess, and Wikispeedia demos.