Open decision models and reproductions with decision models

Dependency-free Python wrapper that turns any LLM API into a Jev-style choose-one-option decision call for old machines.

Small one-pass classifier that labels shell commands as read-only, reversible or destructive before an agent runs them.

Serves MiniCPM5-2B-8bit on Apple Silicon as a Jev-compatible /v1/systemone service and reproduces its JevBench score.

Jev-style skill router for OmO: frozen Qwen2.5-0.5B plus a small head scores the skill catalog and trims the system prompt to top-K.

Gemma 3 4B option scorer that prefills context once and scores all options in one pass, on MLX or PyTorch, with a Doom demo.

Training-free runtime turning local Qwen3/Qwen3.5 checkpoints into a Jev-style Noul/Choice/Score service via candidate-token logits.

Gateway that distils System One or LLM answers into small fine-tuned classifiers and serves them when confident, falling back otherwise.

Formerly OpenJev: open-model 'semantic ifs' that read option logits from a frozen 4B model on one RTX 3090, with a browser demo.

CLM-8B, a contrastively trained System One model that embeds states and actions separately, served behind a TypeSafe-compatible API.

0.6B open Jev replica returning full option distributions with no decoding; one checkpoint plays ViZDoom, Maze and Snake.

Nokia's training-free library that turns open LLMs into Jev-style deciders robust to option order, plus self-distilled Tacit models.

Apache-2.0 multimodal System One models (0.8B, 2B, 4B) that take text, images or video and return probabilities over supplied candidates.

Archived early Jev-compatible API server running Qwen3.6-35B-A3B prefill-only on SGLang via Modal; superseded by SGLang's native endpoint.

Educational MLX project scoring typed questions about one image with Qwen3.5-0.8B on Apple Silicon, with game demos.

Browser MuJoCo Franka Panda workbench comparing Jev, Claude, OpenAI-compatible and local models on pick, stack and obstacle tasks.

Small open decision model on a frozen Qwen3.5-4B serving /v1/systemone in about 200 ms, benchmarked against Jev on JevBench.

Preregistered study: reading a frozen Qwen3-4B's option-letter logits matches grammar-constrained JSON accuracy, and runs faster.

Small multimodal System One models that choose, judge or score text, documents and images in one forward pass.

NIRNAY 450M: open Apache-2.0 decision model fine-tuned from Laya that reports 87.9% on Banking77 with fitted ECE 0.045.

Open-weight 0.6B decision model on a Qwen3 backbone: state and typed questions in, a probability for every option out, nothing decoded.

Open 27B multimodal decision model built largely by autonomous agents, serving choice, noul and score on a TypeSafe-compatible API.

Experimental 17M-400M English decision models for choice, yes/no, score and reranking, with weights, training code and an ONNX browser demo.

Bespoke Labs' open recipe, data and 9B LoRA model for Jev-style choice and true/false decisions, runnable on Apple Silicon or NVIDIA GPUs.

Open Apache-2.0 Jev-like model family on Qwen3.8-27B that reads one-token candidate preferences and serves a TypeSafe-compatible API.

Open 2B non-autoregressive decision model on Qwen3.5-2B for agent tool routing and DOM actions, with BF16, FP8 and INT8 weights.

706K-parameter Jev-style option scorer that rates fill, check, click or skip for each form element in one parallel pass.

Recipe that answers JevBench typed decisions with frozen Gemma-4-12B-it on stock vLLM by reading one option-letter token's probability.

Experiment showing a RLCD-trained LoRA decision head on Qwen3.5-4B generalises only where training data covers the task structure.

399M ModernBERT-large decision model with one universal choice head answering Choice, Noul and Score in a single forward pass.

InternLM's open multimodal decision models (0.8B-4B) trained on Qwen3.5, with calibration tooling and a 96-case calibration benchmark.