JevK5: open-weight alternative to TypeSafe Jev. Typed decisions with probabilities in one forward pass; Apache-2.0 weights and code.
-
Updated
Sep 24, 2026 - Python
#
jevbench
Here are 4 public repositories matching this topic...
A decision model: give it a document and a typed question, get calibrated probabilities for every allowed answer. No text generation. Qwen3.5-4B + LoRA, /v1/systemone wire format.
-
Updated
Sep 23, 2026 - Python
Open-source Jev harness for TypeSafe, OpenJev, LocalJev, Ollama, vLLM, LM Studio, llama.cpp. Typed decisions, calibration, verification, abstention, CI gates.
evaluation typesafe harness codex mlx ai-agents bun structured-output apple-silicon llama-cpp vllm local-llm ollama lm-studio claude-code diffusiongemma jev openjev jevbench localjev
-
Updated
Sep 22, 2026 - Python
Local frozen-backbone decision readout: evidence + criterion + options in, a probability per option out, in one forward pass. JevBench public set 0.805 / hard 0.604 with Qwen3.5-4B, no training.
-
Updated
Sep 24, 2026 - Python
Add this topic to your repo
To associate your repository with the jevbench topic, visit your repo's landing page and select "manage topics."