openJev-verdict-2.0
Calibrated 151M Non-Autoregressive Decision Engine beating TypeSafe Jev & Laya on LocalLLaMA/typed-decisions (77.10% acc, 0.0636 Brier, 0.0144 ECE)
- 306
- Python
- 4 wk ago
Calibrated 151M Non-Autoregressive Decision Engine beating TypeSafe Jev & Laya on LocalLLaMA/typed-decisions (77.10% acc, 0.0636 Brier, 0.0144 ECE)
OpenJev: open-source, local alternative to Jev. System-One decision models: typed questions in, calibrated probabilities out; general decisions and browser-agent steps.
🚀🚀 A 0.8B JEV-like multimodal model playing GUI games directly from raw pixels.
Native Swift implementation of OpenJev, the Jev-compatible typed-decision server: yes/no, choice and score answers read from model probabilities, on Apple silicon Macs and in iPhone apps. Serves Verdict, Laya, DiffusionGemma and JevK5. Apache-2.0.
Super fast Jev like server in JS, model agnostic, working with any OpenAI compatible endpoint, support images
OpenJev: an independent Jev-inspired System One decision API based on TypeSafe.ai concepts. Choice, score and noul primitives, local mock server, Python and TypeScript SDKs. Real inference planned; not affiliated with TypeSafe AI.
Local multimodal decisions on your Mac. Jev-compatible typed probabilities with Qwen, llama.cpp and Metal.
Free English RAG benchmark for TypeSafe Jev 1.13 — frozen candidate pools, calibration, paired bootstrap CIs, $0 runs. Compared with OpenJev and NVIDIA cross-encoders.
Local multimodal decisions on your Mac. Jev-compatible typed probabilities with Qwen, llama.cpp and Metal.
MCP server that gives AI agents typed decisions instead of prose: classify, route, score, and flag with calibrated probabilities. npx -y openjev-mcp
Core ML model packages for typed AI decisions with OpenJevSwift on iOS and macOS (iPhone and Mac).
Claude Code plugin: OpenJev (Codiv) makes the small typed decisions: rule-enforcing edit hook, skill picker, file discovery, browser navigation, review pre-check. Shadow mode by default.
Add as much tabular data as you want to Jev models using adaptive ensembles that learn to query only the rows and columns needed.
Selectia - A family of System One-style models fine-tuned from LFM 2.5, designed for one-pass typed decisions with calibrated probabilities. Decision API (Choice, Noul, Score) powered by open LLMs.