CommunityJev Demos & Experiments
Julia-1 Decision Demo
A ZeroGPU demo of Julia 1: define a state and any set of choice, score, and noul questions and see per-option probabilities rendered as bars and raw JSON.
- Format
- Playground
- Published by
- Community
- Author
- Supersonic Labs
- Last verified
- Oct 2026
- Platforms
- Browser
- Capabilities
- Open sourceRuns locally
Highlights
- Answers any set of named questions independently in one pass, with probability bars and the raw JSON side by side.
- Pins the runtime call exactly: device='cuda', strict_encoding=True, max_length=8192, head_length=512.
- The julia/ package inside the space is vendored verbatim from the model repo, so the demo doubles as a reference implementation.
- Loads the 577 MB fp32 checkpoint from the Hub at startup and answers warm in well under a second.
Watch out
Runs on shared ZeroGPU quota, and cold starts download the weights — the space allows up to a 30-minute startup for that reason.
Questions about this entry
Short answers drawn from the linked project or page.
No. It runs on ZeroGPU, so a browser session is enough; the 577 MB checkpoint downloads at startup and warm inference is under a second. The exact runtime parameters are pinned in the README rather than exposed in the UI.
Yes — any set of named choice, score, and noul questions is scored independently in a single pass, which is the core of the Julia interface. The space also carries an mcp-server tag and has a legacy hugging-apps alias domain.
Per-option probabilities rendered as bars alongside the raw JSON, for each named question, so you can inspect the whole distribution rather than only the selected option.
It loads the 577 MB fp32 checkpoint from the Hub at startup and answers warm in well under a second. Cold starts download the weights, which is why the space allows up to a 30-minute startup.
Yes. The julia package inside the space is vendored verbatim from the model repository, so the demo doubles as a reference implementation you can copy.
It pins device='cuda', strict_encoding=True, max_length=8192 and head_length=512, matching the model card's runtime call rather than exposing the values in the UI.
Any set of named choice, score and noul questions. They are scored independently in a single pass and returned together with their per-option probabilities.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
LinkedIn: What multimodal decision models actually change, and what they do not.
LinkedInJevDirectory.org
Hacker News: Decision Index 0.2.1 scores open reproductions of Jev on a frozen suite.
jackbravo4 pointsDecision Index 0.2.1 – 70 open reproductions of TypeSafe Jev's Decision ModelRead the thread on Hacker NewsHacker News: Pointer to a DiffusionGemma plus vLLM tutorial for a Jev-shaped classifier.
1 pointHow to build a Jev-style classifier with DiffusionGemma and vLLMRead the thread on Hacker NewsHacker News: A one-token logprob wrapper that also classifies webcam frames.
allanrbo151 pointsA single function Jev-like wrapper for LLMs, including vision modelsRead the thread on Hacker NewsMore Jev resources like this
The official Laya playground: eight tabs that show choice, score, and noul decisions on ticket triage, phishing, guardrails, RAG filtering, moderation, routing, and multilingual text.
Jev Demos & ExperimentsPlayground#community#open-models#playground
Community
1.3kGitHub stars
A local daemon that pulls open decision models and serves them on TypeSafe's /v1/systemone, so a Jev client switches hosts with TYPESAFE_BASE_URL.
Jev Models & Reimplementations#community#rust#open-models
Community
ollaya-dev/ollayaRust
ollaya-dev/ollayaRust306GitHub stars
Local macOS computer-use automation on Apple silicon using on-device laya typed decisions and CUA-S1-FORMS for filling, via the Accessibility API.
Jev Demos & Experiments#community#browser#local
Community
FluidInference/FluidUseSwift
FluidInference/FluidUseSwift221GitHub stars
An agent skill that reproduces Jev-style single-step logits over indexed browser controls using local Qwen weights for offline browser use.
Jev Demos & Experiments#community#browser#open-models
Community
APUS-AI-Lab/fast-browser-usePython
APUS-AI-Lab/fast-browser-usePythonSupersonic Labs' 144.3M-parameter decision model on mmBERT-small: choice, score, and noul answers from supplied options in one pass, 73.15% on 2,000 typed decisions, Apache-2.0.
Jev Models & Reimplementations#community#open-models#local
Community
A browser WebGPU export of Julia 1: the same 551 MB decision checkpoint, a Rust WASM tokenizer, and a JavaScript API that answers typed questions client-side with no server or key.
Jev Models & Reimplementations#community#open-models#local
Community
From the Jev guides
Original write-ups on what this entry is for.
Hundreds of repositories carry the system-one tag, but the ecosystem is a dozen ideas in different sizes. A tour of the families, the licenses, and what a download does not include.
Jev Models & Reimplementations#open-models#hugging-face#local
Read article
Taking a decision checkpoint out of Python: what the GGUF and browser WebGPU exports preserve, what they change, and the parity evidence the model cards publish.
Jev Tools & CLIs#open-models#local#onnx
Read article
Interface, size, license, claims — in that order. A selection guide across the system-one catalog, from a 706K form scorer to 27B Jev students.
Jev Practices & Patterns#open-models#evaluation#benchmarks
Read article
From the Jev community
Posts from builders shipping with Jev right now.