What does this Space actually run?

A static React front-end for ra_jev_v3; the model inference does not run here but on the separate ZeroGPU backend Space ra_jev_api.

What model powers the demo?

ra_jev_v3, described in the README as Qwen3.5-4B with a LoRA adapter, with inference served by the ra_jev_api backend.

Can I try the UI without a backend?

Yes. The ?mock=1 URL option runs the front-end with no backend and returns fake scores, intended for UI testing rather than model evaluation.

Can I point the demo at another backend?

Yes. The ?api= URL option lets you target a different backend instead of the default ra_jev_api Space.

What files is the Space built from?

A README, app.js, index.html, and style.css plus git attributes; there is no server code or model weight stored in this repository.

Where is the model card?

The README does not link one; it only names ra_jev_v3 and the ra_jev_api backend, so model details would have to come from those repositories.

What limitations does the card mention?

None explicitly. With a four-line card, there is no licence, benchmark, or input-limit information published here, so the demo is best treated as a UI preview.

CommunityJev Demos & Experiments

RA Jev Demo

A static React front-end for ra_jev_v3, described as Qwen3.5-4B plus LoRA, whose inference runs on the same organisation's ra_jev_api ZeroGPU backend Space, with mock and custom-backend URL options.

See highlights

Open huggingface.co

Format: Playground
Published by: Community
Author: Omartificial-Intelligence-Space
Last verified: Oct 2026

Tagscommunity playground demo frontend

Works forJev for Classification

Used inJev for Software & DevTools

Platforms: Browser
Capabilities: Open sourceRuns locally

Highlights

Serves as the front-end for ra_jev_v3, described in the README as Qwen3.5-4B plus a LoRA adapter.
Inference runs on the separate ra_jev_api Space, a ZeroGPU backend in the same organisation.
Supports ?mock=1 to run with no backend and fake scores for UI testing.
Supports ?api=<backend url> to point the front-end at a different backend.
The repository holds only README, app.js, index.html, and style.css beyond git attributes.

Watch out

The card is four lines long and documents no licence, model measurements, or limits; it defers inference to the ra_jev_api Space and mentions no fallback when that backend is unavailable. Treat the ?mock=1 scores as UI scaffolding rather than model output.

Questions about this entry

Short answers drawn from the linked project or page.

Related terms

Glossary definitions related to this entry.

Playground

More Jev resources like this

JEV-9B Decision Demo

An interactive ZeroGPU demo of AutoTrust's JEV-9B: System 1 answers noul, choice, and score questions in one prefill pass with calibrated probabilities, while an Escalate tab hands low-confidence cases to the untouched Qwen3.5-9B base.