jevland

replica source-backed

PlayJev: a 0.8B visual decision model for ten games

An independent Jev-like model fine-tuned from Qwen3.5-0.8B-Base to choose legal actions from raw game frames. The project publishes model weights, training records and a gallery of ten browser games.

Recorded Snake game with move probabilities and replay controls in the PlayJev gallery.
PlayJev Snake replay by OmniJev, from a recorded episode. Demo screenshot ↗ ·

Open demo ↗

The author reports one forward pass per action, 43 ms per move on an H200, and training on 2.2 million frames; the model does not generate an action as text.

source-backed — Public repository, docs or live artifact. About this label

How to run

Stack
HTML / JavaScript demo; Python model
Requirements
A modern browser for recorded playback
Keys / accounts
No account or API key for the public recorded demo.

Open the published demo and select a game tile to inspect a recorded model episode. Local model serving is a separate Python/CUDA setup documented in the README. Playback does not run live inference.

Open this scenario ↗

README review · · Documentation reviewed; project installation and live API not run.

Next: follow the practical guide → · compare projects for this task →

HTTP availability
Link reachable ·
Method: bounded HTTP request with redirects. HTTP 200 · HTTP response only. Checked destination ↗ · Last reachable
Browser demo scenario
passed ·
Method: browser-automation. Scenario: Load the recorded Snake episode, pause playback, restart it and observe advancing steps and move probabilities. — Saved episode playback; live model inference was not tested.
Build
Not checked
Live API test
Not checked

What these checks cover →

Report a problem →

← Back to the directory