| --- |
| title: Neural DOOM |
| emoji: 💀 |
| colorFrom: red |
| colorTo: purple |
| sdk: gradio |
| sdk_version: 6.15.2 |
| app_file: app.py |
| pinned: true |
| license: gpl-2.0 |
| tags: |
| - track:wood |
| - achievement:offgrid |
| - achievement:welltuned |
| - achievement:offbrand |
| - achievement:fieldnotes |
| --- |
| Social Media Post and Demo Video: https://www.linkedin.com/posts/dean-byrne-02a28b191_neural-doom-for-hugging-face-hackathon-small-ugcPost-7472216018354982912-rqvG/?utm_source=share&utm_medium=member_desktop&rcm=ACoAAC0RumIBxlIKTkKv5tF-hb2OU7TdZ19kxcQ |
| Weights: https://huggingface.co/Quazim0t0/neural-x86-doom/tree/main/models |
| # Neural DOOM |
|
|
| id Software's 1993 DOOM running on an i386 core whose every datapath unit is a |
| neural network verified bit-exact over its complete input domain. A full frame |
| (5,952,699 instructions) replayed fully neurally was bit-identical to the |
| golden run — framebuffer and all 128 MB of machine state. Weights, binary, WAD |
| and the title-frame snapshot are pulled from a private repo via the HF_TOKEN |
| Space secret. ZeroGPU re-verifies all 13 units exhaustively on demand. |
| |
