Downloads · 30 days
58
48% of all-time downloads
neural-drive-model
codelion/neural-drive-model
neural-drive-model is a machine learning model from codelion. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for pytorch. The card lists the license as other.
An action-conditioned world model for SuperTuxKart: it predicts the next frame from the last 7 frames plus your controls, with no game engine underneath. Trained in PyTorch on gameplay (actions extracted automatically…
All-time downloads
120
Public
Repo size
1.4 GB
Likes
10
Public
Repo makeup
Click a slice to open those files.
.pt1.1 GB · 78%
At a glance
- Library
- pytorch
- License
- other
- Access
- Public
- Created
- Jul 19, 2026
- Updated
- Jul 20, 2026
- SHA
- 6bfaf08f
Spaces
Model card
From the Hugging Face model README
Neural Drive — SuperTuxKart World Model
An action-conditioned world model for SuperTuxKart: it predicts the next frame from the last 7 frames plus your controls, with no game engine underneath. Trained in PyTorch on gameplay (actions extracted automatically), and shipped in two runtimes from the same weights.
<video controls autoplay loop muted src="https://huggingface.co/codelion/neural-drive-model/resolve/main/preview.mp4"></video>
▶ Live in-browser demo (WebGPU): https://huggingface.co/spaces/codelion/neural-drive
- Resolution 384×192 · Action space 6-dim
[accelerate, brake, left, right, nitro, drift] - Codec ConvVAE (z_ch 8, /8 spatial) · Dynamics LatentDiT (dim 768 / depth 12 / patch 3, 130.8M), rectified flow + per-frame diffusion forcing
- Sampling few-step distilled (k = 2)
Runtimes
| runtime | where | notes |
|---|---|---|
| PyTorch | CUDA / CPU | training + reference (fp32) |
| ONNX / WebGPU | any browser | fp16, runs on the visitor's GPU |
Files
PyTorch checkpoints (fp32)
| file | what |
|---|---|
dit.pt | dynamics, 100k steps (k=8 teacher) |
dit_distilled.pt | few-step distilled student (k=2) |
vae.pt | ConvVAE codec |
decoder_big.pt | larger LPIPS decoder |
config.json | architecture config |
Web / ONNX (fp16 — the in-browser build)
| file | what |
|---|---|
web/genframe_fp16.onnx | single-graph frame generator: prefills the 7-frame context once, then runs the k=2 denoise steps internally (KV-cache in the graph). ~262 MB |
web/vae.onnx | VAE decoder (fp32, to keep decode stable) |
web/seeds.bin | 18 spawn context states, raw float32 [18,7,8,24,48] |
web/meta.json | shapes + config for the web runtime |
Reference
Playing SuperTuxKart in Your Head: Learning Interactive World Models from Mobile Gameplay Videos — https://x.com/latent_node/status/2033769450592485543
- Library
- pytorch
- License
- other
- Created
- Jul 19, 2026
- Updated
- Jul 20, 2026