Downloads · 30 days
0
vq-pocket
ARotting/vq-pocket
vq-pocket is a machine learning model from ARotting. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
VQ-Pocket is a discrete-latent generative model for handwritten digits. A compact VQ-VAE compresses each 8x8 image into sixteen tokens from a 32-entry visual codebook. A class-conditional GRU then models those tokens…
Access
Public
Updated Jul 30, 2026
Repo size
172 KB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors172 KB · 81%
At a glance
- Access
- Public
- Created
- Jul 30, 2026
- Updated
- Jul 30, 2026
- SHA
- 9dd581e6
Model card
From the Hugging Face model README
VQ-Pocket
VQ-Pocket is a discrete-latent generative model for handwritten digits. A compact VQ-VAE compresses each 8x8 image into sixteen tokens from a 32-entry visual codebook. A class-conditional GRU then models those tokens autoregressively.
The codebook is initialized from warm-started encoder activations with k-means before joint vector-quantized training. This avoids presenting a collapsed codebook as a successful discrete representation. The report includes active-code count, codebook perplexity, reconstruction fidelity, generation fidelity, and unique token-sequence rate.
Verified local result
The 14,193-parameter VQ-VAE used every one of its 32 codes and reached an effective codebook perplexity of 22.72. Its held-out reconstruction MSE was 0.00673 with 95.93% frozen-judge fidelity. The 28,512-parameter conditional prior generated 1,000 samples at 95.6% class fidelity with 99.6% unique code sequences.
Reproduce
uv run python projects/vq-pocket/train.py
uv run pytest tests/test_vq_pocket.py
The model bundle contains both SafeTensors checkpoints and measured evaluation artifacts. The Space displays decoded samples beside the 4x4 token map that generated them. Local artifacts do not imply that the Hub repositories are live.
- Created
- Jul 30, 2026
- Updated
- Jul 30, 2026