Downloads · 30 days
0
dlab-cmu/sf-grids
sf-grids is a machine learning model from dlab-cmu. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
The 27 Gaussian VQ codebook grids of the SF codec catalog, corrected 2026-08-29 (fp16 CLVQ sweep + header audit). Each file is self-contained: raw centroids and the measured raw fp16 Gaussian distortion in one package.
Downloads · 30 days
0
Access
Public
Updated Sep 5, 2026
Repo size
41.4 MB
Likes
0
Public
Click a slice to open those files.
.sf11.8 MB · 100%
From the Hugging Face model README
The 27 Gaussian VQ codebook grids of the SF codec catalog, corrected 2026-08-29 (fp16 CLVQ sweep + header audit). Each file is self-contained: raw centroids and the measured raw fp16 Gaussian distortion in one package.
Naming: ib<index_bits>_p<p>.sf.
Binary format: [uint32 n][uint32 p][float64 distortion] followed by n*p
float32 centroid values. n = 2^index_bits. Runtime shrinkage correction is
kappa = 1 - distortion / p.
Six high-rate extension rows were added 2026-09-05: ib11_p2 through
ib16_p2 (5.5-8.0 bpw, 2048-65,536 centroids), Gaussian CLVQ-trained in
the 2026-09-04 run. They are staged artifacts pending runtime catalog
integration (catalog menus, schema-3 map regeneration, eval-binary
refresh); no pinned revision binds them yet. They supersede and retire
the former sphere-staging branch.
Model-specific sensitivity maps are published separately as
dlab-cmu/sf-map-<model-name> and collected in SF grids and maps.