Skip to page content
SAVRN
Search Plan a project

Open-weight model

fovi-dinov3-splus_a-2.78_res-64_in1k

by Li bigbunny123/fovi-dinov3-splus_a-2.78_res-64_in1k

fovi-dinov3-splus_a-2.78_res-64_in1k is an open-weight model from Li, released under Apache License 2.0. Its published files total 131.5 MB.

This is a pretrained foveated vision model from the fovi library. - Cortical Magnification Function Hyperparameter (a): 2.78 Apache 2.0

Parameters—
Context—
Weights131.5 MB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads—

Model Card

By Li, published under apache-2.0, revision 613656317ac9.

This is a pretrained foveated vision model from the fovi library. - Cortical Magnification Function Hyperparameter (a): 2.78 Apache 2.0

Read Li's full model card

This is a pretrained foveated vision model from the fovi library.

Model Description

  • Architecture: DINOv3 ViT backbone adapted for foveated inputs
  • Variant: ViT-S/16+ (small)
  • Base Model: facebook/dinov3-vits16plus-pretrain-lvd1689m
  • Dataset: ImageNet-1k
  • Cortical Magnification Function Hyperparameter (a): 2.78
  • Sensor Resolution: 64

Usage

from fovi import get_model_from_base_fn

# Model will be automatically downloaded from HuggingFace Hub
model = get_model_from_base_fn('fovi-dinov3-splus_a-2.78_res-64_in1k')

Or using the Trainer class:

from fovi import get_trainer_from_base_fn

trainer = get_trainer_from_base_fn('fovi-dinov3-splus_a-2.78_res-64_in1k')

Installation

pip install git+https://github.com/nblauch/fovi.git

Citation

@article{blauch2026fovi,
  title={FOVI: A biologically-inspired foveated interface for deep vision models},
  author={Blauch, Nicholas M. and Alvarez, George A. and Konkle, Talia},
  journal={arXiv},
  year={2026}
}

License

Apache 2.0

Identity and Version

Repository
bigbunny123/fovi-dinov3-splus_a-2.78_res-64_in1k
Publisher
Li
Task
Not stated by the source
Modality
Other
Library
fovi
Parameters
Not stated by the source
Languages
Not stated by the source
Revision
613656317ac9bae883d213e14ebbf9bde51fcbda
First published
2026-09-20
Last updated
2026-09-20

Files and Weights

5 files, 131.5 MB in total. The weights are 1 file totalling 131.5 MB in pth.

Weights1 file · 131.5 MB
Configuration2 files · 32.1 KB
Documentation1 file · 1.3 KB
Repository1 file · 1.5 KB
Every file
FileTypeSizeSHA-256
state_dict-00000-of-00001.pthWeights131.5 MB 712abe881e2a
config.yamlConfiguration3.0 KB —
state_dict.index.jsonConfiguration29.2 KB —
README.mdDocumentation1.3 KB —
.gitattributesRepository1.5 KB —

License and Download

License
apache-2.0
Access
Open weights, no gate
Download size
131.5 MB
Download from Li

Released by Li through its official repository on Hugging Face. Read the license.

Memory Requirements

PrecisionWeights in memory
As published131.5 MB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Questions About fovi-dinov3-splus_a-2.78_res-64_in1k

Can I use fovi-dinov3-splus_a-2.78_res-64_in1k commercially?

Yes. fovi-dinov3-splus_a-2.78_res-64_in1k is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.