Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
microsoft
/
VITRA-VLA-3B
like
13
Follow
Microsoft
17.5k
Robotics
Transformers
English
Robotics
Vision-Language-Action
Manipulation
Multimodal
Pretraining
Diffusion
arxiv:
2510.21571
License:
mit
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
VITRA-VLA-3B
15.1 GB
1 contributor
History:
3 commits
arnoldland
update the tag
4bd47d5
19 days ago
.gitattributes
1.52 kB
initial commit
20 days ago
README.md
2.56 kB
update the tag
19 days ago
config.json
2.08 kB
Initial commit
20 days ago
dataset_statistics.json
12.4 kB
Initial commit
20 days ago
vitra-vla-3b.pt
15.1 GB
xet
Initial commit
20 days ago