Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
sankim2
/
cosmos
like
1
Image-Text-to-Text
Transformers
vision
vision-language-model
contrastive learning
self-supervised learning
arxiv:
2412.01814
License:
mit
Model card
Files
Files and versions
Community
1
Train
Deploy
Use this model
43c6805
cosmos
Commit History
Upload cosmos_vitb32_yfcc15m.pt
43c6805
verified
sankim2
commited on
about 1 month ago
Upload cosmos_vitb32_pixelprose.pt
d90da68
verified
sankim2
commited on
about 1 month ago
Upload cosmos_vitb32_merged30m.pt
8245fd1
verified
sankim2
commited on
about 1 month ago
Upload cosmos_vitb32_cc12m.pt
45e404c
verified
sankim2
commited on
about 1 month ago
Upload cosmos_vitb32_cc3m.pt
e9bca64
verified
sankim2
commited on
about 1 month ago
Upload cosmos_vitb16_yfcc15m.pt
e23a098
verified
sankim2
commited on
about 1 month ago
Upload cosmos_vitb16_pixelprose.pt
523c0ce
verified
sankim2
commited on
about 1 month ago
Upload cosmos_vitb16_merged30m.pt
d62a2e8
verified
sankim2
commited on
Mar 20
Upload cosmos_vitb16_cc12m.pt
1a1e5c5
verified
sankim2
commited on
Mar 20
Upload cosmos_vitb16_cc3m.pt
cc95a11
verified
sankim2
commited on
Mar 20
initial commit
ed62671
verified
sankim2
commited on
Mar 20