Multimodal models from https://4m.epfl.ch/
EPFL VILAB
AI & ML interests
None defined yet.
Collections
2
spaces
3
models
27
EPFL-VILAB/VPE-ViPer
Image-Text-to-Text
•
Updated
•
24
•
2
EPFL-VILAB/Metric-ViPer
Image-Text-to-Text
•
Updated
•
1
•
2
EPFL-VILAB/4M-21_XL
Any-to-Any
•
Updated
•
147
•
33
EPFL-VILAB/4M-21_L
Any-to-Any
•
Updated
•
72
•
3
EPFL-VILAB/4M-21_B
Any-to-Any
•
Updated
•
623
•
5
EPFL-VILAB/4M-7-SR_L_CC12M
Any-to-Any
•
Updated
•
77
•
2
EPFL-VILAB/4M-7-T2I_XL_CC12M
Any-to-Any
•
Updated
•
9
•
4
EPFL-VILAB/4M-7-T2I_L_CC12M
Any-to-Any
•
Updated
•
12
EPFL-VILAB/4M-7-T2I_B_CC12M
Any-to-Any
•
Updated
•
14
EPFL-VILAB/4M-7_XL_COYO700M
Any-to-Any
•
Updated
•
11
datasets
None public yet