Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
MIL-UT
's Collections
Asagi-VLM
Asagi-VLM
updated
Feb 24
Asagi is a Japanese Vision & Language model, trained on a large-scale synthetic dataset.
Upvote
6
MIL-UT/Asagi-14B
Image-Text-to-Text
•
Updated
Feb 24
•
108
•
9
MIL-UT/Asagi-8B
Image-Text-to-Text
•
Updated
Feb 24
•
54
•
4
MIL-UT/Asagi-4B
Image-Text-to-Text
•
Updated
Feb 24
•
33
•
4
MIL-UT/Asagi-2B
Image-Text-to-Text
•
Updated
Feb 24
•
8
•
4
Upvote
6
+2
Share collection
View history
Collection guide
Browse collections