Asagi-VLM Asagi is a Japanese Vision & Language model, trained on a large-scale synthetic dataset. MIL-UT/Asagi-14B Image-Text-to-Text • 14B • Updated Feb 24 • 38 • 10 MIL-UT/Asagi-8B Image-Text-to-Text • 8B • Updated Feb 24 • 15 • 4 MIL-UT/Asagi-4B Image-Text-to-Text • 4B • Updated Feb 24 • 3 • 4 MIL-UT/Asagi-2B Image-Text-to-Text • 2B • Updated Feb 24 • 5
Asagi-VLM Asagi is a Japanese Vision & Language model, trained on a large-scale synthetic dataset. MIL-UT/Asagi-14B Image-Text-to-Text • 14B • Updated Feb 24 • 38 • 10 MIL-UT/Asagi-8B Image-Text-to-Text • 8B • Updated Feb 24 • 15 • 4 MIL-UT/Asagi-4B Image-Text-to-Text • 4B • Updated Feb 24 • 3 • 4 MIL-UT/Asagi-2B Image-Text-to-Text • 2B • Updated Feb 24 • 5
