Running
401
⚡
InternVL2.5
Better than InternVL 2.0
-
-
Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling
Paper • 2412.05271 • Published • 129 -
OpenGVLab/InternVL2_5-78B
Image-Text-to-Text • Updated • 30.3k • 166 -
OpenGVLab/InternVL2_5-78B-AWQ
Image-Text-to-Text • Updated • 2.37k • 16 -
OpenGVLab/InternVL2_5-38B
Image-Text-to-Text • Updated • 8.48k • 40 -
OpenGVLab/InternVL2_5-38B-AWQ
Image-Text-to-Text • Updated • 510 • 10 -
OpenGVLab/InternVL2_5-26B
Image-Text-to-Text • Updated • 5.11k • 33 -
OpenGVLab/InternVL2_5-26B-AWQ
Image-Text-to-Text • Updated • 1.02k • 11 -
OpenGVLab/InternVL2_5-8B
Image-Text-to-Text • Updated • 35.4k • 73 -
OpenGVLab/InternVL2_5-8B-AWQ
Image-Text-to-Text • Updated • 920 • 8 -
OpenGVLab/InternVL2_5-4B
Image-Text-to-Text • Updated • 12.7k • 41 -
OpenGVLab/InternVL2_5-4B-AWQ
Image-Text-to-Text • Updated • 487 • 9 -
OpenGVLab/InternVL2_5-2B
Image-Text-to-Text • Updated • 10.2k • 27 -
OpenGVLab/InternVL2_5-1B
Image-Text-to-Text • Updated • 19k • 42 -
OpenGVLab/InternViT-300M-448px-V2_5
Image Feature Extraction • Updated • 4.29k • 25 -
OpenGVLab/InternViT-6B-448px-V2_5
Image Feature Extraction • Updated • 693 • 26