Collection by 
Mar 2
-
InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models
Paper • 2504.10479 • Published • 311 -
OpenGVLab/InternVL3-1B
Image-Text-to-Text • 0.9B • Updated • 442k • 85 -
OpenGVLab/InternVL3-2B
Image-Text-to-Text • 2B • Updated • 54.9k • 46 -
OpenGVLab/InternVL3-8B
Image-Text-to-Text • 8B • Updated • 90.1k • 107
