InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models
Paper
•
2504.10479
•
Published
•
158
InternVL3
-
-
OpenGVLab/InternVL3-1B
Image-Text-to-Text • Updated • 2.64k • 25 -
OpenGVLab/InternVL3-2B
Image-Text-to-Text • Updated • 1.58k • 11 -
OpenGVLab/InternVL3-8B
Image-Text-to-Text • Updated • 1.78k • 22 -
OpenGVLab/InternVL3-9B
Image-Text-to-Text • Updated • 413 • 14 -
OpenGVLab/InternVL3-14B
Image-Text-to-Text • Updated • 25.4k • 23 -
OpenGVLab/InternVL3-38B
Image-Text-to-Text • Updated • 573 • 14 -
OpenGVLab/InternVL3-78B
Image-Text-to-Text • Updated • 3.34k • 78 -
OpenGVLab/VisualPRM-8B-v1.1
Image-Text-to-Text • Updated • 16 • 3 -
OpenGVLab/VisualPRM400K-v1.1
Preview • Updated • 4 • 2 -
OpenGVLab/VisualPRM400K-v1.1-Raw
Preview • Updated • 1 • 1 -
OpenGVLab/MMPR-v1.2
Updated • 56 • 5 -
OpenGVLab/MMPR-v1.2-prompts
Updated • 49 • 1