Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization
Paper
•
2411.10442
•
Published
•
68
InternVL2.5-MPO
Enhancing the Reasoning Ability of MLLMs via Mixed Preference Optimization
-
-
OpenGVLab/InternVL2-8B-MPO
Image-Text-to-Text • Updated • 3.23k • 31 -
OpenGVLab/MMPR
Preview • Updated • 220 • 41 -
OpenGVLab/InternVL2_5-1B-MPO
Image-Text-to-Text • Updated • 1.47k • 14 -
OpenGVLab/InternVL2_5-2B-MPO
Image-Text-to-Text • Updated • 165 • 11 -
OpenGVLab/InternVL2_5-4B-MPO
Image-Text-to-Text • Updated • 139 • 11 -
OpenGVLab/InternVL2_5-4B-MPO-AWQ
Image-Text-to-Text • Updated • 28 • 3 -
OpenGVLab/InternVL2_5-8B-MPO
Image-Text-to-Text • Updated • 417 • 14 -
OpenGVLab/InternVL2_5-8B-MPO-AWQ
Image-Text-to-Text • Updated • 44 • 4 -
OpenGVLab/InternVL2_5-26B-MPO
Image-Text-to-Text • Updated • 174 • 9 -
OpenGVLab/InternVL2_5-26B-MPO-AWQ
Image-Text-to-Text • Updated • 63 • 2 -
OpenGVLab/InternVL2_5-38B-MPO
Image-Text-to-Text • Updated • 82 • 13 -
OpenGVLab/InternVL2_5-38B-MPO-AWQ
Image-Text-to-Text • Updated • 45 • 2 -
OpenGVLab/InternVL2_5-78B-MPO
Image-Text-to-Text • Updated • 122 • 21 -
OpenGVLab/MMPR-v1.1
Preview • Updated • 93 • 17 -
OpenGVLab/InternVL2_5-78B-MPO-AWQ
Image-Text-to-Text • Updated • 26 • 5