This collection includes only the InternVL3.5 checkpoints that have completed the full training pipeline (i.e., Pretraining, SFT, MPO, Cascade RL).
-
InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
Paper • 2508.18265 • Published • 165 -
OpenGVLab/InternVL3_5-241B-A28B-HF
Image-Text-to-Text • 241B • Updated • 9 • 3 -
OpenGVLab/InternVL3_5-38B-HF
Image-Text-to-Text • 38B • Updated • 278 • 1 -
OpenGVLab/InternVL3_5-30B-A3B-HF
Image-Text-to-Text • 31B • Updated • 310 • 2
