fastvit_mci2.apple_mclip2_dfndr2b

Model card for fastvit_mci2.apple_mclip2_dfndr2b

A MobileCLIP v2 (image encoder only) for timm. Equivalent to image tower from https://huggingface.co/timm/MobileCLIP2-S2-OpenCLIP.

Model Details

• Dataset: DFNDR-2B
• Papers:
  • MobileCLIP2: Improving Multi-Modal Reinforced Training: https://arxiv.org/abs/2508.20691

Citation

@article{faghri2025mobileclip2,
          title={MobileCLIP2: Improving Multi-Modal Reinforced Training},
          author={Faghri, Fartash and Vasu, Pavan Kumar Anasosalu and Koc, Cem and Shankar, Vaishaal and Toshev, Alexander and Tuzel, Oncel and Pouransari, Hadi},
          journal={arXiv preprint arXiv:2508.20691},
          year={2025}
        }