Skip to content
ModelListedExternal
Browse files

Fastvit Mci4.apple Mclip2 Dfndr2b

A MobileCLIP v2 (image encoder only) for timm. Equivalent to image tower from

Sourcehuggingface.co/timm/fastvit_mci4.apple_mclip2_dfndr2b/tree/793b34b8b7ed7c0d528c1089a9a4463aa86751b5
KindOtherVersionRevision 793b34bCgrade

Model source

Kind
Other
File size
1.20 GB
Version
vRevision 793b34b
Updated
Sep 16, 2026
Downloads
89
Source
Hugging Face

Source description

Model card for fastvit_mci4.apple_mclip2_dfndr2b

A MobileCLIP v2 (image encoder only) for timm. Equivalent to image tower from https://huggingface.co/timm/MobileCLIP2-S4-OpenCLIP.

Model Details

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}
        }

Sources

1 source
Hugging FacePrimaryVersion 793b34b8b7ed7c0d528c1089a9a4463aa86751b5
huggingface.co/timm/fastvit_mci4.apple_mclip2_dfndr2b/tree/793b34b8b7ed7c0d528c1089a9a4463aa86751b5

Verified Sep 2

Download files

Model artifacts

2 artifacts

model.safetensors

safetensors · 1.20 GB · SHA-256 307b0a98832f…cb64 · Hugging Face

Download file

pytorch_model.bin

bin · 1.20 GB · SHA-256 2aeda4fbc95a…ea39 · Hugging Face

Download file

Source excerpts

2 excerpts
ReadmeSep 2huggingface.co/timm/fastvit_mci4.apple_mclip2_dfndr2b

--- tags: - timm - transformers - image-feature-extraction - mobileclip - mobileclip2 library_name: timm license: apple-amlr datasets: - dfndr-2b --- # Model card for fastvit_mci4.apple_mclip2_dfndr2b A MobileCLIP v2 (image encoder only) for `timm`. Equivalent to image tower from https://huggingface.co/timm/MobileCLIP2-S4-OpenCLIP. ## Model Details - **Dataset:** DFNDR-2B - **Papers:** - MobileCLIP2: Improving Multi-Modal Reinforced Training: https://arxiv.org/abs/2508.20691 ## Citation ```bibtex @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} } ```

NoteSep 2huggingface.co/timm/fastvit_mci4.apple_mclip2_dfndr2b

Source context: 89 downloads · 0 likes · Pipeline image-feature-extraction · Library timm · Repo timm/fastvit_mci4.apple_mclip2_dfndr2b