Views
No views yet
| Component | Details |
|---|---|
| Vision Encoder | VMamba-Base (128-256-512-1024 dims, depths [2,2,15,2]) |
| Text Encoder | Mamba-1.4B (state-spaces/mamba-1.4b-hf) |
| Projection Dim | 768 |
| Training Data | CC12M |
| Image Resolution | 224x224 |
| Loss | Symmetric InfoNCE (learned temperature) |
1from models import load_climp
2from data.utils import transform_image
3
4model = load_climp("mamba1")
5transform = transform_image(224)1@article{climp2026,
2 title={CLIMP: Contrastive Language-Image Mamba Pretraining},
3 author={Shabtay, Nimrod and Zimerman, Itamar and Schwartz, Eli and Giryes, Raja},
4 journal={arXiv preprint arXiv:2601.06891},
5 year={2026}
6}