Instructions to use nvidia/MambaVision-L-1K with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nvidia/MambaVision-L-1K with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="nvidia/MambaVision-L-1K", trust_remote_code=True) pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForImageClassification model = AutoModelForImageClassification.from_pretrained("nvidia/MambaVision-L-1K", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download mambavision_large_1k.pth.tar from nvidia/MambaVision-L-1K: direct link, hf CLI and curl.
- Browser
- Download file 2.74 GB
-
https://huggingface.co/nvidia/MambaVision-L-1K/resolve/main/mambavision_large_1k.pth.tar
- Command line
-
hf download hf://nvidia/MambaVision-L-1K/mambavision_large_1k.pth.tar
-
curl -L -o mambavision_large_1k.pth.tar https://huggingface.co/nvidia/MambaVision-L-1K/resolve/main/mambavision_large_1k.pth.tar
2.74 GB
- Xet hash:
- 937361004875c01d816157769130aece66e7d0d14694f6fd1bd5cb82b18ee8b1
- Size of remote file:
- 2.74 GB
- SHA256:
- e133681f82127f5d878d33c2e245f2240ac73f89dfd8f91999b88fa7e6f832e3
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.