Instructions to use nvidia/mit-b5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nvidia/mit-b5 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="nvidia/mit-b5") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# pip install -U transformers accelerate # Load model directly from transformers import AutoImageProcessor, AutoModelForImageClassification processor = AutoImageProcessor.from_pretrained("nvidia/mit-b5") model = AutoModelForImageClassification.from_pretrained("nvidia/mit-b5", device_map="auto") - Inference
- Notebooks
- Google Colab
- Kaggle
Download pytorch_model.bin from nvidia/mit-b5: direct link, hf CLI and curl.
- Browser
- Download file 328 MB
-
https://huggingface.co/nvidia/mit-b5/resolve/main/pytorch_model.bin
- Command line
-
hf download hf://nvidia/mit-b5/pytorch_model.bin
-
curl -L -o pytorch_model.bin https://huggingface.co/nvidia/mit-b5/resolve/main/pytorch_model.bin
328 MB
- Xet hash:
- 646fb4308c0adebd398e35c9ae2398b093d1ed22828395b88284a7c8fcdfd25a
- Size of remote file:
- 328 MB
- SHA256:
- a389c0a604458fa205446fd08a2c01b74e6591a5da3e77de668c6ca5cbf75356
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.