Instructions to use Mooshie/swinv2_base_window8_256.dbv4-full with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- timm
How to use Mooshie/swinv2_base_window8_256.dbv4-full with timm:
import timm model = timm.create_model("hf-hub:Mooshie/swinv2_base_window8_256.dbv4-full", pretrained=True) - Transformers
How to use Mooshie/swinv2_base_window8_256.dbv4-full with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="Mooshie/swinv2_base_window8_256.dbv4-full") 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("Mooshie/swinv2_base_window8_256.dbv4-full") model = AutoModelForImageClassification.from_pretrained("Mooshie/swinv2_base_window8_256.dbv4-full", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download model.onnx from Mooshie/swinv2_base_window8_256.dbv4-full: direct link, hf CLI and curl.
- Browser
- Download file 470 MB
-
https://huggingface.co/Mooshie/swinv2_base_window8_256.dbv4-full/resolve/main/model.onnx
- Command line
-
hf download hf://Mooshie/swinv2_base_window8_256.dbv4-full/model.onnx
-
curl -L -o model.onnx https://huggingface.co/Mooshie/swinv2_base_window8_256.dbv4-full/resolve/main/model.onnx
470 MB
- Xet hash:
- f33c59cd3f97450fb758d0a5ca7ad5fa8490da61f5318f604e7236cccbababb7
- Size of remote file:
- 470 MB
- SHA256:
- e0cd170a003010a7b4f1dde12f9d3729f360cfc74bf326280362c065f6283bac
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.