Instructions to use PumeTu/DFN2B-ViT-B-16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use PumeTu/DFN2B-ViT-B-16 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-image-classification", model="PumeTu/DFN2B-ViT-B-16") pipe( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png", candidate_labels=["animals", "humans", "landscape"], )# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForZeroShotImageClassification processor = AutoProcessor.from_pretrained("PumeTu/DFN2B-ViT-B-16") model = AutoModelForZeroShotImageClassification.from_pretrained("PumeTu/DFN2B-ViT-B-16", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tokenizer.json from PumeTu/DFN2B-ViT-B-16: direct link, hf CLI and curl.
- Browser
- Download file 3.64 MB
-
https://huggingface.co/PumeTu/DFN2B-ViT-B-16/resolve/main/tokenizer.json
- Command line
-
hf download hf://PumeTu/DFN2B-ViT-B-16/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/PumeTu/DFN2B-ViT-B-16/resolve/main/tokenizer.json
3.64 MB
File too large to display, you can check the raw version instead.