Instructions to use apple/DFN-public with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use apple/DFN-public with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-image-classification", model="apple/DFN-public") pipe( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png", candidate_labels=["animals", "humans", "landscape"], )# Load model directly from transformers import AutoProcessor, AutoModelForZeroShotImageClassification processor = AutoProcessor.from_pretrained("apple/DFN-public") model = AutoModelForZeroShotImageClassification.from_pretrained("apple/DFN-public") - Notebooks
- Google Colab
- Kaggle
Loading the processor?
#5
by ryanramos - opened
I noticed that this repo doesn't contain a preprocessor_config.json file so the recommended AutoProcessor.from_pretrained("apple/DFN-public") doesn't work.
Given that the model card describes this DFN's architecture as ViT-B-32, does this mean that something like AutoProcessor.from_pretrained("openai/clip-vit-base-patch32") should work?
Thank you!