How to use Geonmo/CLIP-Giga-config-fixed with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-image-classification", model="Geonmo/CLIP-Giga-config-fixed") 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("Geonmo/CLIP-Giga-config-fixed") model = AutoModelForZeroShotImageClassification.from_pretrained("Geonmo/CLIP-Giga-config-fixed")
It will be removed when the config in laion/CLIP-ViT-bigG-14-laion2B-39B-b160k is fixed.
laion/CLIP-ViT-bigG-14-laion2B-39B-b160k
