Instructions to use google/siglip2-base-patch16-naflex with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/siglip2-base-patch16-naflex with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-image-classification", model="google/siglip2-base-patch16-naflex") 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("google/siglip2-base-patch16-naflex") model = AutoModelForZeroShotImageClassification.from_pretrained("google/siglip2-base-patch16-naflex") - Notebooks
- Google Colab
- Kaggle
NaFlex Variants Availability
#2
by qzlim - opened
Thank you for the great work. I noticed that there are only two sizes of NaFlex variants (base and so400m) being released. Are there any plans to release additional sizes like large in the future?
qzlim changed discussion title from NaFlex Variant Availability to NaFlex Variants Availability