Instructions to use google/siglip2-so400m-patch14-384 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/siglip2-so400m-patch14-384 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-image-classification", model="google/siglip2-so400m-patch14-384") pipe( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png", candidate_labels=["animals", "humans", "landscape"], )# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("google/siglip2-so400m-patch14-384", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Fix model_max_length
#4
by fancyfeast - opened
Set model_max_length to 64.
Looks like model_max_length is erroneous, so this pull request sets it to 64, which I believe is the correct value given the text encoder's maximum input length.
This comment has been hidden