Instructions to use google/siglip2-base-patch16-224 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/siglip2-base-patch16-224 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-image-classification", model="google/siglip2-base-patch16-224") 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-base-patch16-224", dtype="auto") - Notebooks
- Google Colab
- Kaggle
The output is very small
#18 opened 3 months ago
by
weathon
Bug report: seems Siglip2 cannot handle the single-apostrophe character
#16 opened 8 months ago
by
astradzhao
Adding ONNX file of this model
#15 opened 8 months ago
by
Yengoyan
The accuracy on the ImageNet dataset is low
π 1
1
#13 opened 11 months ago
by
qingshuiL
Error loading the SigLIP2 Vision model
ππ€ 3
3
#12 opened 11 months ago
by
jgaubil
Update README.md
1
#11 opened 12 months ago
by
mrgrandsky
mportError: cannot import name 'Siglip2VisionModel' from 'transformers' (/home/AAA/.conda/envs/internvl/lib/python3.9/site-packages/transformers/__init__.py)
1
#9 opened about 1 year ago
by
chenyi502
Why config.json doesn't contains architectures
#8 opened about 1 year ago
by
GaojiLiu
question about number of parameters in vision encoder
ππ 1
1
#6 opened about 1 year ago
by
weidu
question about 'model_type' in config.json
3
#5 opened about 1 year ago
by
XA-hyy
Missing Vocab file
π 1
4
#4 opened about 1 year ago
by
myn0908
Error while loading processor: TypeError: expected str, bytes or os.PathLike object, not NoneType
π€π 3
10
#2 opened about 1 year ago
by
armamut