Instructions to use keras/siglip2_giant_opt_patch16_256 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- KerasHub
How to use keras/siglip2_giant_opt_patch16_256 with KerasHub:
import keras_hub # Create a Backbone model unspecialized for any task backbone = keras_hub.models.Backbone.from_preset("hf://keras/siglip2_giant_opt_patch16_256") - Keras
How to use keras/siglip2_giant_opt_patch16_256 with Keras:
# Available backend options are: "jax", "torch", "tensorflow". import os os.environ["KERAS_BACKEND"] = "jax" import keras model = keras.saving.load_model("hf://keras/siglip2_giant_opt_patch16_256") - Notebooks
- Google Colab
- Kaggle
Download model.weights.h5 from keras/siglip2_giant_opt_patch16_256: direct link, hf CLI and curl.
- Browser
- Download file 7.49 GB
-
https://huggingface.co/keras/siglip2_giant_opt_patch16_256/resolve/main/model.weights.h5
- Command line
-
hf download hf://keras/siglip2_giant_opt_patch16_256/model.weights.h5
-
curl -L -o model.weights.h5 https://huggingface.co/keras/siglip2_giant_opt_patch16_256/resolve/main/model.weights.h5
7.49 GB
- Xet hash:
- deedd204e91761fc9c06da00a7e5a82d63b845eed182507df2fd6ac2f0c7c808
- Size of remote file:
- 7.49 GB
- SHA256:
- 5c7295b363a2b025e0c9101f2dbb0f693d84b7a35971ce384f0124102493a3ac
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.