Instructions to use zeromodels/sam3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ZeroModels
How to use zeromodels/sam3 with ZeroModels:
# pip install -U zeromodels # ZeroModels is pure Keras 3, so pick a backend: "jax", "torch" or "tensorflow". import os os.environ["KERAS_BACKEND"] = "jax" from zeromodels import AutoZModel # AutoZModel reads the repo's model_type and loads the matching class. # For a task head use the matching loader, e.g. AutoZMImageClassify / AutoZMDetect / # AutoZMSemanticSegment / AutoZMTextGenerate (see zeromodels.auto). model = AutoZModel.from_weights("zeromodels/sam3") - Keras
How to use zeromodels/sam3 with Keras:
# !pip install -U keras tensorflow huggingface_hub # Keras needs TensorFlow installed to read "hf://" paths, so the tensorflow backend is selected here; # "jax" and "torch" also work for computation once TensorFlow is installed. import os os.environ["KERAS_BACKEND"] = "tensorflow" import keras model = keras.saving.load_model("hf://zeromodels/sam3") - Notebooks
- Google Colab
- Kaggle
Download model.weights.h5 from zeromodels/sam3: direct link, hf CLI and curl.
- Browser
- Download file 3.36 GB
-
https://huggingface.co/zeromodels/sam3/resolve/main/model.weights.h5
- Command line
-
hf download hf://zeromodels/sam3/model.weights.h5
-
curl -L -o model.weights.h5 https://huggingface.co/zeromodels/sam3/resolve/main/model.weights.h5
3.36 GB
- Xet hash:
- 5918f6ff3d24f5a98773387260d8925246fc8ad50418d6ccc98a64a791d9d5fd
- Size of remote file:
- 3.36 GB
- SHA256:
- a0bcbf75f8dd23444a3e72a7d8128aa66dc573e5f369c32053aecc5fd47775d5
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.