Instructions to use zeromodels/roberta_large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ZeroModels
How to use zeromodels/roberta_large 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/roberta_large") - Keras
How to use zeromodels/roberta_large 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/roberta_large") - Notebooks
- Google Colab
- Kaggle
Download model.weights.h5 from zeromodels/roberta_large: direct link, hf CLI and curl.
- Browser
- Download file 1.63 GB
-
https://huggingface.co/zeromodels/roberta_large/resolve/main/model.weights.h5
- Command line
-
hf download hf://zeromodels/roberta_large/model.weights.h5
-
curl -L -o model.weights.h5 https://huggingface.co/zeromodels/roberta_large/resolve/main/model.weights.h5
1.63 GB
- Xet hash:
- 604a749dad41e018d25a7ca9ac98d7b5abd2785e01fbd55fd2a3ac52090fe2be
- Size of remote file:
- 1.63 GB
- SHA256:
- 83ba9798ad0df42487f1de132704710871961578f39539dd2c7d6a70285c4b39
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.