Instructions to use zeromodels/roberta_base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ZeroModels
How to use zeromodels/roberta_base 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_base") - Keras
How to use zeromodels/roberta_base 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_base") - Notebooks
- Google Colab
- Kaggle
Download model.weights.h5 from zeromodels/roberta_base: direct link, hf CLI and curl.
- Browser
- Download file 656 MB
-
https://huggingface.co/zeromodels/roberta_base/resolve/main/model.weights.h5
- Command line
-
hf download hf://zeromodels/roberta_base/model.weights.h5
-
curl -L -o model.weights.h5 https://huggingface.co/zeromodels/roberta_base/resolve/main/model.weights.h5
656 MB
- Xet hash:
- 5d3eb61d357719d1fe508198e15920f39c37f5c149eff87a8938c1cc2880f29c
- Size of remote file:
- 656 MB
- SHA256:
- 446246ae06a71fb171530c0a15941d6867dded4028917975a61d62d009ab8e2c
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.