Instructions to use keras/modern_bert_large_en with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- KerasHub
How to use keras/modern_bert_large_en with KerasHub:
import keras_hub # Load TextClassifier model text_classifier = keras_hub.models.TextClassifier.from_preset( "hf://keras/modern_bert_large_en", num_classes=2, ) # Fine-tune text_classifier.fit(x=["Thilling adventure!", "Total snoozefest."], y=[1, 0]) # Classify text text_classifier.predict(["Not my cup of tea."])import keras_hub # Create a MaskedLM model task = keras_hub.models.MaskedLM.from_preset("hf://keras/modern_bert_large_en")import keras_hub # Create a Backbone model unspecialized for any task backbone = keras_hub.models.Backbone.from_preset("hf://keras/modern_bert_large_en") - Keras
How to use keras/modern_bert_large_en 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://keras/modern_bert_large_en") - Notebooks
- Google Colab
- Kaggle
Download metadata.json from keras/modern_bert_large_en: direct link, hf CLI and curl.
- Browser
- Download file 215 Bytes
-
https://huggingface.co/keras/modern_bert_large_en/resolve/main/metadata.json
- Command line
-
hf download hf://keras/modern_bert_large_en/metadata.json
-
curl -L -o metadata.json https://huggingface.co/keras/modern_bert_large_en/resolve/main/metadata.json
215 Bytes
| { | |
| "keras_version": "3.15.1", | |
| "keras_hub_version": "0.33.0.dev0", | |
| "parameter_count": 394781696, | |
| "date_saved": "2026-10-08@04:35:14", | |
| "tasks": [ | |
| "MaskedLM", | |
| "TextClassifier" | |
| ] | |
| } |