Instructions to use keras/multilingual_e5_base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- KerasHub
How to use keras/multilingual_e5_base with KerasHub:
import keras_hub # Load TextClassifier model text_classifier = keras_hub.models.TextClassifier.from_preset( "hf://keras/multilingual_e5_base", 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/multilingual_e5_base")import keras_hub # Create a TextEmbedder model task = keras_hub.models.TextEmbedder.from_preset("hf://keras/multilingual_e5_base")import keras_hub # Create a Backbone model unspecialized for any task backbone = keras_hub.models.Backbone.from_preset("hf://keras/multilingual_e5_base") - Keras
How to use keras/multilingual_e5_base 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/multilingual_e5_base") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 581e49bfd62782d94c568ee09f8bdcb26aa05db3759e8ba7e92961596c57833d
- Size of remote file:
- 1.11 GB
- SHA256:
- a90c1d863bae1815a64df2c93182ef22adbbbf275bc38a361e6f5f9ceedb926c
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.