Instructions to use keras/bert_base_multi with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- KerasHub
How to use keras/bert_base_multi with KerasHub:
import keras_hub # Load TextClassifier model text_classifier = keras_hub.models.TextClassifier.from_preset( "hf://keras/bert_base_multi", 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/bert_base_multi")import keras_hub # Create a Backbone model unspecialized for any task backbone = keras_hub.models.Backbone.from_preset("hf://keras/bert_base_multi") - Keras
How to use keras/bert_base_multi 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/bert_base_multi") - Notebooks
- Google Colab
- Kaggle
Update README.md with new model card content
Browse files
README.md
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
---
|
| 2 |
library_name: keras-hub
|
| 3 |
---
|
| 4 |
-
##
|
| 5 |
BERT (Bidirectional Encoder Representations from Transformers) is a set of language models published by Google. They are intended for classification and embedding of text, not for text-generation. See the model card below for benchmarks, data sources, and intended use cases.
|
| 6 |
|
| 7 |
Weights and Keras model code are released under the [Apache 2 License](https://github.com/keras-team/keras-hub/blob/master/LICENSE).
|
|
@@ -41,7 +41,7 @@ The following model checkpoints are provided by the Keras team. Full code exampl
|
|
| 41 |
| `bert_large_en_uncased` | 335.14M | 24-layer BERT model where all input is lowercased. |
|
| 42 |
| `bert_large_en` | 333.58M | 24-layer BERT model where case is maintained. |
|
| 43 |
|
| 44 |
-
##
|
| 45 |
```python
|
| 46 |
import keras
|
| 47 |
import keras_hub
|
|
|
|
| 1 |
---
|
| 2 |
library_name: keras-hub
|
| 3 |
---
|
| 4 |
+
## Model Overview
|
| 5 |
BERT (Bidirectional Encoder Representations from Transformers) is a set of language models published by Google. They are intended for classification and embedding of text, not for text-generation. See the model card below for benchmarks, data sources, and intended use cases.
|
| 6 |
|
| 7 |
Weights and Keras model code are released under the [Apache 2 License](https://github.com/keras-team/keras-hub/blob/master/LICENSE).
|
|
|
|
| 41 |
| `bert_large_en_uncased` | 335.14M | 24-layer BERT model where all input is lowercased. |
|
| 42 |
| `bert_large_en` | 333.58M | 24-layer BERT model where case is maintained. |
|
| 43 |
|
| 44 |
+
## Example Usage
|
| 45 |
```python
|
| 46 |
import keras
|
| 47 |
import keras_hub
|