Update README.md with new model card content
Browse files
README.md
CHANGED
|
@@ -25,6 +25,35 @@ To load preset architectures and weights, use the `from_preset` constructor.
|
|
| 25 |
Disclaimer: Pre-trained models are provided on an "as is" basis, without
|
| 26 |
warranties or conditions of any kind.
|
| 27 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
|
| 29 |
__Arguments__
|
| 30 |
|
|
|
|
| 25 |
Disclaimer: Pre-trained models are provided on an "as is" basis, without
|
| 26 |
warranties or conditions of any kind.
|
| 27 |
|
| 28 |
+
## Links
|
| 29 |
+
|
| 30 |
+
* [ALBERT Quickstart Notebook](https://www.kaggle.com/code/laxmareddypatlolla/albert-quickstart-notebook)
|
| 31 |
+
* [ALBERT API Documentation](https://keras.io/keras_hub/api/models/albert/)
|
| 32 |
+
* [ALBERT Model Card](https://huggingface.co/docs/transformers/en/model_doc/albert)
|
| 33 |
+
* [KerasHub Beginner Guide](https://keras.io/guides/keras_hub/getting_started/)
|
| 34 |
+
* [KerasHub Model Publishing Guide](https://keras.io/guides/keras_hub/upload/)
|
| 35 |
+
|
| 36 |
+
## Installation
|
| 37 |
+
|
| 38 |
+
Keras and KerasHub can be installed with:
|
| 39 |
+
|
| 40 |
+
```
|
| 41 |
+
pip install -U -q keras-hub
|
| 42 |
+
pip install -U -q keras
|
| 43 |
+
```
|
| 44 |
+
|
| 45 |
+
Jax, TensorFlow, and Torch come preinstalled in Kaggle Notebooks. For instructions on installing them in another environment see the [Keras Getting Started](https://keras.io/getting_started/) page.
|
| 46 |
+
|
| 47 |
+
## Presets
|
| 48 |
+
|
| 49 |
+
The following model checkpoints are provided by the Keras team. Full code examples for each are available below.
|
| 50 |
+
| Preset name | Parameters | Description |
|
| 51 |
+
|----------------|------------|--------------------------------------------------|
|
| 52 |
+
| albert_base_en_uncased | 11.68M | 12-layer ALBERT model where all input is lowercased. Trained on English Wikipedia + BooksCorpus.|
|
| 53 |
+
| albert_large_en_uncased| 17.68M | 24-layer ALBERT model where all input is lowercased. Trained on English Wikipedia + BooksCorpus. |
|
| 54 |
+
| albert_extra_large_en_uncased | 58.72M | 24-layer ALBERT model where all input is lowercased. Trained on English Wikipedia + BooksCorpus. |
|
| 55 |
+
| albert_extra_extra_large_en_uncased| 222.60M | 12-layer ALBERT model where all input is lowercased. Trained on English Wikipedia + BooksCorpus. |
|
| 56 |
+
|
| 57 |
|
| 58 |
__Arguments__
|
| 59 |
|