Update README.md with new model card content
Browse files
README.md
CHANGED
|
@@ -22,6 +22,34 @@ warranties or conditions of any kind. The underlying model is provided by a
|
|
| 22 |
third party and subject to a separate license, available
|
| 23 |
[here](https://github.com/facebookresearch/fairseq/).
|
| 24 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
|
| 26 |
__Arguments__
|
| 27 |
|
|
|
|
| 22 |
third party and subject to a separate license, available
|
| 23 |
[here](https://github.com/facebookresearch/fairseq/).
|
| 24 |
|
| 25 |
+
## Links
|
| 26 |
+
|
| 27 |
+
* [OPT Quickstart Notebook](https://www.kaggle.com/code/laxmareddypatlolla/opt-quickstart-notebook)
|
| 28 |
+
* [OPT API Documentation](https://keras.io/keras_hub/api/models/opt/)
|
| 29 |
+
* [KerasHub Beginner Guide](https://keras.io/guides/keras_hub/getting_started/)
|
| 30 |
+
* [KerasHub Model Publishing Guide](https://keras.io/guides/keras_hub/upload/)
|
| 31 |
+
|
| 32 |
+
## Installation
|
| 33 |
+
|
| 34 |
+
Keras and KerasHub can be installed with:
|
| 35 |
+
|
| 36 |
+
```
|
| 37 |
+
pip install -U -q keras-Hub
|
| 38 |
+
pip install -U -q keras
|
| 39 |
+
```
|
| 40 |
+
|
| 41 |
+
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.
|
| 42 |
+
|
| 43 |
+
## Presets
|
| 44 |
+
|
| 45 |
+
The following model checkpoints are provided by the Keras team. Full code examples for each are available below.
|
| 46 |
+
| Preset name | Parameters | Description |
|
| 47 |
+
|----------------|------------|--------------------------------------------------|
|
| 48 |
+
| opt_1.3b_en | 125.24M | 12-layer OPT model where case in maintained. Trained on BookCorpus, CommonCrawl, Pile, and PushShift.io corpora. |
|
| 49 |
+
| opt_125m_en | 1.32B | 24-layer OPT model where case in maintained. Trained on BookCorpus, CommonCrawl, Pile, and PushShift.io corpora. |
|
| 50 |
+
| opt_2.7b_en| 2.70B | 32-layer OPT model where case in maintained. Trained on BookCorpus, CommonCrawl, Pile, and PushShift.io corpora. |
|
| 51 |
+
| opt_6.7b_en| 6.70B | 32-layer OPT model where case in maintained. Trained on BookCorpus, CommonCrawl, Pile, and PushShift.io corpora. |
|
| 52 |
+
|
| 53 |
|
| 54 |
__Arguments__
|
| 55 |
|