Text Generation
KerasHub
Keras
English
text-generation-inference
text-to-text-generation
text-conversation
Instructions to use keras/llama3_instruct_8b_en with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- KerasHub
How to use keras/llama3_instruct_8b_en with KerasHub:
import keras_hub # Create a LlamaCausalLM model task = keras_hub.models.LlamaCausalLM.from_preset("hf://keras/llama3_instruct_8b_en")import keras_hub # Create a Backbone model unspecialized for any task backbone = keras_hub.models.Backbone.from_preset("hf://keras/llama3_instruct_8b_en") - Keras
How to use keras/llama3_instruct_8b_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/llama3_instruct_8b_en") - Notebooks
- Google Colab
- Kaggle
Update README.md with new model card content
Browse files
README.md
CHANGED
|
@@ -17,7 +17,7 @@ Llama 3 is a set of large language models published by Meta. Both pretrained and
|
|
| 17 |
Weights are released under the [Llama 3 Community License](https://ai.meta.com/llama/license/). Keras model code is released under the [Apache 2 License](https://github.com/keras-team/keras-hub/blob/master/LICENSE).
|
| 18 |
|
| 19 |
## Links
|
| 20 |
-
|
| 21 |
* [Llama 3 API Documentation](https://keras.io/api/keras_hub/models/llama3/)
|
| 22 |
* [Llama 3 Model Card & Prompt Formats](https://llama.meta.com/docs/model-cards-and-prompt-formats/meta-llama-3)
|
| 23 |
* [KerasHub Beginner Guide](https://keras.io/guides/keras_hub/getting_started/)
|
|
@@ -29,7 +29,7 @@ Keras and KerasHub can be installed with:
|
|
| 29 |
|
| 30 |
```
|
| 31 |
pip install -U -q keras-hub
|
| 32 |
-
pip install -U -q keras
|
| 33 |
```
|
| 34 |
|
| 35 |
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.
|
|
|
|
| 17 |
Weights are released under the [Llama 3 Community License](https://ai.meta.com/llama/license/). Keras model code is released under the [Apache 2 License](https://github.com/keras-team/keras-hub/blob/master/LICENSE).
|
| 18 |
|
| 19 |
## Links
|
| 20 |
+
* [Llama 3 Quickstart Notebook](https://www.kaggle.com/code/laxmareddypatlolla/llama3-quickstart-notebook)
|
| 21 |
* [Llama 3 API Documentation](https://keras.io/api/keras_hub/models/llama3/)
|
| 22 |
* [Llama 3 Model Card & Prompt Formats](https://llama.meta.com/docs/model-cards-and-prompt-formats/meta-llama-3)
|
| 23 |
* [KerasHub Beginner Guide](https://keras.io/guides/keras_hub/getting_started/)
|
|
|
|
| 29 |
|
| 30 |
```
|
| 31 |
pip install -U -q keras-hub
|
| 32 |
+
pip install -U -q keras
|
| 33 |
```
|
| 34 |
|
| 35 |
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.
|