Text Generation
KerasHub
English
text-generation-inference
text-classification
text-conversation
text-to-text-generation
Instructions to use keras/gemma_1.1_instruct_7b_en with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- KerasHub
How to use keras/gemma_1.1_instruct_7b_en with KerasHub:
import keras_hub # Create a Backbone model unspecialized for any task backbone = keras_hub.models.Backbone.from_preset("hf://keras/gemma_1.1_instruct_7b_en") - Keras
How to use keras/gemma_1.1_instruct_7b_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/gemma_1.1_instruct_7b_en") - Notebooks
- Google Colab
- Kaggle
Download tokenizer.json from keras/gemma_1.1_instruct_7b_en: direct link, hf CLI and curl.
- Browser
- Download file 401 Bytes
-
https://huggingface.co/keras/gemma_1.1_instruct_7b_en/resolve/main/tokenizer.json
- Command line
-
hf download hf://keras/gemma_1.1_instruct_7b_en/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/keras/gemma_1.1_instruct_7b_en/resolve/main/tokenizer.json
401 Bytes
| { | |
| "module": "keras_nlp.src.models.gemma.gemma_tokenizer", | |
| "class_name": "GemmaTokenizer", | |
| "config": { | |
| "name": "gemma_tokenizer", | |
| "trainable": true, | |
| "dtype": "int32", | |
| "proto": null, | |
| "sequence_length": null | |
| }, | |
| "registered_name": "keras_nlp>GemmaTokenizer", | |
| "assets": [ | |
| "assets/tokenizer/vocabulary.spm" | |
| ], | |
| "weights": null | |
| } |