metadata

library_name: keras-nlp
license: gemma
license_link: https://ai.google.dev/gemma/terms
pipeline_tag: text-generation
extra_gated_heading: Access Gemma 1.1 on Hugging Face
extra_gated_prompt: >-
  To access Gemma 1.1 on Hugging Face, you’re required to review and agree to
  Google’s usage license. To do this, please ensure you’re logged-in to Hugging
  Face and click below. Requests are processed immediately.
extra_gated_button_content: Acknowledge license

Gemma 1.1

Google Model Page: Gemma

This model card corresponds to the latest 2B instruct version of the Gemma 1.1 model in Keras.

Keras models can be used with JAX, PyTorch or TensorFlow as numerical backends. JAX, with its support for SPMD model paralellism, is recommended for large models. For more information: distributed training with Keras and JAX.

You can find other models in the Gemma family here:

	Base	Instruct
2B	gemma-2b-keras	gemma-1.1-2b-it-keras
7B	gemma-7b-keras	gemma-1.1-7b-it-keras

For more information about the model, visit https://huggingface.co/google/gemma-1.1-2b-it.

Model Page : Gemma

Resources and Technical Documentation : Technical Report : Responsible Generative AI Toolkit

Authors : Google

Loading the model

import keras_nlp

gemma_lm = keras_nlp.models.GemmaCausalLM.from_preset("hf://google/gemma-1.1-2b-it-keras")