metadata

library_name: keras-hub
extra_gated_heading: Access CodeGemma on Hugging Face
extra_gated_prompt: >-
  To access CodeGemma 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
license: gemma
license_link: https://ai.google.dev/gemma/terms
pipeline_tag: text-generation

CodeGemma

Google Model Page: CodeGemma

This model card corresponds to the latest 7B instruct version of the CodeGemma 1.1 model for usage 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 CodeGemma family here:

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

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

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

Authors : Google

Loading the model

import keras_hub

gemma_lm = keras_hub.models.GemmaCausalLM.from_preset("hf://google/codegemma-1.1-7b-it-keras")