Gemma is a family of open-weights Large Language Model (LLM) by Google DeepMind, based on Gemini research and technology.
This repository contain the implementation of the
gemma PyPI package. A
JAX library to use and fine-tune Gemma.
For examples and uses-cases, see our documentation. Please report issues and feedback in our GitHub.
- To use this library: https://gemma-llm.readthedocs.io/
- Technical reports for metrics and model capabilities:
- Other Gemma implementations and doc on the Gemma ecosystem: https://ai.google.dev/gemma/docs
-
Install JAX for CPU, GPU or TPU. Follow instructions at the JAX website.
-
Run
pip install gemma
To download the model weights. See our documentation.
Our documentation contain various Colabs and tutorial, including:
- Sampling
- Fine-tuning
- LoRA
- ...
Additionally, our examples/ folder contain additional scripts to fine-tune and sample with Gemma.
Gemma can run on a CPU, GPU and TPU. For GPU, we recommend a 8GB+ RAM on GPU for the 2B checkpoint and 24GB+ RAM on GPU for the 7B checkpoint.
This is not an official Google product.
