Skip to main content

Gemma open-weight LLM library from Google DeepMind.

Project description

Gemma

Unittests PyPI version Documentation Status

Gemma is a family of open-weights Large Language Model (LLM) by Google DeepMind, based on Gemini research and technology.

This repository contains the implementation of the gemma PyPI package. A JAX library to use and fine-tune Gemma.

For examples and use cases, see our documentation. Please report issues and feedback in our GitHub.

Installation

  1. Install JAX for CPU, GPU or TPU. Follow the instructions on the JAX website.

  2. Run

    pip install gemma
    

Examples

Here is a minimal example to have a multi-turn, multi-modal conversation with Gemma:

from gemma import gm

# Model and parameters
model = gm.nn.Gemma3_4B()
params = gm.ckpts.load_params(gm.ckpts.CheckpointPath.GEMMA3_4B_IT)

# Example of multi-turn conversation
sampler = gm.text.ChatSampler(
    model=model,
    params=params,
    multi_turn=True,
)

prompt = """Which of the two images do you prefer?

Image 1: <start_of_image>
Image 2: <start_of_image>

Write your answer as a poem."""
out0 = sampler.chat(prompt, images=[image1, image2])

out1 = sampler.chat('What about the other image ?')

Our documentation contains various Colabs and tutorials, including:

Additionally, our examples/ folder contain additional scripts to fine-tune and sample with Gemma.

Learn more about Gemma

Downloading the models

To download the model weights. See our documentation.

System Requirements

Gemma can run on a CPU, GPU and TPU. For GPU, we recommend 8GB+ RAM on GPU for The 2B checkpoint and 24GB+ RAM on GPU are used for the 7B checkpoint.

This is not an official Google product.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

gemma-3.0.2.tar.gz (80.5 kB view details)

Uploaded Source

Built Distribution

gemma-3.0.2-py3-none-any.whl (122.3 kB view details)

Uploaded Python 3

File details

Details for the file gemma-3.0.2.tar.gz.

File metadata

  • Download URL: gemma-3.0.2.tar.gz
  • Upload date:
  • Size: 80.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.11.11

File hashes

Hashes for gemma-3.0.2.tar.gz
Algorithm Hash digest
SHA256 c91d44037189ce17f18abcf43e2ed56604503bfd6fefafbe80465d2885eb7ba4
MD5 6cb594548748c44dbbe2c10c59dc1bf2
BLAKE2b-256 ad17098472e1f0189d095ef92896fb0d201a4bb90bf1c585c6787a5372d6fde8

See more details on using hashes here.

File details

Details for the file gemma-3.0.2-py3-none-any.whl.

File metadata

  • Download URL: gemma-3.0.2-py3-none-any.whl
  • Upload date:
  • Size: 122.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.11.11

File hashes

Hashes for gemma-3.0.2-py3-none-any.whl
Algorithm Hash digest
SHA256 6c86ac1f18e480b33e6235babee2367fdcf1ae149c67c148970e99937b3734aa
MD5 3d49969c98819daabbd690a10c491d9b
BLAKE2b-256 b57636a323ecdde5010197fabcb905cb4f1000126b5a02852d01c41ba58ff6e8

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page