Gemma open-weight LLM library from Google DeepMind.
Project description
Gemma
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
-
Install JAX for CPU, GPU or TPU. Follow the instructions on the JAX website.
-
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
- To use this library: Gemma documentation
- Technical reports for metrics and model capabilities:
- Other Gemma implementations and doc on the Gemma ecosystem
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
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
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
Algorithm | Hash digest | |
---|---|---|
SHA256 | c91d44037189ce17f18abcf43e2ed56604503bfd6fefafbe80465d2885eb7ba4 |
|
MD5 | 6cb594548748c44dbbe2c10c59dc1bf2 |
|
BLAKE2b-256 | ad17098472e1f0189d095ef92896fb0d201a4bb90bf1c585c6787a5372d6fde8 |
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
Algorithm | Hash digest | |
---|---|---|
SHA256 | 6c86ac1f18e480b33e6235babee2367fdcf1ae149c67c148970e99937b3734aa |
|
MD5 | 3d49969c98819daabbd690a10c491d9b |
|
BLAKE2b-256 | b57636a323ecdde5010197fabcb905cb4f1000126b5a02852d01c41ba58ff6e8 |