Gemma

A JAX library for using and fine-tuning Gemma, Google DeepMind's family of open-weight large language models built on Gemini research.

Models

Visit website gemma-llm.readthedocs.io

Gemma is the implementation behind the gemma PyPI package, a JAX library for using and fine-tuning Gemma models. A single ChatSampler API works across Gemma versions 2, 3, 3n and 4, supporting multi-turn, multi-modal conversation.

It installs with pip install gemma after installing JAX for CPU, GPU or TPU, and its documentation includes Colabs and tutorials for sampling, multi-modal use, fine-tuning and LoRA, alongside additional scripts in an examples folder.

It runs on CPU, GPU or TPU; the material recommends 8GB or more of GPU RAM for the 2B checkpoint and 24GB or more for the 7B checkpoint. It is written in Python, licensed under Apache-2.0, and is not an official Google product.

More in Models

See all 405

mini-AGI
github.com
A continual learning language model that trains from scratch on a single 8 GB VRAM GPU, assembling its own architecture and adapting its size to the hardware and data available rather than shipping as a fixed pretrained model.
- Models
Applied Inference Lab: Compliance Control Embedding Stack
github.com
An open-source contrastive-embedding pipeline that maps technical CVE vulnerability descriptions to formal cybersecurity compliance controls in NIST SP 800-53 and CMMC, published with its model generation, fine-tuning and evaluation code.
- Models
- Security
peekaboolean
github.com
A small vision-language model, fine-tuned with LoRA on a 500-million-parameter backbone, that answers typed multiple-choice, ordinal-score and yes/no questions about an image with calibrated probabilities, in about 400 milliseconds on a laptop.
- Models
- Inference

More in Models

mini-AGI

Applied Inference Lab: Compliance Control Embedding Stack

peekaboolean

Cookies