axolotl/examples/gemma3n/README.md

Finetune Gemma-3n with Axolotl

Gemma-3n is a family of multimodal models from Google found on HuggingFace. This guide shows how to fine-tune it with Axolotl.

Getting started

1. Install Axolotl following the installation guide.

   Here is an example of how to install from pip:

# Ensure you have Pytorch installed (Pytorch 2.6.0 min)
uv pip install --no-build-isolation 'axolotl[flash-attn]>=0.12.0'

2. In addition to Axolotl's requirements, Gemma-3n requires:

uv pip install timm==1.0.17

# for loading audio data
uv pip install librosa==0.11.0

3. Download sample dataset files

# for text + vision + audio only
wget https://huggingface.co/datasets/Nanobit/text-vision-audio-2k-test/resolve/main/African_elephant.jpg
wget https://huggingface.co/datasets/Nanobit/text-vision-audio-2k-test/resolve/main/En-us-African_elephant.oga

4. Run the finetuning example:

# text only
axolotl train examples/gemma3n/gemma-3n-e2b-qlora.yml

# text + vision
axolotl train examples/gemma3n/gemma-3n-e2b-vision-qlora.yml

# text + vision + audio
axolotl train examples/gemma3n/gemma-3n-e2b-vision-audio-qlora.yml

Let us know how it goes. Happy finetuning! 🚀

WARNING: The loss and grad norm will be much higher than normal. We suspect this to be inherent to the model as of the moment. If anyone would like to submit a fix for this, we are happy to take a look.

TIPS

• You can run a full finetuning by removing the adapter: qlora and load_in_4bit: true from the config.
• Read more on how to load your own dataset at docs.
• The text dataset format follows the OpenAI Messages format as seen here.
• The multimodal dataset format follows the OpenAI multi-content Messages format as seen here.

Optimization Guides

• Multi-GPU Training
• Multi-Node Training
• LoRA Optimizations

Related Resources

• Gemma 3n Blog
• Axolotl Docs
• Axolotl Website
• Axolotl GitHub
• Axolotl Discord