gemma-tuner-multimodal — Claude Code skill: how to install
Fine-tunes Gemma 4 and 3n models on Apple Silicon hardware with PyTorch MPS. Adapts weights for audio, vision, and text via LoRA.
npx skills add reason-machines/trending-skills --skill gemma-tuner-multimodal -a claude-codeWhat gemma-tuner-multimodal does
This skill guides coding agents through parameter-efficient fine-tuning for Gemma 3n and Gemma 4 models directly on Apple Silicon. No Nvidia card is needed. PyTorch executes directly on Metal Performance Shaders. To handle massive datasets, the pipeline can stream batches directly from BigQuery or Google Cloud Storage without filling your local hard drive.
All tasks revolve around the gemma-macos-tuner command-line tool. It provides dedicated routines to verify system dependencies, walk through an interactive setup wizard, process CSV datasets, and merge LoRA adapters into SafeTensors. Configurations across models, datasets, and hyperparameters are managed hierarchically inside config/config.ini.
Running Python under Rosetta x86_64 breaks execution; you need native arm64 on macOS 12.3 or newer. Training Gemma 4 variants also demands a dedicated virtual environment with packages from requirements-gemma4.txt.
What it helps with
- fine-tune Gemma 3n and 4 on Apple Silicon without Nvidia GPUs
- train multimodal speech models using audio files and transcripts
- configure vision-language LoRA runs for image captioning tasks
- stream training data from BigQuery or GCS without saving files locally
- merge trained LoRA adapters and export them into SafeTensors
Example prompts for the agent
- Verify my local hardware setup using gemma-macos-tuner system-check
- Generate an audio fine-tuning profile inside config.ini for Gemma 3n
- Run dataset preparation and start the text-instruction training profile
How to install gemma-tuner-multimodal
1Skills CLI (Vercel)
npx skills add reason-machines/trending-skills --skill gemma-tuner-multimodal -a claude-code2Manually: put the files in place
~/.claude/skills/gemma-tuner-multimodal/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/gemma-tuner-multimodal/
1Skills CLI (Vercel)
npx skills add reason-machines/trending-skills --skill gemma-tuner-multimodal -a codex2Manually: put the files in place
.agents/skills/gemma-tuner-multimodal/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add reason-machines/trending-skills --skill gemma-tuner-multimodal -a cursor2Manually: put the files in place
.cursor/skills/gemma-tuner-multimodal/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install reason-machines/trending-skills gemma-tuner-multimodal2Manually: put the files in place
.github/skills/gemma-tuner-multimodal/SKILL.md1Skills CLI (Vercel)
npx skills add reason-machines/trending-skills --skill gemma-tuner-multimodal -a gemini-cli2Platform CLI
gemini skills install https://github.com/reason-machines/trending-skills --path skills/gemma-tuner-multimodalManually: put the files in place
.devin/skills/gemma-tuner-multimodal/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add reason-machines/trending-skills --skill gemma-tuner-multimodal -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about gemma-tuner-multimodal
How to install gemma-tuner-multimodal in Claude Code?
Run npx skills add reason-machines/trending-skills --skill gemma-tuner-multimodal -a claude-code. The skill file installs to ~/.claude/skills/gemma-tuner-multimodal/SKILL.md.
What does gemma-tuner-multimodal do?
It gives your AI coding assistant instructions and workflows to run multimodal LoRA fine-tuning for Gemma models on macOS with Apple Silicon.
What hardware and software prerequisites are required?
You need an Apple Silicon Mac running macOS 12.3 or newer, native arm64 Python 3.10+, PyTorch with MPS, and Hugging Face credentials authorized for Gemma access.
