mattmireles/gemma-tuner-multimodal

phase-audit

Audit a Gemma Tuner plan phase against its acceptance criteria, tests, artifacts, leakage controls, hardware claims, and stop conditions.

execute-plan

Execute an approved Gemma Tuner implementation or experiment plan phase by phase with frozen gates and recorded evidence.

write-notes

Record Gemma Tuner investigations, experiment evidence, failures, and operational learnings in the repo's existing notes structure.

markdown

Edit Gemma Tuner Markdown while preserving links, runnable commands, tables, heading structure, and honest model/data/hardware claims.

audit

Audit Gemma Multimodal Fine-Tuner for training correctness, dataset leakage, MPS/device behavior, checkpoint/export integrity, evaluation validity, privacy, and CLI/wizard/visualizer regressions.

debug

Debug Gemma Multimodal Fine-Tuner failures across Python environments, Hugging Face models, PEFT/LoRA, datasets, audio/image processors, MPS, wizard subprocesses, visualizer state, evaluation, or export.

documentation

Write or update Gemma Tuner documentation for CLI, configuration, datasets, training, evaluation, export, MPS behavior, wizard, and visualizer changes.

execute-plan-hardcore

Carry a Gemma Tuner plan through implementation, empirical verification, adversarial audit, and honest closeout. Use only when explicitly invoked. A preregistered KILL is a valid completed result.

git-commit

Create a scoped Gemma Tuner commit after tests pass. Use only when the user explicitly asks to commit.

git-push

Push a tested Gemma Tuner branch after confirming commit scope and remote state. Use only when explicitly requested.

research-debugging

Debug failures that cross Gemma Tuner and external Hugging Face, Transformers, PEFT, PyTorch MPS, dataset, or model-card boundaries.

research-planning

Plan external research for Gemma, Hugging Face, PEFT, PyTorch MPS, multimodal processors, or training behavior when current authoritative knowledge is required.