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.

Idioma del texto original: inglés

execute-plan

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

Idioma del texto original: inglés

write-notes

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

Idioma del texto original: inglés

markdown

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

Idioma del texto original: inglés

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.

Idioma del texto original: inglés

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.

Idioma del texto original: inglés

documentation

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

Idioma del texto original: inglés

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.

Idioma del texto original: inglés

git-commit

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

Idioma del texto original: inglés

git-push

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

Idioma del texto original: inglés

research-debugging

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

Idioma del texto original: inglés

research-planning

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

Idioma del texto original: inglés