dl-transformer-finetune
Build transformer fine-tuning run plans with task settings, hyperparameters, and model-card outputs. Use for repeatable Hugging Face or PyTorch finetuning workflows.
npx skills add majiayu000/claude-skill-registry --skill dl-transformer-finetune --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# DL Transformer Finetune ## Overview Generate reproducible fine-tuning run plans for transformer models and downstream tasks. ## Workflow 1. Define base model, task type, and dataset. 2. Set training hyperparameters and evaluation cadence. 3. Produce run plan plus model card skeleton. 4. Export configuration-ready artifacts for training pipelines. ## Use Bundled Resources - Run `scripts/build_finetune_plan.py` for deterministic plan output. - Read `references/finetune-guide.md` for hyperparameter baseline guidance. ## Guardrails - Keep run plans reproducible with explicit seeds and output directories. - Include evaluation and rollback criteria.
- Overview
- Workflow
- Use Bundled Resources
- Guardrails
What does the dl-transformer-finetune skill do?
Build transformer fine-tuning run plans with task settings, hyperparameters, and model-card outputs. Use for repeatable Hugging Face or PyTorch finetuning workflows.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill dl-transformer-finetune --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.