finetuning-model-onboarding
Skill738 starsChanged 4 days agoAGPL-3.0View on GitHub
Rules for adding a new model or model family to the finetuning pipeline, or changing finetuning behavior for an existing one — engine-agnostic customization via family hooks instead of if/else in the shared script, TRL-compatible chat templates ({% generation %} / pretok_trl), H100-before-H200 GPU probing, populating real_max_context_length/validated_context_length in models.json, and setting finetuning cost/pricing for a new model. Use when onboarding a model to Modal+Unsloth finetuning, adding a ModelFamily, pretok_trl falls back with a training-compatible chat template error, a model fails on its assigned GPU/context length, or pricing a new model's training cost.
We split this skill into the rules it gives an agent
11 rules. About 0 are common, 4 are distinctive, and 7 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
7
Very specific
Tied to their project's names, files or tools. Probably skip.
Licensed with conditions — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
In this repository11 other files it gives its agents.
- AGENTS.mdAGENTS.md
- api-endpointsSkill
- backend-architectureSkill
- code-commentsSkill
- data-workshopSkill
- engineering-tasteSkill
- frontend-designSkill
- mcpSkill
- pr-etiquetteSkill
- run-testsSkill
- seed-demo-dataSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.