Individual skill
finetuning
Use when adapting an open-weight model to a target form or behavior — tone, output format, reasoning pattern — via LoRA/QLoRA or full fine-tuning with TRL SFTTrainer, then preference optimization (DPO/ORPO/KTO/GRPO), and for fine-tune vs prompt vs RAG. NOT adding facts to a model (that is rag); NOT the single-GPU Unsloth backend or GGUF export (that is unsloth).
skills/finetuning/SKILL.md
Source commit d9d6bb338f66cc1e23998585e580a0ea45bbcb82
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- No
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Not checked yet
- Last checked
- Nov 6, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 556
- Repository last updated
- Nov 4, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- agent-skills Repository topic
- agentic-ai Repository topic
- ai-agents Repository topic
- ai-coding Repository topic
- claude-code Repository topic
- cli Repository topic
- cline Repository topic
- codex Repository topic
- coding-assistant Repository topic
- cursor Repository topic
- finetuning Declared skill tag
- lora Declared skill tag
- qlora Declared skill tag
- sft Declared skill tag
- dpo Declared skill tag
- grpo Declared skill tag
- peft Declared skill tag
- trl Declared skill tag
- preference-optimization Declared skill tag
- engineering Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 15,188 bytesSKILL.mdcore · 15,188 bytesSKILL.mdcore · 15,188 bytesSKILL.mdcore · 15,188 bytesevals/README.mddoc · 1,043 bytesevals/cases.yamlasset · 4,697 bytesreferences/hyperparameters-and-eval.mddoc · 4,685 bytesreferences/methods.mddoc · 8,564 bytes
Read excerpt
# finetuning — teach an open model a form or behavior, not a fact
You own the discipline of **adapting an open-weight model**: deciding whether to fine-tune at all,
then running SFT and (optionally) preference optimization with `trl` + `peft`, backend-agnostic.
You are judged by whether the tuned model reliably produces the target **form/behavior** on a
held-out set — not by train loss, and not by vibes.
The one sentence that routes half of all "should I fine-tune?" questions correctly:
**fine-tuning teaches *form and behavior*; RAG supplies *facts*.** If the ask is "know our latest
prices / docs / tickets," that is retrieval (`../rag/SKILL.md`), not training. If the ask is "sound
like us, always emit this JSON, follow this reasoning pattern," that is here.
## Decision gate — try this BEFORE reaching for a GPU
