fine-tuning-customization
LLM fine-tuning with LoRA, QLoRA, DPO alignment, and synthetic data generation. Efficient training, preference learning, data creation. Use when customizing models for specific domains.
npx skills add majiayu000/claude-skill-registry --skill fine-tuning-customization --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.
# Fine-Tuning & Customization Customize LLMs for specific domains using parameter-efficient fine-tuning and alignment techniques. > **Unsloth 2026**: 7x longer context RL, FP8 RL on consumer GPUs, rsLoRA support. **TRL**: OpenEnv integration, vLLM server mode, transformers 5.0.0+ compatible. ## Decision Framework: Fine-Tune or Not? | Approach | Try First | When It Works | |----------|-----------|---------------| | Prompt Engineering | Always | Simple tasks, clear instructions | | RAG | External knowledge needed | Knowledge-intensive tasks | | Fine-Tuning | Last resort | Deep specialization, format control | **Fine-tune ONLY when:** 1. Prompt engineering tried and insufficient 2. RAG doesn't capture domain nuances 3. Specific output format consistently required 4. Persona/style must be deeply embedded 5. You have ~1000+ high-quality examples ## LoRA vs QLoRA (Unsloth 2026) | Criteria | LoRA | QLoRA | |----------|------|-------| | Model fits in VRAM | Use LoRA | | | Memory constrained | | Use QLoRA | | Training speed | 39% faster | | | Memory savings | | 75%+ (dynamic 4-bit quants) | | Quality | Baseline | ~Same (Unsloth recovered accuracy loss) | | 70B LLaMA | | <48GB VRAM with QLoR
- Decision Framework: Fine-Tune or Not?
- LoRA vs QLoRA (Unsloth 2026)
- Quick Reference: LoRA Training
- DPO Alignment
- Synthetic Data Generation
- Key Hyperparameters
- Anti-Patterns (FORBIDDEN)
- Detailed Documentation
- Related Skills
- Capability Details
- lora-qlora
- dpo-alignment
- synthetic-data
- when-to-finetune
What does the fine-tuning-customization skill do?
LLM fine-tuning with LoRA, QLoRA, DPO alignment, and synthetic data generation. Efficient training, preference learning, data creation. Use when customizing models for specific domains.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill fine-tuning-customization --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.