llm-fine-tuning
Fine-tune large language models efficiently using LoRA, QLoRA, and PEFT methods. Use for domain adaptation, instruction tuning, task-specific optimization, and parameter-efficient training of LLMs.
npx skills add majiayu000/claude-skill-registry --skill llm-fine-tuning-jh9282026-manus --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.
# LLM Fine-Tuning Fine-tune large language models efficiently using parameter-efficient methods. ## Overview LLM fine-tuning adapts pre-trained models to specific tasks or domains. This skill covers efficient techniques like LoRA, QLoRA, and full fine-tuning strategies. ## Quick Reference | Scenario | Recommended Approach | Reference File | |----------|---------------------|----------------| | Efficient fine-tuning with limited resources | LoRA, QLoRA, PEFT methods | `/references/peft-methods.md` | | Full model fine-tuning | Supervised fine-tuning, instruction tuning | `/references/full-finetuning.md` | | Alignment and safety | RLHF, DPO, preference optimization | `/references/alignment.md` | ## Core Principles 1. **Parameter Efficiency** - Update small subset of parameters 2. **Task Adaptation** - Specialize model for specific use case 3. **Data Quality** - High-quality training data is critical 4. **Evaluation** - Rigorous testing on held-out data 5. **Monitoring** - Track metrics to prevent degradation ## Fine-Tuning Methods ### LoRA (Low-Rank Adaptation) Inject trainable low-rank matrices into model layers. **Advantages:** - 0.1-1% of parameters trainable - Fast training - Mult
- Overview
- Quick Reference
- Core Principles
- Fine-Tuning Methods
- LoRA (Low-Rank Adaptation)
- QLoRA (Quantized LoRA)
- Full Fine-Tuning
- Training Process
- 1. Data Preparation
- 2. Model Selection
- 3. Training
- 4. Evaluation
- Using the Reference Files
- Best Practices
What does the llm-fine-tuning skill do?
Fine-tune large language models efficiently using LoRA, QLoRA, and PEFT methods. Use for domain adaptation, instruction tuning, task-specific optimization, and parameter-efficient training of LLMs.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill llm-fine-tuning-jh9282026-manus --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.