Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Fine-tunes LLMs and trains custom models using LoRA/QLoRA adapters, JSONL training datasets, hyperparameter configuration, RLHF, DPO, and model quantization.
| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-17 | ✗→✓ | ▲ Improved | 54% | 0% |
| case-01 | ✓→✗ | ▼ Worse | 33% | 0% |
| case-18 | ✓→✓ | ＝ Same ✓ | 12% | 0% |
| case-02 | ✓→✓ | ＝ Same ✓ | 13% | 0% |
| case-03 | ✓→✓ | ＝ Same ✓ | 15% | 0% |
name: fine-tuning-expert description: > Fine-tunes LLMs and trains custom models using LoRA/QLoRA adapters, JSONL training datasets, hyperparameter configuration, RLHF, DPO, and model quantization. metadata: sources:
repo: jeffallan/claude-skills path: skills/fine-tuning-expert/SKILL.md commit: 3bf9a24b76a7c122f1fc05e83929fbc84e1c207a attribution: Jeffallan license: MIT usage: referenced
Other measured skills in the registry, with their headline benchmark lift.