Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.
8.7
Rating
0
Installs
AI & LLM
Category
Excellent skill for parameter-efficient fine-tuning of LLMs. The description clearly explains when to use PEFT/LoRA/QLoRA, and SKILL.md provides comprehensive, production-ready code examples covering the full workflow from installation through training, merging, and multi-adapter serving. Task knowledge is outstanding with detailed parameter selection guidance, architecture-specific configurations, integration patterns (TRL, Axolotl, vLLM), performance benchmarks, and troubleshooting. Structure is clean with a logical flow and references to advanced-usage.md and troubleshooting.md for deeper topics. Novelty is strong—fine-tuning 70B models on consumer GPUs with <1% parameter training is a complex task requiring specialized knowledge of quantization, adapter methods, and memory optimization that would consume significant tokens for a CLI agent to discover independently. Minor improvement could include more decision-tree guidance for method selection, but overall this is a high-quality, immediately actionable skill.
davila7
Skill Author
Loading SKILL.md…
Skill Author
