peft-fine-tuning

SKILL.md

Fine-tune LLMs by training <1% of parameters using LoRA, QLoRA, and 25+ adapter methods.

| Rank | Trainable Params | Memory | Quality | Use Case |

| 4 | 3M | Minimal | Lower | Simple tasks, prototyping | | 8 | 7M | Low | Good | Recommended starting point | | 16 | 14M | Medium | Better | General fine-tuning | | 32 | 27M | Higher | High | Complex tasks | | 64 | 54M | High | Highest | Domain adaptation, 70B models |

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. Source: orchestra-research/ai-research-skills.

View raw