peft
peft（Orchestra-Research/AI-Research-SKILLs）：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.
GitHub 星
13k
评分
—
综合分
41.2863
来源: Orchestra-Research/AI-Research-SKILLs · 03-fine-tuning/peft/SKILL.md
npx skills add Orchestra-Research/AI-Research-SKILLs --skill peft
相关技能
| 01 | axolotlOrchestra-Research/AI-Research-SKILLs | 科学 | 13k | 4128.6 |
↗ | Orchestra-Research/AI-Research-SKILLs · 科学 · 4128.6 |
| 02 | neuroskill-bciNousResearch/hermes-agent | 科学 | 255k | 5406.3 |
↗ | NousResearch/hermes-agent · 科学 · 5406.3 |
| 03 | aeonK-Dense-AI/scientific-agent-skills | 科学 | 52k | 4720.1 |
↗ | K-Dense-AI/scientific-agent-skills · 科学 · 4720.1 |
| 04 | anndataK-Dense-AI/scientific-agent-skills | 科学 | 52k | 4720.1 |
↗ | K-Dense-AI/scientific-agent-skills · 科学 · 4720.1 |
| 05 | powerbi-modelinggithub/awesome-copilot | 科学 | 40k | 4603.6 |
↗ | github/awesome-copilot · 科学 · 4603.6 |