Unsloth Fine-Tuning (Orchestra)
13,149 starsExpert guidance for fast fine-tuning with Unsloth: 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization.
- First published：2025-11-03
- data as of：
- 2026-09-30
- Licence：
- MIT
When to use it
When fine-tuning LLMs on consumer or single-GPU hardware.
Caution
Requires an NVIDIA GPU environment; Unsloth iterates fast and guidance can lag the latest release.
Install prompt
請幫我安裝「Unsloth Fine-Tuning (Orchestra)」技能：從 https://github.com/Orchestra-Research/AI-Research-SKILLs/tree/main/03-fine-tuning/unsloth（技能路徑：03-fine-tuning/unsloth/） 取得完整的技能目錄，放進我的 Agent 的技能目錄（例如專案內的 skills/ 資料夾，或該 Agent 文件指明的全域技能位置），確認裡面的 SKILL.md 存在、frontmatter 的 name 與 description 完整，然後列出這個技能宣告的腳本、外部工具與 API 需求，先不要執行任何腳本。Paste this to your agent. It deliberately contains no tool subcommands — check the tool's official docs for commands.
Compatible with