home/categories/llm-ai/atrawog-bazzite-ai-plugins-bazzite-ai-jupyter-skills-peft-skill-md

llm-aidata-ai

peft

Name: peft
Author: atrawog

Parameter-efficient fine-tuning with LoRA and Unsloth. Covers LoraConfig, target module selection, QLoRA for 4-bit training, adapter merging, and Unsloth optimizations for 2x faster training.

查看源碼 llm-ai

maintainer

atrawog

更新於 1/12/2026

星標

分支

quick start

Installation and usage

Parameter-efficient fine-tuning with LoRA and Unsloth. Covers LoraConfig, target module selection, QLoRA for 4-bit training, adapter merging, and Unsloth optimizations for 2x faster training.

安裝

$ install --globalskills.sh

使用

安裝後，您可以通過在終端運行以下命令來使用此技能：

skills use peft