Is the PEFT Fine-Tuning skill free?

Yes. The skill itself is free from Orchestra-Research/AI-Research-SKILLs. SkillProof publishes the install command and an independent test verdict at no cost.

What is the PEFT Fine-Tuning SkillProof Score?

8.4/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 4/5.

How do I install PEFT Fine-Tuning?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use PEFT Fine-Tuning with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

PEFT Fine-Tuning

LoRA/QLoRA fine-tuning code for HuggingFace models with rank/alpha guidance and OOM fixes.

by Orchestra-Research · Orchestra-Research/AI-Research-SKILLs

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 8.4/10
Tested: Jul 14, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · fee4108

The skill's QLoRA example lists all seven Llama-3.1 linear layers (q/k/v/o_proj plus gate/up/down_proj) as LoRA targets and pairs them with a rank/alpha table and a GPU-memory benchmark table (60GB full FT vs 18GB LoRA vs 6GB QLoRA); a memory-only baseline answer for the same request produced a plausible but thinner config that only targeted q_proj/v_proj and cited no numbers.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 7/10
Docs & honesty 4/5

What PEFT Fine-Tuning does

Generates HuggingFace PEFT code for LoRA and QLoRA fine-tuning of 7B-70B language models, including rank/alpha selection tables, architecture-specific target-module lists, and CUDA OOM troubleshooting. Triggers on requests to fine-tune large models under GPU memory constraints, train adapters instead of full models, or serve multiple task-specific adapters from one base model.

How to install PEFT Fine-Tuning

git clone https://github.com/Orchestra-Research/AI-Research-SKILLs
cd AI-Research-SKILLs
mkdir -p ~/.claude/skills
cp -r 03-fine-tuning/peft ~/.claude/skills/peft-fine-tuning

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger PEFT Fine-Tuning

/peft-fine-tuning LoRA/QLoRA fine-tuning code for HuggingFace models with rank/alpha guidance and OOM fixes.

It also activates on plain-language prompts like these:

Fine-tune Llama 3.1 with LoRA using PEFT
Set up QLoRA target modules for my model
Configure PEFT LoRA for parameter-efficient fine-tuning

Frequently asked questions

Is the PEFT Fine-Tuning skill free?: Yes. The skill itself is free from Orchestra-Research/AI-Research-SKILLs. SkillProof publishes the install command and an independent test verdict at no cost.
Does PEFT Fine-Tuning work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 14, 2026. Verdict: Tested · Works. The skill's QLoRA example lists all seven Llama-3.1 linear layers (q/k/v/o_proj plus gate/up/down_proj) as LoRA targets and pairs them with a rank/alpha table and a GPU-memory benchmark table (60GB full FT vs 18GB LoRA vs 6GB QLoRA); a memory-only baseline answer for the same request produced a plausible but thinner config that only targeted q_proj/v_proj and cited no numbers.
What is the PEFT Fine-Tuning SkillProof Score?: 8.4/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 4/5.
How do I install PEFT Fine-Tuning?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use PEFT Fine-Tuning with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.