# fine-tuning-llama-factory

Guides fine-tuning workflows with LLaMA-Factory, covering no-code WebUI setups and QLoRA quantization. Useful when training open-source models like Llama, Qwen, or Gemma.

- skill · `type=skill` · Claude Code · 62 installs
- Author: Orchestra Research
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/davila7/claude-code-templates/tree/HEAD/cli-tool/components/skills/ai-research/fine-tuning-llama-factory
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/skills/fine-tuning-llama-factory

## What it does

This skill supplies Claude Code with reference guides for training language and multimodal models via LLaMA-Factory. It covers over 100 architectures. You can ask the assistant to configure QLoRA from 2-bit to 8-bit precision or launch the no-code WebUI.

The skill organizes documentation inside a `references/` folder with dedicated files for onboarding, advanced configurations, and image processing. The assistant inspects these files directly to extract code snippets or debug configurations. Running LLaMA-Factory requires dependencies such as `torch`, `peft`, and `transformers` in your environment.

## Install

### Claude Code (native platform)

1. **claude-code-templates**
```bash
npx claude-code-templates@latest --skill ai-research/fine-tuning-llama-factory
```

2. **Skills CLI (Vercel)**
```bash
npx skills add davila7/claude-code-templates --skill fine-tuning-llama-factory -a claude-code
```

3. **Manually: put the files in place**
- File: `~/.claude/skills/fine-tuning-llama-factory/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/fine-tuning-llama-factory/

### Codex

**Manually: put the files in place**
- File: `.agents/skills/fine-tuning-llama-factory/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

**Manually: put the files in place**
- File: `.cursor/skills/fine-tuning-llama-factory/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install davila7/claude-code-templates fine-tuning-llama-factory
```

2. **Manually: put the files in place**
- File: `.github/skills/fine-tuning-llama-factory/SKILL.md`

### Gemini CLI

**Platform CLI**
```bash
gemini skills install https://github.com/davila7/claude-code-templates --path cli-tool/components/skills/ai-research/fine-tuning-llama-factory
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/fine-tuning-llama-factory/SKILL.md` — The legacy .windsurf/skills/ path still works

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/davila7/claude-code-templates/tree/HEAD/cli-tool/components/skills/ai-research/fine-tuning-llama-factory

## When to use it
- Configure model fine-tuning through the no-code WebUI
- Set up QLoRA with 2-bit to 8-bit quantization
- Prepare multimodal training for Llama, Qwen, or Gemma models
- Look up configuration parameters for `peft` and `accelerate`

## Example prompts
- Help me configure 4-bit QLoRA for fine-tuning a Qwen model in LLaMA-Factory
- How do I launch the LLaMA-Factory no-code WebUI for training?
- Check advanced.md for multimodal fine-tuning parameters in LLaMA-Factory

## Similar
- [skill-creator](https://affpapa.org/en/nevibecode/skills/skill-creator.md) — skill · 414180 installs
- [writing-for-agents](https://affpapa.org/en/nevibecode/skills/writing-for-agents.md) — skill · 466719 installs
- [media-use](https://affpapa.org/en/nevibecode/skills/media-use.md) — skill · 1100000 installs
- [mcp-builder](https://affpapa.org/en/nevibecode/skills/mcp-builder.md) — skill · 130949 installs
- [subagent-driven-development](https://affpapa.org/en/nevibecode/skills/subagent-driven-development.md) — skill · 237746 installs
- [orchestration](https://affpapa.org/en/nevibecode/skills/orchestration.md) — skill · 350300 installs

From the same set: [davila7/claude-code-templates](https://affpapa.org/en/nevibecode/by/davila7/claude-code-templates.md) — 804 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md