Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
orchestra-research avatar

Llama Factory

  • 396 installs
  • 11.2k repo stars
  • Updated June 16, 2026
  • orchestra-research/ai-research-skills

llama-factory is an agent skill that guides LLaMA-Factory fine-tuning and serving workflows—LoRA, RLHF/DPO/KTO trainers, Web UI, and vLLM inference—for developers who adapt open LLMs on GPU or NPU hardware.

About

llama-factory is an agent-assisted workflow skill from orchestra-research/ai-research-skills built on LLaMA-Factory documentation spanning installation, LoRA fine-tuning, weight merging, and chat inference. It references a 3-step GPT-OSS LoRA path requiring VRAM above 44 GB on a single GPU with multi-GPU support, plus advanced topics across 14 documented pages including quantization visuals and Web UI screenshots. Developers reach for llama-factory when standing up preference optimization (RLHF, DPO, KTO), merging adapters, or serving tuned models through vLLM or NPU backends. The skill translates LLaMA-Factory CLI and UI options into agent-ready setup sequences for open-weight model customization.

  • Covers GPT-OSS LoRA fine-tuning with install, single-GPU train (>44 GB VRAM), merge, and Web UI paths
  • Documents trainer modes: pre-training, SFT, RLHF (reward model, PPO), DPO, and KTO
  • Includes Ascend NPU inference setup with vLLM-Ascend and Web UI chat using vLLM engine
  • References quantization and Web UI screenshots from official LLaMA-Factory Read the Docs structure

Llama Factory by the numbers

  • 396 all-time installs (skills.sh)
  • +35 installs in the week ending Jul 18, 2026 (Skillselion tracking)
  • Ranked #507 of 2,066 Data Science & ML skills by installs in the Skillselion catalog
  • Security screen: MEDIUM risk (skills.sh audit)
  • Data as of Jul 28, 2026 (Skillselion catalog sync)
npx skills add https://github.com/orchestra-research/ai-research-skills --skill llama-factory

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs396
repo stars11.2k
Security audit3 / 3 scanners passed
Last updatedJune 16, 2026
Repositoryorchestra-research/ai-research-skills

How do you fine-tune open LLMs with LLaMA-Factory?

Fine-tune and serve open LLMs with LLaMA-Factory workflows—LoRA, RLHF/DPO/KTO trainers, Web UI, and NPU/vLLM inference—from agent-assisted setup.

Who is it for?

ML engineers fine-tuning open LLMs who want LoRA, preference trainers, and vLLM/NPU serving in one LLaMA-Factory workflow.

Skip if: Teams training entirely custom architectures outside Hugging Face–compatible open LLM stacks or without GPU/NPU resources.

When should I use this skill?

An agent must configure LLaMA-Factory for LoRA, RLHF, DPO, KTO training, weight merging, or vLLM/NPU inference.

What you get

Trained LoRA adapters, merged full weights, configured Web UI jobs, and a serving-ready open LLM checkpoint.

  • LoRA adapter checkpoint
  • Merged model weights
  • Inference-ready served model

By the numbers

  • Documents a 3-step GPT-OSS LoRA fine-tuning workflow
  • References 14 advanced documentation pages in LLaMA-Factory

Files

SKILL.mdMarkdownGitHub ↗

Llama-Factory Skill

Comprehensive assistance with llama-factory development, generated from official documentation.

When to Use This Skill

This skill should be triggered when:

  • Working with llama-factory
  • Asking about llama-factory features or APIs
  • Implementing llama-factory solutions
  • Debugging llama-factory code
  • Learning llama-factory best practices

Quick Reference

Common Patterns

Quick reference patterns will be added as you use the skill.

Reference Files

This skill includes comprehensive documentation in references/:

  • _images.md - Images documentation
  • advanced.md - Advanced documentation
  • getting_started.md - Getting Started documentation
  • other.md - Other documentation

Use view to read specific reference files when detailed information is needed.

Working with This Skill

For Beginners

Start with the getting_started or tutorials reference files for foundational concepts.

For Specific Features

Use the appropriate category reference file (api, guides, etc.) for detailed information.

For Code Examples

The quick reference section above contains common patterns extracted from the official docs.

Resources

references/

Organized documentation extracted from official sources. These files contain:

  • Detailed explanations
  • Code examples with language annotations
  • Links to original documentation
  • Table of contents for quick navigation

scripts/

Add helper scripts here for common automation tasks.

assets/

Add templates, boilerplate, or example projects here.

Notes

  • This skill was automatically generated from official documentation
  • Reference files preserve the structure and examples from source docs
  • Code examples include language detection for better syntax highlighting
  • Quick reference patterns are extracted from common usage examples in the docs

Updating

To refresh this skill with updated documentation: 1. Re-run the scraper with the same configuration 2. The skill will be rebuilt with the latest information

Related skills

How it compares

Choose llama-factory for unified open-LLM fine-tune-and-serve UX; use simpo-training when the job is SimPO-specific dataset schema prep only.

FAQ

Which trainers does llama-factory support?

llama-factory documents LoRA fine-tuning plus RLHF, DPO, and KTO preference trainers within LLaMA-Factory. Workflows include installing dependencies, launching training, merging LoRA weights, and chatting with the tuned model.

What GPU memory does GPT-OSS LoRA need in LLaMA-Factory?

llama-factory cites LLaMA-Factory guidance that GPT-OSS LoRA fine-tuning on a single GPU requires VRAM greater than 44 GB, with multi-GPU training supported for larger runs.

Is Llama Factory safe to install?

skills.sh reports 3 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.

Data Science & MLllmautomation

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.