ai-agent

LlamaFactory: Fine-Tune AI Models

Name: LlamaFactory: Fine-Tune AI Models
Author: hiyouga

Fine-tune 100+ AI models with LlamaFactory.

74,055 stars9,060 forksPythonGuide quality 8/10Updated 8/10/2026100% free · open source

What it does

LlamaFactory allows founders to fine-tune over 100 pre-trained AI models for their specific use cases, enabling more accurate and efficient AI-powered solutions.

When to use it

•When you need to adapt a pre-trained AI model to your specific industry or task
•When you want to improve the performance of an AI model on a custom dataset
•When you need to deploy AI models in a production environment with minimal expertise

Ready-to-paste prompt

Fine-tune a T5-base model on your custom dataset with `python train.py --model_name t5-base --dataset your_dataset --batch_size 16 --epochs 5`

Heads up: Make sure you have the correct version of Python (>=3.8) and the necessary GPU resources to run the model fine-tuning process, as specified in the README

Saves to your device

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/llamafactory && curl -fsSL https://workflowstacks.com/api/skills/llamafactory/claude-skill -o ~/.claude/skills/llamafactory/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How LlamaFactory: Fine-Tune AI Models works

Codeflow

Free to inspect

LlamaFactory: Fine-Tune AI Models is a large Python project (~55k lines across 267 code files, plus 37 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, Apache-2.0 license, has a test suite.

Size

Large codebase

~55k lines · 267 code files · ~8 h to skim

Setup

Developer setup

A real software project. Use it via its install path; don't expect to read it all.

Runs on

Python

No API keys detected

Python 100%

What happens, step by step

Fine-tune AI models easily

You give

Model data

1Install Tool

Install required packages

2Prepare Data

Prepare model data

3Fine-Tune Model

Fine-tune the model

src/llamafactory/__init__.py

4Deploy Model

Deploy the model

You get

Trained model

Where to start reading

1
README.md
Start here — what it does and how to install it
2
CLAUDE.md
The instructions the AI actually follows
3
pyproject.toml
Dependencies and the commands it exposes
4
src/llamafactory/__init__.py
Inside src/ — the main logic begins here
5
examples/README.md
A worked example — copy this to get going

What's in each folder

src/Core code — the actual logic218 files

examples/Examples you can copy107 files

docs/Documentation66 files

data/Data files35 files

requirements/Folder25 files

scripts/Helper scripts21 files

tests_v1/Folder20 files

docker/Deployment / infrastructure12 files

READMEHas testsDocumentedCI checksExamples includedApache-2.0 licenseUpdated this month