← All projects
Training & fine-tuning

LMFlow

A toolkit for fine-tuning large AI language models on your own data and then running them.

Research-backedNew this week

What it does

LMFlow is a toolbox for fine-tuning large language models, which means teaching an existing AI model new skills or knowledge using your own examples. It supports full training as well as lighter methods such as LoRA and LISA that need less graphics memory.

It also covers running the tuned model, deploying it and testing it. The team has released tuned models of its own, and its makers say the project won a best demo paper award at the NAACL 2024 conference.

The makers note it is tested on Linux, and other systems may run into errors.

Who it's for

Researchers and engineers who want to customise open AI language models.

Can I use it without coding?

Developers only. Setup uses Python environments and command-line scripts. New to this? Start here.

Can I run it?

Cost
FreeNothing to pay or sign up for.
Runs on
Linux
Computer
Works best on a powerful computer or one with a graphics card (GPU)
Privacy
Runs on your own device: your data stays with you
API key
Not needed

Try it

Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?

Before you install

  • Only download from the official GitHub page. Copies with similar names exist for many popular projects.
  • License (Apache-2.0): Permissive: free to use, change and share, including for business.
  • More on staying safe

Where people are talking about it