Plain-AyI
← All projects
Training & fine-tuning

GPT-NeoX

EleutherAI's software for training very large language models from scratch across many graphics cards.

Research-backedNew this week

What it does

GPT-NeoX is a library for training large language models, the kind of AI behind chatbots, on many GPUs (graphics cards) at once. It builds on well-known training tools from NVIDIA and Microsoft.

Its makers say it has been used by many universities, companies and labs to train dozens of models, including EleutherAI's own Pythia models. It has ready-made settings for popular model designs and can export models to the widely used Hugging Face format.

The README is clear that it is meant for training models with billions of parameters from scratch. For simply running a model, it recommends other tools.

Who it's for

Research labs and companies training their own large language models on big computing clusters.

Can I use it without coding?

Developers only. It requires programming and access to powerful GPU servers. New to this? Start here.

Can I run it?

Cost
FreeNothing to pay or sign up for.
Runs on
Server
Computer
Made for servers or data centres
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