Plain-AyI
← All projects
Training & fine-tuning

EasyR1

A framework for training language and vision-language AI models to reason better with reinforcement learning.

Research-backedNew this week

What it does

EasyR1 trains AI models with reinforcement learning, where a model improves by being rewarded for good answers. It's a fork of the veRL project, extended to support vision-language models that understand both images and text.

It supports models like Llama, Qwen and Qwen-VL, several popular training methods such as GRPO, and lighter LoRA training.

It needs powerful graphics cards. The README's table shows even the smallest models need at least one GPU with lots of memory.

Who it's for

AI researchers and engineers training reasoning models.

Can I use it without coding?

Developers only. It's run with Python and Docker on GPU machines. 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