FreeAIRepo
Training & fine-tuning

hiyouga/EasyR1

EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL

Really freeApache-2.0Python
Open on GitHub Website
Stars
5.2k
Forks
398
Open issues
51
Last push
1mo ago

About EasyR1

EasyR1 is a free, open-source machine learning tool by hiyouga, written mainly in Python. EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL. It has 5.2k GitHub stars and 398 forks, and was last updated 1mo ago. It's released under the Apache-2.0 license, a standard open-source license.

License
Apache-2.0
Language
Python
Stars
5,206
Last update
1mo ago
Runs on Mac
Not stated
GPU
Not stated
Paid API key
Not required
Self-hostable
Yes

Similar free tools

All Training & fine-tuning tools →

EasyR1 FAQ

Is EasyR1 free?

Yes. EasyR1 is open source and free to use. It's released under the Apache-2.0 license, a standard open-source license.

Does EasyR1 run on a Mac?

The project doesn't say. Check its installation guide before you start.

Does EasyR1 need a GPU?

The project doesn't state hardware needs. AI models generally run much faster with a GPU.

Is EasyR1 still maintained?

It was last updated 1mo ago. Check recent issues on GitHub to judge how active it is.

What are alternatives to EasyR1?

Similar free, open-source tools include LlamaFactory, argilla, MetaClaw, ludwig.

Related topics

aigptllmnlpreinforcement-learningrldeepseekqwen