FreeAIRepo
Training & fine-tuning

verl-project/verl-omni

Multimodal RL training framework for diffusion & omni models

Really freeApache-2.0Python
Open on GitHub Website
Stars
1.3k
Forks
271
Open issues
104
Last push
today

About verl-omni

verl-omni is a free, open-source machine learning tool by verl-project, written mainly in Python. Multimodal RL training framework for diffusion & omni models. It has 1.3k GitHub stars and 271 forks, and was last updated today. It's released under the Apache-2.0 license, a standard open-source license.

License
Apache-2.0
Language
Python
Stars
1,332
Last update
today
Runs on Mac
Not stated
GPU
Not stated
Paid API key
Not required
Self-hostable
Not stated

Similar free tools

All Training & fine-tuning tools →

verl-omni FAQ

Is verl-omni free?

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

Does verl-omni run on a Mac?

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

Does verl-omni need a GPU?

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

Is verl-omni still maintained?

Yes. It was last updated today and has 104 open issues on GitHub.

What are alternatives to verl-omni?

Similar free, open-source tools include pytorch-image-models, safe-rlhf, Flow-Factory, MetaClaw.

Related topics

diffusion-modelsflow-matchinggrpomultimodalreinforcement-learningrlhfvllmqwen