DaoyuanLi2816/mini-verl
verl for a single consumer GPU. PPO, GRPO and on-policy distillation on NVIDIA GPUs.
- Stars
- 307
- Forks
- 75
- Open issues
- 1
- Last push
- 1mo ago
About mini-verl
mini-verl is a free, open-source machine learning tool by DaoyuanLi2816, written mainly in Python. verl for a single consumer GPU. PPO, GRPO and on-policy distillation on NVIDIA GPUs. It has 307 GitHub stars and 75 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
- 307
- Last update
- 1mo ago
- Runs on Mac
- Not stated
- GPU
- Not stated
- Paid API key
- Not required
- Self-hostable
- Yes
Similar free tools
verl24k stars · verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework
MetaClaw3.5k stars · 🦞 Just talk to your agent — it learns and EVOLVES 🧬.
peft22k stars · 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
safe-rlhf1.6k stars · Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback
argilla5.2k stars · Argilla is a collaboration tool for AI engineers and domain experts to build high-quality datasets
mini-verl FAQ
Is mini-verl free?
Yes. mini-verl is open source and free to use. It's released under the Apache-2.0 license, a standard open-source license.
Does mini-verl run on a Mac?
The project doesn't say. Check its installation guide before you start.
Does mini-verl need a GPU?
The project doesn't state hardware needs. AI models generally run much faster with a GPU.
Is mini-verl still maintained?
It was last updated 1mo ago. Check recent issues on GitHub to judge how active it is.
What are alternatives to mini-verl?
Similar free, open-source tools include verl, MetaClaw, peft, safe-rlhf.