← Back to List
⚠
Notice:This resource is provided by a third-party author. Please review the code with AI tools or manually before use to ensure security and compatibility.
Pythonverl-project/verl-omni

verl-omni

Multimodal RL training framework for diffusion & omni models

72.9/100
★ 585Forks: 82
View on GitHub →Homepage →
Loading report...

Similar Projects

VLM-R1

72

Solve Visual Understanding with Reinforced VLMs

Python★ 6.0K

ART

91

Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!

Python★ 10.5K

Relax

69

An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale

Python★ 504

LlamaFactory

92

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

Python★ 73.3K
← Back to List