veRL is a flexible and efficient RL framework for LLMs.
Cross-referenced across 55 tracked directories
#435
Popularity Rank
2 / 55
Listed In
Growing
Adoption Stage
10/31/2024
Created
20,052
GitHub Stars
3,455
Forks
1,885
Open Issues
3/19/2026
Last Commit
Gaining traction in the ecosystem
Cross-Posting Opportunities
Could also be listed in these directories:
Score: 100/100
0 dependency vulnerabilities found
Leandro von Werra <[email protected]>
Train transformer language models with reinforcement learning.
20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.
Open-source framework for fine-tuning and evaluating LLMs. It simplifies the process of experimenting with different training configurations and makes it easy to reproduce and share results, supporting features like LoRA, QLoRA, DeepSpeed, PEFT, and multi-GPU setups.
...more