1.5~20 times higher throughput, ByteBeanBag Big Model team and HKU release and open source new RLHF framework

ByteDanceBean bag large modelTeams andThe University of Hong KongPublicizing the results of joint research -- HybridFlow.

The official claim that HybridFlow (open source project name: veRL) is a flexible and efficient large model RL training framework , compatible with a variety of training and inference frameworks , support for flexible model deployment and a variety of RL algorithm implementation .

The framework adopts a hybrid programming model that combines the flexibility of Single-Controller and the efficiency of Multi-Controller to better implement and execute multiple RL algorithms, significantly improve training throughput, and reduce development and maintenance complexity.

1.5~20 times higher throughput, ByteBeanBag Big Model team and HKU release and open source new RLHF framework
▲ Flow of one iteration of 3D-HybridEngine (Hybrid Technology for Training Reasoning)

Experimental results show that HybridFlow, under various model sizes and RL algorithms, the1.5x to 20x increase in training throughput compared to other frameworks.

The paper has now been accepted by EuroSys 2025 and the code repository has been made available to the public with relevant links below:

  • Link to paper: https://arxiv.org/abs/2409.19256
  • Link to code: https://github.com/volcengine/veRL
statement:The content is collected from various media platforms such as public websites. If the included content infringes on your rights, please contact us by email and we will deal with it as soon as possible.
Information

West China Hospital and Huawei Data Storage Release "Huaxi HCM" Medical Model: Integrating More Than 10 Types of General Models and More Than 50 Types of Pendant Domain Models

2024-11-4 1:25:03

Information

Researchers bypassed the GPT-4o model security fence and successfully programmed it with a vulnerability using "hexadecimal strings".

2024-11-4 21:05:55

Search