Use Cases

Distributed Rlhf On Multi-gpu Clusters Up To 70b+ Params

1 project

Lora-based Parameter-efficient Rlhf

1 project

Reproducing Online Iterative Rlhf Alignment From Open Data

1 project

Research On Rlhf Vs Offline Alignment Methods

1 project

Rlhf/dpo Fine-tuning Of Large Models

1 project

Train Llms With Rlhf/ppo/grpo At Scale

1 project

Vision-language Model Rlhf With Image Inputs

1 project