Quick Start To use this model, follow these three steps: 1. Clone verl agent. 2. Set actor rollout ref.model.path to your local path, e.g. your/own/path/GiGPO Qwen2.5 7B Instruct ALFWorld . 3. Ensure trainer.val before train=True , so evaluation runs before training. For more details, please refer to the verl agent. Notes GiGPO Qwen2.5 7B Instruct WebShop is trained using GiGPO and the following prompt:
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy