| license: mit | |
| datasets: | |
| - YanqiDai/MMRole_dataset | |
| language: | |
| - en | |
| - zh | |
| base_model: Qwen/Qwen-VL-Chat | |
| The model weights of the reward model in *MMRole*, A Comprehensive Framework for Developing and Evaluating Multimodal Role-Playing Agents. | |
| Please refer to our paper (https://arxiv.org/abs/2408.04203) and code (https://github.com/YanqiDai/MMRole) for more details. |