Request to add MoE-LLaVA-2.7B×4 into the MME benchmark

[LinB203]

Hi,

Thanks for the efforts in building the MME benchmark!

I request to add our MoE-LLaVA-2.7B×4 to the MME benchmark.

Title: "MoE-LLaVA: Mixture of Experts for Large Vision-Language Models" Paper: https://arxiv.org/abs/2401.15947 Code: https://github.com/PKU-YuanGroup/MoE-LLaVA Evaluation Codes: https://github.com/PKU-YuanGroup/MoE-LLaVA/blob/main/moellava/eval/model_vqa_loader.py Results:

Thank you very much!

[BradyFU]

Copy that! dear binbin : )