llava-interleave-bench
收藏资源简介:
LLaVA-Interleave Bench是一个综合的多图像数据集,主要用于评估大型多模态模型在交错多图像推理能力。该数据集包含从公共数据集收集或通过GPT-4V API生成的图像,分为Split1和Split2两个部分,并包含多个JSON文件。数据集主要用于研究大型多模态模型和聊天机器人,主要用户群体为计算机视觉、自然语言处理、机器学习和人工智能领域的研究人员和爱好者。
LLaVA-Interleave Bench is a comprehensive multi-image dataset primarily utilized to evaluate the interleaved multi-image reasoning capabilities of large multimodal models. This dataset comprises images collected from public datasets or generated via the GPT-4V API, and is divided into two subsets: Split 1 and Split 2, with multiple JSON files included. It is mainly developed for research on large multimodal models and chatbots, and its primary target users are researchers and enthusiasts in the fields of computer vision, natural language processing, machine learning, and artificial intelligence.




