零一万物Yi系列模型家族近日迎来新成员Yi Vision Language（Yi-VL）多模态语言大模型，该模型已面向全球开源。Yi-VL模型基于Yi语言模型开发，包括Yi-VL-34B和Yi-VL-6B两个版本。其在英文数据集MMMU和中文数据集CMMMU上表现卓越，成功领跑两大榜单。
Yi-VL模型具备卓越的图文理解和对话生成能力，展示了在复杂跨学科任务上的强大实力。此次开源举措将有助于推动我国人工智能技术的发展，促进全球范围内的技术交流与合作。
英文翻译：
Zero One Wu Ming’s Yi-VL multimodal large model opensource, leading global ranking
Keywords: Yi-VL multimodal large model, opensource, global ranking
News Content:
Zero One Wu Ming’s Yi series model family has recently welcomed a new member, the Yi Vision Language (Yi-VL) multimodal language large model, which has been opened up to the global community. The Yi-VL model is developed based on the Yi language model, including two versions: Yi-VL-34B and Yi-VL-6B. With excellent image-text understanding and dialogue generation capabilities, the Yi-VL model has demonstrated strong performance on two major global ranking lists, successfully leading the MMMU English dataset and CMMMU Chinese dataset.
The open-source initiative of the Yi-VL model will contribute to the development of artificial intelligence technology in China and promote technical exchanges and cooperation on a global scale.
【来源】https://www.jiqizhixin.com/articles/2024-01-22-10
Views: 1