近日，我国知名人工智能公司零一万物正式开源了其Yi系列模型家族的新成员——Yi Vision Language（Yi-VL）多模态语言大模型。该模型基于Yi语言模型开发，包含Yi-VL-34B和Yi-VL-6B两个版本，以其卓越的图文理解和对话生成能力，在英文数据集MMMU和中文数据集CMMMU上取得了领先成绩。
Yi-VL模型的开源，标志着我国在人工智能领域再次取得了重要突破。这一模型不仅展示了我国在复杂跨学科任务上的强大实力，也为全球人工智能研究者和开发者提供了一个宝贵的资源和工具。
据悉，Yi-VL模型在多个方面都表现出了出色的性能，包括图文理解和对话生成等。这使得它可以在很多领域得到应用，如智能客服、智能问答、智能推荐等。未来，随着Yi-VL模型的进一步优化和升级，我们有理由相信，它将在人工智能领域发挥更大的作用。
英文翻译：
Recently, the well-known Chinese artificial intelligence company Zero One Wuqi officially opened source its new member of Yi series model family – Yi Vision Language (Yi-VL) multimodal language large model. The model is based on Yi language model and includes two versions, Yi-VL-34B and Yi-VL-6B. With its excellent image-text understanding and dialogue generation capabilities, the Yi-VL model has achieved leading results on English dataset MMMU and Chinese dataset CMMMU.
The opening source of Yi-VL model marks another important breakthrough of China in the field of artificial intelligence. This model not only shows China’s strong strength in complex interdisciplinary tasks, but also provides a valuable resource and tool for global artificial intelligence researchers and developers.
It is reported that Yi-VL model has shown excellent performance in many aspects, including image-text understanding and dialogue generation. This enables it to be applied in many fields, such as intelligent customer service, intelligent question and answer, intelligent recommendation, etc. In the future, with the further optimization and upgrading of Yi-VL model, we have reason to believe that it will play a greater role in the field of artificial intelligence.
【来源】https://www.jiqizhixin.com/articles/2024-01-22-10
Views: 0