近日，我国知名人工智能公司零一万物正式开源了Yi Vision Language（Yi-VL）多模态语言大模型，面向全球用户开放。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，图文理解和对话生成能力卓越。
在英文数据集MMMU和中文数据集CMMMU上，Yi-VL模型取得了领先成绩，展现了其在复杂跨学科任务上的强大实力。此次开源，将为全球人工智能研究和应用领域带来新的突破和变革。
Yi-VL模型的发布，标志着我国在多模态大模型领域取得了重要进展。开源的背后，是我国人工智能技术的不断发展和创新。未来，Yi-VL模型将在全球范围内发挥重要作用，助力人工智能产业的繁荣和发展。
英文翻译：
Title: ZeroOne Release Yi-VL Multimodal Large Model Open Source
Keywords: Multimodal large model, open source, leading
News content:
Recently, the well-known Chinese artificial intelligence company ZeroOne has officially opened the source code of the Yi Vision Language (Yi-VL) multimodal language model to the global community. The model is based on the Yi language model and includes two versions, Yi-VL-34B and Yi-VL-6B. It has excellent visual understanding and dialogue generation capabilities.
On the English dataset MMMU and the Chinese dataset CMMMU, the Yi-VL model has achieved leading results, demonstrating its strong capabilities in complex interdisciplinary tasks. This open source will bring new breakthroughs and transformations to the global artificial intelligence research and application fields.
The release of the Yi-VL model marks an important progress in the field of multimodal large models in China. Behind the open source is the continuous development and innovation of China’s artificial intelligence technology. In the future, the Yi-VL model will play an important role globally and contribute to the prosperity and development of the artificial intelligence industry.
【来源】https://www.jiqizhixin.com/articles/2024-01-22-10
Views: 1