近日，我国知名技术团队零一万物发布了一款名为Yi-VL的多模态大模型，并宣布将其面向全球开源。这款模型基于Yi语言模型开发，包含Yi-VL-34B和Yi-VL-6B两个版本。据悉，Yi-VL模型在英文数据集MMMU和中文数据集CMMMU上取得了领先成绩，展示了其在复杂跨学科任务上的强大实力。
Yi-VL模型以其卓越的图文理解和对话生成能力受到了广泛关注。该模型可以广泛应用于人工智能领域，如智能客服、智能问答、自然语言处理等。此次开源也意味着全球开发者都可以免费使用并进一步研究和改进这款模型，有望推动人工智能领域的发展。
Title: ZeroOne releases Yi-VL multimodal large model
Keywords: Multimodal large model, Yi-VL, Open source
News content:
Recently, a well-known technical team in China, ZeroOne, has released a multimodal large model called Yi-VL and announced that it will be open-sourced to the global community. This model is based on the Yi language model and includes two versions, Yi-VL-34B and Yi-VL-6B. It has achieved leading results on the English dataset MMMU and the Chinese dataset CMMMU, demonstrating its strong capabilities in complex interdisciplinary tasks.
The Yi-VL model has received widespread attention for its excellent image-text understanding and dialogue generation capabilities. The model can be widely applied in the field of artificial intelligence, such as intelligent customer service, intelligent question answering, natural language processing, etc. This open-source release means that developers worldwide can use this model for free and further study and improve it, which is expected to promote the development of the artificial intelligence field.
【来源】https://www.jiqizhixin.com/articles/2024-01-22-10
Views: 1