Most of the existing multi-modal models, hindered by their incapacity to adeptly manage interleaved image-and-text inputs in multi-image, multi-round dialogues, face substantial constraints in resource allocation for training and data accessibility, impacting their adaptability and scalability across varied interaction realms. To address this, we present the DeepSpeed-VisualChat framework, designed to optimize Large Language Models (LLMs) by incorporating multi-modal capabilities, with a focus on enhancing the proficiency of Large Vision and Language Models in handling interleaved inputs. Our framework is notable for (1) its open-source support for multi-round and multi-image dialogues, (2) introducing an innovative multi-modal causal attention mechanism, and (3) utilizing data blending techniques on existing datasets to assure seamless interactions in multi-round, multi-image conversations. Compared to existing frameworks, DeepSpeed-VisualChat shows superior scalability up to 70B parameter language model size, representing a significant advancement in multi-modal language models and setting a solid foundation for future explorations.

翻译：大多数现有多模态模型受限于无法有效处理多图像、多轮对话中的交错图文输入，在训练资源分配和数据可用性方面面临显著约束，进而影响其在不同交互场景中的适应性和可扩展性。为解决这一问题，我们提出DeepSpeed-VisualChat框架，该框架通过融合多模态能力优化大语言模型（LLMs），重点提升大型视觉语言模型处理交错输入的能力。本框架具有以下显著特征：（1）开源支持多轮多图像对话；（2）引入创新的多模态因果注意力机制；（3）利用现有数据集的数据混合技术保障多轮多图像对话的无缝交互。与现有框架相比，DeepSpeed-VisualChat在高达700亿参数的语言模型规模上展现出优越的可扩展性，标志着多模态语言模型的重大进展，为未来探索奠定了坚实基础。