In the realm of large multi-modal models (LMMs), efficient modality alignment
is crucial yet often constrained by the scarcity of high-quality image-text
data. To address this bottleneck, we introduce the ShareGPT4V dataset, a
pioneering large-scale resource featuring 1.2 million highly descriptive
captions, which surpasses existing datasets in diversity and information
content, covering world knowledge, object properties, spatial relationships,
and aesthetic evaluations. Specifically, ShareGPT4V originates from a curated
100K high-quality captions collected from advanced GPT4-Vision and has been
expanded to 1.2M with a superb caption model trained on this subset. ShareGPT4V
first demonstrates its effectiveness for the Supervised Fine-Tuning (SFT)
phase, by substituting an equivalent quantity of detailed captions in existing
SFT datasets with a subset of our high-quality captions, significantly
enhancing the LMMs like LLaVA-7B, LLaVA-1.5-13B, and Qwen-VL-Chat-7B on the MME
and MMBench benchmarks, with respective gains of 222.8/22.0/22.3 and
2.7/1.3/1.5. We further incorporate ShareGPT4V data into both the pre-training
and SFT phases, obtaining ShareGPT4V-7B, a superior LMM based on a simple
architecture that has remarkable performance across a majority of the
multi-modal benchmarks. This project is available at
this https URL to serve as a pivotal resource for advancing the
LMMs community.

在大型多模态模型领域，高效的模态对齐对于提升模型性能至关重要，但由于高质量图文数据的稀缺性而受限。为了解决这一瓶颈，我们介绍了 ShareGPT4V 数据集，这是一个包含 120 万条高度描述性的标题的创新大规模资源，其在多样性和信息内容上超越了现有数据集，涵盖了世界知识、对象属性、空间关系和美学评估。具体来说，ShareGPT4V 源于 Advanced GPT4-Vision 收集的 10 万个高质量标题，通过在该子集上进行训练，将其扩展到 120 万个。ShareGPT4V 首先在监督微调（SFT）阶段展示了其有效性，通过用高质量标题子集替换现有 SFT 数据集中等量的详细标题，显著提升了 MME 和 MMBench 基准测试中的 LLaVA-7B、LLaVA-1.5-13B 和 Qwen-VL-Chat-7B 等 LMMs 模型，分别增益为 222.8/22.0/22.3 和 2.7/1.3/1.5。我们进一步将 ShareGPT4V 数据集融入到预训练和 SFT 阶段，获得了 ShareGPT4V-7B，一个基于简单架构的优秀 LMM 模型，其在大多数多模态基准测试上表现出色。该项目可通过此 https 链接获得，以服务于 LMMs 社区的进一步发展。