The salient multimodal capabilities and interactive experience of GPT-4o highlight its critical role in practical applications, yet it lacks a high-performing open-source counterpart. In this paper, we introduce Baichuan-omni, the first open-source 7B Multimodal Large Language Model (MLLM) adept at concurrently processing and analyzing modalities of image, video, audio, and text, while delivering an advanced multimodal interactive experience and strong performance. We propose an effective multimodal training schema starting with 7B model and proceeding through two stages of multimodal alignment and multitask fine-tuning across audio, image, video, and text modal. This approach equips the language model with the ability to handle visual and audio data effectively. Demonstrating strong performance across various omni-modal and multimodal benchmarks, we aim for this contribution to serve as a competitive baseline for the open-source community in advancing multimodal understanding and real-time interaction.
@article{arxiv.2410.08565,
title = {Baichuan-Omni Technical Report},
author = {Yadong Li and Haoze Sun and Mingan Lin and Tianpeng Li and Guosheng Dong and Tao Zhang and Bowen Ding and Wei Song and Zhenglin Cheng and Yuqi Huo and Song Chen and Xu Li and Da Pan and Shusen Zhang and Xin Wu and Zheng Liang and Jun Liu and Tao Zhang and Keer Lu and Yaqi Zhao and Yanjun Shen and Fan Yang and Kaicheng Yu and Tao Lin and Jianhua Xu and Zenan Zhou and Weipeng Chen},
journal= {arXiv preprint arXiv:2410.08565},
year = {2024}
}