Baichuan-Omni Technical Report

Yadong Li, Alvin Sun, lma, Tianpeng Li, guosheng dong, Tao Zhang, Ding Bowen, Wei Song (SII), Zhenglin Cheng, Yuqi Huo, Song Chen, Xu Li, Da Pan, zss, Xin Wu, Zheng Liang, Jun Liu, Tao Zhang, Keer Lu, Yaqi Zhao, Yanjun Sheng, FanYang, Kaicheng Yu, Tao LIN, jianhua Xu, Zenan Zhou, Wei-Peng Chen

Baichuan-Omni Technical Report: 79 upvotes on Hugging Face Daily Papers, #1 of 20 papers on 2024-10-14. Day-by-day upvote history. It lost 10 votes when the Hub removed votes in bulk.

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.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.