Baichuan-Omni Technical Report

TL;DR

Baichuan-Omni is the first open-source 7B multimodal large language model capable of processing image, video, audio, and text, providing advanced multimodal interaction and strong benchmark performance.

Contribution

It introduces a novel multimodal training schema and an open-source 7B MLLM that effectively handles multiple modalities for improved multimodal understanding.

Findings

Strong performance on various benchmarks

Effective multimodal training schema

Open-source baseline for multimodal research

Abstract

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.