Internlm-xcomposer-2.5: A Versatile Large Vision Language Model Supporting Long-contextual Input And Output

Zhang Pan, Dong Xiaoyi, Zang Yuhang, Cao Yuhang, Qian Rui, Chen Lin, Guo Qipeng, Duan Haodong, Wang Bin, Ouyang Linke, Zhang Songyang, Zhang Wenwei, Li Yining, Gao Yang, Sun Peng, Zhang Xinyue, Li Wei, Li Jingwen, Wang Wenhai, Yan Hang, He Conghui, Zhang Xingcheng, Chen Kai, Dai Jifeng, Qiao Yu, Lin Dahua, Wang Jiaqi. Arxiv 2024

[Paper] [Code]    
Applications Fine Tuning GPT Has Code Model Architecture Multimodal Models Reinforcement Learning

We present InternLM-XComposer-2.5 (IXC-2.5), a versatile large-vision language model that supports long-contextual input and output. IXC-2.5 excels in various text-image comprehension and composition applications, achieving GPT-4V level capabilities with merely 7B LLM backend. Trained with 24K interleaved image-text contexts, it can seamlessly extend to 96K long contexts via RoPE extrapolation. This long-context capability allows IXC-2.5 to excel in tasks requiring extensive input and output contexts. Compared to its previous 2.0 version, InternLM-XComposer-2.5 features three major upgrades in vision-language comprehension: (1) Ultra-High Resolution Understanding, (2) Fine-Grained Video Understanding, and (3) Multi-Turn Multi-Image Dialogue. In addition to comprehension, IXC-2.5 extends to two compelling applications using extra LoRA parameters for text-image composition: (1) Crafting Webpages and (2) Composing High-Quality Text-Image Articles. IXC-2.5 has been evaluated on 28 benchmarks, outperforming existing open-source state-of-the-art models on 16 benchmarks. It also surpasses or competes closely with GPT-4V and Gemini Pro on 16 key tasks. The InternLM-XComposer-2.5 is publicly available at https://github.com/InternLM/InternLM-XComposer.

Similar Work