Xmodel-VLM: A Simple Baseline for Multimodal Vision Language Model

Wanting Xu; Yang Liu; Langping He; Xucheng Huang; Ling Jiang

返回文献探索

Paper · arXiv 2405.09215

Xmodel-VLM: A Simple Baseline for Multimodal Vision Language Model

Wanting Xu, Yang Liu, Langping He, Xucheng Huang, Ling Jiang

20 upvotesMay 15, 2024arXiv 预印本

AI 摘要

Xmodel-VLM is a lightweight multimodal vision language model developed for efficient deployment, achieving performance comparable to larger models with a 1B language model trained using the LLaVA paradigm.

multimodal vision language modelconsumer GPU serversservice costs1B-scale language modelLLaVA paradigmmodal alignmentmultimodal benchmarks

Abstract

We introduce Xmodel-VLM, a cutting-edge multimodal vision language model. It is designed for efficient deployment on consumer GPU servers. Our work directly confronts a pivotal industry issue by grappling with the prohibitive service costs that hinder the broad adoption of large-scale multimodal systems. Through rigorous training, we have developed a 1B-scale language model from the ground up, employing the LLaVA paradigm for modal alignment. The result, which we call Xmodel-VLM, is a lightweight yet powerful multimodal vision language model. Extensive testing across numerous classic multimodal benchmarks has revealed that despite its smaller size and faster execution, Xmodel-VLM delivers performance comparable to that of larger models. Our model checkpoints and code are publicly available on GitHub at https://github.com/XiaoduoAILab/XmodelVLM.