5,536,768 AI resources indexedWorking toward the world’s largest AI resource index.

PDF

SPHINX-X: Scaling Data and Parameters for a Family of Multi-modal Large Language Models

Research paper by Peng Gao and collaborators. Published 2024-02-08. Topics: SPHINX-X, Multimodality Large Language Model, MLLM, visual encoders, skip tokens.

Resource information

Authors
Dongyang Liu, Renrui Zhang, Longtian Qiu, Siyuan Huang, Weifeng Lin, Shitian Zhao, Shijie Geng, Ziyi Lin, Peng Jin, Kaipeng Zhang, Wenqi Shao, Chao Xu, Conghui He, Junjun He, Hao Shao, Pan Lu, Hongsheng Li, Yu Qiao, Peng Gao
Research area
Computer vision
Application domain
General AI research
AI methods
Large language models
Research topics
cs.CV, cs.AI, cs.CL, cs.LG
arXiv record date
2025-03-21
Publication date
2024-02-08
Publication
arXiv
Upstream last modified
Mar 24, 2025
Last record update
Nov 3, 2026

Abstract

We propose SPHINX-X, an extensive Multimodality Large Language Model (MLLM) series developed upon SPHINX. To improve the architecture and training efficiency, we modify the SPHINX framework by removing redundant visual encoders, bypassing fully-padded sub-images with skip tokens, and simplifying multi-stage training into a one-stage all-in-one paradigm. To fully unleash the potential of MLLMs, we assemble a comprehensive multi-domain and multimodal dataset covering publicly available resources in language, vision, and vision-language tasks. We further enrich this collection with our curated OCR intensive and Set-of-Mark datasets, extending the diversity and generality. By training over different base LLMs including TinyLlama1.1B, InternLM2-7B, LLaMA2-13B, and Mixtral8x7B, we obtain a spectrum of MLLMs that vary in parameter size and multilingual capabilities. Comprehensive benchmarking reveals a strong correlation between the multi-modal performance with the data and parameter scales. Code and models are released at https://github.com/Alpha-VLLM/LLaMA2-Accessory