TinyLLaVA: A Framework of Small-scale Large Multimodal Models
Research paper by Baichuan Zhou and collaborators. Published 2024-02-22. Topics: Small-scale Large Multimodal Models, vision encoders, connection modules, language models, training data.
Resource information
- Authors
- Baichuan Zhou, Ying Hu, Xi Weng, Junlong Jia, Jie Luo, Xien Liu, Ji Wu, Lei Huang
- Research topics
- Small-scale Large Multimodal Models, vision encoders, connection modules, language models, training data, training recipes, TinyLLaVA-3.1B, LLaVA-1.5, Qwen-VL, data scaling, model selections
- Publication date
- 2024-02-22
- Publication
- arXiv
- Last record update
- Nov 3, 2026