Tinyllava: A Framework Of Small-scale Large Multimodal Models | Awesome LLM Papers Add your paper to Awesome LLM Papers

Tinyllava: A Framework Of Small-scale Large Multimodal Models

Baichuan Zhou, Ying Hu, Xi Weng, Junlong Jia, Jie Luo, Xien Liu, Ji Wu, Lei Huang . No Venue 2024

[Paper]   Search on Google Scholar   Search on Semantic Scholar
Compositional Generalization Image Text Integration Interdisciplinary Approaches Multimodal Semantic Representation Tools Training Techniques Visual Contextualization

We present the TinyLLaVA framework that provides a unified perspective in designing and analyzing the small-scale Large Multimodal Models (LMMs). We empirically study the effects of different vision encoders, connection modules, language models, training data and training recipes. Our extensive experiments showed that better quality of data combined with better training recipes, smaller LMMs can consistently achieve on-par performances compared to bigger LMMs. Under our framework, we train a family of small-scale LMMs. Our best model, TinyLLaVA-3.1B, achieves better overall performance against existing 7B models such as LLaVA-1.5 and Qwen-VL. We hope our findings can serve as baselines for future research in terms of data scaling, training setups and model selections. Our model weights and codes will be made public.

Similar Work