| # SoM-LLaVA Model Card | |
| LLaVA-v1.5 mixed trained with SoM style data (QA+listing). | |
| The model can understand tag-style visual prompts on the image (e.g., what is the object tagged with id 9?), also gained improved performance on MLLM benchmarks (POPE, MME, SEED, MM-Vet, LLav-wild), even when the input testing images has no tags. | |
| **For more information about SoM-LLaVA, check our [github page](https://github.com/zzxslp/SoM-LLaVA) and [paper](https://arxiv.org/abs/2404.16375)!** | |
| ## Getting Started | |
| This model should be used in the [official LLaVA repo](https://github.com/haotian-liu/LLaVA) for training and evalution. | |
| If you would like to load the model in HF style, check the converted model weights: [[SoM-LLaVA-v1.5-13B-HF](https://huggingface.co/zzxslp/som-llava-v1.5-13b-hf)] | |
| ## Citation | |
| If you find our data or model useful for your research and applications, please cite our paper: | |
| ``` | |
| @article{yan2024list, | |
| title={List Items One by One: A New Data Source and Learning Paradigm for Multimodal LLMs}, | |
| author={Yan, An and Yang, Zhengyuan and Wu, Junda and Zhu, Wanrong and Yang, Jianwei and Li, Linjie and Lin, Kevin and Wang, Jianfeng and McAuley, Julian and Gao, Jianfeng and others}, | |
| journal={arXiv preprint arXiv:2404.16375}, | |
| year={2024} | |
| } | |
| ``` |