update readme

README.md

@@ -70,7 +70,8 @@ We conduct evaluation on 9 commonly-used benchmarks, including 5 academic VQA be
 
 | Models | Size | VQAv2 | GQA | SQA(IMG) | TextVQA | POPE |  MME(P) | MMB  |MMBCN  |MM-Vet|
 |:--------:|:-----:|:----:|:-------------:|:--------:|:-----:|:----:|:-------:|:-------:|:-------:|:-------:|
-| [LLaVA-v1.5-lora](https://huggingface.co/liuhaotian/llava-v1.5-7b) | 7B |79.10 | 63.00|  68.40 |58.20| 86.40 | 1476.9 | 66.10 |- |30.2|
+| [Mini-Gemini-2B](https://github.com/dvlab-research/MGM) | 2B |- | -|  56.2 |-| -|  1341 | 59.8 |- | 31.1|
+| [Bunny-v1.0-2B-zh](https://huggingface.co/BAAI/Bunny-v1_0-2B-zh) | 2B |76.6 | 59.6|  64.6 |-| 85.8 |  1300.8 | 59.1 |58.5 | 31.1|
 | **Imp-v1.5-2B-Qwen1.5** | 3B | 79.2 | 61.93 | 66.14| 54.52 | 86.74| 1304.8 | 63.83| 61.34 |33.5|
 
 ## License
@@ -88,6 +89,6 @@ If you use our model or refer our work in your studies, please cite:
   author = {Shao, Zhenwei and Ouyang, Xuecheng and Yu, Zhou and Yu, Jun},
   title = {Imp: An Emprical Study of Multimodal Small Language Models},
   year = {2024},
-  url = {https://huggingface.co/MILVLG/imp-v1-3b}
+  url = {https://huggingface.co/MILVLG/Imp-v1.5-2B-Qwen1.5}
 }
 ```