Merge branch 'main' of https://huggingface.co/MILVLG/Imp-v0-3b into main

README.md

@@ -49,7 +49,7 @@ print(tokenizer.decode(output_ids[input_ids.shape[1]:], skip_special_tokens=True
 ```
 
 ## Model evaluation
-We perform evaluation on 9 commonly-used benchmarks to validate the effectiveness of our model, including 5 academic VQA benchmarks and 4 popular MLLM benchmarks.
+We conduct evaluation on 9 commonly-used benchmarks, including 5 academic VQA benchmarks and 4 popular MLLM benchmarks, to compare our Imp model with LLaVA (7B) and existing MSLMs with similar sizes.
 
 | Models | Size | VQAv2 | GQA |VisWiz  | SQA (IMG) | TextVQA | POPE |  MME | MMB  |MM-Vet|
 |:--------:|:-----:|:----:|:----:|:-------------:|:--------:|:-----:|:----:|:-------:|:-------:|:-------:|
@@ -65,4 +65,4 @@ We perform evaluation on 9 commonly-used benchmarks to validate the effectivenes
 This project is licensed under the Apache License 2.0 - see the [LICENSE](https://www.apache.org/licenses/LICENSE-2.0) file for details.
 
 ## About us
-This project is maintained by the [MILVLG](https://github.com/MILVLG)@Hangzhou Dianzi University (HDU) led by Prof. Zhou Yu and Jun Yu, and mainly developed by Zhenwei Shao and Xuecheng Ouyang. We hope our model may serve as a strong baseline to inspire future research on MSLM, as well as its derivative applications on mobile devices and robots. 
+This project is maintained by the [MILVLG](https://github.com/MILVLG)@Hangzhou Dianzi University (HDU) led by Prof. Zhou Yu and Jun Yu, and is mainly developed by Zhenwei Shao and Xuecheng Ouyang. We hope our model may serve as a strong baseline to inspire future research on MSLM, as well as its derivative applications on mobile devices and robots.