OpenGVLab
/

VisualPRM-8B-v1.1

Image-Text-to-Text

feature-extraction

Model card Files Files and versions Community

Weiyun1025 commited on 15 days ago

Commit

aeb9591

·

verified ·

1 Parent(s): c6c0583

Upload folder using huggingface_hub

Files changed (1) hide show

README.md +3 -1

README.md CHANGED Viewed

@@ -25,7 +25,9 @@ tags:
 [\[🤗 dataset\]](https://huggingface.co/datasets/OpenGVLab/VisualPRM400K)
 [\[🤗 benchmark\]](https://huggingface.co/datasets/OpenGVLab/VisualProcessBench)
-***This is a newer version of [VisualPRM-8B](https://huggingface.co/OpenGVLab/VisualPRM-8B), which exhibits superior performance compared to [VisualPRM-8B](https://huggingface.co/OpenGVLab/VisualPRM-8B).***
 ## Introduction

 [\[🤗 dataset\]](https://huggingface.co/datasets/OpenGVLab/VisualPRM400K)
 [\[🤗 benchmark\]](https://huggingface.co/datasets/OpenGVLab/VisualProcessBench)
+***This is a newer version of [VisualPRM-8B](https://huggingface.co/OpenGVLab/VisualPRM-8B), which exhibits superior performance compared to [VisualPRM-8B](https://huggingface.co/OpenGVLab/VisualPRM-8B). Using VisualPRM-8B-v1.1 as the critic model, the reasoning abilities of InternVL3 are further enhanced.***
+![image/png](https://huggingface.co/datasets/Weiyun1025/InternVL-Performance/resolve/main/internvl3/reasoning.png)
 ## Introduction