Add model card

This PR adds a model card for LLaVANext-OmniAlign-32B, including the relevant metadata, links to the paper, Github repository, and project page, and performance results.

README.md

@@ -1,3 +1,8 @@
+---
+license: cc-by-nc-4.0
+library_name: transformers
+pipeline_tag: image-text-to-text
+---
 
 ### Introduction
 Paper: [Paper](https://arxiv.org/abs/2502.18411),
@@ -37,7 +42,4 @@ By integrating OmniAlign-V datasets in Supervised Fine-tuning(SFT) stage, we can
 
 For MM-AlignBench and WildVision, A/B denotes Winning Rate/Reward.
 ### How to use
-Please refer to our [Github](https://github.com/PhoenixZ810/OmniAlign-V) for more details about training and evaluation.
-
-
-
+Please refer to our [Github](https://github.com/PhoenixZ810/OmniAlign-V) for more details about training and evaluation.