openbmb
/

RLAIF-V-12B

Text Generation

Inference Endpoints

Model card Files Files and versions Community

HaoyeZhang commited on May 25

Commit

2235170

•

1 Parent(s): 0e6260c

Update README.md

Files changed (1) hide show

README.md +3 -5

README.md CHANGED Viewed

@@ -23,16 +23,14 @@ We utilize a novel framework, **RLAIF-V**, which **aligns MLLMs in a fully open-
 * 💪 **Maintaining Well Performance on General Abilities**: On benchmarks tested with the general abilities (e.g. LLaVABench, MMStar), RLAIF-V-12B also performs well.
 <p align="center">
-  <img src="https://cdn-uploads.huggingface.co/production/uploads/6566e0c493e30c8a60048eb3/ypXZxb4HE-jDPJU9115bi.png" alt="fig1" width="60%"/>
 </p>
 <!-- ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6566e0c493e30c8a60048eb3/ypXZxb4HE-jDPJU9115bi.png) -->
 ### Examples
 <p align="center">
-  <img src="https://cdn-uploads.huggingface.co/production/uploads/6566e0c493e30c8a60048eb3/yg-Ksp9qi8AodURSmX769.png" alt="fig2-1" width="60%"/>
-</p>
-<p align="center">
-  <img src="https://cdn-uploads.huggingface.co/production/uploads/6566e0c493e30c8a60048eb3/NSEkeBmH99B44rX8GTZig.png" alt="fig2-1" width="60%"/>
 </p>
 ### Model Description

 * 💪 **Maintaining Well Performance on General Abilities**: On benchmarks tested with the general abilities (e.g. LLaVABench, MMStar), RLAIF-V-12B also performs well.
 <p align="center">
+  <img src="https://cdn-uploads.huggingface.co/production/uploads/6566e0c493e30c8a60048eb3/ypXZxb4HE-jDPJU9115bi.png" alt="fig1" width="80%"/>
 </p>
 <!-- ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6566e0c493e30c8a60048eb3/ypXZxb4HE-jDPJU9115bi.png) -->
 ### Examples
 <p align="center">
+  <img src="https://cdn-uploads.huggingface.co/production/uploads/6566e0c493e30c8a60048eb3/yg-Ksp9qi8AodURSmX769.png" alt="fig2-1" width="80%"/>
+  <img src="https://cdn-uploads.huggingface.co/production/uploads/6566e0c493e30c8a60048eb3/NSEkeBmH99B44rX8GTZig.png" alt="fig2-1" width="80%"/>
 </p>
 ### Model Description