POLARIS-Project
/

Polaris-4B-Preview

Model card Files Files and versions

Chancy commited on Jun 29

Commit

675dc44

·

verified ·

1 Parent(s): 5ae511a

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -34,7 +34,7 @@ Polaris is an open-source post-training method that uses reinforcement learning
  By leveraging open-source data and academic-level resources, Polaris pushes the capabilities of open-recipe reasoning models to unprecedented heights. In benchmark tests, our method even surpasses top commercial systems, including Claude-4-Opus, Grok-3-Beta, and o3-mini-high (2025/01/03).
 <div align="center">
-  <img src="https://raw.githubusercontent.com/ChenxinAn-fdu/POLARIS/main/figs/aime25.png" alt="performance" style="width:60%;">
 </div>
 ## Polaris's Recipe

  By leveraging open-source data and academic-level resources, Polaris pushes the capabilities of open-recipe reasoning models to unprecedented heights. In benchmark tests, our method even surpasses top commercial systems, including Claude-4-Opus, Grok-3-Beta, and o3-mini-high (2025/01/03).
 <div align="center">
+  <img src="https://raw.githubusercontent.com/ChenxinAn-fdu/POLARIS/main/figs/aime25.png" alt="performance" style="width:100%;">
 </div>
 ## Polaris's Recipe