Update README.md

README.md

@@ -14,7 +14,32 @@ library_name: transformers
 
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/646a1939c37ca1e12308fe81/SRxJKkSuC0y-oMB7SFeR6.png)
 
-[[**ArXiv**]]() | [[**GitHub**](https://github.com/VainF/Thinkless)]
+<table>
+  <thead>
+  </thead>
+  <tbody>
+    <tr>
+      <td>📄 <strong>Paper Link</strong></td>
+      <td><a href="https://arxiv.org/abs/">ArXiv</a></td>
+    </tr>
+    <tr>
+      <td>🤖 <strong>RL Model</strong></td>
+      <td><a href="https://huggingface.co/Vinnnf/Thinkless-1.5B-RL-DeepScaleR">Thinkless-1.5B-RL-DeepScaleR</a></td>
+    </tr>
+    <tr>
+      <td>🐣 <strong>Warmup Model</strong></td>
+      <td><a href="https://huggingface.co/Vinnnf/Thinkless-1.5B-Warmup">Thinkless-1.5B-Warmup</a></td>
+    </tr>
+    <tr>
+      <td>📊 <strong>Data for Warmup</strong></td>
+      <td><a href="https://huggingface.co/datasets/Vinnnf/Hybrid-OpenThoughts-1M-1.5B">Hybrid-OpenThoughts-1M-1.5B</a></td>
+    </tr>
+    <tr>
+      <td>📊 <strong>Data for RL</strong></td>
+      <td><a href="https://huggingface.co/datasets/agentica-org/DeepScaleR-Preview-Dataset">agentica-org/DeepScaleR-Preview-Dataset</a></td>
+    </tr>
+  </tbody>
+</table>
 
 > [!IMPORTANT] 
 > This is a warm-up model and should be used as an initialization for RL. It was trained on [OpenThoughts-1M-Hybrid-1.5B](https://huggingface.co/datasets/open-thoughts/OpenThoughts2-1M) and can generate both long and short answers with comparable probabilities (~50%).