Update README.md

README.md

@@ -48,11 +48,29 @@ This approach enables the model to scale significantly by utilizing a sparse ope
 The training utilized the BiMed1.3M dataset, focusing on bilingual medical interactions in both English and Arabic, with a substantial corpus of over 632 million healthcare-specialized tokens. 
 The model's fine-tuning process includes a low-rank adaptation technique (QLoRA) to efficiently adapt the model to specific tasks while keeping computational demands manageable. 
 
-| Model Name   | Download |
-|--------------|----------|
-| BiMediX-Eng  | [HuggingFace Link](https://huggingface.co/BiMediX/BiMediX-Eng) |
-| BiMediX-Ara  | [HuggingFace Link](https://huggingface.co/BiMediX/BiMediX-Ara) |
-| BiMediX-Bi   | [HuggingFace Link](https://huggingface.co/BiMediX/BiMediX-Bi) |
+
+<div style="width: 50%;float: left;">
+<table>
+<tr>
+<th>Model Name</th>
+<th>Download</th>
+</tr>
+<tr>
+<td>BiMediX-Eng</td>
+<td><a href="https://huggingface.co/BiMediX/BiMediX-Eng">HuggingFace</a></td>
+</tr>
+<tr>
+<td>BiMediX-Ara</td>
+<td><a href="https://huggingface.co/BiMediX/BiMediX-Ara">HuggingFace</a></td>
+</tr>
+<tr>
+<td>BiMediX-Bi</td>
+<td><a href="https://huggingface.co/BiMediX/BiMediX-Bi">HuggingFace</a></td>
+</tr>
+</table>
+</div>  
+
+
 
 ## Dataset