Update README.md

README.md

@@ -216,8 +216,11 @@ a:hover {text-decoration: underline;}
       <p>The model then went through DPO training using approx 1100 chosen examples from the SFT dataset that were of exceptional quality or showed verifiable instruction following. Rejected samples were generated using another Llama 3.3 finetune that is known for poor instruction following.</p>
       <h3 class="subheading">Axolotl configs</h3>
       <p>Neither are optimized for cost / performance efficiency, YMMV.</p>
-      <h3 class="subheading">SFT 1*H200</h3>
-<pre><code>
+    </div>
+  </div>
+</div>
+<h3>SFT 1*H200</h3>
+```yml
 # ====================
 # MODEL CONFIGURATION
 # ====================
@@ -327,9 +330,9 @@ save_safetensors: true
 wandb_project: project_name
 # wandb_entity: your_entity  # Uncomment and set if needed
 # wandb_name: your_run_name  # Uncomment and set if needed
-</code></pre>
-<h3 class="subheading">DPO 2*H200</h3>
-<pre><code>
+```
+<h3>DPO 2*H200</h3>
+```yml
 # ====================
 # MODEL CONFIGURATION
 # ====================
@@ -425,9 +428,6 @@ save_safetensors: true
 wandb_project: project_name
 # wandb_entity: your_entity  # Uncomment and set if needed
 # wandb_name: your_run_name  # Uncomment and set if needed
-</code></pre>
-    </div>
-  </div>
-</div>
+```
 </body>
 </html>