Update README.md

README.md

@@ -17,6 +17,7 @@ license: apache-2.0
       <div class="header"> 
         <h1>Aura-llama</h1> </div> <div class="info"> 
           <strong>there was an error in the first model config it has been fixed in the new repo <a href="https://huggingface.co/TheSkullery/Aura-llama-v1">TheSkullery/Aura-llama-v1</a> </strong>
+          <p>^^^^^^^^^^^</p> 
           <img src="https://cdn-uploads.huggingface.co/production/uploads/64545af5ec40bbbd01242ca6/QYpWMEXTe0_X3A7HyeBm0.webp" alt="Aura-llama image"> 
           <p>Now that the cute anime girl has your attention.</p> 
           <p>Aura-llama is using the methodology presented by SOLAR for scaling LLMs called depth up-scaling (DUS), which encompasses architectural modifications with continued pretraining. Using the solar paper as a base, I integrated Llama-3 weights into the upscaled layers, and In the future plan to continue training the model.</p> 
@@ -26,32 +27,6 @@ license: apache-2.0
             <li><a href="https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct">meta-llama/Meta-Llama-3-8B-Instruct</a></li> 
           </ul> 
         </div> 
-      <div class="update-section"> 
-        <h2>Merged Evals (Has Not Been Finetuned, waiting for tests):</h2> 
-        <p>Aura-llama</p> 
-        <ul> 
-          <li>Avg: ?</li> 
-          <li>ARC: ?</li> 
-          <li>HellaSwag: ?</li> 
-          <li>MMLU: ?</li> 
-          <li>T-QA: ?</li> 
-          <li>Winogrande: ?</li> 
-          <li>GSM8K: ?</li> 
-        </ul> 
-      </div> 
-      <div class="update-section"> 
-        <h2>🧩 Configuration</h2> 
-        <pre><code>
-          slices: 
-            - sources: 
-              - model: meta-llama/Meta-Llama-3-8B-Instruct 
-                layer_range: [0, 23] 
-            - sources: 
-              - model: meta-llama/Meta-Llama-3-8B-Instruct 
-                layer_range: [7, 31] 
-          merge_method: passthrough 
-          dtype: bfloat16 
-        </code></pre> 
       </div> 
     </div> 
     </body>