Update README.md

README.md

@@ -1898,28 +1898,23 @@ library_name: transformers
                 </details>
               </li>
               <li><span class="model-component"><a href="https://huggingface.co/EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.0" target="_blank">EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.0</a></span> Core capabilities</li>
-              <li><span class="model-component"><a href="https://huggingface.co/LatitudeGames/Wayfarer-Large-70B-Llama-3.3" target="_blank">LatitudeGames/Wayfarer-Large-70B-Llama-3.3</a></span> Enhanced reasoning</li>
-              <li><span class="model-component"><a href="https://huggingface.co/Sao10K/L3.3-70B-Euryale-v2.3" target="_blank">Sao10K/L3.3-70B-Euryale-v2.3</a></span> Improved capabilities</li>
+              <li><span class="model-component"><a href="https://huggingface.co/LatitudeGames/Wayfarer-Large-70B-Llama-3.3" target="_blank">LatitudeGames/Wayfarer-Large-70B-Llama-3.3</a></span> Enhanced Storytelling and RP</li>
+              <li><span class="model-component"><a href="https://huggingface.co/Sao10K/L3.3-70B-Euryale-v2.3" target="_blank">Sao10K/L3.3-70B-Euryale-v2.3</a></span> Improved all rounder capabilities</li>
               <li><span class="model-component"><a href="https://huggingface.co/Sao10K/70B-L3.3-Cirrus-x1" target="_blank">Sao10K/70B-L3.3-Cirrus-x1</a></span> Improved coherence</li>
               <li><span class="model-component"><a href="https://huggingface.co/Sao10K/L3.1-70B-Hanami-x1" target="_blank">Sao10K/L3.1-70B-Hanami-x1</a></span> Balanced responses</li>
               <li><span class="model-component"><a href="https://huggingface.co/TheDrummer/Anubis-70B-v1" target="_blank">TheDrummer/Anubis-70B-v1</a></span> Enhanced detail</li>
-              <li><span class="model-component"><a href="https://huggingface.co/SicariusSicariiStuff/Negative_LLAMA_70B" target="_blank">SicariusSicariiStuff/Negative_LLAMA_70B</a></span> Reduced bias</li>
+              <li><span class="model-component"><a href="https://huggingface.co/SicariusSicariiStuff/Negative_LLAMA_70B" target="_blank">SicariusSicariiStuff/Negative_LLAMA_70B</a></span> Reduced bias - Base</li>
+              <li><span class="model-component"><a href="https://huggingface.co/TheDrummer/Fallen-Llama-3.3-R1-70B-v1" target="_blank">TheDrummer/Fallen-Llama-3.3-R1-70B-v1</a></span> Reduced bias - Base</li>
             </ul>
           <div class="model-description">
             <h4>Model Series Overview</h4>
-            <p>L3.3-Electra-R1-70b represents the foundational release in a three-part model series, followed by L3.3-Cu-Mai-R1-70b (Version A) and L3.3-Mokume-Gane-R1-70b (Version C). The name "Electra" draws inspiration from the electric-powered aesthetic of the model's mascot, representing the powerful capabilities and lightning-fast responses that define this model's performance.</p>
+            <p>L3.3-Electra-R1-70b is the newest release of the Unnamed series, this is the 6th iteration based of user feedback.</p>
             <h4>Technical Architecture</h4>
-            <p>Built on a custom DeepSeek R1 Distill base (TheSkullery/L3.1x3.3-Hydroblated-R1-70B-v4.4), Electra-R1 integrates specialized components through the SCE merge method with a select_topk parameter of 0.16. The model uses float32 dtype during processing with a bfloat16 output dtype for optimized performance.</p>
-            <ul>
-              <li>EVA and Wayfarer foundations for creative expression and scene comprehension</li>
-              <li>Euryale, Cirrus and Hanami elements for enhanced reasoning capabilities</li>
-              <li>Anubis components for detailed scene description</li>
-              <li>Negative_LLAMA integration for balanced perspective and response</li>
-            </ul>
+            <p>Built on a custom DeepSeek R1 Distill base (TheSkullery/L3.1x3.3-Hydroblated-R1-70B-v4.4), Electra-R1 integrates specialized components through the SCE merge method. The model uses float32 dtype during processing with a bfloat16 output dtype for optimized performance.</p>
             <h4>Core Capabilities</h4>
-            <p>As the OG model in the series, Electra-R1 serves as the gold standard and reliable baseline. User feedback consistently highlights its superior intelligence, coherence, and unique ability to provide deep character insights. Through proper prompting, the model demonstrates advanced reasoning capabilities and an "X-factor" that enables unprompted exploration of character inner thoughts and motivations.</p>
+            <p>Electra-R1 serves newest gold standard and baseline. User feedback consistently highlights its superior intelligence, coherence, and unique ability to provide deep character insights. Through proper prompting, the model demonstrates advanced reasoning capabilities and unprompted exploration of character inner thoughts and motivations.</p>
             <h4>Base Architecture</h4>
-            <p>The model utilizes the custom Hydroblated-R1 base, engineered for stability and enhanced reasoning. The SCE merge method's settings are precisely tuned based on extensive community feedback, ensuring optimal component integration while maintaining model coherence and reliability. This foundation establishes Electra-R1 as the benchmark upon which its variant models build and expand.</p>
+            <p>The model utilizes the custom Hydroblated-R1 base, created for stability and enhanced reasoning. The SCE merge method's settings are precisely tuned based on extensive community feedback (of over 10 diffrent models from Nevoria to Cu-Mai), ensuring optimal component integration while maintaining model coherence and reliability. This foundation establishes Electra-R1 as the benchmark upon which its variant models build and expand.</p>
           </div>
         </div>
       </div>
@@ -2230,7 +2225,7 @@ library_name: transformers
                 </div>
                 <div class="settings-content">
                   <div class="setting-item">
-                    <p>'<span style="color: var(--electra-primary)">&lt;think&gt;</span> OK, as an objective, detached narrative analyst, let's think this through carefully:'</p>
+                    <p>'<span style="color: #00b2ff">&lt;think&gt;</span> OK, as an objective, detached narrative analyst, let's think this through carefully:'</p>
                   </div>
                 </div>
               </div>
@@ -2241,11 +2236,11 @@ library_name: transformers
                 <div class="settings-content">
                   <div class="setting-item">
                     <span class="setting-label">Prefix:</span>
-                    <span class="setting-value">'<span style="color: var(--electra-primary)">&lt;think&gt;</span>'</span>
+                    <span class="setting-value">'<span style="color: #00b2ff">&lt;think&gt;</span>'</span>
                   </div>
                   <div class="setting-item">
                     <span class="setting-label">Suffix:</span>
-                    <span class="setting-value">'<span style="color: var(--electra-primary)">&lt;/think&gt;</span>'</span>
+                    <span class="setting-value">'<span style="color: #00b2ff">&lt;/think&gt;</span>'</span>
                   </div>
                 </div>
               </div>