Update README.md

README.md

@@ -129,19 +129,10 @@ library_name: transformers
                         </div>
                         <p>
                             Dans-PersonalityEngine is a versatile model series
-                            designed for exceptional performance across a wide
-                            range of tasks and domains.
-                        </p>
-                        <p>
-                            Fine-tuned on a diverse corpus of 50+ specialized
-                            datasets, this series excels at both creative
-                            endeavors (like roleplay and co-writing) and
-                            technical tasks (such as code generation, tool use,
-                            and complex reasoning).
-                        </p>
-                        <p>
-                            The total dataset size is around 1.7B tokens, 1.1B
-                            of which is creative and 600M being technical.
+                            fine-tuned on 50+ specialized datasets, designed to
+                            excel at both creative tasks (like roleplay and
+                            co-writing) and technical challenges (such as code
+                            generation, tool use, and complex reasoning).
                         </p>
                         <p>
                             V1.3.0 introduces multilingual capabilities with
@@ -152,22 +143,22 @@ library_name: transformers
                         </p>
                         <h3>Multilingual Support</h3>
                         <pre class="code-block">
-Arabic  Chinese   English  French      German
-Hindi   Japanese  Korean   Portuguese  Spanish</pre
+Arabic    Chinese  English
+French    German   Hindi
+Japanese  Korean   Portuguese
+          Spanish</pre
                         >
                         <h3>Key Details</h3>
                         <pre class="code-block">
 BASE MODEL: mistralai/Mistral-Small-3.1-24B-Base-2503
 LICENSE: apache-2.0
 LANGUAGE: Multilingual with 10 supported languages
-CONTEXT LENGTH: 32768 tokens, 131072 with degraded quality</pre
+CONTEXT LENGTH: 32768 tokens, 131072 with degraded recall</pre
                         >
                         <h3>Recommended Settings</h3>
                         <pre class="code-block">
 TEMPERATURE: 1.0
-TOP_P: 0.95
-MIN_P: 0.05
-REPETITION_PENALTY: 1.04</pre
+TOP_P: 0.9</pre
                         >
                         <h3>Prompting Format</h3>
                         <p>
@@ -180,11 +171,9 @@ REPETITION_PENALTY: 1.04</pre
                         <h3>Why not ChatML?</h3>
                         <p>
                             While ChatML is a standard format for LLMs, it has
-                            limitations. DanChat-2 uses unique special tokens
+                            limitations. DanChat-2 uses special tokens
                             for each role, reducing biases and helping the model
-                            adapt to different tasks more readily. While similar
-                            effects could be achieved with modified ChatML, such
-                            approaches come with their own caveats.
+                            adapt to different tasks more readily.
                         </p>
                         <h3>SillyTavern Template</h3>
                         <p>