Delta-Vector
/

Hamanasu-4B-Instruct-KTO-V1

Model card Files Files and versions

Delta-Vector commited on Apr 6

Commit

99158f1

·

verified ·

1 Parent(s): 2bbf3c9

Update README.md

Files changed (1) hide show

README.md +4 -1

README.md CHANGED Viewed

@@ -173,12 +173,15 @@ details summary:hover {
 ## 🌌 Overview
-<i>This model is a finetune of Hamanasu-4B-PT that has been trained with Instruct data.</i>
 <i>A generalist model that's quick to adapt to any type of roleplay.<i>
 <i>All thanks to Tav for funding the train.</i>
 </div>
 <div style="display: grid; grid-template-columns: repeat(auto-fit, minmax(250px, 1fr)); gap: 20px; margin: 20px 0;">

 ## 🌌 Overview
+<i>This model is a finetune of Hamanasu-4B-Instruct with IFeval data to increase SLM instruct following.</i>
 <i>A generalist model that's quick to adapt to any type of roleplay.<i>
 <i>All thanks to Tav for funding the train.</i>
+<i>Support me and my finetunes on Ko-Fi https://ko-fi.com/deltavector</i>
 </div>
 <div style="display: grid; grid-template-columns: repeat(auto-fit, minmax(250px, 1fr)); gap: 20px; margin: 20px 0;">