Update README.md

README.md

@@ -19,8 +19,12 @@ pipeline_tag: text-generation
 
 # OpenChat 3.5 CTranslate 2 Quantized Int8 Float16
 
-For efficient inference and low VRAM 7GB (when small context window, othertime up to 10GB)
+For efficient inference and low VRAM 7GB to up to 9GB with a short context window.
 
+[Follow me, Vaclav Kosar, for more software and machine learning.](https://vaclavkosar.com/)
+
+
+Original model description:
 
 
 # OpenChat: Advancing Open-source Language Models with Mixed-Quality Data