Update README.md

README.md

@@ -10,7 +10,7 @@ license_link: https://ai.google.dev/gemma/terms
 
 Gemma-Wukong-2b is a dealigned chat finetune of the original Gemma 2b developed by the Google Deepmind and various other teams
 
-This model was trained on the teknium OpenHeremes-2.5 dataset and the  from Cognitive Computations https://erichartford.com/dolphin 🐬
+This model was trained on the teknium OpenHeremes-2.5 dataset and the excellent Dolphin dataset from Cognitive Computations https://erichartford.com/dolphin 🐬
 
 This model was trained for 3 epochs over 4 3090's.