Update README.md

README.md

@@ -28,7 +28,7 @@ This is a merge of two G3 models, one trained on instruct and one trained on bas
   
 The result is a lovely blend of Glitter's ability to follow instructions and Confetti's free-spirit prose, effectively 'loosening up' much of the hesitancy that was left in Glitter. 
 
-Vision works (as well as any vision works with this model right now) if you pair a GGUF of this with an appropriate mmproj file; I intend to fix the missing vision tower + make this properly multimodal in the near future. 
+**Update**: Vision tower is back! Have fun. 
 
 *Thank you to [jebcarter](https://huggingface.co/jebcarter) for the idea to make this. I love how it turned out!*