Update README.md

README.md

@@ -27,7 +27,7 @@ Cephalo provides a robust framework for multimodal interaction and understanding
 - [Cephalo-Idefics-2-vision-8b-beta](https://huggingface.co/lamm-mit/Cephalo-Idefics-2-vision-8b-beta)
   - Trained on GPT-4o distilled image-text data from Wikipedia and scientific papers. Gives longer answers, with enhanced reasoning. Can struggle with complex concepts.  
 - [Cephalo-Llava-v1.6-Mistral-8b-alpha](https://huggingface.co/lamm-mit/Cephalo-Llava-v1.6-Mistral-8b-alpha)
-  - Trained on GPT-4o distilled image-text data from Wikipedia and scientific papers. 
+  - Trained on GPT-4o distilled image-text data from Wikipedia, with low-resolution images. Does not perform well on multiple image queries, and has some inconsistencies in understanding.  
 
 ## Citation