Update README.md

README.md

@@ -5,31 +5,20 @@ language:
 pipeline_tag: image-text-to-text
 ---
 
-# Cerule - A <span style="color: #4285F4;">Tiny</span> <span style="color: #DB4437;">Mighty</span> <span style="color: #F4B400;">Vision</span> <span style="color: #0F9D58;">Model</span>
+# Cerule - A Tiny Mighty Vision Model
 ### Based on Google's - <span style="color: #D56c76;">Gemma-2b + SigLIP</span>
 
 
 
 ```
-
-
  ██████╗███████╗██████╗ ██╗   ██╗██╗     ███████╗
 ██╔════╝██╔════╝██╔══██╗██║   ██║██║     ██╔════╝
-██║     █████╗  ██████╔╝██║   ██║██║     █████╗  
-██║     ██╔══╝  ██╔══██╗██║   ██║██║     ██╔══╝  
+██║     █████╗  ██████╔╝██║   ██║██║     █████╗
+██║     ██╔══╝  ██╔══██╗██║   ██║██║     ██╔══╝
 ╚██████╗███████╗██║  ██║╚██████╔╝███████╗███████╗
- ╚═════╝╚══════╝╚═╝  ╚═╝ ╚═════╝ ╚══════╝╚══════╝
-                                                 
-
-
-                                                                
-                                                                
+ ╚═════╝╚══════╝╚═╝  ╚═╝ ╚═════╝ ╚══════╝╚══════╝               
  ```                                                               
 
-
-                        
-
-
 We train and release "Cerule", a tiny yet powerful Vision Lanuage Model based on the newly released Google's [Gemma-2b](https://huggingface.co/google/gemma-2b) and Google's [SigLIP](https://huggingface.co/google/siglip-so400m-patch14-384). 
 
 We utilise highly efficient data selection techniques with:
@@ -104,4 +93,4 @@ print(tokenizer.decode(output_ids[input_ids.shape[1]:], skip_special_tokens=Fals
 ```
 
 ## License
-Apache 2.0? Maybe... idk
+Apache 2.0