update readme

README.md

@@ -21,7 +21,7 @@ The idea with freezing feedforward and self-attention layers in pretrained trans
 Also, the model has a good chance for over-fitting text modality and lost generalization. 
 To deal with this problem is increased coefficient 10^3 in weighted cross-entropy loss for image codebooks part. 
 
-Full version of code is available on Kaggle [here](https://www.kaggle.com/shonenkov/emojich-rudall-e).
+Full version of training code is available on Kaggle: [![Kaggle](https://kaggle.com/static/images/open-in-kaggle.svg)](https://www.kaggle.com/shonenkov/emojich-rudall-e)
 
 
 ### Examples of generated emojis