Update README.md

README.md

@@ -7,7 +7,7 @@ tags:
 - LSTM
 ---
 
-## Introduction
+# Introduction
 
 This model is defined as proposed in the book "mastering pytorch".
 It is based on CNN-encoder and a LSTM-decoder.
@@ -17,8 +17,13 @@ The LSTM-decoder use an input of 256, a hidden layer of 512, and uses the vocabu
 
 The model has been trained as a pure learning exercise, and so the model performances remain relatively mean.
 
-## Training procedure
+# Training procedure
 
 For the sake of the exercise, the model has been trained for only 5 epochs.
 
-It has been trained on the COCO dataset.
+It has been trained on the COCO dataset.
+
+# Support
+
+If you like my work, feel free to support me here:
+[buymeacoffee.com/selfmaker](https://buymeacoffee.com/selfmaker)