Update README.md

README.md

@@ -28,7 +28,7 @@ just replace the pretrained model name and make sure you use Arabic text and spl
 You can train a better model if you have access to adequate compute (can fine tune this model on more data, seed 42 was used tp pick the 100K sample).
 
 # Training script 
-```
+```python
 from datasets import load_dataset
 from ragatouille import RAGTrainer
 sample_size = 100000