Update README.md

README.md

@@ -50,12 +50,13 @@ This version of the Google T5-Base model has been fine-tuned on a bilingual data
 `"translate Lezghian to Russian: "` - Lez-Ru    
 
 ## How to Get Started with the Model
+
+```python
 from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
 
 model = AutoModelForSeq2SeqLM.from_pretrained("leks-forever/mt5-base")
 tokenizer = AutoTokenizer.from_pretrained("leks-forever/mt5-base")
 
-```python
 def predict(text, prefix, a=32, b=3, max_input_length=1024, num_beams=1, **kwargs):
     inputs = tokenizer(prefix + text, return_tensors='pt', padding=True, truncation=True, max_length=max_input_length)
     result = model.generate(