enable greedy

README.md

@@ -104,10 +104,9 @@ inputs = {key: value.to(device) for (key, value) in inputs.items()}
 # Generate the output
 output = model.generate(
             **inputs,
-            temperature=0.8,
             max_new_tokens=50,
             num_return_sequences=1,
-            do_sample=True,
+            do_sample=False,
         )
 
 # Decode the output