Update app.py

app.py

@@ -48,8 +48,11 @@ def generate(
 
     
 
+    messages = [
+        {"role": "user", "content": prompt}
+    ]
 
-    inputs = tokenizer.apply_chat_template(formatted_prompt, return_tensors="pt")
+    inputs = tokenizer.apply_chat_template(messages, return_tensors="pt")
     stream = model.generate(inputs, **generate_kwargs, stream=True, details=True, return_full_text=False)
     output = ""