Update app.py

app.py

@@ -26,9 +26,9 @@ FastLanguageModel.for_inference(model)
 def predict(question):
     inputs = tokenizer(
     [f'''### Question:
-    {question}
-    
-    ### Answer:
+{question}
+
+### Answer:
 '''], return_tensors = "pt").to("cuda")
 
     outputs = model.generate(**inputs, max_new_tokens = 128)
@@ -39,7 +39,7 @@ def predict(question):
 
 inputs = gr.Textbox(lines=2, label="Enter a question", value="Як отримати виплати ВПО?")
 
-outputs = gr.Textbox(label="Answer")
+outputs = gr.Markdown(label="Answer")
 
 demo = gr.Interface(fn=predict, inputs=inputs, outputs=outputs)
 demo.launch()