Correcting Demo

app.py

@@ -25,7 +25,7 @@ def make_inference(product_name, product_description):
     with torch.cuda.amp.autocast():
         output_tokens = model.generate(**batch, max_new_tokens=50)
 
-    print(tokenizer.decode(output_tokens[0], skip_special_tokens=True))
+    return tokenizer.decode(output_tokens[0], skip_special_tokens=True)
 
 
 if __name__ == "__main__":