Update app.py

app.py

@@ -75,7 +75,7 @@ option_mapping = {"translation": "### TRANSLATION ###", "mcq": "### MCQ ###", "n
     "long response": "### LONG RESPONSE ###", "direct response": "### DIRECT RESPONSE ###", "paraphrase": "### PARAPHRASE ###", "code": "### CODE ###"}
 def generate_response(message, temperature, max_new_tokens, top_p, task):
     append_text = option_mapping.get(task, "")
-    prompt = f"INPUT : {message} {append_text} ### RESPONSE : "
+    prompt = f"INPUT : {message} {append_text} RESPONSE : "
     print(f"Prompt: {prompt}")
     start_time = time.time()
     inputs = tokenizer.encode(prompt, return_tensors="pt").to(model.device)