Minor fix

app.py

@@ -26,7 +26,7 @@ tokenizer.padding_side = "right"
 pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
 
 def infer(message, history):
-    prompt = pipe.tokenizer.apply_chat_template([{"role": "user", "content": prompt}], tokenize=False, add_generation_prompt=True)
+    prompt = pipe.tokenizer.apply_chat_template([{"role": "user", "content": message}], tokenize=False, add_generation_prompt=True)
     outputs = pipe(prompt, max_new_tokens=256, do_sample=True, num_beams=1, temperature=0.3, top_k=50, top_p=0.95, max_time= 180)
     return outputs[0]['generated_text'][len(prompt):].strip()