Update app.py

app.py

@@ -24,7 +24,7 @@ def generate_response(message, history):
 
     # synth,cot composite — reasoning / CoT style (see Disclaimer for other modes)
     condition = "<|quad_end|><|object_ref_end|>"
-        prompt = f"<|im_start|>{condition}{history} {message}<|im_end|>"
+    prompt = f"<|im_start|>{condition}{history} {message}<|im_end|>"
     
     inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
     # Mark the prompt as a single bidirectional prefix block — see "PrefixLM mask" below.