Update app.py

app.py

@@ -23,8 +23,13 @@ def generate_response(message, history):
       
 
     # synth,cot composite — reasoning / CoT style (see Disclaimer for other modes)
+    conversation = ""
+    for user_msg, assistant_msg in history:
+        conversation += f"user: {user_msg}\nassistant: {assistant_msg}\n"
+    conversation += f"user: {message}\nassistant: "
+    
     condition = "<|quad_end|><|object_ref_end|>"
-    prompt = f"<|im_start|>{condition}{history} {message}<|im_end|>"
+    prompt = f"<|im_start|>{condition}{conversation} <|im_end|>"
     
     inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
     # Mark the prompt as a single bidirectional prefix block — see "PrefixLM mask" below.