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}Explain why the sky is blue.<|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.
@@ -36,8 +36,8 @@ def generate_response(message, history):
 chatbot = gr.ChatInterface(
     fn=generate_response,
     title="Simple ZeroGPU Chatbot",
-    description="A simple chatbot using DialoGPT, running on Hugging Face ZeroGPU.",
-    examples=["Hello!", "How are you today?", "What's the latest news?"]
+    description="A simple chatbot using HRM-Text, running on Hugging Face ZeroGPU.",
+    examples=["Explain why the sky is blue?", "Introduce yourself?", "What's the latest news?"]
 )
 
 if __name__ == "__main__":