Update app.py

app.py

@@ -306,7 +306,7 @@ async def generate_response_stream(messages: List[Dict[str,str]], max_tokens=600
         while attempts < max_attempts:
             attempts += 1
             # Clear, explicit generation label for UI
-            yield f"data: {json.dumps({'status': f'Generating — LLM{attempts})...'})}\n\n"
+            yield f"data: {json.dumps({'status': f'Generating — LLM {attempts})...'})}\n\n"
             await asyncio.sleep(0)
 
             model_inputs = tokenizer(text_prompt, return_tensors="pt", truncation=True, max_length=4096).to(next(model.parameters()).device)