Update app.py

app.py

@@ -115,6 +115,14 @@ def remove_repetitive_responses(responses):
     return unique_responses
 
 @spaces.GPU(duration=0)
+async def generate_model_response(model, inputs, top_k, top_p, temperature):
+    try:
+        responses = model.generate(inputs, top_k=top_k, top_p=top_p, temperature=temperature)
+        return responses
+    except Exception as e:
+        print(f"Error generating model response: {e}")
+        return []
+
 @app.post("/generate")
 async def generate(request: ChatRequest):
     try:
@@ -123,7 +131,7 @@ async def generate(request: ChatRequest):
         
         model = global_data['models'][0]['model']
         inputs = normalize_input(request.message)
-        responses = model.generate(inputs, top_k=request.top_k, top_p=request.top_p, temperature=request.temperature)
+        responses = await generate_model_response(model, inputs, request.top_k, request.top_p, request.temperature)
         best_response = responses[0] if responses else {}
         unique_responses = remove_repetitive_responses(responses)
         return {