Update app.py

app.py

@@ -30,7 +30,7 @@ client = InferenceClient(model_id)
 # stop_token_ids = [torch.LongTensor(x).to(cuda.current_device() if cuda.is_available() else 'cpu') for x in stop_token_ids]
 
 # Create text generation pipeline
-def generate(prompt, history, system_prompt=None, temperature=0.2, max_new_tokens=1024, top_p=0.95, repetition_penalty=1.0):
+def generate(prompt, history = None, system_prompt=None, temperature=0.2, max_new_tokens=1024, top_p=0.95, repetition_penalty=1.0):
     temperature = float(temperature)
     if temperature < 1e-2:
         temperature = 1e-2