Update app.py

app.py

@@ -7,7 +7,7 @@ tokenizer = AutoTokenizer.from_pretrained("BirdL/DeepSeek-Coder-V2-Lite-Instruct
 model = AutoModelForCausalLM.from_pretrained("BirdL/DeepSeek-Coder-V2-Lite-Instruct-FlashAttnPatch", trust_remote_code=True, torch_dtype=torch.bfloat16).cuda()    
 
 @spaces.GPU
-def respond(message):
+def respond(message, history):
     inputs = tokenizer.apply_chat_template(message, add_generation_prompt=True, return_tensors="pt").to(model.device)
     outputs = model.generate(inputs, max_new_tokens=512, do_sample=False, top_k=50, top_p=0.95, num_return_sequences=1, eos_token_id=tokenizer.eos_token_id)
     return outputs