Update app.py

app.py

@@ -9,7 +9,8 @@ model = AutoModelForCausalLM.from_pretrained("BirdL/DeepSeek-Coder-V2-Lite-Instr
 @spaces.GPU
 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)
+    outputs = model.generate(inputs, max_new_tokens=192, do_sample=False, top_k=50, top_p=0.95, num_return_sequences=1, eos_token_id=tokenizer.eos_token_id)
+    ouputs = (tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True))
     return outputs
 
 demo = gr.ChatInterface(respond)