feat: 最大2分钟

app.py

@@ -10,7 +10,7 @@ subprocess.run('pip install flash-attn --no-build-isolation', env={'FLASH_ATTENT
 tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct", trust_remote_code=True)
 model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct", trust_remote_code=True, torch_dtype=torch.bfloat16).cuda()
 
-@spaces.GPU(duration=300)
+@spaces.GPU(duration=120)
 def respond(
     message,
     history: list[tuple[str, str]],