ModelScope中，部署FC使用时出现这种错误，请帮忙看下？

ModelScope中，部署FC使用时出现这种错误：response: {'Code': 400, 'Data': '', 'Message': '[\' File "/usr/src/app/app.py", line 96, in invoke\n pred = pipe.generate(inputs)\n\', \' File "/root/.cache/huggingface/modules/transformers_modules/Qwen-7B/modeling_qwen.py", line 1318, in generate\n return super().generate(\n\', \' File "/opt/conda/lib/python3.8/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context\n return func(*args, kwargs)\n\', \' File "/opt/conda/lib/python3.8/site-packages/transformers/generation/utils.py", line 1572, in generate\n return self.sample(\n\', \' File "/opt/conda/lib/python3.8/site-packages/transformers/generation/utils.py", line 2619, in sample\n outputs = self(\n\', \' File "/opt/conda/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl\n return forward_call(args, **kwargs)\n\', \' File "/opt/conda/lib/python3.8/site-packages/accelerate/hooks.py", line 165, in new_forward\n output = old_forward(args, kwargs)\n\', \' File "/root/.cache/huggingface/modules/transformers_modules/Qwen-7B/modeling_qwen.py", line 1125, in forward\n lm_logits = self.lm_head(hidden_states)\n\', \' File "/opt/conda/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl\n return forward_call(*args, kwargs)\n\', \' File "/opt/conda/lib/python3.8/site-packages/accelerate/hooks.py", line 160, in new_forward\n args, kwargs = module._hf_hook.pre_forward(module, args, *kwargs)\n\', \' File "/opt/conda/lib/python3.8/site-packages/accelerate/hooks.py", line 286, in pre_forward\n set_module_tensor_to_device(\n\', \' File "/opt/conda/lib/python3.8/site-packages/accelerate/utils/modeling.py", line 298, in set_module_tensor_to_device\n new_value = value.to(device)\n\']', 'RequestId': '1-6523828a-667832bb3fe6fb5817f7de2a', 'Success': False}modelscope上的代码可以，我想尝试使用API的方式