原模型能在mindie镜像下跑通推理，微调后的模型报错：

Traceback (most recent call last):

  File "/usr/local/python3.10.2/lib/python3.10/runpy.py", line 196, in _run_module_as_main

    return _run_code(code, main_globals, None,

  File "/usr/local/python3.10.2/lib/python3.10/runpy.py", line 86, in _run_code

    exec(code, run_globals)

  File "/usr/local/Ascend/llm_model/examples/run_pa.py", line 345, in <module>

    pa_runner = PARunner(**input_dict)

  File "/usr/local/Ascend/llm_model/examples/run_pa.py", line 40, in __init__

    self.model = ModelRunner(

  File "/usr/local/Ascend/llm_model/atb_llm/runner/model_runner.py", line 44, in __init__

    self.config = router_ins.config

  File "/usr/local/Ascend/llm_model/atb_llm/models/base/router.py", line 40, in config

    self._config = self.get_config()

  File "/usr/local/Ascend/llm_model/atb_llm/models/qwen2/router_qwen2.py", line 16, in get_config

    self.checkout_config_qwen(config)

  File "/usr/local/Ascend/llm_model/atb_llm/models/qwen2/router_qwen2.py", line 39, in checkout_config_qwen

    if value < min_val or value > max_val:

TypeError: '<' not supported between instances of 'NoneType' and 'int'

[ERROR] 2024-11-01-08:10:42 (PID:134133, Device:-1, RankID:-1) ERR99999 UNKNOWN application exception

[2024-11-01 08:10:45,284] torch.distributed.elastic.multiprocessing.api: [ERROR] failed (exitcode: 1) local_rank: 0 (pid: 134128) of binary: /usr/local/python3.10.2/bin/python3.10