使用opencompass eval 报错

[dage1210]

想使用eval测评一下1B左右的模型，能到多少分，但出现以下错误。
好像是模型结构的问题，请楼主帮忙看看。

Traceback (most recent call last):
File "/home/haitaiwork/pbg/eval/opencompass-main/opencompass/tasks/openicl_infer.py", line 162, in
inferencer.run()
File "/home/haitaiwork/pbg/eval/opencompass-main/opencompass/tasks/openicl_infer.py", line 73, in run
self.model = build_model_from_cfg(model_cfg)
File "/home/haitaiwork/pbg/eval/opencompass-main/opencompass/utils/build.py", line 25, in build_model_from_cfg
return MODELS.build(model_cfg)
File "/home/haitaiwork/llm/anaconda3/lib/python3.10/site-packages/mmengine/registry/registry.py", line 570, in build
return self.build_func(cfg, *args, **kwargs, registry=self)
File "/home/haitaiwork/llm/anaconda3/lib/python3.10/site-packages/mmengine/registry/build_functions.py", line 121, in build_from_cfg
obj = obj_cls(**args) # type: ignore
File "/home/haitaiwork/pbg/eval/opencompass-main/opencompass/models/huggingface_above_v4_33.py", line 166, in init
self._load_tokenizer(tokenizer_path or path, tokenizer_kwargs, pad_token_id)
File "/home/haitaiwork/pbg/eval/opencompass-main/opencompass/models/huggingface_above_v4_33.py", line 183, in _load_tokenizer
self.tokenizer = AutoTokenizer.from_pretrained(path, **tokenizer_kwargs)
File "/home/haitaiwork/llm/anaconda3/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py", line 880, in from_pretrained
return tokenizer_class.from_pretrained(pretrained_model_name_or_path, *inputs, **kwargs)
File "/home/haitaiwork/llm/anaconda3/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line 2110, in from_pretrained
return cls._from_pretrained(
File "/home/haitaiwork/llm/anaconda3/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line 2336, in _from_pretrained
tokenizer = cls(*init_inputs, **init_kwargs)
File "/home/haitaiwork/llm/anaconda3/lib/python3.10/site-packages/transformers/models/qwen2/tokenization_qwen2_fast.py", line 120, in init
super().init(
File "/home/haitaiwork/llm/anaconda3/lib/python3.10/site-packages/transformers/tokenization_utils_fast.py", line 114, in init
fast_tokenizer = TokenizerFast.from_file(fast_tokenizer_file)
Exception: data did not match any variant of untagged enum ModelWrapper at line 757443 column 3
E0120 10:43:50.609000 139627271737856 torch/distributed/elastic/multiprocessing/api.py:833] failed (exitcode: 1) local_rank: 0 (pid: 8743) of binary: /home/haitaiwork/llm/anaconda3/bin/python

Traceback (most recent call last):
File "/home/haitaiwork/llm/anaconda3/bin/torchrun", line 8, in
sys.exit(main())
File "/home/haitaiwork/llm/anaconda3/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/init.py", line 348, in wrapper
return f(*args, **kwargs)
File "/home/haitaiwork/llm/anaconda3/lib/python3.10/site-packages/torch/distributed/run.py", line 901, in main
run(args)
File "/home/haitaiwork/llm/anaconda3/lib/python3.10/site-packages/torch/distributed/run.py", line 892, in run
elastic_launch(
File "/home/haitaiwork/llm/anaconda3/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 133, in call
return launch_agent(self._config, self._entrypoint, list(args))
File "/home/haitaiwork/llm/anaconda3/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 264, in launch_agent
raise ChildFailedError(
torch.distributed.elastic.multiprocessing.errors.ChildFailedError: