启动int4的v2.5模型出错

[lingyezhixing]

是否已有关于该错误的issue或讨论？ | Is there an existing issue / discussion for this?

• [X] 我已经搜索过已有的issues和讨论 | I have searched the existing issues / discussions

该问题是否在FAQ中有解答？ | Is there an existing answer for this in FAQ?

• [X] 我已经搜索过FAQ | I have searched FAQ

当前行为 | Current Behavior

load_model_and_tokenizer from D:\LLM\models\LLM\OpenBMB\minicpm-v2.5 2024-05-28 23:14:15.301 Uncaught app exception Traceback (most recent call last): File "D:\LLM\MiniCPM-V\runtime\lib\site-packages\streamlit\runtime\scriptrunner\script_runner.py", line 600, in _run_script exec(code, module.dict) File "D:\LLM\MiniCPM-V\web_demo_streamlit-2_5.py", line 32, in st.session_state.model, st.session_state.tokenizer = load_model_and_tokenizer() File "D:\LLM\MiniCPM-V\runtime\lib\site-packages\streamlit\runtime\caching\cache_utils.py", line 165, in wrapper return cached_func(*args, *kwargs) File "D:\LLM\MiniCPM-V\runtime\lib\site-packages\streamlit\runtime\caching\cache_utils.py", line 194, in call return self._get_or_create_cached_value(args, kwargs) File "D:\LLM\MiniCPM-V\runtime\lib\site-packages\streamlit\runtime\caching\cache_utils.py", line 221, in _get_or_create_cached_value return self._handle_cache_miss(cache, value_key, func_args, func_kwargs) File "D:\LLM\MiniCPM-V\runtime\lib\site-packages\streamlit\runtime\caching\cache_utils.py", line 277, in _handle_cache_miss computed_value = self._info.func(func_args, **func_kwargs) File "D:\LLM\MiniCPM-V\web_demo_streamlit-2_5.py", line 25, in load_model_and_tokenizer model = AutoModel.from_pretrained(model_path, trust_remote_code=True, torch_dtype=torch.float16).to(device="cuda") File "D:\LLM\MiniCPM-V\runtime\lib\site-packages\transformers\models\auto\auto_factory.py", line 550, in from_pretrained model_class = get_class_from_dynamic_module( File "D:\LLM\MiniCPM-V\runtime\lib\site-packages\transformers\dynamic_module_utils.py", line 501, in get_class_from_dynamic_module return get_class_in_module(class_name, final_module) File "D:\LLM\MiniCPM-V\runtime\lib\site-packages\transformers\dynamic_module_utils.py", line 201, in get_class_in_module module = importlib.machinery.SourceFileLoader(name, module_path).load_module() File "", line 548, in _check_name_wrapper File "", line 1063, in load_module File "", line 888, in load_module File "", line 290, in _load_module_shim File "", line 719, in _load File "", line 688, in _load_unlocked File "", line 883, in exec_module File "", line 241, in _call_with_frames_removed File "C:\Users\31940.cache\huggingface\modules\transformers_modules\minicpm-v2.5\modeling_minicpmv.py", line 14, in from .resampler import Resampler ModuleNotFoundError: No module named 'transformers_modules.minicpm-v2'

期望行为 | Expected Behavior

No response

复现方法 | Steps To Reproduce

No response

运行环境 | Environment

- OS:win11
- Python:3.10
- transformers:4.40.0
- CUDA (`python -c 'import torch; print(torch.version.cuda)'`):12.4

备注 | Anything else?

No response

[iceflame89]

由于transformers dynamic import 机制问题，模型目录不能带有小数点 请将模型目录minicpm-v2.5改成minicpm-v2_5后重试

[lingyezhixing]

由于transformers dynamic import 机制问题，模型目录不能带有小数点 请将模型目录minicpm-v2.5改成minicpm-v2_5后重试 已解决，感谢