[Bug] Failed to start up after upgrade to v2.0.2 from v2.0.1 #3835
Description
Contact Information
No response
MaxKB Version
v2.0.2
Problem Description
2025-08-01 00:20:23 [handle_exception ERROR] Unable to load weights from pytorch checkpoint file for '/opt/maxkb/local/models/bge-m3/pytorch_model.bin' at '/opt/maxkb/local/models/bge-m3/pytorch_model.bin'. If you tried to load a PyTorch model from a TF 2.0 checkpoint, please set from_tf=True.:Traceback (most recent call last):
File "/opt/py3/lib/python3.11/site-packages/transformers/modeling_utils.py", line 574, in load_state_dict
return torch.load(
^^^^^^^^^^^
File "/opt/py3/lib/python3.11/site-packages/torch/serialization.py", line 1511, in load
overall_storage = torch.UntypedStorage.from_file(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: unable to mmap 2271145830 bytes from file </opt/maxkb/local/models/bge-m3/pytorch_model.bin>: Cannot allocate memory (12)
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/opt/py3/lib/python3.11/site-packages/transformers/modeling_utils.py", line 583, in load_state_dict
if f.read(7) == "version":
^^^^^^^^^
File "", line 322, in decode
UnicodeDecodeError: 'utf-8' codec can't decode byte 0x80 in position 64: invalid start byte
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/opt/py3/lib/python3.11/site-packages/rest_framework/views.py", line 512, in dispatch
response = handler(request, *args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/maxkb-app/community/apps/models_provider/views/model_apply.py", line 33, in post
File "/opt/maxkb-app/community/apps/models_provider/serializers/model_apply_serializers.py", line 58, in embed_documents
File "/opt/maxkb-app/community/apps/models_provider/serializers/model_apply_serializers.py", line 25, in get_embedding_model
File "/opt/maxkb-app/community/apps/common/config/embedding_config.py", line 43, in get_model
File "/opt/maxkb-app/community/apps/models_provider/serializers/model_apply_serializers.py", line 26, in
File "/opt/maxkb-app/community/apps/models_provider/tools.py", line 50, in get_model
File "/opt/maxkb-app/community/apps/models_provider/tools.py", line 35, in get_model_
File "/opt/maxkb-app/community/apps/models_provider/base_model_provider.py", line 79, in get_model
File "/opt/maxkb-app/community/apps/models_provider/impl/local_model_provider/model/embedding.py", line 57, in new_instance
File "/opt/py3/lib/python3.11/site-packages/langchain_huggingface/embeddings/huggingface.py", line 94, in init
self._client = model_cls(
^^^^^^^^^^
File "/opt/py3/lib/python3.11/site-packages/sentence_transformers/SentenceTransformer.py", line 327, in init
modules, self.module_kwargs = self._load_sbert_model(
^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/py3/lib/python3.11/site-packages/sentence_transformers/SentenceTransformer.py", line 2254, in _load_sbert_model
module = module_class.load(
^^^^^^^^^^^^^^^^^^
File "/opt/py3/lib/python3.11/site-packages/sentence_transformers/models/Transformer.py", line 541, in load
return cls(model_name_or_path=model_name_or_path, **init_kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/py3/lib/python3.11/site-packages/sentence_transformers/models/Transformer.py", line 88, in init
self._load_model(model_name_or_path, config, cache_dir, backend, is_peft_model, **model_args)
File "/opt/py3/lib/python3.11/site-packages/sentence_transformers/models/Transformer.py", line 186, in _load_model
self.auto_model = AutoModel.from_pretrained(
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/py3/lib/python3.11/site-packages/transformers/models/auto/auto_factory.py", line 600, in from_pretrained
return model_class.from_pretrained(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/py3/lib/python3.11/site-packages/transformers/modeling_utils.py", line 311, in _wrapper
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "/opt/py3/lib/python3.11/site-packages/transformers/modeling_utils.py", line 4839, in from_pretrained
) = cls._load_pretrained_model(
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/py3/lib/python3.11/site-packages/transformers/modeling_utils.py", line 5302, in _load_pretrained_model
_error_msgs, disk_offload_index, cpu_offload_index = load_shard_file(args)
^^^^^^^^^^^^^^^^^^^^^
File "/opt/py3/lib/python3.11/site-packages/transformers/modeling_utils.py", line 920, in load_shard_file
state_dict = load_state_dict(
^^^^^^^^^^^^^^^^
File "/opt/py3/lib/python3.11/site-packages/transformers/modeling_utils.py", line 595, in load_state_dict
raise OSError(
OSError: Unable to load weights from pytorch checkpoint file for '/opt/maxkb/local/models/bge-m3/pytorch_model.bin' at '/opt/maxkb/local/models/bge-m3/pytorch_model.bin'. If you tried to load a PyTorch model from a TF 2.0 checkpoint, please set from_tf=True.
2025-08-01 00:20:23 [listener_manage ERROR] 向量段落: 01986140-4f35-7ed2-b0e3-6f2b92d80854 错误：Unable to load weights from pytorch checkpoint file for '/opt/maxkb/local/models/bge-m3/pytorch_model.bin' at '/opt/maxkb/local/models/bge-m3/pytorch_model.bin'. If you tried to load a PyTorch model from a TF 2.0 checkpoint, please set from_tf=True. Traceback (most recent call last):
File "/opt/maxkb-app/community/apps/common/event/listener_manage.py", line 148, in embedding_by_paragraph
File "/opt/maxkb-app/community/apps/knowledge/vector/base_vector.py", line 102, in batch_save
File "/opt/maxkb-app/community/apps/knowledge/vector/pg_vector.py", line 66, in _batch_save
File "/opt/maxkb-app/community/apps/models_provider/impl/local_model_provider/model/embedding.py", line 49, in embed_documents
Exception: Unable to load weights from pytorch checkpoint file for '/opt/maxkb/local/models/bge-m3/pytorch_model.bin' at '/opt/maxkb/local/models/bge-m3/pytorch_model.bin'. If you tried to load a PyTorch model from a TF 2.0 checkpoint, please set from_tf=True.
Steps to Reproduce
run upgrade script of v2.0.2 for the upgrade from 2.0.1
The expected correct result
No response
Related log output
Additional Information
No response