search

sacdallago / bio_embeddings

Get protein embeddings from protein sequences
http://docs.bioembeddings.com
MIT License
460 stars 65 forks source link

Protocol prottrans_bert_bfd: OSError: Unable to load weights from pytorch checkpoint file for .catch/bio_embeddings/prottrans_bert_bfd/model_directory/pytorch_model.bin' at '.catch/bio_embeddings/prottrans_bert_bfd/model_directory/pytorch_model.bin'. If you tried to load a PyTorch model from a TF 2.0 checkpoint, please set from_tf=True. #242

Open Meng-AnunaAI opened 7 months ago

Meng-AnunaAI commented 7 months ago

Metadata

key value
version 0.2.2
cuda False

Parameter

key value
type embed
protocol prottrans_bert_bfd
reduce True
discard_per_amino_acid_embeddings True

Traceback

Traceback (most recent call last):
  File "/home/mengma/miniconda3/envs/Interactome/lib/python3.8/site-packages/transformers/modeling_utils.py", line 533, in load_state_dict
    return torch.load(
  File "/home/mengma/miniconda3/envs/Interactome/lib/python3.8/site-packages/torch/serialization.py", line 608, in load
    return _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args)
  File "/home/mengma/miniconda3/envs/Interactome/lib/python3.8/site-packages/torch/serialization.py", line 777, in _legacy_load
    magic_number = pickle_module.load(f, **pickle_load_args)
**TypeError: 'weights_only' is an invalid keyword argument for load()**

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/home/mengma/miniconda3/envs/Interactome/lib/python3.8/site-packages/transformers/modeling_utils.py", line 542, in load_state_dict
    if f.read(7) == "version":
  File "/home/mengma/miniconda3/envs/Interactome/lib/python3.8/codecs.py", line 322, in decode
    (result, consumed) = self._buffer_decode(data, self.errors, final)
UnicodeDecodeError: 'utf-8' codec can't decode byte 0x80 in position 0: invalid start byte

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/home/mengma/miniconda3/envs/Interactome/lib/python3.8/site-packages/bio_embeddings/utilities/pipeline.py", line 284, in execute_pipeline_from_config
    stage_output_parameters = stage_runnable(**stage_parameters)
  File "/home/mengma/miniconda3/envs/Interactome/lib/python3.8/site-packages/bio_embeddings/embed/pipeline.py", line 400, in run
    embedder: EmbedderInterface = embedder_class(**result_kwargs)
  File "/home/mengma/miniconda3/envs/Interactome/lib/python3.8/site-packages/bio_embeddings/embed/prottrans_bert_bfd_embedder.py", line 36, in __init__
    self._model = BertModel.from_pretrained(self._model_directory)
  File "/home/mengma/miniconda3/envs/Interactome/lib/python3.8/site-packages/transformers/modeling_utils.py", line 3527, in from_pretrained
    state_dict = load_state_dict(resolved_archive_file)
  File "/home/mengma/miniconda3/envs/Interactome/lib/python3.8/site-packages/transformers/modeling_utils.py", line 554, in load_state_dict
    raise OSError(
OSError: Unable to load weights from pytorch checkpoint file for '/home/mengma/.cache/bio_embeddings/prottrans_bert_bfd/model_directory/pytorch_model.bin' at '/home/mengma/.cache/bio_embeddings/prottrans_bert_bfd/model_directory/pytorch_model.bin'. If you tried to load a PyTorch model from a TF 2.0 checkpoint, please set from_tf=True.

More info