During prediction step, PytorchStreamReader failed reading zip archive: failed finding central directory

Hi again,

Thank you for your help so far. The script is running successfully through the MSA step for me. At the prediction on GPU step, I get the following error:

start to load params ./alphalink_weights.pt
---------------------------------------------------------------------------
RuntimeError                              Traceback (most recent call last)
[<ipython-input-25-da14335aba1a>](https://localhost:8080/#) in <cell line: 5>()
      3 from unifold.colab.model import colab_inference
      4 
----> 5 best_result = colab_inference(
      6     target_id=target_id,
      7     data_dir=output_dir,

2 frames
[/usr/local/lib/python3.10/dist-packages/unifold/colab/model.py](https://localhost:8080/#) in colab_inference(target_id, data_dir, param_dir, output_dir, is_multimer, max_recycling_iters, num_ensembles, times, manual_seed, device)
     44     model = AlphaFold(config)
     45     print("start to load params {}".format(param_path))
---> 46     state_dict = torch.load(param_path)["ema"]["params"]
     47     state_dict = {".".join(k.split(".")[1:]): v for k, v in state_dict.items()}
     48     model.load_state_dict(state_dict)

[/usr/local/lib/python3.10/dist-packages/torch/serialization.py](https://localhost:8080/#) in load(f, map_location, pickle_module, weights_only, mmap, **pickle_load_args)
   1002             orig_position = opened_file.tell()
   1003             overall_storage = None
-> 1004             with _open_zipfile_reader(opened_file) as opened_zipfile:
   1005                 if _is_torchscript_zip(opened_zipfile):
   1006                     warnings.warn("'torch.load' received a zip file that looks like a TorchScript archive"

[/usr/local/lib/python3.10/dist-packages/torch/serialization.py](https://localhost:8080/#) in __init__(self, name_or_buffer)
    454 class _open_zipfile_reader(_opener):
    455     def __init__(self, name_or_buffer) -> None:
--> 456         super().__init__(torch._C.PyTorchFileReader(name_or_buffer))
    457 
    458 

RuntimeError: PytorchStreamReader failed reading zip archive: failed finding central directory

How can this issue be resolved? Thanks again. For reference, I was testing the script with: FASTA: from 2W9Z on PDB Crosslink: 22 A 133 B 0.2

Rappsilber-Laboratory / AlphaLink2

During prediction step, PytorchStreamReader failed reading zip archive: failed finding central directory #26