AttributeErrorAttributeError: : 'BiRefNet' object has no attribute

[Notbici]

This is for bugs only

Did you already ask in the discord?

Yes/No

You verified that this is a bug and not a feature request or question by asking in the discord?

Yes/No

Describe the bug

Under a fresh install on Linux:

Error running job: 'BiRefNet' object has no attribute 'all_tied_weights_keys'
========================================
Result:
 - 0 completed jobs
 - 1 failure
========================================
Traceback (most recent call last):
Traceback (most recent call last):
  File "/ai-toolkit/run.py", line 135, in <module>
  File "/ai-toolkit/run.py", line 135, in <module>
        main()main()
  File "/ai-toolkit/run.py", line 123, in main
  File "/ai-toolkit/run.py", line 123, in main
        raise eraise e
  File "/ai-toolkit/run.py", line 111, in main
  File "/ai-toolkit/run.py", line 111, in main
        job.run()job.run()
  File "/ai-toolkit/jobs/ExtensionJob.py", line 22, in run
  File "/ai-toolkit/jobs/ExtensionJob.py", line 22, in run
        process.run()process.run()
  File "/ai-toolkit/jobs/process/BaseSDTrainProcess.py", line 2046, in run
  File "/ai-toolkit/jobs/process/BaseSDTrainProcess.py", line 2046, in run
        self.data_loader = get_dataloader_from_datasets(self.datasets, self.train_config.batch_size, self.sd)self.data_loader = get_dataloader_from_datasets(self.datasets, self.train_config.batch_size, self.sd)
                                              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/ai-toolkit/toolkit/data_loader.py", line 666, in get_dataloader_from_datasets
  File "/ai-toolkit/toolkit/data_loader.py", line 666, in get_dataloader_from_datasets
        dataset = AiToolkitDataset(config, batch_size=batch_size, sd=sd)dataset = AiToolkitDataset(config, batch_size=batch_size, sd=sd)
                            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/ai-toolkit/toolkit/data_loader.py", line 589, in __init__
  File "/ai-toolkit/toolkit/data_loader.py", line 589, in __init__
        self.setup_epoch()self.setup_epoch()
  File "/ai-toolkit/toolkit/data_loader.py", line 606, in setup_epoch
  File "/ai-toolkit/toolkit/data_loader.py", line 606, in setup_epoch
        self.setup_controls()self.setup_controls()
  File "/ai-toolkit/toolkit/dataloader_mixins.py", line 2330, in setup_controls
  File "/ai-toolkit/toolkit/dataloader_mixins.py", line 2330, in setup_controls
        control_path = self.control_generator.get_control_path(file_item.path, control_type)control_path = self.control_generator.get_control_path(file_item.path, control_type)
                                      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/ai-toolkit/toolkit/control_generator.py", line 54, in get_control_path
  File "/ai-toolkit/toolkit/control_generator.py", line 54, in get_control_path
        return self._generate_control(img_path, control_type)return self._generate_control(img_path, control_type)
                      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/ai-toolkit/toolkit/control_generator.py", line 156, in _generate_control
  File "/ai-toolkit/toolkit/control_generator.py", line 156, in _generate_control
        self.control_bg_remover = AutoModelForImageSegmentation.from_pretrained(self.control_bg_remover = AutoModelForImageSegmentation.from_pretrained(
                                                            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/ai-toolkit/venv/lib/python3.12/site-packages/transformers/models/auto/auto_factory.py", line 380, in from_pretrained
  File "/ai-toolkit/venv/lib/python3.12/site-packages/transformers/models/auto/auto_factory.py", line 380, in from_pretrained
        return model_class.from_pretrained(return model_class.from_pretrained(
                      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/ai-toolkit/venv/lib/python3.12/site-packages/transformers/modeling_utils.py", line 4246, in from_pretrained
  File "/ai-toolkit/venv/lib/python3.12/site-packages/transformers/modeling_utils.py", line 4246, in from_pretrained
        loading_info = cls._finalize_model_loading(model, load_config, loading_info)loading_info = cls._finalize_model_loading(model, load_config, loading_info)
                                      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/ai-toolkit/venv/lib/python3.12/site-packages/transformers/modeling_utils.py", line 4402, in _finalize_model_loading
  File "/ai-toolkit/venv/lib/python3.12/site-packages/transformers/modeling_utils.py", line 4402, in _finalize_model_loading
        model._move_missing_keys_from_meta_to_device(model._move_missing_keys_from_meta_to_device(
  File "/ai-toolkit/venv/lib/python3.12/site-packages/transformers/modeling_utils.py", line 4665, in _move_missing_keys_from_meta_to_device
  File "/ai-toolkit/venv/lib/python3.12/site-packages/transformers/modeling_utils.py", line 4665, in _move_missing_keys_from_meta_to_device
        for key in missing_keys - self.all_tied_weights_keys.keys():for key in missing_keys - self.all_tied_weights_keys.keys():
                                                            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/ai-toolkit/venv/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1964, in __getattr__
  File "/ai-toolkit/venv/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1964, in __getattr__
        raise AttributeError(raise AttributeError(
AttributeErrorAttributeError: : 'BiRefNet' object has no attribute 'all_tied_weights_keys''BiRefNet' object has no attribute 'all_tied_weights_keys'. Did you mean: '_tied_weights_keys'?. Did you mean: '_tied_weights_keys'?

I followed the readme instructions for Linux, added some training data, setup a new job for Flux2, didnt touch any other settings besides Differential Ouput Preservation and started.

It downloaded all the models, but the error looks more like a bug? Is there something I missed in the readme?