You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
12 pretrained_model = DonutModel.from_pretrained(args.pretrained_path)
13
14 if torch.cuda.is_available():
2 frames /usr/local/lib/python3.10/dist-packages/transformers/modeling_utils.py in _load_pretrained_model(cls, model, state_dict, loaded_keys, resolved_archive_file, pretrained_model_name_or_path, ignore_mismatched_sizes, sharded_metadata, _fast_init, low_cpu_mem_usage, device_map, offload_folder, offload_state_dict, dtype, is_quantized, keep_in_fp32_modules)
3929 "\n\tYou may consider adding ignore_mismatched_sizes=True in the model from_pretrained method."
3930 )
-> 3931 raise RuntimeError(f"Error(s) in loading state_dict for {model.class.name}:\n\t{error_msg}")
3932
3933 if is_quantized:
RuntimeError: Error(s) in loading state_dict for DonutModel:
size mismatch for encoder.model.layers.1.downsample.norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([512]).
size mismatch for encoder.model.layers.1.downsample.norm.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([512]).
size mismatch for encoder.model.layers.1.downsample.reduction.weight: copying a param with shape torch.Size([512, 1024]) from checkpoint, the shape in current model is torch.Size([256, 512]).
size mismatch for encoder.model.layers.2.downsample.norm.weight: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for encoder.model.layers.2.downsample.norm.bias: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for encoder.model.layers.2.downsample.reduction.weight: copying a param with shape torch.Size([1024, 2048]) from checkpoint, the shape in current model is torch.Size([512, 1024]).
You may consider adding ignore_mismatched_sizes=True in the model from_pretrained method.
The text was updated successfully, but these errors were encountered:
It seems to be a problem of incorrect package version.
After changing transformers to version 4.25.1 and timm to version 0.5.4, I have solved this problem.
12 pretrained_model = DonutModel.from_pretrained(args.pretrained_path)
13
14 if torch.cuda.is_available():
2 frames
/usr/local/lib/python3.10/dist-packages/transformers/modeling_utils.py in _load_pretrained_model(cls, model, state_dict, loaded_keys, resolved_archive_file, pretrained_model_name_or_path, ignore_mismatched_sizes, sharded_metadata, _fast_init, low_cpu_mem_usage, device_map, offload_folder, offload_state_dict, dtype, is_quantized, keep_in_fp32_modules)
3929 "\n\tYou may consider adding
ignore_mismatched_sizes=True
in the modelfrom_pretrained
method."3930 )
-> 3931 raise RuntimeError(f"Error(s) in loading state_dict for {model.class.name}:\n\t{error_msg}")
3932
3933 if is_quantized:
RuntimeError: Error(s) in loading state_dict for DonutModel:
size mismatch for encoder.model.layers.1.downsample.norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([512]).
size mismatch for encoder.model.layers.1.downsample.norm.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([512]).
size mismatch for encoder.model.layers.1.downsample.reduction.weight: copying a param with shape torch.Size([512, 1024]) from checkpoint, the shape in current model is torch.Size([256, 512]).
size mismatch for encoder.model.layers.2.downsample.norm.weight: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for encoder.model.layers.2.downsample.norm.bias: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for encoder.model.layers.2.downsample.reduction.weight: copying a param with shape torch.Size([1024, 2048]) from checkpoint, the shape in current model is torch.Size([512, 1024]).
You may consider adding
ignore_mismatched_sizes=True
in the modelfrom_pretrained
method.The text was updated successfully, but these errors were encountered: