Using Seq2rel function with cuda

[jjyhh1223]

Here's how I pass the device argument for function Seq2rel

from seq2rel import Seq2Rel
from seq2rel.common import util
model = 'model.tar.gz'
kwargs = {'cuda_device': 1}
seq2rel = Seq2Rel(model, **kwargs)

and got this error:

---------------------------------------------------------------------------
RuntimeError                              Traceback (most recent call last)
[<ipython-input-15-d951d9bfd1c5>](https://localhost:8080/#) in <cell line: 2>()
      1 kwargs = {'cuda_device': 1}
----> 2 seq2rel = Seq2Rel(model, **kwargs)

12 frames
[/content/drive/MyDrive/seq2rel/seq2rel/seq2rel.py](https://localhost:8080/#) in __init__(self, pretrained_model_name_or_path, **kwargs)
     86         if "overrides" in kwargs:
     87             overrides.update(kwargs.pop("overrides"))
---> 88         archive = load_archive(pretrained_model_name_or_path, overrides=overrides, **kwargs)
     89         self._predictor = Predictor.from_archive(archive, predictor_name="seq2seq")
     90 

[/usr/local/lib/python3.9/dist-packages/allennlp/models/archival.py](https://localhost:8080/#) in load_archive(archive_file, cuda_device, overrides, weights_file)
    233             config.duplicate(), serialization_dir
    234         )
--> 235         model = _load_model(config.duplicate(), weights_path, serialization_dir, cuda_device)
    236 
    237         # Load meta.

[/usr/local/lib/python3.9/dist-packages/allennlp/models/archival.py](https://localhost:8080/#) in _load_model(config, weights_path, serialization_dir, cuda_device)
    277 
    278 def _load_model(config, weights_path, serialization_dir, cuda_device):
--> 279     return Model.load(
    280         config,
    281         weights_file=weights_path,

[/usr/local/lib/python3.9/dist-packages/allennlp/models/model.py](https://localhost:8080/#) in load(cls, config, serialization_dir, weights_file, cuda_device)
    436             # get_model_class method, that recurses whenever it finds a from_archive model type.
    437             model_class = Model
--> 438         return model_class._load(config, serialization_dir, weights_file, cuda_device)
    439 
    440     def extend_embedder_vocab(self, embedding_sources_mapping: Dict[str, str] = None) -> None:

[/usr/local/lib/python3.9/dist-packages/allennlp/models/model.py](https://localhost:8080/#) in _load(cls, config, serialization_dir, weights_file, cuda_device)
    341         # in sync with the weights
    342         if cuda_device >= 0:
--> 343             model.cuda(cuda_device)
    344         else:
    345             model.cpu()

[/usr/local/lib/python3.9/dist-packages/torch/nn/modules/module.py](https://localhost:8080/#) in cuda(self, device)
    686             Module: self
    687         """
--> 688         return self._apply(lambda t: t.cuda(device))
    689 
    690     def xpu(self: T, device: Optional[Union[int, device]] = None) -> T:

[/usr/local/lib/python3.9/dist-packages/torch/nn/modules/module.py](https://localhost:8080/#) in _apply(self, fn)
    576     def _apply(self, fn):
    577         for module in self.children():
--> 578             module._apply(fn)
    579 
    580         def compute_should_use_set_data(tensor, tensor_applied):

[/usr/local/lib/python3.9/dist-packages/torch/nn/modules/module.py](https://localhost:8080/#) in _apply(self, fn)
    576     def _apply(self, fn):
    577         for module in self.children():
--> 578             module._apply(fn)
    579 
    580         def compute_should_use_set_data(tensor, tensor_applied):

[/usr/local/lib/python3.9/dist-packages/torch/nn/modules/module.py](https://localhost:8080/#) in _apply(self, fn)
    576     def _apply(self, fn):
    577         for module in self.children():
--> 578             module._apply(fn)
    579 
    580         def compute_should_use_set_data(tensor, tensor_applied):

[/usr/local/lib/python3.9/dist-packages/torch/nn/modules/module.py](https://localhost:8080/#) in _apply(self, fn)
    576     def _apply(self, fn):
    577         for module in self.children():
--> 578             module._apply(fn)
    579 
    580         def compute_should_use_set_data(tensor, tensor_applied):

[/usr/local/lib/python3.9/dist-packages/torch/nn/modules/module.py](https://localhost:8080/#) in _apply(self, fn)
    576     def _apply(self, fn):
    577         for module in self.children():
--> 578             module._apply(fn)
    579 
    580         def compute_should_use_set_data(tensor, tensor_applied):

[/usr/local/lib/python3.9/dist-packages/torch/nn/modules/module.py](https://localhost:8080/#) in _apply(self, fn)
    599             # `with torch.no_grad():`
    600             with torch.no_grad():
--> 601                 param_applied = fn(param)
    602             should_use_set_data = compute_should_use_set_data(param, param_applied)
    603             if should_use_set_data:

[/usr/local/lib/python3.9/dist-packages/torch/nn/modules/module.py](https://localhost:8080/#) in <lambda>(t)
    686             Module: self
    687         """
--> 688         return self._apply(lambda t: t.cuda(device))
    689 
    690     def xpu(self: T, device: Optional[Union[int, device]] = None) -> T:

RuntimeError: CUDA error: invalid device ordinal
CUDA kernel errors might be asynchronously reported at some other API call,so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1.

What is the correct way of using Seq2rel with cuda? Thank you!