Week 0 inference does not work

[KansaiUser]

I run the train.py script, but when I try the inference.py I got

python inference.py 
/home/me/anaconda3/envs/MLProj38/lib/python3.8/site-packages/transformers/tokenization_utils_base.py:1601: FutureWarning: `clean_up_tokenization_spaces` was not set. It will be set to `True` by default. This behavior will be depracted in transformers v4.45, and will be then set to `False` by default. For more details check this issue: https://github.com/huggingface/transformers/issues/31884
  warnings.warn(
Traceback (most recent call last):
  File "inference.py", line 34, in <module>
    print(predictor.predict(sentence))
  File "inference.py", line 19, in predict
    logits = self.model(
  File "/home/me/anaconda3/envs/MLProj38/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/home/me/anaconda3/envs/MLProj38/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl
    return forward_call(*args, **kwargs)
  File "/media/sensetime/cbe421fe-1303-4821-9392-a849bfdd00e21/MyStudy/MLOps/MLOps-Basics/week_0_project_setup/model.py", line 19, in forward
    outputs = self.bert(input_ids=input_ids, attention_mask=attention_mask)
  File "/home/me/anaconda3/envs/MLProj38/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/home/me/anaconda3/envs/MLProj38/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl
    return forward_call(*args, **kwargs)
  File "/home/me/anaconda3/envs/MLProj38/lib/python3.8/site-packages/transformers/models/bert/modeling_bert.py", line 1077, in forward
    embedding_output = self.embeddings(
  File "/home/me/anaconda3/envs/MLProj38/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/home/me/anaconda3/envs/MLProj38/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl
    return forward_call(*args, **kwargs)
  File "/home/me/anaconda3/envs/MLProj38/lib/python3.8/site-packages/transformers/models/bert/modeling_bert.py", line 210, in forward
    inputs_embeds = self.word_embeddings(input_ids)
  File "/home/me/anaconda3/envs/MLProj38/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/home/me/anaconda3/envs/MLProj38/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl
    return forward_call(*args, **kwargs)
  File "/home/me/anaconda3/envs/MLProj38/lib/python3.8/site-packages/torch/nn/modules/sparse.py", line 164, in forward
    return F.embedding(
  File "/home/me/anaconda3/envs/MLProj38/lib/python3.8/site-packages/torch/nn/functional.py", line 2267, in embedding
    return torch.embedding(weight, input, padding_idx, scale_grad_by_freq, sparse)
RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu! (when checking argument for argument index in method wrapper_CUDA__index_select)

Apparently the error is on

logits = self.model(
            torch.tensor([processed["input_ids"]]),
            torch.tensor([processed["attention_mask"]]),
        )

Any idea how to make the script work?

By the way the link to the posts is dead so there is no explanation to the code here