interactive_shell_NER.ipynb 실행시 model load 부분 문제

[wwjhang]

main() 실행 시 RuntimeError: Input, output and indices must be on the current device라고 뜨면서 NER수행이 안되는데 혹시 수정할 부분 있을까요 의존성은 requirements.txt대로 깔았습니다 ㅠ
전체 에러문입니다.
`RuntimeError Traceback (most recent call last)
Input In [5], in <cell line: 1>()
----> 1 main()

Input In [3], in main()
45 list_of_input_ids = tokenizer.list_of_string_to_list_of_cls_sep_token_ids([input_text])
46 x_input = torch.tensor(list_of_input_ids).long()
---> 47 list_of_pred_ids = model(x_input)
49 list_of_ner_word, decoding_ner_sentence = decoder_from_res(list_of_input_ids=list_of_input_ids, list_of_pred_ids=list_of_pred_ids)
50 print("output>", decoding_ner_sentence)

File /electra/ner_tagging/.venv/lib/python3.8/site-packages/torch/nn/modules/module.py:889, in Module._call_impl(self, *input, **kwargs)
887 result = self._slow_forward(*input, **kwargs)
888 else:
--> 889 result = self.forward(*input, **kwargs)
890 for hook in itertools.chain(
891 _global_forward_hooks.values(),
892 self._forward_hooks.values()):
893 hook_result = hook(self, input, result)

File /electra/ner_tagging/pytorch-bert-crf-ner/model/net.py:41, in KobertCRF.forward(self, input_ids, token_type_ids, tags)
38 attention_mask = input_ids.ne(self.vocab.token_to_idx[self.vocab.padding_token]).float()
40 # outputs: (last_encoder_layer, pooled_output, attention_weight)
---> 41 outputs = self.bert(input_ids=input_ids,
42 token_type_ids=token_type_ids,
43 attention_mask=attention_mask)
44 last_encoder_layer = outputs[0]
45 last_encoder_layer = self.dropout(last_encoder_layer)

File /electra/ner_tagging/.venv/lib/python3.8/site-packages/torch/nn/modules/module.py:889, in Module._call_impl(self, *input, **kwargs)
887 result = self._slow_forward(*input, **kwargs)
888 else:
--> 889 result = self.forward(*input, **kwargs)
890 for hook in itertools.chain(
891 _global_forward_hooks.values(),
892 self._forward_hooks.values()):
893 hook_result = hook(self, input, result)

File /electra/ner_tagging/.venv/lib/python3.8/site-packages/pytorch_pretrained_bert/modeling.py:730, in BertModel.forward(self, input_ids, token_type_ids, attention_mask, output_all_encoded_layers)
727 extended_attention_mask = extended_attention_mask.to(dtype=next(self.parameters()).dtype) # fp16 compatibility
728 extended_attention_mask = (1.0 - extended_attention_mask) * -10000.0
--> 730 embedding_output = self.embeddings(input_ids, token_type_ids)
731 encoded_layers = self.encoder(embedding_output,
732 extended_attention_mask,
733 output_all_encoded_layers=output_all_encoded_layers)
734 sequence_output = encoded_layers[-1]

File /electra/ner_tagging/.venv/lib/python3.8/site-packages/torch/nn/modules/module.py:889, in Module._call_impl(self, *input, **kwargs)
887 result = self._slow_forward(*input, **kwargs)
888 else:
--> 889 result = self.forward(*input, **kwargs)
890 for hook in itertools.chain(
891 _global_forward_hooks.values(),
892 self._forward_hooks.values()):
893 hook_result = hook(self, input, result)

File /electra/ner_tagging/.venv/lib/python3.8/site-packages/pytorch_pretrained_bert/modeling.py:267, in BertEmbeddings.forward(self, input_ids, token_type_ids)
264 if token_type_ids is None:
265 token_type_ids = torch.zeros_like(input_ids)
--> 267 words_embeddings = self.word_embeddings(input_ids)
268 position_embeddings = self.position_embeddings(position_ids)
269 token_type_embeddings = self.token_type_embeddings(token_type_ids)

File /electra/ner_tagging/.venv/lib/python3.8/site-packages/torch/nn/modules/module.py:889, in Module._call_impl(self, *input, **kwargs)
887 result = self._slow_forward(*input, **kwargs)
888 else:
--> 889 result = self.forward(*input, **kwargs)
890 for hook in itertools.chain(
891 _global_forward_hooks.values(),
892 self._forward_hooks.values()):
893 hook_result = hook(self, input, result)

File /electra/ner_tagging/.venv/lib/python3.8/site-packages/torch/nn/modules/sparse.py:156, in Embedding.forward(self, input)
155 def forward(self, input: Tensor) -> Tensor:
--> 156 return F.embedding(
157 input, self.weight, self.padding_idx, self.max_norm,
158 self.norm_type, self.scale_grad_by_freq, self.sparse)

File /electra/ner_tagging/.venv/lib/python3.8/site-packages/torch/nn/functional.py:1916, in embedding(input, weight, padding_idx, max_norm, norm_type, scale_grad_by_freq, sparse)
1910 # Note [embedding_renorm set_grad_enabled]
1911 # XXX: equivalent to
1912 # with torch.no_grad():
1913 # torch.embedding_renorm_
1914 # remove once script supports set_grad_enabled
1915 no_grad_embedding_renorm(weight, input, max_norm, norm_type)
-> 1916 return torch.embedding(weight, input, padding_idx, scale_grad_by_freq, sparse)

RuntimeError: Input, output and indices must be on the current device`