youtube-jocoding/kogpt-interview

google colaboratory 에서 실행하였으나 실패하였습니다.

Opened this issue · 0 comments

PC (windows 10, i7-10700, ram: 32GB, Nvidia: GTX 1660 8GB) 에서 실패해서 환경이 문제인가 싶어서
google colaboratory도 프로로 구매해서 테스트 해봤지만 실패하였습니다.
사용 환경상 16기가 모델로 테스트 하였습니다.

테스트한 환경 정보 공유 부탁 드립니다.

여러번 실패한 중에 남아 있는 실패 로그도 공유합니다.

--------------------------------------------------------------------------
RuntimeError                              Traceback (most recent call last)
[<ipython-input-4-f4f7dc2d49ea>](https://localhost:8080/#) in <module>
      1 prompt = """그러면 대화가 가능한 현존 최고 수준의 인공지능과의 인터뷰를 진행해보겠습니다. Q: 인공지능님 안녕하세요. 만나서 반갑습니다. 조코딩 구독자 분들에게 인사한번 부탁드립니다. A: """
----> 2 gpt(prompt)

10 frames
[<ipython-input-3-c1309a025c46>](https://localhost:8080/#) in gpt(prompt)
      2   with torch.no_grad():
      3     tokens = tokenizer.encode(prompt, return_tensors='pt').to(device='cpu', non_blocking=True)
----> 4     gen_tokens = model.generate(tokens, do_sample=True, temperature=0.8, max_length=256)
      5     generated = tokenizer.batch_decode(gen_tokens)[0]
      6 

[/usr/local/lib/python3.7/dist-packages/torch/autograd/grad_mode.py](https://localhost:8080/#) in decorate_context(*args, **kwargs)
     26         def decorate_context(*args, **kwargs):
     27             with self.__class__():
---> 28                 return func(*args, **kwargs)
     29         return cast(F, decorate_context)
     30 

[/usr/local/lib/python3.7/dist-packages/transformers/generation_utils.py](https://localhost:8080/#) in generate(self, input_ids, max_length, min_length, do_sample, early_stopping, num_beams, temperature, top_k, top_p, repetition_penalty, bad_words_ids, bos_token_id, pad_token_id, eos_token_id, length_penalty, no_repeat_ngram_size, encoder_no_repeat_ngram_size, num_return_sequences, max_time, max_new_tokens, decoder_start_token_id, use_cache, num_beam_groups, diversity_penalty, prefix_allowed_tokens_fn, output_attentions, output_hidden_states, output_scores, return_dict_in_generate, forced_bos_token_id, forced_eos_token_id, remove_invalid_values, synced_gpus, **model_kwargs)
   1025                 return_dict_in_generate=return_dict_in_generate,
   1026                 synced_gpus=synced_gpus,
-> 1027                 **model_kwargs,
   1028             )
   1029 

[/usr/local/lib/python3.7/dist-packages/transformers/generation_utils.py](https://localhost:8080/#) in sample(self, input_ids, logits_processor, stopping_criteria, logits_warper, max_length, pad_token_id, eos_token_id, output_attentions, output_hidden_states, output_scores, return_dict_in_generate, synced_gpus, **model_kwargs)
   1533                 return_dict=True,
   1534                 output_attentions=output_attentions,
-> 1535                 output_hidden_states=output_hidden_states,
   1536             )
   1537 

[/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py](https://localhost:8080/#) in _call_impl(self, *input, **kwargs)
   1069             input = bw_hook.setup_input_hook(input)
   1070 
-> 1071         result = forward_call(*input, **kwargs)
   1072         if _global_forward_hooks or self._forward_hooks:
   1073             for hook in itertools.chain(

[/usr/local/lib/python3.7/dist-packages/transformers/models/gptj/modeling_gptj.py](https://localhost:8080/#) in forward(self, input_ids, past_key_values, attention_mask, token_type_ids, position_ids, head_mask, inputs_embeds, labels, use_cache, output_attentions, output_hidden_states, return_dict)
    783             output_attentions=output_attentions,
    784             output_hidden_states=output_hidden_states,
--> 785             return_dict=return_dict,
    786         )
    787         hidden_states = transformer_outputs[0]

[/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py](https://localhost:8080/#) in _call_impl(self, *input, **kwargs)
   1069             input = bw_hook.setup_input_hook(input)
   1070 
-> 1071         result = forward_call(*input, **kwargs)
   1072         if _global_forward_hooks or self._forward_hooks:
   1073             for hook in itertools.chain(

[/usr/local/lib/python3.7/dist-packages/transformers/models/gptj/modeling_gptj.py](https://localhost:8080/#) in forward(self, input_ids, past_key_values, attention_mask, token_type_ids, position_ids, head_mask, inputs_embeds, use_cache, output_attentions, output_hidden_states, return_dict)
    574 
    575         if inputs_embeds is None:
--> 576             inputs_embeds = self.wte(input_ids)
    577 
    578         hidden_states = inputs_embeds

[/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py](https://localhost:8080/#) in _call_impl(self, *input, **kwargs)
   1049         if not (self._backward_hooks or self._forward_hooks or self._forward_pre_hooks or _global_backward_hooks
   1050                 or _global_forward_hooks or _global_forward_pre_hooks):
-> 1051             return forward_call(*input, **kwargs)
   1052         # Do not call functions when jit is used
   1053         full_backward_hooks, non_full_backward_hooks = [], []

[/usr/local/lib/python3.7/dist-packages/torch/nn/modules/sparse.py](https://localhost:8080/#) in forward(self, input)
    158         return F.embedding(
    159             input, self.weight, self.padding_idx, self.max_norm,
--> 160             self.norm_type, self.scale_grad_by_freq, self.sparse)
    161 
    162     def extra_repr(self) -> str:

[/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py](https://localhost:8080/#) in embedding(input, weight, padding_idx, max_norm, norm_type, scale_grad_by_freq, sparse)
   2041         # remove once script supports set_grad_enabled
   2042         _no_grad_embedding_renorm_(weight, input, max_norm, norm_type)
-> 2043     return torch.embedding(weight, input, padding_idx, scale_grad_by_freq, sparse)
   2044 
   2045 

RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu! (when checking arugment for argument index in method wrapper_index_select)

감사합니다.