youtube-jocoding / kogpt-interview Goto Github PK

--------------------------------------------------------------------------
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)