RuntimeError: Expected object of backend CUDA but got backend CPU for argument #3 'index'

[Tiger-Wh]

Hello author, I am very interested in your research. But I have a little problem reproducing your code, can you give me an answer？
When I experimented with cc2vec, the following error occurred:

Research Question 2
test case similarity cut-off: 0.8
Testing Chart
----------------
Chart_1
Traceback (most recent call last):
  File "main.py", line 173, in <module>
    e.run(arg1, arg2, arg3, arg4)
  File "main.py", line 118, in run
    eval.predict_collected_projects(path_collected_patch=self.path_generated_patch, cut_off=0.8, distance_method=distance.cosine, ASE2020=False, patchsim=False, )
  File "/home/extra_space/hanwei/BATS-main/experiment/evaluate.py", line 635, in predict_collected_projects
    patch_id_list, label_list, generated_patch_list, vector_ML_list = self.vector4patch(available_path_patch, compare=ASE2020,)
  File "/home/extra_space/hanwei/BATS-main/experiment/evaluate.py", line 262, in vector4patch
    vector, _ = w2v.convert_single_patch(p)
  File "/home/extra_space/hanwei/BATS-main/representation/word2vector.py", line 207, in convert_single_patch
    raise e
  File "/home/extra_space/hanwei/BATS-main/representation/word2vector.py", line 175, in convert_single_patch
    learned_vector = lmg_cc2ftr_interface.learned_feature(p, load_model=MODEL_CC2Vec + 'cc2ftr.pt', dictionary=self.dictionary)
  File "/home/extra_space/hanwei/BATS-main/representation/CC2Vec/lmg_cc2ftr_interface.py", line 20, in learned_feature
    ftr = extracted_cc2ftr(data=data, params=params)
  File "/home/extra_space/hanwei/BATS-main/representation/CC2Vec/lmg_cli.py", line 131, in extracted_cc2ftr
    commit_ftr = model.forward_commit_embeds_diff(pad_added_code, pad_removed_code, state_hunk, state_sent, state_word)                
  File "/home/extra_space/hanwei/BATS-main/representation/CC2Vec/lmg_cc2ftr_model.py", line 172, in forward_commit_embeds_diff
    x_added_code = self.forward_code(x=added_code, hid_state=hid_state)
  File "/home/extra_space/hanwei/BATS-main/representation/CC2Vec/lmg_cc2ftr_model.py", line 139, in forward_code
    sent, state_word = self.wordRNN(torch.LongTensor(words).view(-1, self.batch_size), hid_state_word)
  File "/home/hanwei/.conda/envs/hw1/lib/python3.7/site-packages/torch/nn/modules/module.py", line 547, in __call__
    result = self.forward(*input, **kwargs)
  File "/home/extra_space/hanwei/BATS-main/representation/CC2Vec/lmg_cc2ftr_model.py", line 37, in forward
    emb_out = self.embed(inp)
  File "/home/hanwei/.conda/envs/hw1/lib/python3.7/site-packages/torch/nn/modules/module.py", line 547, in __call__
    result = self.forward(*input, **kwargs)
  File "/home/hanwei/.conda/envs/hw1/lib/python3.7/site-packages/torch/nn/modules/sparse.py", line 114, in forward
    self.norm_type, self.scale_grad_by_freq, self.sparse)
  File "/home/hanwei/.conda/envs/hw1/lib/python3.7/site-packages/torch/nn/functional.py", line 1467, in embedding
    return torch.embedding(weight, input, padding_idx, scale_grad_by_freq, sparse)
RuntimeError: Expected object of backend CUDA but got backend CPU for argument #3 'index'

I look forward to hearing from you very much.