graykode/xlnet-Pytorch

Issues

• Confusion about the relative position embedding with attn_type='bi' but bsz=1

  #12 opened 5 years ago by NotANumber124
  1

• Parameter initialized with torch.randn may be not a good choice

  #17 opened 3 years ago by lddsdu
  0

• position-wise feedforward only one linear layer?

  #16 opened 3 years ago by yuanenming
  0

• Runtime Error in colab

  #15 opened 4 years ago by shiningrain
  0

• Batch training

  #14 opened 4 years ago by FruVirus
  0

• Error and general question

  #13 opened 4 years ago by jbmaxwell
  1

• RuntimeError: Expected object of scalar type Byte but got scalar type Bool for argument #2 'other'

  #11 opened 5 years ago by Petkomat
  3

• how to save the pre-trained language model?

  #10 opened 5 years ago by TE-andrewshin
  1

• how to do inference?

  #9 opened 5 years ago by EricBK
  1

• Model name 'bert-large-uncased' was not found in model name list (bert-base-uncased, bert-large-uncased, bert-base-cased, bert-large-cased, bert-base-multilingual-uncased, bert-base-multilingual-cased, bert-base-chinese).

  #8 opened 5 years ago by 17764591637
  0

• TypeError:can't convert np.ndarray of type numpy.bool_

  #6 opened 5 years ago by menggehe
  2

• about first men‘s bug

  #5 opened 5 years ago by sherry-1001
  0

• Reimplement training time and the performance on each task?

  #3 opened 5 years ago by Zzmonica
  5

• Low accuracy on sample task

  #2 opened 5 years ago by ndalton12
  1

• Re-implementation Performance

  #1 opened 5 years ago by lukemelas
  1

• do we need to create_data for every epoch?

  #7 opened 5 years ago by mehdimashayekhi
  0

• The permutation function " _local_perm" is confused.

  #4 opened 5 years ago by chenwq95
  0