affjljoo3581/GPT2

Issues

• bidirectional training in GPT2

  #8 opened 3 months ago by lytum
  1

• GPT-2 implementation problem

  #10 opened 3 months ago by sanhai77
  1

• Which kind of tokenizer do you use? It looks like WordPiece, not BPE.

  #9 opened a year ago by Suxyuuu
  1

• Training spec #2

  #7 opened 3 years ago by jisngprk
  2

• Training spec

  #6 opened 3 years ago by jisngprk
  2

• Activaiton Function

  #5 opened 3 years ago by myoons
  3

• Multi GPU mode is stuck at the beginning

  #4 opened 4 years ago by liygzting
  14

• Is Apex useful for GPT-2?

  #3 opened 4 years ago by iRmantou
  2

• Confusions on Usage

  #2 opened 4 years ago by ZorrowHu
  3

• Dataset에 대해 문의 드립니다.

  #1 opened 4 years ago by hyunwoongko
  1