luyug/GC-DPR

Issues

• Gradient caching vs Model dropout

  #12 opened a year ago by harveyp123
  3

• How to see the difference between DPR and GC-DPR?

  #11 opened 2 years ago by beihai2013
  0

• pip install . 之后的报错

  #10 opened 2 years ago by RudolphXu
  0

• coCondenser hyperparameter

  #9 opened 2 years ago by ehdlf4999
  0

• fine tuning existing dpr model

  #8 opened 2 years ago by vijayirlapati
  0

• Multiply by distributed_factor/8.

  #7 opened 3 years ago by wavy-jung
  2

• multilingual-bert issue?

  #6 opened 3 years ago by Smu-Tan
  4

• TPU support?

  #5 opened 3 years ago by OhadRubin
  1

• surrogate = surrogate * (trainer.distributed_factor / 8.)

  #4 opened 3 years ago by kinglai
  1

• 太赞了

  #3 opened 3 years ago by hangzhang-nlp
  1

• Multi GPU support

  #2 opened 4 years ago by MXueguang
  4

• 关于Reader_train部分GC技术使用问题

  #1 opened 4 years ago by Graduo
  0