clovaai/length-adaptive-transformer

Issues

• Loading the optimizer before training length adaptive

  #5 opened 4 years ago by shira-g
  0

• Which version of transformers did you use

  #4 opened 4 years ago by cin-hubert
  1

• Batch size for reproduction

  #3 opened 4 years ago by shira-g
  2

• Pareto curves clarifications

  #2 opened 4 years ago by shira-g
  2

• slimmable argument

  #1 opened 4 years ago by shira-g
  2