l4rz/gpt-2-training

Issues

• Learning rate schedule for training smaller models

  #10 opened 3 years ago by Ashokvardhan
  0

• encoder.json is missing in the largest model and 117M model archived at mega.nz

  #9 opened 3 years ago by cloudcell
  0

• Long time to download models

  #8 opened 4 years ago by idler
  0

• Text generation on default models

  #7 opened 4 years ago by alsvartr
  1

• How to train large models?

  #6 opened 4 years ago by sowich
  3

• Colab Notebook public share

  #5 opened 4 years ago by Nehc
  2

• Colab Notebook

  #3 opened 5 years ago by Merzmensch
  6

• Decoding not working?

  #4 opened 4 years ago by NightShadow777
  5

• Can't use last 1250M model

  #2 opened 5 years ago by max-frai
  1