GPT-2 1558M Github link

09/11/2019

Here’s a copy of the code I have working for the OpenAI GPT-2 1558M model
A couple of changes to the source code that were required to get it to execute:

  • tensorflow-gpu==1.12.0 wouldn’t work, updated to:
    • !pip3 install tensorflow-gpu==1.16.0
  • interactive_conditional_samples.py updated to:
    • model_name=’1558M’

https://github.com/AmbiguousError/gpt-2/blob/master/GPT_2.ipynb