Hacker News new | ask | show | jobs
by mosseater 1277 days ago
GPT-J specifically was written using Google Cloud's TPU stuff.

https://github.com/kingoflolz/mesh-transformer-jax/#gpt-j-6b

They even have a google colab notebook thingie. Not much setup needed, just an account.

https://colab.research.google.com/github/kingoflolz/mesh-tra...