Code for the paper "Language Models are Unsupervised Multitask Learners"
Why do you think that https://github.com/kingoflolz/mesh-transformer-jax is a good alternative to gpt-2
Code for the paper "Language Models are Unsupervised Multitask Learners"
Why do you think that https://github.com/kingoflolz/mesh-transformer-jax is a good alternative to gpt-2