They haven't released such models, though, and I don't know if it would be drop-in compatible with the OA GPT-2-774M checkpoint (they're training their own GPT-2s using their own webtext corpus).
Re:GPT-2: 6-Month Follow-Up
by JonathanFly on Tuesday August 20, 2019 @04:03PM
(#20751433)
I haven't look into at all myself, but he also said:
>We do provide training code that should work out of the box for gpt2 117M/345M
It would take forever (or $$$) to train even 117M model from scratch.
Re:GPT-2: 6-Month Follow-Up
by JonathanFly on Tuesday August 20, 2019 @05:02PM
(#20752107)
I read that meaning you can start with the actual pre-trained GPT-2 models but I never got an answer when I specifically asked if that was the case.
>What would be the largest model one could train across 2x 2080Ti?
>~800M gpt2. this is largely due to the memory required to House parameters + optimizer states. If one uses a smaller optimizer than Adam training something larger should be possible. Make sure to turn on activation checkpointing with —checkpoint-activations
https://twitter.com/TheRealRPuri/status/1161322580126470145