News for hackers. Stuff that matters.

A comment on Meta is inviting researchers to pick apart the flaws in its version of GPT-3. Parent comment

Re:Meta is inviting researchers to pick apart the flaws in i... by screye on Monday June 27, 2022 @04:48PM (#31900580)
Not this one, but Google's PaLM (which is 4x OPT3) trains semi-deterministically.

These kinds of large transformers can be relatively reproduceable in results and benchmarks. However, making them converge to the exact same parameter set might not be a reasonable expectation.

[ Parent | on HN ]

There are no comments on this comment yet.