Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
dylanbyte
on March 21, 2021
|
parent
|
context
|
favorite
| on:
GPT Neo: open-source GPT model, with pretrained 1....
Curious to see what parameter size of gpt3 this will end up being equivalent to. Obviously we won't know until they evaluate their models.
sailingparrot
on March 21, 2021
[–]
It's trained using the same architecture, and with a very similar dataset, so it should be very close.
dylanbyte
on March 22, 2021
|
parent
[–]
My experience is that replicating papers is actually nontrivial. For example someone announced they had replicated gpt2 some time back but when evals were run it turned about to be the equivalent of a much smaller model.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
