Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
make3
on Aug 21, 2019
|
parent
|
context
|
favorite
| on:
The State of Transfer Learning in NLP
there are some much smaller BERT models available on tf-hub and elsewhere if you wish.
most people also actually distill BERT to reduce the computation cost
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
most people also actually distill BERT to reduce the computation cost