Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
entropicdrifter
on Oct 8, 2024
|
parent
|
context
|
favorite
| on:
Differential Transformer
I think it
would
negate the RAM savings, but it would also reduce the amount of storage needed at rest and possibly reduce initial start up times depending on storage speed and model size. So, possibly good for low-end models on consumer devices?
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: