Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
mobicham
5 months ago
|
parent
|
context
|
favorite
| on:
Towards 1-bit Machine Learning Models
LoRA training should benefit from the same speed-up, because the 1-bit weights will be frozen and all you need for both the forward and backward pass is a binary matmul, then maybe cast after to get more stable gradients.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: