Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
sva_
on Feb 28, 2024
|
parent
|
context
|
favorite
| on:
The Era of 1-bit LLMs: ternary parameters for cost...
I'm also curious about the potential speed gains in automatic differentiation, as there are way less branches to 'go up'. Or am I wrong here?
lumost
on Feb 28, 2024
[–]
They actually use a relu to represent the model weights. But I'm not convinced that this can't be avoided. We do gradient boosted decision tree training without this trick.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
