Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
YetAnotherNick
on Aug 16, 2023
|
parent
|
context
|
favorite
| on:
How Is LLaMa.cpp Possible?
The effect is lesser than you think. 5 bit quantization has negligible performance loss compared to 16 bits:
https://github.com/ggerganov/llama.cpp/pull/1684
astrange
on Aug 16, 2023
[–]
This paper from last month has a method for acceptable 3-bit quantization and a start at 2-bit.
https://arxiv.org/abs/2307.13304
Consider applying for YC's Fall 2026 batch!
Applications
are open till July 27.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
