luckystarr@feddit.deM to luckystarr@feddit.de · 9 months ago

The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits

0

1

The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits

luckystarr@feddit.deM to luckystarr@feddit.de · 9 months ago

0

HN discussion here: https://news.ycombinator.com/item?id=39535800

The paper is coming out of Microsoft Research and the University of Chinese Academy of Sciences, so highly likely to not be a fake.

This is huge. I wonder when the NVIDIA stock is going to react.

You must log in or register to comment.

Chat

luckystarr@feddit.de

luckystarr@feddit.de

You are not logged in. However you can subscribe from another Fediverse account, for example Lemmy or Mastodon. To do this, paste the following into the search field of your instance: !luckystarr@feddit.de

If it interests me, it should interest you.

Anything I like and want to remember.

Anything you unknowingly wanted to know for a long time.

Note: If you think you know something that could interest me, feel free to submit, though I reserve the right to remove it if I’m not interested. No hard feelings.

Visibility: Public

This community can be federated to other instances and be posted/commented in by their users.

1 user / day
1 user / week
1 user / month
1 user / 6 months
0 local subscribers
45 subscribers
50 Posts
0 Comments
Modlog

mods:
luckystarr@feddit.de