@eggandbacon_0056 - Communick News

0 Posts
4 Comments

Joined 1 year ago

Cake day: November 8th, 2023

You are not logged in. If you use a Fediverse account that is able to follow users, you can follow this user.

OverviewCommentsPosts

eggandbacon_0056@alien.topBtoLocalLLaMA@poweruser.forum•Could multiple 7b models outperform 70b models?
link
fedilink
English
arrow-up
1·
1 year ago
Still waiting for someone to use actual ensemble models and inference over all models and pick max or similar

link
fedilink

eggandbacon_0056@alien.topBtoLocalLLaMA@poweruser.forum•Orca 2: Teaching Small Language Models How to Reason
link
fedilink
English
arrow-up
1·
1 year ago
Come on stop that bs smh …

https://preview.redd.it/u02s07bxup1c1.png?width=1567&format=png&auto=webp&s=f64dbc83fcd64fbf33c18007f3b8b45419703179

link
fedilink

eggandbacon_0056@alien.topBtoLocalLLaMA@poweruser.forum•Finetuning LLMs: Does it add new knowledge to model or not?
link
fedilink
arrow-up
1·
1 year ago
Wrong.

link
fedilink

eggandbacon_0056@alien.topBtoLocalLLaMA@poweruser.forum•Finetuning LLMs: Does it add new knowledge to model or not?
link
fedilink
English
arrow-up
1·
1 year ago
Obviously it is adding knowledge.

The training is done the same as for the preparing with adjusted hyper parameters. …

link
fedilink