liquiddandruff

joined 1 year ago

The overthinker in c/localllama@poweruser.forum

[–] liquiddandruff@alien.top 1 points 11 months ago

dang, that's actually very impressive

permalink
fedilink
source
context

Finetuning LLMs: Does it add new knowledge to model or not? in c/localllama@poweruser.forum

[–] liquiddandruff@alien.top 1 points 1 year ago

Yes, people have done experiments with fine tuning on just a dump of the ue5 game engine documentation and it was able to recall the changes in the new documentation that wasn't in the base model. The repo for this is on GitHub, you should be able to find it.

permalink
fedilink
source