LocalLLaMA

3 readers

1 users here now

Community to discuss about Llama, the family of large language models created by Meta AI.

founded 1 year ago

MODERATORS

submitted 11 months ago by petitponeyrose@alien.top to c/localllama@poweruser.forum

12 comments fedilink hide all child comments

you are viewing a single comment's thread
view the rest of the comments

[–] mcmoose1900@alien.top 1 points 11 months ago

which is largely due to model size

I disagree. I would argue GPT-4 is useful because of the sea of augmentations built up around it.

If it was just raw responses from a single base model (like most local LLMs), with no preprocessing, I believe GPT-4 would be much less impressive.