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 ivan75@alien.top to c/localllama@poweruser.forum

37 comments fedilink hide all child comments

I like 7b but 13b like orca2 are better, no? What is the best?

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

[–] rookierook00000@alien.top 1 points 11 months ago

makes sense. the models do get updated from time to time so a monthly check if they've improved or worsened helps - just look at ChatGPT.