LocalLLaMA

4 readers

4 users here now

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

founded 2 years ago

MODERATORS

communick@poweruser.forum

30,000 AI models (alien.top)

submitted 2 years ago by Creative_Bottle_3225@alien.top to c/localllama@poweruser.forum

19 comments fedilink hide all child comments

30,000 AI models

too many really. But from what I read in conversations and posts I notice one thing: you all try out Model all the time and that's fine, but I haven't yet read that anyone habitually uses one Model over others. It seems like you use one template for a few days and then start with a new one. Don't have your favorite? Which?

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

[–] dothack@alien.top 1 points 2 years ago (1 children)

OpenHermes-2.5-Mistral-7B is better than all the 13b and 7b model available.

[–] morphles@alien.top 1 points 2 years ago

What settings you use for it? In what UI? I tried it in silly tavern yesterday (via ooba backend), unmitigated disaster... tried bunch of setting nothing worked, as far as I go prompt template should be ChatML, but even with that...