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

Run an openAI powered startup. What’s the best alternative to got 3.5 with function calling that I can run in the cloud? (alien.top)

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

18 comments fedilink hide all child comments

Looking for speed and accuracy. Any suggestions on cloud hosts?

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

[–] Crafty-Run-6559@alien.top 1 points 11 months ago

How many users do you have? If you've been keeping your inputs/outputs to gpt4, then you can probably use that to tune a your own model that will perform similarly.

The biggest issue you're going to have is probably hardware.

LLMs are not cheap to run, and if you start needing multiple of them to replace OpenAI, your bill is going to be pretty significant just to keep the models online.

It's also going to be tough to maintain all the infra you'll need without a full time devops/mlops person.