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

Has anyone fine tuned a local model on their company database? (alien.top)

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

6 comments fedilink hide all child comments

Curious if it can be connected to, or set up to update fine tunings on a schedule? Admittedly I’ve only slightly paid attention RAG so far, but not sure if this is a step further, or already a current capability.

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

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

My two cents. Unless you have jargon in your field you just need RAG. Fine-tuning is for adjusting the token associations to predict the most likely next token.

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

Ok, so I’ll look more into RAG. I just saw Mathew Bermans video on creating agents with YouAI, but I’m hoping for something that’ll connect to our database (or even just a couple specific tables) instead of having to manually export csv files from my db to then upload.

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

You have to do some type of search for the correct information for the question. It doesn't matter how you get the information.