local_llama icon indicating copy to clipboard operation
local_llama copied to clipboard
verified publisher icon jlonge4

Awsome project!

Open mountainrocky opened this issue 2 years ago • 2 comments

This is an awsome project. I pull the code and get it up running quickly.

Do you have any idea how to improve the query results from my uploaded documents? or how to fine tune the LLM based on my updated documents? Any suggestions to improve the search speed?

Thanks Kevin

mountainrocky avatar Nov 29 '23 16:11 mountainrocky

@mountainrocky thanks a lot I'm glad you like it! I have been wanting to try to run inference using mojo for speed, but that's quite a dependency. As far as fine tuning you would have to actually use hugging face for that or get into some nitty gritty coding.

jlonge4 avatar Dec 07 '23 02:12 jlonge4

This is an awsome project. I pull the code and get it up running quickly.

Do you have any idea how to improve the query results from my uploaded documents? or how to fine tune the LLM based on my updated documents? Any suggestions to improve the search speed?

Thanks

Kevin

@mountainrocky Checkout v3, and follow the new update instructions in the read me. You won't be disappointed.

jlonge4 avatar Feb 07 '24 03:02 jlonge4