Content
@
0 reply
0 recast
0 reaction
Stephan
@stephancill
Is there an easy way to fine tune an LLM on stuff I write so that I can talk to myself? Transforming data is not a requirement, can do it myself
7 replies
4 recasts
39 reactions
casslin.eth
@casslineth
RAG is enough. Most of cases no need to do fine tuning.
2 replies
0 recast
4 reactions
rafa
@rafa
What’s RAG? Is that like a prompt framework?
2 replies
0 recast
0 reaction
casslin.eth
@casslineth
If u are on Claude pro, the "projects" is one simpler method of RAG, namely u upload a bunch of docs to the LLM, give it some context, and ask it related questions or work on related topics, it usually works better cuz more context
1 reply
1 recast
4 reactions
rafa
@rafa
Oh great advice. Will try it out
0 reply
0 recast
1 reaction