LlamaIndex
Log in

Find answers from the community

Updated 9 months ago

Hi, everyone

๊ถŒ๊ถŒ์”จ ๐Ÿ˜ฎ๐Ÿ’จ
ยท
Hi, everyone
im While listening to the lecture, a question arose. Now the lecture is about fine tuning. But Why is a technology called RAG used when fine tuning exists?
T
1 comment
TTeemu
Fine-tuning is inefficient for Q/A use-cases because it requires a lot of work to make datasets and the knowledge retention is very poor.

It can be used for augmenting RAG but just fine-tuning itself doesn't yield good results.

RAG is more accurate, cheaper, faster and flexible.
Add a reply
Sign up and join the conversation on Discord