Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Solving the out-of-context chunk problem for RAG. Parent comment
I regularly do fine tuning on a model with fine results and little damage to the base functionality.
It is possible, but it's too complex for the majority of users. It requires a lot of work per dataset you want trained on.
There are no comments on this comment yet.
I regularly do fine tuning on a model with fine results and little damage to the base functionality.
It is possible, but it's too complex for the majority of users. It requires a lot of work per dataset you want trained on.