←back to thread

345 points kashifr | 1 comments | | HN request time: 0.229s | source
Show context
_1 ◴[] No.44501951[source]
Which small model is good for fine tuning to various enterprise data sets? Our business units are wanting to run small models in browser and on mobile devices, without dealing with RAG and cloud resources.
replies(5): >>44502175 #>>44502283 #>>44502496 #>>44502868 #>>44508851 #
1. thatjoeoverthr ◴[] No.44508851[source]
Tuning is really not the way to add information.

Bite the bullet and do some kind of RAG; you need to provide clear, authoritative information to a model that is skilled enough to remix it for the user.

Tuning the model to imitate the dataset will damage the model's skills and "common sense" but won't train it reliably recall information.