Custom 4-bit Finetuning 5-7 times faster inference than QLora

#5
by rmihaylov - opened

Hi this is excellent , i see currntly it supports only two dataset types Alpaca /gpt4All
Can we use this for simple datasets or do we need to pre-process the datasets as per Alpaca or gpt4All structure

Your need to confirm your account before you can post a new comment.

Sign up or log in to comment