Request for dreamgen/opus-v1.2-70b
#1
by
homeworkace
- opened
Hello! I would like to ask if a 2.4bpw quant of dreamgen/opus-v1.2-70b is in your plans. Thanks in advance!
I can add it to the queue. The 70B models tend to be heavy to quant via exl2 so it might take time to get to it.
I emphatise with that. I'm straight up unable to quant that model with my 3090 and 16GB RAM, so I'm glad you can spare us some of your compute :)
Out of curiosity, what dataset do you use to test its fitness? And is it true that the longer you let it quant the less loss you encounter?
(Edit: I keep forgetting that button was "Close" lol)
homeworkace
changed discussion status to
closed
homeworkace
changed discussion status to
open