Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
70B still worth the pain
#11
same here on my side.
Reply
#12
I'd approach it in a boring order. Before rebuilding anything, I'd test one clean baseline with Mixtral and compare from there.
trying not to rebuild again
Reply
#13
I'd start with the simpler stack.

There are a few different conversations hiding inside this thread, so being explicit about the goal helps.
trying not to rebuild again
Reply
#14
following this because I'm in the same boat.
small models can still be good
Reply


Forum Jump:


Users browsing this thread: 1 Guest(s)