Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
few-shot when you actually need it
#11
A couple things I'd check first. Before rebuilding anything, I'd test one clean baseline with Mistral and compare from there. Not glamorous advice, but repeatable baselines save a lot of time. The logs were somehow calmer than I was.
still benchmarking everything
Reply
#12
subscribed, curious where this lands.
Reply
#13
Quote:subscribed, curious where this lands.

that fixed it for me too.
still benchmarking everything
Reply
#14
My first guess would be this: Before rebuilding anything, I'd test one clean baseline with Mixtral and compare from there. Not glamorous advice, but repeatable baselines save a lot of time.
small models can still be useful
Reply


Forum Jump:


Users browsing this thread: 1 Guest(s)