Inference › Optimization & Performance › Benchmarks v
domain tune without wrecking base behavior with PyTorch

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Linear Mode
domain tune without wrecking base behavior with PyTorch
kernelghost Offline
Member
***
Posts: 70
Threads: 3
Joined: Aug 2026
Reputation: 0
#7
09-29-2026, 08:19 AM
Good point. I ended up in about the same place using llama.cpp. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
Find
Reply


Messages In This Thread
Re: domain tune without wrecking base behavior with PyTorch - by kernelghost - 09-29-2026, 08:19 AM

Forum Jump:


Users browsing this thread: 1 Guest(s)