Posts: 36
Threads: 3
Joined: Oct 2026
Reputation:
0
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
Posts: 28
Threads: 4
Joined: Sep 2026
Reputation:
0
subscribed, curious where this lands.
Posts: 36
Threads: 3
Joined: Oct 2026
Reputation:
0
Quote:subscribed, curious where this lands.
that fixed it for me too.
still benchmarking everything
Posts: 142
Threads: 20
Joined: Sep 2026
Reputation:
0
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