geepytee@alien.topBtoLocalLLaMA@poweruser.forum•Starling-RM-7B-alpha: New RLAIF Finetuned 7b Model beats Openchat 3.5 and comes close to GPT-4English
1·
10 months agoThey tested to MT Bench with GPT-4 as judge
They tested to MT Bench with GPT-4 as judge
I built a new that has required preprocessing
Nice! How are you preprocessing the code?
It is pretty good, just not as good