tomccc

joined 9 months ago
sorted by: new top controversial old
Is Open LLM Leaderboard reliable source ? yi:34B is at the top but I get better results with neural-chat:7B model in c/localllama@poweruser.forum
[–] tomccc@alien.top 1 points 9 months ago

I had very bad experiences using all the Yi models until recently. Going to chalk it up as user error on my part. LoneStriker_Capybara-Tess-Yi-34B-200K-DARE-Ties-4.0bpw-h6-exl2 is really good. I made sure to have all the right settings.