INSTINSTINST

#2
by Slayery - opened

quantized version of the model spams INST.

Owner

Hey, I didn't really test gguf versions since the high score of the original model was kind of unexpected for me so I just prepared and published gguf version since people might ask it. Sorry to hear that though, which of the gguf version(s) is problematic? All or?

I have only tested Q4_K_M, but I think others have this problem too. For a couple of weeks now, models with this problem have been appearing constantly in the LLM leaderboard, and they are at the top of the list.

Owner

Yes, I can imagine my model inheriting this from other models since it's just a merge of a couple of top models. Sadly, top models in the leaderboard are sorted based on their higher precision capabilities by default, sadly no comparison for gguf versions available there...

Sign up or log in to comment