zlacker

>>tosh+(OP)
I’m really struggling to find a use case for these local models when even ChatGPT 3.5 can do it as good as any of them so far.

>>m3kw9+zH
The article shows (fine tuned) Mistral 7B outperforming GPT-4, never mind GPT-3.5.

>>coder5+KK
This model is not close to even 3.5 from when I used it. It first of all does not follow instructions properly and it just runs on and on