My feedback.
After using the model for three weeks, I can say it’s my favorite. Apparatus is good, but this model is better. It's smarter, has a better understanding of context, and follows instructions more accurately. Even though I searched, I couldn’t find a model that understands me better, and I’ve tried a lot over the past couple of years.
In Russian, it still understands context, but the grammar is poor, and it often repeats itself and hallucinates (just like other models).
My settings: T 1.01 Min P 0.035 Penalty 0.05 Smoothing Factor 0.3 DRY [1 2 4] – everything else off
Template: Mistral V7
Thank you for feedback! Glad that you liked model! For Russian performance, i use ChatML, other settings on screenshot, maybe on these settings will work better. Also, if you use not fully ru cards, performance is significantly worse.