Llama.cpp received an update to improve the support of new Mistral models.
#2
by
MrDevolver
- opened
Have you guys tried it with latest llama.cpp? They merged some fixes for these latest Mistral AI models. While the bigger motivation was the Devstral 2 model, I believe it also improved the Ministral models including its finetunes. More fixes may come later still. I think it's fair to give all of these first finetunes a second chance. I already tried the Brother-Dusk-14B-v1b-GGUF again and it was pretty good.
If it's just chat template changes it will do nothing