This is quantized version of
Undi95/Lumimaid-Magnum-v4-12B created using llama.cpp
Merge of Lumimaid and Magnum as requested by some.
UPDATE : Magnum v4 used in this merge as asked hereI used the DELLA merge method in mergekit and added a finetune of Nemo only on Claude input, trained on 16k ctx, in the mix.
