This is quantized version of
aetherwiing/MN-12B-Starcannon-v2 created using llama.cpp
This is a merge of pre-trained language models created using
mergekit. Turned out to be a bit more Magnum-esque, but still is very creative, and writing style is pretty nice, even if some slop words appear time to time. Might be a good fit for people wanting more variety than Magnum has, and more verbose prose than Celeste v1.9 has.
Dynamic FP8
Static GGUF (by Mradermacher)
EXL2 (by kingbri of RoyalLab)This model was merged using the
TIES merge method using
nothingiisreal/MN-12B-Celeste-V1.9 as a base.
1models:
2 - model: intervitens/mini-magnum-12b-v1.1
3 parameters:
4 density: 0.3
5 weight: 0.5
6 - model: nothingiisreal/MN-12B-Celeste-V1.9
7 parameters:
8 density: 0.7
9 weight: 0.5
10
11merge_method: ties
12base_model: nothingiisreal/MN-12B-Celeste-V1.9
13parameters:
14 normalize: true
15 int8_mask: true
16dtype: bfloat16
17
