mergekit-community/MN-Hekate-Limenoskopos-12B

Partial fine-tune vs mergekit-community/MN-Hekate-Anassa-17B. Partial change: 62% of the weights changed (attention, mlp, norms), in 28 of 40 layers.

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 43/81, MLP 84/120, Attention 112/160

3 derivatives checked