Sakalti/ultiima-14B-v0.2

Partial fine-tune vs sometimesanotion/Lamarck-14B-v0.6. Partial change: 10% of the weights changed (attention, mlp, norms), in 21 of 48 layers.

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 5/97, MLP 15/144, Attention 26/336

2 derivatives checked