yamatazen/NeonMaid-12B-v2

Partial fine-tune vs yamatazen/NeonMaid-12B. Partial change: 73% of the weights changed (attention, lm_head, mlp, norms), in 40 of 40 layers.

Tensors changed: lm_head 1/1, Embeddings 0/1, Norms 63/81, MLP 89/120, Attention 137/160

3 derivatives checked