yamatazen/Himeyuri-Magnum-12B-v2

Full fine-tune vs Elizezen/Himeyuri-v0.1-12B. Fine-tune: 94% of the weights changed, across 40 of 40 layers.

Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 1/81, MLP 111/120, Attention 149/160

2 derivatives checked