Snqwii/Rose-Engine-12B

Full fine-tune vs Fizzarolli/MN-12b-Rosier-v1. Fine-tune: 100% of the weights changed, across 40 of 40 layers.

Tensors changed: Embeddings 1/1, Norms 80/81, MLP 120/120, Attention 160/160, lm_head 1/1

4 derivatives checked