mergekit-community/mergekit-model_stock-tiwlqms

Full fine-tune vs ReadyArt/Forgotten-Abomination-12B-v4.0. Fine-tune: 100% of the weights changed, across 40 of 40 layers.

Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 32/81, MLP 120/120, Attention 160/160

2 derivatives checked