taozi555/MN-12B-Mag-Mell-R1-KTO

Full fine-tune vs inflatebot/MN-12B-Mag-Mell-R1. Fine-tune: 100% of the weights changed, across 40 of 40 layers.

Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 29/81, MLP 120/120, Attention 160/160

1 derivatives checked