prithivMLmods/Porpoise-Opus-14B-Exp

Full fine-tune vs prithivMLmods/Sombrero-Opus-14B-Elite5. Fine-tune: 98% of the weights changed, across 48 of 48 layers.

Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 95/97, MLP 141/144, Attention 327/336

3 derivatives checked