prithivMLmods/Condor-Opus-14B-Exp

Full fine-tune vs prithivMLmods/Pegasus-Opus-14B-Exp. Fine-tune: 100% of the weights changed, across 48 of 48 layers.

Tensors changed: Norms 97/97, MLP 144/144, Attention 336/336

3 derivatives checked