djuna/G2-BigGSHT-27B-calc

Full fine-tune vs DazzlingXeno/G2-Xeno-SimPO-27b. Fine-tune: 100% of the weights changed, across 46 of 46 layers.

Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 62/185, MLP 138/138, Attention 184/184

2 derivatives checked