MultiverseComputingCAI/Hypernova-60B-2602

Full fine-tune vs MultiverseComputingCAI/HyperNova-60B. Fine-tune: 92% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 0/1, Norms 0/65, MLP 245/256, Attention 0/288, lm_head 1/1

4 derivatives checked