knifeayumu/Behemoth-v1.2-Magnum-v4-123B

Full fine-tune vs TheDrummer/Behemoth-123B-v1.2. Fine-tune: 100% of the weights changed, across 88 of 88 layers.

Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 67/177, MLP 264/264, Attention 352/352

1 derivatives checked

On the Hub · Downloads on Model Pulse