MRockatansky/Precog-Magnum-31B

Partial fine-tune vs TheDrummer/Precog-24B-v1. Partial change: 31% of the weights changed (attention, mlp, norms), in 13 of 40 layers.

Tensors changed: Embeddings 0/1, Norms 26/81, MLP 39/120, Attention 52/160, lm_head 0/1

2 derivatives checked

On the Hub · Downloads on Model Pulse