djuna/MN-Lulanum-12B-FIX

Full fine-tune vs NeverSleep/Lumimaid-v0.2-12B. Fine-tune: 100% of the weights changed, across 40 of 40 layers.

Tensors changed: Norms 36/81, MLP 120/120, Attention 160/160

2 derivatives checked

On the Hub · Downloads on Model Pulse