DavidAU/LFM2-12B-A1B-SpeedDemon-The-Deckard-II-HERETIC-Uncensored
Partial fine-tune vs LiquidAI/LFM2-8B-A1B. Partial change: 31% of the weights changed (attention, mlp, norms, other), in 24 of 24 layers.
Tensors changed: MLP 589/2071, Embeddings 0/2, other 37/51, Norms 14/58, Attention 20/20