Vortex5/Darkest-Grimoire-12B
Partial fine-tune vs Retreatcost/Darkstar-12B. Partial change: 62% of the weights changed (attention, embeddings, mlp, norms), in 40 of 40 layers.
Tensors changed: lm_head 0/1, Embeddings 1/1, Norms 49/81, MLP 75/120, Attention 108/160
2 derivatives checked
- mradermacher/Darkest-Grimoire-12B-i1-GGUF: Quantization
- mradermacher/Darkest-Grimoire-12B-GGUF: Quantization