Vortex5/Darklit-Maiden-12B

Full fine-tune vs Retreatcost/KansenSakura-Erosion-RP-12b. Fine-tune: 100% of the weights changed, across 40 of 40 layers.

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

3 derivatives checked

• mradermacher/Darklit-Maiden-12B-i1-GGUF: Quantization
• mradermacher/Darklit-Maiden-12B-GGUF: Quantization
• Sorihon/Darklit-Maiden-12B-Heretic: Abliterated

On the Hub · Downloads on Model Pulse