Undi95/Lumimaid-Magnum-12B
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
4 derivatives checked
- mradermacher/Lumimaid-Magnum-12B-i1-GGUF: Quantization
- bartowski/Lumimaid-Magnum-12B-GGUF: Same weights, converted
- mradermacher/Lumimaid-Magnum-12B-GGUF: Quantization
- featherless-ai-quants/Undi95-Lumimaid-Magnum-12B-GGUF: Quantization