redrix/fratricide-12B-Unslop-Mell-DARKNESS
Full fine-tune vs DavidAU/MN-GRAND-Gutenberg-Lyra4-Lyra-12B-DARKNESS. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Norms 42/81, MLP 120/120, Attention 160/160
3 derivatives checked
- MaziyarPanahi/fratricide-12B-Unslop-Mell-DARKNESS-GGUF: Same weights, converted
- mradermacher/fratricide-12B-Unslop-Mell-DARKNESS-i1-GGUF: Quantization
- mradermacher/fratricide-12B-Unslop-Mell-DARKNESS-GGUF: Quantization