ParasiticRogue/Magnum-Instruct-DPO-12B
Full fine-tune vs intervitens/mini-magnum-12b-v1.1. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Norms 47/81, MLP 120/120, Attention 160/160
4 derivatives checked
- featherless-ai-quants/ParasiticRogue-Magnum-Instruct-DPO-12B-GGUF: Quantization
- mradermacher/Magnum-Instruct-DPO-12B-GGUF: Quantization
- mradermacher/Magnum-Instruct-DPO-12B-i1-GGUF: Quantization
- mergekit-community/Slush-FallMix-Test_V6c_12B: Full fine-tune
2 other repos hold byte-for-byte identical weight files.