SubMaroon/MN-12B-Mag-Mell-R1-SODOM-v1
Full fine-tune vs inflatebot/MN-12B-Mag-Mell-R1. Fine-tune: 95% of the weights changed, across 40 of 40 layers.
Tensors changed: lm_head 1/1, Embeddings 0/1, Norms 31/81, MLP 120/120, Attention 160/160
2 derivatives checked
- mradermacher/MN-12B-Mag-Mell-R1-SODOM-v1-i1-GGUF: Quantization
- mradermacher/MN-12B-Mag-Mell-R1-SODOM-v1-GGUF: Quantization