GalrionSoftworks/MagnusIntellectus-12B-v1
Full fine-tune vs UsernameJustAnother/Nemo-12B-Marlin-v5. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 1/1, Norms 47/81, MLP 120/120, Attention 160/160, lm_head 1/1
4 derivatives checked
- mradermacher/MagnusIntellectus-12B-v1-i1-GGUF: Quantization
- mradermacher/MagnusIntellectus-12B-v1-GGUF: Quantization
- featherless-ai-quants/GalrionSoftworks-Margnum-12B-v1-GGUF: Quantization
- featherless-ai-quants/GalrionSoftworks-MagnusIntellectus-12B-v1-GGUF: Quantization