DarkArtsForge/MN-Raven-12B-v1
Adapter vs Naphula-Archives/MN-Raven-12B-v0c-Base-LoRA. Naphula-Archives/MN-Raven-12B-v0c-Base-LoRA is a LoRA adapter, not full weights: rank 64, on down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj in 40 layers (280 adapted matrices). It modifies DarkArtsForge/MN-Raven-12B-v1 at load time.
5 derivatives checked
- mradermacher/MN-Raven-12B-v1-i1-GGUF: Quantization
- mradermacher/MN-Raven-12B-v1-GGUF: Quantization
- Naphula/MN-Raven-12B-v1-GGUF: Quantization
- OccultAI/MN-Nazgul-12B-v1: Full fine-tune
- DarkArtsForge/Vesper-Zenith-12B: Full fine-tune