Naphula/Goetia-26B-A4B-v1.3-Absolute-Heretic-ARA
Full fine-tune vs ApocalypseParty/G4-26B-SFT-6. Fine-tune: 100% of the weights changed, across 30 of 30 layers.
Tensors changed: Embeddings 4/4, MLP 231/231, Norms 371/433, other 30/122, Attention 223/223
8 derivatives checked
- mradermacher/Goetia-26B-A4B-v1.3-Absolute-Heretic-ARA-i1-GGUF: Quantization
- mradermacher/Goetia-26B-A4B-v1.3-Absolute-Heretic-ARA-GGUF: Quantization
- 26B-Suite/Goetia-26B-A4B-v1.3-Absolute-Heretic-ARA-GGUF: Quantization
- otherwhere1/Goetia-26B-A4B-v1.3-Absolute-Heretic-ARA-mlx-8Bit: Quantization
- Phil2Sat/Goetia-26B-A4B-v1.3-Absolute-Heretic-Restored-I-Compact-MXFP4-GGUF: Full fine-tune
- SubMaroon/Dark-Goetia-26B-A4B-LoRA-RU-v1: Adapter
- SUPEROXIDES/GOETIA_V1.3_ABSOLUTE_HERETIC_ARA_26B-A4B_-_GGUF_-_MXFP4_MOE: Same weights, converted
- Kraekin/Goetia-26B-A4B-v1.3-Absolute-Heretic-ARA-Q4_K_M-GGUF: Quantization