Vortex5/Abyssal-Seraph-12B
Full fine-tune vs Vortex5/Dark-Quill-12B. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Norms 81/81, MLP 120/120, Attention 160/160
7 derivatives checked
- mradermacher/Abyssal-Seraph-12B-i1-GGUF: Quantization
- mradermacher/Abyssal-Seraph-12B-GGUF: Quantization
- Vortex5/Crimson-Twilight-12B: Full fine-tune
- Vortex5/Scarlet-Seraph-12B: Full fine-tune
- Vortex5/Hollow-Aether-12B: Full fine-tune
- Vortex5/Sunlit-Shadow-12B: Full fine-tune
- Vortex5/Lunar-Abyss-12B: Full fine-tune