Vortex5/Silver-Siren-12B
Full fine-tune vs ReadyArt/Dark-Nexus-12B-v2.0. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Norms 53/81, MLP 120/120, Attention 160/160
3 derivatives checked
- mradermacher/Silver-Siren-12B-i1-GGUF: Quantization
- mradermacher/Silver-Siren-12B-GGUF: Quantization
- ewald1976/Silver-Siren-ST-12B: Identical copy
1 other repos hold byte-for-byte identical weight files.