Vortex5/Cosmic-Night-12B

Full fine-tune vs SuperbEmphasis/MN-12b-RP-Ink-RP-Longform. 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/Cosmic-Night-12B-i1-GGUF: Quantization
• mradermacher/Cosmic-Night-12B-GGUF: Quantization
• Sorihon/Cosmic-Night-12B-Heretic: Abliterated

On the Hub · Downloads on Model Pulse