mergekit-community/Arisu-12B
Full fine-tune vs LatitudeGames/Wayfarer-2-12B. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Norms 32/81, MLP 120/120, Attention 160/160
2 derivatives checked
- mradermacher/Arisu-12B-i1-GGUF: Quantization
- mradermacher/Arisu-12B-GGUF: Quantization