Vortex5/Mystic-Rune-v2-12B
Partial fine-tune vs Vortex5/MN-Mystic-Rune-12B. Partial change: 78% of the weights changed (attention, embeddings, lm_head, mlp, norms), in 40 of 40 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 1/81, MLP 90/120, Attention 121/160
2 derivatives checked
- mradermacher/Mystic-Rune-v2-12B-i1-GGUF: Quantization
- mradermacher/Mystic-Rune-v2-12B-GGUF: Quantization