pot99rta/NS-12b-DarkSlushCapV2
Full fine-tune vs Nitral-AI/Irixxed-Magcap-12B-Slerp. Fine-tune: 98% of the weights changed, across 40 of 40 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 49/81, MLP 117/120, Attention 156/160
2 derivatives checked
- mradermacher/NS-12b-DarkSlushCapV2-i1-GGUF: Quantization
- mradermacher/NS-12b-DarkSlushCapV2-GGUF: Quantization