Nitral-AI/Irixxed-Magcap-12B-Slerp
Full fine-tune vs DreadPoor/Irix-12B-Model_Stock. Fine-tune: 98% of the weights changed, across 40 of 40 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 80/81, MLP 117/120, Attention 156/160
4 derivatives checked
- mradermacher/Irixxed-Magcap-12B-Slerp-i1-GGUF: Quantization
- mradermacher/Irixxed-Magcap-12B-Slerp-GGUF: Quantization
- DevQuasar/Nitral-AI.Irixxed-Magcap-12B-Slerp-GGUF: Same weights, converted
- pot99rta/NS-12b-DarkSlushCapV2: Full fine-tune