Vortex5/Luminous-Mirror-26B-A4B
Partial fine-tune vs ReadyArt/For-Her-Darkside-26B-A4B-v1.4. Partial change: 34% of the weights changed (attention, mlp), in 30 of 30 layers.
Tensors changed: Embeddings 0/4, MLP 118/231, Norms 0/433, other 0/122, Attention 115/223
2 derivatives checked
- mradermacher/Luminous-Mirror-26B-A4B-i1-GGUF: Quantization
- mradermacher/Luminous-Mirror-26B-A4B-GGUF: Quantization