Alsebay/SaoRPM-2x8B
MoE built from dense models vs Sao10K/L3-8B-Lunaris-v1. Alsebay/SaoRPM-2x8B is a mixture of 2 experts assembled from dense models (mergekit-moe style): expert 1 is an exact copy of Sao10K/L3-8B-Lunaris-v1's MLP; the other experts come from other models. Shared tensors (attention, norms, embeddings): 0 of 195 identical.
2 derivatives checked
- mradermacher/SaoRPM-2x8B-i1-GGUF: Quantization
- mradermacher/SaoRPM-2x8B-GGUF: Quantization