tannedbum/L3-Rhaenys-2x8B
MoE built from dense models vs Sao10K/L3-8B-Niitama-v1. tannedbum/L3-Rhaenys-2x8B is a mixture of 2 experts with the same shape as Sao10K/L3-8B-Niitama-v1's MLP, but none of them is a copy of it: they come from other models or were trained further. Shared tensors (attention, norms, embeddings): 0 of 195 identical.
2 derivatives checked
- mradermacher/L3-Rhaenys-2x8B-i1-GGUF: Quantization
- mradermacher/L3-Rhaenys-2x8B-GGUF: Quantization