LunaticPython161/Lily-MoE-2x7b
MoE built from dense models vs LunaticPython161/CyberWitch-7B. LunaticPython161/Lily-MoE-2x7b is a mixture of 2 experts assembled from dense models (mergekit-moe style): expert 1 is an exact copy of LunaticPython161/CyberWitch-7B's MLP; the other experts come from other models. Shared tensors (attention, norms, embeddings): 0 of 193 identical.
2 derivatives checked
- mradermacher/Lily-MoE-2x7b-i1-GGUF: Quantization
- mradermacher/Lily-MoE-2x7b-GGUF: Quantization