Naphula/Meme-Trix-MoE-14B-A8B-v1
MoE built from dense models vs OccultAI/Morpheus-8B-v1. Naphula/Meme-Trix-MoE-14B-A8B-v1 is a mixture of 2 experts assembled from dense models (mergekit-moe style): expert 0 is an exact copy of OccultAI/Morpheus-8B-v1's MLP; the other experts come from other models. Shared tensors (attention, norms, embeddings): 54 of 195 identical.
2 derivatives checked
- mradermacher/Meme-Trix-MoE-14B-A8B-v1-i1-GGUF: Quantization
- mradermacher/Meme-Trix-MoE-14B-A8B-v1-GGUF: Quantization