mayacinka/ExpertRamonda-7Bx2_MoE
MoE built from dense models vs bardsai/jaskier-7b-dpo-v5.6. mayacinka/ExpertRamonda-7Bx2_MoE is a mixture of 2 experts assembled from dense models (mergekit-moe style): expert 1 is an exact copy of bardsai/jaskier-7b-dpo-v5.6's MLP; the other experts come from other models. Shared tensors (attention, norms, embeddings): 0 of 195 identical.
1 derivatives checked
- mradermacher/ExpertRamonda-7Bx2_MoE-GGUF: Quantization