DoppelReflEx/MoETest-3E2A-3x3B

MoE built from dense models vs NousResearch/Hermes-3-Llama-3.2-3B. DoppelReflEx/MoETest-3E2A-3x3B is a mixture of 3 experts assembled from dense models (mergekit-moe style): expert 2 is an exact copy of NousResearch/Hermes-3-Llama-3.2-3B's MLP; the other experts come from other models. Shared tensors (attention, norms, embeddings): 0 of 170 identical.

1 derivatives checked

On the Hub · Downloads on Model Pulse