SvalTek/ColdBrew-Icarus

MoE built from dense models vs SvalTek/ColdBrew-Aphid. SvalTek/ColdBrew-Icarus is a mixture of 2 experts assembled from dense models (mergekit-moe style): experts 0, 1 are an exact copy of SvalTek/ColdBrew-Aphid's MLP; the other experts come from other models. Shared tensors (attention, norms, embeddings): 171 of 171 identical.

1 derivatives checked

On the Hub · Downloads on Model Pulse