jsfs11/RandomMergeNoNormWEIGHTED-7B-2x7BMOE

MoE built from dense models vs macadeliccc/WestLake-7B-v2-laser-truthy-dpo. jsfs11/RandomMergeNoNormWEIGHTED-7B-2x7BMOE is a mixture of 2 experts assembled from dense models (mergekit-moe style): expert 1 is an exact copy of macadeliccc/WestLake-7B-v2-laser-truthy-dpo's MLP; the other experts come from other models. Shared tensors (attention, norms, embeddings): 0 of 195 identical.

2 derivatives checked

On the Hub · Downloads on Model Pulse