lodrick-the-lafted/Grafted-Wind-Elementals-2x70B

MoE built from dense models vs 152334H/miqu-1-70b-sf. lodrick-the-lafted/Grafted-Wind-Elementals-2x70B is a mixture of 2 experts with the same shape as 152334H/miqu-1-70b-sf's MLP, but none of them is a copy of it: they come from other models or were trained further. Shared tensors (attention, norms, embeddings): 0 of 483 identical.

2 derivatives checked

On the Hub · Downloads on Model Pulse