Nan-Do/FusionNet_7Bx2_MoE_14B-GGUF

Same weights, converted vs TomGrc/FusionNet_7Bx2_MoE_14B. Same weights stored in another dtype (BF16 → F16/F32), plus 192 new tensors.

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/65, other 0/32, Attention 0/128

On the Hub · Downloads on Model Pulse