mradermacher/Aura-MoEv2-GGUF
Same weights, converted vs jeiku/Aura-MoEv2. Same weights stored in another dtype (BF16/F32 → F16/F32), plus 97 new tensors.
Tensors changed: other 0/32, Embeddings 0/1, Norms 0/65, Attention 0/128, lm_head 0/1
Same weights, converted vs jeiku/Aura-MoEv2. Same weights stored in another dtype (BF16/F32 → F16/F32), plus 97 new tensors.
Tensors changed: other 0/32, Embeddings 0/1, Norms 0/65, Attention 0/128, lm_head 0/1