mradermacher/Bohf-12B-MoE-3A-GGUF
Same weights, converted vs theprint/Bohf-12B-MoE-3A. Same weights stored in another dtype (BF16 → F16/F32), plus 85 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/57, Attention 0/112, other 0/28
Same weights, converted vs theprint/Bohf-12B-MoE-3A. Same weights stored in another dtype (BF16 → F16/F32), plus 85 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/57, Attention 0/112, other 0/28