mradermacher/Huihui-MoE-0.8B-2E-GGUF
Same weights, converted vs huihui-ai/Huihui-MoE-0.8B-2E. Same weights stored in another dtype (BF16 → F16/F32), plus 84 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/113, MLP 0/28, Attention 0/112
Same weights, converted vs huihui-ai/Huihui-MoE-0.8B-2E. Same weights stored in another dtype (BF16 → F16/F32), plus 84 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/113, MLP 0/28, Attention 0/112