Qwe1325/Huihui-gemma-3n-E4B-it-abliterated-GGUF
Same weights, converted (fewer layers) vs huihui-ai/Huihui-gemma-3n-E4B-it-abliterated. Qwe1325/Huihui-gemma-3n-E4B-it-abliterated-GGUF matches part of huihui-ai/Huihui-gemma-3n-E4B-it-abliterated (809 of its 1675 tensors; the rest of huihui-ai/Huihui-gemma-3n-E4B-it-abliterated has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32), plus 37 new tensors.
Tensors changed: Embeddings 0/1, other 0/246, Norms 0/317, MLP 0/105, Attention 0/140