ArtomYuan/Qwen3.8-27B-abliterated-ROCmFPX
Same weights, converted vs huihui-ai/Huihui-Qwen3.8-27B-abliterated. Same weights stored in another dtype (BF16 → T103/F32), plus 63 new tensors.
Tensors changed: Norms 0/161
Same weights, converted vs huihui-ai/Huihui-Qwen3.8-27B-abliterated. Same weights stored in another dtype (BF16 → T103/F32), plus 63 new tensors.
Tensors changed: Norms 0/161