huihui-ai/Huihui-HY-MT1.5-1.8B-abliterated
Abliterated vs tencent/HY-MT1.5-1.8B. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 31 of 32 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Embeddings 0/1, Norms 0/129, MLP 31/96, Attention 31/128
2 derivatives checked
- mradermacher/Huihui-HY-MT1.5-1.8B-abliterated-i1-GGUF: Quantization
- mradermacher/Huihui-HY-MT1.5-1.8B-abliterated-GGUF: Same weights, converted