huihui-ai/Huihui-MiroThinker-v1.0-8B-abliterated
Abliterated vs miromind-ai/MiroThinker-v1.0-8B. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 35 of 36 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Embeddings 0/1, Norms 0/145, MLP 35/108, Attention 35/144, lm_head 0/1
3 derivatives checked
- mradermacher/Huihui-MiroThinker-v1.0-8B-abliterated-i1-GGUF: Quantization
- mradermacher/Huihui-MiroThinker-v1.0-8B-abliterated-GGUF: Same weights, converted
- noctrex/Huihui-MiroThinker-v1.0-8B-abliterated-GGUF: Same weights, converted