richardyoung/Qwen3-8B-Abliterated
Abliterated vs Qwen/Qwen3-8B. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 16 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 16/108, Attention 16/144, lm_head 0/1
2 derivatives checked
- richardyoung/Qwen3-8B-Abliterated-GGUF: Quantization
- poloxov/Qwen3-8B-Abliterated-GGUF: Quantization