RootMonsteR/Qwen3-14B-Abliterated
Abliterated vs Qwen/Qwen3-14B. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 32 of 40 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Embeddings 0/1, Norms 0/161, MLP 32/120, Attention 19/160, lm_head 0/1
1 derivatives checked
- RootMonsteR/Qwen3-14B-Abliterated-GGUF: Quantization