richardyoung/Qwen3-14B-abliterated-GGUF
Abliterated vs Qwen/Qwen3-14B. richardyoung/Qwen3-14B-abliterated-GGUF is a GGUF (F16) of different weights. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 35 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 35/120, Attention 23/160, lm_head 0/1