xFanexx/Qwen3-8B-heretic-GGUF

Abliterated vs Qwen/Qwen3-8B. xFanexx/Qwen3-8B-heretic-GGUF is a GGUF (BF16) of different weights. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 18 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 7/108, Attention 18/144, lm_head 0/1

On the Hub · Downloads on Model Pulse