Gustav0-Freind/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-MTP-GGUF
Abliterated vs lordx64/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled. Gustav0-Freind/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-MTP-GGUF is a GGUF (F16) of different weights. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 39 of 40 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Embeddings 0/1, Norms 0/101, MLP 39/200, Attention 10/40, lm_head 0/1