llmfan46/Qwen3.5-122B-A10B-Uncensored-Heretic-Native-MTP-Preserved-GGUF
Abliterated vs Qwen/Qwen3.5-122B-A10B. llmfan46/Qwen3.5-122B-A10B-Uncensored-Heretic-Native-MTP-Preserved-GGUF is a GGUF (BF16/F32) of different weights. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 35 of 48 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: lm_head 0/1, Embeddings 0/1, Attention 9/48, MLP 35/192, Norms 0/121