llmfan46/Qwen3.6-27B-uncensored-heretic-v1
Abliterated vs Qwen/Qwen3.6-27B. Looks like abliteration (refusal removal): only the output projections (o_proj, out_proj) changed, in 27 of 64 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Embeddings 0/4, MLP 0/304, Attention 27/556, lm_head 0/1, Norms 0/319
2 derivatives checked
- llmfan46/Qwen3.6-27B-uncensored-heretic-v1-GGUF: Same weights, converted
- CCSSNE/llmfan46-Qwen3.6-27B-uncensored-heretic-v1-GGUF: Same weights, converted
1 other repos hold byte-for-byte identical weight files.