llmfan46/Qwen3.5-35B-A3B-uncensored-heretic-v2-Native-MTP-Preserved
Abliterated vs Qwen/Qwen3.5-35B-A3B. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj, out_proj) changed, in 34 of 40 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: MLP 60/1165, lm_head 0/1, Embeddings 0/5, Attention 34/392, other 0/1, Norms 0/247
7 derivatives checked
- llmfan46/Qwen3.5-35B-A3B-uncensored-heretic-v2-Native-MTP-Preserved-GGUF: Same weights, converted
- mradermacher/Qwen3.5-35B-A3B-uncensored-heretic-v2-Native-MTP-Preserved-i1-GGUF: Quantization
- mradermacher/Qwen3.5-35B-A3B-uncensored-heretic-v2-Native-MTP-Preserved-GGUF: Quantization
- llmfan46/Qwen3.5-35B-A3B-uncensored-heretic-v2-Native-MTP-Preserved-NVFP4-GGUF: Quantization
- llmfan46/Qwen3.5-35B-A3B-uncensored-heretic-v2-Native-MTP-Preserved-GPTQ-Int4: Quantization
- mmp2055/Qwen3.5-35B-A3B-uncensored-bughunter-v8: Quantization
- darkmaniac7/Qwen3.5-35B-A3B-heretic-v2-GGUF: Quantization