wangzhang/Qwen3.6-35B-A3B-abliterated
Abliterated vs Qwen/Qwen3.6-35B-A3B. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj, out_proj) changed, in 20 of 40 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Embeddings 0/1, Attention 20/280, MLP 2/280, Norms 0/131, lm_head 0/1
2 derivatives checked
- mradermacher/Qwen3.6-35B-A3B-abliterated-i1-GGUF: Quantization
- mradermacher/Qwen3.6-35B-A3B-abliterated-GGUF: Quantization