prithivMLmods/Qwen3.5-35B-A3B-Unredacted-MAX
Abliterated vs Qwen/Qwen3.5-35B-A3B. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj, out_proj) changed, in 40 of 40 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: lm_head 0/1, Embeddings 0/4, Attention 40/388, MLP 40/312, Norms 0/241
2 derivatives checked
- mradermacher/Qwen3.5-35B-A3B-Unredacted-MAX-i1-GGUF: Quantization
- mradermacher/Qwen3.5-35B-A3B-Unredacted-MAX-GGUF: Quantization