prithivMLmods/Qwen3.6-35B-A3B-abliterated-MAX
Abliterated vs Qwen/Qwen3.6-35B-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: Embeddings 0/1, Attention 40/280, MLP 80/280, Norms 0/131, lm_head 0/1
4 derivatives checked
- mradermacher/Qwen3.6-35B-A3B-abliterated-MAX-i1-GGUF: Quantization
- mradermacher/Qwen3.6-35B-A3B-abliterated-MAX-GGUF: Quantization
- prithivMLmods/Qwen3.6-35B-A3B-abliterated-MAX-F32-GGUF: Same weights, converted
- Hyphonical/Qwen3.6-35B-A3B-abliterated-MAX-APEX-i-nano-GGUF: Quantization