prithivMLmods/Polaris-VGA-9B-Post1.0e
Abliterated vs Qwen/Qwen3.5-9B. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj, out_proj) changed, in 31 of 32 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: lm_head 0/1, Embeddings 0/4, MLP 31/208, Attention 31/332, Norms 0/215
2 derivatives checked
- mradermacher/Polaris-VGA-9B-Post1.0e-i1-GGUF: Quantization
- mradermacher/Polaris-VGA-9B-Post1.0e-GGUF: Same weights, converted