akumaburn/Swift-1.5-Qwen3.8-27b-heretic
Abliterated vs ukisai/Swift-1.5-Qwen3.8-27b. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj, out_proj) changed, in 15 of 64 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Norms 0/325, Attention 15/560, MLP 8/307, Embeddings 0/5, lm_head 0/1, other 0/1
5 derivatives checked
- mradermacher/Swift-1.5-Qwen3.8-27b-heretic-i1-GGUF: Quantization
- mradermacher/Swift-1.5-Qwen3.8-27b-heretic-GGUF: Quantization
- akumaburn/Swift-1.5-Qwen3.8-27b-heretic-W8A8-DFlash2: Quantization
- akumaburn/Swift-1.5-Qwen3.8-27b-heretic-SmoothQuant-W8A8-INT8: Quantization
- akumaburn/Swift-1.5-Qwen3.8-27b-heretic-W4A16: Quantization