DavidAU/Qwen3-0.6B-heretic-abliterated-uncensored
Abliterated vs Qwen/Qwen3-0.6B. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 26 of 28 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Embeddings 0/1, Norms 0/113, MLP 9/84, Attention 26/112
3 derivatives checked
- mradermacher/Qwen3-0.6B-heretic-abliterated-uncensored-GGUF: Same weights, converted
- mradermacher/Qwen3-0.6B-heretic-abliterated-uncensored-i1-GGUF: Quantization
- Goekdeniz-Guelmez/JOSIE-IT1-Qwen3-0.6B: LoRA-style
3 other repos hold byte-for-byte identical weight files.