mlabonne/Qwen3-1.7B-abliterated
Abliterated vs Qwen/Qwen3-1.7B. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 28 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 28/84, Attention 28/112
5 derivatives checked
- bartowski/mlabonne_Qwen3-1.7B-abliterated-GGUF: Abliterated
- mradermacher/Qwen3-1.7B-abliterated-GGUF: Abliterated
- swittk/Qwen3-1.7B-abliterated-Q4_K_M-GGUF: Quantization
- hermeschen1116/Qwen3-1.7B-abliterated-6bit-mixed_4_6-mlx: Quantization
- NikolayKozloff/Qwen3-1.7B-abliterated-Q8_0-GGUF: Quantization