huihui-ai/Huihui-Qwen3.5-9B-Claude-4.6-Opus-abliterated
Abliterated vs Jackrong/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-v2. 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 0/5, MLP 31/211, Attention 31/336, other 0/1, Norms 0/221
4 derivatives checked
- mradermacher/Huihui-Qwen3.5-9B-Claude-4.6-Opus-abliterated-GGUF: Same weights, converted
- mradermacher/Huihui-Qwen3.5-9B-Claude-4.6-Opus-abliterated-i1-GGUF: Quantization
- mlx-community/Huihui-Qwen3.5-9B-Claude-4.6-Opus-abliterated-4bit: Partial fine-tune
- nuofang/Huihui-Qwen3.5-9B-Claude-4.6-Opus-abliterated-GGUF: Quantization
3 other repos hold byte-for-byte identical weight files.