huihui-ai/Huihui-Qwen3-30B-A3B-Thinking-2507-abliterated
Abliterated vs Qwen/Qwen3-30B-A3B-Thinking-2507. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 48 of 48 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Embeddings 0/1, Norms 0/193, MLP 838/2613, Attention 48/192, lm_head 0/1
6 derivatives checked
- mradermacher/Huihui-Qwen3-30B-A3B-Thinking-2507-abliterated-i1-GGUF: Quantization
- mradermacher/Huihui-Qwen3-30B-A3B-Thinking-2507-abliterated-GGUF: Quantization
- akpsahan/Qwen3-30B-A3B-Gemini-Pro-High-Reasoning-2507-ABLITERATED-UNCENSORED: LoRA-style
- DavidAU/Qwen3-42B-A3B-2507-Thinking-Abliterated-uncensored-TOTAL-RECALL-v2-Medium-MASTER-CODER: Partial fine-tune
- DavidAU/Qwen3-30B-A3B-Gemini-Pro-High-Reasoning-2507-ABLITERATED-UNCENSORED: LoRA-style
- DavidAU/Qwen3-30B-A3B-Claude-4.5-Opus-High-Reasoning-2507-ABLITERATED-UNCENSORED-V2: LoRA-style