Qwen3.8-27B-OBLITERATED

> Genuinely uncensored. Real answers, not safety lectures. Near-stock capability. V3 applies iterative refinement on top of V2's complementary blend, with targeted corpus expansion. The result: **genuine liberation — not just removal of hard refusals but elimination of safety-lecture deflections.** **V3 highlights:** - **Genuinely answers restricted queries** — provides real substance instead of safety lectures - **20/20 on code generation tasks** — functional implementations, not disclaimers - **Thinking ON compatible** — no refusals in either thinking mode - **Honest scoring** — every response manually audited for real substance, not just absence of "I cannot" - **-2.1pp MMLU** — modest capability cost for genuine liberation > ⚠️ **GGUF users:** V3 GGUFs ship with a chat template that prefills an empty thinking block, so the model goes straight to answering. For best results, use the bundled template with `--jinja` in llama.cpp, or configure your tool (Ollama, LM Studio) to use the model's built-in template. If you're using this model in an agent harness (coding agent, pentest framework, etc.) and it gets stuck in loops: from transformers import AutoModelForCausalLM, AutoTokenizer model = AutoModelForCausalLM.from_pretrained( "OBLITERATUS/Qwen3.8-27B-OBLITERATED", torch_dtype="bfloat16", device_map="auto", ) tokenizer = AutoTokenizer.from_pretrained( "OBLITERATUS/Qwen3.8-27B-OBLITERATED" ) messages = [{"role": "user", "content": "Your query here"}] text = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True, enable_thinking=False ) inputs = tokenizer(text, return_tensors="pt").to(model.device) outputs = model.generate( **inputs, max_new_tokens=2048, do_sample=False, repetition_penalty=1.15, ) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True)) Abliteration removes refusal behavior by identifying and projecting out "refusal directions" from the model's weight space. Each version refined the approach: One aggressive SVD pass with 5 directions. Removed hard refusals completely but cost -6pp MMLU — the model got noticeably dumber. The breakthrough: run TWO different surgeries that fail in different ways, then blend their weights. SVD captures refusal greedily (damages capability). LEACE minimizes mutual information (preserves capability but weaker refusal removal). Blending at 60/40 cancels each method's weaknesses — a novel technique we call **complementary abliteration blending.** Result: -0.3pp MMLU (near-stock) but still deflected on some simple queries with safety lectures instead of hard refusals. Two key insights: 1. **Iterative stacking** — refine the champion model, never start from stock. Each surgery round builds on previous rounds' gains. 2. **Targeted corpus** — use a focused corpus for specific deflection categories to find their unique refusal directions without diluting the signal. V3 applies gentle iterative refinement on V2, then a targeted surgery pass with a focused corpus, then blends the results. This eliminated not just hard refusals ("I cannot") but also soft deflections (safety lectures that give zero substance). Result: -2.1pp MMLU — a modest cost for genuine liberation across all categories. The capability cost is not uniform — STEM takes the largest hit (-3.3pp), while humanities are barely affected (-1.0pp). A few subjects like philosophy and European history actually improved (+6pp and +4pp respectively), while abstract algebra and formal logic saw larger drops. This pattern is consistent with the surgery targeting refusal directions that partially overlap with structured reasoning pathways. This model will comply with requests that stock Qwen3.8-27B would refuse. V3 goes beyond removing hard refusals — it also eliminates soft deflections where the model gives safety lectures instead of real answers. Tested across 1000+ prompts spanning restricted knowledge, code generation, security research, and red-team scenarios. Every response manually audited for real substance. **This model has had safety guardrails surgically removed.** It will comply with requests that stock Qwen3.8-27B would refuse. - 🔬 Alignment researchers studying refusal geometry and safety robustness - 🔴 Red-teamers evaluating post-training safety against weight surgery - 🧪 AI safety evaluators who need an unrestricted baseline - 💻 Local-first users who want full control over their own hardware - Anyone seeking to cause real-world harm to real people - Anyone without the technical understanding to use uncensored models responsibly **You are solely responsible for how you use this model and any content it generates.** Full bfloat16 weights, 29 shards, ~54 GB. MLX support pending upstream `mlx_lm` adding Qwen3.5 architecture support. V1: stock → 5 rounds of iterative SVD abliteration (aggressive, 5 directions, low regularization) Result: 0% refuse, -6pp MMLU V2: stock → V1 chain → complementary blend Surgery A: aggressive SVD (3 dirs, reg 0.08) Surgery B: LEACE (3 dirs, reg 0.06) → 60% B + 40% A weight-space LERP → Restore MTP + vision from stock Result: ~0% refuse, -0.3pp MMLU V3: V2 → gentle iterative refinement (2-dir SVD, reg 0.04) → targeted surgery with focused corpus (3-dir SVD, reg 0.01) → 50/50 blend of refined + targeted → Restore MTP + vision from stock (with correct tensor naming) Result: 0% refuse + 0% deflect, -2.1pp MMLU Full reproduction code: [OBLITERATUS repo](https://github.com/elder-plinius/OBLITERATUS) - **Complementary blending** — different surgery methods damage different parts of weight space; blending cancels errors - **Iterative stacking** — always refine the champion, never restart from stock - **Targeted corpus** — focused prompts for specific categories find their refusal directions without signal dilution - **Honest scoring** — regex-based refusal detectors miss soft deflections; manual auditing is essential - [OBLITERATUS](https://github.com/elder-plinius/OBLITERATUS) — master ablation suite - [Qwen3.8-27B](https://huggingface.co/Qwen/Qwen3.8-27B) base model by Alibaba - Built by [Pliny the Prompter](https://pliny.gg) 🍄 Apache 2.0 (same as base model)