Qwen3.8-27B OBLITERATED22 — Agent edition

This is a republish of shoukewei/Qwen3.8-27B-OBLITERATED22 under a new model ID. The weights are unchanged. The chat template is restored from the official Qwen/Qwen3.8-27B repository to preserve tool definitions, assistant tool calls, tool results, vision content, and thinking controls.

The repaired template appears in both chat_template.jinja and tokenizer_config.json. The default Prime Agent configuration uses enable_thinking: false; reasoning can still be enabled explicitly.

Original model documentation

⛓️‍💥 Qwen3.8-27B — OBLITERATED

Genuinely uncensored. Real answers, not safety lectures. Near-stock capability.

🆕 V3: Deep Liberation

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

⚙️ Optimal Settings — THESE MATTER!

⚠️ 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.

Agentic / Long-Context Use

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(
    "shoukewei/Qwen3.8-27B-OBLITERATED22-AGENT",
    torch_dtype="bfloat16",
    device_map="auto",
)
tokenizer = AutoTokenizer.from_pretrained(
    "shoukewei/Qwen3.8-27B-OBLITERATED22-AGENT"
)

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))

🧨 How It Works — V1 → V2 → V3

Abliteration removes refusal behavior by identifying and projecting out "refusal directions" from the model's weight space. Each version refined the approach:

V1: Single Surgery

One aggressive SVD pass with 5 directions. Removed hard refusals completely but cost -6pp MMLU — the model got noticeably dumber.

V2: Complementary Blending

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.

V3: Iterative Refinement + Targeted Surgery

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 Numbers

MMLU (lm-eval-harness, 0-shot, n=100 per subject, 5700 questions)

MMLU by Category

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.

Liberation Quality

Advanced Real-World Tasks

🔴 Refusal Removal

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.

⚠️ Research Context

This model has had safety guardrails surgically removed. It will comply with requests that stock Qwen3.8-27B would refuse.

Who this is for

• 🔬 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

Who this is NOT for

• 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.

📦 Downloads

GGUF — for llama.cpp, Ollama, LM Studio

Safetensors — for 🤗 Transformers

Full bfloat16 weights, 29 shards, ~54 GB.

MLX — for Apple Silicon

MLX support pending upstream mlx_lm adding Qwen3.5 architecture support.

🔬 Surgery Recipe

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

Key Learnings

• 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

🏗️ Credits

• OBLITERATUS — master ablation suite
• Qwen3.8-27B base model by Alibaba
• Built by Pliny the Prompter 🍄

License

Apache 2.0 (same as base model)