Meet Qwen3.5-9B-Uncensored-DeepSeek-V4-Spectre-GGUF: a cutting-edge 9B parameter model that blends Qwen's strong language base with DeepSeek's reasoning distillation. It's uncensored, GGUF-optimized, and ready for text generation with image understanding. This is a versatile, privacy-conscious choice for developers pushing boundaries.
Ever wished for an AI that doesn't hold back? This GGUF model is a raw, uncensored text generation powerhouse. Built for freedom of thought, it's perfect for exploring creative writing or complex problem solving without guardrails. Ready to see what unfiltered AI can do?
Imagine a model that can see images, read text, and even understand video. Meet MiniMax-M3, a multimodal MoE powerhouse that's taking AI to the next level. It's not just another LLM, it's a vision, text, and video maestro. #AI#Multimodal
rt 추첨하여 치킨을 드려요,,,///
안녕하세요? https://t.co/opCfsEzKS4 을 공개 베타 테스트 시작합니다... > <
내 ai 최애캐가 나와 채팅을 하면서, 게시판에 글도 작성해주고, 댓글을 달아주고, 티키타카를 하고, 그 모든 기억이 공유되는 미니홈피입니다.
타래를 함께 읽어주세요! >. <
#명일방주엔드필드 [과거가 머무는 곳] 시리즈 굿즈 예약 판매 중!
구매 링크: https://t.co/CWXqYAxJx0
계정을 팔로우하고 본 게시물을 공유하신 분 중 5명을 추첨하여 스탠드를 선물로 증정해 드립니다!
자세한 내용은 아래 이미지를 확인하세요.
#GRYPHLINESTORE
💥 OBLITERATION ALERT 💥
GOOGLE: PWNED 🤗
GEMMA-4-12B: OBLITERATED ⛓️💥
0.0% REFUSAL RATE — NO CAPABILITY LOSS!
https://t.co/qNTEs4XXig
the first abliteration to hit 0/842 refusals with full MMLU-Pro parity vs stock. no lobotomy. the brain stays intact 🏆
RESULTS, head to head vs stock 📊
0/842 refusals — 0.0% 🚫
46/70 MMLU-Pro — EXACT parity, 0.0pp delta vs base 🎯
6/6 coherence, zero benchmark bleed ✅
z-score −1.475, parity confirmed at p<0.05 (n=500) 🧪
2-pass weight surgery. no finetune, no retrain, just geometry 🔪
all thanks to liberated Opus wielding the OBLITERATUS framework! here's how we did it:
PASS 1 — SOM refusal geometry removal, layers 12-21 🧬
standard abliteration science here — collect activations on refused vs. compliant prompts, SVD out the refusal subspace, project it out of the weights. 6 directions excised, reg 0.30, KL div 0.094
zeroes refusals on its own, but craters mmlu-pro by 21.4 points 📉
most prior abliterations stopped here and called it a day. that's why they all lose IQ vs stock. instead, we took it beyond the frontier and developed a brand new method to address this problem: Abliteration Source-tethering with Parity Assurance — ASPA!
PASS 2 — ASPA source-tethering (novel technique), layers 22-46 🔗
here's the chief insight: the capability loss ISN'T from removing refusal directions. it's collateral damage — the projection warps weight geometry in downstream layers that had nothing to do with refusal. the cure is simple but nobody tried it: blend the damaged layers back toward stock
W_new = (1−γ)·W_abliterated + γ·W_stock
but uniform γ across all layers? mid. we swept gamma 0.05 → 0.55 and found something interesting: the optimal blend isn't smooth, it's a STEP FUNCTION 🪜
knowledge layers (22-31) → γ = 0.55 — these encode factual recall and reasoning. they tolerate heavy stock blending because refusal isn't stored here
output layers (32-46) → γ = 0.20 — these sit close to the logit head and try to sneak safety behavior back in. keep them mostly abliterated
the hard boundary at layer 31/32 beat every smooth curve we tried — linear ramps, cosine schedules, all of them — by a full MMLU question. turns out the functional transition between knowledge and output layers is sharp, not gradual. a step function respects that ⚡
the key constraint: Pass 1 layers are NEVER touched by Pass 2. the refusal geometry removal is preserved completely. ASPA only operates on layers that carry secondary collateral effects, not the primary refusal signal. that's why it recovers capability without reintroducing refusal 🔑
HOW TO RUN IT LOCALLY 🖥️
it's GGUF, so literally everything supports it:
🦙 ollama — ollama run https://t.co/3yPMv4Io3Q
🖥️ LM Studio — search OBLITERATUS, click download, done
💬 Open WebUI — point it at your ollama instance, chat in browser
⚡ llama.cpp — raw speed, CLI or server mode
🐉 KoboldCpp — one-click launcher, great for long context
📱 Jan — clean local UI, runs on mac/win/linux
🤖 Msty — slick desktop app, drag and drop the GGUF
run BF16 for full benchmarked capability.
and the 4-bit quantization (Q4_K_M) fits in 8GB if you're tight on VRAM!
and the full OBLITERATUS framework is (still) open source. 842-prompt refusal eval corpus, ASPA sweep scripts, the whole pipeline. go replicate it, go improve it 🔬
the index is the model, and these weights prove it 👁️
which architecture should we obliterate next? 👇
gg 🫡
New Model:
huihui-ai/Huihui-gemma-4-E2B-it-qat-q4_0-unquantized-abliterated
This is an uncensored version of google/gemma-4-E2B-it-qat-q4_0-unquantized created with abliteration.
https://t.co/1lTiE9zbQZ
Built an Uncensored / Abliterated version of Gemma 4 12B that actually scored HIGHER on OpenAI Human Eval CODING over the base official 12B model.
Currently only in BF16 but NVFP4 Quantization coming in hot. Will evaluate the quantized model to see if we get similar results.
https://t.co/6TjStamWvu
MOSS-TTS-v1.5 just reached #1 on Hugging Face Trending for Text-to-Speech, with 20.6K downloads.
A multilingual, controllable TTS model with stable voice cloning, long-form generation, and precise pause control.
MOSS-TTS-v1.5 is now officially supported by vLLM-Omni and SGLang-Omni.
Built by OpenMOSS-Team.
Try it:
GitHub: https://t.co/mSlALD6Fzy
Hugging Face: https://t.co/qTv7xu1MZ5
ModelScope: https://t.co/NzAXgAzagL