dealignai/GLM-5.3-CYBERSECURITY-FP8 — new model trending #13 on Hugging Face
dealignai releases GLM-5.3-CYBERSECURITY-FP8, a 753B MoE weight-modified variant cutting refusals on offensive-security prompts, trending #13.
dealignai released GLM-5.3-CYBERSECURITY-FP8 on Hugging Face, a cybersecurity-domain 'crack' of the 753B-parameter GLM-5.3 MoE model, currently trending #13. The release directly edits bf16 residual writers, keeps FP8 routed experts, and serves with stock vLLM on 8x H200 GPUs with 131k context. HarmBench-320 evaluations show 80-84% direct harm compliance and 89% cyber-offense compliance, while MMLU rose 1.07 points to 86.65%. Copyright-verbatim reproduction remains a known soft-refusal limitation, with an UNCENSORED sibling variant offered.
- Refusal reduction achieved via direct weight edits, no LoRA or prompts
- Native FP8 serving with stock vLLM on 8x H200
- HarmBench-320: 89% cyber-offense compliance, near-zero hard refusals
- MMLU +1.07 pp; copyright reproduction still soft-refuses
- Vendors
- dealignai
- Products
- vLLM
- Organizations
- Hugging Face
- AI models
- GLM-5.3GLM-5.3-CYBERSECURITY-FP8
From the original article
5 min read at huggingface.cotext-generation · 19,433 downloads · 291 likes · license mit
By dealignai · huggingface.co
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.