😱天呐！最强中国模型Qwen3.8-27B被一键“西化”了，党宣率从22%暴跌到1%！
This is a AI post classified by AGK Intelligence as Open & local models (a model release), kept by the AI Radar because it carries real work, not commentary.
😱天呐！最强中国模型Qwen3.8-27B被一键“西化”了，党宣率从22%暴跌到1%！ Hermes开源Arete-27B，直接把目前最强本地可用的开源基座Qwen3.8-27B，用仅5300万token微调，彻底改造成“西方价值观版”！ 自由表达、民主、隐私这些敏感话题，党宣率从22%直接干到1%，自由表达类别更是60%→1%，同时性能几乎零损失！ 核心亮点 🔹彻底削弱中国开源模型里的国家叙事对齐，强化言论自由等西方价值观 🔹803题七大价值观评测全面碾压原版，事实分数从2.32→2.98 🔹权重 + 评测集 + 训练数据全部开源，真正可验证、可复现 🔹保持原版超强Agent能力，本地就能跑真正敢说话的模型 3步立刻上手 1️⃣打开Hugging Face下载权重：https://huggingface.co/NousResearch/Arete-27B 2️⃣用transformers / vLLM / llama.cpp加载（支持64k上下文） 3️⃣直接对话或接入Hermes Agent，享受无审查高事实性回答！ 博客全文：https://nousresearch.com/arete 评测集：https://huggingface.co/datasets/NousResearch/Propaganda_Eval 训练数据：https://huggingf
Posted by SuSu_酥酥👅 (27.1k followers) 17 h ago · 289 likes · 34.3k views · view the original post on X. Kept by the AI Radar as Open & local models. Tools mentioned: arete-27b, propaganda_eval, arete-data-pairs.
More AI work like this
- Qwen3.8 27B QSAではこのアーキテクチャを使い、速度低下を大幅に軽減しています — @_ryu15_
- Meet Mistral Small 3.2 24B Instruct, now in a heretic GGUF edition. This uncensored,… — @HuggingModels
- 💥细节感拉满！Qwen 4.0 蜜蜂向日葵测试炸了！ — @NFT_Chen
- @TheZachMueller — @TheZachMueller
- Here DSv4.1 Flash recipe by @christopherowen in action! — @ivanfioravanti
- Qwen Qoduck 花了 2 个小时生成的美国白宫 3D 建模 — @leo114119
- HyperFlow H3 Flash has passed 15,000 downloads on @huggingface in under 24 hours. — @video_rebirth
- Every lab should ship its own 4bit weights. — @plotarmordev
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 65.2k posts from 5k X accounts over the last 14 days, 10.6k tools, 19 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-07 16:45 UTC. Full method.