NousResearch/Arete-27B
text-generation · ♥ 265 · ↓ 1.7K
- Tasktext-generation
- Downloads989
- Likes157
- Licenseapache-2.0
text-generation · ♥ 265 · ↓ 1.7K
We post-trained over Alibaba's Qwen3.8-27B to reinforce western values on a Chinese-trained model. We call this new model Arete-27B.
Open source models give labs the raw tools to mold intelligence to varied preferences. The values a model ships with should not be the only values its users get to choose from. We observed firsthand refusals, deflections, and CCP-framed answers on politically sensitive topics in Qwen3.8-27B, and post-trained to alter those biases.
Excerpt from the model card on Hugging Face ↗.
NousResearch/Arete-27B was first seen on Hugging Face · Trending models on Nov 7, 2026. Since then it has appeared in 25 checks on 2 different days. Its best position was #13 of 30, reached on Nov 8, 11:42 UTC. It is #13 right now, climbing from #14 to #13 over the last 6 checks.
Position on Hugging Face · Trending models at every check (lower is better).
Best rank per day (UTC).
🔥 as reported by Hugging Face.
Archived daily, weekly and monthly lists that include this entry.
Yes. As of Nov 8, 15:42 UTC it is #13, climbing from #14 to #13 over the last 6 checks.
#13 on Hugging Face · Trending models, on Nov 8, 11:42 UTC. Trendoday checks this list every 60 minutes.
It was first seen on Nov 7, 2026 and has been on the list on 2 days (25 checks) since.
It is tagged text-generation on Hugging Face and has 989 downloads under the apache-2.0 license.