Nous Research ·

Nous Research unveils Arete-27B, a post-trained Qwen3.8-27B model that reinforces Western values, saying the underlying Chinese model's bias layer is shallow

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.

Nous Research unveils Arete-27B, a post-trained Qwen3.8-27B model that reinforces Western values, saying the underlying Chinese model's bias layer is shallow

Lead Source

How this story grew

Coverage · 0 Discussion · 0
Nov 8Nov 10

More

Implicator.ai: Implicator.ai
The Decoder: The Decoder
Nous Research on Hugging Face: Nous Research on Hugging Face
Nous Research on Hugging Face: Nous Research on Hugging Face

Discussion

Related stories