Skip to content
Trending storyDeveloping

Nous Research releases Arete-27B, a Qwen3.8-27B fine-tune for lower propaganda rates

1 article1 sourcesince Nov 6Last article 4h ago ·

Overview

AISummary of 1 article

Nous Research releases Arete-27B, a post-trained version of Qwen3.8-27B, with its weights, evaluation and training data.

The company says fine-tuning on about 53 million tokens cut the model's propaganda rate on its 803-prompt eval from 22% to 1%.

Nous Research also says the model shows no significant performance tradeoff on its Hermes Bench score. These results are the company's own claims, reported in its X post and blog post at nousresearch.com/arete, and have not been independently verified.

Written by AI from the articles below · updated Nov 6, 4:57 PM ET

Check the sources:

Latest developmentNov 6, 4:48 PM ET
Nous Research releases Arete-27B, a Qwen3.8-27B fine-tune with reduced propaganda rate

Article timeline

The articles in this story. Times are ET.

Nov 6
  1. Nous ResearchOfficial
    Nous Research releases Arete-27B, a Qwen3.8-27B fine-tune with reduced propaganda rate

    AINous Research releases Arete-27B, a post-trained version of Qwen3.8-27B, with its weights, evaluation, and training data. The company says fine-tuning on roughly 53 million tokens cut the model's propaganda rate on its 803-prompt eval from 22% to 1%. It says the model's Hermes Bench score shows no significant performance tradeoff.

    Video from @NousResearch's post

Heat Trend

Current comparable heat
9
Peak comparable heat
10Nov 6, 5:00 PM ET
Change in past 24 hours
–

The trend compares only continuously observed participants, so its scope may be smaller than the current heat total. Hover or tap for hourly heat; use arrow keys with a keyboard.