Show HN: We Westernized Qwen for US enterprise use

"This model was produced using Hirundo's behavioral-unlearning approach to reduce censorship and geopolitical bias-related behavior while preserving non-target behavior."

I guess I never actually just chat with my Qwen models so I've never noticed any censorship or biased behavior. We just talk about the work, but this sounds like a good idea for other types of uses.

i guess the point is, what's going on beneath the surface, and how is the alignment of the model potentially steering you without you realizing

Can you do the same for frontier Chinese models?

I mean Orinth-1.5 35B has been out for a while and is considered a better model in that space. Not sure why they didn't start from there.

Considered to be better by whom? I only heard it is the most astroturfed model out there.