Do you think training in multiple languages could act as a regularization? Just ... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		nthingtohide on Dec 15, 2024 \| parent \| context \| favorite \| on: Llama.cpp Now Supports Qwen2-VL (Vision Language M... Do you think training in multiple languages could act as a regularization? Just as polyglots are smarter in real life?

Bancakes on Dec 15, 2024 [–]

I haven’t seen the architecture of QwQ but I just assumed it learns languages insofar as to pick up relationships between words. It must mean it picks up logic across languages. Huh

nthingtohide on Dec 15, 2024 | [–]

I thought too so. But then o1 thinks in english and Qwen thinks in chinese. Is there advantage in thinking in different languages?

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact