Anuncio

SRExpert

Deja de saltar entre 6 herramientas de Kubernetes.

Monitoreo, alertas, seguridad, despliegues Helm y operaciones con IA en una sola plataforma.

Probar 30 días gratis

Fine-tuning GPT-OSS-20B for multilingual reasoning on Amazon SageMaker HyperPod

23d

Antigüedad

Publicado
Recolectado

Learn how we fine-tuned GPT-OSS-20B for multilingual reasoning on Amazon SageMaker HyperPod, and how to decide between supervised fine-tuning (SFT) and reinforcement learning with GRPO. SFT took reasoning-language accuracy from 22% to 100%, and GRPO added measurable gains where headroom existed.

Extracto de la fuente

GPT-OSS-20B is an open-weight reasoning model that thinks in English. Ask it to reason in French, German, Spanish, or Italian and it acknowledges the instruction, then produces its chain-of-thought in English anyway. On a 50-example multilingual reasoning test, the base model reasoned in the correct target language only 22 percent of the time. That 22 percent was almost entirely the English examples (English 100 percent, French 0 percent, German 10 percent, Spanish 0 percent, Italian 0…

overfeed.news indexa y enlaza. Publicamos un extracto breve; el artículo completo sigue en AWS Machine Learning Blog.

Inicia sesión para seguir esta fuente
Fine-tuning GPT-OSS-20B for multilingual reasoning on Amazon…