{"id":"215e7dca-1e23-47cb-81ef-5ea5f2bee04b","url":"https://api.tumn.com/news/215e7dca-1e23-47cb-81ef-5ea5f2bee04b","title":"Fine-tuning GPT-OSS-20B for multilingual reasoning on Amazon SageMaker HyperPod","summary":"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 h","sections":[],"faq":[],"sources":[{"url":"https://aws.amazon.com/blogs/machine-learning/fine-tuning-gpt-oss-20b-for-multilingual-reasoning-on-amazon-sagemaker-hyperpod/","title":"AWS Machine Learning Blog","publishedAt":"2026-10-20T17:48:27.000Z"}],"author":"TUMN 큐레이션","aiAssisted":false,"reviewStatus":"automated","reviewNote":"원문 제목과 공개된 발췌를 인용하고 원문으로 연결합니다. 내용을 재작성하거나 요약하지 않았습니다.","publishedAt":"2026-10-20T17:48:27.000Z","modifiedAt":"2026-10-20T19:25:36.000Z","checkedAt":"2026-10-20T19:25:36.253Z","language":"ko","kind":"link","sourceLabel":"AI 공식","profile":null,"via":null,"formats":{"json":"https://api.tumn.com/news/215e7dca-1e23-47cb-81ef-5ea5f2bee04b.json","markdown":"https://api.tumn.com/news/215e7dca-1e23-47cb-81ef-5ea5f2bee04b.md"}}