Long context GPT-OSS fine-tuning | Hacker News

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

		Long context GPT-OSS fine-tuning (unsloth.ai)
		4 points by danielhanchen 3 months ago \| hide \| past \| favorite \| 1 comment

danielhanchen 3 months ago [–]

Hey HN! Just sharing some work we did to make gpt-oss finetuning use O(N) and not O(N^2) VRAM via Flex Attention + some bug fixes :)

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