> It's not actually a 600B+ model. It's a mixture of experts. Is this described ... | Hacker News

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

		ur-whale on Jan 23, 2025 \| parent \| context \| favorite \| on: DeepSeek and the Effects of GPU Export Controls > It's not actually a 600B+ model. It's a mixture of experts. Is this described in the paper or was this inferred from the model itself ? Just curious, especially if the latter.

lopuhin on Jan 23, 2025 [–]

It's a 600B+ mixture of experts and yes it's described in the paper, GitHub, etc.

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