TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

How Deepseek R1 Was Trained

31 pointsby amrrs4 months ago

2 comments

mfi4 months ago
Deepseek R1 paper that the blogpost is written around: <a href="https:&#x2F;&#x2F;arxiv.org&#x2F;pdf&#x2F;2501.12948" rel="nofollow">https:&#x2F;&#x2F;arxiv.org&#x2F;pdf&#x2F;2501.12948</a>
okdood644 months ago
Can someone dumb to me, a generalist engineer who has a very surface level knowledge of how training LLMs work: what people were doing before and what GRPO is doing different?
评论 #42849790 未加载