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.

Open-R1: an open reproduction of DeepSeek-R1

394 pointsby jonbaer4 months ago

18 comments

LZ_Khan4 months ago
Note: This is not an actual model but rather an announcement of an effort to reproduce the R1 model.
评论 #42851093 未加载
评论 #42851197 未加载
ipnon4 months ago
Is this what the Web was like in the beginning? Something exciting and fascinating every week?
评论 #42850531 未加载
评论 #42851622 未加载
评论 #42850622 未加载
评论 #42849974 未加载
评论 #42850362 未加载
评论 #42850255 未加载
评论 #42850065 未加载
评论 #42850579 未加载
评论 #42851498 未加载
评论 #42852395 未加载
评论 #42850171 未加载
评论 #42849883 未加载
评论 #42850014 未加载
评论 #42850768 未加载
评论 #42852004 未加载
评论 #42850059 未加载
评论 #42850809 未加载
nutanc4 months ago
How can we help. Can crowd sourcing help? Is there any list of tasks that we want a crowd to do? The reason I am asking is because we have done a couple of crowdsourcing efforts and collected story data in Telugu(Chandamama Kathalu) and ASR speech data using college going students. Since we have access to the students, we can mobilize them and get this going. We will also be doing an internship program for 100,000 students in Telangana as part of Viswam[1] in April. Can include some work as part of this effort.<p>[1] <a href="https:&#x2F;&#x2F;viswam.ai&#x2F;" rel="nofollow">https:&#x2F;&#x2F;viswam.ai&#x2F;</a>
评论 #42851443 未加载
评论 #42851751 未加载
breadwinner4 months ago
From the article: <i>they didn’t release everything—although the model weights are open, the datasets and code used to train the model are not.</i><p>Is that true about Meta Llama as well? Specifically, the code used to train the model is not open? (I know no one releases datasets). If so the label &quot;open source&quot; is inappropriate. &quot;Open weights&quot; would be more appropriate.
sunshine-o4 months ago
Now that things are really getting wild in the LLM space and people are just running anything that come it seems I did a quick search on the thead model of hosting you own LLM.<p>I didn&#x27;t find much, starting with llama.ccp which is just reminding you to sandbox and isolate everything if running untrusted models.<p>I feel we are back in the Windows 95 &#x2F; early Internet era when people would just run anything without caring about security.
评论 #42851066 未加载
评论 #42852742 未加载
评论 #42851065 未加载
评论 #42851613 未加载
fblp4 months ago
Given DeepSeek&#x27;s open philosophy I wonder what their response is to simply being asked for access to the code and data that this project intends to recreate?
评论 #42850134 未加载
评论 #42850187 未加载
评论 #42850049 未加载
drakenot4 months ago
What are some other domains outside of Math and Coding that would be suitable for RL with automated verification?
评论 #42849881 未加载
评论 #42850093 未加载
评论 #42850267 未加载
评论 #42850682 未加载
评论 #42849918 未加载
评论 #42850995 未加载
评论 #42851030 未加载
zoobab4 months ago
For &quot;open source&quot;, we will wait that Debian ships them to have the guarantee it&#x27;s actually &quot;open&quot; and with &quot;sources&quot;. Right now it&#x27;s a mystery how they produce their binaries.
评论 #42851895 未加载
DeflectedFlux4 months ago
About the training data, cant the datasets from the Tulu3 Model by the Allen Institute be used? They claim that they have used a fully open source training dataset.
评论 #42851913 未加载
htrp4 months ago
The hf team tweeted they&#x27;d be doing this over the weekend. I guess now it&#x27;s an official project with headcount
freddealmeida4 months ago
how is this open vs whatdeepseek did?
评论 #42849710 未加载
评论 #42849783 未加载
cadamsdotcom4 months ago
Exciting to see this being reproduced, loving the hyper-fast movement in open source!<p>This is exactly why it is not “US vs China”, the battle is between heavily-capitalized Silicon Valley companies versus open source.<p>Every believer in this tech owes DeepSeek some gratitude, but even they stand on shoulders of giants in the form of everyone else who pushed the frontier forward and chose to publish, rather than exploit, what they learned.
评论 #42849859 未加载
评论 #42849907 未加载
评论 #42850163 未加载
评论 #42850099 未加载
评论 #42849842 未加载
评论 #42849948 未加载
评论 #42850261 未加载
vinni24 months ago
I wonder how long it takes to reproduce it and would having access to latest GPUs speed it up?
amelius4 months ago
Are there any other groups trying this?
Babawomba4 months ago
super cool to see an open initiative like this—love the idea of replicating DeepSeek-R1 in a transparent way.<p>I do like the idea of making these reasoning techniques accessible to everyone. If they really manage to replicate the results of DeepSeek-R1, especially on a smaller budget, that’s a huge win for open-source AI.<p>I’m all for projects that push innovation and share the process with others, even if it’s messy.<p>But yeah—lots of hurdles. They might hit a wall because they don’t have DeepSeek’s original datasets.
fl4tul44 months ago
Is OpenAI open as of yesterday?
readthenotes14 months ago
Stopped reading when it said DeepSeek brokevtge stock market
vinni24 months ago
Where is the evaluation numbers? without it you can’t call it reproduction.
评论 #42850674 未加载