Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Open-R1: an open reproduction of DeepSeek-R1

huggingface.co

Post reply on HN
Print view View original

241–246 of 246 posts

Re: Open-R1: an open reproduction of DeepSeek-R1

#241

Post by manmal »

raxxor wrote: post #158
manmal wrote: post #18

Earlier quoted context omitted.

Can you elaborate which models you are using? I‘m running an R1 distilled Qwen coder with 32B Q4, and while it’s giving useful answers, it‘s quite slow on my M1 Max. Slow enough that I keep reaching for cloud models.

Not on my machine currently, I use the 14b Q4 model I think, which delivers very good answers. I run a 4060 with 16gb memory and performance is quite good. I used the largest model that was recommended with this amount of VRAM, I think it was the 14b one. I do have some applications that process images, text and pdf files and I use smaller models for extracting embeddings. I think my system wouldn't be able to handle…

Interesting, I didn’t like the quality of the output of the 14B models. Could be the quantization though, apparently some are a bit broken.

Re: Open-R1: an open reproduction of DeepSeek-R1

#242

Post by davidron »

master-lincoln wrote: post #140
icetank wrote: post #118

Earlier quoted context omitted.

I can tell you from personal experience that chatgpt is a game changer in universities and schools. Close to 100% of students use chatgpt to study. I know in our university pretty much everyone that attends exams uses chatgpt to study. Chatgpt is arguably more valuable then Wikipedia and Google for studies.

It will be interesting to see if this benefits the learning of students or just helps them pass more easily without retaining any knowledge...

This is EXACTLY what I remember people saying about Cell Phones and PDAs when they were popular in the 90s (people can't remember phone numbers any more), Google when it was first unleashed (people won't know how to use card catalogs and libraries any more), and then again about Wikipedia when it became popular. What actually happened was that behavior changed and people became more efficient with these better tools.

Re: Open-R1: an open reproduction of DeepSeek-R1

#243

Post by maximus-decimus »

ChrisMarshallNY wrote: post #191
icetank wrote: post #118

Earlier quoted context omitted.

I can tell you from personal experience that chatgpt is a game changer in universities and schools. Close to 100% of students use chatgpt to study. I know in our university pretty much everyone that attends exams uses chatgpt to study. Chatgpt is arguably more valuable then Wikipedia and Google for studies.

There was a posting, some time ago, about someone complaining that their young, primary-school-age sister was using ChatGPT to an absurd degree. I'm not sure that's a bad thing. She'll probably be one of the Thought Leaders, of Generation AI. I think that ML will have a really big impact on almost everyone, in every developed (and maybe developing, as well) nation. We need to keep in mind that ML is still very much i…

It's like when we were kids and teachers said "you won't always have a calculator in your pocket". In 30 years, we might all have an AI model in a brain chip, who knows.

Re: Open-R1: an open reproduction of DeepSeek-R1

#244

Post by brisray »

bsaul wrote: post #77
ipnon wrote: post #10

Is this what the Web was like in the beginning? Something exciting and fascinating every week?

the web was fascinating every second. You could click on a link without having ANY idea what you would land on. The overall quality was very poor, but it was thrilling. A bit like indie cinema.

It was inevitable the web would be commercialized but there's plenty of people still creating their own personal websites - they're just a bit harder to find now.

There are people around trying to make these sites a bit more findable by creating specialized search engines. I have put the ones I know of at https://brisray.com/web/altsearch.htm

Re: Open-R1: an open reproduction of DeepSeek-R1

#245

Post by brisray »

philsnow wrote: post #134
bsaul wrote: post #77

Earlier quoted context omitted.

the web was fascinating every second. You could click on a link without having ANY idea what you would land on. The overall quality was very poor, but it was thrilling. A bit like indie cinema.

I miss webrings [0], and especially the 'random' link that would take you to a random site within a given webring. [0] it feels weird to have to link to this but there's probably somebody who's never heard of them: https://en.wikipedia.org/wiki/Webring

Webrings are making a little bit of a comeback. I've listed all the ones I know of on https://brisray.com/web/webring-list.htm

Re: Open-R1: an open reproduction of DeepSeek-R1

#246

Post by JetSpiegel »

whamlastxmas wrote: post #207
mojuba wrote: post #172

Earlier quoted context omitted.

> Chatgpt is arguably more valuable then Wikipedia and Google for studies. But ChatGPT is just a glorified Wikipedia/Google. For the consumers it's an incremental thing (although from the engineering perspective it may seem to be a breakthrough).

Go try to learn a college level mathematics concept from Wikipedia, then try to learn it from ChatGPT. The wiki article may as well be written in a foreign language

Sure, a glorified Google, it will link to 3Blue1Brown and its ilk, not AI slop.
Post reply on HN