Re:Open-R1: an open reproduction of DeepSeek-R1
by boznz on Tuesday January 28, 2025 @03:27AM
(#42850082)
Genuine question, but how do you replicate the effort exactly without $5M in compute? and can you test that the published weights etc are actually those in the model?
Am I missing something?
Re:Open-R1: an open reproduction of DeepSeek-R1
by simonw on Tuesday January 28, 2025 @03:41AM
(#42850166)
The $5.5m in compute wasn't for R1, it was for DeepSeek v3.
The R1 trick looks like it may be a whole lot cheaper than that. R1 apparently used just 800,000 samples - I don't fully understand the processing needed on top of those samples but I get the impression it's a whole lot less compute than the $5.5m used to train v3.
> The release of DeepSeek-R1 is an amazing boon for the community, but they didn’t release everything—although the model weights are open, the datasets and code used to train the model are not.
> The goal of Open-R1 is to build these last missing pieces so that the whole research and industry community can build similar or better models using these recipes and datasets.