Open-R1: an open reproduction of DeepSeek-R1
huggingface.co
Open-R1: an open reproduction of DeepSeek-R1
1–10 of 246 posts
Re: Open-R1: an open reproduction of DeepSeek-R1
#2how is this open vs whatdeepseek did?
Re: Open-R1: an open reproduction of DeepSeek-R1
#3how is this open vs whatdeepseek did?
From that article:
> 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.
Re: Open-R1: an open reproduction of DeepSeek-R1
#4Exciting to see this being reproduced, loving the hyper-fast movement in open source!
This is exactly why it is not “US vs China”, the battle is between heavily-capitalized Silicon Valley companies versus open source.
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.
Re: Open-R1: an open reproduction of DeepSeek-R1
#5how is this open vs whatdeepseek did?
deepseek claims they are "open source" but they are not. They are open weight.
IMO a truly "open" AI model should have 3 components publicly available: the weights, the code, and the dataset.
Without all 3 the model is not reproducible. Could make the argument that the code and data are sufficient though.
Re: Open-R1: an open reproduction of DeepSeek-R1
#6What are some other domains outside of Math and Coding that would be suitable for RL with automated verification?
Re: Open-R1: an open reproduction of DeepSeek-R1
#7Exciting to see this being reproduced, loving the hyper-fast movement in open source! This is exactly why it is not “US vs China”, the battle is between heavily-capitalized Silicon Valley companies versus open source. 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 exploi…
[dead]
Re: Open-R1: an open reproduction of DeepSeek-R1
#8how is this open vs whatdeepseek did?
deepseek claims they are "open source" but they are not. They are open weight. IMO a truly "open" AI model should have 3 components publicly available: the weights, the code, and the dataset. Without all 3 the model is not reproducible. Could make the argument that the code and data are sufficient though.
Only meaningful if code+data deterministically reproduce the weights.
At that point, the weights are just the cached output. Which has value since it's costly to produce from code+data.
Re: Open-R1: an open reproduction of DeepSeek-R1
#9Exciting to see this being reproduced, loving the hyper-fast movement in open source! This is exactly why it is not “US vs China”, the battle is between heavily-capitalized Silicon Valley companies versus open source. 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 exploi…
Oh yes, I am firmly on Team China here because US companies got too greedy. Meta is an exception here though and they also propelled AI development massively.
DeepSeek is awesome. Any AI task yet implemented in our business can be run from my local PC with just the smaller models. And my PC is fairly crappy to begin with.
OpenAI looks quite silly with their "we have to close everything".
Re: Open-R1: an open reproduction of DeepSeek-R1
#10Is this what the Web was like in the beginning? Something exciting and fascinating every week?