@[email protected] to Microblog [email protected]English • 3 months agodeepseeklemmy.mlimagemessage-square266fedilinkarrow-up11.12K
arrow-up11.12Kimagedeepseeklemmy.ml@[email protected] to Microblog [email protected]English • 3 months agomessage-square266fedilink
minus-square@[email protected]linkfedilinkEnglish4•3 months agoTrue, but in this case I believe the also open sourced the training data and the training process.
minus-squareAlexlinkfedilinkEnglish5•3 months agoTheir paper outlines the training process but doesn’t supply the actual data or training code. There is a project on huggingface: https://huggingface.co/blog/open-r1 that is attempting a fully open recreation based on what is public.
True, but in this case I believe the also open sourced the training data and the training process.
Their paper outlines the training process but doesn’t supply the actual data or training code. There is a project on huggingface: https://huggingface.co/blog/open-r1 that is attempting a fully open recreation based on what is public.