About model weights and training data

[THINK2TRY]

Thanks for the great work! The results are really amazing. Will you open-source the model weights and the data to train the policy and reward model ?

[BeyonderXX]

Not everyone has sufficient GPU resources or time to verify the results.
Thanks!

[dimy93]

I would also love to have the weights. We have a project that can really benefit from this model, however doing the training by ourselves might be too computationally heavy for us. Also there is no guarantees that we will be able to achieve the same results

[Swaraj-1925]

I don't know about the model weights, but the README mentions that math problems are sourced from NuminaMath and MetaMath